[2023-03-09 02:53:18,146][613581] Saving configuration to /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/config.json... [2023-03-09 02:53:18,162][613581] Rollout worker 0 uses device cpu [2023-03-09 02:53:18,162][613581] Rollout worker 1 uses device cpu [2023-03-09 02:53:18,162][613581] Rollout worker 2 uses device cpu [2023-03-09 02:53:18,163][613581] Rollout worker 3 uses device cpu [2023-03-09 02:53:18,163][613581] Rollout worker 4 uses device cpu [2023-03-09 02:53:18,163][613581] Rollout worker 5 uses device cpu [2023-03-09 02:53:18,163][613581] Rollout worker 6 uses device cpu [2023-03-09 02:53:18,163][613581] Rollout worker 7 uses device cpu [2023-03-09 02:53:18,163][613581] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 [2023-03-09 02:53:18,175][613581] InferenceWorker_p0-w0: min num requests: 2 [2023-03-09 02:53:18,194][613581] Starting all processes... [2023-03-09 02:53:18,195][613581] Starting process learner_proc0 [2023-03-09 02:53:18,244][613581] Starting all processes... [2023-03-09 02:53:18,305][613581] Starting process inference_proc0-0 [2023-03-09 02:53:18,315][613581] Starting process rollout_proc0 [2023-03-09 02:53:18,316][613581] Starting process rollout_proc1 [2023-03-09 02:53:18,316][613581] Starting process rollout_proc2 [2023-03-09 02:53:18,317][613581] Starting process rollout_proc3 [2023-03-09 02:53:18,317][613581] Starting process rollout_proc4 [2023-03-09 02:53:18,317][613581] Starting process rollout_proc5 [2023-03-09 02:53:18,317][613581] Starting process rollout_proc6 [2023-03-09 02:53:18,317][613581] Starting process rollout_proc7 [2023-03-09 02:53:19,804][613841] Starting seed is not provided [2023-03-09 02:53:19,804][613841] Initializing actor-critic model on device cpu [2023-03-09 02:53:19,805][613841] RunningMeanStd input shape: (39,) [2023-03-09 02:53:19,805][613841] RunningMeanStd input shape: (1,) [2023-03-09 02:53:19,872][613841] Created Actor Critic model with architecture: [2023-03-09 02:53:19,872][613841] 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) ) ) [2023-03-09 02:53:19,969][613886] Worker 0 uses CPU cores [0, 1, 2, 3] [2023-03-09 02:53:20,031][613922] Worker 5 uses CPU cores [20, 21, 22, 23] [2023-03-09 02:53:20,115][613887] Worker 1 uses CPU cores [4, 5, 6, 7] [2023-03-09 02:53:20,229][613841] Using optimizer [2023-03-09 02:53:20,230][613841] No checkpoints found [2023-03-09 02:53:20,230][613841] Did not load from checkpoint, starting from scratch! [2023-03-09 02:53:20,230][613841] Initialized policy 0 weights for model version 0 [2023-03-09 02:53:20,231][613841] LearnerWorker_p0 finished initialization! [2023-03-09 02:53:20,232][613885] RunningMeanStd input shape: (39,) [2023-03-09 02:53:20,233][613885] RunningMeanStd input shape: (1,) [2023-03-09 02:53:20,329][613581] Inference worker 0-0 is ready! [2023-03-09 02:53:20,330][613581] All inference workers are ready! Signal rollout workers to start! [2023-03-09 02:53:20,410][613986] Worker 7 uses CPU cores [28, 29, 30, 31] [2023-03-09 02:53:20,445][613921] Worker 4 uses CPU cores [16, 17, 18, 19] [2023-03-09 02:53:20,534][613889] Worker 3 uses CPU cores [12, 13, 14, 15] [2023-03-09 02:53:20,569][613954] Worker 6 uses CPU cores [24, 25, 26, 27] [2023-03-09 02:53:20,718][613888] Worker 2 uses CPU cores [8, 9, 10, 11] [2023-03-09 02:53:20,829][613581] 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) [2023-03-09 02:53:24,398][613887] Decorrelating experience for 0 frames... [2023-03-09 02:53:24,398][613922] Decorrelating experience for 0 frames... [2023-03-09 02:53:24,399][613886] Decorrelating experience for 0 frames... [2023-03-09 02:53:24,412][613887] Decorrelating experience for 64 frames... [2023-03-09 02:53:24,412][613922] Decorrelating experience for 64 frames... [2023-03-09 02:53:24,412][613886] Decorrelating experience for 64 frames... [2023-03-09 02:53:24,449][613887] Decorrelating experience for 128 frames... [2023-03-09 02:53:24,449][613922] Decorrelating experience for 128 frames... [2023-03-09 02:53:24,450][613886] Decorrelating experience for 128 frames... [2023-03-09 02:53:24,510][613887] Decorrelating experience for 192 frames... [2023-03-09 02:53:24,510][613922] Decorrelating experience for 192 frames... [2023-03-09 02:53:24,511][613886] Decorrelating experience for 192 frames... [2023-03-09 02:53:24,554][613921] Decorrelating experience for 0 frames... [2023-03-09 02:53:24,554][613986] Decorrelating experience for 0 frames... [2023-03-09 02:53:24,567][613921] Decorrelating experience for 64 frames... [2023-03-09 02:53:24,568][613986] Decorrelating experience for 64 frames... [2023-03-09 02:53:24,606][613986] Decorrelating experience for 128 frames... [2023-03-09 02:53:24,606][613921] Decorrelating experience for 128 frames... [2023-03-09 02:53:24,667][613986] Decorrelating experience for 192 frames... [2023-03-09 02:53:24,668][613921] Decorrelating experience for 192 frames... [2023-03-09 02:53:24,681][613889] Decorrelating experience for 0 frames... [2023-03-09 02:53:24,694][613889] Decorrelating experience for 64 frames... [2023-03-09 02:53:24,731][613889] Decorrelating experience for 128 frames... [2023-03-09 02:53:24,742][613954] Decorrelating experience for 0 frames... [2023-03-09 02:53:24,756][613954] Decorrelating experience for 64 frames... [2023-03-09 02:53:24,791][613889] Decorrelating experience for 192 frames... [2023-03-09 02:53:24,793][613954] Decorrelating experience for 128 frames... [2023-03-09 02:53:24,852][613954] Decorrelating experience for 192 frames... [2023-03-09 02:53:25,829][613581] 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) [2023-03-09 02:53:25,904][613888] Decorrelating experience for 0 frames... [2023-03-09 02:53:25,925][613888] Decorrelating experience for 64 frames... [2023-03-09 02:53:25,986][613888] Decorrelating experience for 128 frames... [2023-03-09 02:53:26,067][613888] Decorrelating experience for 192 frames... [2023-03-09 02:53:28,510][613886] Decorrelating experience for 256 frames... [2023-03-09 02:53:28,515][613887] Decorrelating experience for 256 frames... [2023-03-09 02:53:28,546][613922] Decorrelating experience for 256 frames... [2023-03-09 02:53:28,618][613886] Decorrelating experience for 320 frames... [2023-03-09 02:53:28,652][613922] Decorrelating experience for 320 frames... [2023-03-09 02:53:28,655][613887] Decorrelating experience for 320 frames... [2023-03-09 02:53:28,669][613921] Decorrelating experience for 256 frames... [2023-03-09 02:53:28,693][613986] Decorrelating experience for 256 frames... [2023-03-09 02:53:28,748][613886] Decorrelating experience for 384 frames... [2023-03-09 02:53:28,779][613921] Decorrelating experience for 320 frames... [2023-03-09 02:53:28,783][613922] Decorrelating experience for 384 frames... [2023-03-09 02:53:28,786][613887] Decorrelating experience for 384 frames... [2023-03-09 02:53:28,801][613986] Decorrelating experience for 320 frames... [2023-03-09 02:53:28,813][613889] Decorrelating experience for 256 frames... [2023-03-09 02:53:28,898][613886] Decorrelating experience for 448 frames... [2023-03-09 02:53:28,908][613921] Decorrelating experience for 384 frames... [2023-03-09 02:53:28,918][613889] Decorrelating experience for 320 frames... [2023-03-09 02:53:28,933][613986] Decorrelating experience for 384 frames... [2023-03-09 02:53:28,938][613922] Decorrelating experience for 448 frames... [2023-03-09 02:53:28,941][613887] Decorrelating experience for 448 frames... [2023-03-09 02:53:29,046][613889] Decorrelating experience for 384 frames... [2023-03-09 02:53:29,058][613921] Decorrelating experience for 448 frames... [2023-03-09 02:53:29,083][613986] Decorrelating experience for 448 frames... [2023-03-09 02:53:29,169][613954] Decorrelating experience for 256 frames... [2023-03-09 02:53:29,198][613889] Decorrelating experience for 448 frames... [2023-03-09 02:53:29,279][613954] Decorrelating experience for 320 frames... [2023-03-09 02:53:29,406][613954] Decorrelating experience for 384 frames... [2023-03-09 02:53:29,556][613954] Decorrelating experience for 448 frames... [2023-03-09 02:53:30,147][613888] Decorrelating experience for 256 frames... [2023-03-09 02:53:30,276][613888] Decorrelating experience for 320 frames... [2023-03-09 02:53:30,403][613888] Decorrelating experience for 384 frames... [2023-03-09 02:53:30,559][613888] Decorrelating experience for 448 frames... [2023-03-09 02:53:30,829][613581] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 49.2. Samples: 492. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 02:53:30,829][613581] Avg episode reward: [(0, '1.798')] [2023-03-09 02:53:30,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000000_0.pth... [2023-03-09 02:53:35,131][613885] Updated weights for policy 0, policy_version 80 (0.0005) [2023-03-09 02:53:35,829][613581] Fps is (10 sec: 4505.6, 60 sec: 3003.7, 300 sec: 3003.7). Total num frames: 45056. Throughput: 0: 2912.5. Samples: 43688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:53:35,829][613581] Avg episode reward: [(0, '244.900')] [2023-03-09 02:53:38,171][613581] Heartbeat connected on Batcher_0 [2023-03-09 02:53:38,173][613581] Heartbeat connected on LearnerWorker_p0 [2023-03-09 02:53:38,177][613581] Heartbeat connected on InferenceWorker_p0-w0 [2023-03-09 02:53:38,181][613581] Heartbeat connected on RolloutWorker_w0 [2023-03-09 02:53:38,183][613581] Heartbeat connected on RolloutWorker_w1 [2023-03-09 02:53:38,186][613581] Heartbeat connected on RolloutWorker_w2 [2023-03-09 02:53:38,191][613581] Heartbeat connected on RolloutWorker_w4 [2023-03-09 02:53:38,194][613581] Heartbeat connected on RolloutWorker_w7 [2023-03-09 02:53:38,197][613581] Heartbeat connected on RolloutWorker_w6 [2023-03-09 02:53:38,200][613581] Heartbeat connected on RolloutWorker_w3 [2023-03-09 02:53:38,205][613581] Heartbeat connected on RolloutWorker_w5 [2023-03-09 02:53:39,226][613885] Updated weights for policy 0, policy_version 160 (0.0005) [2023-03-09 02:53:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 4915.2, 300 sec: 4915.2). Total num frames: 98304. Throughput: 0: 3669.6. Samples: 73392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:53:40,829][613581] Avg episode reward: [(0, '452.506')] [2023-03-09 02:53:43,029][613885] Updated weights for policy 0, policy_version 240 (0.0005) [2023-03-09 02:53:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 5898.2, 300 sec: 5898.2). Total num frames: 147456. Throughput: 0: 5422.9. Samples: 135572. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 02:53:45,829][613581] Avg episode reward: [(0, '1023.304')] [2023-03-09 02:53:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000288_147456.pth... [2023-03-09 02:53:45,834][613841] Saving new best policy, reward=1023.304! [2023-03-09 02:53:47,058][613885] Updated weights for policy 0, policy_version 320 (0.0004) [2023-03-09 02:53:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 6690.1, 300 sec: 6690.1). Total num frames: 200704. Throughput: 0: 6646.0. Samples: 199380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:53:50,829][613581] Avg episode reward: [(0, '1702.997')] [2023-03-09 02:53:50,830][613841] Saving new best policy, reward=1702.997! [2023-03-09 02:53:50,875][613885] Updated weights for policy 0, policy_version 400 (0.0004) [2023-03-09 02:53:54,968][613885] Updated weights for policy 0, policy_version 480 (0.0004) [2023-03-09 02:53:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 7255.8, 300 sec: 7255.8). Total num frames: 253952. Throughput: 0: 6562.6. Samples: 229692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:53:55,829][613581] Avg episode reward: [(0, '1792.517')] [2023-03-09 02:53:55,830][613841] Saving new best policy, reward=1792.517! [2023-03-09 02:53:58,769][613885] Updated weights for policy 0, policy_version 560 (0.0005) [2023-03-09 02:54:00,829][613581] Fps is (10 sec: 10649.5, 60 sec: 7680.0, 300 sec: 7680.0). Total num frames: 307200. Throughput: 0: 7311.4. Samples: 292456. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 02:54:00,829][613581] Avg episode reward: [(0, '1822.382')] [2023-03-09 02:54:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000600_307200.pth... [2023-03-09 02:54:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000000_0.pth [2023-03-09 02:54:00,836][613841] Saving new best policy, reward=1822.382! [2023-03-09 02:54:02,729][613885] Updated weights for policy 0, policy_version 640 (0.0005) [2023-03-09 02:54:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 8010.0, 300 sec: 8010.0). Total num frames: 360448. Throughput: 0: 7925.4. Samples: 356644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:54:05,829][613581] Avg episode reward: [(0, '1831.226')] [2023-03-09 02:54:05,830][613841] Saving new best policy, reward=1831.226! [2023-03-09 02:54:06,477][613885] Updated weights for policy 0, policy_version 720 (0.0005) [2023-03-09 02:54:10,446][613885] Updated weights for policy 0, policy_version 800 (0.0005) [2023-03-09 02:54:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 8273.9, 300 sec: 8273.9). Total num frames: 413696. Throughput: 0: 8644.5. Samples: 389004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:54:10,829][613581] Avg episode reward: [(0, '1845.120')] [2023-03-09 02:54:10,830][613841] Saving new best policy, reward=1845.120! [2023-03-09 02:54:14,162][613885] Updated weights for policy 0, policy_version 880 (0.0005) [2023-03-09 02:54:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 8489.9, 300 sec: 8489.9). Total num frames: 466944. Throughput: 0: 10052.6. Samples: 452860. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 02:54:15,829][613581] Avg episode reward: [(0, '1845.486')] [2023-03-09 02:54:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000912_466944.pth... [2023-03-09 02:54:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000288_147456.pth [2023-03-09 02:54:15,836][613841] Saving new best policy, reward=1845.486! [2023-03-09 02:54:17,955][613885] Updated weights for policy 0, policy_version 960 (0.0004) [2023-03-09 02:54:20,829][613581] Fps is (10 sec: 10240.1, 60 sec: 8601.6, 300 sec: 8601.6). Total num frames: 516096. Throughput: 0: 10494.8. Samples: 515956. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 02:54:20,829][613581] Avg episode reward: [(0, '1845.300')] [2023-03-09 02:54:21,971][613885] Updated weights for policy 0, policy_version 1040 (0.0005) [2023-03-09 02:54:25,736][613885] Updated weights for policy 0, policy_version 1120 (0.0005) [2023-03-09 02:54:25,829][613581] Fps is (10 sec: 10649.7, 60 sec: 9557.3, 300 sec: 8822.1). Total num frames: 573440. Throughput: 0: 10550.0. Samples: 548144. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 02:54:25,829][613581] Avg episode reward: [(0, '1847.095')] [2023-03-09 02:54:25,830][613841] Saving new best policy, reward=1847.095! [2023-03-09 02:54:29,702][613885] Updated weights for policy 0, policy_version 1200 (0.0005) [2023-03-09 02:54:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 8894.2). Total num frames: 622592. Throughput: 0: 10559.3. Samples: 610740. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 02:54:30,829][613581] Avg episode reward: [(0, '1834.174')] [2023-03-09 02:54:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001216_622592.pth... [2023-03-09 02:54:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000600_307200.pth [2023-03-09 02:54:33,731][613885] Updated weights for policy 0, policy_version 1280 (0.0006) [2023-03-09 02:54:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 9011.2). Total num frames: 675840. Throughput: 0: 10516.3. Samples: 672612. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 02:54:35,829][613581] Avg episode reward: [(0, '1852.115')] [2023-03-09 02:54:35,830][613841] Saving new best policy, reward=1852.115! [2023-03-09 02:54:37,775][613885] Updated weights for policy 0, policy_version 1360 (0.0005) [2023-03-09 02:54:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 9062.4). Total num frames: 724992. Throughput: 0: 10490.5. Samples: 701764. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 02:54:40,829][613581] Avg episode reward: [(0, '1844.132')] [2023-03-09 02:54:41,931][613885] Updated weights for policy 0, policy_version 1440 (0.0005) [2023-03-09 02:54:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10444.8, 300 sec: 9107.6). Total num frames: 774144. Throughput: 0: 10414.4. Samples: 761104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:54:45,829][613581] Avg episode reward: [(0, '1844.585')] [2023-03-09 02:54:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001512_774144.pth... [2023-03-09 02:54:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000912_466944.pth [2023-03-09 02:54:46,114][613885] Updated weights for policy 0, policy_version 1520 (0.0005) [2023-03-09 02:54:49,944][613885] Updated weights for policy 0, policy_version 1600 (0.0005) [2023-03-09 02:54:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 9193.2). Total num frames: 827392. Throughput: 0: 10371.5. Samples: 823360. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 02:54:50,829][613581] Avg episode reward: [(0, '1861.774')] [2023-03-09 02:54:50,830][613841] Saving new best policy, reward=1861.774! [2023-03-09 02:54:53,996][613885] Updated weights for policy 0, policy_version 1680 (0.0005) [2023-03-09 02:54:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 9269.9). Total num frames: 880640. Throughput: 0: 10355.9. Samples: 855020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:54:55,829][613581] Avg episode reward: [(0, '1882.877')] [2023-03-09 02:54:55,830][613841] Saving new best policy, reward=1882.877! [2023-03-09 02:54:57,691][613885] Updated weights for policy 0, policy_version 1760 (0.0005) [2023-03-09 02:55:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 9297.9). Total num frames: 929792. Throughput: 0: 10368.7. Samples: 919452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:55:00,829][613581] Avg episode reward: [(0, '1944.969')] [2023-03-09 02:55:00,857][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001824_933888.pth... [2023-03-09 02:55:00,859][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001216_622592.pth [2023-03-09 02:55:00,860][613841] Saving new best policy, reward=1944.969! [2023-03-09 02:55:01,721][613885] Updated weights for policy 0, policy_version 1840 (0.0005) [2023-03-09 02:55:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 9323.3). Total num frames: 978944. Throughput: 0: 10243.5. Samples: 976916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:55:05,829][613581] Avg episode reward: [(0, '1845.771')] [2023-03-09 02:55:06,051][613885] Updated weights for policy 0, policy_version 1920 (0.0005) [2023-03-09 02:55:10,222][613885] Updated weights for policy 0, policy_version 2000 (0.0005) [2023-03-09 02:55:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 9346.3). Total num frames: 1028096. Throughput: 0: 10182.7. Samples: 1006364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:55:10,829][613581] Avg episode reward: [(0, '1888.188')] [2023-03-09 02:55:14,304][613885] Updated weights for policy 0, policy_version 2080 (0.0004) [2023-03-09 02:55:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.7, 300 sec: 9367.4). Total num frames: 1077248. Throughput: 0: 10100.4. Samples: 1065256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:55:15,829][613581] Avg episode reward: [(0, '2357.620')] [2023-03-09 02:55:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002104_1077248.pth... [2023-03-09 02:55:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001512_774144.pth [2023-03-09 02:55:15,835][613841] Saving new best policy, reward=2357.620! [2023-03-09 02:55:18,562][613885] Updated weights for policy 0, policy_version 2160 (0.0004) [2023-03-09 02:55:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10171.7, 300 sec: 9386.7). Total num frames: 1126400. Throughput: 0: 10051.6. Samples: 1124936. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 02:55:20,830][613581] Avg episode reward: [(0, '2668.109')] [2023-03-09 02:55:20,830][613841] Saving new best policy, reward=2668.109! [2023-03-09 02:55:22,552][613885] Updated weights for policy 0, policy_version 2240 (0.0006) [2023-03-09 02:55:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10103.5, 300 sec: 9437.2). Total num frames: 1179648. Throughput: 0: 10072.8. Samples: 1155040. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 02:55:25,829][613581] Avg episode reward: [(0, '3488.282')] [2023-03-09 02:55:25,830][613841] Saving new best policy, reward=3488.282! [2023-03-09 02:55:26,705][613885] Updated weights for policy 0, policy_version 2320 (0.0005) [2023-03-09 02:55:30,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 9420.8). Total num frames: 1224704. Throughput: 0: 10043.9. Samples: 1213080. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 02:55:30,829][613581] Avg episode reward: [(0, '4032.378')] [2023-03-09 02:55:30,841][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002400_1228800.pth... [2023-03-09 02:55:30,842][613885] Updated weights for policy 0, policy_version 2400 (0.0005) [2023-03-09 02:55:30,843][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001824_933888.pth [2023-03-09 02:55:30,843][613841] Saving new best policy, reward=4032.378! [2023-03-09 02:55:35,200][613885] Updated weights for policy 0, policy_version 2480 (0.0005) [2023-03-09 02:55:35,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9966.9, 300 sec: 9436.0). Total num frames: 1273856. Throughput: 0: 9961.6. Samples: 1271632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:55:35,840][613581] Avg episode reward: [(0, '3819.151')] [2023-03-09 02:55:39,166][613885] Updated weights for policy 0, policy_version 2560 (0.0004) [2023-03-09 02:55:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 9479.3). Total num frames: 1327104. Throughput: 0: 9946.2. Samples: 1302600. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 02:55:40,840][613581] Avg episode reward: [(0, '4155.041')] [2023-03-09 02:55:40,841][613841] Saving new best policy, reward=4155.041! [2023-03-09 02:55:43,270][613885] Updated weights for policy 0, policy_version 2640 (0.0005) [2023-03-09 02:55:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10035.2, 300 sec: 9491.4). Total num frames: 1376256. Throughput: 0: 9836.9. Samples: 1362116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:55:45,840][613581] Avg episode reward: [(0, '4220.050')] [2023-03-09 02:55:45,844][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002688_1376256.pth... [2023-03-09 02:55:45,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002104_1077248.pth [2023-03-09 02:55:45,847][613841] Saving new best policy, reward=4220.050! [2023-03-09 02:55:47,562][613885] Updated weights for policy 0, policy_version 2720 (0.0005) [2023-03-09 02:55:50,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9898.7, 300 sec: 9475.4). Total num frames: 1421312. Throughput: 0: 9836.4. Samples: 1419552. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 02:55:50,829][613581] Avg episode reward: [(0, '4184.287')] [2023-03-09 02:55:51,834][613885] Updated weights for policy 0, policy_version 2800 (0.0004) [2023-03-09 02:55:55,829][613581] Fps is (10 sec: 9421.0, 60 sec: 9830.4, 300 sec: 9486.9). Total num frames: 1470464. Throughput: 0: 9803.3. Samples: 1447512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:55:55,829][613581] Avg episode reward: [(0, '3970.249')] [2023-03-09 02:55:55,932][613885] Updated weights for policy 0, policy_version 2880 (0.0004) [2023-03-09 02:55:59,863][613885] Updated weights for policy 0, policy_version 2960 (0.0005) [2023-03-09 02:56:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 9523.2). Total num frames: 1523712. Throughput: 0: 9912.7. Samples: 1511328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:56:00,829][613581] Avg episode reward: [(0, '3634.082')] [2023-03-09 02:56:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002976_1523712.pth... [2023-03-09 02:56:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002400_1228800.pth [2023-03-09 02:56:03,808][613885] Updated weights for policy 0, policy_version 3040 (0.0005) [2023-03-09 02:56:05,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 9532.5). Total num frames: 1572864. Throughput: 0: 9954.1. Samples: 1572872. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 02:56:05,829][613581] Avg episode reward: [(0, '4281.769')] [2023-03-09 02:56:05,845][613841] Saving new best policy, reward=4281.769! [2023-03-09 02:56:07,955][613885] Updated weights for policy 0, policy_version 3120 (0.0005) [2023-03-09 02:56:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 9966.9, 300 sec: 9565.4). Total num frames: 1626112. Throughput: 0: 9924.4. Samples: 1601640. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 02:56:10,829][613581] Avg episode reward: [(0, '4176.784')] [2023-03-09 02:56:11,868][613885] Updated weights for policy 0, policy_version 3200 (0.0005) [2023-03-09 02:56:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 9572.9). Total num frames: 1675264. Throughput: 0: 10004.7. Samples: 1663292. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 02:56:15,829][613581] Avg episode reward: [(0, '3798.473')] [2023-03-09 02:56:15,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003272_1675264.pth... [2023-03-09 02:56:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002688_1376256.pth [2023-03-09 02:56:15,958][613885] Updated weights for policy 0, policy_version 3280 (0.0005) [2023-03-09 02:56:20,280][613885] Updated weights for policy 0, policy_version 3360 (0.0006) [2023-03-09 02:56:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 9580.1). Total num frames: 1724416. Throughput: 0: 9985.5. Samples: 1720980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:56:20,829][613581] Avg episode reward: [(0, '3894.069')] [2023-03-09 02:56:24,249][613885] Updated weights for policy 0, policy_version 3440 (0.0005) [2023-03-09 02:56:25,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9898.7, 300 sec: 9586.9). Total num frames: 1773568. Throughput: 0: 10001.0. Samples: 1752644. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 02:56:25,829][613581] Avg episode reward: [(0, '4260.015')] [2023-03-09 02:56:28,478][613885] Updated weights for policy 0, policy_version 3520 (0.0004) [2023-03-09 02:56:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 9593.3). Total num frames: 1822720. Throughput: 0: 9966.0. Samples: 1810584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:56:30,829][613581] Avg episode reward: [(0, '4184.395')] [2023-03-09 02:56:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003560_1822720.pth... [2023-03-09 02:56:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002976_1523712.pth [2023-03-09 02:56:32,720][613885] Updated weights for policy 0, policy_version 3600 (0.0005) [2023-03-09 02:56:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 9599.3). Total num frames: 1871872. Throughput: 0: 10014.0. Samples: 1870180. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 02:56:35,829][613581] Avg episode reward: [(0, '4282.292')] [2023-03-09 02:56:35,830][613841] Saving new best policy, reward=4282.292! [2023-03-09 02:56:36,789][613885] Updated weights for policy 0, policy_version 3680 (0.0005) [2023-03-09 02:56:40,775][613885] Updated weights for policy 0, policy_version 3760 (0.0005) [2023-03-09 02:56:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 9625.6). Total num frames: 1925120. Throughput: 0: 10065.0. Samples: 1900440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:56:40,829][613581] Avg episode reward: [(0, '4301.133')] [2023-03-09 02:56:40,830][613841] Saving new best policy, reward=4301.133! [2023-03-09 02:56:44,666][613885] Updated weights for policy 0, policy_version 3840 (0.0005) [2023-03-09 02:56:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10035.2, 300 sec: 9650.6). Total num frames: 1978368. Throughput: 0: 10033.0. Samples: 1962812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:56:45,829][613581] Avg episode reward: [(0, '4440.336')] [2023-03-09 02:56:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003864_1978368.pth... [2023-03-09 02:56:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003272_1675264.pth [2023-03-09 02:56:45,835][613841] Saving new best policy, reward=4440.336! [2023-03-09 02:56:48,645][613885] Updated weights for policy 0, policy_version 3920 (0.0004) [2023-03-09 02:56:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 9654.9). Total num frames: 2027520. Throughput: 0: 10012.4. Samples: 2023432. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 02:56:50,829][613581] Avg episode reward: [(0, '4437.069')] [2023-03-09 02:56:52,953][613885] Updated weights for policy 0, policy_version 4000 (0.0004) [2023-03-09 02:56:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 9658.9). Total num frames: 2076672. Throughput: 0: 10011.5. Samples: 2052160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:56:55,829][613581] Avg episode reward: [(0, '4388.168')] [2023-03-09 02:56:56,914][613885] Updated weights for policy 0, policy_version 4080 (0.0005) [2023-03-09 02:57:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 9662.8). Total num frames: 2125824. Throughput: 0: 10007.0. Samples: 2113608. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 02:57:00,829][613581] Avg episode reward: [(0, '4210.790')] [2023-03-09 02:57:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004152_2125824.pth... [2023-03-09 02:57:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003560_1822720.pth [2023-03-09 02:57:01,052][613885] Updated weights for policy 0, policy_version 4160 (0.0004) [2023-03-09 02:57:05,045][613885] Updated weights for policy 0, policy_version 4240 (0.0004) [2023-03-09 02:57:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 9666.6). Total num frames: 2174976. Throughput: 0: 10084.6. Samples: 2174788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:57:05,829][613581] Avg episode reward: [(0, '3813.025')] [2023-03-09 02:57:09,143][613885] Updated weights for policy 0, policy_version 4320 (0.0005) [2023-03-09 02:57:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9966.9, 300 sec: 9670.1). Total num frames: 2224128. Throughput: 0: 10021.6. Samples: 2203616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:57:10,829][613581] Avg episode reward: [(0, '3482.005')] [2023-03-09 02:57:13,405][613885] Updated weights for policy 0, policy_version 4400 (0.0004) [2023-03-09 02:57:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 9673.5). Total num frames: 2273280. Throughput: 0: 10063.5. Samples: 2263440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:57:15,829][613581] Avg episode reward: [(0, '3822.379')] [2023-03-09 02:57:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004440_2273280.pth... [2023-03-09 02:57:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003864_1978368.pth [2023-03-09 02:57:17,497][613885] Updated weights for policy 0, policy_version 4480 (0.0005) [2023-03-09 02:57:20,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10035.2, 300 sec: 9693.9). Total num frames: 2326528. Throughput: 0: 10054.1. Samples: 2322616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:57:20,840][613581] Avg episode reward: [(0, '3814.011')] [2023-03-09 02:57:21,505][613885] Updated weights for policy 0, policy_version 4560 (0.0005) [2023-03-09 02:57:25,814][613885] Updated weights for policy 0, policy_version 4640 (0.0004) [2023-03-09 02:57:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10035.2, 300 sec: 9696.7). Total num frames: 2375680. Throughput: 0: 10022.3. Samples: 2351444. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 02:57:25,829][613581] Avg episode reward: [(0, '4167.152')] [2023-03-09 02:57:29,668][613885] Updated weights for policy 0, policy_version 4720 (0.0005) [2023-03-09 02:57:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10103.5, 300 sec: 9715.7). Total num frames: 2428928. Throughput: 0: 10009.3. Samples: 2413232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:57:30,829][613581] Avg episode reward: [(0, '4257.248')] [2023-03-09 02:57:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004744_2428928.pth... [2023-03-09 02:57:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004152_2125824.pth [2023-03-09 02:57:33,625][613885] Updated weights for policy 0, policy_version 4800 (0.0004) [2023-03-09 02:57:35,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10103.5, 300 sec: 9718.0). Total num frames: 2478080. Throughput: 0: 10038.2. Samples: 2475152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:57:35,829][613581] Avg episode reward: [(0, '4460.275')] [2023-03-09 02:57:35,830][613841] Saving new best policy, reward=4460.275! [2023-03-09 02:57:37,692][613885] Updated weights for policy 0, policy_version 4880 (0.0005) [2023-03-09 02:57:40,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10103.5, 300 sec: 9735.9). Total num frames: 2531328. Throughput: 0: 10091.2. Samples: 2506264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:57:40,830][613581] Avg episode reward: [(0, '4390.766')] [2023-03-09 02:57:41,547][613885] Updated weights for policy 0, policy_version 4960 (0.0005) [2023-03-09 02:57:45,505][613885] Updated weights for policy 0, policy_version 5040 (0.0005) [2023-03-09 02:57:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 9737.7). Total num frames: 2580480. Throughput: 0: 10144.2. Samples: 2570096. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 02:57:45,829][613581] Avg episode reward: [(0, '4372.717')] [2023-03-09 02:57:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005040_2580480.pth... [2023-03-09 02:57:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004440_2273280.pth [2023-03-09 02:57:49,570][613885] Updated weights for policy 0, policy_version 5120 (0.0006) [2023-03-09 02:57:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10103.5, 300 sec: 9754.5). Total num frames: 2633728. Throughput: 0: 10107.8. Samples: 2629640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:57:50,829][613581] Avg episode reward: [(0, '4314.561')] [2023-03-09 02:57:53,701][613885] Updated weights for policy 0, policy_version 5200 (0.0005) [2023-03-09 02:57:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 9755.9). Total num frames: 2682880. Throughput: 0: 10129.5. Samples: 2659444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:57:55,829][613581] Avg episode reward: [(0, '4155.903')] [2023-03-09 02:57:57,773][613885] Updated weights for policy 0, policy_version 5280 (0.0004) [2023-03-09 02:58:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 9757.3). Total num frames: 2732032. Throughput: 0: 10141.5. Samples: 2719808. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 02:58:00,829][613581] Avg episode reward: [(0, '4032.268')] [2023-03-09 02:58:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005336_2732032.pth... [2023-03-09 02:58:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004744_2428928.pth [2023-03-09 02:58:01,727][613885] Updated weights for policy 0, policy_version 5360 (0.0005) [2023-03-09 02:58:05,741][613885] Updated weights for policy 0, policy_version 5440 (0.0005) [2023-03-09 02:58:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 9772.9). Total num frames: 2785280. Throughput: 0: 10192.0. Samples: 2781256. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 02:58:05,829][613581] Avg episode reward: [(0, '4136.975')] [2023-03-09 02:58:09,632][613885] Updated weights for policy 0, policy_version 5520 (0.0005) [2023-03-09 02:58:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 9773.9). Total num frames: 2834432. Throughput: 0: 10277.2. Samples: 2813920. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 02:58:10,829][613581] Avg episode reward: [(0, '3910.750')] [2023-03-09 02:58:13,721][613885] Updated weights for policy 0, policy_version 5600 (0.0005) [2023-03-09 02:58:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 9788.7). Total num frames: 2887680. Throughput: 0: 10237.4. Samples: 2873916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:58:15,829][613581] Avg episode reward: [(0, '4248.393')] [2023-03-09 02:58:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005640_2887680.pth... [2023-03-09 02:58:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005040_2580480.pth [2023-03-09 02:58:17,788][613885] Updated weights for policy 0, policy_version 5680 (0.0005) [2023-03-09 02:58:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 9955.4). Total num frames: 2936832. Throughput: 0: 10257.8. Samples: 2936752. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 02:58:20,829][613581] Avg episode reward: [(0, '4420.844')] [2023-03-09 02:58:21,580][613885] Updated weights for policy 0, policy_version 5760 (0.0005) [2023-03-09 02:58:25,580][613885] Updated weights for policy 0, policy_version 5840 (0.0004) [2023-03-09 02:58:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10135.9). Total num frames: 2990080. Throughput: 0: 10215.9. Samples: 2965980. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 02:58:25,829][613581] Avg episode reward: [(0, '4487.037')] [2023-03-09 02:58:25,830][613841] Saving new best policy, reward=4487.037! [2023-03-09 02:58:29,797][613885] Updated weights for policy 0, policy_version 5920 (0.0005) [2023-03-09 02:58:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 10149.7). Total num frames: 3039232. Throughput: 0: 10153.8. Samples: 3027016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:58:30,829][613581] Avg episode reward: [(0, '4436.555')] [2023-03-09 02:58:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005936_3039232.pth... [2023-03-09 02:58:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005336_2732032.pth [2023-03-09 02:58:33,795][613885] Updated weights for policy 0, policy_version 6000 (0.0005) [2023-03-09 02:58:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10149.7). Total num frames: 3092480. Throughput: 0: 10194.5. Samples: 3088392. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 02:58:35,829][613581] Avg episode reward: [(0, '4402.705')] [2023-03-09 02:58:37,690][613885] Updated weights for policy 0, policy_version 6080 (0.0005) [2023-03-09 02:58:40,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10149.7). Total num frames: 3141632. Throughput: 0: 10233.2. Samples: 3119940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:58:40,829][613581] Avg episode reward: [(0, '4180.390')] [2023-03-09 02:58:41,708][613885] Updated weights for policy 0, policy_version 6160 (0.0005) [2023-03-09 02:58:45,682][613885] Updated weights for policy 0, policy_version 6240 (0.0005) [2023-03-09 02:58:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10149.7). Total num frames: 3194880. Throughput: 0: 10281.6. Samples: 3182480. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 02:58:45,829][613581] Avg episode reward: [(0, '4315.294')] [2023-03-09 02:58:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006240_3194880.pth... [2023-03-09 02:58:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005640_2887680.pth [2023-03-09 02:58:49,584][613885] Updated weights for policy 0, policy_version 6320 (0.0005) [2023-03-09 02:58:50,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 10149.7). Total num frames: 3248128. Throughput: 0: 10283.9. Samples: 3244032. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 02:58:50,829][613581] Avg episode reward: [(0, '4198.011')] [2023-03-09 02:58:53,391][613885] Updated weights for policy 0, policy_version 6400 (0.0004) [2023-03-09 02:58:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10149.7). Total num frames: 3301376. Throughput: 0: 10286.4. Samples: 3276808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:58:55,829][613581] Avg episode reward: [(0, '4274.720')] [2023-03-09 02:58:57,017][613885] Updated weights for policy 0, policy_version 6480 (0.0005) [2023-03-09 02:59:00,801][613885] Updated weights for policy 0, policy_version 6560 (0.0005) [2023-03-09 02:59:00,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10444.8, 300 sec: 10163.6). Total num frames: 3358720. Throughput: 0: 10421.5. Samples: 3342884. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:59:00,829][613581] Avg episode reward: [(0, '4445.224')] [2023-03-09 02:59:00,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006560_3358720.pth... [2023-03-09 02:59:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005936_3039232.pth [2023-03-09 02:59:04,693][613885] Updated weights for policy 0, policy_version 6640 (0.0004) [2023-03-09 02:59:05,829][613581] Fps is (10 sec: 11059.3, 60 sec: 10444.8, 300 sec: 10163.6). Total num frames: 3411968. Throughput: 0: 10467.2. Samples: 3407776. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 02:59:05,829][613581] Avg episode reward: [(0, '4266.905')] [2023-03-09 02:59:08,457][613885] Updated weights for policy 0, policy_version 6720 (0.0005) [2023-03-09 02:59:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10163.6). Total num frames: 3465216. Throughput: 0: 10545.0. Samples: 3440504. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 02:59:10,829][613581] Avg episode reward: [(0, '4231.800')] [2023-03-09 02:59:12,120][613885] Updated weights for policy 0, policy_version 6800 (0.0005) [2023-03-09 02:59:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10513.1, 300 sec: 10177.5). Total num frames: 3518464. Throughput: 0: 10640.4. Samples: 3505836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:59:15,829][613581] Avg episode reward: [(0, '3988.723')] [2023-03-09 02:59:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006872_3518464.pth... [2023-03-09 02:59:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006240_3194880.pth [2023-03-09 02:59:16,047][613885] Updated weights for policy 0, policy_version 6880 (0.0005) [2023-03-09 02:59:19,928][613885] Updated weights for policy 0, policy_version 6960 (0.0004) [2023-03-09 02:59:20,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10163.6). Total num frames: 3571712. Throughput: 0: 10649.6. Samples: 3567624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:59:20,830][613581] Avg episode reward: [(0, '3950.270')] [2023-03-09 02:59:23,975][613885] Updated weights for policy 0, policy_version 7040 (0.0005) [2023-03-09 02:59:25,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10513.1, 300 sec: 10163.6). Total num frames: 3620864. Throughput: 0: 10628.6. Samples: 3598228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:59:25,829][613581] Avg episode reward: [(0, '4227.541')] [2023-03-09 02:59:27,741][613885] Updated weights for policy 0, policy_version 7120 (0.0004) [2023-03-09 02:59:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10177.5). Total num frames: 3678208. Throughput: 0: 10680.3. Samples: 3663092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:59:30,830][613581] Avg episode reward: [(0, '4357.305')] [2023-03-09 02:59:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007184_3678208.pth... [2023-03-09 02:59:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006560_3358720.pth [2023-03-09 02:59:31,661][613885] Updated weights for policy 0, policy_version 7200 (0.0004) [2023-03-09 02:59:35,625][613885] Updated weights for policy 0, policy_version 7280 (0.0004) [2023-03-09 02:59:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.4, 300 sec: 10177.5). Total num frames: 3727360. Throughput: 0: 10665.5. Samples: 3723980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:59:35,829][613581] Avg episode reward: [(0, '4350.747')] [2023-03-09 02:59:39,741][613885] Updated weights for policy 0, policy_version 7360 (0.0005) [2023-03-09 02:59:40,829][613581] Fps is (10 sec: 9830.6, 60 sec: 10581.3, 300 sec: 10177.5). Total num frames: 3776512. Throughput: 0: 10648.0. Samples: 3755968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:59:40,829][613581] Avg episode reward: [(0, '4377.857')] [2023-03-09 02:59:43,592][613885] Updated weights for policy 0, policy_version 7440 (0.0005) [2023-03-09 02:59:45,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10649.6, 300 sec: 10191.4). Total num frames: 3833856. Throughput: 0: 10546.4. Samples: 3817472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:59:45,829][613581] Avg episode reward: [(0, '4427.688')] [2023-03-09 02:59:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007488_3833856.pth... [2023-03-09 02:59:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006872_3518464.pth [2023-03-09 02:59:47,121][613885] Updated weights for policy 0, policy_version 7520 (0.0004) [2023-03-09 02:59:50,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10649.6, 300 sec: 10191.4). Total num frames: 3887104. Throughput: 0: 10630.7. Samples: 3886160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 02:59:50,829][613581] Avg episode reward: [(0, '4064.364')] [2023-03-09 02:59:50,855][613885] Updated weights for policy 0, policy_version 7600 (0.0004) [2023-03-09 02:59:54,720][613885] Updated weights for policy 0, policy_version 7680 (0.0004) [2023-03-09 02:59:55,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10205.3). Total num frames: 3940352. Throughput: 0: 10637.7. Samples: 3919200. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 02:59:55,829][613581] Avg episode reward: [(0, '4189.276')] [2023-03-09 02:59:58,586][613885] Updated weights for policy 0, policy_version 7760 (0.0004) [2023-03-09 03:00:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10219.2). Total num frames: 3993600. Throughput: 0: 10562.6. Samples: 3981152. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:00:00,829][613581] Avg episode reward: [(0, '4298.103')] [2023-03-09 03:00:00,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007800_3993600.pth... [2023-03-09 03:00:00,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007184_3678208.pth [2023-03-09 03:00:02,538][613885] Updated weights for policy 0, policy_version 7840 (0.0004) [2023-03-09 03:00:05,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10233.1). Total num frames: 4046848. Throughput: 0: 10591.5. Samples: 4044240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:00:05,829][613581] Avg episode reward: [(0, '4388.587')] [2023-03-09 03:00:06,335][613885] Updated weights for policy 0, policy_version 7920 (0.0005) [2023-03-09 03:00:10,142][613885] Updated weights for policy 0, policy_version 8000 (0.0004) [2023-03-09 03:00:10,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10246.9). Total num frames: 4100096. Throughput: 0: 10628.8. Samples: 4076524. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:00:10,829][613581] Avg episode reward: [(0, '4224.488')] [2023-03-09 03:00:14,142][613885] Updated weights for policy 0, policy_version 8080 (0.0005) [2023-03-09 03:00:15,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.4, 300 sec: 10260.8). Total num frames: 4153344. Throughput: 0: 10595.7. Samples: 4139896. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:00:15,829][613581] Avg episode reward: [(0, '4466.727')] [2023-03-09 03:00:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008112_4153344.pth... [2023-03-09 03:00:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007488_3833856.pth [2023-03-09 03:00:17,864][613885] Updated weights for policy 0, policy_version 8160 (0.0005) [2023-03-09 03:00:20,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.4, 300 sec: 10260.8). Total num frames: 4206592. Throughput: 0: 10635.3. Samples: 4202568. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:00:20,829][613581] Avg episode reward: [(0, '4370.771')] [2023-03-09 03:00:21,931][613885] Updated weights for policy 0, policy_version 8240 (0.0005) [2023-03-09 03:00:25,759][613885] Updated weights for policy 0, policy_version 8320 (0.0004) [2023-03-09 03:00:25,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10649.6, 300 sec: 10288.6). Total num frames: 4259840. Throughput: 0: 10648.1. Samples: 4235132. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:00:25,829][613581] Avg episode reward: [(0, '4263.620')] [2023-03-09 03:00:29,659][613885] Updated weights for policy 0, policy_version 8400 (0.0005) [2023-03-09 03:00:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10513.1, 300 sec: 10288.6). Total num frames: 4308992. Throughput: 0: 10678.9. Samples: 4298020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:00:30,829][613581] Avg episode reward: [(0, '4187.812')] [2023-03-09 03:00:30,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008416_4308992.pth... [2023-03-09 03:00:30,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007800_3993600.pth [2023-03-09 03:00:33,713][613885] Updated weights for policy 0, policy_version 8480 (0.0004) [2023-03-09 03:00:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10581.3, 300 sec: 10288.6). Total num frames: 4362240. Throughput: 0: 10509.8. Samples: 4359100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:00:35,829][613581] Avg episode reward: [(0, '4335.922')] [2023-03-09 03:00:37,701][613885] Updated weights for policy 0, policy_version 8560 (0.0004) [2023-03-09 03:00:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10581.3, 300 sec: 10288.6). Total num frames: 4411392. Throughput: 0: 10469.4. Samples: 4390324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:00:40,829][613581] Avg episode reward: [(0, '4328.843')] [2023-03-09 03:00:41,643][613885] Updated weights for policy 0, policy_version 8640 (0.0004) [2023-03-09 03:00:45,426][613885] Updated weights for policy 0, policy_version 8720 (0.0005) [2023-03-09 03:00:45,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10316.4). Total num frames: 4464640. Throughput: 0: 10471.6. Samples: 4452372. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:00:45,829][613581] Avg episode reward: [(0, '4312.921')] [2023-03-09 03:00:45,849][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008728_4468736.pth... [2023-03-09 03:00:45,851][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008112_4153344.pth [2023-03-09 03:00:49,456][613885] Updated weights for policy 0, policy_version 8800 (0.0005) [2023-03-09 03:00:50,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10513.1, 300 sec: 10330.2). Total num frames: 4517888. Throughput: 0: 10440.3. Samples: 4514052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:00:50,829][613581] Avg episode reward: [(0, '4301.959')] [2023-03-09 03:00:53,499][613885] Updated weights for policy 0, policy_version 8880 (0.0005) [2023-03-09 03:00:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10316.4). Total num frames: 4567040. Throughput: 0: 10441.7. Samples: 4546400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:00:55,829][613581] Avg episode reward: [(0, '4374.069')] [2023-03-09 03:00:57,584][613885] Updated weights for policy 0, policy_version 8960 (0.0005) [2023-03-09 03:01:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10330.3). Total num frames: 4620288. Throughput: 0: 10383.8. Samples: 4607168. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:01:00,829][613581] Avg episode reward: [(0, '4412.317')] [2023-03-09 03:01:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009024_4620288.pth... [2023-03-09 03:01:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008416_4308992.pth [2023-03-09 03:01:01,451][613885] Updated weights for policy 0, policy_version 9040 (0.0005) [2023-03-09 03:01:05,435][613885] Updated weights for policy 0, policy_version 9120 (0.0005) [2023-03-09 03:01:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10330.2). Total num frames: 4673536. Throughput: 0: 10374.3. Samples: 4669412. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:01:05,829][613581] Avg episode reward: [(0, '4410.136')] [2023-03-09 03:01:09,327][613885] Updated weights for policy 0, policy_version 9200 (0.0005) [2023-03-09 03:01:10,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10330.2). Total num frames: 4722688. Throughput: 0: 10326.4. Samples: 4699820. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:01:10,829][613581] Avg episode reward: [(0, '4154.152')] [2023-03-09 03:01:13,474][613885] Updated weights for policy 0, policy_version 9280 (0.0005) [2023-03-09 03:01:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 10330.3). Total num frames: 4771840. Throughput: 0: 10261.8. Samples: 4759800. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:01:15,829][613581] Avg episode reward: [(0, '2784.754')] [2023-03-09 03:01:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009320_4771840.pth... [2023-03-09 03:01:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008728_4468736.pth [2023-03-09 03:01:17,556][613885] Updated weights for policy 0, policy_version 9360 (0.0004) [2023-03-09 03:01:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.2, 300 sec: 10344.1). Total num frames: 4825088. Throughput: 0: 10264.5. Samples: 4821000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:01:20,829][613581] Avg episode reward: [(0, '3669.750')] [2023-03-09 03:01:21,556][613885] Updated weights for policy 0, policy_version 9440 (0.0005) [2023-03-09 03:01:25,389][613885] Updated weights for policy 0, policy_version 9520 (0.0006) [2023-03-09 03:01:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10358.0). Total num frames: 4878336. Throughput: 0: 10259.8. Samples: 4852016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:01:25,829][613581] Avg episode reward: [(0, '4122.534')] [2023-03-09 03:01:29,340][613885] Updated weights for policy 0, policy_version 9600 (0.0005) [2023-03-09 03:01:30,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10358.0). Total num frames: 4927488. Throughput: 0: 10286.7. Samples: 4915272. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:01:30,829][613581] Avg episode reward: [(0, '4343.848')] [2023-03-09 03:01:30,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009624_4927488.pth... [2023-03-09 03:01:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009024_4620288.pth [2023-03-09 03:01:33,678][613885] Updated weights for policy 0, policy_version 9680 (0.0005) [2023-03-09 03:01:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10344.1). Total num frames: 4976640. Throughput: 0: 10233.0. Samples: 4974536. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:01:35,829][613581] Avg episode reward: [(0, '4152.977')] [2023-03-09 03:01:37,591][613885] Updated weights for policy 0, policy_version 9760 (0.0004) [2023-03-09 03:01:40,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10344.1). Total num frames: 5029888. Throughput: 0: 10209.1. Samples: 5005812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:01:40,829][613581] Avg episode reward: [(0, '4319.020')] [2023-03-09 03:01:41,368][613885] Updated weights for policy 0, policy_version 9840 (0.0004) [2023-03-09 03:01:45,420][613885] Updated weights for policy 0, policy_version 9920 (0.0005) [2023-03-09 03:01:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10358.0). Total num frames: 5083136. Throughput: 0: 10274.7. Samples: 5069528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:01:45,829][613581] Avg episode reward: [(0, '4317.669')] [2023-03-09 03:01:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009928_5083136.pth... [2023-03-09 03:01:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009320_4771840.pth [2023-03-09 03:01:49,389][613885] Updated weights for policy 0, policy_version 10000 (0.0005) [2023-03-09 03:01:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10358.0). Total num frames: 5132288. Throughput: 0: 10239.9. Samples: 5130208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:01:50,829][613581] Avg episode reward: [(0, '4229.357')] [2023-03-09 03:01:53,417][613885] Updated weights for policy 0, policy_version 10080 (0.0005) [2023-03-09 03:01:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 5185536. Throughput: 0: 10247.3. Samples: 5160948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:01:55,829][613581] Avg episode reward: [(0, '4319.175')] [2023-03-09 03:01:57,111][613885] Updated weights for policy 0, policy_version 10160 (0.0005) [2023-03-09 03:02:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.2, 300 sec: 10385.8). Total num frames: 5238784. Throughput: 0: 10349.5. Samples: 5225528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:02:00,829][613581] Avg episode reward: [(0, '4333.248')] [2023-03-09 03:02:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010232_5238784.pth... [2023-03-09 03:02:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009624_4927488.pth [2023-03-09 03:02:01,108][613885] Updated weights for policy 0, policy_version 10240 (0.0005) [2023-03-09 03:02:05,079][613885] Updated weights for policy 0, policy_version 10320 (0.0004) [2023-03-09 03:02:05,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10308.3, 300 sec: 10399.7). Total num frames: 5292032. Throughput: 0: 10373.4. Samples: 5287804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:02:05,829][613581] Avg episode reward: [(0, '4308.664')] [2023-03-09 03:02:08,788][613885] Updated weights for policy 0, policy_version 10400 (0.0005) [2023-03-09 03:02:10,829][613581] Fps is (10 sec: 10649.8, 60 sec: 10376.6, 300 sec: 10413.6). Total num frames: 5345280. Throughput: 0: 10414.2. Samples: 5320652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:02:10,829][613581] Avg episode reward: [(0, '4301.194')] [2023-03-09 03:02:12,613][613885] Updated weights for policy 0, policy_version 10480 (0.0005) [2023-03-09 03:02:15,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10413.6). Total num frames: 5398528. Throughput: 0: 10465.0. Samples: 5386196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:02:15,829][613581] Avg episode reward: [(0, '4305.056')] [2023-03-09 03:02:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010544_5398528.pth... [2023-03-09 03:02:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009928_5083136.pth [2023-03-09 03:02:16,242][613885] Updated weights for policy 0, policy_version 10560 (0.0005) [2023-03-09 03:02:20,359][613885] Updated weights for policy 0, policy_version 10640 (0.0005) [2023-03-09 03:02:20,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10427.4). Total num frames: 5451776. Throughput: 0: 10515.7. Samples: 5447744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:02:20,829][613581] Avg episode reward: [(0, '4010.607')] [2023-03-09 03:02:24,229][613885] Updated weights for policy 0, policy_version 10720 (0.0005) [2023-03-09 03:02:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10427.4). Total num frames: 5505024. Throughput: 0: 10537.3. Samples: 5479988. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:02:25,829][613581] Avg episode reward: [(0, '3570.258')] [2023-03-09 03:02:27,888][613885] Updated weights for policy 0, policy_version 10800 (0.0005) [2023-03-09 03:02:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.0, 300 sec: 10441.3). Total num frames: 5558272. Throughput: 0: 10586.8. Samples: 5545936. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:02:30,829][613581] Avg episode reward: [(0, '4057.769')] [2023-03-09 03:02:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010856_5558272.pth... [2023-03-09 03:02:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010232_5238784.pth [2023-03-09 03:02:31,824][613885] Updated weights for policy 0, policy_version 10880 (0.0006) [2023-03-09 03:02:35,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10513.1, 300 sec: 10427.4). Total num frames: 5607424. Throughput: 0: 10575.5. Samples: 5606104. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:02:35,829][613581] Avg episode reward: [(0, '3979.248')] [2023-03-09 03:02:35,950][613885] Updated weights for policy 0, policy_version 10960 (0.0005) [2023-03-09 03:02:39,872][613885] Updated weights for policy 0, policy_version 11040 (0.0005) [2023-03-09 03:02:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10441.3). Total num frames: 5660672. Throughput: 0: 10593.1. Samples: 5637636. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:02:40,829][613581] Avg episode reward: [(0, '4199.813')] [2023-03-09 03:02:43,751][613885] Updated weights for policy 0, policy_version 11120 (0.0005) [2023-03-09 03:02:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10441.3). Total num frames: 5713920. Throughput: 0: 10560.6. Samples: 5700756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:02:45,829][613581] Avg episode reward: [(0, '4188.264')] [2023-03-09 03:02:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011160_5713920.pth... [2023-03-09 03:02:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010544_5398528.pth [2023-03-09 03:02:47,364][613885] Updated weights for policy 0, policy_version 11200 (0.0005) [2023-03-09 03:02:50,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.3, 300 sec: 10455.2). Total num frames: 5767168. Throughput: 0: 10568.3. Samples: 5763376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:02:50,829][613581] Avg episode reward: [(0, '4198.953')] [2023-03-09 03:02:51,456][613885] Updated weights for policy 0, policy_version 11280 (0.0005) [2023-03-09 03:02:55,274][613885] Updated weights for policy 0, policy_version 11360 (0.0005) [2023-03-09 03:02:55,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.3, 300 sec: 10469.1). Total num frames: 5820416. Throughput: 0: 10562.6. Samples: 5795968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:02:55,829][613581] Avg episode reward: [(0, '4091.882')] [2023-03-09 03:02:59,051][613885] Updated weights for policy 0, policy_version 11440 (0.0005) [2023-03-09 03:03:00,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10469.1). Total num frames: 5873664. Throughput: 0: 10559.8. Samples: 5861388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:03:00,829][613581] Avg episode reward: [(0, '4146.272')] [2023-03-09 03:03:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011472_5873664.pth... [2023-03-09 03:03:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010856_5558272.pth [2023-03-09 03:03:02,861][613885] Updated weights for policy 0, policy_version 11520 (0.0004) [2023-03-09 03:03:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10483.0). Total num frames: 5926912. Throughput: 0: 10560.5. Samples: 5922968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:03:05,829][613581] Avg episode reward: [(0, '4302.180')] [2023-03-09 03:03:06,870][613885] Updated weights for policy 0, policy_version 11600 (0.0004) [2023-03-09 03:03:10,619][613885] Updated weights for policy 0, policy_version 11680 (0.0004) [2023-03-09 03:03:10,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.3, 300 sec: 10483.0). Total num frames: 5980160. Throughput: 0: 10550.1. Samples: 5954744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:03:10,829][613581] Avg episode reward: [(0, '4290.705')] [2023-03-09 03:03:14,219][613885] Updated weights for policy 0, policy_version 11760 (0.0004) [2023-03-09 03:03:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10496.9). Total num frames: 6033408. Throughput: 0: 10601.0. Samples: 6022980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:03:15,830][613581] Avg episode reward: [(0, '4356.778')] [2023-03-09 03:03:15,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011784_6033408.pth... [2023-03-09 03:03:15,838][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011160_5713920.pth [2023-03-09 03:03:18,416][613885] Updated weights for policy 0, policy_version 11840 (0.0005) [2023-03-09 03:03:20,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10496.9). Total num frames: 6086656. Throughput: 0: 10604.4. Samples: 6083300. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:03:20,829][613581] Avg episode reward: [(0, '4334.223')] [2023-03-09 03:03:22,193][613885] Updated weights for policy 0, policy_version 11920 (0.0005) [2023-03-09 03:03:25,829][613581] Fps is (10 sec: 10649.8, 60 sec: 10581.3, 300 sec: 10510.8). Total num frames: 6139904. Throughput: 0: 10631.5. Samples: 6116052. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:03:25,829][613581] Avg episode reward: [(0, '4348.276')] [2023-03-09 03:03:25,895][613885] Updated weights for policy 0, policy_version 12000 (0.0005) [2023-03-09 03:03:29,725][613885] Updated weights for policy 0, policy_version 12080 (0.0005) [2023-03-09 03:03:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10510.8). Total num frames: 6193152. Throughput: 0: 10670.5. Samples: 6180928. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:03:30,829][613581] Avg episode reward: [(0, '4320.711')] [2023-03-09 03:03:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012096_6193152.pth... [2023-03-09 03:03:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011472_5873664.pth [2023-03-09 03:03:33,595][613885] Updated weights for policy 0, policy_version 12160 (0.0005) [2023-03-09 03:03:35,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10649.6, 300 sec: 10524.6). Total num frames: 6246400. Throughput: 0: 10730.6. Samples: 6246252. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:03:35,829][613581] Avg episode reward: [(0, '4276.558')] [2023-03-09 03:03:37,484][613885] Updated weights for policy 0, policy_version 12240 (0.0004) [2023-03-09 03:03:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10524.6). Total num frames: 6299648. Throughput: 0: 10689.9. Samples: 6277012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:03:40,829][613581] Avg episode reward: [(0, '4262.345')] [2023-03-09 03:03:41,274][613885] Updated weights for policy 0, policy_version 12320 (0.0004) [2023-03-09 03:03:45,076][613885] Updated weights for policy 0, policy_version 12400 (0.0004) [2023-03-09 03:03:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10524.6). Total num frames: 6352896. Throughput: 0: 10650.9. Samples: 6340680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:03:45,829][613581] Avg episode reward: [(0, '4097.348')] [2023-03-09 03:03:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012408_6352896.pth... [2023-03-09 03:03:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011784_6033408.pth [2023-03-09 03:03:48,759][613885] Updated weights for policy 0, policy_version 12480 (0.0005) [2023-03-09 03:03:50,829][613581] Fps is (10 sec: 11059.3, 60 sec: 10717.9, 300 sec: 10538.5). Total num frames: 6410240. Throughput: 0: 10752.7. Samples: 6406836. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:03:50,840][613581] Avg episode reward: [(0, '4101.642')] [2023-03-09 03:03:52,583][613885] Updated weights for policy 0, policy_version 12560 (0.0004) [2023-03-09 03:03:55,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 10524.6). Total num frames: 6463488. Throughput: 0: 10760.7. Samples: 6438976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:03:55,840][613581] Avg episode reward: [(0, '4210.283')] [2023-03-09 03:03:56,424][613885] Updated weights for policy 0, policy_version 12640 (0.0004) [2023-03-09 03:04:00,400][613885] Updated weights for policy 0, policy_version 12720 (0.0005) [2023-03-09 03:04:00,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10717.9, 300 sec: 10524.6). Total num frames: 6516736. Throughput: 0: 10622.1. Samples: 6500972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:04:00,840][613581] Avg episode reward: [(0, '3969.308')] [2023-03-09 03:04:00,844][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012728_6516736.pth... [2023-03-09 03:04:00,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012096_6193152.pth [2023-03-09 03:04:04,283][613885] Updated weights for policy 0, policy_version 12800 (0.0005) [2023-03-09 03:04:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10649.6, 300 sec: 10510.8). Total num frames: 6565888. Throughput: 0: 10678.5. Samples: 6563832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:04:05,840][613581] Avg episode reward: [(0, '4047.911')] [2023-03-09 03:04:08,322][613885] Updated weights for policy 0, policy_version 12880 (0.0005) [2023-03-09 03:04:10,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10649.6, 300 sec: 10510.8). Total num frames: 6619136. Throughput: 0: 10636.8. Samples: 6594712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:04:10,840][613581] Avg episode reward: [(0, '4180.267')] [2023-03-09 03:04:12,225][613885] Updated weights for policy 0, policy_version 12960 (0.0004) [2023-03-09 03:04:15,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10510.8). Total num frames: 6672384. Throughput: 0: 10648.2. Samples: 6660096. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:04:15,840][613581] Avg episode reward: [(0, '4103.545')] [2023-03-09 03:04:15,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013032_6672384.pth... [2023-03-09 03:04:15,844][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012408_6352896.pth [2023-03-09 03:04:15,952][613885] Updated weights for policy 0, policy_version 13040 (0.0005) [2023-03-09 03:04:20,054][613885] Updated weights for policy 0, policy_version 13120 (0.0004) [2023-03-09 03:04:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10524.6). Total num frames: 6725632. Throughput: 0: 10563.3. Samples: 6721600. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:04:20,840][613581] Avg episode reward: [(0, '4126.787')] [2023-03-09 03:04:23,792][613885] Updated weights for policy 0, policy_version 13200 (0.0004) [2023-03-09 03:04:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10510.8). Total num frames: 6778880. Throughput: 0: 10606.8. Samples: 6754316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:04:25,829][613581] Avg episode reward: [(0, '4282.623')] [2023-03-09 03:04:27,728][613885] Updated weights for policy 0, policy_version 13280 (0.0005) [2023-03-09 03:04:30,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10581.4, 300 sec: 10510.8). Total num frames: 6828032. Throughput: 0: 10591.8. Samples: 6817308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:04:30,829][613581] Avg episode reward: [(0, '4141.118')] [2023-03-09 03:04:30,844][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013344_6832128.pth... [2023-03-09 03:04:30,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012728_6516736.pth [2023-03-09 03:04:31,708][613885] Updated weights for policy 0, policy_version 13360 (0.0004) [2023-03-09 03:04:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10513.1, 300 sec: 10510.8). Total num frames: 6877184. Throughput: 0: 10450.1. Samples: 6877092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:04:35,829][613581] Avg episode reward: [(0, '4294.882')] [2023-03-09 03:04:35,850][613885] Updated weights for policy 0, policy_version 13440 (0.0005) [2023-03-09 03:04:39,918][613885] Updated weights for policy 0, policy_version 13520 (0.0005) [2023-03-09 03:04:40,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10513.1, 300 sec: 10496.9). Total num frames: 6930432. Throughput: 0: 10394.6. Samples: 6906732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:04:40,829][613581] Avg episode reward: [(0, '4407.925')] [2023-03-09 03:04:43,541][613885] Updated weights for policy 0, policy_version 13600 (0.0005) [2023-03-09 03:04:45,829][613581] Fps is (10 sec: 11059.0, 60 sec: 10581.3, 300 sec: 10510.7). Total num frames: 6987776. Throughput: 0: 10482.8. Samples: 6972700. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:04:45,830][613581] Avg episode reward: [(0, '4249.889')] [2023-03-09 03:04:45,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013648_6987776.pth... [2023-03-09 03:04:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013032_6672384.pth [2023-03-09 03:04:47,489][613885] Updated weights for policy 0, policy_version 13680 (0.0005) [2023-03-09 03:04:50,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10483.0). Total num frames: 7032832. Throughput: 0: 10415.5. Samples: 7032532. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:04:50,829][613581] Avg episode reward: [(0, '4005.469')] [2023-03-09 03:04:51,850][613885] Updated weights for policy 0, policy_version 13760 (0.0005) [2023-03-09 03:04:55,700][613885] Updated weights for policy 0, policy_version 13840 (0.0005) [2023-03-09 03:04:55,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10376.5, 300 sec: 10483.0). Total num frames: 7086080. Throughput: 0: 10372.4. Samples: 7061468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:04:55,829][613581] Avg episode reward: [(0, '4375.790')] [2023-03-09 03:04:59,688][613885] Updated weights for policy 0, policy_version 13920 (0.0004) [2023-03-09 03:05:00,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10469.1). Total num frames: 7135232. Throughput: 0: 10293.0. Samples: 7123284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:05:00,829][613581] Avg episode reward: [(0, '4358.804')] [2023-03-09 03:05:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013936_7135232.pth... [2023-03-09 03:05:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013344_6832128.pth [2023-03-09 03:05:03,772][613885] Updated weights for policy 0, policy_version 14000 (0.0005) [2023-03-09 03:05:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 10455.2). Total num frames: 7184384. Throughput: 0: 10282.9. Samples: 7184332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:05:05,829][613581] Avg episode reward: [(0, '4318.570')] [2023-03-09 03:05:08,002][613885] Updated weights for policy 0, policy_version 14080 (0.0004) [2023-03-09 03:05:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10455.2). Total num frames: 7237632. Throughput: 0: 10193.1. Samples: 7213008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:05:10,829][613581] Avg episode reward: [(0, '4343.499')] [2023-03-09 03:05:11,933][613885] Updated weights for policy 0, policy_version 14160 (0.0005) [2023-03-09 03:05:15,829][613581] Fps is (10 sec: 10239.8, 60 sec: 10239.9, 300 sec: 10441.3). Total num frames: 7286784. Throughput: 0: 10172.6. Samples: 7275076. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:05:15,830][613581] Avg episode reward: [(0, '4309.723')] [2023-03-09 03:05:15,880][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014240_7290880.pth... [2023-03-09 03:05:15,881][613885] Updated weights for policy 0, policy_version 14240 (0.0005) [2023-03-09 03:05:15,882][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013648_6987776.pth [2023-03-09 03:05:20,161][613885] Updated weights for policy 0, policy_version 14320 (0.0004) [2023-03-09 03:05:20,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10171.8, 300 sec: 10427.4). Total num frames: 7335936. Throughput: 0: 10159.9. Samples: 7334288. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:05:20,829][613581] Avg episode reward: [(0, '4374.906')] [2023-03-09 03:05:24,152][613885] Updated weights for policy 0, policy_version 14400 (0.0005) [2023-03-09 03:05:25,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10171.7, 300 sec: 10441.3). Total num frames: 7389184. Throughput: 0: 10176.4. Samples: 7364672. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:05:25,829][613581] Avg episode reward: [(0, '4326.981')] [2023-03-09 03:05:28,087][613885] Updated weights for policy 0, policy_version 14480 (0.0005) [2023-03-09 03:05:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10240.0, 300 sec: 10441.3). Total num frames: 7442432. Throughput: 0: 10093.3. Samples: 7426900. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:05:30,829][613581] Avg episode reward: [(0, '4227.340')] [2023-03-09 03:05:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014536_7442432.pth... [2023-03-09 03:05:30,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013936_7135232.pth [2023-03-09 03:05:31,917][613885] Updated weights for policy 0, policy_version 14560 (0.0005) [2023-03-09 03:05:35,667][613885] Updated weights for policy 0, policy_version 14640 (0.0005) [2023-03-09 03:05:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10455.2). Total num frames: 7495680. Throughput: 0: 10237.7. Samples: 7493228. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:05:35,829][613581] Avg episode reward: [(0, '4335.693')] [2023-03-09 03:05:39,416][613885] Updated weights for policy 0, policy_version 14720 (0.0004) [2023-03-09 03:05:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10455.2). Total num frames: 7548928. Throughput: 0: 10302.9. Samples: 7525100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:05:40,829][613581] Avg episode reward: [(0, '4080.334')] [2023-03-09 03:05:43,346][613885] Updated weights for policy 0, policy_version 14800 (0.0005) [2023-03-09 03:05:45,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10240.0, 300 sec: 10455.2). Total num frames: 7602176. Throughput: 0: 10366.0. Samples: 7589756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:05:45,830][613581] Avg episode reward: [(0, '4325.283')] [2023-03-09 03:05:45,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014848_7602176.pth... [2023-03-09 03:05:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014240_7290880.pth [2023-03-09 03:05:47,130][613885] Updated weights for policy 0, policy_version 14880 (0.0005) [2023-03-09 03:05:50,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10469.1). Total num frames: 7655424. Throughput: 0: 10403.9. Samples: 7652508. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:05:50,829][613581] Avg episode reward: [(0, '4303.845')] [2023-03-09 03:05:51,049][613885] Updated weights for policy 0, policy_version 14960 (0.0004) [2023-03-09 03:05:54,742][613885] Updated weights for policy 0, policy_version 15040 (0.0004) [2023-03-09 03:05:55,829][613581] Fps is (10 sec: 10649.8, 60 sec: 10376.5, 300 sec: 10469.1). Total num frames: 7708672. Throughput: 0: 10513.3. Samples: 7686108. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:05:55,829][613581] Avg episode reward: [(0, '4143.469')] [2023-03-09 03:05:58,543][613885] Updated weights for policy 0, policy_version 15120 (0.0004) [2023-03-09 03:06:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10469.1). Total num frames: 7761920. Throughput: 0: 10557.0. Samples: 7750140. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:06:00,829][613581] Avg episode reward: [(0, '4041.379')] [2023-03-09 03:06:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015160_7761920.pth... [2023-03-09 03:06:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014536_7442432.pth [2023-03-09 03:06:02,644][613885] Updated weights for policy 0, policy_version 15200 (0.0004) [2023-03-09 03:06:05,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10444.8, 300 sec: 10469.1). Total num frames: 7811072. Throughput: 0: 10534.5. Samples: 7808340. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:06:05,829][613581] Avg episode reward: [(0, '4093.132')] [2023-03-09 03:06:06,773][613885] Updated weights for policy 0, policy_version 15280 (0.0004) [2023-03-09 03:06:10,813][613885] Updated weights for policy 0, policy_version 15360 (0.0005) [2023-03-09 03:06:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10483.0). Total num frames: 7864320. Throughput: 0: 10557.3. Samples: 7839752. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:06:10,830][613581] Avg episode reward: [(0, '3935.080')] [2023-03-09 03:06:14,571][613885] Updated weights for policy 0, policy_version 15440 (0.0005) [2023-03-09 03:06:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10513.1, 300 sec: 10483.0). Total num frames: 7917568. Throughput: 0: 10590.7. Samples: 7903484. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:06:15,829][613581] Avg episode reward: [(0, '3904.209')] [2023-03-09 03:06:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015464_7917568.pth... [2023-03-09 03:06:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014848_7602176.pth [2023-03-09 03:06:18,601][613885] Updated weights for policy 0, policy_version 15520 (0.0005) [2023-03-09 03:06:20,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10469.1). Total num frames: 7966720. Throughput: 0: 10442.6. Samples: 7963144. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:06:20,829][613581] Avg episode reward: [(0, '4167.000')] [2023-03-09 03:06:22,833][613885] Updated weights for policy 0, policy_version 15600 (0.0004) [2023-03-09 03:06:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10444.8, 300 sec: 10469.1). Total num frames: 8015872. Throughput: 0: 10380.0. Samples: 7992200. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:06:25,829][613581] Avg episode reward: [(0, '3882.140')] [2023-03-09 03:06:26,843][613885] Updated weights for policy 0, policy_version 15680 (0.0005) [2023-03-09 03:06:30,667][613885] Updated weights for policy 0, policy_version 15760 (0.0005) [2023-03-09 03:06:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10444.8, 300 sec: 10483.0). Total num frames: 8069120. Throughput: 0: 10347.9. Samples: 8055408. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:06:30,829][613581] Avg episode reward: [(0, '3985.243')] [2023-03-09 03:06:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015760_8069120.pth... [2023-03-09 03:06:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015160_7761920.pth [2023-03-09 03:06:34,631][613885] Updated weights for policy 0, policy_version 15840 (0.0004) [2023-03-09 03:06:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10469.1). Total num frames: 8118272. Throughput: 0: 10348.1. Samples: 8118172. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:06:35,829][613581] Avg episode reward: [(0, '4261.555')] [2023-03-09 03:06:38,545][613885] Updated weights for policy 0, policy_version 15920 (0.0005) [2023-03-09 03:06:40,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10444.8, 300 sec: 10483.0). Total num frames: 8175616. Throughput: 0: 10295.1. Samples: 8149388. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:06:40,829][613581] Avg episode reward: [(0, '3822.604')] [2023-03-09 03:06:42,117][613885] Updated weights for policy 0, policy_version 16000 (0.0005) [2023-03-09 03:06:45,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10444.8, 300 sec: 10496.9). Total num frames: 8228864. Throughput: 0: 10365.4. Samples: 8216584. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:06:45,829][613581] Avg episode reward: [(0, '3916.893')] [2023-03-09 03:06:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016072_8228864.pth... [2023-03-09 03:06:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015464_7917568.pth [2023-03-09 03:06:45,999][613885] Updated weights for policy 0, policy_version 16080 (0.0005) [2023-03-09 03:06:49,731][613885] Updated weights for policy 0, policy_version 16160 (0.0005) [2023-03-09 03:06:50,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10496.9). Total num frames: 8282112. Throughput: 0: 10492.7. Samples: 8280508. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:06:50,829][613581] Avg episode reward: [(0, '4155.241')] [2023-03-09 03:06:53,577][613885] Updated weights for policy 0, policy_version 16240 (0.0005) [2023-03-09 03:06:55,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10513.1, 300 sec: 10510.8). Total num frames: 8339456. Throughput: 0: 10506.0. Samples: 8312520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:06:55,829][613581] Avg episode reward: [(0, '4263.486')] [2023-03-09 03:06:57,359][613885] Updated weights for policy 0, policy_version 16320 (0.0004) [2023-03-09 03:07:00,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10496.9). Total num frames: 8388608. Throughput: 0: 10508.9. Samples: 8376384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:07:00,829][613581] Avg episode reward: [(0, '4293.510')] [2023-03-09 03:07:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016384_8388608.pth... [2023-03-09 03:07:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015760_8069120.pth [2023-03-09 03:07:01,326][613885] Updated weights for policy 0, policy_version 16400 (0.0004) [2023-03-09 03:07:05,149][613885] Updated weights for policy 0, policy_version 16480 (0.0004) [2023-03-09 03:07:05,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10496.9). Total num frames: 8441856. Throughput: 0: 10609.7. Samples: 8440580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:07:05,829][613581] Avg episode reward: [(0, '4369.871')] [2023-03-09 03:07:09,326][613885] Updated weights for policy 0, policy_version 16560 (0.0005) [2023-03-09 03:07:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10483.0). Total num frames: 8491008. Throughput: 0: 10592.6. Samples: 8468868. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:07:10,829][613581] Avg episode reward: [(0, '4371.458')] [2023-03-09 03:07:13,216][613885] Updated weights for policy 0, policy_version 16640 (0.0004) [2023-03-09 03:07:15,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10513.1, 300 sec: 10496.9). Total num frames: 8548352. Throughput: 0: 10596.8. Samples: 8532264. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:07:15,829][613581] Avg episode reward: [(0, '4432.550')] [2023-03-09 03:07:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016696_8548352.pth... [2023-03-09 03:07:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016072_8228864.pth [2023-03-09 03:07:16,911][613885] Updated weights for policy 0, policy_version 16720 (0.0005) [2023-03-09 03:07:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10483.0). Total num frames: 8597504. Throughput: 0: 10642.2. Samples: 8597068. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:07:20,829][613581] Avg episode reward: [(0, '4421.603')] [2023-03-09 03:07:20,879][613885] Updated weights for policy 0, policy_version 16800 (0.0005) [2023-03-09 03:07:24,362][613885] Updated weights for policy 0, policy_version 16880 (0.0005) [2023-03-09 03:07:25,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10496.9). Total num frames: 8654848. Throughput: 0: 10714.6. Samples: 8631544. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:07:25,829][613581] Avg episode reward: [(0, '4420.208')] [2023-03-09 03:07:27,841][613885] Updated weights for policy 0, policy_version 16960 (0.0005) [2023-03-09 03:07:30,829][613581] Fps is (10 sec: 11468.6, 60 sec: 10717.9, 300 sec: 10524.6). Total num frames: 8712192. Throughput: 0: 10740.7. Samples: 8699916. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:07:30,829][613581] Avg episode reward: [(0, '4381.678')] [2023-03-09 03:07:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017016_8712192.pth... [2023-03-09 03:07:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016384_8388608.pth [2023-03-09 03:07:31,661][613885] Updated weights for policy 0, policy_version 17040 (0.0004) [2023-03-09 03:07:35,709][613885] Updated weights for policy 0, policy_version 17120 (0.0004) [2023-03-09 03:07:35,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10786.1, 300 sec: 10524.6). Total num frames: 8765440. Throughput: 0: 10687.7. Samples: 8761456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:07:35,829][613581] Avg episode reward: [(0, '4329.033')] [2023-03-09 03:07:39,653][613885] Updated weights for policy 0, policy_version 17200 (0.0005) [2023-03-09 03:07:40,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10717.9, 300 sec: 10524.6). Total num frames: 8818688. Throughput: 0: 10700.5. Samples: 8794040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:07:40,829][613581] Avg episode reward: [(0, '4236.744')] [2023-03-09 03:07:43,608][613885] Updated weights for policy 0, policy_version 17280 (0.0005) [2023-03-09 03:07:45,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10649.6, 300 sec: 10510.8). Total num frames: 8867840. Throughput: 0: 10648.2. Samples: 8855552. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:07:45,829][613581] Avg episode reward: [(0, '4318.384')] [2023-03-09 03:07:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017320_8867840.pth... [2023-03-09 03:07:45,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016696_8548352.pth [2023-03-09 03:07:47,610][613885] Updated weights for policy 0, policy_version 17360 (0.0005) [2023-03-09 03:07:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10581.3, 300 sec: 10496.9). Total num frames: 8916992. Throughput: 0: 10533.3. Samples: 8914580. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:07:50,829][613581] Avg episode reward: [(0, '4355.426')] [2023-03-09 03:07:51,728][613885] Updated weights for policy 0, policy_version 17440 (0.0004) [2023-03-09 03:07:55,462][613885] Updated weights for policy 0, policy_version 17520 (0.0005) [2023-03-09 03:07:55,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10513.1, 300 sec: 10496.9). Total num frames: 8970240. Throughput: 0: 10596.9. Samples: 8945728. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:07:55,829][613581] Avg episode reward: [(0, '4284.460')] [2023-03-09 03:07:59,421][613885] Updated weights for policy 0, policy_version 17600 (0.0005) [2023-03-09 03:08:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10496.9). Total num frames: 9023488. Throughput: 0: 10641.6. Samples: 9011136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:08:00,829][613581] Avg episode reward: [(0, '4286.903')] [2023-03-09 03:08:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017624_9023488.pth... [2023-03-09 03:08:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017016_8712192.pth [2023-03-09 03:08:03,194][613885] Updated weights for policy 0, policy_version 17680 (0.0005) [2023-03-09 03:08:05,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10649.6, 300 sec: 10510.8). Total num frames: 9080832. Throughput: 0: 10679.2. Samples: 9077632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:08:05,829][613581] Avg episode reward: [(0, '4190.421')] [2023-03-09 03:08:06,783][613885] Updated weights for policy 0, policy_version 17760 (0.0005) [2023-03-09 03:08:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10496.9). Total num frames: 9129984. Throughput: 0: 10614.5. Samples: 9109196. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:08:10,829][613581] Avg episode reward: [(0, '4308.552')] [2023-03-09 03:08:10,919][613885] Updated weights for policy 0, policy_version 17840 (0.0004) [2023-03-09 03:08:14,696][613885] Updated weights for policy 0, policy_version 17920 (0.0004) [2023-03-09 03:08:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10581.4, 300 sec: 10496.9). Total num frames: 9183232. Throughput: 0: 10479.1. Samples: 9171476. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:08:15,829][613581] Avg episode reward: [(0, '4117.471')] [2023-03-09 03:08:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017944_9187328.pth... [2023-03-09 03:08:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017320_8867840.pth [2023-03-09 03:08:18,437][613885] Updated weights for policy 0, policy_version 18000 (0.0005) [2023-03-09 03:08:20,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 10510.7). Total num frames: 9240576. Throughput: 0: 10587.9. Samples: 9237912. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:08:20,829][613581] Avg episode reward: [(0, '4033.697')] [2023-03-09 03:08:22,210][613885] Updated weights for policy 0, policy_version 18080 (0.0004) [2023-03-09 03:08:25,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10649.6, 300 sec: 10510.8). Total num frames: 9293824. Throughput: 0: 10612.4. Samples: 9271600. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:08:25,829][613581] Avg episode reward: [(0, '4195.604')] [2023-03-09 03:08:25,922][613885] Updated weights for policy 0, policy_version 18160 (0.0005) [2023-03-09 03:08:29,727][613885] Updated weights for policy 0, policy_version 18240 (0.0005) [2023-03-09 03:08:30,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10649.6, 300 sec: 10524.6). Total num frames: 9351168. Throughput: 0: 10663.3. Samples: 9335400. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:08:30,829][613581] Avg episode reward: [(0, '4181.220')] [2023-03-09 03:08:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018264_9351168.pth... [2023-03-09 03:08:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017624_9023488.pth [2023-03-09 03:08:33,404][613885] Updated weights for policy 0, policy_version 18320 (0.0004) [2023-03-09 03:08:35,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10649.6, 300 sec: 10524.6). Total num frames: 9404416. Throughput: 0: 10832.9. Samples: 9402060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:08:35,840][613581] Avg episode reward: [(0, '4120.508')] [2023-03-09 03:08:37,119][613885] Updated weights for policy 0, policy_version 18400 (0.0004) [2023-03-09 03:08:40,705][613885] Updated weights for policy 0, policy_version 18480 (0.0005) [2023-03-09 03:08:40,829][613581] Fps is (10 sec: 11059.3, 60 sec: 10717.9, 300 sec: 10538.5). Total num frames: 9461760. Throughput: 0: 10864.1. Samples: 9434612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:08:40,829][613581] Avg episode reward: [(0, '4058.685')] [2023-03-09 03:08:44,554][613885] Updated weights for policy 0, policy_version 18560 (0.0005) [2023-03-09 03:08:45,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 10524.6). Total num frames: 9515008. Throughput: 0: 10894.8. Samples: 9501404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:08:45,829][613581] Avg episode reward: [(0, '3956.055')] [2023-03-09 03:08:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018584_9515008.pth... [2023-03-09 03:08:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017944_9187328.pth [2023-03-09 03:08:48,493][613885] Updated weights for policy 0, policy_version 18640 (0.0004) [2023-03-09 03:08:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10786.1, 300 sec: 10510.8). Total num frames: 9564160. Throughput: 0: 10806.9. Samples: 9563940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:08:50,829][613581] Avg episode reward: [(0, '3964.265')] [2023-03-09 03:08:52,556][613885] Updated weights for policy 0, policy_version 18720 (0.0005) [2023-03-09 03:08:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10786.1, 300 sec: 10510.8). Total num frames: 9617408. Throughput: 0: 10749.1. Samples: 9592904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:08:55,829][613581] Avg episode reward: [(0, '3955.427')] [2023-03-09 03:08:56,371][613885] Updated weights for policy 0, policy_version 18800 (0.0005) [2023-03-09 03:09:00,001][613885] Updated weights for policy 0, policy_version 18880 (0.0006) [2023-03-09 03:09:00,829][613581] Fps is (10 sec: 11059.0, 60 sec: 10854.4, 300 sec: 10538.5). Total num frames: 9674752. Throughput: 0: 10858.0. Samples: 9660088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:09:00,829][613581] Avg episode reward: [(0, '3401.243')] [2023-03-09 03:09:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018896_9674752.pth... [2023-03-09 03:09:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018264_9351168.pth [2023-03-09 03:09:03,972][613885] Updated weights for policy 0, policy_version 18960 (0.0005) [2023-03-09 03:09:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10524.6). Total num frames: 9723904. Throughput: 0: 10780.6. Samples: 9723040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:09:05,840][613581] Avg episode reward: [(0, '3276.824')] [2023-03-09 03:09:07,910][613885] Updated weights for policy 0, policy_version 19040 (0.0005) [2023-03-09 03:09:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10717.9, 300 sec: 10510.8). Total num frames: 9773056. Throughput: 0: 10689.8. Samples: 9752640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:09:10,840][613581] Avg episode reward: [(0, '3331.438')] [2023-03-09 03:09:12,025][613885] Updated weights for policy 0, policy_version 19120 (0.0005) [2023-03-09 03:09:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10717.9, 300 sec: 10510.8). Total num frames: 9826304. Throughput: 0: 10633.8. Samples: 9813920. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:09:15,840][613581] Avg episode reward: [(0, '3442.820')] [2023-03-09 03:09:15,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019192_9826304.pth... [2023-03-09 03:09:15,844][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018584_9515008.pth [2023-03-09 03:09:15,965][613885] Updated weights for policy 0, policy_version 19200 (0.0005) [2023-03-09 03:09:19,737][613885] Updated weights for policy 0, policy_version 19280 (0.0005) [2023-03-09 03:09:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10510.8). Total num frames: 9879552. Throughput: 0: 10608.5. Samples: 9879444. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:09:20,840][613581] Avg episode reward: [(0, '3766.220')] [2023-03-09 03:09:23,802][613885] Updated weights for policy 0, policy_version 19360 (0.0004) [2023-03-09 03:09:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10524.6). Total num frames: 9932800. Throughput: 0: 10526.1. Samples: 9908288. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:09:25,840][613581] Avg episode reward: [(0, '3949.859')] [2023-03-09 03:09:27,609][613885] Updated weights for policy 0, policy_version 19440 (0.0005) [2023-03-09 03:09:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10538.5). Total num frames: 9986048. Throughput: 0: 10466.8. Samples: 9972412. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:09:30,829][613581] Avg episode reward: [(0, '4047.223')] [2023-03-09 03:09:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019504_9986048.pth... [2023-03-09 03:09:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018896_9674752.pth [2023-03-09 03:09:31,450][613885] Updated weights for policy 0, policy_version 19520 (0.0004) [2023-03-09 03:09:35,455][613885] Updated weights for policy 0, policy_version 19600 (0.0005) [2023-03-09 03:09:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10538.5). Total num frames: 10039296. Throughput: 0: 10469.8. Samples: 10035084. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:09:35,829][613581] Avg episode reward: [(0, '3861.186')] [2023-03-09 03:09:39,393][613885] Updated weights for policy 0, policy_version 19680 (0.0004) [2023-03-09 03:09:40,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10444.8, 300 sec: 10510.8). Total num frames: 10088448. Throughput: 0: 10531.6. Samples: 10066824. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:09:40,829][613581] Avg episode reward: [(0, '3811.317')] [2023-03-09 03:09:43,264][613885] Updated weights for policy 0, policy_version 19760 (0.0004) [2023-03-09 03:09:45,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10513.1, 300 sec: 10552.4). Total num frames: 10145792. Throughput: 0: 10457.6. Samples: 10130680. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:09:45,830][613581] Avg episode reward: [(0, '3913.010')] [2023-03-09 03:09:45,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019816_10145792.pth... [2023-03-09 03:09:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019192_9826304.pth [2023-03-09 03:09:46,999][613885] Updated weights for policy 0, policy_version 19840 (0.0005) [2023-03-09 03:09:50,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10513.1, 300 sec: 10538.5). Total num frames: 10194944. Throughput: 0: 10479.8. Samples: 10194632. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:09:50,829][613581] Avg episode reward: [(0, '4028.036')] [2023-03-09 03:09:50,857][613885] Updated weights for policy 0, policy_version 19920 (0.0005) [2023-03-09 03:09:54,630][613885] Updated weights for policy 0, policy_version 20000 (0.0005) [2023-03-09 03:09:55,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10513.1, 300 sec: 10552.4). Total num frames: 10248192. Throughput: 0: 10554.9. Samples: 10227612. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:09:55,829][613581] Avg episode reward: [(0, '3856.000')] [2023-03-09 03:09:58,563][613885] Updated weights for policy 0, policy_version 20080 (0.0005) [2023-03-09 03:10:00,829][613581] Fps is (10 sec: 11059.0, 60 sec: 10513.1, 300 sec: 10580.2). Total num frames: 10305536. Throughput: 0: 10576.8. Samples: 10289876. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:10:00,829][613581] Avg episode reward: [(0, '3953.634')] [2023-03-09 03:10:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000020128_10305536.pth... [2023-03-09 03:10:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019504_9986048.pth [2023-03-09 03:10:02,373][613885] Updated weights for policy 0, policy_version 20160 (0.0005) [2023-03-09 03:10:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10566.3). Total num frames: 10354688. Throughput: 0: 10559.3. Samples: 10354612. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:10:05,829][613581] Avg episode reward: [(0, '3930.645')] [2023-03-09 03:10:06,263][613885] Updated weights for policy 0, policy_version 20240 (0.0006) [2023-03-09 03:10:10,095][613885] Updated weights for policy 0, policy_version 20320 (0.0005) [2023-03-09 03:10:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10581.3, 300 sec: 10580.2). Total num frames: 10407936. Throughput: 0: 10621.0. Samples: 10386232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:10:10,829][613581] Avg episode reward: [(0, '3906.282')] [2023-03-09 03:10:14,204][613885] Updated weights for policy 0, policy_version 20400 (0.0004) [2023-03-09 03:10:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10594.1). Total num frames: 10461184. Throughput: 0: 10542.6. Samples: 10446828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:10:15,829][613581] Avg episode reward: [(0, '3887.243')] [2023-03-09 03:10:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000020432_10461184.pth... [2023-03-09 03:10:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019816_10145792.pth [2023-03-09 03:10:18,008][613885] Updated weights for policy 0, policy_version 20480 (0.0005) [2023-03-09 03:10:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10594.1). Total num frames: 10514432. Throughput: 0: 10561.3. Samples: 10510344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:10:20,829][613581] Avg episode reward: [(0, '3910.907')] [2023-03-09 03:10:21,818][613885] Updated weights for policy 0, policy_version 20560 (0.0005) [2023-03-09 03:10:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10580.2). Total num frames: 10563584. Throughput: 0: 10584.0. Samples: 10543104. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:10:25,829][613581] Avg episode reward: [(0, '4001.572')] [2023-03-09 03:10:25,858][613885] Updated weights for policy 0, policy_version 20640 (0.0004) [2023-03-09 03:10:29,637][613885] Updated weights for policy 0, policy_version 20720 (0.0005) [2023-03-09 03:10:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10594.1). Total num frames: 10620928. Throughput: 0: 10590.1. Samples: 10607232. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:10:30,829][613581] Avg episode reward: [(0, '3744.443')] [2023-03-09 03:10:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000020744_10620928.pth... [2023-03-09 03:10:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000020128_10305536.pth [2023-03-09 03:10:33,582][613885] Updated weights for policy 0, policy_version 20800 (0.0004) [2023-03-09 03:10:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10580.2). Total num frames: 10670080. Throughput: 0: 10476.1. Samples: 10666056. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:10:35,829][613581] Avg episode reward: [(0, '3741.778')] [2023-03-09 03:10:37,640][613885] Updated weights for policy 0, policy_version 20880 (0.0005) [2023-03-09 03:10:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10581.3, 300 sec: 10580.2). Total num frames: 10723328. Throughput: 0: 10459.2. Samples: 10698276. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:10:40,829][613581] Avg episode reward: [(0, '3870.196')] [2023-03-09 03:10:41,605][613885] Updated weights for policy 0, policy_version 20960 (0.0005) [2023-03-09 03:10:45,472][613885] Updated weights for policy 0, policy_version 21040 (0.0005) [2023-03-09 03:10:45,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10566.3). Total num frames: 10772480. Throughput: 0: 10460.8. Samples: 10760612. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:10:45,829][613581] Avg episode reward: [(0, '3619.652')] [2023-03-09 03:10:45,841][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000021048_10776576.pth... [2023-03-09 03:10:45,843][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000020432_10461184.pth [2023-03-09 03:10:49,164][613885] Updated weights for policy 0, policy_version 21120 (0.0005) [2023-03-09 03:10:50,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10580.2). Total num frames: 10829824. Throughput: 0: 10473.1. Samples: 10825904. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:10:50,829][613581] Avg episode reward: [(0, '3741.673')] [2023-03-09 03:10:52,885][613885] Updated weights for policy 0, policy_version 21200 (0.0005) [2023-03-09 03:10:55,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10581.3, 300 sec: 10580.2). Total num frames: 10883072. Throughput: 0: 10503.2. Samples: 10858876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:10:55,830][613581] Avg episode reward: [(0, '3896.184')] [2023-03-09 03:10:56,908][613885] Updated weights for policy 0, policy_version 21280 (0.0005) [2023-03-09 03:11:00,812][613885] Updated weights for policy 0, policy_version 21360 (0.0005) [2023-03-09 03:11:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10594.1). Total num frames: 10936320. Throughput: 0: 10515.1. Samples: 10920008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:11:00,830][613581] Avg episode reward: [(0, '3896.921')] [2023-03-09 03:11:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000021360_10936320.pth... [2023-03-09 03:11:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000020744_10620928.pth [2023-03-09 03:11:04,675][613885] Updated weights for policy 0, policy_version 21440 (0.0005) [2023-03-09 03:11:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10594.1). Total num frames: 10989568. Throughput: 0: 10556.9. Samples: 10985404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:11:05,829][613581] Avg episode reward: [(0, '3657.132')] [2023-03-09 03:11:08,426][613885] Updated weights for policy 0, policy_version 21520 (0.0004) [2023-03-09 03:11:10,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.3, 300 sec: 10594.1). Total num frames: 11042816. Throughput: 0: 10556.5. Samples: 11018144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:11:10,829][613581] Avg episode reward: [(0, '3493.422')] [2023-03-09 03:11:12,316][613885] Updated weights for policy 0, policy_version 21600 (0.0005) [2023-03-09 03:11:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10513.1, 300 sec: 10594.1). Total num frames: 11091968. Throughput: 0: 10500.3. Samples: 11079744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:11:15,829][613581] Avg episode reward: [(0, '3603.140')] [2023-03-09 03:11:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000021664_11091968.pth... [2023-03-09 03:11:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000021048_10776576.pth [2023-03-09 03:11:16,385][613885] Updated weights for policy 0, policy_version 21680 (0.0005) [2023-03-09 03:11:20,449][613885] Updated weights for policy 0, policy_version 21760 (0.0005) [2023-03-09 03:11:20,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10513.1, 300 sec: 10607.9). Total num frames: 11145216. Throughput: 0: 10554.5. Samples: 11141008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:11:20,840][613581] Avg episode reward: [(0, '3336.106')] [2023-03-09 03:11:24,461][613885] Updated weights for policy 0, policy_version 21840 (0.0005) [2023-03-09 03:11:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10594.1). Total num frames: 11194368. Throughput: 0: 10515.6. Samples: 11171480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:11:25,829][613581] Avg episode reward: [(0, '2791.444')] [2023-03-09 03:11:28,305][613885] Updated weights for policy 0, policy_version 21920 (0.0005) [2023-03-09 03:11:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10607.9). Total num frames: 11247616. Throughput: 0: 10519.3. Samples: 11233980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:11:30,829][613581] Avg episode reward: [(0, '3389.244')] [2023-03-09 03:11:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000021968_11247616.pth... [2023-03-09 03:11:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000021360_10936320.pth [2023-03-09 03:11:32,149][613885] Updated weights for policy 0, policy_version 22000 (0.0005) [2023-03-09 03:11:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10580.2). Total num frames: 11296768. Throughput: 0: 10460.0. Samples: 11296604. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:11:35,829][613581] Avg episode reward: [(0, '3871.247')] [2023-03-09 03:11:36,175][613885] Updated weights for policy 0, policy_version 22080 (0.0004) [2023-03-09 03:11:40,094][613885] Updated weights for policy 0, policy_version 22160 (0.0005) [2023-03-09 03:11:40,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10513.1, 300 sec: 10594.1). Total num frames: 11354112. Throughput: 0: 10449.4. Samples: 11329100. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:11:40,829][613581] Avg episode reward: [(0, '3823.885')] [2023-03-09 03:11:43,604][613885] Updated weights for policy 0, policy_version 22240 (0.0005) [2023-03-09 03:11:45,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10581.3, 300 sec: 10594.1). Total num frames: 11407360. Throughput: 0: 10558.4. Samples: 11395136. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:11:45,829][613581] Avg episode reward: [(0, '3485.065')] [2023-03-09 03:11:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000022280_11407360.pth... [2023-03-09 03:11:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000021664_11091968.pth [2023-03-09 03:11:47,544][613885] Updated weights for policy 0, policy_version 22320 (0.0005) [2023-03-09 03:11:50,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10580.2). Total num frames: 11460608. Throughput: 0: 10524.0. Samples: 11458984. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:11:50,829][613581] Avg episode reward: [(0, '3560.985')] [2023-03-09 03:11:51,309][613885] Updated weights for policy 0, policy_version 22400 (0.0004) [2023-03-09 03:11:55,124][613885] Updated weights for policy 0, policy_version 22480 (0.0004) [2023-03-09 03:11:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10594.1). Total num frames: 11513856. Throughput: 0: 10478.6. Samples: 11489684. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:11:55,840][613581] Avg episode reward: [(0, '3560.847')] [2023-03-09 03:11:58,956][613885] Updated weights for policy 0, policy_version 22560 (0.0005) [2023-03-09 03:12:00,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10513.1, 300 sec: 10594.1). Total num frames: 11567104. Throughput: 0: 10558.6. Samples: 11554880. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:12:00,842][613581] Avg episode reward: [(0, '3481.328')] [2023-03-09 03:12:00,845][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000022592_11567104.pth... [2023-03-09 03:12:00,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000021968_11247616.pth [2023-03-09 03:12:02,896][613885] Updated weights for policy 0, policy_version 22640 (0.0005) [2023-03-09 03:12:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10607.9). Total num frames: 11620352. Throughput: 0: 10566.8. Samples: 11616512. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:12:05,840][613581] Avg episode reward: [(0, '3399.247')] [2023-03-09 03:12:06,906][613885] Updated weights for policy 0, policy_version 22720 (0.0005) [2023-03-09 03:12:10,820][613885] Updated weights for policy 0, policy_version 22800 (0.0004) [2023-03-09 03:12:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.0, 300 sec: 10594.1). Total num frames: 11673600. Throughput: 0: 10609.9. Samples: 11648928. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:12:10,840][613581] Avg episode reward: [(0, '3300.003')] [2023-03-09 03:12:14,869][613885] Updated weights for policy 0, policy_version 22880 (0.0005) [2023-03-09 03:12:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10594.1). Total num frames: 11722752. Throughput: 0: 10586.4. Samples: 11710368. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:12:15,840][613581] Avg episode reward: [(0, '3369.961')] [2023-03-09 03:12:15,843][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000022896_11722752.pth... [2023-03-09 03:12:15,845][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000022280_11407360.pth [2023-03-09 03:12:18,765][613885] Updated weights for policy 0, policy_version 22960 (0.0005) [2023-03-09 03:12:20,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10580.2). Total num frames: 11776000. Throughput: 0: 10562.2. Samples: 11771904. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:12:20,840][613581] Avg episode reward: [(0, '3832.229')] [2023-03-09 03:12:22,742][613885] Updated weights for policy 0, policy_version 23040 (0.0005) [2023-03-09 03:12:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10552.4). Total num frames: 11825152. Throughput: 0: 10564.6. Samples: 11804508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:12:25,829][613581] Avg episode reward: [(0, '3980.678')] [2023-03-09 03:12:26,704][613885] Updated weights for policy 0, policy_version 23120 (0.0005) [2023-03-09 03:12:30,574][613885] Updated weights for policy 0, policy_version 23200 (0.0005) [2023-03-09 03:12:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10513.1, 300 sec: 10552.4). Total num frames: 11878400. Throughput: 0: 10463.1. Samples: 11865976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:12:30,830][613581] Avg episode reward: [(0, '2966.466')] [2023-03-09 03:12:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000023200_11878400.pth... [2023-03-09 03:12:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000022592_11567104.pth [2023-03-09 03:12:34,422][613885] Updated weights for policy 0, policy_version 23280 (0.0004) [2023-03-09 03:12:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10552.4). Total num frames: 11931648. Throughput: 0: 10485.2. Samples: 11930820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:12:35,829][613581] Avg episode reward: [(0, '3092.910')] [2023-03-09 03:12:38,304][613885] Updated weights for policy 0, policy_version 23360 (0.0005) [2023-03-09 03:12:40,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10513.0, 300 sec: 10566.3). Total num frames: 11984896. Throughput: 0: 10465.6. Samples: 11960636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:12:40,830][613581] Avg episode reward: [(0, '3847.664')] [2023-03-09 03:12:42,331][613885] Updated weights for policy 0, policy_version 23440 (0.0005) [2023-03-09 03:12:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10566.3). Total num frames: 12034048. Throughput: 0: 10375.3. Samples: 12021768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:12:45,829][613581] Avg episode reward: [(0, '4233.367')] [2023-03-09 03:12:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000023504_12034048.pth... [2023-03-09 03:12:45,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000022896_11722752.pth [2023-03-09 03:12:46,428][613885] Updated weights for policy 0, policy_version 23520 (0.0005) [2023-03-09 03:12:50,240][613885] Updated weights for policy 0, policy_version 23600 (0.0004) [2023-03-09 03:12:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10566.3). Total num frames: 12087296. Throughput: 0: 10397.7. Samples: 12084408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:12:50,829][613581] Avg episode reward: [(0, '4148.878')] [2023-03-09 03:12:54,195][613885] Updated weights for policy 0, policy_version 23680 (0.0005) [2023-03-09 03:12:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10566.3). Total num frames: 12140544. Throughput: 0: 10380.1. Samples: 12116032. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:12:55,829][613581] Avg episode reward: [(0, '4025.549')] [2023-03-09 03:12:58,068][613885] Updated weights for policy 0, policy_version 23760 (0.0005) [2023-03-09 03:13:00,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10552.4). Total num frames: 12193792. Throughput: 0: 10429.0. Samples: 12179672. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:13:00,830][613581] Avg episode reward: [(0, '4195.593')] [2023-03-09 03:13:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000023816_12193792.pth... [2023-03-09 03:13:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000023200_11878400.pth [2023-03-09 03:13:01,729][613885] Updated weights for policy 0, policy_version 23840 (0.0005) [2023-03-09 03:13:05,692][613885] Updated weights for policy 0, policy_version 23920 (0.0004) [2023-03-09 03:13:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10566.3). Total num frames: 12247040. Throughput: 0: 10481.1. Samples: 12243556. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:13:05,829][613581] Avg episode reward: [(0, '4308.999')] [2023-03-09 03:13:09,581][613885] Updated weights for policy 0, policy_version 24000 (0.0004) [2023-03-09 03:13:10,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10444.8, 300 sec: 10566.3). Total num frames: 12300288. Throughput: 0: 10473.1. Samples: 12275796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:13:10,829][613581] Avg episode reward: [(0, '4221.198')] [2023-03-09 03:13:13,628][613885] Updated weights for policy 0, policy_version 24080 (0.0004) [2023-03-09 03:13:15,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10538.5). Total num frames: 12349440. Throughput: 0: 10462.2. Samples: 12336772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:13:15,829][613581] Avg episode reward: [(0, '4330.027')] [2023-03-09 03:13:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000024120_12349440.pth... [2023-03-09 03:13:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000023504_12034048.pth [2023-03-09 03:13:17,422][613885] Updated weights for policy 0, policy_version 24160 (0.0004) [2023-03-09 03:13:20,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10538.5). Total num frames: 12402688. Throughput: 0: 10482.9. Samples: 12402552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:13:20,829][613581] Avg episode reward: [(0, '4140.255')] [2023-03-09 03:13:21,160][613885] Updated weights for policy 0, policy_version 24240 (0.0005) [2023-03-09 03:13:24,896][613885] Updated weights for policy 0, policy_version 24320 (0.0005) [2023-03-09 03:13:25,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10581.3, 300 sec: 10538.5). Total num frames: 12460032. Throughput: 0: 10549.3. Samples: 12435352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:13:25,829][613581] Avg episode reward: [(0, '4034.459')] [2023-03-09 03:13:28,898][613885] Updated weights for policy 0, policy_version 24400 (0.0005) [2023-03-09 03:13:30,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10581.3, 300 sec: 10538.5). Total num frames: 12513280. Throughput: 0: 10604.0. Samples: 12498948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:13:30,830][613581] Avg episode reward: [(0, '4165.059')] [2023-03-09 03:13:30,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000024440_12513280.pth... [2023-03-09 03:13:30,838][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000023816_12193792.pth [2023-03-09 03:13:32,782][613885] Updated weights for policy 0, policy_version 24480 (0.0004) [2023-03-09 03:13:35,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10513.1, 300 sec: 10510.7). Total num frames: 12562432. Throughput: 0: 10533.1. Samples: 12558400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:13:35,830][613581] Avg episode reward: [(0, '3896.402')] [2023-03-09 03:13:37,015][613885] Updated weights for policy 0, policy_version 24560 (0.0004) [2023-03-09 03:13:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10444.8, 300 sec: 10496.9). Total num frames: 12611584. Throughput: 0: 10507.7. Samples: 12588876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:13:40,829][613581] Avg episode reward: [(0, '3994.039')] [2023-03-09 03:13:41,027][613885] Updated weights for policy 0, policy_version 24640 (0.0005) [2023-03-09 03:13:44,919][613885] Updated weights for policy 0, policy_version 24720 (0.0004) [2023-03-09 03:13:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10510.7). Total num frames: 12664832. Throughput: 0: 10500.3. Samples: 12652184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:13:45,829][613581] Avg episode reward: [(0, '4090.854')] [2023-03-09 03:13:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000024736_12664832.pth... [2023-03-09 03:13:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000024120_12349440.pth [2023-03-09 03:13:48,574][613885] Updated weights for policy 0, policy_version 24800 (0.0005) [2023-03-09 03:13:50,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10581.4, 300 sec: 10524.6). Total num frames: 12722176. Throughput: 0: 10579.5. Samples: 12719632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:13:50,829][613581] Avg episode reward: [(0, '4136.091')] [2023-03-09 03:13:51,898][613885] Updated weights for policy 0, policy_version 24880 (0.0005) [2023-03-09 03:13:55,829][613581] Fps is (10 sec: 11059.3, 60 sec: 10581.3, 300 sec: 10510.8). Total num frames: 12775424. Throughput: 0: 10645.3. Samples: 12754836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:13:55,829][613581] Avg episode reward: [(0, '3944.501')] [2023-03-09 03:13:55,832][613885] Updated weights for policy 0, policy_version 24960 (0.0004) [2023-03-09 03:13:59,535][613885] Updated weights for policy 0, policy_version 25040 (0.0005) [2023-03-09 03:14:00,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10649.6, 300 sec: 10538.5). Total num frames: 12832768. Throughput: 0: 10732.0. Samples: 12819712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:14:00,829][613581] Avg episode reward: [(0, '4001.338')] [2023-03-09 03:14:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000025064_12832768.pth... [2023-03-09 03:14:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000024440_12513280.pth [2023-03-09 03:14:03,211][613885] Updated weights for policy 0, policy_version 25120 (0.0005) [2023-03-09 03:14:05,829][613581] Fps is (10 sec: 11059.3, 60 sec: 10649.6, 300 sec: 10552.4). Total num frames: 12886016. Throughput: 0: 10652.8. Samples: 12881928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:14:05,829][613581] Avg episode reward: [(0, '3927.411')] [2023-03-09 03:14:07,276][613885] Updated weights for policy 0, policy_version 25200 (0.0005) [2023-03-09 03:14:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10581.3, 300 sec: 10538.5). Total num frames: 12935168. Throughput: 0: 10627.0. Samples: 12913568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:14:10,829][613581] Avg episode reward: [(0, '4307.064')] [2023-03-09 03:14:11,305][613885] Updated weights for policy 0, policy_version 25280 (0.0005) [2023-03-09 03:14:15,220][613885] Updated weights for policy 0, policy_version 25360 (0.0004) [2023-03-09 03:14:15,829][613581] Fps is (10 sec: 10239.8, 60 sec: 10649.6, 300 sec: 10538.5). Total num frames: 12988416. Throughput: 0: 10603.7. Samples: 12976112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:14:15,829][613581] Avg episode reward: [(0, '4043.001')] [2023-03-09 03:14:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000025368_12988416.pth... [2023-03-09 03:14:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000024736_12664832.pth [2023-03-09 03:14:19,265][613885] Updated weights for policy 0, policy_version 25440 (0.0005) [2023-03-09 03:14:20,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10649.6, 300 sec: 10538.5). Total num frames: 13041664. Throughput: 0: 10648.2. Samples: 13037568. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:14:20,829][613581] Avg episode reward: [(0, '4163.131')] [2023-03-09 03:14:23,104][613885] Updated weights for policy 0, policy_version 25520 (0.0005) [2023-03-09 03:14:25,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.3, 300 sec: 10538.5). Total num frames: 13094912. Throughput: 0: 10683.8. Samples: 13069648. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:14:25,829][613581] Avg episode reward: [(0, '4011.972')] [2023-03-09 03:14:27,084][613885] Updated weights for policy 0, policy_version 25600 (0.0004) [2023-03-09 03:14:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10524.6). Total num frames: 13144064. Throughput: 0: 10654.9. Samples: 13131656. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:14:30,829][613581] Avg episode reward: [(0, '4138.243')] [2023-03-09 03:14:30,871][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000025680_13148160.pth... [2023-03-09 03:14:30,871][613885] Updated weights for policy 0, policy_version 25680 (0.0004) [2023-03-09 03:14:30,872][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000025064_12832768.pth [2023-03-09 03:14:34,509][613885] Updated weights for policy 0, policy_version 25760 (0.0005) [2023-03-09 03:14:35,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10552.4). Total num frames: 13201408. Throughput: 0: 10616.5. Samples: 13197376. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:14:35,829][613581] Avg episode reward: [(0, '4066.276')] [2023-03-09 03:14:38,593][613885] Updated weights for policy 0, policy_version 25840 (0.0005) [2023-03-09 03:14:40,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10649.6, 300 sec: 10524.6). Total num frames: 13250560. Throughput: 0: 10520.6. Samples: 13228264. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:14:40,829][613581] Avg episode reward: [(0, '4056.720')] [2023-03-09 03:14:42,581][613885] Updated weights for policy 0, policy_version 25920 (0.0005) [2023-03-09 03:14:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10649.6, 300 sec: 10538.5). Total num frames: 13303808. Throughput: 0: 10433.4. Samples: 13289216. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:14:45,829][613581] Avg episode reward: [(0, '3633.784')] [2023-03-09 03:14:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000025984_13303808.pth... [2023-03-09 03:14:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000025368_12988416.pth [2023-03-09 03:14:46,491][613885] Updated weights for policy 0, policy_version 26000 (0.0005) [2023-03-09 03:14:50,472][613885] Updated weights for policy 0, policy_version 26080 (0.0005) [2023-03-09 03:14:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.0, 300 sec: 10524.6). Total num frames: 13352960. Throughput: 0: 10463.7. Samples: 13352796. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:14:50,829][613581] Avg episode reward: [(0, '4282.114')] [2023-03-09 03:14:54,438][613885] Updated weights for policy 0, policy_version 26160 (0.0005) [2023-03-09 03:14:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10510.8). Total num frames: 13406208. Throughput: 0: 10447.0. Samples: 13383684. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:14:55,829][613581] Avg episode reward: [(0, '4067.262')] [2023-03-09 03:14:58,706][613885] Updated weights for policy 0, policy_version 26240 (0.0005) [2023-03-09 03:15:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10510.7). Total num frames: 13455360. Throughput: 0: 10337.7. Samples: 13441308. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:15:00,829][613581] Avg episode reward: [(0, '3784.146')] [2023-03-09 03:15:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000026280_13455360.pth... [2023-03-09 03:15:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000025680_13148160.pth [2023-03-09 03:15:02,890][613885] Updated weights for policy 0, policy_version 26320 (0.0005) [2023-03-09 03:15:05,829][613581] Fps is (10 sec: 9420.9, 60 sec: 10240.0, 300 sec: 10483.0). Total num frames: 13500416. Throughput: 0: 10282.7. Samples: 13500288. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:15:05,829][613581] Avg episode reward: [(0, '3475.302')] [2023-03-09 03:15:07,238][613885] Updated weights for policy 0, policy_version 26400 (0.0004) [2023-03-09 03:15:10,829][613581] Fps is (10 sec: 9420.9, 60 sec: 10240.0, 300 sec: 10469.1). Total num frames: 13549568. Throughput: 0: 10163.2. Samples: 13526992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:15:10,829][613581] Avg episode reward: [(0, '3515.217')] [2023-03-09 03:15:11,389][613885] Updated weights for policy 0, policy_version 26480 (0.0005) [2023-03-09 03:15:15,640][613885] Updated weights for policy 0, policy_version 26560 (0.0005) [2023-03-09 03:15:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10171.7, 300 sec: 10455.2). Total num frames: 13598720. Throughput: 0: 10105.5. Samples: 13586404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:15:15,829][613581] Avg episode reward: [(0, '3827.800')] [2023-03-09 03:15:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000026560_13598720.pth... [2023-03-09 03:15:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000025984_13303808.pth [2023-03-09 03:15:19,872][613885] Updated weights for policy 0, policy_version 26640 (0.0005) [2023-03-09 03:15:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10103.5, 300 sec: 10455.2). Total num frames: 13647872. Throughput: 0: 9932.6. Samples: 13644344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:15:20,829][613581] Avg episode reward: [(0, '4238.034')] [2023-03-09 03:15:24,227][613885] Updated weights for policy 0, policy_version 26720 (0.0005) [2023-03-09 03:15:25,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9966.9, 300 sec: 10413.6). Total num frames: 13692928. Throughput: 0: 9870.7. Samples: 13672444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:15:25,830][613581] Avg episode reward: [(0, '4155.270')] [2023-03-09 03:15:28,141][613885] Updated weights for policy 0, policy_version 26800 (0.0005) [2023-03-09 03:15:30,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10035.2, 300 sec: 10427.4). Total num frames: 13746176. Throughput: 0: 9879.4. Samples: 13733788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:15:30,829][613581] Avg episode reward: [(0, '4069.968')] [2023-03-09 03:15:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000026848_13746176.pth... [2023-03-09 03:15:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000026280_13455360.pth [2023-03-09 03:15:32,233][613885] Updated weights for policy 0, policy_version 26880 (0.0005) [2023-03-09 03:15:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 9898.7, 300 sec: 10413.6). Total num frames: 13795328. Throughput: 0: 9831.0. Samples: 13795188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:15:35,829][613581] Avg episode reward: [(0, '4116.383')] [2023-03-09 03:15:36,276][613885] Updated weights for policy 0, policy_version 26960 (0.0005) [2023-03-09 03:15:40,172][613885] Updated weights for policy 0, policy_version 27040 (0.0004) [2023-03-09 03:15:40,829][613581] Fps is (10 sec: 10240.1, 60 sec: 9966.9, 300 sec: 10427.4). Total num frames: 13848576. Throughput: 0: 9786.4. Samples: 13824072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:15:40,829][613581] Avg episode reward: [(0, '3922.168')] [2023-03-09 03:15:44,164][613885] Updated weights for policy 0, policy_version 27120 (0.0005) [2023-03-09 03:15:45,829][613581] Fps is (10 sec: 10649.5, 60 sec: 9966.9, 300 sec: 10413.6). Total num frames: 13901824. Throughput: 0: 9925.2. Samples: 13887940. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:15:45,829][613581] Avg episode reward: [(0, '4190.752')] [2023-03-09 03:15:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000027152_13901824.pth... [2023-03-09 03:15:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000026560_13598720.pth [2023-03-09 03:15:47,917][613885] Updated weights for policy 0, policy_version 27200 (0.0005) [2023-03-09 03:15:50,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10035.2, 300 sec: 10413.6). Total num frames: 13955072. Throughput: 0: 10016.9. Samples: 13951048. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:15:50,829][613581] Avg episode reward: [(0, '3996.988')] [2023-03-09 03:15:51,920][613885] Updated weights for policy 0, policy_version 27280 (0.0004) [2023-03-09 03:15:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 10399.7). Total num frames: 14004224. Throughput: 0: 10127.9. Samples: 13982748. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:15:55,829][613581] Avg episode reward: [(0, '4121.669')] [2023-03-09 03:15:56,238][613885] Updated weights for policy 0, policy_version 27360 (0.0005) [2023-03-09 03:16:00,328][613885] Updated weights for policy 0, policy_version 27440 (0.0005) [2023-03-09 03:16:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10385.8). Total num frames: 14053376. Throughput: 0: 10078.9. Samples: 14039956. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:16:00,829][613581] Avg episode reward: [(0, '3888.420')] [2023-03-09 03:16:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000027448_14053376.pth... [2023-03-09 03:16:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000026848_13746176.pth [2023-03-09 03:16:04,495][613885] Updated weights for policy 0, policy_version 27520 (0.0005) [2023-03-09 03:16:05,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10371.9). Total num frames: 14102528. Throughput: 0: 10114.8. Samples: 14099508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:16:05,829][613581] Avg episode reward: [(0, '4015.181')] [2023-03-09 03:16:08,681][613885] Updated weights for policy 0, policy_version 27600 (0.0005) [2023-03-09 03:16:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 10371.9). Total num frames: 14151680. Throughput: 0: 10120.0. Samples: 14127844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:16:10,829][613581] Avg episode reward: [(0, '3957.942')] [2023-03-09 03:16:12,764][613885] Updated weights for policy 0, policy_version 27680 (0.0004) [2023-03-09 03:16:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 10358.0). Total num frames: 14200832. Throughput: 0: 10105.5. Samples: 14188536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:16:15,829][613581] Avg episode reward: [(0, '3425.868')] [2023-03-09 03:16:15,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000027736_14200832.pth... [2023-03-09 03:16:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000027152_13901824.pth [2023-03-09 03:16:16,915][613885] Updated weights for policy 0, policy_version 27760 (0.0004) [2023-03-09 03:16:20,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10358.0). Total num frames: 14249984. Throughput: 0: 10083.0. Samples: 14248924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:16:20,829][613581] Avg episode reward: [(0, '3846.575')] [2023-03-09 03:16:20,938][613885] Updated weights for policy 0, policy_version 27840 (0.0004) [2023-03-09 03:16:24,956][613885] Updated weights for policy 0, policy_version 27920 (0.0005) [2023-03-09 03:16:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10358.0). Total num frames: 14303232. Throughput: 0: 10076.7. Samples: 14277524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:16:25,829][613581] Avg episode reward: [(0, '4067.310')] [2023-03-09 03:16:28,799][613885] Updated weights for policy 0, policy_version 28000 (0.0005) [2023-03-09 03:16:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10171.7, 300 sec: 10371.9). Total num frames: 14356480. Throughput: 0: 10074.6. Samples: 14341296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:16:30,830][613581] Avg episode reward: [(0, '4110.732')] [2023-03-09 03:16:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000028040_14356480.pth... [2023-03-09 03:16:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000027448_14053376.pth [2023-03-09 03:16:32,930][613885] Updated weights for policy 0, policy_version 28080 (0.0005) [2023-03-09 03:16:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10330.3). Total num frames: 14401536. Throughput: 0: 10010.6. Samples: 14401524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:16:35,829][613581] Avg episode reward: [(0, '4355.416')] [2023-03-09 03:16:37,101][613885] Updated weights for policy 0, policy_version 28160 (0.0005) [2023-03-09 03:16:40,829][613581] Fps is (10 sec: 9420.9, 60 sec: 10035.2, 300 sec: 10316.4). Total num frames: 14450688. Throughput: 0: 9943.2. Samples: 14430192. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:16:40,829][613581] Avg episode reward: [(0, '4378.632')] [2023-03-09 03:16:41,541][613885] Updated weights for policy 0, policy_version 28240 (0.0005) [2023-03-09 03:16:45,668][613885] Updated weights for policy 0, policy_version 28320 (0.0006) [2023-03-09 03:16:45,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9966.9, 300 sec: 10302.5). Total num frames: 14499840. Throughput: 0: 9938.2. Samples: 14487176. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:16:45,829][613581] Avg episode reward: [(0, '4010.189')] [2023-03-09 03:16:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000028320_14499840.pth... [2023-03-09 03:16:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000027736_14200832.pth [2023-03-09 03:16:49,799][613885] Updated weights for policy 0, policy_version 28400 (0.0005) [2023-03-09 03:16:50,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9898.7, 300 sec: 10288.6). Total num frames: 14548992. Throughput: 0: 9935.6. Samples: 14546608. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:16:50,829][613581] Avg episode reward: [(0, '4249.330')] [2023-03-09 03:16:53,913][613885] Updated weights for policy 0, policy_version 28480 (0.0004) [2023-03-09 03:16:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 10274.7). Total num frames: 14598144. Throughput: 0: 9975.5. Samples: 14576740. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:16:55,829][613581] Avg episode reward: [(0, '4087.485')] [2023-03-09 03:16:58,138][613885] Updated weights for policy 0, policy_version 28560 (0.0005) [2023-03-09 03:17:00,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9898.7, 300 sec: 10260.8). Total num frames: 14647296. Throughput: 0: 9923.4. Samples: 14635088. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:17:00,829][613581] Avg episode reward: [(0, '4171.957')] [2023-03-09 03:17:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000028608_14647296.pth... [2023-03-09 03:17:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000028040_14356480.pth [2023-03-09 03:17:02,236][613885] Updated weights for policy 0, policy_version 28640 (0.0005) [2023-03-09 03:17:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 10246.9). Total num frames: 14696448. Throughput: 0: 9942.2. Samples: 14696324. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:17:05,829][613581] Avg episode reward: [(0, '4265.772')] [2023-03-09 03:17:06,320][613885] Updated weights for policy 0, policy_version 28720 (0.0005) [2023-03-09 03:17:10,093][613885] Updated weights for policy 0, policy_version 28800 (0.0004) [2023-03-09 03:17:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10035.2, 300 sec: 10274.7). Total num frames: 14753792. Throughput: 0: 9961.9. Samples: 14725812. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:17:10,829][613581] Avg episode reward: [(0, '4160.155')] [2023-03-09 03:17:13,917][613885] Updated weights for policy 0, policy_version 28880 (0.0005) [2023-03-09 03:17:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10035.2, 300 sec: 10260.8). Total num frames: 14802944. Throughput: 0: 9992.5. Samples: 14790960. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:17:15,829][613581] Avg episode reward: [(0, '4314.020')] [2023-03-09 03:17:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000028912_14802944.pth... [2023-03-09 03:17:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000028320_14499840.pth [2023-03-09 03:17:17,887][613885] Updated weights for policy 0, policy_version 28960 (0.0005) [2023-03-09 03:17:20,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10103.5, 300 sec: 10274.7). Total num frames: 14856192. Throughput: 0: 10090.2. Samples: 14855584. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:17:20,829][613581] Avg episode reward: [(0, '3829.927')] [2023-03-09 03:17:21,693][613885] Updated weights for policy 0, policy_version 29040 (0.0005) [2023-03-09 03:17:25,701][613885] Updated weights for policy 0, policy_version 29120 (0.0005) [2023-03-09 03:17:25,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10103.5, 300 sec: 10274.7). Total num frames: 14909440. Throughput: 0: 10105.9. Samples: 14884960. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:17:25,829][613581] Avg episode reward: [(0, '4191.836')] [2023-03-09 03:17:29,662][613885] Updated weights for policy 0, policy_version 29200 (0.0005) [2023-03-09 03:17:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10035.2, 300 sec: 10260.8). Total num frames: 14958592. Throughput: 0: 10224.9. Samples: 14947296. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:17:30,829][613581] Avg episode reward: [(0, '4140.178')] [2023-03-09 03:17:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000029216_14958592.pth... [2023-03-09 03:17:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000028608_14647296.pth [2023-03-09 03:17:33,472][613885] Updated weights for policy 0, policy_version 29280 (0.0005) [2023-03-09 03:17:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10260.8). Total num frames: 15011840. Throughput: 0: 10295.4. Samples: 15009900. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:17:35,829][613581] Avg episode reward: [(0, '4240.070')] [2023-03-09 03:17:37,552][613885] Updated weights for policy 0, policy_version 29360 (0.0004) [2023-03-09 03:17:40,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10171.7, 300 sec: 10260.8). Total num frames: 15060992. Throughput: 0: 10302.7. Samples: 15040360. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:17:40,829][613581] Avg episode reward: [(0, '4223.874')] [2023-03-09 03:17:41,817][613885] Updated weights for policy 0, policy_version 29440 (0.0005) [2023-03-09 03:17:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10171.7, 300 sec: 10246.9). Total num frames: 15110144. Throughput: 0: 10285.1. Samples: 15097920. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:17:45,829][613581] Avg episode reward: [(0, '4055.024')] [2023-03-09 03:17:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000029512_15110144.pth... [2023-03-09 03:17:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000028912_14802944.pth [2023-03-09 03:17:46,114][613885] Updated weights for policy 0, policy_version 29520 (0.0004) [2023-03-09 03:17:50,318][613885] Updated weights for policy 0, policy_version 29600 (0.0005) [2023-03-09 03:17:50,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10171.7, 300 sec: 10233.1). Total num frames: 15159296. Throughput: 0: 10201.9. Samples: 15155408. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:17:50,829][613581] Avg episode reward: [(0, '4368.001')] [2023-03-09 03:17:54,296][613885] Updated weights for policy 0, policy_version 29680 (0.0005) [2023-03-09 03:17:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10233.1). Total num frames: 15212544. Throughput: 0: 10259.9. Samples: 15187508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:17:55,829][613581] Avg episode reward: [(0, '4272.537')] [2023-03-09 03:17:58,178][613885] Updated weights for policy 0, policy_version 29760 (0.0005) [2023-03-09 03:18:00,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10308.3, 300 sec: 10233.1). Total num frames: 15265792. Throughput: 0: 10215.9. Samples: 15250676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:18:00,829][613581] Avg episode reward: [(0, '3852.671')] [2023-03-09 03:18:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000029816_15265792.pth... [2023-03-09 03:18:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000029216_14958592.pth [2023-03-09 03:18:02,010][613885] Updated weights for policy 0, policy_version 29840 (0.0005) [2023-03-09 03:18:05,827][613885] Updated weights for policy 0, policy_version 29920 (0.0005) [2023-03-09 03:18:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10233.1). Total num frames: 15319040. Throughput: 0: 10180.8. Samples: 15313720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:18:05,829][613581] Avg episode reward: [(0, '4063.139')] [2023-03-09 03:18:10,104][613885] Updated weights for policy 0, policy_version 30000 (0.0005) [2023-03-09 03:18:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.7, 300 sec: 10219.2). Total num frames: 15364096. Throughput: 0: 10192.4. Samples: 15343616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:18:10,829][613581] Avg episode reward: [(0, '3356.482')] [2023-03-09 03:18:14,194][613885] Updated weights for policy 0, policy_version 30080 (0.0004) [2023-03-09 03:18:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10240.0, 300 sec: 10219.2). Total num frames: 15417344. Throughput: 0: 10132.2. Samples: 15403244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:18:15,829][613581] Avg episode reward: [(0, '3355.513')] [2023-03-09 03:18:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000030112_15417344.pth... [2023-03-09 03:18:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000029512_15110144.pth [2023-03-09 03:18:18,264][613885] Updated weights for policy 0, policy_version 30160 (0.0005) [2023-03-09 03:18:20,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 10191.4). Total num frames: 15466496. Throughput: 0: 10091.0. Samples: 15463996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:18:20,829][613581] Avg episode reward: [(0, '3991.264')] [2023-03-09 03:18:22,085][613885] Updated weights for policy 0, policy_version 30240 (0.0005) [2023-03-09 03:18:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.8, 300 sec: 10191.4). Total num frames: 15519744. Throughput: 0: 10137.5. Samples: 15496548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:18:25,829][613581] Avg episode reward: [(0, '4045.154')] [2023-03-09 03:18:25,879][613885] Updated weights for policy 0, policy_version 30320 (0.0004) [2023-03-09 03:18:29,513][613885] Updated weights for policy 0, policy_version 30400 (0.0004) [2023-03-09 03:18:30,829][613581] Fps is (10 sec: 11059.3, 60 sec: 10308.3, 300 sec: 10219.2). Total num frames: 15577088. Throughput: 0: 10334.4. Samples: 15562968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:18:30,829][613581] Avg episode reward: [(0, '4084.633')] [2023-03-09 03:18:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000030424_15577088.pth... [2023-03-09 03:18:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000029816_15265792.pth [2023-03-09 03:18:33,636][613885] Updated weights for policy 0, policy_version 30480 (0.0005) [2023-03-09 03:18:35,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10240.0, 300 sec: 10219.2). Total num frames: 15626240. Throughput: 0: 10413.2. Samples: 15624004. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:18:35,829][613581] Avg episode reward: [(0, '3943.981')] [2023-03-09 03:18:37,650][613885] Updated weights for policy 0, policy_version 30560 (0.0005) [2023-03-09 03:18:40,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10240.0, 300 sec: 10205.3). Total num frames: 15675392. Throughput: 0: 10369.3. Samples: 15654128. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:18:40,829][613581] Avg episode reward: [(0, '3974.156')] [2023-03-09 03:18:41,983][613885] Updated weights for policy 0, policy_version 30640 (0.0005) [2023-03-09 03:18:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10177.5). Total num frames: 15724544. Throughput: 0: 10258.8. Samples: 15712320. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:18:45,829][613581] Avg episode reward: [(0, '3124.496')] [2023-03-09 03:18:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000030712_15724544.pth... [2023-03-09 03:18:45,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000030112_15417344.pth [2023-03-09 03:18:45,907][613885] Updated weights for policy 0, policy_version 30720 (0.0005) [2023-03-09 03:18:50,041][613885] Updated weights for policy 0, policy_version 30800 (0.0005) [2023-03-09 03:18:50,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10240.0, 300 sec: 10163.6). Total num frames: 15773696. Throughput: 0: 10218.1. Samples: 15773532. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:18:50,829][613581] Avg episode reward: [(0, '3627.316')] [2023-03-09 03:18:54,078][613885] Updated weights for policy 0, policy_version 30880 (0.0005) [2023-03-09 03:18:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10149.8). Total num frames: 15826944. Throughput: 0: 10194.5. Samples: 15802368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:18:55,829][613581] Avg episode reward: [(0, '3734.182')] [2023-03-09 03:18:58,292][613885] Updated weights for policy 0, policy_version 30960 (0.0005) [2023-03-09 03:19:00,829][613581] Fps is (10 sec: 10239.8, 60 sec: 10171.7, 300 sec: 10135.9). Total num frames: 15876096. Throughput: 0: 10190.4. Samples: 15861812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:19:00,829][613581] Avg episode reward: [(0, '4057.419')] [2023-03-09 03:19:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000031008_15876096.pth... [2023-03-09 03:19:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000030424_15577088.pth [2023-03-09 03:19:02,290][613885] Updated weights for policy 0, policy_version 31040 (0.0004) [2023-03-09 03:19:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10135.9). Total num frames: 15925248. Throughput: 0: 10245.1. Samples: 15925024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:19:05,829][613581] Avg episode reward: [(0, '4061.348')] [2023-03-09 03:19:06,308][613885] Updated weights for policy 0, policy_version 31120 (0.0005) [2023-03-09 03:19:10,316][613885] Updated weights for policy 0, policy_version 31200 (0.0004) [2023-03-09 03:19:10,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10240.0, 300 sec: 10135.9). Total num frames: 15978496. Throughput: 0: 10175.4. Samples: 15954440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:19:10,829][613581] Avg episode reward: [(0, '4178.945')] [2023-03-09 03:19:14,559][613885] Updated weights for policy 0, policy_version 31280 (0.0005) [2023-03-09 03:19:15,829][613581] Fps is (10 sec: 10239.8, 60 sec: 10171.7, 300 sec: 10122.0). Total num frames: 16027648. Throughput: 0: 10026.2. Samples: 16014148. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:19:15,830][613581] Avg episode reward: [(0, '4267.181')] [2023-03-09 03:19:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000031304_16027648.pth... [2023-03-09 03:19:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000030712_15724544.pth [2023-03-09 03:19:18,730][613885] Updated weights for policy 0, policy_version 31360 (0.0004) [2023-03-09 03:19:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10171.7, 300 sec: 10108.1). Total num frames: 16076800. Throughput: 0: 9971.1. Samples: 16072704. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:19:20,830][613581] Avg episode reward: [(0, '4382.487')] [2023-03-09 03:19:22,892][613885] Updated weights for policy 0, policy_version 31440 (0.0005) [2023-03-09 03:19:25,829][613581] Fps is (10 sec: 9420.9, 60 sec: 10035.2, 300 sec: 10094.2). Total num frames: 16121856. Throughput: 0: 9954.0. Samples: 16102056. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:19:25,829][613581] Avg episode reward: [(0, '4154.786')] [2023-03-09 03:19:27,096][613885] Updated weights for policy 0, policy_version 31520 (0.0004) [2023-03-09 03:19:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10080.3). Total num frames: 16175104. Throughput: 0: 10000.7. Samples: 16162352. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:19:30,829][613581] Avg episode reward: [(0, '4183.112')] [2023-03-09 03:19:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000031592_16175104.pth... [2023-03-09 03:19:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000031008_15876096.pth [2023-03-09 03:19:31,224][613885] Updated weights for policy 0, policy_version 31600 (0.0005) [2023-03-09 03:19:35,204][613885] Updated weights for policy 0, policy_version 31680 (0.0004) [2023-03-09 03:19:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 10080.3). Total num frames: 16224256. Throughput: 0: 9967.4. Samples: 16222068. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:19:35,829][613581] Avg episode reward: [(0, '4258.582')] [2023-03-09 03:19:39,317][613885] Updated weights for policy 0, policy_version 31760 (0.0004) [2023-03-09 03:19:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 10080.3). Total num frames: 16277504. Throughput: 0: 10006.5. Samples: 16252660. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:19:40,829][613581] Avg episode reward: [(0, '4131.008')] [2023-03-09 03:19:43,133][613885] Updated weights for policy 0, policy_version 31840 (0.0005) [2023-03-09 03:19:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10103.5, 300 sec: 10094.2). Total num frames: 16330752. Throughput: 0: 10058.4. Samples: 16314440. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:19:45,829][613581] Avg episode reward: [(0, '4133.909')] [2023-03-09 03:19:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000031896_16330752.pth... [2023-03-09 03:19:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000031304_16027648.pth [2023-03-09 03:19:46,818][613885] Updated weights for policy 0, policy_version 31920 (0.0005) [2023-03-09 03:19:50,674][613885] Updated weights for policy 0, policy_version 32000 (0.0005) [2023-03-09 03:19:50,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10171.7, 300 sec: 10094.2). Total num frames: 16384000. Throughput: 0: 10115.5. Samples: 16380224. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:19:50,829][613581] Avg episode reward: [(0, '4099.478')] [2023-03-09 03:19:54,667][613885] Updated weights for policy 0, policy_version 32080 (0.0005) [2023-03-09 03:19:55,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10171.7, 300 sec: 10108.1). Total num frames: 16437248. Throughput: 0: 10181.9. Samples: 16412624. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:19:55,829][613581] Avg episode reward: [(0, '4031.957')] [2023-03-09 03:19:58,438][613885] Updated weights for policy 0, policy_version 32160 (0.0004) [2023-03-09 03:20:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 10135.9). Total num frames: 16490496. Throughput: 0: 10273.3. Samples: 16476444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:20:00,829][613581] Avg episode reward: [(0, '3410.675')] [2023-03-09 03:20:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000032208_16490496.pth... [2023-03-09 03:20:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000031592_16175104.pth [2023-03-09 03:20:02,286][613885] Updated weights for policy 0, policy_version 32240 (0.0005) [2023-03-09 03:20:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10149.7). Total num frames: 16543744. Throughput: 0: 10405.4. Samples: 16540944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:20:05,829][613581] Avg episode reward: [(0, '4021.877')] [2023-03-09 03:20:05,986][613885] Updated weights for policy 0, policy_version 32320 (0.0005) [2023-03-09 03:20:09,788][613885] Updated weights for policy 0, policy_version 32400 (0.0005) [2023-03-09 03:20:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10163.6). Total num frames: 16596992. Throughput: 0: 10505.1. Samples: 16574784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:20:10,829][613581] Avg episode reward: [(0, '4000.481')] [2023-03-09 03:20:13,783][613885] Updated weights for policy 0, policy_version 32480 (0.0005) [2023-03-09 03:20:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 10177.5). Total num frames: 16650240. Throughput: 0: 10543.0. Samples: 16636788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:20:15,829][613581] Avg episode reward: [(0, '4233.435')] [2023-03-09 03:20:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000032520_16650240.pth... [2023-03-09 03:20:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000031896_16330752.pth [2023-03-09 03:20:17,601][613885] Updated weights for policy 0, policy_version 32560 (0.0005) [2023-03-09 03:20:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10205.3). Total num frames: 16703488. Throughput: 0: 10607.4. Samples: 16699400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:20:20,829][613581] Avg episode reward: [(0, '4111.276')] [2023-03-09 03:20:21,554][613885] Updated weights for policy 0, policy_version 32640 (0.0005) [2023-03-09 03:20:25,371][613885] Updated weights for policy 0, policy_version 32720 (0.0005) [2023-03-09 03:20:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10205.3). Total num frames: 16756736. Throughput: 0: 10655.6. Samples: 16732160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:20:25,829][613581] Avg episode reward: [(0, '3967.500')] [2023-03-09 03:20:29,446][613885] Updated weights for policy 0, policy_version 32800 (0.0004) [2023-03-09 03:20:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10513.1, 300 sec: 10205.3). Total num frames: 16805888. Throughput: 0: 10646.5. Samples: 16793532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:20:30,829][613581] Avg episode reward: [(0, '4020.531')] [2023-03-09 03:20:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000032824_16805888.pth... [2023-03-09 03:20:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000032208_16490496.pth [2023-03-09 03:20:33,289][613885] Updated weights for policy 0, policy_version 32880 (0.0004) [2023-03-09 03:20:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10581.4, 300 sec: 10205.3). Total num frames: 16859136. Throughput: 0: 10554.4. Samples: 16855172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:20:35,829][613581] Avg episode reward: [(0, '4097.018')] [2023-03-09 03:20:37,319][613885] Updated weights for policy 0, policy_version 32960 (0.0005) [2023-03-09 03:20:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10205.3). Total num frames: 16912384. Throughput: 0: 10551.6. Samples: 16887448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:20:40,830][613581] Avg episode reward: [(0, '3744.954')] [2023-03-09 03:20:41,167][613885] Updated weights for policy 0, policy_version 33040 (0.0005) [2023-03-09 03:20:45,095][613885] Updated weights for policy 0, policy_version 33120 (0.0005) [2023-03-09 03:20:45,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10581.3, 300 sec: 10205.3). Total num frames: 16965632. Throughput: 0: 10508.2. Samples: 16949312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:20:45,829][613581] Avg episode reward: [(0, '3926.512')] [2023-03-09 03:20:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000033136_16965632.pth... [2023-03-09 03:20:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000032520_16650240.pth [2023-03-09 03:20:48,927][613885] Updated weights for policy 0, policy_version 33200 (0.0005) [2023-03-09 03:20:50,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10219.2). Total num frames: 17018880. Throughput: 0: 10526.2. Samples: 17014624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:20:50,829][613581] Avg episode reward: [(0, '3306.112')] [2023-03-09 03:20:52,648][613885] Updated weights for policy 0, policy_version 33280 (0.0005) [2023-03-09 03:20:55,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.3, 300 sec: 10233.1). Total num frames: 17072128. Throughput: 0: 10505.8. Samples: 17047544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:20:55,829][613581] Avg episode reward: [(0, '3234.011')] [2023-03-09 03:20:56,488][613885] Updated weights for policy 0, policy_version 33360 (0.0004) [2023-03-09 03:21:00,151][613885] Updated weights for policy 0, policy_version 33440 (0.0004) [2023-03-09 03:21:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10246.9). Total num frames: 17125376. Throughput: 0: 10597.5. Samples: 17113676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:21:00,829][613581] Avg episode reward: [(0, '3357.848')] [2023-03-09 03:21:00,867][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000033456_17129472.pth... [2023-03-09 03:21:00,869][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000032824_16805888.pth [2023-03-09 03:21:03,957][613885] Updated weights for policy 0, policy_version 33520 (0.0005) [2023-03-09 03:21:05,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10649.6, 300 sec: 10274.7). Total num frames: 17182720. Throughput: 0: 10649.6. Samples: 17178632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:21:05,829][613581] Avg episode reward: [(0, '2809.652')] [2023-03-09 03:21:07,600][613885] Updated weights for policy 0, policy_version 33600 (0.0005) [2023-03-09 03:21:10,829][613581] Fps is (10 sec: 11059.3, 60 sec: 10649.6, 300 sec: 10288.6). Total num frames: 17235968. Throughput: 0: 10649.8. Samples: 17211400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:21:10,829][613581] Avg episode reward: [(0, '3150.185')] [2023-03-09 03:21:11,446][613885] Updated weights for policy 0, policy_version 33680 (0.0005) [2023-03-09 03:21:14,981][613885] Updated weights for policy 0, policy_version 33760 (0.0005) [2023-03-09 03:21:15,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 10316.4). Total num frames: 17293312. Throughput: 0: 10780.2. Samples: 17278640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:21:15,829][613581] Avg episode reward: [(0, '3455.471')] [2023-03-09 03:21:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000033776_17293312.pth... [2023-03-09 03:21:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000033136_16965632.pth [2023-03-09 03:21:18,742][613885] Updated weights for policy 0, policy_version 33840 (0.0006) [2023-03-09 03:21:20,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 10316.4). Total num frames: 17346560. Throughput: 0: 10830.3. Samples: 17342536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:21:20,829][613581] Avg episode reward: [(0, '3113.262')] [2023-03-09 03:21:22,764][613885] Updated weights for policy 0, policy_version 33920 (0.0004) [2023-03-09 03:21:25,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10717.9, 300 sec: 10316.4). Total num frames: 17399808. Throughput: 0: 10815.4. Samples: 17374140. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:21:25,829][613581] Avg episode reward: [(0, '3845.831')] [2023-03-09 03:21:26,404][613885] Updated weights for policy 0, policy_version 34000 (0.0005) [2023-03-09 03:21:30,185][613885] Updated weights for policy 0, policy_version 34080 (0.0005) [2023-03-09 03:21:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10344.1). Total num frames: 17453056. Throughput: 0: 10921.4. Samples: 17440776. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:21:30,829][613581] Avg episode reward: [(0, '3217.736')] [2023-03-09 03:21:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000034088_17453056.pth... [2023-03-09 03:21:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000033456_17129472.pth [2023-03-09 03:21:34,138][613885] Updated weights for policy 0, policy_version 34160 (0.0004) [2023-03-09 03:21:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10358.0). Total num frames: 17506304. Throughput: 0: 10851.8. Samples: 17502956. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:21:35,829][613581] Avg episode reward: [(0, '2828.323')] [2023-03-09 03:21:37,982][613885] Updated weights for policy 0, policy_version 34240 (0.0005) [2023-03-09 03:21:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10717.9, 300 sec: 10358.0). Total num frames: 17555456. Throughput: 0: 10833.2. Samples: 17535040. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:21:40,829][613581] Avg episode reward: [(0, '2396.349')] [2023-03-09 03:21:41,992][613885] Updated weights for policy 0, policy_version 34320 (0.0005) [2023-03-09 03:21:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10717.9, 300 sec: 10371.9). Total num frames: 17608704. Throughput: 0: 10729.0. Samples: 17596480. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:21:45,829][613581] Avg episode reward: [(0, '3154.131')] [2023-03-09 03:21:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000034392_17608704.pth... [2023-03-09 03:21:45,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000033776_17293312.pth [2023-03-09 03:21:45,956][613885] Updated weights for policy 0, policy_version 34400 (0.0005) [2023-03-09 03:21:50,295][613885] Updated weights for policy 0, policy_version 34480 (0.0004) [2023-03-09 03:21:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10649.6, 300 sec: 10371.9). Total num frames: 17657856. Throughput: 0: 10569.1. Samples: 17654240. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:21:50,829][613581] Avg episode reward: [(0, '3153.278')] [2023-03-09 03:21:54,157][613885] Updated weights for policy 0, policy_version 34560 (0.0005) [2023-03-09 03:21:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10649.6, 300 sec: 10385.8). Total num frames: 17711104. Throughput: 0: 10560.2. Samples: 17686608. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:21:55,829][613581] Avg episode reward: [(0, '2596.427')] [2023-03-09 03:21:58,183][613885] Updated weights for policy 0, policy_version 34640 (0.0005) [2023-03-09 03:22:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10581.3, 300 sec: 10385.8). Total num frames: 17760256. Throughput: 0: 10426.2. Samples: 17747820. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:22:00,829][613581] Avg episode reward: [(0, '2085.631')] [2023-03-09 03:22:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000034688_17760256.pth... [2023-03-09 03:22:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000034088_17453056.pth [2023-03-09 03:22:02,368][613885] Updated weights for policy 0, policy_version 34720 (0.0005) [2023-03-09 03:22:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10444.8, 300 sec: 10358.0). Total num frames: 17809408. Throughput: 0: 10349.3. Samples: 17808256. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:22:05,829][613581] Avg episode reward: [(0, '2920.682')] [2023-03-09 03:22:06,288][613885] Updated weights for policy 0, policy_version 34800 (0.0004) [2023-03-09 03:22:10,359][613885] Updated weights for policy 0, policy_version 34880 (0.0004) [2023-03-09 03:22:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10371.9). Total num frames: 17862656. Throughput: 0: 10315.9. Samples: 17838356. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:22:10,829][613581] Avg episode reward: [(0, '2531.392')] [2023-03-09 03:22:14,391][613885] Updated weights for policy 0, policy_version 34960 (0.0004) [2023-03-09 03:22:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10358.0). Total num frames: 17911808. Throughput: 0: 10194.6. Samples: 17899532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:22:15,829][613581] Avg episode reward: [(0, '3217.458')] [2023-03-09 03:22:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000034984_17911808.pth... [2023-03-09 03:22:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000034392_17608704.pth [2023-03-09 03:22:18,135][613885] Updated weights for policy 0, policy_version 35040 (0.0004) [2023-03-09 03:22:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 17969152. Throughput: 0: 10262.4. Samples: 17964764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:22:20,829][613581] Avg episode reward: [(0, '2928.481')] [2023-03-09 03:22:21,963][613885] Updated weights for policy 0, policy_version 35120 (0.0005) [2023-03-09 03:22:25,691][613885] Updated weights for policy 0, policy_version 35200 (0.0005) [2023-03-09 03:22:25,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10376.5, 300 sec: 10385.8). Total num frames: 18022400. Throughput: 0: 10280.1. Samples: 17997644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:22:25,829][613581] Avg episode reward: [(0, '3107.179')] [2023-03-09 03:22:29,573][613885] Updated weights for policy 0, policy_version 35280 (0.0004) [2023-03-09 03:22:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10385.8). Total num frames: 18075648. Throughput: 0: 10351.0. Samples: 18062276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:22:30,829][613581] Avg episode reward: [(0, '2528.517')] [2023-03-09 03:22:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000035304_18075648.pth... [2023-03-09 03:22:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000034688_17760256.pth [2023-03-09 03:22:33,529][613885] Updated weights for policy 0, policy_version 35360 (0.0004) [2023-03-09 03:22:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10385.8). Total num frames: 18124800. Throughput: 0: 10367.4. Samples: 18120776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:22:35,829][613581] Avg episode reward: [(0, '2723.222')] [2023-03-09 03:22:37,857][613885] Updated weights for policy 0, policy_version 35440 (0.0005) [2023-03-09 03:22:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 10385.8). Total num frames: 18173952. Throughput: 0: 10311.8. Samples: 18150640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:22:40,829][613581] Avg episode reward: [(0, '3227.365')] [2023-03-09 03:22:41,850][613885] Updated weights for policy 0, policy_version 35520 (0.0005) [2023-03-09 03:22:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10385.8). Total num frames: 18223104. Throughput: 0: 10318.9. Samples: 18212168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:22:45,829][613581] Avg episode reward: [(0, '3180.283')] [2023-03-09 03:22:45,837][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000035600_18227200.pth... [2023-03-09 03:22:45,838][613885] Updated weights for policy 0, policy_version 35600 (0.0004) [2023-03-09 03:22:45,839][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000034984_17911808.pth [2023-03-09 03:22:49,854][613885] Updated weights for policy 0, policy_version 35680 (0.0004) [2023-03-09 03:22:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10385.8). Total num frames: 18276352. Throughput: 0: 10336.5. Samples: 18273400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:22:50,829][613581] Avg episode reward: [(0, '3600.375')] [2023-03-09 03:22:54,036][613885] Updated weights for policy 0, policy_version 35760 (0.0005) [2023-03-09 03:22:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10371.9). Total num frames: 18325504. Throughput: 0: 10281.0. Samples: 18301000. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:22:55,829][613581] Avg episode reward: [(0, '3015.952')] [2023-03-09 03:22:58,068][613885] Updated weights for policy 0, policy_version 35840 (0.0005) [2023-03-09 03:23:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 18378752. Throughput: 0: 10317.6. Samples: 18363824. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:23:00,829][613581] Avg episode reward: [(0, '3812.269')] [2023-03-09 03:23:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000035896_18378752.pth... [2023-03-09 03:23:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000035304_18075648.pth [2023-03-09 03:23:01,907][613885] Updated weights for policy 0, policy_version 35920 (0.0005) [2023-03-09 03:23:05,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10385.8). Total num frames: 18427904. Throughput: 0: 10289.5. Samples: 18427792. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:23:05,829][613581] Avg episode reward: [(0, '3669.270')] [2023-03-09 03:23:05,869][613885] Updated weights for policy 0, policy_version 36000 (0.0004) [2023-03-09 03:23:10,092][613885] Updated weights for policy 0, policy_version 36080 (0.0005) [2023-03-09 03:23:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10385.8). Total num frames: 18481152. Throughput: 0: 10189.4. Samples: 18456168. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:23:10,829][613581] Avg episode reward: [(0, '3926.032')] [2023-03-09 03:23:13,745][613885] Updated weights for policy 0, policy_version 36160 (0.0005) [2023-03-09 03:23:15,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10376.5, 300 sec: 10399.7). Total num frames: 18534400. Throughput: 0: 10194.6. Samples: 18521032. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:23:15,829][613581] Avg episode reward: [(0, '3876.040')] [2023-03-09 03:23:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000036200_18534400.pth... [2023-03-09 03:23:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000035600_18227200.pth [2023-03-09 03:23:17,593][613885] Updated weights for policy 0, policy_version 36240 (0.0005) [2023-03-09 03:23:20,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10308.3, 300 sec: 10399.7). Total num frames: 18587648. Throughput: 0: 10283.9. Samples: 18583552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:23:20,829][613581] Avg episode reward: [(0, '3766.038')] [2023-03-09 03:23:21,611][613885] Updated weights for policy 0, policy_version 36320 (0.0005) [2023-03-09 03:23:25,330][613885] Updated weights for policy 0, policy_version 36400 (0.0004) [2023-03-09 03:23:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10385.8). Total num frames: 18640896. Throughput: 0: 10349.9. Samples: 18616384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:23:25,829][613581] Avg episode reward: [(0, '3669.299')] [2023-03-09 03:23:29,045][613885] Updated weights for policy 0, policy_version 36480 (0.0005) [2023-03-09 03:23:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10399.7). Total num frames: 18694144. Throughput: 0: 10438.9. Samples: 18681920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:23:30,829][613581] Avg episode reward: [(0, '3751.021')] [2023-03-09 03:23:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000036512_18694144.pth... [2023-03-09 03:23:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000035896_18378752.pth [2023-03-09 03:23:32,941][613885] Updated weights for policy 0, policy_version 36560 (0.0004) [2023-03-09 03:23:35,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10376.6, 300 sec: 10413.6). Total num frames: 18747392. Throughput: 0: 10442.2. Samples: 18743296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:23:35,829][613581] Avg episode reward: [(0, '3294.555')] [2023-03-09 03:23:36,933][613885] Updated weights for policy 0, policy_version 36640 (0.0005) [2023-03-09 03:23:40,604][613885] Updated weights for policy 0, policy_version 36720 (0.0005) [2023-03-09 03:23:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10427.4). Total num frames: 18800640. Throughput: 0: 10558.4. Samples: 18776128. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:23:40,829][613581] Avg episode reward: [(0, '3989.090')] [2023-03-09 03:23:44,501][613885] Updated weights for policy 0, policy_version 36800 (0.0005) [2023-03-09 03:23:45,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10513.1, 300 sec: 10441.3). Total num frames: 18853888. Throughput: 0: 10603.9. Samples: 18841000. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:23:45,829][613581] Avg episode reward: [(0, '4090.527')] [2023-03-09 03:23:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000036824_18853888.pth... [2023-03-09 03:23:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000036200_18534400.pth [2023-03-09 03:23:48,367][613885] Updated weights for policy 0, policy_version 36880 (0.0005) [2023-03-09 03:23:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10427.4). Total num frames: 18903040. Throughput: 0: 10555.8. Samples: 18902804. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:23:50,829][613581] Avg episode reward: [(0, '4110.600')] [2023-03-09 03:23:52,372][613885] Updated weights for policy 0, policy_version 36960 (0.0004) [2023-03-09 03:23:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10441.3). Total num frames: 18956288. Throughput: 0: 10625.2. Samples: 18934300. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:23:55,829][613581] Avg episode reward: [(0, '4136.114')] [2023-03-09 03:23:56,270][613885] Updated weights for policy 0, policy_version 37040 (0.0005) [2023-03-09 03:23:59,924][613885] Updated weights for policy 0, policy_version 37120 (0.0004) [2023-03-09 03:24:00,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10581.3, 300 sec: 10469.1). Total num frames: 19013632. Throughput: 0: 10641.0. Samples: 18999876. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:24:00,829][613581] Avg episode reward: [(0, '3269.250')] [2023-03-09 03:24:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000037136_19013632.pth... [2023-03-09 03:24:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000036512_18694144.pth [2023-03-09 03:24:03,729][613885] Updated weights for policy 0, policy_version 37200 (0.0005) [2023-03-09 03:24:05,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10649.6, 300 sec: 10469.1). Total num frames: 19066880. Throughput: 0: 10670.7. Samples: 19063736. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:24:05,829][613581] Avg episode reward: [(0, '4071.060')] [2023-03-09 03:24:07,335][613885] Updated weights for policy 0, policy_version 37280 (0.0005) [2023-03-09 03:24:10,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 10496.9). Total num frames: 19124224. Throughput: 0: 10740.8. Samples: 19099720. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:24:10,829][613581] Avg episode reward: [(0, '4054.268')] [2023-03-09 03:24:11,151][613885] Updated weights for policy 0, policy_version 37360 (0.0005) [2023-03-09 03:24:15,337][613885] Updated weights for policy 0, policy_version 37440 (0.0004) [2023-03-09 03:24:15,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10496.9). Total num frames: 19173376. Throughput: 0: 10641.4. Samples: 19160784. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:24:15,829][613581] Avg episode reward: [(0, '4012.588')] [2023-03-09 03:24:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000037448_19173376.pth... [2023-03-09 03:24:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000036824_18853888.pth [2023-03-09 03:24:19,516][613885] Updated weights for policy 0, policy_version 37520 (0.0005) [2023-03-09 03:24:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10581.3, 300 sec: 10510.8). Total num frames: 19222528. Throughput: 0: 10610.6. Samples: 19220776. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:24:20,829][613581] Avg episode reward: [(0, '4301.362')] [2023-03-09 03:24:23,481][613885] Updated weights for policy 0, policy_version 37600 (0.0005) [2023-03-09 03:24:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10513.1, 300 sec: 10496.9). Total num frames: 19271680. Throughput: 0: 10552.8. Samples: 19251004. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:24:25,829][613581] Avg episode reward: [(0, '3823.353')] [2023-03-09 03:24:27,572][613885] Updated weights for policy 0, policy_version 37680 (0.0005) [2023-03-09 03:24:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10513.0, 300 sec: 10510.7). Total num frames: 19324928. Throughput: 0: 10447.2. Samples: 19311124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:24:30,830][613581] Avg episode reward: [(0, '4140.272')] [2023-03-09 03:24:30,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000037744_19324928.pth... [2023-03-09 03:24:30,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000037136_19013632.pth [2023-03-09 03:24:31,648][613885] Updated weights for policy 0, policy_version 37760 (0.0005) [2023-03-09 03:24:35,731][613885] Updated weights for policy 0, policy_version 37840 (0.0005) [2023-03-09 03:24:35,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10444.8, 300 sec: 10496.9). Total num frames: 19374080. Throughput: 0: 10389.9. Samples: 19370352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:24:35,829][613581] Avg episode reward: [(0, '4379.480')] [2023-03-09 03:24:39,708][613885] Updated weights for policy 0, policy_version 37920 (0.0004) [2023-03-09 03:24:40,829][613581] Fps is (10 sec: 9830.6, 60 sec: 10376.5, 300 sec: 10483.0). Total num frames: 19423232. Throughput: 0: 10383.5. Samples: 19401556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:24:40,829][613581] Avg episode reward: [(0, '3838.079')] [2023-03-09 03:24:43,538][613885] Updated weights for policy 0, policy_version 38000 (0.0004) [2023-03-09 03:24:45,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 10483.0). Total num frames: 19476480. Throughput: 0: 10324.7. Samples: 19464488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:24:45,829][613581] Avg episode reward: [(0, '4325.842')] [2023-03-09 03:24:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000038040_19476480.pth... [2023-03-09 03:24:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000037448_19173376.pth [2023-03-09 03:24:47,485][613885] Updated weights for policy 0, policy_version 38080 (0.0005) [2023-03-09 03:24:50,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10483.0). Total num frames: 19529728. Throughput: 0: 10322.4. Samples: 19528244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:24:50,829][613581] Avg episode reward: [(0, '4123.944')] [2023-03-09 03:24:51,322][613885] Updated weights for policy 0, policy_version 38160 (0.0005) [2023-03-09 03:24:55,027][613885] Updated weights for policy 0, policy_version 38240 (0.0004) [2023-03-09 03:24:55,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10513.1, 300 sec: 10496.9). Total num frames: 19587072. Throughput: 0: 10238.7. Samples: 19560460. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:24:55,829][613581] Avg episode reward: [(0, '3805.333')] [2023-03-09 03:24:58,940][613885] Updated weights for policy 0, policy_version 38320 (0.0005) [2023-03-09 03:25:00,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10376.6, 300 sec: 10483.0). Total num frames: 19636224. Throughput: 0: 10300.6. Samples: 19624308. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:25:00,829][613581] Avg episode reward: [(0, '4172.669')] [2023-03-09 03:25:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000038352_19636224.pth... [2023-03-09 03:25:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000037744_19324928.pth [2023-03-09 03:25:02,923][613885] Updated weights for policy 0, policy_version 38400 (0.0004) [2023-03-09 03:25:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10483.0). Total num frames: 19689472. Throughput: 0: 10325.9. Samples: 19685440. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:25:05,829][613581] Avg episode reward: [(0, '4004.446')] [2023-03-09 03:25:06,911][613885] Updated weights for policy 0, policy_version 38480 (0.0005) [2023-03-09 03:25:10,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10469.1). Total num frames: 19738624. Throughput: 0: 10377.3. Samples: 19717984. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:25:10,829][613581] Avg episode reward: [(0, '4140.110')] [2023-03-09 03:25:10,914][613885] Updated weights for policy 0, policy_version 38560 (0.0005) [2023-03-09 03:25:14,859][613885] Updated weights for policy 0, policy_version 38640 (0.0005) [2023-03-09 03:25:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10469.1). Total num frames: 19791872. Throughput: 0: 10403.0. Samples: 19779256. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:25:15,829][613581] Avg episode reward: [(0, '3858.382')] [2023-03-09 03:25:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000038656_19791872.pth... [2023-03-09 03:25:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000038040_19476480.pth [2023-03-09 03:25:18,951][613885] Updated weights for policy 0, policy_version 38720 (0.0005) [2023-03-09 03:25:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10455.2). Total num frames: 19841024. Throughput: 0: 10436.6. Samples: 19839996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:25:20,829][613581] Avg episode reward: [(0, '4211.652')] [2023-03-09 03:25:22,858][613885] Updated weights for policy 0, policy_version 38800 (0.0005) [2023-03-09 03:25:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 10469.1). Total num frames: 19894272. Throughput: 0: 10425.1. Samples: 19870684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:25:25,829][613581] Avg episode reward: [(0, '4298.290')] [2023-03-09 03:25:26,494][613885] Updated weights for policy 0, policy_version 38880 (0.0004) [2023-03-09 03:25:30,415][613885] Updated weights for policy 0, policy_version 38960 (0.0005) [2023-03-09 03:25:30,829][613581] Fps is (10 sec: 11059.0, 60 sec: 10444.8, 300 sec: 10483.0). Total num frames: 19951616. Throughput: 0: 10488.4. Samples: 19936468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:25:30,830][613581] Avg episode reward: [(0, '4154.589')] [2023-03-09 03:25:30,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000038968_19951616.pth... [2023-03-09 03:25:30,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000038352_19636224.pth [2023-03-09 03:25:34,571][613885] Updated weights for policy 0, policy_version 39040 (0.0005) [2023-03-09 03:25:35,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10469.1). Total num frames: 20000768. Throughput: 0: 10409.8. Samples: 19996684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:25:35,829][613581] Avg episode reward: [(0, '4375.796')] [2023-03-09 03:25:38,736][613885] Updated weights for policy 0, policy_version 39120 (0.0005) [2023-03-09 03:25:40,829][613581] Fps is (10 sec: 9421.0, 60 sec: 10376.5, 300 sec: 10441.3). Total num frames: 20045824. Throughput: 0: 10335.4. Samples: 20025552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:25:40,829][613581] Avg episode reward: [(0, '4095.497')] [2023-03-09 03:25:43,064][613885] Updated weights for policy 0, policy_version 39200 (0.0005) [2023-03-09 03:25:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 10441.3). Total num frames: 20099072. Throughput: 0: 10205.5. Samples: 20083556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:25:45,829][613581] Avg episode reward: [(0, '4324.897')] [2023-03-09 03:25:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000039256_20099072.pth... [2023-03-09 03:25:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000038656_19791872.pth [2023-03-09 03:25:46,971][613885] Updated weights for policy 0, policy_version 39280 (0.0004) [2023-03-09 03:25:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10427.4). Total num frames: 20148224. Throughput: 0: 10254.1. Samples: 20146876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:25:50,829][613581] Avg episode reward: [(0, '4234.991')] [2023-03-09 03:25:51,064][613885] Updated weights for policy 0, policy_version 39360 (0.0004) [2023-03-09 03:25:55,103][613885] Updated weights for policy 0, policy_version 39440 (0.0005) [2023-03-09 03:25:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.7, 300 sec: 10413.6). Total num frames: 20197376. Throughput: 0: 10174.2. Samples: 20175824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:25:55,829][613581] Avg episode reward: [(0, '4194.421')] [2023-03-09 03:25:59,027][613885] Updated weights for policy 0, policy_version 39520 (0.0005) [2023-03-09 03:26:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10399.7). Total num frames: 20250624. Throughput: 0: 10203.4. Samples: 20238408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:26:00,830][613581] Avg episode reward: [(0, '4096.015')] [2023-03-09 03:26:00,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000039552_20250624.pth... [2023-03-09 03:26:00,838][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000038968_19951616.pth [2023-03-09 03:26:02,899][613885] Updated weights for policy 0, policy_version 39600 (0.0004) [2023-03-09 03:26:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.8, 300 sec: 10385.8). Total num frames: 20299776. Throughput: 0: 10216.5. Samples: 20299736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:26:05,829][613581] Avg episode reward: [(0, '4285.834')] [2023-03-09 03:26:07,088][613885] Updated weights for policy 0, policy_version 39680 (0.0005) [2023-03-09 03:26:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10371.9). Total num frames: 20353024. Throughput: 0: 10187.6. Samples: 20329128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:26:10,829][613581] Avg episode reward: [(0, '4387.637')] [2023-03-09 03:26:11,088][613885] Updated weights for policy 0, policy_version 39760 (0.0004) [2023-03-09 03:26:15,403][613885] Updated weights for policy 0, policy_version 39840 (0.0004) [2023-03-09 03:26:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 10358.0). Total num frames: 20402176. Throughput: 0: 10070.2. Samples: 20389628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:26:15,829][613581] Avg episode reward: [(0, '4354.940')] [2023-03-09 03:26:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000039848_20402176.pth... [2023-03-09 03:26:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000039256_20099072.pth [2023-03-09 03:26:19,446][613885] Updated weights for policy 0, policy_version 39920 (0.0004) [2023-03-09 03:26:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.7, 300 sec: 10344.1). Total num frames: 20451328. Throughput: 0: 10029.2. Samples: 20447996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:26:20,829][613581] Avg episode reward: [(0, '4494.939')] [2023-03-09 03:26:20,830][613841] Saving new best policy, reward=4494.939! [2023-03-09 03:26:23,416][613885] Updated weights for policy 0, policy_version 40000 (0.0004) [2023-03-09 03:26:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10344.1). Total num frames: 20504576. Throughput: 0: 10096.2. Samples: 20479880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:26:25,829][613581] Avg episode reward: [(0, '4379.681')] [2023-03-09 03:26:27,343][613885] Updated weights for policy 0, policy_version 40080 (0.0005) [2023-03-09 03:26:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 10330.2). Total num frames: 20553728. Throughput: 0: 10175.2. Samples: 20541440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:26:30,829][613581] Avg episode reward: [(0, '4493.203')] [2023-03-09 03:26:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000040144_20553728.pth... [2023-03-09 03:26:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000039552_20250624.pth [2023-03-09 03:26:31,489][613885] Updated weights for policy 0, policy_version 40160 (0.0004) [2023-03-09 03:26:35,652][613885] Updated weights for policy 0, policy_version 40240 (0.0005) [2023-03-09 03:26:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 10330.2). Total num frames: 20602880. Throughput: 0: 10071.5. Samples: 20600092. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:26:35,829][613581] Avg episode reward: [(0, '4312.770')] [2023-03-09 03:26:39,773][613885] Updated weights for policy 0, policy_version 40320 (0.0005) [2023-03-09 03:26:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10103.5, 300 sec: 10316.4). Total num frames: 20652032. Throughput: 0: 10100.7. Samples: 20630356. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:26:40,829][613581] Avg episode reward: [(0, '4058.352')] [2023-03-09 03:26:43,967][613885] Updated weights for policy 0, policy_version 40400 (0.0005) [2023-03-09 03:26:45,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10316.4). Total num frames: 20701184. Throughput: 0: 10010.4. Samples: 20688872. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:26:45,829][613581] Avg episode reward: [(0, '4417.370')] [2023-03-09 03:26:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000040432_20701184.pth... [2023-03-09 03:26:45,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000039848_20402176.pth [2023-03-09 03:26:48,286][613885] Updated weights for policy 0, policy_version 40480 (0.0004) [2023-03-09 03:26:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 10302.5). Total num frames: 20750336. Throughput: 0: 9922.6. Samples: 20746256. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:26:50,829][613581] Avg episode reward: [(0, '4344.217')] [2023-03-09 03:26:52,341][613885] Updated weights for policy 0, policy_version 40560 (0.0005) [2023-03-09 03:26:55,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10035.2, 300 sec: 10302.5). Total num frames: 20799488. Throughput: 0: 9937.9. Samples: 20776332. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:26:55,829][613581] Avg episode reward: [(0, '4141.541')] [2023-03-09 03:26:56,317][613885] Updated weights for policy 0, policy_version 40640 (0.0005) [2023-03-09 03:27:00,512][613885] Updated weights for policy 0, policy_version 40720 (0.0005) [2023-03-09 03:27:00,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9967.0, 300 sec: 10302.5). Total num frames: 20848640. Throughput: 0: 9958.9. Samples: 20837776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:27:00,829][613581] Avg episode reward: [(0, '4245.439')] [2023-03-09 03:27:00,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000040720_20848640.pth... [2023-03-09 03:27:00,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000040144_20553728.pth [2023-03-09 03:27:04,736][613885] Updated weights for policy 0, policy_version 40800 (0.0005) [2023-03-09 03:27:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10288.6). Total num frames: 20897792. Throughput: 0: 9942.8. Samples: 20895420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:27:05,829][613581] Avg episode reward: [(0, '4519.250')] [2023-03-09 03:27:05,830][613841] Saving new best policy, reward=4519.250! [2023-03-09 03:27:09,221][613885] Updated weights for policy 0, policy_version 40880 (0.0005) [2023-03-09 03:27:10,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9898.7, 300 sec: 10288.6). Total num frames: 20946944. Throughput: 0: 9834.5. Samples: 20922432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:27:10,829][613581] Avg episode reward: [(0, '4472.243')] [2023-03-09 03:27:13,350][613885] Updated weights for policy 0, policy_version 40960 (0.0005) [2023-03-09 03:27:15,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9830.4, 300 sec: 10246.9). Total num frames: 20992000. Throughput: 0: 9761.8. Samples: 20980720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:27:15,829][613581] Avg episode reward: [(0, '4475.043')] [2023-03-09 03:27:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000041000_20992000.pth... [2023-03-09 03:27:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000040432_20701184.pth [2023-03-09 03:27:17,634][613885] Updated weights for policy 0, policy_version 41040 (0.0004) [2023-03-09 03:27:20,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9830.4, 300 sec: 10233.1). Total num frames: 21041152. Throughput: 0: 9711.8. Samples: 21037120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:27:20,829][613581] Avg episode reward: [(0, '4353.756')] [2023-03-09 03:27:22,090][613885] Updated weights for policy 0, policy_version 41120 (0.0005) [2023-03-09 03:27:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 10219.2). Total num frames: 21090304. Throughput: 0: 9699.5. Samples: 21066832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:27:25,829][613581] Avg episode reward: [(0, '4080.278')] [2023-03-09 03:27:26,198][613885] Updated weights for policy 0, policy_version 41200 (0.0005) [2023-03-09 03:27:30,469][613885] Updated weights for policy 0, policy_version 41280 (0.0005) [2023-03-09 03:27:30,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9693.9, 300 sec: 10205.3). Total num frames: 21135360. Throughput: 0: 9648.9. Samples: 21123072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:27:30,829][613581] Avg episode reward: [(0, '4082.616')] [2023-03-09 03:27:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000041280_21135360.pth... [2023-03-09 03:27:30,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000040720_20848640.pth [2023-03-09 03:27:34,683][613885] Updated weights for policy 0, policy_version 41360 (0.0005) [2023-03-09 03:27:35,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9693.9, 300 sec: 10205.3). Total num frames: 21184512. Throughput: 0: 9734.7. Samples: 21184316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:27:35,829][613581] Avg episode reward: [(0, '4446.128')] [2023-03-09 03:27:38,940][613885] Updated weights for policy 0, policy_version 41440 (0.0005) [2023-03-09 03:27:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 10205.3). Total num frames: 21233664. Throughput: 0: 9703.6. Samples: 21212992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:27:40,829][613581] Avg episode reward: [(0, '4462.363')] [2023-03-09 03:27:43,171][613885] Updated weights for policy 0, policy_version 41520 (0.0005) [2023-03-09 03:27:45,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9693.8, 300 sec: 10191.4). Total num frames: 21282816. Throughput: 0: 9607.0. Samples: 21270092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:27:45,829][613581] Avg episode reward: [(0, '4191.360')] [2023-03-09 03:27:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000041568_21282816.pth... [2023-03-09 03:27:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000041000_20992000.pth [2023-03-09 03:27:47,482][613885] Updated weights for policy 0, policy_version 41600 (0.0004) [2023-03-09 03:27:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 10177.5). Total num frames: 21327872. Throughput: 0: 9609.2. Samples: 21327832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:27:50,829][613581] Avg episode reward: [(0, '3939.135')] [2023-03-09 03:27:51,664][613885] Updated weights for policy 0, policy_version 41680 (0.0005) [2023-03-09 03:27:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 10163.6). Total num frames: 21377024. Throughput: 0: 9645.7. Samples: 21356488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:27:55,829][613581] Avg episode reward: [(0, '4450.943')] [2023-03-09 03:27:56,035][613885] Updated weights for policy 0, policy_version 41760 (0.0005) [2023-03-09 03:28:00,269][613885] Updated weights for policy 0, policy_version 41840 (0.0005) [2023-03-09 03:28:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 10163.6). Total num frames: 21426176. Throughput: 0: 9626.0. Samples: 21413888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:28:00,829][613581] Avg episode reward: [(0, '4317.774')] [2023-03-09 03:28:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000041848_21426176.pth... [2023-03-09 03:28:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000041280_21135360.pth [2023-03-09 03:28:04,251][613885] Updated weights for policy 0, policy_version 41920 (0.0005) [2023-03-09 03:28:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 10149.7). Total num frames: 21475328. Throughput: 0: 9707.1. Samples: 21473940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:28:05,829][613581] Avg episode reward: [(0, '4457.237')] [2023-03-09 03:28:08,579][613885] Updated weights for policy 0, policy_version 42000 (0.0005) [2023-03-09 03:28:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 10135.9). Total num frames: 21524480. Throughput: 0: 9697.7. Samples: 21503228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:28:10,829][613581] Avg episode reward: [(0, '4473.870')] [2023-03-09 03:28:12,904][613885] Updated weights for policy 0, policy_version 42080 (0.0005) [2023-03-09 03:28:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 10122.0). Total num frames: 21573632. Throughput: 0: 9716.6. Samples: 21560320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:28:15,830][613581] Avg episode reward: [(0, '4425.796')] [2023-03-09 03:28:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000042136_21573632.pth... [2023-03-09 03:28:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000041568_21282816.pth [2023-03-09 03:28:17,031][613885] Updated weights for policy 0, policy_version 42160 (0.0005) [2023-03-09 03:28:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.8, 300 sec: 10108.1). Total num frames: 21622784. Throughput: 0: 9654.1. Samples: 21618752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:28:20,829][613581] Avg episode reward: [(0, '4431.875')] [2023-03-09 03:28:21,101][613885] Updated weights for policy 0, policy_version 42240 (0.0005) [2023-03-09 03:28:25,330][613885] Updated weights for policy 0, policy_version 42320 (0.0005) [2023-03-09 03:28:25,829][613581] Fps is (10 sec: 9830.6, 60 sec: 9693.9, 300 sec: 10094.2). Total num frames: 21671936. Throughput: 0: 9654.0. Samples: 21647424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:28:25,829][613581] Avg episode reward: [(0, '4416.264')] [2023-03-09 03:28:29,808][613885] Updated weights for policy 0, policy_version 42400 (0.0005) [2023-03-09 03:28:30,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9693.8, 300 sec: 10066.4). Total num frames: 21716992. Throughput: 0: 9657.3. Samples: 21704672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:28:30,830][613581] Avg episode reward: [(0, '4445.000')] [2023-03-09 03:28:30,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000042416_21716992.pth... [2023-03-09 03:28:30,838][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000041848_21426176.pth [2023-03-09 03:28:34,188][613885] Updated weights for policy 0, policy_version 42480 (0.0005) [2023-03-09 03:28:35,829][613581] Fps is (10 sec: 9011.1, 60 sec: 9625.6, 300 sec: 10038.7). Total num frames: 21762048. Throughput: 0: 9638.1. Samples: 21761548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:28:35,829][613581] Avg episode reward: [(0, '4437.943')] [2023-03-09 03:28:38,252][613885] Updated weights for policy 0, policy_version 42560 (0.0005) [2023-03-09 03:28:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 10038.7). Total num frames: 21815296. Throughput: 0: 9676.2. Samples: 21791916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:28:40,829][613581] Avg episode reward: [(0, '4433.130')] [2023-03-09 03:28:42,503][613885] Updated weights for policy 0, policy_version 42640 (0.0005) [2023-03-09 03:28:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9693.9, 300 sec: 10038.7). Total num frames: 21864448. Throughput: 0: 9733.0. Samples: 21851876. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:28:45,829][613581] Avg episode reward: [(0, '4425.074')] [2023-03-09 03:28:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000042704_21864448.pth... [2023-03-09 03:28:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000042136_21573632.pth [2023-03-09 03:28:46,526][613885] Updated weights for policy 0, policy_version 42720 (0.0005) [2023-03-09 03:28:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.8, 300 sec: 10010.9). Total num frames: 21909504. Throughput: 0: 9650.9. Samples: 21908232. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:28:50,829][613581] Avg episode reward: [(0, '4520.126')] [2023-03-09 03:28:50,830][613841] Saving new best policy, reward=4520.126! [2023-03-09 03:28:51,011][613885] Updated weights for policy 0, policy_version 42800 (0.0006) [2023-03-09 03:28:55,414][613885] Updated weights for policy 0, policy_version 42880 (0.0004) [2023-03-09 03:28:55,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9625.6, 300 sec: 9969.2). Total num frames: 21954560. Throughput: 0: 9621.9. Samples: 21936212. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:28:55,829][613581] Avg episode reward: [(0, '4530.129')] [2023-03-09 03:28:55,874][613841] Saving new best policy, reward=4530.129! [2023-03-09 03:28:59,416][613885] Updated weights for policy 0, policy_version 42960 (0.0005) [2023-03-09 03:29:00,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9969.3). Total num frames: 22007808. Throughput: 0: 9671.1. Samples: 21995520. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:29:00,829][613581] Avg episode reward: [(0, '4547.050')] [2023-03-09 03:29:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000042984_22007808.pth... [2023-03-09 03:29:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000042416_21716992.pth [2023-03-09 03:29:00,835][613841] Saving new best policy, reward=4547.050! [2023-03-09 03:29:03,593][613885] Updated weights for policy 0, policy_version 43040 (0.0005) [2023-03-09 03:29:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9927.6). Total num frames: 22052864. Throughput: 0: 9645.9. Samples: 22052816. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:29:05,829][613581] Avg episode reward: [(0, '4543.672')] [2023-03-09 03:29:08,024][613885] Updated weights for policy 0, policy_version 43120 (0.0006) [2023-03-09 03:29:10,829][613581] Fps is (10 sec: 9420.6, 60 sec: 9625.6, 300 sec: 9927.6). Total num frames: 22102016. Throughput: 0: 9638.8. Samples: 22081172. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:29:10,830][613581] Avg episode reward: [(0, '4502.143')] [2023-03-09 03:29:12,454][613885] Updated weights for policy 0, policy_version 43200 (0.0005) [2023-03-09 03:29:15,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9557.3, 300 sec: 9913.7). Total num frames: 22147072. Throughput: 0: 9580.5. Samples: 22135792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:29:15,829][613581] Avg episode reward: [(0, '4411.762')] [2023-03-09 03:29:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000043256_22147072.pth... [2023-03-09 03:29:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000042704_21864448.pth [2023-03-09 03:29:16,821][613885] Updated weights for policy 0, policy_version 43280 (0.0005) [2023-03-09 03:29:20,829][613581] Fps is (10 sec: 9011.4, 60 sec: 9489.1, 300 sec: 9899.8). Total num frames: 22192128. Throughput: 0: 9567.6. Samples: 22192088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:29:20,829][613581] Avg episode reward: [(0, '4089.210')] [2023-03-09 03:29:21,404][613885] Updated weights for policy 0, policy_version 43360 (0.0005) [2023-03-09 03:29:25,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9420.8, 300 sec: 9872.1). Total num frames: 22237184. Throughput: 0: 9469.5. Samples: 22218044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:29:25,829][613581] Avg episode reward: [(0, '4525.363')] [2023-03-09 03:29:25,962][613885] Updated weights for policy 0, policy_version 43440 (0.0004) [2023-03-09 03:29:30,125][613885] Updated weights for policy 0, policy_version 43520 (0.0005) [2023-03-09 03:29:30,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9489.1, 300 sec: 9872.1). Total num frames: 22286336. Throughput: 0: 9383.8. Samples: 22274148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:29:30,829][613581] Avg episode reward: [(0, '4487.151')] [2023-03-09 03:29:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000043528_22286336.pth... [2023-03-09 03:29:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000042984_22007808.pth [2023-03-09 03:29:34,448][613885] Updated weights for policy 0, policy_version 43600 (0.0005) [2023-03-09 03:29:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9858.2). Total num frames: 22331392. Throughput: 0: 9403.6. Samples: 22331392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:29:35,829][613581] Avg episode reward: [(0, '4491.993')] [2023-03-09 03:29:39,014][613885] Updated weights for policy 0, policy_version 43680 (0.0005) [2023-03-09 03:29:40,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 9830.4). Total num frames: 22376448. Throughput: 0: 9412.2. Samples: 22359760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:29:40,829][613581] Avg episode reward: [(0, '4544.369')] [2023-03-09 03:29:43,547][613885] Updated weights for policy 0, policy_version 43760 (0.0005) [2023-03-09 03:29:45,829][613581] Fps is (10 sec: 9011.1, 60 sec: 9284.3, 300 sec: 9802.6). Total num frames: 22421504. Throughput: 0: 9277.6. Samples: 22413012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:29:45,829][613581] Avg episode reward: [(0, '4557.166')] [2023-03-09 03:29:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000043792_22421504.pth... [2023-03-09 03:29:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000043256_22147072.pth [2023-03-09 03:29:45,835][613841] Saving new best policy, reward=4557.166! [2023-03-09 03:29:48,229][613885] Updated weights for policy 0, policy_version 43840 (0.0004) [2023-03-09 03:29:50,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9761.0). Total num frames: 22466560. Throughput: 0: 9146.5. Samples: 22464408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:29:50,829][613581] Avg episode reward: [(0, '4555.782')] [2023-03-09 03:29:52,914][613885] Updated weights for policy 0, policy_version 43920 (0.0005) [2023-03-09 03:29:55,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9284.3, 300 sec: 9747.1). Total num frames: 22511616. Throughput: 0: 9111.8. Samples: 22491200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:29:55,829][613581] Avg episode reward: [(0, '4549.109')] [2023-03-09 03:29:57,412][613885] Updated weights for policy 0, policy_version 44000 (0.0005) [2023-03-09 03:30:00,829][613581] Fps is (10 sec: 9011.1, 60 sec: 9147.7, 300 sec: 9719.3). Total num frames: 22556672. Throughput: 0: 9119.6. Samples: 22546172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:30:00,829][613581] Avg episode reward: [(0, '4532.882')] [2023-03-09 03:30:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000044056_22556672.pth... [2023-03-09 03:30:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000043528_22286336.pth [2023-03-09 03:30:01,975][613885] Updated weights for policy 0, policy_version 44080 (0.0005) [2023-03-09 03:30:05,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9147.7, 300 sec: 9705.4). Total num frames: 22601728. Throughput: 0: 9028.4. Samples: 22598364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:30:05,829][613581] Avg episode reward: [(0, '4489.074')] [2023-03-09 03:30:06,667][613885] Updated weights for policy 0, policy_version 44160 (0.0005) [2023-03-09 03:30:10,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9677.7). Total num frames: 22646784. Throughput: 0: 9083.9. Samples: 22626820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:30:10,829][613581] Avg episode reward: [(0, '4501.166')] [2023-03-09 03:30:10,891][613885] Updated weights for policy 0, policy_version 44240 (0.0005) [2023-03-09 03:30:15,403][613885] Updated weights for policy 0, policy_version 44320 (0.0005) [2023-03-09 03:30:15,829][613581] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9663.8). Total num frames: 22691840. Throughput: 0: 9093.2. Samples: 22683340. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:30:15,829][613581] Avg episode reward: [(0, '4535.099')] [2023-03-09 03:30:15,864][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000044328_22695936.pth... [2023-03-09 03:30:15,866][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000043792_22421504.pth [2023-03-09 03:30:19,991][613885] Updated weights for policy 0, policy_version 44400 (0.0005) [2023-03-09 03:30:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 9649.9). Total num frames: 22740992. Throughput: 0: 9012.6. Samples: 22736960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:30:20,829][613581] Avg episode reward: [(0, '4548.207')] [2023-03-09 03:30:24,417][613885] Updated weights for policy 0, policy_version 44480 (0.0005) [2023-03-09 03:30:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 9608.2). Total num frames: 22786048. Throughput: 0: 9012.1. Samples: 22765304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:30:25,829][613581] Avg episode reward: [(0, '4407.180')] [2023-03-09 03:30:28,453][613885] Updated weights for policy 0, policy_version 44560 (0.0005) [2023-03-09 03:30:30,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9147.7, 300 sec: 9608.2). Total num frames: 22835200. Throughput: 0: 9110.5. Samples: 22822984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:30:30,829][613581] Avg episode reward: [(0, '3768.441')] [2023-03-09 03:30:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000044600_22835200.pth... [2023-03-09 03:30:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000044056_22556672.pth [2023-03-09 03:30:32,844][613885] Updated weights for policy 0, policy_version 44640 (0.0005) [2023-03-09 03:30:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9216.0, 300 sec: 9622.1). Total num frames: 22884352. Throughput: 0: 9251.0. Samples: 22880704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:30:35,829][613581] Avg episode reward: [(0, '4346.507')] [2023-03-09 03:30:36,906][613885] Updated weights for policy 0, policy_version 44720 (0.0005) [2023-03-09 03:30:40,829][613581] Fps is (10 sec: 9421.0, 60 sec: 9216.0, 300 sec: 9594.4). Total num frames: 22929408. Throughput: 0: 9288.6. Samples: 22909184. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:30:40,829][613581] Avg episode reward: [(0, '4421.922')] [2023-03-09 03:30:41,282][613885] Updated weights for policy 0, policy_version 44800 (0.0005) [2023-03-09 03:30:45,245][613885] Updated weights for policy 0, policy_version 44880 (0.0005) [2023-03-09 03:30:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9352.5, 300 sec: 9608.2). Total num frames: 22982656. Throughput: 0: 9428.0. Samples: 22970432. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:30:45,829][613581] Avg episode reward: [(0, '4315.506')] [2023-03-09 03:30:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000044888_22982656.pth... [2023-03-09 03:30:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000044328_22695936.pth [2023-03-09 03:30:49,674][613885] Updated weights for policy 0, policy_version 44960 (0.0005) [2023-03-09 03:30:50,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9420.8, 300 sec: 9608.2). Total num frames: 23031808. Throughput: 0: 9523.7. Samples: 23026932. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:30:50,829][613581] Avg episode reward: [(0, '4323.394')] [2023-03-09 03:30:53,495][613885] Updated weights for policy 0, policy_version 45040 (0.0005) [2023-03-09 03:30:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9489.1, 300 sec: 9594.4). Total num frames: 23080960. Throughput: 0: 9608.0. Samples: 23059180. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:30:55,829][613581] Avg episode reward: [(0, '4157.865')] [2023-03-09 03:30:57,801][613885] Updated weights for policy 0, policy_version 45120 (0.0005) [2023-03-09 03:31:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9594.4). Total num frames: 23130112. Throughput: 0: 9651.6. Samples: 23117660. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:31:00,829][613581] Avg episode reward: [(0, '4434.104')] [2023-03-09 03:31:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000045176_23130112.pth... [2023-03-09 03:31:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000044600_22835200.pth [2023-03-09 03:31:02,109][613885] Updated weights for policy 0, policy_version 45200 (0.0005) [2023-03-09 03:31:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9566.6). Total num frames: 23175168. Throughput: 0: 9708.3. Samples: 23173832. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:31:05,829][613581] Avg episode reward: [(0, '4198.424')] [2023-03-09 03:31:06,468][613885] Updated weights for policy 0, policy_version 45280 (0.0005) [2023-03-09 03:31:10,502][613885] Updated weights for policy 0, policy_version 45360 (0.0004) [2023-03-09 03:31:10,829][613581] Fps is (10 sec: 9421.0, 60 sec: 9625.6, 300 sec: 9566.6). Total num frames: 23224320. Throughput: 0: 9751.7. Samples: 23204128. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:31:10,829][613581] Avg episode reward: [(0, '4157.016')] [2023-03-09 03:31:15,025][613885] Updated weights for policy 0, policy_version 45440 (0.0005) [2023-03-09 03:31:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9552.7). Total num frames: 23269376. Throughput: 0: 9709.2. Samples: 23259896. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:31:15,829][613581] Avg episode reward: [(0, '4336.819')] [2023-03-09 03:31:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000045448_23269376.pth... [2023-03-09 03:31:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000044888_22982656.pth [2023-03-09 03:31:19,638][613885] Updated weights for policy 0, policy_version 45520 (0.0005) [2023-03-09 03:31:20,829][613581] Fps is (10 sec: 9011.1, 60 sec: 9557.3, 300 sec: 9524.9). Total num frames: 23314432. Throughput: 0: 9607.8. Samples: 23313056. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:31:20,829][613581] Avg episode reward: [(0, '4336.536')] [2023-03-09 03:31:24,193][613885] Updated weights for policy 0, policy_version 45600 (0.0004) [2023-03-09 03:31:25,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9557.3, 300 sec: 9511.1). Total num frames: 23359488. Throughput: 0: 9570.1. Samples: 23339840. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:31:25,829][613581] Avg episode reward: [(0, '4258.071')] [2023-03-09 03:31:28,585][613885] Updated weights for policy 0, policy_version 45680 (0.0005) [2023-03-09 03:31:30,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9489.1, 300 sec: 9497.2). Total num frames: 23404544. Throughput: 0: 9462.1. Samples: 23396224. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:31:30,829][613581] Avg episode reward: [(0, '4472.421')] [2023-03-09 03:31:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000045712_23404544.pth... [2023-03-09 03:31:30,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000045176_23130112.pth [2023-03-09 03:31:33,063][613885] Updated weights for policy 0, policy_version 45760 (0.0006) [2023-03-09 03:31:35,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9420.8, 300 sec: 9483.3). Total num frames: 23449600. Throughput: 0: 9389.1. Samples: 23449440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:31:35,829][613581] Avg episode reward: [(0, '4506.882')] [2023-03-09 03:31:37,846][613885] Updated weights for policy 0, policy_version 45840 (0.0005) [2023-03-09 03:31:40,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9420.8, 300 sec: 9469.4). Total num frames: 23494656. Throughput: 0: 9254.5. Samples: 23475632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:31:40,829][613581] Avg episode reward: [(0, '4166.670')] [2023-03-09 03:31:42,278][613885] Updated weights for policy 0, policy_version 45920 (0.0004) [2023-03-09 03:31:45,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9455.5). Total num frames: 23539712. Throughput: 0: 9163.6. Samples: 23530020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:31:45,829][613581] Avg episode reward: [(0, '4342.536')] [2023-03-09 03:31:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000045976_23539712.pth... [2023-03-09 03:31:45,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000045448_23269376.pth [2023-03-09 03:31:46,638][613885] Updated weights for policy 0, policy_version 46000 (0.0005) [2023-03-09 03:31:50,787][613885] Updated weights for policy 0, policy_version 46080 (0.0005) [2023-03-09 03:31:50,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9352.6, 300 sec: 9469.4). Total num frames: 23592960. Throughput: 0: 9222.2. Samples: 23588828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:31:50,829][613581] Avg episode reward: [(0, '4379.921')] [2023-03-09 03:31:55,137][613885] Updated weights for policy 0, policy_version 46160 (0.0005) [2023-03-09 03:31:55,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9284.3, 300 sec: 9455.5). Total num frames: 23638016. Throughput: 0: 9193.7. Samples: 23617848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:31:55,830][613581] Avg episode reward: [(0, '3886.452')] [2023-03-09 03:31:59,654][613885] Updated weights for policy 0, policy_version 46240 (0.0005) [2023-03-09 03:32:00,829][613581] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 9441.6). Total num frames: 23683072. Throughput: 0: 9168.5. Samples: 23672480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:32:00,829][613581] Avg episode reward: [(0, '3765.910')] [2023-03-09 03:32:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000046256_23683072.pth... [2023-03-09 03:32:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000045712_23404544.pth [2023-03-09 03:32:03,924][613885] Updated weights for policy 0, policy_version 46320 (0.0005) [2023-03-09 03:32:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9441.6). Total num frames: 23732224. Throughput: 0: 9227.9. Samples: 23728312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:32:05,829][613581] Avg episode reward: [(0, '3525.506')] [2023-03-09 03:32:08,016][613885] Updated weights for policy 0, policy_version 46400 (0.0005) [2023-03-09 03:32:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9284.3, 300 sec: 9455.5). Total num frames: 23781376. Throughput: 0: 9358.4. Samples: 23760968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:32:10,829][613581] Avg episode reward: [(0, '4272.388')] [2023-03-09 03:32:12,460][613885] Updated weights for policy 0, policy_version 46480 (0.0005) [2023-03-09 03:32:15,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9441.6). Total num frames: 23826432. Throughput: 0: 9307.4. Samples: 23815056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:32:15,829][613581] Avg episode reward: [(0, '4195.996')] [2023-03-09 03:32:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000046536_23826432.pth... [2023-03-09 03:32:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000045976_23539712.pth [2023-03-09 03:32:16,960][613885] Updated weights for policy 0, policy_version 46560 (0.0005) [2023-03-09 03:32:20,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9284.3, 300 sec: 9427.7). Total num frames: 23871488. Throughput: 0: 9378.3. Samples: 23871464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:32:20,829][613581] Avg episode reward: [(0, '4079.510')] [2023-03-09 03:32:21,186][613885] Updated weights for policy 0, policy_version 46640 (0.0005) [2023-03-09 03:32:25,398][613885] Updated weights for policy 0, policy_version 46720 (0.0005) [2023-03-09 03:32:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9420.8, 300 sec: 9455.5). Total num frames: 23924736. Throughput: 0: 9442.2. Samples: 23900532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:32:25,829][613581] Avg episode reward: [(0, '3716.529')] [2023-03-09 03:32:29,658][613885] Updated weights for policy 0, policy_version 46800 (0.0004) [2023-03-09 03:32:30,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9420.8, 300 sec: 9441.6). Total num frames: 23969792. Throughput: 0: 9549.4. Samples: 23959744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:32:30,829][613581] Avg episode reward: [(0, '3685.089')] [2023-03-09 03:32:30,873][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000046824_23973888.pth... [2023-03-09 03:32:30,875][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000046256_23683072.pth [2023-03-09 03:32:33,679][613885] Updated weights for policy 0, policy_version 46880 (0.0005) [2023-03-09 03:32:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9441.6). Total num frames: 24018944. Throughput: 0: 9538.4. Samples: 24018056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:32:35,829][613581] Avg episode reward: [(0, '4147.558')] [2023-03-09 03:32:38,113][613885] Updated weights for policy 0, policy_version 46960 (0.0005) [2023-03-09 03:32:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9441.6). Total num frames: 24068096. Throughput: 0: 9533.7. Samples: 24046864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:32:40,829][613581] Avg episode reward: [(0, '4408.152')] [2023-03-09 03:32:42,459][613885] Updated weights for policy 0, policy_version 47040 (0.0005) [2023-03-09 03:32:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9441.6). Total num frames: 24113152. Throughput: 0: 9586.5. Samples: 24103872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:32:45,829][613581] Avg episode reward: [(0, '4383.537')] [2023-03-09 03:32:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000047104_24117248.pth... [2023-03-09 03:32:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000046536_23826432.pth [2023-03-09 03:32:46,707][613885] Updated weights for policy 0, policy_version 47120 (0.0005) [2023-03-09 03:32:50,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9489.1, 300 sec: 9441.6). Total num frames: 24162304. Throughput: 0: 9584.3. Samples: 24159604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:32:50,829][613581] Avg episode reward: [(0, '4082.681')] [2023-03-09 03:32:51,086][613885] Updated weights for policy 0, policy_version 47200 (0.0005) [2023-03-09 03:32:55,389][613885] Updated weights for policy 0, policy_version 47280 (0.0005) [2023-03-09 03:32:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9427.7). Total num frames: 24207360. Throughput: 0: 9521.5. Samples: 24189436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:32:55,829][613581] Avg episode reward: [(0, '4559.633')] [2023-03-09 03:32:55,866][613841] Saving new best policy, reward=4559.633! [2023-03-09 03:32:59,860][613885] Updated weights for policy 0, policy_version 47360 (0.0004) [2023-03-09 03:33:00,829][613581] Fps is (10 sec: 9420.6, 60 sec: 9557.3, 300 sec: 9427.7). Total num frames: 24256512. Throughput: 0: 9538.5. Samples: 24244288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:33:00,829][613581] Avg episode reward: [(0, '4492.484')] [2023-03-09 03:33:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000047376_24256512.pth... [2023-03-09 03:33:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000046824_23973888.pth [2023-03-09 03:33:04,496][613885] Updated weights for policy 0, policy_version 47440 (0.0005) [2023-03-09 03:33:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9413.9). Total num frames: 24301568. Throughput: 0: 9481.4. Samples: 24298128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:33:05,829][613581] Avg episode reward: [(0, '4494.113')] [2023-03-09 03:33:08,781][613885] Updated weights for policy 0, policy_version 47520 (0.0005) [2023-03-09 03:33:10,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9489.1, 300 sec: 9413.9). Total num frames: 24350720. Throughput: 0: 9458.3. Samples: 24326156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:33:10,829][613581] Avg episode reward: [(0, '4548.221')] [2023-03-09 03:33:12,966][613885] Updated weights for policy 0, policy_version 47600 (0.0005) [2023-03-09 03:33:15,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9489.1, 300 sec: 9400.0). Total num frames: 24395776. Throughput: 0: 9418.0. Samples: 24383552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:33:15,829][613581] Avg episode reward: [(0, '4554.287')] [2023-03-09 03:33:15,869][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000047656_24399872.pth... [2023-03-09 03:33:15,872][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000047104_24117248.pth [2023-03-09 03:33:17,312][613885] Updated weights for policy 0, policy_version 47680 (0.0005) [2023-03-09 03:33:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9400.0). Total num frames: 24444928. Throughput: 0: 9395.2. Samples: 24440840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:33:20,829][613581] Avg episode reward: [(0, '4502.813')] [2023-03-09 03:33:21,542][613885] Updated weights for policy 0, policy_version 47760 (0.0005) [2023-03-09 03:33:25,599][613885] Updated weights for policy 0, policy_version 47840 (0.0005) [2023-03-09 03:33:25,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9489.1, 300 sec: 9413.9). Total num frames: 24494080. Throughput: 0: 9443.8. Samples: 24471836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:33:25,829][613581] Avg episode reward: [(0, '4514.464')] [2023-03-09 03:33:29,954][613885] Updated weights for policy 0, policy_version 47920 (0.0005) [2023-03-09 03:33:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9427.7). Total num frames: 24543232. Throughput: 0: 9480.7. Samples: 24530504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:33:30,829][613581] Avg episode reward: [(0, '4477.141')] [2023-03-09 03:33:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000047936_24543232.pth... [2023-03-09 03:33:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000047376_24256512.pth [2023-03-09 03:33:33,929][613885] Updated weights for policy 0, policy_version 48000 (0.0005) [2023-03-09 03:33:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9413.9). Total num frames: 24592384. Throughput: 0: 9548.2. Samples: 24589272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:33:35,829][613581] Avg episode reward: [(0, '4433.181')] [2023-03-09 03:33:38,321][613885] Updated weights for policy 0, policy_version 48080 (0.0005) [2023-03-09 03:33:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9557.4, 300 sec: 9413.9). Total num frames: 24641536. Throughput: 0: 9503.3. Samples: 24617084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:33:40,829][613581] Avg episode reward: [(0, '4446.629')] [2023-03-09 03:33:42,305][613885] Updated weights for policy 0, policy_version 48160 (0.0005) [2023-03-09 03:33:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9427.7). Total num frames: 24690688. Throughput: 0: 9652.6. Samples: 24678656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:33:45,830][613581] Avg episode reward: [(0, '4335.059')] [2023-03-09 03:33:45,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000048224_24690688.pth... [2023-03-09 03:33:45,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000047656_24399872.pth [2023-03-09 03:33:46,328][613885] Updated weights for policy 0, policy_version 48240 (0.0005) [2023-03-09 03:33:50,051][613885] Updated weights for policy 0, policy_version 48320 (0.0005) [2023-03-09 03:33:50,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9693.9, 300 sec: 9455.5). Total num frames: 24743936. Throughput: 0: 9905.2. Samples: 24743860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:33:50,829][613581] Avg episode reward: [(0, '4315.552')] [2023-03-09 03:33:53,944][613885] Updated weights for policy 0, policy_version 48400 (0.0005) [2023-03-09 03:33:55,829][613581] Fps is (10 sec: 10649.7, 60 sec: 9830.4, 300 sec: 9455.5). Total num frames: 24797184. Throughput: 0: 9975.6. Samples: 24775060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:33:55,829][613581] Avg episode reward: [(0, '4522.307')] [2023-03-09 03:33:57,786][613885] Updated weights for policy 0, policy_version 48480 (0.0005) [2023-03-09 03:34:00,829][613581] Fps is (10 sec: 10649.5, 60 sec: 9898.7, 300 sec: 9483.3). Total num frames: 24850432. Throughput: 0: 10102.0. Samples: 24838144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:34:00,829][613581] Avg episode reward: [(0, '4396.022')] [2023-03-09 03:34:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000048536_24850432.pth... [2023-03-09 03:34:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000047936_24543232.pth [2023-03-09 03:34:01,841][613885] Updated weights for policy 0, policy_version 48560 (0.0005) [2023-03-09 03:34:05,767][613885] Updated weights for policy 0, policy_version 48640 (0.0005) [2023-03-09 03:34:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10035.2, 300 sec: 9497.2). Total num frames: 24903680. Throughput: 0: 10194.5. Samples: 24899592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:34:05,829][613581] Avg episode reward: [(0, '4349.512')] [2023-03-09 03:34:09,705][613885] Updated weights for policy 0, policy_version 48720 (0.0005) [2023-03-09 03:34:10,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10035.2, 300 sec: 9511.1). Total num frames: 24952832. Throughput: 0: 10211.4. Samples: 24931348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:34:10,829][613581] Avg episode reward: [(0, '4277.158')] [2023-03-09 03:34:13,708][613885] Updated weights for policy 0, policy_version 48800 (0.0005) [2023-03-09 03:34:15,829][613581] Fps is (10 sec: 10239.8, 60 sec: 10171.7, 300 sec: 9538.8). Total num frames: 25006080. Throughput: 0: 10264.2. Samples: 24992396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:34:15,830][613581] Avg episode reward: [(0, '4472.694')] [2023-03-09 03:34:15,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000048840_25006080.pth... [2023-03-09 03:34:15,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000048224_24690688.pth [2023-03-09 03:34:17,803][613885] Updated weights for policy 0, policy_version 48880 (0.0005) [2023-03-09 03:34:20,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 9552.7). Total num frames: 25055232. Throughput: 0: 10303.0. Samples: 25052908. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:34:20,829][613581] Avg episode reward: [(0, '4270.994')] [2023-03-09 03:34:21,782][613885] Updated weights for policy 0, policy_version 48960 (0.0005) [2023-03-09 03:34:25,829][613581] Fps is (10 sec: 9830.6, 60 sec: 10171.7, 300 sec: 9552.7). Total num frames: 25104384. Throughput: 0: 10371.4. Samples: 25083800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:34:25,829][613581] Avg episode reward: [(0, '4293.195')] [2023-03-09 03:34:25,895][613885] Updated weights for policy 0, policy_version 49040 (0.0005) [2023-03-09 03:34:30,016][613885] Updated weights for policy 0, policy_version 49120 (0.0004) [2023-03-09 03:34:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 9580.5). Total num frames: 25157632. Throughput: 0: 10313.3. Samples: 25142752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:34:30,829][613581] Avg episode reward: [(0, '3852.591')] [2023-03-09 03:34:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000049136_25157632.pth... [2023-03-09 03:34:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000048536_24850432.pth [2023-03-09 03:34:34,069][613885] Updated weights for policy 0, policy_version 49200 (0.0004) [2023-03-09 03:34:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 9594.4). Total num frames: 25206784. Throughput: 0: 10225.2. Samples: 25203992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:34:35,829][613581] Avg episode reward: [(0, '3921.001')] [2023-03-09 03:34:38,013][613885] Updated weights for policy 0, policy_version 49280 (0.0005) [2023-03-09 03:34:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10240.0, 300 sec: 9608.2). Total num frames: 25255936. Throughput: 0: 10227.3. Samples: 25235288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:34:40,829][613581] Avg episode reward: [(0, '4247.692')] [2023-03-09 03:34:42,165][613885] Updated weights for policy 0, policy_version 49360 (0.0004) [2023-03-09 03:34:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10240.0, 300 sec: 9622.1). Total num frames: 25305088. Throughput: 0: 10128.2. Samples: 25293912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:34:45,829][613581] Avg episode reward: [(0, '4317.335')] [2023-03-09 03:34:45,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000049432_25309184.pth... [2023-03-09 03:34:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000048840_25006080.pth [2023-03-09 03:34:46,170][613885] Updated weights for policy 0, policy_version 49440 (0.0005) [2023-03-09 03:34:50,160][613885] Updated weights for policy 0, policy_version 49520 (0.0004) [2023-03-09 03:34:50,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 9649.9). Total num frames: 25358336. Throughput: 0: 10153.6. Samples: 25356504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:34:50,829][613581] Avg episode reward: [(0, '4396.927')] [2023-03-09 03:34:54,201][613885] Updated weights for policy 0, policy_version 49600 (0.0004) [2023-03-09 03:34:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 9663.8). Total num frames: 25407488. Throughput: 0: 10125.7. Samples: 25387004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:34:55,829][613581] Avg episode reward: [(0, '4367.891')] [2023-03-09 03:34:58,257][613885] Updated weights for policy 0, policy_version 49680 (0.0004) [2023-03-09 03:35:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 9705.4). Total num frames: 25464832. Throughput: 0: 10134.5. Samples: 25448448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:35:00,829][613581] Avg episode reward: [(0, '4374.845')] [2023-03-09 03:35:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000049736_25464832.pth... [2023-03-09 03:35:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000049136_25157632.pth [2023-03-09 03:35:01,991][613885] Updated weights for policy 0, policy_version 49760 (0.0005) [2023-03-09 03:35:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10171.7, 300 sec: 9719.3). Total num frames: 25513984. Throughput: 0: 10241.0. Samples: 25513752. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:35:05,829][613581] Avg episode reward: [(0, '4574.661')] [2023-03-09 03:35:05,830][613841] Saving new best policy, reward=4574.661! [2023-03-09 03:35:05,888][613885] Updated weights for policy 0, policy_version 49840 (0.0005) [2023-03-09 03:35:09,818][613885] Updated weights for policy 0, policy_version 49920 (0.0005) [2023-03-09 03:35:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 9747.1). Total num frames: 25567232. Throughput: 0: 10228.4. Samples: 25544076. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:35:10,829][613581] Avg episode reward: [(0, '4182.338')] [2023-03-09 03:35:13,473][613885] Updated weights for policy 0, policy_version 50000 (0.0004) [2023-03-09 03:35:15,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10308.3, 300 sec: 9774.9). Total num frames: 25624576. Throughput: 0: 10397.2. Samples: 25610624. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:35:15,829][613581] Avg episode reward: [(0, '4046.306')] [2023-03-09 03:35:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000050048_25624576.pth... [2023-03-09 03:35:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000049432_25309184.pth [2023-03-09 03:35:17,414][613885] Updated weights for policy 0, policy_version 50080 (0.0005) [2023-03-09 03:35:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 9788.7). Total num frames: 25673728. Throughput: 0: 10407.6. Samples: 25672336. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:35:20,829][613581] Avg episode reward: [(0, '3759.749')] [2023-03-09 03:35:21,323][613885] Updated weights for policy 0, policy_version 50160 (0.0005) [2023-03-09 03:35:25,324][613885] Updated weights for policy 0, policy_version 50240 (0.0005) [2023-03-09 03:35:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 9802.6). Total num frames: 25726976. Throughput: 0: 10381.7. Samples: 25702464. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:35:25,830][613581] Avg episode reward: [(0, '4263.178')] [2023-03-09 03:35:29,349][613885] Updated weights for policy 0, policy_version 50320 (0.0004) [2023-03-09 03:35:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 9802.6). Total num frames: 25776128. Throughput: 0: 10444.3. Samples: 25763904. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:35:30,829][613581] Avg episode reward: [(0, '3901.824')] [2023-03-09 03:35:30,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000050344_25776128.pth... [2023-03-09 03:35:30,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000049736_25464832.pth [2023-03-09 03:35:33,428][613885] Updated weights for policy 0, policy_version 50400 (0.0005) [2023-03-09 03:35:35,829][613581] Fps is (10 sec: 9830.6, 60 sec: 10308.3, 300 sec: 9816.5). Total num frames: 25825280. Throughput: 0: 10412.7. Samples: 25825076. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:35:35,829][613581] Avg episode reward: [(0, '3567.259')] [2023-03-09 03:35:37,480][613885] Updated weights for policy 0, policy_version 50480 (0.0004) [2023-03-09 03:35:40,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 9816.5). Total num frames: 25878528. Throughput: 0: 10409.5. Samples: 25855432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:35:40,829][613581] Avg episode reward: [(0, '4262.193')] [2023-03-09 03:35:41,339][613885] Updated weights for policy 0, policy_version 50560 (0.0005) [2023-03-09 03:35:45,364][613885] Updated weights for policy 0, policy_version 50640 (0.0005) [2023-03-09 03:35:45,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10444.8, 300 sec: 9830.4). Total num frames: 25931776. Throughput: 0: 10432.9. Samples: 25917928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:35:45,829][613581] Avg episode reward: [(0, '4431.295')] [2023-03-09 03:35:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000050648_25931776.pth... [2023-03-09 03:35:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000050048_25624576.pth [2023-03-09 03:35:49,415][613885] Updated weights for policy 0, policy_version 50720 (0.0005) [2023-03-09 03:35:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 9830.4). Total num frames: 25980928. Throughput: 0: 10315.1. Samples: 25977932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:35:50,829][613581] Avg episode reward: [(0, '4033.864')] [2023-03-09 03:35:53,403][613885] Updated weights for policy 0, policy_version 50800 (0.0004) [2023-03-09 03:35:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 9844.3). Total num frames: 26034176. Throughput: 0: 10345.0. Samples: 26009600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:35:55,829][613581] Avg episode reward: [(0, '4312.015')] [2023-03-09 03:35:57,064][613885] Updated weights for policy 0, policy_version 50880 (0.0005) [2023-03-09 03:36:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.6, 300 sec: 9872.1). Total num frames: 26087424. Throughput: 0: 10353.8. Samples: 26076544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:36:00,829][613581] Avg episode reward: [(0, '4251.413')] [2023-03-09 03:36:00,850][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000050960_26091520.pth... [2023-03-09 03:36:00,850][613885] Updated weights for policy 0, policy_version 50960 (0.0005) [2023-03-09 03:36:00,851][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000050344_25776128.pth [2023-03-09 03:36:04,430][613885] Updated weights for policy 0, policy_version 51040 (0.0005) [2023-03-09 03:36:05,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10513.1, 300 sec: 9899.8). Total num frames: 26144768. Throughput: 0: 10447.7. Samples: 26142484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:36:05,829][613581] Avg episode reward: [(0, '4142.352')] [2023-03-09 03:36:08,423][613885] Updated weights for policy 0, policy_version 51120 (0.0005) [2023-03-09 03:36:10,829][613581] Fps is (10 sec: 11059.0, 60 sec: 10513.0, 300 sec: 9927.6). Total num frames: 26198016. Throughput: 0: 10463.8. Samples: 26173336. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:36:10,829][613581] Avg episode reward: [(0, '4298.999')] [2023-03-09 03:36:12,291][613885] Updated weights for policy 0, policy_version 51200 (0.0004) [2023-03-09 03:36:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 9941.5). Total num frames: 26247168. Throughput: 0: 10463.4. Samples: 26234756. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:36:15,829][613581] Avg episode reward: [(0, '4298.554')] [2023-03-09 03:36:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000051264_26247168.pth... [2023-03-09 03:36:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000050648_25931776.pth [2023-03-09 03:36:16,499][613885] Updated weights for policy 0, policy_version 51280 (0.0005) [2023-03-09 03:36:20,527][613885] Updated weights for policy 0, policy_version 51360 (0.0004) [2023-03-09 03:36:20,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10376.5, 300 sec: 9955.4). Total num frames: 26296320. Throughput: 0: 10435.8. Samples: 26294688. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:36:20,829][613581] Avg episode reward: [(0, '4467.323')] [2023-03-09 03:36:24,377][613885] Updated weights for policy 0, policy_version 51440 (0.0005) [2023-03-09 03:36:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 9983.1). Total num frames: 26349568. Throughput: 0: 10497.1. Samples: 26327800. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:36:25,829][613581] Avg episode reward: [(0, '4047.833')] [2023-03-09 03:36:28,269][613885] Updated weights for policy 0, policy_version 51520 (0.0005) [2023-03-09 03:36:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10010.9). Total num frames: 26402816. Throughput: 0: 10481.8. Samples: 26389608. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:36:30,829][613581] Avg episode reward: [(0, '4253.226')] [2023-03-09 03:36:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000051568_26402816.pth... [2023-03-09 03:36:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000050960_26091520.pth [2023-03-09 03:36:32,275][613885] Updated weights for policy 0, policy_version 51600 (0.0004) [2023-03-09 03:36:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10024.8). Total num frames: 26451968. Throughput: 0: 10533.1. Samples: 26451920. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:36:35,829][613581] Avg episode reward: [(0, '4518.798')] [2023-03-09 03:36:36,158][613885] Updated weights for policy 0, policy_version 51680 (0.0005) [2023-03-09 03:36:40,043][613885] Updated weights for policy 0, policy_version 51760 (0.0005) [2023-03-09 03:36:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10052.6). Total num frames: 26505216. Throughput: 0: 10539.6. Samples: 26483880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:36:40,829][613581] Avg episode reward: [(0, '4449.715')] [2023-03-09 03:36:43,944][613885] Updated weights for policy 0, policy_version 51840 (0.0005) [2023-03-09 03:36:45,829][613581] Fps is (10 sec: 11059.0, 60 sec: 10513.1, 300 sec: 10066.4). Total num frames: 26562560. Throughput: 0: 10445.2. Samples: 26546580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:36:45,829][613581] Avg episode reward: [(0, '4307.946')] [2023-03-09 03:36:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000051880_26562560.pth... [2023-03-09 03:36:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000051264_26247168.pth [2023-03-09 03:36:47,433][613885] Updated weights for policy 0, policy_version 51920 (0.0005) [2023-03-09 03:36:50,829][613581] Fps is (10 sec: 11059.3, 60 sec: 10581.3, 300 sec: 10094.2). Total num frames: 26615808. Throughput: 0: 10442.2. Samples: 26612384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:36:50,829][613581] Avg episode reward: [(0, '4210.312')] [2023-03-09 03:36:51,429][613885] Updated weights for policy 0, policy_version 52000 (0.0005) [2023-03-09 03:36:55,410][613885] Updated weights for policy 0, policy_version 52080 (0.0004) [2023-03-09 03:36:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10122.0). Total num frames: 26669056. Throughput: 0: 10469.9. Samples: 26644480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:36:55,830][613581] Avg episode reward: [(0, '4306.740')] [2023-03-09 03:36:59,283][613885] Updated weights for policy 0, policy_version 52160 (0.0004) [2023-03-09 03:37:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10513.0, 300 sec: 10122.0). Total num frames: 26718208. Throughput: 0: 10486.0. Samples: 26706624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:37:00,829][613581] Avg episode reward: [(0, '4108.881')] [2023-03-09 03:37:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000052184_26718208.pth... [2023-03-09 03:37:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000051568_26402816.pth [2023-03-09 03:37:03,084][613885] Updated weights for policy 0, policy_version 52240 (0.0005) [2023-03-09 03:37:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10135.9). Total num frames: 26771456. Throughput: 0: 10537.8. Samples: 26768888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:37:05,830][613581] Avg episode reward: [(0, '4468.004')] [2023-03-09 03:37:07,207][613885] Updated weights for policy 0, policy_version 52320 (0.0005) [2023-03-09 03:37:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10163.6). Total num frames: 26824704. Throughput: 0: 10497.6. Samples: 26800192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:37:10,829][613581] Avg episode reward: [(0, '4178.850')] [2023-03-09 03:37:11,150][613885] Updated weights for policy 0, policy_version 52400 (0.0004) [2023-03-09 03:37:15,072][613885] Updated weights for policy 0, policy_version 52480 (0.0005) [2023-03-09 03:37:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10177.5). Total num frames: 26873856. Throughput: 0: 10498.3. Samples: 26862032. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:37:15,830][613581] Avg episode reward: [(0, '4077.645')] [2023-03-09 03:37:15,862][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000052496_26877952.pth... [2023-03-09 03:37:15,864][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000051880_26562560.pth [2023-03-09 03:37:18,937][613885] Updated weights for policy 0, policy_version 52560 (0.0005) [2023-03-09 03:37:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10177.5). Total num frames: 26927104. Throughput: 0: 10499.9. Samples: 26924416. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:37:20,830][613581] Avg episode reward: [(0, '3573.786')] [2023-03-09 03:37:23,034][613885] Updated weights for policy 0, policy_version 52640 (0.0004) [2023-03-09 03:37:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10191.4). Total num frames: 26976256. Throughput: 0: 10486.6. Samples: 26955776. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:37:25,829][613581] Avg episode reward: [(0, '4065.383')] [2023-03-09 03:37:26,982][613885] Updated weights for policy 0, policy_version 52720 (0.0004) [2023-03-09 03:37:30,694][613885] Updated weights for policy 0, policy_version 52800 (0.0005) [2023-03-09 03:37:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10219.2). Total num frames: 27033600. Throughput: 0: 10464.1. Samples: 27017464. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:37:30,829][613581] Avg episode reward: [(0, '3073.155')] [2023-03-09 03:37:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000052800_27033600.pth... [2023-03-09 03:37:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000052184_26718208.pth [2023-03-09 03:37:34,427][613885] Updated weights for policy 0, policy_version 52880 (0.0005) [2023-03-09 03:37:35,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10581.3, 300 sec: 10233.1). Total num frames: 27086848. Throughput: 0: 10494.5. Samples: 27084636. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:37:35,829][613581] Avg episode reward: [(0, '3324.801')] [2023-03-09 03:37:38,402][613885] Updated weights for policy 0, policy_version 52960 (0.0005) [2023-03-09 03:37:40,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.3, 300 sec: 10260.8). Total num frames: 27140096. Throughput: 0: 10467.6. Samples: 27115520. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:37:40,829][613581] Avg episode reward: [(0, '3355.829')] [2023-03-09 03:37:42,368][613885] Updated weights for policy 0, policy_version 53040 (0.0005) [2023-03-09 03:37:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10444.8, 300 sec: 10260.8). Total num frames: 27189248. Throughput: 0: 10413.8. Samples: 27175244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:37:45,829][613581] Avg episode reward: [(0, '3607.660')] [2023-03-09 03:37:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000053104_27189248.pth... [2023-03-09 03:37:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000052496_26877952.pth [2023-03-09 03:37:46,579][613885] Updated weights for policy 0, policy_version 53120 (0.0005) [2023-03-09 03:37:50,529][613885] Updated weights for policy 0, policy_version 53200 (0.0005) [2023-03-09 03:37:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 10274.7). Total num frames: 27238400. Throughput: 0: 10386.4. Samples: 27236276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:37:50,829][613581] Avg episode reward: [(0, '3729.896')] [2023-03-09 03:37:54,547][613885] Updated weights for policy 0, policy_version 53280 (0.0005) [2023-03-09 03:37:55,829][613581] Fps is (10 sec: 9830.6, 60 sec: 10308.3, 300 sec: 10274.7). Total num frames: 27287552. Throughput: 0: 10376.6. Samples: 27267136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:37:55,829][613581] Avg episode reward: [(0, '3588.320')] [2023-03-09 03:37:58,611][613885] Updated weights for policy 0, policy_version 53360 (0.0004) [2023-03-09 03:38:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10302.5). Total num frames: 27340800. Throughput: 0: 10367.9. Samples: 27328584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:38:00,829][613581] Avg episode reward: [(0, '4255.197')] [2023-03-09 03:38:00,869][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000053408_27344896.pth... [2023-03-09 03:38:00,871][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000052800_27033600.pth [2023-03-09 03:38:02,498][613885] Updated weights for policy 0, policy_version 53440 (0.0005) [2023-03-09 03:38:05,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 10316.4). Total num frames: 27394048. Throughput: 0: 10430.0. Samples: 27393764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:38:05,829][613581] Avg episode reward: [(0, '4312.360')] [2023-03-09 03:38:06,294][613885] Updated weights for policy 0, policy_version 53520 (0.0005) [2023-03-09 03:38:10,416][613885] Updated weights for policy 0, policy_version 53600 (0.0005) [2023-03-09 03:38:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10330.2). Total num frames: 27443200. Throughput: 0: 10374.3. Samples: 27422620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:38:10,829][613581] Avg episode reward: [(0, '4399.399')] [2023-03-09 03:38:14,441][613885] Updated weights for policy 0, policy_version 53680 (0.0005) [2023-03-09 03:38:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10344.1). Total num frames: 27496448. Throughput: 0: 10368.4. Samples: 27484044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:38:15,829][613581] Avg episode reward: [(0, '3866.696')] [2023-03-09 03:38:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000053704_27496448.pth... [2023-03-09 03:38:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000053104_27189248.pth [2023-03-09 03:38:18,535][613885] Updated weights for policy 0, policy_version 53760 (0.0005) [2023-03-09 03:38:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10344.1). Total num frames: 27545600. Throughput: 0: 10216.9. Samples: 27544396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:38:20,829][613581] Avg episode reward: [(0, '4044.600')] [2023-03-09 03:38:22,537][613885] Updated weights for policy 0, policy_version 53840 (0.0005) [2023-03-09 03:38:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 27598848. Throughput: 0: 10227.5. Samples: 27575756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:38:25,829][613581] Avg episode reward: [(0, '4220.250')] [2023-03-09 03:38:26,333][613885] Updated weights for policy 0, policy_version 53920 (0.0006) [2023-03-09 03:38:30,356][613885] Updated weights for policy 0, policy_version 54000 (0.0005) [2023-03-09 03:38:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 27652096. Throughput: 0: 10274.9. Samples: 27637612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:38:30,829][613581] Avg episode reward: [(0, '4271.131')] [2023-03-09 03:38:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000054008_27652096.pth... [2023-03-09 03:38:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000053408_27344896.pth [2023-03-09 03:38:34,295][613885] Updated weights for policy 0, policy_version 54080 (0.0006) [2023-03-09 03:38:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10385.8). Total num frames: 27705344. Throughput: 0: 10331.7. Samples: 27701204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:38:35,829][613581] Avg episode reward: [(0, '4240.128')] [2023-03-09 03:38:38,114][613885] Updated weights for policy 0, policy_version 54160 (0.0005) [2023-03-09 03:38:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10385.8). Total num frames: 27754496. Throughput: 0: 10355.4. Samples: 27733132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:38:40,829][613581] Avg episode reward: [(0, '4473.460')] [2023-03-09 03:38:42,489][613885] Updated weights for policy 0, policy_version 54240 (0.0006) [2023-03-09 03:38:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10240.0, 300 sec: 10371.9). Total num frames: 27803648. Throughput: 0: 10247.5. Samples: 27789720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:38:45,829][613581] Avg episode reward: [(0, '4321.015')] [2023-03-09 03:38:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000054304_27803648.pth... [2023-03-09 03:38:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000053704_27496448.pth [2023-03-09 03:38:46,515][613885] Updated weights for policy 0, policy_version 54320 (0.0005) [2023-03-09 03:38:50,437][613885] Updated weights for policy 0, policy_version 54400 (0.0005) [2023-03-09 03:38:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10358.0). Total num frames: 27852800. Throughput: 0: 10194.2. Samples: 27852504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:38:50,829][613581] Avg episode reward: [(0, '4323.703')] [2023-03-09 03:38:54,539][613885] Updated weights for policy 0, policy_version 54480 (0.0004) [2023-03-09 03:38:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.2, 300 sec: 10358.0). Total num frames: 27906048. Throughput: 0: 10209.0. Samples: 27882024. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:38:55,829][613581] Avg episode reward: [(0, '4345.133')] [2023-03-09 03:38:58,490][613885] Updated weights for policy 0, policy_version 54560 (0.0004) [2023-03-09 03:39:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10358.0). Total num frames: 27959296. Throughput: 0: 10225.0. Samples: 27944168. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:39:00,829][613581] Avg episode reward: [(0, '4413.673')] [2023-03-09 03:39:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000054608_27959296.pth... [2023-03-09 03:39:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000054008_27652096.pth [2023-03-09 03:39:02,371][613885] Updated weights for policy 0, policy_version 54640 (0.0005) [2023-03-09 03:39:05,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10358.0). Total num frames: 28008448. Throughput: 0: 10271.7. Samples: 28006624. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:39:05,829][613581] Avg episode reward: [(0, '4297.542')] [2023-03-09 03:39:06,322][613885] Updated weights for policy 0, policy_version 54720 (0.0005) [2023-03-09 03:39:10,277][613885] Updated weights for policy 0, policy_version 54800 (0.0005) [2023-03-09 03:39:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10358.0). Total num frames: 28061696. Throughput: 0: 10270.8. Samples: 28037944. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:39:10,829][613581] Avg episode reward: [(0, '4247.880')] [2023-03-09 03:39:14,266][613885] Updated weights for policy 0, policy_version 54880 (0.0005) [2023-03-09 03:39:15,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10358.0). Total num frames: 28110848. Throughput: 0: 10262.0. Samples: 28099400. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:39:15,829][613581] Avg episode reward: [(0, '4232.193')] [2023-03-09 03:39:15,853][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000054912_28114944.pth... [2023-03-09 03:39:15,854][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000054304_27803648.pth [2023-03-09 03:39:18,287][613885] Updated weights for policy 0, policy_version 54960 (0.0005) [2023-03-09 03:39:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 28164096. Throughput: 0: 10254.4. Samples: 28162652. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:39:20,829][613581] Avg episode reward: [(0, '4552.195')] [2023-03-09 03:39:22,230][613885] Updated weights for policy 0, policy_version 55040 (0.0005) [2023-03-09 03:39:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10358.0). Total num frames: 28213248. Throughput: 0: 10212.2. Samples: 28192680. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:39:25,829][613581] Avg episode reward: [(0, '4381.506')] [2023-03-09 03:39:26,344][613885] Updated weights for policy 0, policy_version 55120 (0.0004) [2023-03-09 03:39:30,143][613885] Updated weights for policy 0, policy_version 55200 (0.0005) [2023-03-09 03:39:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10371.9). Total num frames: 28266496. Throughput: 0: 10317.1. Samples: 28253988. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:39:30,829][613581] Avg episode reward: [(0, '4395.528')] [2023-03-09 03:39:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000055208_28266496.pth... [2023-03-09 03:39:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000054608_27959296.pth [2023-03-09 03:39:34,045][613885] Updated weights for policy 0, policy_version 55280 (0.0005) [2023-03-09 03:39:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 10385.8). Total num frames: 28319744. Throughput: 0: 10332.6. Samples: 28317468. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:39:35,829][613581] Avg episode reward: [(0, '4457.966')] [2023-03-09 03:39:37,995][613885] Updated weights for policy 0, policy_version 55360 (0.0005) [2023-03-09 03:39:40,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10308.3, 300 sec: 10399.7). Total num frames: 28372992. Throughput: 0: 10371.2. Samples: 28348728. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:39:40,829][613581] Avg episode reward: [(0, '4552.707')] [2023-03-09 03:39:41,989][613885] Updated weights for policy 0, policy_version 55440 (0.0005) [2023-03-09 03:39:45,829][613581] Fps is (10 sec: 10239.8, 60 sec: 10308.3, 300 sec: 10385.8). Total num frames: 28422144. Throughput: 0: 10342.4. Samples: 28409576. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:39:45,829][613581] Avg episode reward: [(0, '4524.695')] [2023-03-09 03:39:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000055512_28422144.pth... [2023-03-09 03:39:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000054912_28114944.pth [2023-03-09 03:39:46,201][613885] Updated weights for policy 0, policy_version 55520 (0.0004) [2023-03-09 03:39:50,288][613885] Updated weights for policy 0, policy_version 55600 (0.0004) [2023-03-09 03:39:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 10385.8). Total num frames: 28471296. Throughput: 0: 10246.9. Samples: 28467732. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:39:50,829][613581] Avg episode reward: [(0, '4505.819')] [2023-03-09 03:39:54,333][613885] Updated weights for policy 0, policy_version 55680 (0.0005) [2023-03-09 03:39:55,829][613581] Fps is (10 sec: 9830.6, 60 sec: 10240.0, 300 sec: 10358.0). Total num frames: 28520448. Throughput: 0: 10256.1. Samples: 28499468. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:39:55,829][613581] Avg episode reward: [(0, '4460.078')] [2023-03-09 03:39:58,409][613885] Updated weights for policy 0, policy_version 55760 (0.0005) [2023-03-09 03:40:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.8, 300 sec: 10358.0). Total num frames: 28569600. Throughput: 0: 10205.4. Samples: 28558644. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:40:00,829][613581] Avg episode reward: [(0, '4483.083')] [2023-03-09 03:40:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000055800_28569600.pth... [2023-03-09 03:40:00,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000055208_28266496.pth [2023-03-09 03:40:02,738][613885] Updated weights for policy 0, policy_version 55840 (0.0005) [2023-03-09 03:40:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.8, 300 sec: 10344.1). Total num frames: 28618752. Throughput: 0: 10115.0. Samples: 28617828. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:40:05,829][613581] Avg episode reward: [(0, '4457.557')] [2023-03-09 03:40:06,578][613885] Updated weights for policy 0, policy_version 55920 (0.0005) [2023-03-09 03:40:10,413][613885] Updated weights for policy 0, policy_version 56000 (0.0005) [2023-03-09 03:40:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10330.3). Total num frames: 28672000. Throughput: 0: 10138.7. Samples: 28648920. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:40:10,829][613581] Avg episode reward: [(0, '4201.305')] [2023-03-09 03:40:14,291][613885] Updated weights for policy 0, policy_version 56080 (0.0005) [2023-03-09 03:40:15,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 10344.1). Total num frames: 28725248. Throughput: 0: 10212.0. Samples: 28713528. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:40:15,829][613581] Avg episode reward: [(0, '4435.094')] [2023-03-09 03:40:15,853][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000056112_28729344.pth... [2023-03-09 03:40:15,855][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000055512_28422144.pth [2023-03-09 03:40:18,150][613885] Updated weights for policy 0, policy_version 56160 (0.0005) [2023-03-09 03:40:20,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10308.3, 300 sec: 10358.0). Total num frames: 28782592. Throughput: 0: 10254.7. Samples: 28778932. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:40:20,829][613581] Avg episode reward: [(0, '4334.475')] [2023-03-09 03:40:21,979][613885] Updated weights for policy 0, policy_version 56240 (0.0005) [2023-03-09 03:40:25,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.2, 300 sec: 10358.0). Total num frames: 28831744. Throughput: 0: 10227.5. Samples: 28808964. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:40:25,829][613581] Avg episode reward: [(0, '4527.479')] [2023-03-09 03:40:26,106][613885] Updated weights for policy 0, policy_version 56320 (0.0004) [2023-03-09 03:40:30,064][613885] Updated weights for policy 0, policy_version 56400 (0.0005) [2023-03-09 03:40:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 28884992. Throughput: 0: 10216.4. Samples: 28869312. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:40:30,829][613581] Avg episode reward: [(0, '4430.253')] [2023-03-09 03:40:30,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000056416_28884992.pth... [2023-03-09 03:40:30,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000055800_28569600.pth [2023-03-09 03:40:33,898][613885] Updated weights for policy 0, policy_version 56480 (0.0004) [2023-03-09 03:40:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10358.0). Total num frames: 28934144. Throughput: 0: 10341.9. Samples: 28933116. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:40:35,829][613581] Avg episode reward: [(0, '4423.755')] [2023-03-09 03:40:37,939][613885] Updated weights for policy 0, policy_version 56560 (0.0005) [2023-03-09 03:40:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10358.0). Total num frames: 28987392. Throughput: 0: 10303.6. Samples: 28963128. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:40:40,829][613581] Avg episode reward: [(0, '4517.885')] [2023-03-09 03:40:41,820][613885] Updated weights for policy 0, policy_version 56640 (0.0004) [2023-03-09 03:40:45,705][613885] Updated weights for policy 0, policy_version 56720 (0.0004) [2023-03-09 03:40:45,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 29040640. Throughput: 0: 10409.7. Samples: 29027080. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:40:45,830][613581] Avg episode reward: [(0, '4538.876')] [2023-03-09 03:40:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000056720_29040640.pth... [2023-03-09 03:40:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000056112_28729344.pth [2023-03-09 03:40:49,554][613885] Updated weights for policy 0, policy_version 56800 (0.0004) [2023-03-09 03:40:50,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 29093888. Throughput: 0: 10489.5. Samples: 29089856. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:40:50,829][613581] Avg episode reward: [(0, '4536.834')] [2023-03-09 03:40:53,525][613885] Updated weights for policy 0, policy_version 56880 (0.0004) [2023-03-09 03:40:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 29143040. Throughput: 0: 10499.7. Samples: 29121408. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:40:55,829][613581] Avg episode reward: [(0, '4431.310')] [2023-03-09 03:40:57,528][613885] Updated weights for policy 0, policy_version 56960 (0.0005) [2023-03-09 03:41:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10444.8, 300 sec: 10344.1). Total num frames: 29196288. Throughput: 0: 10456.5. Samples: 29184072. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:41:00,830][613581] Avg episode reward: [(0, '4434.166')] [2023-03-09 03:41:00,859][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000057032_29200384.pth... [2023-03-09 03:41:00,861][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000056416_28884992.pth [2023-03-09 03:41:01,268][613885] Updated weights for policy 0, policy_version 57040 (0.0005) [2023-03-09 03:41:05,429][613885] Updated weights for policy 0, policy_version 57120 (0.0004) [2023-03-09 03:41:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10330.3). Total num frames: 29245440. Throughput: 0: 10363.3. Samples: 29245280. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:41:05,829][613581] Avg episode reward: [(0, '4541.446')] [2023-03-09 03:41:09,296][613885] Updated weights for policy 0, policy_version 57200 (0.0005) [2023-03-09 03:41:10,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10513.0, 300 sec: 10358.0). Total num frames: 29302784. Throughput: 0: 10364.1. Samples: 29275348. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:41:10,829][613581] Avg episode reward: [(0, '4557.932')] [2023-03-09 03:41:13,139][613885] Updated weights for policy 0, policy_version 57280 (0.0005) [2023-03-09 03:41:15,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10513.0, 300 sec: 10371.9). Total num frames: 29356032. Throughput: 0: 10480.5. Samples: 29340936. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:41:15,829][613581] Avg episode reward: [(0, '4531.629')] [2023-03-09 03:41:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000057336_29356032.pth... [2023-03-09 03:41:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000056720_29040640.pth [2023-03-09 03:41:17,032][613885] Updated weights for policy 0, policy_version 57360 (0.0004) [2023-03-09 03:41:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 29405184. Throughput: 0: 10402.1. Samples: 29401212. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:41:20,829][613581] Avg episode reward: [(0, '4505.321')] [2023-03-09 03:41:21,118][613885] Updated weights for policy 0, policy_version 57440 (0.0005) [2023-03-09 03:41:25,151][613885] Updated weights for policy 0, policy_version 57520 (0.0004) [2023-03-09 03:41:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10376.5, 300 sec: 10344.1). Total num frames: 29454336. Throughput: 0: 10411.6. Samples: 29431652. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:41:25,829][613581] Avg episode reward: [(0, '4553.872')] [2023-03-09 03:41:29,133][613885] Updated weights for policy 0, policy_version 57600 (0.0004) [2023-03-09 03:41:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 29507584. Throughput: 0: 10375.4. Samples: 29493972. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:41:30,829][613581] Avg episode reward: [(0, '4455.939')] [2023-03-09 03:41:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000057632_29507584.pth... [2023-03-09 03:41:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000057032_29200384.pth [2023-03-09 03:41:33,188][613885] Updated weights for policy 0, policy_version 57680 (0.0005) [2023-03-09 03:41:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10344.1). Total num frames: 29556736. Throughput: 0: 10321.3. Samples: 29554316. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:41:35,829][613581] Avg episode reward: [(0, '4365.869')] [2023-03-09 03:41:37,251][613885] Updated weights for policy 0, policy_version 57760 (0.0006) [2023-03-09 03:41:40,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 10330.3). Total num frames: 29609984. Throughput: 0: 10310.3. Samples: 29585372. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:41:40,829][613581] Avg episode reward: [(0, '4251.588')] [2023-03-09 03:41:41,172][613885] Updated weights for policy 0, policy_version 57840 (0.0005) [2023-03-09 03:41:45,236][613885] Updated weights for policy 0, policy_version 57920 (0.0005) [2023-03-09 03:41:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10316.4). Total num frames: 29659136. Throughput: 0: 10281.5. Samples: 29646740. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 03:41:45,829][613581] Avg episode reward: [(0, '4264.568')] [2023-03-09 03:41:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000057928_29659136.pth... [2023-03-09 03:41:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000057336_29356032.pth [2023-03-09 03:41:49,336][613885] Updated weights for policy 0, policy_version 58000 (0.0005) [2023-03-09 03:41:50,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10240.0, 300 sec: 10302.5). Total num frames: 29708288. Throughput: 0: 10272.7. Samples: 29707552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:41:50,829][613581] Avg episode reward: [(0, '4170.665')] [2023-03-09 03:41:53,172][613885] Updated weights for policy 0, policy_version 58080 (0.0005) [2023-03-09 03:41:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10316.4). Total num frames: 29761536. Throughput: 0: 10310.6. Samples: 29739324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:41:55,829][613581] Avg episode reward: [(0, '4056.646')] [2023-03-09 03:41:57,150][613885] Updated weights for policy 0, policy_version 58160 (0.0005) [2023-03-09 03:42:00,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10316.4). Total num frames: 29814784. Throughput: 0: 10227.3. Samples: 29801164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:42:00,829][613581] Avg episode reward: [(0, '4068.575')] [2023-03-09 03:42:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000058232_29814784.pth... [2023-03-09 03:42:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000057632_29507584.pth [2023-03-09 03:42:01,028][613885] Updated weights for policy 0, policy_version 58240 (0.0005) [2023-03-09 03:42:04,992][613885] Updated weights for policy 0, policy_version 58320 (0.0004) [2023-03-09 03:42:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10316.4). Total num frames: 29868032. Throughput: 0: 10282.8. Samples: 29863936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:42:05,829][613581] Avg episode reward: [(0, '3756.216')] [2023-03-09 03:42:09,025][613885] Updated weights for policy 0, policy_version 58400 (0.0004) [2023-03-09 03:42:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10316.4). Total num frames: 29917184. Throughput: 0: 10254.0. Samples: 29893084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:42:10,829][613581] Avg episode reward: [(0, '3601.222')] [2023-03-09 03:42:12,932][613885] Updated weights for policy 0, policy_version 58480 (0.0005) [2023-03-09 03:42:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10316.4). Total num frames: 29970432. Throughput: 0: 10300.0. Samples: 29957472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:42:15,829][613581] Avg episode reward: [(0, '3638.972')] [2023-03-09 03:42:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000058536_29970432.pth... [2023-03-09 03:42:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000057928_29659136.pth [2023-03-09 03:42:16,809][613885] Updated weights for policy 0, policy_version 58560 (0.0005) [2023-03-09 03:42:20,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10316.4). Total num frames: 30019584. Throughput: 0: 10335.1. Samples: 30019396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:42:20,829][613581] Avg episode reward: [(0, '3732.187')] [2023-03-09 03:42:20,898][613885] Updated weights for policy 0, policy_version 58640 (0.0004) [2023-03-09 03:42:25,132][613885] Updated weights for policy 0, policy_version 58720 (0.0004) [2023-03-09 03:42:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 30068736. Throughput: 0: 10287.8. Samples: 30048320. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:42:25,829][613581] Avg episode reward: [(0, '3657.450')] [2023-03-09 03:42:29,101][613885] Updated weights for policy 0, policy_version 58800 (0.0005) [2023-03-09 03:42:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 30121984. Throughput: 0: 10270.1. Samples: 30108896. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:42:30,829][613581] Avg episode reward: [(0, '3520.621')] [2023-03-09 03:42:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000058832_30121984.pth... [2023-03-09 03:42:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000058232_29814784.pth [2023-03-09 03:42:32,978][613885] Updated weights for policy 0, policy_version 58880 (0.0004) [2023-03-09 03:42:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 30175232. Throughput: 0: 10354.9. Samples: 30173524. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:42:35,829][613581] Avg episode reward: [(0, '3390.454')] [2023-03-09 03:42:36,801][613885] Updated weights for policy 0, policy_version 58960 (0.0005) [2023-03-09 03:42:40,762][613885] Updated weights for policy 0, policy_version 59040 (0.0005) [2023-03-09 03:42:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 30228480. Throughput: 0: 10322.5. Samples: 30203836. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:42:40,829][613581] Avg episode reward: [(0, '3215.592')] [2023-03-09 03:42:44,755][613885] Updated weights for policy 0, policy_version 59120 (0.0005) [2023-03-09 03:42:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 30277632. Throughput: 0: 10315.4. Samples: 30265356. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:42:45,829][613581] Avg episode reward: [(0, '3503.652')] [2023-03-09 03:42:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000059136_30277632.pth... [2023-03-09 03:42:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000058536_29970432.pth [2023-03-09 03:42:48,620][613885] Updated weights for policy 0, policy_version 59200 (0.0005) [2023-03-09 03:42:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10316.4). Total num frames: 30330880. Throughput: 0: 10295.4. Samples: 30327228. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:42:50,829][613581] Avg episode reward: [(0, '3706.554')] [2023-03-09 03:42:52,793][613885] Updated weights for policy 0, policy_version 59280 (0.0005) [2023-03-09 03:42:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 30380032. Throughput: 0: 10310.7. Samples: 30357068. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:42:55,829][613581] Avg episode reward: [(0, '3531.814')] [2023-03-09 03:42:56,931][613885] Updated weights for policy 0, policy_version 59360 (0.0004) [2023-03-09 03:43:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 30429184. Throughput: 0: 10204.3. Samples: 30416664. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:43:00,829][613581] Avg episode reward: [(0, '3911.573')] [2023-03-09 03:43:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000059432_30429184.pth... [2023-03-09 03:43:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000058832_30121984.pth [2023-03-09 03:43:01,245][613885] Updated weights for policy 0, policy_version 59440 (0.0004) [2023-03-09 03:43:04,923][613885] Updated weights for policy 0, policy_version 59520 (0.0005) [2023-03-09 03:43:05,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10302.5). Total num frames: 30482432. Throughput: 0: 10198.8. Samples: 30478344. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:43:05,829][613581] Avg episode reward: [(0, '4223.516')] [2023-03-09 03:43:08,641][613885] Updated weights for policy 0, policy_version 59600 (0.0005) [2023-03-09 03:43:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 30535680. Throughput: 0: 10285.7. Samples: 30511176. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:43:10,829][613581] Avg episode reward: [(0, '4250.763')] [2023-03-09 03:43:12,534][613885] Updated weights for policy 0, policy_version 59680 (0.0004) [2023-03-09 03:43:15,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10316.4). Total num frames: 30588928. Throughput: 0: 10386.2. Samples: 30576276. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:43:15,829][613581] Avg episode reward: [(0, '4155.778')] [2023-03-09 03:43:15,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000059744_30588928.pth... [2023-03-09 03:43:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000059136_30277632.pth [2023-03-09 03:43:16,380][613885] Updated weights for policy 0, policy_version 59760 (0.0005) [2023-03-09 03:43:20,197][613885] Updated weights for policy 0, policy_version 59840 (0.0005) [2023-03-09 03:43:20,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10376.5, 300 sec: 10316.4). Total num frames: 30642176. Throughput: 0: 10365.9. Samples: 30639988. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:43:20,829][613581] Avg episode reward: [(0, '4408.817')] [2023-03-09 03:43:24,245][613885] Updated weights for policy 0, policy_version 59920 (0.0005) [2023-03-09 03:43:25,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10302.5). Total num frames: 30691328. Throughput: 0: 10378.0. Samples: 30670844. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:43:25,829][613581] Avg episode reward: [(0, '4280.324')] [2023-03-09 03:43:28,568][613885] Updated weights for policy 0, policy_version 60000 (0.0004) [2023-03-09 03:43:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10302.5). Total num frames: 30744576. Throughput: 0: 10286.7. Samples: 30728256. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:43:30,829][613581] Avg episode reward: [(0, '4468.690')] [2023-03-09 03:43:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000060048_30744576.pth... [2023-03-09 03:43:30,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000059432_30429184.pth [2023-03-09 03:43:32,418][613885] Updated weights for policy 0, policy_version 60080 (0.0004) [2023-03-09 03:43:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 30793728. Throughput: 0: 10279.8. Samples: 30789820. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:43:35,829][613581] Avg episode reward: [(0, '4378.509')] [2023-03-09 03:43:36,566][613885] Updated weights for policy 0, policy_version 60160 (0.0004) [2023-03-09 03:43:40,814][613885] Updated weights for policy 0, policy_version 60240 (0.0005) [2023-03-09 03:43:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10302.5). Total num frames: 30842880. Throughput: 0: 10272.3. Samples: 30819320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:43:40,829][613581] Avg episode reward: [(0, '4325.783')] [2023-03-09 03:43:45,048][613885] Updated weights for policy 0, policy_version 60320 (0.0005) [2023-03-09 03:43:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 10171.7, 300 sec: 10288.6). Total num frames: 30887936. Throughput: 0: 10243.2. Samples: 30877608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:43:45,829][613581] Avg episode reward: [(0, '4295.727')] [2023-03-09 03:43:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000060328_30887936.pth... [2023-03-09 03:43:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000059744_30588928.pth [2023-03-09 03:43:48,940][613885] Updated weights for policy 0, policy_version 60400 (0.0005) [2023-03-09 03:43:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.7, 300 sec: 10288.6). Total num frames: 30941184. Throughput: 0: 10251.3. Samples: 30939652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:43:50,829][613581] Avg episode reward: [(0, '4386.388')] [2023-03-09 03:43:53,077][613885] Updated weights for policy 0, policy_version 60480 (0.0005) [2023-03-09 03:43:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10274.7). Total num frames: 30990336. Throughput: 0: 10184.1. Samples: 30969460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:43:55,829][613581] Avg episode reward: [(0, '4377.603')] [2023-03-09 03:43:57,247][613885] Updated weights for policy 0, policy_version 60560 (0.0005) [2023-03-09 03:44:00,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10171.8, 300 sec: 10274.7). Total num frames: 31039488. Throughput: 0: 10038.7. Samples: 31028016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:44:00,829][613581] Avg episode reward: [(0, '4349.596')] [2023-03-09 03:44:00,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000060624_31039488.pth... [2023-03-09 03:44:00,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000060048_30744576.pth [2023-03-09 03:44:01,274][613885] Updated weights for policy 0, policy_version 60640 (0.0005) [2023-03-09 03:44:05,163][613885] Updated weights for policy 0, policy_version 60720 (0.0005) [2023-03-09 03:44:05,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10274.7). Total num frames: 31092736. Throughput: 0: 10032.4. Samples: 31091448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:44:05,829][613581] Avg episode reward: [(0, '4418.863')] [2023-03-09 03:44:09,175][613885] Updated weights for policy 0, policy_version 60800 (0.0005) [2023-03-09 03:44:10,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10171.7, 300 sec: 10288.6). Total num frames: 31145984. Throughput: 0: 10019.9. Samples: 31121740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:44:10,829][613581] Avg episode reward: [(0, '4336.589')] [2023-03-09 03:44:12,902][613885] Updated weights for policy 0, policy_version 60880 (0.0005) [2023-03-09 03:44:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10171.7, 300 sec: 10288.6). Total num frames: 31199232. Throughput: 0: 10122.0. Samples: 31183748. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:44:15,829][613581] Avg episode reward: [(0, '3886.673')] [2023-03-09 03:44:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000060936_31199232.pth... [2023-03-09 03:44:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000060328_30887936.pth [2023-03-09 03:44:16,989][613885] Updated weights for policy 0, policy_version 60960 (0.0004) [2023-03-09 03:44:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 10288.6). Total num frames: 31248384. Throughput: 0: 10151.9. Samples: 31246656. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:44:20,829][613581] Avg episode reward: [(0, '4356.562')] [2023-03-09 03:44:21,009][613885] Updated weights for policy 0, policy_version 61040 (0.0005) [2023-03-09 03:44:25,035][613885] Updated weights for policy 0, policy_version 61120 (0.0005) [2023-03-09 03:44:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10288.6). Total num frames: 31301632. Throughput: 0: 10171.9. Samples: 31277056. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:44:25,829][613581] Avg episode reward: [(0, '4383.842')] [2023-03-09 03:44:28,826][613885] Updated weights for policy 0, policy_version 61200 (0.0005) [2023-03-09 03:44:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10171.7, 300 sec: 10288.6). Total num frames: 31354880. Throughput: 0: 10282.4. Samples: 31340316. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:44:30,829][613581] Avg episode reward: [(0, '4454.236')] [2023-03-09 03:44:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000061240_31354880.pth... [2023-03-09 03:44:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000060624_31039488.pth [2023-03-09 03:44:32,727][613885] Updated weights for policy 0, policy_version 61280 (0.0005) [2023-03-09 03:44:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10274.7). Total num frames: 31404032. Throughput: 0: 10264.2. Samples: 31401540. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:44:35,829][613581] Avg episode reward: [(0, '4352.449')] [2023-03-09 03:44:36,904][613885] Updated weights for policy 0, policy_version 61360 (0.0005) [2023-03-09 03:44:40,828][613885] Updated weights for policy 0, policy_version 61440 (0.0005) [2023-03-09 03:44:40,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 31457280. Throughput: 0: 10258.0. Samples: 31431068. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:44:40,829][613581] Avg episode reward: [(0, '3831.953')] [2023-03-09 03:44:44,674][613885] Updated weights for policy 0, policy_version 61520 (0.0005) [2023-03-09 03:44:45,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 31506432. Throughput: 0: 10362.3. Samples: 31494320. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:44:45,829][613581] Avg episode reward: [(0, '4249.034')] [2023-03-09 03:44:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000061536_31506432.pth... [2023-03-09 03:44:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000060936_31199232.pth [2023-03-09 03:44:48,910][613885] Updated weights for policy 0, policy_version 61600 (0.0005) [2023-03-09 03:44:50,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 31555584. Throughput: 0: 10304.3. Samples: 31555140. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:44:50,829][613581] Avg episode reward: [(0, '4451.679')] [2023-03-09 03:44:53,029][613885] Updated weights for policy 0, policy_version 61680 (0.0005) [2023-03-09 03:44:55,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 31604736. Throughput: 0: 10276.8. Samples: 31584196. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:44:55,829][613581] Avg episode reward: [(0, '4495.271')] [2023-03-09 03:44:57,051][613885] Updated weights for policy 0, policy_version 61760 (0.0004) [2023-03-09 03:45:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.2, 300 sec: 10302.5). Total num frames: 31657984. Throughput: 0: 10264.1. Samples: 31645632. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:45:00,829][613581] Avg episode reward: [(0, '4349.906')] [2023-03-09 03:45:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000061832_31657984.pth... [2023-03-09 03:45:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000061240_31354880.pth [2023-03-09 03:45:01,045][613885] Updated weights for policy 0, policy_version 61840 (0.0005) [2023-03-09 03:45:04,848][613885] Updated weights for policy 0, policy_version 61920 (0.0005) [2023-03-09 03:45:05,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 31711232. Throughput: 0: 10246.8. Samples: 31707764. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:45:05,829][613581] Avg episode reward: [(0, '4404.913')] [2023-03-09 03:45:08,845][613885] Updated weights for policy 0, policy_version 62000 (0.0004) [2023-03-09 03:45:10,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 31764480. Throughput: 0: 10276.2. Samples: 31739484. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:45:10,829][613581] Avg episode reward: [(0, '4377.797')] [2023-03-09 03:45:12,594][613885] Updated weights for policy 0, policy_version 62080 (0.0004) [2023-03-09 03:45:15,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 31817728. Throughput: 0: 10298.7. Samples: 31803756. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:45:15,829][613581] Avg episode reward: [(0, '4288.247')] [2023-03-09 03:45:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000062144_31817728.pth... [2023-03-09 03:45:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000061536_31506432.pth [2023-03-09 03:45:16,423][613885] Updated weights for policy 0, policy_version 62160 (0.0004) [2023-03-09 03:45:20,401][613885] Updated weights for policy 0, policy_version 62240 (0.0005) [2023-03-09 03:45:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 31866880. Throughput: 0: 10340.9. Samples: 31866880. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:45:20,829][613581] Avg episode reward: [(0, '4360.703')] [2023-03-09 03:45:24,467][613885] Updated weights for policy 0, policy_version 62320 (0.0005) [2023-03-09 03:45:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 31920128. Throughput: 0: 10372.2. Samples: 31897816. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:45:25,829][613581] Avg episode reward: [(0, '4304.279')] [2023-03-09 03:45:28,149][613885] Updated weights for policy 0, policy_version 62400 (0.0004) [2023-03-09 03:45:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 31973376. Throughput: 0: 10376.8. Samples: 31961276. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:45:30,829][613581] Avg episode reward: [(0, '4380.518')] [2023-03-09 03:45:30,865][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000062456_31977472.pth... [2023-03-09 03:45:30,866][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000061832_31657984.pth [2023-03-09 03:45:32,060][613885] Updated weights for policy 0, policy_version 62480 (0.0005) [2023-03-09 03:45:35,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 10302.5). Total num frames: 32026624. Throughput: 0: 10386.2. Samples: 32022520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:45:35,829][613581] Avg episode reward: [(0, '4405.447')] [2023-03-09 03:45:36,152][613885] Updated weights for policy 0, policy_version 62560 (0.0005) [2023-03-09 03:45:40,282][613885] Updated weights for policy 0, policy_version 62640 (0.0004) [2023-03-09 03:45:40,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 32075776. Throughput: 0: 10381.5. Samples: 32051364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:45:40,829][613581] Avg episode reward: [(0, '4305.345')] [2023-03-09 03:45:44,179][613885] Updated weights for policy 0, policy_version 62720 (0.0005) [2023-03-09 03:45:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10288.6). Total num frames: 32129024. Throughput: 0: 10431.1. Samples: 32115032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:45:45,829][613581] Avg episode reward: [(0, '4024.688')] [2023-03-09 03:45:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000062752_32129024.pth... [2023-03-09 03:45:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000062144_31817728.pth [2023-03-09 03:45:48,027][613885] Updated weights for policy 0, policy_version 62800 (0.0005) [2023-03-09 03:45:50,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10302.5). Total num frames: 32182272. Throughput: 0: 10455.0. Samples: 32178240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:45:50,829][613581] Avg episode reward: [(0, '4028.505')] [2023-03-09 03:45:52,134][613885] Updated weights for policy 0, policy_version 62880 (0.0005) [2023-03-09 03:45:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10288.6). Total num frames: 32231424. Throughput: 0: 10389.3. Samples: 32207004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:45:55,829][613581] Avg episode reward: [(0, '3624.016')] [2023-03-09 03:45:56,245][613885] Updated weights for policy 0, policy_version 62960 (0.0005) [2023-03-09 03:45:59,943][613885] Updated weights for policy 0, policy_version 63040 (0.0005) [2023-03-09 03:46:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10302.5). Total num frames: 32284672. Throughput: 0: 10396.3. Samples: 32271588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:46:00,829][613581] Avg episode reward: [(0, '3878.248')] [2023-03-09 03:46:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000063056_32284672.pth... [2023-03-09 03:46:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000062456_31977472.pth [2023-03-09 03:46:03,955][613885] Updated weights for policy 0, policy_version 63120 (0.0005) [2023-03-09 03:46:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10274.7). Total num frames: 32333824. Throughput: 0: 10369.3. Samples: 32333500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:46:05,829][613581] Avg episode reward: [(0, '3862.869')] [2023-03-09 03:46:07,857][613885] Updated weights for policy 0, policy_version 63200 (0.0005) [2023-03-09 03:46:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 10274.7). Total num frames: 32387072. Throughput: 0: 10349.2. Samples: 32363532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:46:10,829][613581] Avg episode reward: [(0, '3869.802')] [2023-03-09 03:46:11,575][613885] Updated weights for policy 0, policy_version 63280 (0.0005) [2023-03-09 03:46:15,521][613885] Updated weights for policy 0, policy_version 63360 (0.0005) [2023-03-09 03:46:15,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10288.6). Total num frames: 32440320. Throughput: 0: 10375.1. Samples: 32428156. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:46:15,829][613581] Avg episode reward: [(0, '3930.949')] [2023-03-09 03:46:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000063360_32440320.pth... [2023-03-09 03:46:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000062752_32129024.pth [2023-03-09 03:46:19,488][613885] Updated weights for policy 0, policy_version 63440 (0.0005) [2023-03-09 03:46:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10302.5). Total num frames: 32493568. Throughput: 0: 10380.3. Samples: 32489632. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:46:20,829][613581] Avg episode reward: [(0, '4239.275')] [2023-03-09 03:46:23,215][613885] Updated weights for policy 0, policy_version 63520 (0.0005) [2023-03-09 03:46:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10302.5). Total num frames: 32546816. Throughput: 0: 10499.8. Samples: 32523856. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:46:25,830][613581] Avg episode reward: [(0, '4287.554')] [2023-03-09 03:46:27,227][613885] Updated weights for policy 0, policy_version 63600 (0.0005) [2023-03-09 03:46:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10316.4). Total num frames: 32600064. Throughput: 0: 10424.4. Samples: 32584132. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:46:30,830][613581] Avg episode reward: [(0, '4228.351')] [2023-03-09 03:46:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000063672_32600064.pth... [2023-03-09 03:46:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000063056_32284672.pth [2023-03-09 03:46:31,080][613885] Updated weights for policy 0, policy_version 63680 (0.0005) [2023-03-09 03:46:34,920][613885] Updated weights for policy 0, policy_version 63760 (0.0005) [2023-03-09 03:46:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10316.4). Total num frames: 32653312. Throughput: 0: 10471.1. Samples: 32649440. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:46:35,829][613581] Avg episode reward: [(0, '4305.322')] [2023-03-09 03:46:38,696][613885] Updated weights for policy 0, policy_version 63840 (0.0005) [2023-03-09 03:46:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10330.3). Total num frames: 32706560. Throughput: 0: 10564.5. Samples: 32682408. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:46:40,829][613581] Avg episode reward: [(0, '4336.181')] [2023-03-09 03:46:42,607][613885] Updated weights for policy 0, policy_version 63920 (0.0005) [2023-03-09 03:46:45,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10513.1, 300 sec: 10344.1). Total num frames: 32759808. Throughput: 0: 10560.6. Samples: 32746816. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:46:45,829][613581] Avg episode reward: [(0, '4333.350')] [2023-03-09 03:46:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000063984_32759808.pth... [2023-03-09 03:46:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000063360_32440320.pth [2023-03-09 03:46:46,453][613885] Updated weights for policy 0, policy_version 64000 (0.0005) [2023-03-09 03:46:50,316][613885] Updated weights for policy 0, policy_version 64080 (0.0005) [2023-03-09 03:46:50,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10344.1). Total num frames: 32813056. Throughput: 0: 10570.7. Samples: 32809180. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:46:50,840][613581] Avg episode reward: [(0, '4331.067')] [2023-03-09 03:46:54,004][613885] Updated weights for policy 0, policy_version 64160 (0.0005) [2023-03-09 03:46:55,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.3, 300 sec: 10344.1). Total num frames: 32866304. Throughput: 0: 10671.0. Samples: 32843728. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:46:55,829][613581] Avg episode reward: [(0, '4229.053')] [2023-03-09 03:46:57,961][613885] Updated weights for policy 0, policy_version 64240 (0.0005) [2023-03-09 03:47:00,829][613581] Fps is (10 sec: 11059.0, 60 sec: 10649.6, 300 sec: 10358.0). Total num frames: 32923648. Throughput: 0: 10639.7. Samples: 32906944. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:47:00,830][613581] Avg episode reward: [(0, '4292.862')] [2023-03-09 03:47:00,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000064304_32923648.pth... [2023-03-09 03:47:00,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000063672_32600064.pth [2023-03-09 03:47:01,623][613885] Updated weights for policy 0, policy_version 64320 (0.0005) [2023-03-09 03:47:05,428][613885] Updated weights for policy 0, policy_version 64400 (0.0005) [2023-03-09 03:47:05,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 10371.9). Total num frames: 32976896. Throughput: 0: 10732.3. Samples: 32972584. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:47:05,830][613581] Avg episode reward: [(0, '4090.908')] [2023-03-09 03:47:09,496][613885] Updated weights for policy 0, policy_version 64480 (0.0004) [2023-03-09 03:47:10,829][613581] Fps is (10 sec: 10240.3, 60 sec: 10649.6, 300 sec: 10358.0). Total num frames: 33026048. Throughput: 0: 10631.3. Samples: 33002264. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:47:10,829][613581] Avg episode reward: [(0, '4229.572')] [2023-03-09 03:47:13,466][613885] Updated weights for policy 0, policy_version 64560 (0.0005) [2023-03-09 03:47:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10649.6, 300 sec: 10371.9). Total num frames: 33079296. Throughput: 0: 10705.7. Samples: 33065888. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:47:15,840][613581] Avg episode reward: [(0, '4074.659')] [2023-03-09 03:47:15,844][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000064608_33079296.pth... [2023-03-09 03:47:15,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000063984_32759808.pth [2023-03-09 03:47:17,239][613885] Updated weights for policy 0, policy_version 64640 (0.0005) [2023-03-09 03:47:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10385.8). Total num frames: 33132544. Throughput: 0: 10676.1. Samples: 33129864. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:47:20,840][613581] Avg episode reward: [(0, '3986.910')] [2023-03-09 03:47:21,018][613885] Updated weights for policy 0, policy_version 64720 (0.0005) [2023-03-09 03:47:24,703][613885] Updated weights for policy 0, policy_version 64800 (0.0005) [2023-03-09 03:47:25,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10385.8). Total num frames: 33185792. Throughput: 0: 10713.7. Samples: 33164524. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:47:25,829][613581] Avg episode reward: [(0, '3931.565')] [2023-03-09 03:47:28,575][613885] Updated weights for policy 0, policy_version 64880 (0.0006) [2023-03-09 03:47:30,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10649.6, 300 sec: 10385.8). Total num frames: 33239040. Throughput: 0: 10659.5. Samples: 33226492. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:47:30,839][613581] Avg episode reward: [(0, '4326.177')] [2023-03-09 03:47:30,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000064920_33239040.pth... [2023-03-09 03:47:30,844][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000064304_32923648.pth [2023-03-09 03:47:32,671][613885] Updated weights for policy 0, policy_version 64960 (0.0005) [2023-03-09 03:47:35,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10385.8). Total num frames: 33292288. Throughput: 0: 10670.7. Samples: 33289360. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:47:35,829][613581] Avg episode reward: [(0, '3797.222')] [2023-03-09 03:47:36,262][613885] Updated weights for policy 0, policy_version 65040 (0.0005) [2023-03-09 03:47:40,364][613885] Updated weights for policy 0, policy_version 65120 (0.0005) [2023-03-09 03:47:40,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10399.7). Total num frames: 33345536. Throughput: 0: 10605.3. Samples: 33320968. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:47:40,840][613581] Avg episode reward: [(0, '4204.890')] [2023-03-09 03:47:44,464][613885] Updated weights for policy 0, policy_version 65200 (0.0005) [2023-03-09 03:47:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10581.3, 300 sec: 10385.8). Total num frames: 33394688. Throughput: 0: 10535.8. Samples: 33381052. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:47:45,840][613581] Avg episode reward: [(0, '3965.483')] [2023-03-09 03:47:45,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000065224_33394688.pth... [2023-03-09 03:47:45,843][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000064608_33079296.pth [2023-03-09 03:47:48,316][613885] Updated weights for policy 0, policy_version 65280 (0.0005) [2023-03-09 03:47:50,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10581.3, 300 sec: 10399.7). Total num frames: 33447936. Throughput: 0: 10476.8. Samples: 33444040. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:47:50,829][613581] Avg episode reward: [(0, '4018.185')] [2023-03-09 03:47:52,295][613885] Updated weights for policy 0, policy_version 65360 (0.0005) [2023-03-09 03:47:55,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.4, 300 sec: 10413.6). Total num frames: 33501184. Throughput: 0: 10531.4. Samples: 33476176. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:47:55,829][613581] Avg episode reward: [(0, '4032.170')] [2023-03-09 03:47:56,011][613885] Updated weights for policy 0, policy_version 65440 (0.0005) [2023-03-09 03:48:00,120][613885] Updated weights for policy 0, policy_version 65520 (0.0004) [2023-03-09 03:48:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10399.7). Total num frames: 33550336. Throughput: 0: 10513.4. Samples: 33538992. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:48:00,829][613581] Avg episode reward: [(0, '4110.258')] [2023-03-09 03:48:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000065528_33550336.pth... [2023-03-09 03:48:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000064920_33239040.pth [2023-03-09 03:48:04,190][613885] Updated weights for policy 0, policy_version 65600 (0.0005) [2023-03-09 03:48:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10376.6, 300 sec: 10385.8). Total num frames: 33599488. Throughput: 0: 10436.3. Samples: 33599496. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:48:05,829][613581] Avg episode reward: [(0, '4178.321')] [2023-03-09 03:48:08,173][613885] Updated weights for policy 0, policy_version 65680 (0.0005) [2023-03-09 03:48:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10385.8). Total num frames: 33652736. Throughput: 0: 10357.2. Samples: 33630600. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:48:10,829][613581] Avg episode reward: [(0, '4277.324')] [2023-03-09 03:48:12,330][613885] Updated weights for policy 0, policy_version 65760 (0.0005) [2023-03-09 03:48:15,829][613581] Fps is (10 sec: 10239.8, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 33701888. Throughput: 0: 10290.9. Samples: 33689580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:48:15,829][613581] Avg episode reward: [(0, '3600.536')] [2023-03-09 03:48:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000065824_33701888.pth... [2023-03-09 03:48:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000065224_33394688.pth [2023-03-09 03:48:16,441][613885] Updated weights for policy 0, policy_version 65840 (0.0005) [2023-03-09 03:48:20,191][613885] Updated weights for policy 0, policy_version 65920 (0.0004) [2023-03-09 03:48:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10385.8). Total num frames: 33755136. Throughput: 0: 10305.4. Samples: 33753104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:48:20,829][613581] Avg episode reward: [(0, '4091.986')] [2023-03-09 03:48:24,074][613885] Updated weights for policy 0, policy_version 66000 (0.0005) [2023-03-09 03:48:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10385.8). Total num frames: 33808384. Throughput: 0: 10320.7. Samples: 33785400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:48:25,829][613581] Avg episode reward: [(0, '4303.164')] [2023-03-09 03:48:27,890][613885] Updated weights for policy 0, policy_version 66080 (0.0005) [2023-03-09 03:48:30,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10444.8, 300 sec: 10413.6). Total num frames: 33865728. Throughput: 0: 10429.5. Samples: 33850380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:48:30,829][613581] Avg episode reward: [(0, '4246.395')] [2023-03-09 03:48:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000066144_33865728.pth... [2023-03-09 03:48:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000065528_33550336.pth [2023-03-09 03:48:31,432][613885] Updated weights for policy 0, policy_version 66160 (0.0005) [2023-03-09 03:48:35,355][613885] Updated weights for policy 0, policy_version 66240 (0.0005) [2023-03-09 03:48:35,829][613581] Fps is (10 sec: 11059.3, 60 sec: 10444.8, 300 sec: 10427.4). Total num frames: 33918976. Throughput: 0: 10464.6. Samples: 33914944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:48:35,840][613581] Avg episode reward: [(0, '3767.371')] [2023-03-09 03:48:39,137][613885] Updated weights for policy 0, policy_version 66320 (0.0005) [2023-03-09 03:48:40,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10444.8, 300 sec: 10455.2). Total num frames: 33972224. Throughput: 0: 10495.7. Samples: 33948484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:48:40,840][613581] Avg episode reward: [(0, '4069.456')] [2023-03-09 03:48:43,058][613885] Updated weights for policy 0, policy_version 66400 (0.0005) [2023-03-09 03:48:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10444.8, 300 sec: 10441.3). Total num frames: 34021376. Throughput: 0: 10452.3. Samples: 34009344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:48:45,840][613581] Avg episode reward: [(0, '4031.744')] [2023-03-09 03:48:45,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000066456_34025472.pth... [2023-03-09 03:48:45,845][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000065824_33701888.pth [2023-03-09 03:48:46,955][613885] Updated weights for policy 0, policy_version 66480 (0.0005) [2023-03-09 03:48:50,812][613885] Updated weights for policy 0, policy_version 66560 (0.0005) [2023-03-09 03:48:50,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10513.1, 300 sec: 10469.1). Total num frames: 34078720. Throughput: 0: 10558.6. Samples: 34074636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:48:50,830][613581] Avg episode reward: [(0, '4104.237')] [2023-03-09 03:48:54,850][613885] Updated weights for policy 0, policy_version 66640 (0.0005) [2023-03-09 03:48:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10469.1). Total num frames: 34127872. Throughput: 0: 10510.6. Samples: 34103576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:48:55,829][613581] Avg episode reward: [(0, '4084.831')] [2023-03-09 03:48:58,640][613885] Updated weights for policy 0, policy_version 66720 (0.0005) [2023-03-09 03:49:00,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10469.1). Total num frames: 34181120. Throughput: 0: 10649.3. Samples: 34168800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:49:00,829][613581] Avg episode reward: [(0, '3836.005')] [2023-03-09 03:49:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000066760_34181120.pth... [2023-03-09 03:49:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000066144_33865728.pth [2023-03-09 03:49:02,464][613885] Updated weights for policy 0, policy_version 66800 (0.0005) [2023-03-09 03:49:05,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.3, 300 sec: 10469.1). Total num frames: 34234368. Throughput: 0: 10636.7. Samples: 34231756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:49:05,829][613581] Avg episode reward: [(0, '4230.111')] [2023-03-09 03:49:06,379][613885] Updated weights for policy 0, policy_version 66880 (0.0006) [2023-03-09 03:49:10,133][613885] Updated weights for policy 0, policy_version 66960 (0.0005) [2023-03-09 03:49:10,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10581.3, 300 sec: 10469.1). Total num frames: 34287616. Throughput: 0: 10633.6. Samples: 34263912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:49:10,829][613581] Avg episode reward: [(0, '4148.535')] [2023-03-09 03:49:14,093][613885] Updated weights for policy 0, policy_version 67040 (0.0005) [2023-03-09 03:49:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10649.6, 300 sec: 10483.0). Total num frames: 34340864. Throughput: 0: 10608.5. Samples: 34327764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:49:15,829][613581] Avg episode reward: [(0, '4167.040')] [2023-03-09 03:49:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000067072_34340864.pth... [2023-03-09 03:49:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000066456_34025472.pth [2023-03-09 03:49:17,853][613885] Updated weights for policy 0, policy_version 67120 (0.0005) [2023-03-09 03:49:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10483.0). Total num frames: 34394112. Throughput: 0: 10604.2. Samples: 34392132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:49:20,829][613581] Avg episode reward: [(0, '4248.722')] [2023-03-09 03:49:21,876][613885] Updated weights for policy 0, policy_version 67200 (0.0005) [2023-03-09 03:49:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10581.3, 300 sec: 10469.1). Total num frames: 34443264. Throughput: 0: 10502.8. Samples: 34421112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:49:25,829][613581] Avg episode reward: [(0, '4399.532')] [2023-03-09 03:49:26,033][613885] Updated weights for policy 0, policy_version 67280 (0.0006) [2023-03-09 03:49:29,977][613885] Updated weights for policy 0, policy_version 67360 (0.0005) [2023-03-09 03:49:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10483.0). Total num frames: 34496512. Throughput: 0: 10469.4. Samples: 34480468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:49:30,829][613581] Avg episode reward: [(0, '4136.873')] [2023-03-09 03:49:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000067376_34496512.pth... [2023-03-09 03:49:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000066760_34181120.pth [2023-03-09 03:49:33,797][613885] Updated weights for policy 0, policy_version 67440 (0.0005) [2023-03-09 03:49:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10483.0). Total num frames: 34549760. Throughput: 0: 10507.1. Samples: 34547456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:49:35,829][613581] Avg episode reward: [(0, '4237.796')] [2023-03-09 03:49:37,591][613885] Updated weights for policy 0, policy_version 67520 (0.0005) [2023-03-09 03:49:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10496.9). Total num frames: 34603008. Throughput: 0: 10563.8. Samples: 34578948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:49:40,829][613581] Avg episode reward: [(0, '4320.503')] [2023-03-09 03:49:41,416][613885] Updated weights for policy 0, policy_version 67600 (0.0005) [2023-03-09 03:49:45,449][613885] Updated weights for policy 0, policy_version 67680 (0.0005) [2023-03-09 03:49:45,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10496.9). Total num frames: 34652160. Throughput: 0: 10476.5. Samples: 34640240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:49:45,829][613581] Avg episode reward: [(0, '4370.033')] [2023-03-09 03:49:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000067680_34652160.pth... [2023-03-09 03:49:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000067072_34340864.pth [2023-03-09 03:49:49,517][613885] Updated weights for policy 0, policy_version 67760 (0.0005) [2023-03-09 03:49:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10510.7). Total num frames: 34705408. Throughput: 0: 10436.0. Samples: 34701376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:49:50,829][613581] Avg episode reward: [(0, '4494.590')] [2023-03-09 03:49:53,347][613885] Updated weights for policy 0, policy_version 67840 (0.0004) [2023-03-09 03:49:55,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10513.1, 300 sec: 10510.8). Total num frames: 34758656. Throughput: 0: 10449.6. Samples: 34734144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:49:55,830][613581] Avg episode reward: [(0, '4520.466')] [2023-03-09 03:49:57,205][613885] Updated weights for policy 0, policy_version 67920 (0.0005) [2023-03-09 03:50:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10510.8). Total num frames: 34811904. Throughput: 0: 10477.7. Samples: 34799260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:50:00,829][613581] Avg episode reward: [(0, '4134.857')] [2023-03-09 03:50:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000067992_34811904.pth... [2023-03-09 03:50:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000067376_34496512.pth [2023-03-09 03:50:01,010][613885] Updated weights for policy 0, policy_version 68000 (0.0005) [2023-03-09 03:50:04,947][613885] Updated weights for policy 0, policy_version 68080 (0.0004) [2023-03-09 03:50:05,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10513.1, 300 sec: 10510.8). Total num frames: 34865152. Throughput: 0: 10450.2. Samples: 34862392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:50:05,829][613581] Avg episode reward: [(0, '4326.241')] [2023-03-09 03:50:08,608][613885] Updated weights for policy 0, policy_version 68160 (0.0005) [2023-03-09 03:50:10,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10513.1, 300 sec: 10510.8). Total num frames: 34918400. Throughput: 0: 10543.7. Samples: 34895576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:50:10,829][613581] Avg episode reward: [(0, '4498.781')] [2023-03-09 03:50:12,350][613885] Updated weights for policy 0, policy_version 68240 (0.0004) [2023-03-09 03:50:15,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10581.3, 300 sec: 10538.5). Total num frames: 34975744. Throughput: 0: 10702.7. Samples: 34962088. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:50:15,829][613581] Avg episode reward: [(0, '4392.088')] [2023-03-09 03:50:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000068312_34975744.pth... [2023-03-09 03:50:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000067680_34652160.pth [2023-03-09 03:50:16,102][613885] Updated weights for policy 0, policy_version 68320 (0.0004) [2023-03-09 03:50:19,816][613885] Updated weights for policy 0, policy_version 68400 (0.0005) [2023-03-09 03:50:20,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10581.3, 300 sec: 10538.5). Total num frames: 35028992. Throughput: 0: 10662.1. Samples: 35027252. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:50:20,829][613581] Avg episode reward: [(0, '4307.383')] [2023-03-09 03:50:23,623][613885] Updated weights for policy 0, policy_version 68480 (0.0005) [2023-03-09 03:50:25,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10538.5). Total num frames: 35082240. Throughput: 0: 10667.7. Samples: 35058996. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:50:25,829][613581] Avg episode reward: [(0, '4396.007')] [2023-03-09 03:50:27,588][613885] Updated weights for policy 0, policy_version 68560 (0.0005) [2023-03-09 03:50:30,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10538.5). Total num frames: 35135488. Throughput: 0: 10711.8. Samples: 35122272. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:50:30,829][613581] Avg episode reward: [(0, '4268.591')] [2023-03-09 03:50:30,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000068624_35135488.pth... [2023-03-09 03:50:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000067992_34811904.pth [2023-03-09 03:50:31,531][613885] Updated weights for policy 0, policy_version 68640 (0.0005) [2023-03-09 03:50:35,659][613885] Updated weights for policy 0, policy_version 68720 (0.0004) [2023-03-09 03:50:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10581.3, 300 sec: 10538.5). Total num frames: 35184640. Throughput: 0: 10670.2. Samples: 35181536. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:50:35,829][613581] Avg episode reward: [(0, '4410.586')] [2023-03-09 03:50:39,778][613885] Updated weights for policy 0, policy_version 68800 (0.0005) [2023-03-09 03:50:40,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10513.1, 300 sec: 10524.6). Total num frames: 35233792. Throughput: 0: 10643.1. Samples: 35213084. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:50:40,829][613581] Avg episode reward: [(0, '4305.672')] [2023-03-09 03:50:43,904][613885] Updated weights for policy 0, policy_version 68880 (0.0004) [2023-03-09 03:50:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10513.0, 300 sec: 10510.8). Total num frames: 35282944. Throughput: 0: 10481.8. Samples: 35270940. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:50:45,829][613581] Avg episode reward: [(0, '3932.686')] [2023-03-09 03:50:45,859][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000068920_35287040.pth... [2023-03-09 03:50:45,861][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000068312_34975744.pth [2023-03-09 03:50:47,787][613885] Updated weights for policy 0, policy_version 68960 (0.0005) [2023-03-09 03:50:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10524.6). Total num frames: 35336192. Throughput: 0: 10507.7. Samples: 35335240. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:50:50,829][613581] Avg episode reward: [(0, '3818.776')] [2023-03-09 03:50:51,676][613885] Updated weights for policy 0, policy_version 69040 (0.0005) [2023-03-09 03:50:55,417][613885] Updated weights for policy 0, policy_version 69120 (0.0005) [2023-03-09 03:50:55,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10581.3, 300 sec: 10538.5). Total num frames: 35393536. Throughput: 0: 10496.0. Samples: 35367896. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 03:50:55,829][613581] Avg episode reward: [(0, '4212.801')] [2023-03-09 03:50:59,318][613885] Updated weights for policy 0, policy_version 69200 (0.0005) [2023-03-09 03:51:00,829][613581] Fps is (10 sec: 11059.0, 60 sec: 10581.3, 300 sec: 10552.4). Total num frames: 35446784. Throughput: 0: 10411.1. Samples: 35430588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:51:00,830][613581] Avg episode reward: [(0, '3680.916')] [2023-03-09 03:51:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000069232_35446784.pth... [2023-03-09 03:51:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000068624_35135488.pth [2023-03-09 03:51:03,249][613885] Updated weights for policy 0, policy_version 69280 (0.0004) [2023-03-09 03:51:05,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10538.5). Total num frames: 35495936. Throughput: 0: 10389.1. Samples: 35494760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:51:05,829][613581] Avg episode reward: [(0, '4040.967')] [2023-03-09 03:51:07,227][613885] Updated weights for policy 0, policy_version 69360 (0.0005) [2023-03-09 03:51:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.0, 300 sec: 10538.5). Total num frames: 35549184. Throughput: 0: 10345.7. Samples: 35524552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:51:10,830][613581] Avg episode reward: [(0, '4283.155')] [2023-03-09 03:51:11,182][613885] Updated weights for policy 0, policy_version 69440 (0.0005) [2023-03-09 03:51:15,094][613885] Updated weights for policy 0, policy_version 69520 (0.0005) [2023-03-09 03:51:15,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10538.5). Total num frames: 35602432. Throughput: 0: 10308.2. Samples: 35586140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:51:15,829][613581] Avg episode reward: [(0, '4008.179')] [2023-03-09 03:51:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000069536_35602432.pth... [2023-03-09 03:51:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000068920_35287040.pth [2023-03-09 03:51:19,100][613885] Updated weights for policy 0, policy_version 69600 (0.0005) [2023-03-09 03:51:20,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10376.6, 300 sec: 10524.6). Total num frames: 35651584. Throughput: 0: 10403.1. Samples: 35649676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:51:20,829][613581] Avg episode reward: [(0, '4042.248')] [2023-03-09 03:51:22,904][613885] Updated weights for policy 0, policy_version 69680 (0.0005) [2023-03-09 03:51:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10524.6). Total num frames: 35704832. Throughput: 0: 10400.6. Samples: 35681112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:51:25,829][613581] Avg episode reward: [(0, '4280.923')] [2023-03-09 03:51:26,714][613885] Updated weights for policy 0, policy_version 69760 (0.0005) [2023-03-09 03:51:30,691][613885] Updated weights for policy 0, policy_version 69840 (0.0005) [2023-03-09 03:51:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10524.6). Total num frames: 35758080. Throughput: 0: 10509.1. Samples: 35743848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:51:30,829][613581] Avg episode reward: [(0, '4328.270')] [2023-03-09 03:51:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000069840_35758080.pth... [2023-03-09 03:51:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000069232_35446784.pth [2023-03-09 03:51:34,268][613885] Updated weights for policy 0, policy_version 69920 (0.0005) [2023-03-09 03:51:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10524.6). Total num frames: 35811328. Throughput: 0: 10568.7. Samples: 35810832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:51:35,829][613581] Avg episode reward: [(0, '4292.513')] [2023-03-09 03:51:38,189][613885] Updated weights for policy 0, policy_version 70000 (0.0004) [2023-03-09 03:51:40,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10513.1, 300 sec: 10524.6). Total num frames: 35864576. Throughput: 0: 10540.8. Samples: 35842232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:51:40,829][613581] Avg episode reward: [(0, '4225.059')] [2023-03-09 03:51:42,115][613885] Updated weights for policy 0, policy_version 70080 (0.0005) [2023-03-09 03:51:45,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10524.6). Total num frames: 35917824. Throughput: 0: 10533.3. Samples: 35904584. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:51:45,830][613581] Avg episode reward: [(0, '4277.374')] [2023-03-09 03:51:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000070152_35917824.pth... [2023-03-09 03:51:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000069536_35602432.pth [2023-03-09 03:51:46,139][613885] Updated weights for policy 0, policy_version 70160 (0.0005) [2023-03-09 03:51:50,267][613885] Updated weights for policy 0, policy_version 70240 (0.0005) [2023-03-09 03:51:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10510.8). Total num frames: 35966976. Throughput: 0: 10420.1. Samples: 35963664. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:51:50,829][613581] Avg episode reward: [(0, '4072.985')] [2023-03-09 03:51:54,405][613885] Updated weights for policy 0, policy_version 70320 (0.0005) [2023-03-09 03:51:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 10483.0). Total num frames: 36016128. Throughput: 0: 10439.7. Samples: 35994340. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:51:55,829][613581] Avg episode reward: [(0, '4139.441')] [2023-03-09 03:51:58,611][613885] Updated weights for policy 0, policy_version 70400 (0.0005) [2023-03-09 03:52:00,829][613581] Fps is (10 sec: 9830.2, 60 sec: 10308.3, 300 sec: 10469.1). Total num frames: 36065280. Throughput: 0: 10374.6. Samples: 36053000. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:52:00,830][613581] Avg episode reward: [(0, '4117.407')] [2023-03-09 03:52:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000070440_36065280.pth... [2023-03-09 03:52:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000069840_35758080.pth [2023-03-09 03:52:02,639][613885] Updated weights for policy 0, policy_version 70480 (0.0005) [2023-03-09 03:52:05,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10308.3, 300 sec: 10469.1). Total num frames: 36114432. Throughput: 0: 10306.0. Samples: 36113448. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:52:05,829][613581] Avg episode reward: [(0, '4293.116')] [2023-03-09 03:52:06,757][613885] Updated weights for policy 0, policy_version 70560 (0.0005) [2023-03-09 03:52:10,682][613885] Updated weights for policy 0, policy_version 70640 (0.0005) [2023-03-09 03:52:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10469.1). Total num frames: 36167680. Throughput: 0: 10276.2. Samples: 36143544. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:52:10,829][613581] Avg episode reward: [(0, '4137.514')] [2023-03-09 03:52:14,770][613885] Updated weights for policy 0, policy_version 70720 (0.0005) [2023-03-09 03:52:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10455.2). Total num frames: 36216832. Throughput: 0: 10237.9. Samples: 36204552. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:52:15,829][613581] Avg episode reward: [(0, '4276.075')] [2023-03-09 03:52:15,848][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000070744_36220928.pth... [2023-03-09 03:52:15,850][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000070152_35917824.pth [2023-03-09 03:52:18,502][613885] Updated weights for policy 0, policy_version 70800 (0.0005) [2023-03-09 03:52:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10455.2). Total num frames: 36270080. Throughput: 0: 10184.1. Samples: 36269116. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 03:52:20,829][613581] Avg episode reward: [(0, '4160.183')] [2023-03-09 03:52:22,523][613885] Updated weights for policy 0, policy_version 70880 (0.0004) [2023-03-09 03:52:25,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10455.2). Total num frames: 36323328. Throughput: 0: 10146.3. Samples: 36298816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:52:25,829][613581] Avg episode reward: [(0, '4080.428')] [2023-03-09 03:52:26,487][613885] Updated weights for policy 0, policy_version 70960 (0.0005) [2023-03-09 03:52:30,573][613885] Updated weights for policy 0, policy_version 71040 (0.0005) [2023-03-09 03:52:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10441.3). Total num frames: 36372480. Throughput: 0: 10124.8. Samples: 36360200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:52:30,829][613581] Avg episode reward: [(0, '3980.196')] [2023-03-09 03:52:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000071040_36372480.pth... [2023-03-09 03:52:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000070440_36065280.pth [2023-03-09 03:52:34,310][613885] Updated weights for policy 0, policy_version 71120 (0.0005) [2023-03-09 03:52:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10441.3). Total num frames: 36425728. Throughput: 0: 10230.7. Samples: 36424048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:52:35,829][613581] Avg episode reward: [(0, '4141.858')] [2023-03-09 03:52:38,523][613885] Updated weights for policy 0, policy_version 71200 (0.0005) [2023-03-09 03:52:40,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10441.3). Total num frames: 36474880. Throughput: 0: 10214.9. Samples: 36454008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:52:40,829][613581] Avg episode reward: [(0, '3283.939')] [2023-03-09 03:52:42,512][613885] Updated weights for policy 0, policy_version 71280 (0.0005) [2023-03-09 03:52:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10441.3). Total num frames: 36528128. Throughput: 0: 10272.0. Samples: 36515240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:52:45,829][613581] Avg episode reward: [(0, '2160.694')] [2023-03-09 03:52:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000071344_36528128.pth... [2023-03-09 03:52:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000070744_36220928.pth [2023-03-09 03:52:46,493][613885] Updated weights for policy 0, policy_version 71360 (0.0005) [2023-03-09 03:52:50,735][613885] Updated weights for policy 0, policy_version 71440 (0.0005) [2023-03-09 03:52:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10427.4). Total num frames: 36577280. Throughput: 0: 10218.9. Samples: 36573300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:52:50,829][613581] Avg episode reward: [(0, '2984.736')] [2023-03-09 03:52:54,927][613885] Updated weights for policy 0, policy_version 71520 (0.0004) [2023-03-09 03:52:55,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10171.7, 300 sec: 10427.4). Total num frames: 36626432. Throughput: 0: 10220.7. Samples: 36603476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:52:55,829][613581] Avg episode reward: [(0, '2790.781')] [2023-03-09 03:52:58,955][613885] Updated weights for policy 0, policy_version 71600 (0.0005) [2023-03-09 03:53:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.8, 300 sec: 10427.4). Total num frames: 36675584. Throughput: 0: 10200.8. Samples: 36663588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:53:00,829][613581] Avg episode reward: [(0, '2759.345')] [2023-03-09 03:53:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000071632_36675584.pth... [2023-03-09 03:53:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000071040_36372480.pth [2023-03-09 03:53:03,199][613885] Updated weights for policy 0, policy_version 71680 (0.0004) [2023-03-09 03:53:05,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10171.7, 300 sec: 10413.6). Total num frames: 36724736. Throughput: 0: 10042.8. Samples: 36721040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:53:05,829][613581] Avg episode reward: [(0, '2879.809')] [2023-03-09 03:53:07,296][613885] Updated weights for policy 0, policy_version 71760 (0.0005) [2023-03-09 03:53:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10427.4). Total num frames: 36777984. Throughput: 0: 10099.8. Samples: 36753308. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:53:10,829][613581] Avg episode reward: [(0, '3880.925')] [2023-03-09 03:53:11,088][613885] Updated weights for policy 0, policy_version 71840 (0.0005) [2023-03-09 03:53:15,170][613885] Updated weights for policy 0, policy_version 71920 (0.0005) [2023-03-09 03:53:15,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10413.6). Total num frames: 36827136. Throughput: 0: 10104.7. Samples: 36814912. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:53:15,829][613581] Avg episode reward: [(0, '4134.180')] [2023-03-09 03:53:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000071928_36827136.pth... [2023-03-09 03:53:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000071344_36528128.pth [2023-03-09 03:53:19,138][613885] Updated weights for policy 0, policy_version 72000 (0.0005) [2023-03-09 03:53:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10413.6). Total num frames: 36880384. Throughput: 0: 10063.9. Samples: 36876924. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:53:20,829][613581] Avg episode reward: [(0, '3930.210')] [2023-03-09 03:53:23,054][613885] Updated weights for policy 0, policy_version 72080 (0.0005) [2023-03-09 03:53:25,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10171.7, 300 sec: 10399.7). Total num frames: 36933632. Throughput: 0: 10112.0. Samples: 36909048. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:53:25,829][613581] Avg episode reward: [(0, '3981.267')] [2023-03-09 03:53:26,826][613885] Updated weights for policy 0, policy_version 72160 (0.0005) [2023-03-09 03:53:30,801][613885] Updated weights for policy 0, policy_version 72240 (0.0005) [2023-03-09 03:53:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10240.0, 300 sec: 10399.7). Total num frames: 36986880. Throughput: 0: 10148.2. Samples: 36971908. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:53:30,829][613581] Avg episode reward: [(0, '3804.852')] [2023-03-09 03:53:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000072240_36986880.pth... [2023-03-09 03:53:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000071632_36675584.pth [2023-03-09 03:53:34,679][613885] Updated weights for policy 0, policy_version 72320 (0.0004) [2023-03-09 03:53:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10385.8). Total num frames: 37036032. Throughput: 0: 10282.3. Samples: 37036004. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:53:35,829][613581] Avg episode reward: [(0, '4041.542')] [2023-03-09 03:53:38,556][613885] Updated weights for policy 0, policy_version 72400 (0.0005) [2023-03-09 03:53:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10399.7). Total num frames: 37089280. Throughput: 0: 10310.1. Samples: 37067432. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:53:40,829][613581] Avg episode reward: [(0, '4087.003')] [2023-03-09 03:53:42,560][613885] Updated weights for policy 0, policy_version 72480 (0.0005) [2023-03-09 03:53:45,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10240.0, 300 sec: 10385.8). Total num frames: 37142528. Throughput: 0: 10325.0. Samples: 37128212. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:53:45,829][613581] Avg episode reward: [(0, '4352.275')] [2023-03-09 03:53:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000072544_37142528.pth... [2023-03-09 03:53:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000071928_36827136.pth [2023-03-09 03:53:46,443][613885] Updated weights for policy 0, policy_version 72560 (0.0004) [2023-03-09 03:53:50,441][613885] Updated weights for policy 0, policy_version 72640 (0.0005) [2023-03-09 03:53:50,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10308.3, 300 sec: 10399.7). Total num frames: 37195776. Throughput: 0: 10457.0. Samples: 37191604. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 03:53:50,840][613581] Avg episode reward: [(0, '4427.836')] [2023-03-09 03:53:54,424][613885] Updated weights for policy 0, policy_version 72720 (0.0005) [2023-03-09 03:53:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10385.8). Total num frames: 37244928. Throughput: 0: 10419.1. Samples: 37222168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:53:55,840][613581] Avg episode reward: [(0, '4226.542')] [2023-03-09 03:53:58,355][613885] Updated weights for policy 0, policy_version 72800 (0.0006) [2023-03-09 03:54:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10385.8). Total num frames: 37298176. Throughput: 0: 10422.2. Samples: 37283912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:54:00,830][613581] Avg episode reward: [(0, '4368.597')] [2023-03-09 03:54:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000072848_37298176.pth... [2023-03-09 03:54:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000072240_36986880.pth [2023-03-09 03:54:02,346][613885] Updated weights for policy 0, policy_version 72880 (0.0005) [2023-03-09 03:54:05,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 37347328. Throughput: 0: 10385.8. Samples: 37344284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:54:05,829][613581] Avg episode reward: [(0, '3959.630')] [2023-03-09 03:54:06,454][613885] Updated weights for policy 0, policy_version 72960 (0.0005) [2023-03-09 03:54:10,159][613885] Updated weights for policy 0, policy_version 73040 (0.0005) [2023-03-09 03:54:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 37400576. Throughput: 0: 10415.2. Samples: 37377732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:54:10,829][613581] Avg episode reward: [(0, '4273.320')] [2023-03-09 03:54:14,130][613885] Updated weights for policy 0, policy_version 73120 (0.0005) [2023-03-09 03:54:15,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10371.9). Total num frames: 37453824. Throughput: 0: 10409.7. Samples: 37440344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:54:15,829][613581] Avg episode reward: [(0, '4129.584')] [2023-03-09 03:54:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000073152_37453824.pth... [2023-03-09 03:54:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000072544_37142528.pth [2023-03-09 03:54:18,150][613885] Updated weights for policy 0, policy_version 73200 (0.0004) [2023-03-09 03:54:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10385.8). Total num frames: 37507072. Throughput: 0: 10378.9. Samples: 37503056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:54:20,829][613581] Avg episode reward: [(0, '4240.533')] [2023-03-09 03:54:21,790][613885] Updated weights for policy 0, policy_version 73280 (0.0005) [2023-03-09 03:54:25,813][613885] Updated weights for policy 0, policy_version 73360 (0.0005) [2023-03-09 03:54:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10385.8). Total num frames: 37560320. Throughput: 0: 10406.7. Samples: 37535736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:54:25,829][613581] Avg episode reward: [(0, '4096.469')] [2023-03-09 03:54:29,676][613885] Updated weights for policy 0, policy_version 73440 (0.0004) [2023-03-09 03:54:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 37609472. Throughput: 0: 10423.0. Samples: 37597248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:54:30,829][613581] Avg episode reward: [(0, '4116.082')] [2023-03-09 03:54:30,850][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000073464_37613568.pth... [2023-03-09 03:54:30,852][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000072848_37298176.pth [2023-03-09 03:54:33,938][613885] Updated weights for policy 0, policy_version 73520 (0.0005) [2023-03-09 03:54:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 37658624. Throughput: 0: 10302.9. Samples: 37655236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:54:35,829][613581] Avg episode reward: [(0, '3958.886')] [2023-03-09 03:54:37,997][613885] Updated weights for policy 0, policy_version 73600 (0.0006) [2023-03-09 03:54:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 10358.0). Total num frames: 37707776. Throughput: 0: 10335.0. Samples: 37687244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:54:40,829][613581] Avg episode reward: [(0, '4208.897')] [2023-03-09 03:54:42,069][613885] Updated weights for policy 0, policy_version 73680 (0.0004) [2023-03-09 03:54:45,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10358.0). Total num frames: 37761024. Throughput: 0: 10308.2. Samples: 37747780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:54:45,829][613581] Avg episode reward: [(0, '4101.293')] [2023-03-09 03:54:45,890][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000073760_37765120.pth... [2023-03-09 03:54:45,890][613885] Updated weights for policy 0, policy_version 73760 (0.0004) [2023-03-09 03:54:45,891][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000073152_37453824.pth [2023-03-09 03:54:50,007][613885] Updated weights for policy 0, policy_version 73840 (0.0005) [2023-03-09 03:54:50,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.2, 300 sec: 10358.0). Total num frames: 37814272. Throughput: 0: 10354.6. Samples: 37810240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:54:50,830][613581] Avg episode reward: [(0, '4146.723')] [2023-03-09 03:54:53,963][613885] Updated weights for policy 0, policy_version 73920 (0.0005) [2023-03-09 03:54:55,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 37867520. Throughput: 0: 10296.7. Samples: 37841084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:54:55,829][613581] Avg episode reward: [(0, '4133.348')] [2023-03-09 03:54:57,499][613885] Updated weights for policy 0, policy_version 74000 (0.0005) [2023-03-09 03:55:00,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 37920768. Throughput: 0: 10398.2. Samples: 37908260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:55:00,829][613581] Avg episode reward: [(0, '3840.456')] [2023-03-09 03:55:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000074064_37920768.pth... [2023-03-09 03:55:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000073464_37613568.pth [2023-03-09 03:55:01,340][613885] Updated weights for policy 0, policy_version 74080 (0.0006) [2023-03-09 03:55:05,284][613885] Updated weights for policy 0, policy_version 74160 (0.0005) [2023-03-09 03:55:05,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10444.8, 300 sec: 10358.0). Total num frames: 37974016. Throughput: 0: 10388.2. Samples: 37970524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:55:05,829][613581] Avg episode reward: [(0, '4154.560')] [2023-03-09 03:55:09,115][613885] Updated weights for policy 0, policy_version 74240 (0.0006) [2023-03-09 03:55:10,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10344.1). Total num frames: 38027264. Throughput: 0: 10378.3. Samples: 38002760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:55:10,829][613581] Avg episode reward: [(0, '3834.219')] [2023-03-09 03:55:13,328][613885] Updated weights for policy 0, policy_version 74320 (0.0005) [2023-03-09 03:55:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10330.2). Total num frames: 38076416. Throughput: 0: 10369.4. Samples: 38063872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:55:15,829][613581] Avg episode reward: [(0, '3921.208')] [2023-03-09 03:55:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000074368_38076416.pth... [2023-03-09 03:55:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000073760_37765120.pth [2023-03-09 03:55:17,402][613885] Updated weights for policy 0, policy_version 74400 (0.0005) [2023-03-09 03:55:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 10316.4). Total num frames: 38125568. Throughput: 0: 10373.7. Samples: 38122052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:55:20,830][613581] Avg episode reward: [(0, '3711.710')] [2023-03-09 03:55:21,660][613885] Updated weights for policy 0, policy_version 74480 (0.0005) [2023-03-09 03:55:25,331][613885] Updated weights for policy 0, policy_version 74560 (0.0005) [2023-03-09 03:55:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10316.4). Total num frames: 38178816. Throughput: 0: 10312.1. Samples: 38151288. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:55:25,829][613581] Avg episode reward: [(0, '3827.195')] [2023-03-09 03:55:29,420][613885] Updated weights for policy 0, policy_version 74640 (0.0004) [2023-03-09 03:55:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.2, 300 sec: 10316.4). Total num frames: 38227968. Throughput: 0: 10397.7. Samples: 38215676. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:55:30,829][613581] Avg episode reward: [(0, '4073.516')] [2023-03-09 03:55:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000074664_38227968.pth... [2023-03-09 03:55:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000074064_37920768.pth [2023-03-09 03:55:33,500][613885] Updated weights for policy 0, policy_version 74720 (0.0005) [2023-03-09 03:55:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 10316.4). Total num frames: 38277120. Throughput: 0: 10349.5. Samples: 38275964. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:55:35,829][613581] Avg episode reward: [(0, '4169.075')] [2023-03-09 03:55:37,444][613885] Updated weights for policy 0, policy_version 74800 (0.0005) [2023-03-09 03:55:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10344.1). Total num frames: 38334464. Throughput: 0: 10387.2. Samples: 38308508. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:55:40,830][613581] Avg episode reward: [(0, '4259.839')] [2023-03-09 03:55:41,206][613885] Updated weights for policy 0, policy_version 74880 (0.0005) [2023-03-09 03:55:45,116][613885] Updated weights for policy 0, policy_version 74960 (0.0005) [2023-03-09 03:55:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10330.3). Total num frames: 38383616. Throughput: 0: 10292.0. Samples: 38371400. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:55:45,829][613581] Avg episode reward: [(0, '4334.429')] [2023-03-09 03:55:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000074968_38383616.pth... [2023-03-09 03:55:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000074368_38076416.pth [2023-03-09 03:55:49,174][613885] Updated weights for policy 0, policy_version 75040 (0.0005) [2023-03-09 03:55:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.6, 300 sec: 10316.4). Total num frames: 38436864. Throughput: 0: 10273.5. Samples: 38432832. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:55:50,829][613581] Avg episode reward: [(0, '4295.525')] [2023-03-09 03:55:53,146][613885] Updated weights for policy 0, policy_version 75120 (0.0005) [2023-03-09 03:55:55,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 10316.4). Total num frames: 38490112. Throughput: 0: 10250.2. Samples: 38464020. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:55:55,829][613581] Avg episode reward: [(0, '4330.850')] [2023-03-09 03:55:56,965][613885] Updated weights for policy 0, policy_version 75200 (0.0005) [2023-03-09 03:56:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10316.4). Total num frames: 38539264. Throughput: 0: 10284.0. Samples: 38526652. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:56:00,829][613581] Avg episode reward: [(0, '4295.072')] [2023-03-09 03:56:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000075272_38539264.pth... [2023-03-09 03:56:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000074664_38227968.pth [2023-03-09 03:56:01,073][613885] Updated weights for policy 0, policy_version 75280 (0.0005) [2023-03-09 03:56:05,133][613885] Updated weights for policy 0, policy_version 75360 (0.0005) [2023-03-09 03:56:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10302.5). Total num frames: 38588416. Throughput: 0: 10345.3. Samples: 38587588. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:56:05,829][613581] Avg episode reward: [(0, '4503.504')] [2023-03-09 03:56:08,816][613885] Updated weights for policy 0, policy_version 75440 (0.0005) [2023-03-09 03:56:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10316.4). Total num frames: 38645760. Throughput: 0: 10442.3. Samples: 38621192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:56:10,829][613581] Avg episode reward: [(0, '4469.923')] [2023-03-09 03:56:12,542][613885] Updated weights for policy 0, policy_version 75520 (0.0005) [2023-03-09 03:56:15,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10376.5, 300 sec: 10330.2). Total num frames: 38699008. Throughput: 0: 10456.0. Samples: 38686196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:56:15,829][613581] Avg episode reward: [(0, '4518.793')] [2023-03-09 03:56:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000075584_38699008.pth... [2023-03-09 03:56:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000074968_38383616.pth [2023-03-09 03:56:16,544][613885] Updated weights for policy 0, policy_version 75600 (0.0005) [2023-03-09 03:56:20,441][613885] Updated weights for policy 0, policy_version 75680 (0.0005) [2023-03-09 03:56:20,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.6, 300 sec: 10316.4). Total num frames: 38748160. Throughput: 0: 10489.9. Samples: 38748008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:56:20,829][613581] Avg episode reward: [(0, '4465.545')] [2023-03-09 03:56:24,726][613885] Updated weights for policy 0, policy_version 75760 (0.0005) [2023-03-09 03:56:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 38797312. Throughput: 0: 10403.1. Samples: 38776644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:56:25,829][613581] Avg episode reward: [(0, '4303.889')] [2023-03-09 03:56:28,831][613885] Updated weights for policy 0, policy_version 75840 (0.0004) [2023-03-09 03:56:30,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 38846464. Throughput: 0: 10316.8. Samples: 38835656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:56:30,829][613581] Avg episode reward: [(0, '4464.361')] [2023-03-09 03:56:30,847][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000075880_38850560.pth... [2023-03-09 03:56:30,848][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000075272_38539264.pth [2023-03-09 03:56:32,785][613885] Updated weights for policy 0, policy_version 75920 (0.0005) [2023-03-09 03:56:35,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10288.6). Total num frames: 38899712. Throughput: 0: 10293.1. Samples: 38896024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:56:35,829][613581] Avg episode reward: [(0, '4527.633')] [2023-03-09 03:56:36,919][613885] Updated weights for policy 0, policy_version 76000 (0.0004) [2023-03-09 03:56:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10274.7). Total num frames: 38948864. Throughput: 0: 10312.3. Samples: 38928072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:56:40,829][613581] Avg episode reward: [(0, '4350.917')] [2023-03-09 03:56:40,889][613885] Updated weights for policy 0, policy_version 76080 (0.0005) [2023-03-09 03:56:44,945][613885] Updated weights for policy 0, policy_version 76160 (0.0005) [2023-03-09 03:56:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.2, 300 sec: 10288.6). Total num frames: 39002112. Throughput: 0: 10247.8. Samples: 38987804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:56:45,829][613581] Avg episode reward: [(0, '4423.355')] [2023-03-09 03:56:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000076176_39002112.pth... [2023-03-09 03:56:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000075584_38699008.pth [2023-03-09 03:56:48,619][613885] Updated weights for policy 0, policy_version 76240 (0.0005) [2023-03-09 03:56:50,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 39055360. Throughput: 0: 10369.9. Samples: 39054232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:56:50,829][613581] Avg episode reward: [(0, '4459.955')] [2023-03-09 03:56:52,346][613885] Updated weights for policy 0, policy_version 76320 (0.0004) [2023-03-09 03:56:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10316.4). Total num frames: 39108608. Throughput: 0: 10328.7. Samples: 39085984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:56:55,829][613581] Avg episode reward: [(0, '4494.292')] [2023-03-09 03:56:56,521][613885] Updated weights for policy 0, policy_version 76400 (0.0004) [2023-03-09 03:57:00,440][613885] Updated weights for policy 0, policy_version 76480 (0.0005) [2023-03-09 03:57:00,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 10330.2). Total num frames: 39161856. Throughput: 0: 10230.7. Samples: 39146576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:57:00,830][613581] Avg episode reward: [(0, '4258.762')] [2023-03-09 03:57:00,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000076488_39161856.pth... [2023-03-09 03:57:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000075880_38850560.pth [2023-03-09 03:57:04,632][613885] Updated weights for policy 0, policy_version 76560 (0.0005) [2023-03-09 03:57:05,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 39206912. Throughput: 0: 10197.9. Samples: 39206912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:57:05,829][613581] Avg episode reward: [(0, '4416.546')] [2023-03-09 03:57:08,691][613885] Updated weights for policy 0, policy_version 76640 (0.0005) [2023-03-09 03:57:10,829][613581] Fps is (10 sec: 9421.0, 60 sec: 10171.8, 300 sec: 10302.5). Total num frames: 39256064. Throughput: 0: 10200.1. Samples: 39235648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:57:10,829][613581] Avg episode reward: [(0, '4299.204')] [2023-03-09 03:57:12,981][613885] Updated weights for policy 0, policy_version 76720 (0.0005) [2023-03-09 03:57:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 10302.5). Total num frames: 39309312. Throughput: 0: 10209.0. Samples: 39295060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:57:15,829][613581] Avg episode reward: [(0, '4478.482')] [2023-03-09 03:57:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000076776_39309312.pth... [2023-03-09 03:57:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000076176_39002112.pth [2023-03-09 03:57:17,000][613885] Updated weights for policy 0, policy_version 76800 (0.0005) [2023-03-09 03:57:20,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 10288.6). Total num frames: 39358464. Throughput: 0: 10202.8. Samples: 39355152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:57:20,829][613581] Avg episode reward: [(0, '4517.558')] [2023-03-09 03:57:21,084][613885] Updated weights for policy 0, policy_version 76880 (0.0005) [2023-03-09 03:57:25,144][613885] Updated weights for policy 0, policy_version 76960 (0.0005) [2023-03-09 03:57:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.7, 300 sec: 10288.6). Total num frames: 39407616. Throughput: 0: 10180.8. Samples: 39386208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:57:25,829][613581] Avg episode reward: [(0, '4457.302')] [2023-03-09 03:57:29,275][613885] Updated weights for policy 0, policy_version 77040 (0.0005) [2023-03-09 03:57:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.7, 300 sec: 10274.7). Total num frames: 39456768. Throughput: 0: 10165.2. Samples: 39445236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:57:30,829][613581] Avg episode reward: [(0, '4449.759')] [2023-03-09 03:57:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000077064_39456768.pth... [2023-03-09 03:57:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000076488_39161856.pth [2023-03-09 03:57:33,368][613885] Updated weights for policy 0, policy_version 77120 (0.0005) [2023-03-09 03:57:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10274.7). Total num frames: 39505920. Throughput: 0: 10008.2. Samples: 39504600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:57:35,829][613581] Avg episode reward: [(0, '4530.144')] [2023-03-09 03:57:37,586][613885] Updated weights for policy 0, policy_version 77200 (0.0004) [2023-03-09 03:57:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10260.8). Total num frames: 39555072. Throughput: 0: 9960.2. Samples: 39534192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 03:57:40,829][613581] Avg episode reward: [(0, '4494.708')] [2023-03-09 03:57:41,838][613885] Updated weights for policy 0, policy_version 77280 (0.0005) [2023-03-09 03:57:45,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10260.8). Total num frames: 39604224. Throughput: 0: 9906.6. Samples: 39592372. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:57:45,829][613581] Avg episode reward: [(0, '4506.918')] [2023-03-09 03:57:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000077352_39604224.pth... [2023-03-09 03:57:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000076776_39309312.pth [2023-03-09 03:57:45,893][613885] Updated weights for policy 0, policy_version 77360 (0.0004) [2023-03-09 03:57:49,764][613885] Updated weights for policy 0, policy_version 77440 (0.0005) [2023-03-09 03:57:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10035.2, 300 sec: 10274.7). Total num frames: 39657472. Throughput: 0: 10002.8. Samples: 39657036. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:57:50,829][613581] Avg episode reward: [(0, '4456.840')] [2023-03-09 03:57:53,770][613885] Updated weights for policy 0, policy_version 77520 (0.0005) [2023-03-09 03:57:55,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10035.2, 300 sec: 10288.6). Total num frames: 39710720. Throughput: 0: 10010.0. Samples: 39686100. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:57:55,830][613581] Avg episode reward: [(0, '4443.090')] [2023-03-09 03:57:57,668][613885] Updated weights for policy 0, policy_version 77600 (0.0004) [2023-03-09 03:58:00,829][613581] Fps is (10 sec: 10649.3, 60 sec: 10035.2, 300 sec: 10302.5). Total num frames: 39763968. Throughput: 0: 10121.1. Samples: 39750512. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:58:00,830][613581] Avg episode reward: [(0, '4445.429')] [2023-03-09 03:58:00,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000077664_39763968.pth... [2023-03-09 03:58:00,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000077064_39456768.pth [2023-03-09 03:58:01,494][613885] Updated weights for policy 0, policy_version 77680 (0.0004) [2023-03-09 03:58:05,231][613885] Updated weights for policy 0, policy_version 77760 (0.0004) [2023-03-09 03:58:05,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10171.7, 300 sec: 10302.5). Total num frames: 39817216. Throughput: 0: 10210.8. Samples: 39814640. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:58:05,829][613581] Avg episode reward: [(0, '4357.390')] [2023-03-09 03:58:09,186][613885] Updated weights for policy 0, policy_version 77840 (0.0004) [2023-03-09 03:58:10,829][613581] Fps is (10 sec: 10649.8, 60 sec: 10240.0, 300 sec: 10316.4). Total num frames: 39870464. Throughput: 0: 10215.4. Samples: 39845900. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:58:10,829][613581] Avg episode reward: [(0, '4462.413')] [2023-03-09 03:58:13,338][613885] Updated weights for policy 0, policy_version 77920 (0.0004) [2023-03-09 03:58:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10302.5). Total num frames: 39919616. Throughput: 0: 10249.5. Samples: 39906464. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:58:15,829][613581] Avg episode reward: [(0, '4515.743')] [2023-03-09 03:58:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000077968_39919616.pth... [2023-03-09 03:58:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000077352_39604224.pth [2023-03-09 03:58:17,103][613885] Updated weights for policy 0, policy_version 78000 (0.0005) [2023-03-09 03:58:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10302.5). Total num frames: 39972864. Throughput: 0: 10336.1. Samples: 39969724. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:58:20,829][613581] Avg episode reward: [(0, '4184.218')] [2023-03-09 03:58:21,066][613885] Updated weights for policy 0, policy_version 78080 (0.0004) [2023-03-09 03:58:25,048][613885] Updated weights for policy 0, policy_version 78160 (0.0004) [2023-03-09 03:58:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 40022016. Throughput: 0: 10374.6. Samples: 40001048. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 03:58:25,829][613581] Avg episode reward: [(0, '4181.343')] [2023-03-09 03:58:28,816][613885] Updated weights for policy 0, policy_version 78240 (0.0004) [2023-03-09 03:58:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 10316.4). Total num frames: 40079360. Throughput: 0: 10498.3. Samples: 40064796. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:58:30,829][613581] Avg episode reward: [(0, '4319.227')] [2023-03-09 03:58:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000078280_40079360.pth... [2023-03-09 03:58:30,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000077664_39763968.pth [2023-03-09 03:58:32,743][613885] Updated weights for policy 0, policy_version 78320 (0.0005) [2023-03-09 03:58:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.6, 300 sec: 10302.5). Total num frames: 40128512. Throughput: 0: 10465.1. Samples: 40127964. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:58:35,829][613581] Avg episode reward: [(0, '4386.084')] [2023-03-09 03:58:36,835][613885] Updated weights for policy 0, policy_version 78400 (0.0005) [2023-03-09 03:58:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10376.5, 300 sec: 10288.6). Total num frames: 40177664. Throughput: 0: 10463.9. Samples: 40156976. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:58:40,829][613581] Avg episode reward: [(0, '4434.562')] [2023-03-09 03:58:40,841][613885] Updated weights for policy 0, policy_version 78480 (0.0005) [2023-03-09 03:58:45,105][613885] Updated weights for policy 0, policy_version 78560 (0.0004) [2023-03-09 03:58:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 10274.7). Total num frames: 40226816. Throughput: 0: 10321.1. Samples: 40214960. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:58:45,829][613581] Avg episode reward: [(0, '4212.940')] [2023-03-09 03:58:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000078568_40226816.pth... [2023-03-09 03:58:45,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000077968_39919616.pth [2023-03-09 03:58:49,300][613885] Updated weights for policy 0, policy_version 78640 (0.0005) [2023-03-09 03:58:50,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10308.3, 300 sec: 10274.7). Total num frames: 40275968. Throughput: 0: 10232.4. Samples: 40275096. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:58:50,829][613581] Avg episode reward: [(0, '4229.297')] [2023-03-09 03:58:53,383][613885] Updated weights for policy 0, policy_version 78720 (0.0005) [2023-03-09 03:58:55,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10240.0, 300 sec: 10260.8). Total num frames: 40325120. Throughput: 0: 10194.5. Samples: 40304652. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:58:55,829][613581] Avg episode reward: [(0, '4199.621')] [2023-03-09 03:58:57,618][613885] Updated weights for policy 0, policy_version 78800 (0.0004) [2023-03-09 03:59:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10171.8, 300 sec: 10260.8). Total num frames: 40374272. Throughput: 0: 10156.4. Samples: 40363500. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:59:00,829][613581] Avg episode reward: [(0, '4011.415')] [2023-03-09 03:59:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000078856_40374272.pth... [2023-03-09 03:59:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000078280_40079360.pth [2023-03-09 03:59:01,634][613885] Updated weights for policy 0, policy_version 78880 (0.0004) [2023-03-09 03:59:05,790][613885] Updated weights for policy 0, policy_version 78960 (0.0005) [2023-03-09 03:59:05,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10260.8). Total num frames: 40427520. Throughput: 0: 10081.5. Samples: 40423392. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:59:05,829][613581] Avg episode reward: [(0, '4266.736')] [2023-03-09 03:59:09,489][613885] Updated weights for policy 0, policy_version 79040 (0.0005) [2023-03-09 03:59:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10171.7, 300 sec: 10260.8). Total num frames: 40480768. Throughput: 0: 10115.9. Samples: 40456264. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:59:10,829][613581] Avg episode reward: [(0, '4546.790')] [2023-03-09 03:59:13,637][613885] Updated weights for policy 0, policy_version 79120 (0.0005) [2023-03-09 03:59:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 10246.9). Total num frames: 40529920. Throughput: 0: 10059.3. Samples: 40517464. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 03:59:15,829][613581] Avg episode reward: [(0, '4408.001')] [2023-03-09 03:59:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000079160_40529920.pth... [2023-03-09 03:59:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000078568_40226816.pth [2023-03-09 03:59:17,726][613885] Updated weights for policy 0, policy_version 79200 (0.0005) [2023-03-09 03:59:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10246.9). Total num frames: 40583168. Throughput: 0: 10026.2. Samples: 40579144. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:59:20,829][613581] Avg episode reward: [(0, '4130.204')] [2023-03-09 03:59:21,544][613885] Updated weights for policy 0, policy_version 79280 (0.0005) [2023-03-09 03:59:25,617][613885] Updated weights for policy 0, policy_version 79360 (0.0004) [2023-03-09 03:59:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10246.9). Total num frames: 40632320. Throughput: 0: 10050.5. Samples: 40609252. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:59:25,829][613581] Avg episode reward: [(0, '4404.838')] [2023-03-09 03:59:29,687][613885] Updated weights for policy 0, policy_version 79440 (0.0005) [2023-03-09 03:59:30,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10246.9). Total num frames: 40681472. Throughput: 0: 10111.2. Samples: 40669964. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:59:30,829][613581] Avg episode reward: [(0, '4393.057')] [2023-03-09 03:59:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000079456_40681472.pth... [2023-03-09 03:59:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000078856_40374272.pth [2023-03-09 03:59:33,830][613885] Updated weights for policy 0, policy_version 79520 (0.0004) [2023-03-09 03:59:35,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10246.9). Total num frames: 40730624. Throughput: 0: 10109.0. Samples: 40730004. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:59:35,829][613581] Avg episode reward: [(0, '4103.884')] [2023-03-09 03:59:37,858][613885] Updated weights for policy 0, policy_version 79600 (0.0005) [2023-03-09 03:59:40,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10103.4, 300 sec: 10246.9). Total num frames: 40783872. Throughput: 0: 10114.8. Samples: 40759820. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:59:40,830][613581] Avg episode reward: [(0, '4240.878')] [2023-03-09 03:59:41,965][613885] Updated weights for policy 0, policy_version 79680 (0.0005) [2023-03-09 03:59:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10103.4, 300 sec: 10233.1). Total num frames: 40833024. Throughput: 0: 10165.5. Samples: 40820948. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:59:45,829][613581] Avg episode reward: [(0, '4410.940')] [2023-03-09 03:59:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000079752_40833024.pth... [2023-03-09 03:59:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000079160_40529920.pth [2023-03-09 03:59:45,928][613885] Updated weights for policy 0, policy_version 79760 (0.0005) [2023-03-09 03:59:49,986][613885] Updated weights for policy 0, policy_version 79840 (0.0005) [2023-03-09 03:59:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10233.1). Total num frames: 40886272. Throughput: 0: 10194.8. Samples: 40882160. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:59:50,829][613581] Avg episode reward: [(0, '4533.716')] [2023-03-09 03:59:53,841][613885] Updated weights for policy 0, policy_version 79920 (0.0005) [2023-03-09 03:59:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10219.2). Total num frames: 40935424. Throughput: 0: 10188.6. Samples: 40914752. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 03:59:55,829][613581] Avg episode reward: [(0, '4483.565')] [2023-03-09 03:59:57,720][613885] Updated weights for policy 0, policy_version 80000 (0.0004) [2023-03-09 04:00:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10233.1). Total num frames: 40992768. Throughput: 0: 10248.5. Samples: 40978648. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:00:00,829][613581] Avg episode reward: [(0, '4452.735')] [2023-03-09 04:00:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000080064_40992768.pth... [2023-03-09 04:00:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000079456_40681472.pth [2023-03-09 04:00:01,581][613885] Updated weights for policy 0, policy_version 80080 (0.0004) [2023-03-09 04:00:05,585][613885] Updated weights for policy 0, policy_version 80160 (0.0004) [2023-03-09 04:00:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 10219.2). Total num frames: 41041920. Throughput: 0: 10243.4. Samples: 41040096. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:00:05,829][613581] Avg episode reward: [(0, '4457.069')] [2023-03-09 04:00:09,766][613885] Updated weights for policy 0, policy_version 80240 (0.0005) [2023-03-09 04:00:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.7, 300 sec: 10219.2). Total num frames: 41091072. Throughput: 0: 10247.6. Samples: 41070392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:00:10,829][613581] Avg episode reward: [(0, '4335.329')] [2023-03-09 04:00:13,451][613885] Updated weights for policy 0, policy_version 80320 (0.0004) [2023-03-09 04:00:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10246.9). Total num frames: 41148416. Throughput: 0: 10331.9. Samples: 41134900. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:00:15,829][613581] Avg episode reward: [(0, '4473.284')] [2023-03-09 04:00:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000080368_41148416.pth... [2023-03-09 04:00:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000079752_40833024.pth [2023-03-09 04:00:17,326][613885] Updated weights for policy 0, policy_version 80400 (0.0005) [2023-03-09 04:00:20,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10240.0, 300 sec: 10233.1). Total num frames: 41197568. Throughput: 0: 10369.3. Samples: 41196624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:00:20,829][613581] Avg episode reward: [(0, '4170.126')] [2023-03-09 04:00:21,291][613885] Updated weights for policy 0, policy_version 80480 (0.0005) [2023-03-09 04:00:25,054][613885] Updated weights for policy 0, policy_version 80560 (0.0005) [2023-03-09 04:00:25,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10376.6, 300 sec: 10260.8). Total num frames: 41254912. Throughput: 0: 10373.5. Samples: 41226628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:00:25,829][613581] Avg episode reward: [(0, '4229.178')] [2023-03-09 04:00:28,725][613885] Updated weights for policy 0, policy_version 80640 (0.0005) [2023-03-09 04:00:30,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10444.8, 300 sec: 10274.7). Total num frames: 41308160. Throughput: 0: 10534.2. Samples: 41294988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:00:30,829][613581] Avg episode reward: [(0, '4439.042')] [2023-03-09 04:00:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000080680_41308160.pth... [2023-03-09 04:00:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000080064_40992768.pth [2023-03-09 04:00:32,656][613885] Updated weights for policy 0, policy_version 80720 (0.0005) [2023-03-09 04:00:35,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10444.8, 300 sec: 10246.9). Total num frames: 41357312. Throughput: 0: 10554.4. Samples: 41357108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:00:35,829][613581] Avg episode reward: [(0, '4102.754')] [2023-03-09 04:00:36,710][613885] Updated weights for policy 0, policy_version 80800 (0.0005) [2023-03-09 04:00:40,614][613885] Updated weights for policy 0, policy_version 80880 (0.0005) [2023-03-09 04:00:40,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10444.8, 300 sec: 10260.8). Total num frames: 41410560. Throughput: 0: 10485.0. Samples: 41386576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:00:40,829][613581] Avg episode reward: [(0, '4318.185')] [2023-03-09 04:00:44,668][613885] Updated weights for policy 0, policy_version 80960 (0.0005) [2023-03-09 04:00:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10246.9). Total num frames: 41459712. Throughput: 0: 10455.8. Samples: 41449156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:00:45,829][613581] Avg episode reward: [(0, '4326.914')] [2023-03-09 04:00:45,871][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000080984_41463808.pth... [2023-03-09 04:00:45,873][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000080368_41148416.pth [2023-03-09 04:00:48,500][613885] Updated weights for policy 0, policy_version 81040 (0.0004) [2023-03-09 04:00:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10246.9). Total num frames: 41512960. Throughput: 0: 10446.3. Samples: 41510180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:00:50,829][613581] Avg episode reward: [(0, '4387.994')] [2023-03-09 04:00:52,639][613885] Updated weights for policy 0, policy_version 81120 (0.0005) [2023-03-09 04:00:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10246.9). Total num frames: 41562112. Throughput: 0: 10471.8. Samples: 41541620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:00:55,829][613581] Avg episode reward: [(0, '4290.013')] [2023-03-09 04:00:56,701][613885] Updated weights for policy 0, policy_version 81200 (0.0005) [2023-03-09 04:01:00,646][613885] Updated weights for policy 0, policy_version 81280 (0.0005) [2023-03-09 04:01:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10260.8). Total num frames: 41615360. Throughput: 0: 10391.7. Samples: 41602528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:01:00,829][613581] Avg episode reward: [(0, '3954.050')] [2023-03-09 04:01:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000081280_41615360.pth... [2023-03-09 04:01:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000080680_41308160.pth [2023-03-09 04:01:04,673][613885] Updated weights for policy 0, policy_version 81360 (0.0004) [2023-03-09 04:01:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10233.1). Total num frames: 41664512. Throughput: 0: 10393.5. Samples: 41664332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:01:05,829][613581] Avg episode reward: [(0, '4313.692')] [2023-03-09 04:01:08,730][613885] Updated weights for policy 0, policy_version 81440 (0.0005) [2023-03-09 04:01:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10233.1). Total num frames: 41717760. Throughput: 0: 10371.8. Samples: 41693360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:01:10,829][613581] Avg episode reward: [(0, '4297.668')] [2023-03-09 04:01:12,692][613885] Updated weights for policy 0, policy_version 81520 (0.0005) [2023-03-09 04:01:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10233.1). Total num frames: 41766912. Throughput: 0: 10214.1. Samples: 41754624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:01:15,829][613581] Avg episode reward: [(0, '4446.220')] [2023-03-09 04:01:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000081576_41766912.pth... [2023-03-09 04:01:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000080984_41463808.pth [2023-03-09 04:01:16,710][613885] Updated weights for policy 0, policy_version 81600 (0.0005) [2023-03-09 04:01:20,693][613885] Updated weights for policy 0, policy_version 81680 (0.0005) [2023-03-09 04:01:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10246.9). Total num frames: 41820160. Throughput: 0: 10235.5. Samples: 41817704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:01:20,829][613581] Avg episode reward: [(0, '4255.187')] [2023-03-09 04:01:24,594][613885] Updated weights for policy 0, policy_version 81760 (0.0005) [2023-03-09 04:01:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10260.8). Total num frames: 41873408. Throughput: 0: 10272.4. Samples: 41848832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:01:25,829][613581] Avg episode reward: [(0, '4337.503')] [2023-03-09 04:01:28,495][613885] Updated weights for policy 0, policy_version 81840 (0.0004) [2023-03-09 04:01:30,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10246.9). Total num frames: 41922560. Throughput: 0: 10248.5. Samples: 41910336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:01:30,829][613581] Avg episode reward: [(0, '4402.116')] [2023-03-09 04:01:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000081880_41922560.pth... [2023-03-09 04:01:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000081280_41615360.pth [2023-03-09 04:01:32,526][613885] Updated weights for policy 0, policy_version 81920 (0.0005) [2023-03-09 04:01:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10260.8). Total num frames: 41975808. Throughput: 0: 10300.9. Samples: 41973720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:01:35,829][613581] Avg episode reward: [(0, '4398.785')] [2023-03-09 04:01:36,373][613885] Updated weights for policy 0, policy_version 82000 (0.0005) [2023-03-09 04:01:40,164][613885] Updated weights for policy 0, policy_version 82080 (0.0005) [2023-03-09 04:01:40,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10260.8). Total num frames: 42029056. Throughput: 0: 10318.6. Samples: 42005960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:01:40,829][613581] Avg episode reward: [(0, '4363.699')] [2023-03-09 04:01:44,385][613885] Updated weights for policy 0, policy_version 82160 (0.0004) [2023-03-09 04:01:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10246.9). Total num frames: 42078208. Throughput: 0: 10297.8. Samples: 42065928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:01:45,829][613581] Avg episode reward: [(0, '4482.802')] [2023-03-09 04:01:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000082184_42078208.pth... [2023-03-09 04:01:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000081576_41766912.pth [2023-03-09 04:01:48,595][613885] Updated weights for policy 0, policy_version 82240 (0.0004) [2023-03-09 04:01:50,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10240.0, 300 sec: 10233.1). Total num frames: 42127360. Throughput: 0: 10244.0. Samples: 42125312. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:01:50,829][613581] Avg episode reward: [(0, '4358.924')] [2023-03-09 04:01:52,569][613885] Updated weights for policy 0, policy_version 82320 (0.0005) [2023-03-09 04:01:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10233.1). Total num frames: 42180608. Throughput: 0: 10281.6. Samples: 42156032. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:01:55,829][613581] Avg episode reward: [(0, '4368.551')] [2023-03-09 04:01:56,429][613885] Updated weights for policy 0, policy_version 82400 (0.0006) [2023-03-09 04:02:00,312][613885] Updated weights for policy 0, policy_version 82480 (0.0006) [2023-03-09 04:02:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10260.8). Total num frames: 42233856. Throughput: 0: 10368.1. Samples: 42221188. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:02:00,829][613581] Avg episode reward: [(0, '4451.893')] [2023-03-09 04:02:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000082488_42233856.pth... [2023-03-09 04:02:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000081880_41922560.pth [2023-03-09 04:02:04,169][613885] Updated weights for policy 0, policy_version 82560 (0.0006) [2023-03-09 04:02:05,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10376.5, 300 sec: 10274.7). Total num frames: 42287104. Throughput: 0: 10341.5. Samples: 42283072. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:02:05,829][613581] Avg episode reward: [(0, '4405.551')] [2023-03-09 04:02:07,979][613885] Updated weights for policy 0, policy_version 82640 (0.0005) [2023-03-09 04:02:10,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 10274.7). Total num frames: 42340352. Throughput: 0: 10378.0. Samples: 42315840. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:02:10,829][613581] Avg episode reward: [(0, '4261.967')] [2023-03-09 04:02:11,628][613885] Updated weights for policy 0, policy_version 82720 (0.0005) [2023-03-09 04:02:15,710][613885] Updated weights for policy 0, policy_version 82800 (0.0005) [2023-03-09 04:02:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10288.6). Total num frames: 42393600. Throughput: 0: 10449.7. Samples: 42380572. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:02:15,829][613581] Avg episode reward: [(0, '4285.159')] [2023-03-09 04:02:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000082800_42393600.pth... [2023-03-09 04:02:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000082184_42078208.pth [2023-03-09 04:02:19,498][613885] Updated weights for policy 0, policy_version 82880 (0.0005) [2023-03-09 04:02:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10302.5). Total num frames: 42446848. Throughput: 0: 10455.7. Samples: 42444228. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:02:20,829][613581] Avg episode reward: [(0, '4504.112')] [2023-03-09 04:02:23,513][613885] Updated weights for policy 0, policy_version 82960 (0.0005) [2023-03-09 04:02:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10302.5). Total num frames: 42496000. Throughput: 0: 10425.5. Samples: 42475108. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:02:25,829][613581] Avg episode reward: [(0, '4493.459')] [2023-03-09 04:02:27,477][613885] Updated weights for policy 0, policy_version 83040 (0.0005) [2023-03-09 04:02:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10330.3). Total num frames: 42553344. Throughput: 0: 10473.0. Samples: 42537212. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:02:30,829][613581] Avg episode reward: [(0, '4572.107')] [2023-03-09 04:02:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000083112_42553344.pth... [2023-03-09 04:02:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000082488_42233856.pth [2023-03-09 04:02:31,232][613885] Updated weights for policy 0, policy_version 83120 (0.0004) [2023-03-09 04:02:35,210][613885] Updated weights for policy 0, policy_version 83200 (0.0005) [2023-03-09 04:02:35,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10330.2). Total num frames: 42602496. Throughput: 0: 10545.7. Samples: 42599872. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:02:35,829][613581] Avg episode reward: [(0, '4528.046')] [2023-03-09 04:02:39,253][613885] Updated weights for policy 0, policy_version 83280 (0.0005) [2023-03-09 04:02:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10344.1). Total num frames: 42655744. Throughput: 0: 10536.6. Samples: 42630180. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:02:40,829][613581] Avg episode reward: [(0, '4258.011')] [2023-03-09 04:02:42,679][613885] Updated weights for policy 0, policy_version 83360 (0.0004) [2023-03-09 04:02:45,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10581.3, 300 sec: 10358.0). Total num frames: 42713088. Throughput: 0: 10613.7. Samples: 42698808. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:02:45,829][613581] Avg episode reward: [(0, '4346.788')] [2023-03-09 04:02:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000083424_42713088.pth... [2023-03-09 04:02:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000082800_42393600.pth [2023-03-09 04:02:46,425][613885] Updated weights for policy 0, policy_version 83440 (0.0005) [2023-03-09 04:02:50,471][613885] Updated weights for policy 0, policy_version 83520 (0.0004) [2023-03-09 04:02:50,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10344.1). Total num frames: 42762240. Throughput: 0: 10645.8. Samples: 42762132. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:02:50,829][613581] Avg episode reward: [(0, '4495.267')] [2023-03-09 04:02:54,417][613885] Updated weights for policy 0, policy_version 83600 (0.0004) [2023-03-09 04:02:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10581.3, 300 sec: 10344.1). Total num frames: 42815488. Throughput: 0: 10594.9. Samples: 42792612. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:02:55,829][613581] Avg episode reward: [(0, '4475.788')] [2023-03-09 04:02:58,044][613885] Updated weights for policy 0, policy_version 83680 (0.0004) [2023-03-09 04:03:00,829][613581] Fps is (10 sec: 11468.7, 60 sec: 10717.8, 300 sec: 10371.9). Total num frames: 42876928. Throughput: 0: 10611.5. Samples: 42858092. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:03:00,829][613581] Avg episode reward: [(0, '4476.652')] [2023-03-09 04:03:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000083744_42876928.pth... [2023-03-09 04:03:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000083112_42553344.pth [2023-03-09 04:03:01,565][613885] Updated weights for policy 0, policy_version 83760 (0.0005) [2023-03-09 04:03:05,442][613885] Updated weights for policy 0, policy_version 83840 (0.0005) [2023-03-09 04:03:05,829][613581] Fps is (10 sec: 11468.9, 60 sec: 10717.9, 300 sec: 10371.9). Total num frames: 42930176. Throughput: 0: 10706.1. Samples: 42926004. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:03:05,829][613581] Avg episode reward: [(0, '4543.037')] [2023-03-09 04:03:09,454][613885] Updated weights for policy 0, policy_version 83920 (0.0005) [2023-03-09 04:03:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10649.6, 300 sec: 10371.9). Total num frames: 42979328. Throughput: 0: 10714.6. Samples: 42957264. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:03:10,829][613581] Avg episode reward: [(0, '4566.025')] [2023-03-09 04:03:13,496][613885] Updated weights for policy 0, policy_version 84000 (0.0005) [2023-03-09 04:03:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10649.6, 300 sec: 10371.9). Total num frames: 43032576. Throughput: 0: 10714.5. Samples: 43019364. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:03:15,829][613581] Avg episode reward: [(0, '4448.257')] [2023-03-09 04:03:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000084048_43032576.pth... [2023-03-09 04:03:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000083424_42713088.pth [2023-03-09 04:03:17,231][613885] Updated weights for policy 0, policy_version 84080 (0.0005) [2023-03-09 04:03:20,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10385.8). Total num frames: 43085824. Throughput: 0: 10744.8. Samples: 43083388. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:03:20,829][613581] Avg episode reward: [(0, '4329.639')] [2023-03-09 04:03:20,914][613885] Updated weights for policy 0, policy_version 84160 (0.0005) [2023-03-09 04:03:24,818][613885] Updated weights for policy 0, policy_version 84240 (0.0005) [2023-03-09 04:03:25,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10717.9, 300 sec: 10371.9). Total num frames: 43139072. Throughput: 0: 10762.9. Samples: 43114512. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:03:25,829][613581] Avg episode reward: [(0, '4340.255')] [2023-03-09 04:03:28,930][613885] Updated weights for policy 0, policy_version 84320 (0.0005) [2023-03-09 04:03:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10581.3, 300 sec: 10371.9). Total num frames: 43188224. Throughput: 0: 10604.3. Samples: 43176000. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:03:30,829][613581] Avg episode reward: [(0, '4200.293')] [2023-03-09 04:03:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000084352_43188224.pth... [2023-03-09 04:03:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000083744_42876928.pth [2023-03-09 04:03:32,763][613885] Updated weights for policy 0, policy_version 84400 (0.0004) [2023-03-09 04:03:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10399.7). Total num frames: 43245568. Throughput: 0: 10652.2. Samples: 43241480. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:03:35,829][613581] Avg episode reward: [(0, '4263.161')] [2023-03-09 04:03:36,663][613885] Updated weights for policy 0, policy_version 84480 (0.0005) [2023-03-09 04:03:40,569][613885] Updated weights for policy 0, policy_version 84560 (0.0005) [2023-03-09 04:03:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10399.7). Total num frames: 43294720. Throughput: 0: 10660.8. Samples: 43272348. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:03:40,829][613581] Avg episode reward: [(0, '4446.018')] [2023-03-09 04:03:44,648][613885] Updated weights for policy 0, policy_version 84640 (0.0005) [2023-03-09 04:03:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10513.1, 300 sec: 10399.7). Total num frames: 43343872. Throughput: 0: 10562.1. Samples: 43333384. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:03:45,829][613581] Avg episode reward: [(0, '4448.498')] [2023-03-09 04:03:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000084656_43343872.pth... [2023-03-09 04:03:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000084048_43032576.pth [2023-03-09 04:03:48,597][613885] Updated weights for policy 0, policy_version 84720 (0.0005) [2023-03-09 04:03:50,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10427.4). Total num frames: 43401216. Throughput: 0: 10466.8. Samples: 43397008. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:03:50,829][613581] Avg episode reward: [(0, '4398.296')] [2023-03-09 04:03:52,445][613885] Updated weights for policy 0, policy_version 84800 (0.0005) [2023-03-09 04:03:55,829][613581] Fps is (10 sec: 11059.3, 60 sec: 10649.6, 300 sec: 10441.3). Total num frames: 43454464. Throughput: 0: 10443.7. Samples: 43427228. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:03:55,829][613581] Avg episode reward: [(0, '4151.968')] [2023-03-09 04:03:56,038][613885] Updated weights for policy 0, policy_version 84880 (0.0005) [2023-03-09 04:03:59,825][613885] Updated weights for policy 0, policy_version 84960 (0.0005) [2023-03-09 04:04:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10441.3). Total num frames: 43507712. Throughput: 0: 10564.9. Samples: 43494784. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:04:00,829][613581] Avg episode reward: [(0, '4336.098')] [2023-03-09 04:04:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000084984_43511808.pth... [2023-03-09 04:04:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000084352_43188224.pth [2023-03-09 04:04:03,482][613885] Updated weights for policy 0, policy_version 85040 (0.0005) [2023-03-09 04:04:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10441.3). Total num frames: 43560960. Throughput: 0: 10538.2. Samples: 43557608. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:04:05,829][613581] Avg episode reward: [(0, '4383.355')] [2023-03-09 04:04:07,550][613885] Updated weights for policy 0, policy_version 85120 (0.0005) [2023-03-09 04:04:10,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10455.2). Total num frames: 43614208. Throughput: 0: 10552.7. Samples: 43589384. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:04:10,829][613581] Avg episode reward: [(0, '4255.260')] [2023-03-09 04:04:11,592][613885] Updated weights for policy 0, policy_version 85200 (0.0005) [2023-03-09 04:04:15,494][613885] Updated weights for policy 0, policy_version 85280 (0.0005) [2023-03-09 04:04:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10441.3). Total num frames: 43663360. Throughput: 0: 10581.4. Samples: 43652164. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:04:15,829][613581] Avg episode reward: [(0, '4076.304')] [2023-03-09 04:04:15,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000085280_43663360.pth... [2023-03-09 04:04:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000084656_43343872.pth [2023-03-09 04:04:19,306][613885] Updated weights for policy 0, policy_version 85360 (0.0005) [2023-03-09 04:04:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10455.2). Total num frames: 43716608. Throughput: 0: 10541.6. Samples: 43715852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:04:20,829][613581] Avg episode reward: [(0, '3559.338')] [2023-03-09 04:04:23,028][613885] Updated weights for policy 0, policy_version 85440 (0.0005) [2023-03-09 04:04:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10469.1). Total num frames: 43769856. Throughput: 0: 10598.9. Samples: 43749296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:04:25,829][613581] Avg episode reward: [(0, '3630.829')] [2023-03-09 04:04:27,141][613885] Updated weights for policy 0, policy_version 85520 (0.0005) [2023-03-09 04:04:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10513.1, 300 sec: 10469.1). Total num frames: 43819008. Throughput: 0: 10532.6. Samples: 43807352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:04:30,829][613581] Avg episode reward: [(0, '3802.397')] [2023-03-09 04:04:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000085584_43819008.pth... [2023-03-09 04:04:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000084984_43511808.pth [2023-03-09 04:04:31,246][613885] Updated weights for policy 0, policy_version 85600 (0.0005) [2023-03-09 04:04:35,137][613885] Updated weights for policy 0, policy_version 85680 (0.0005) [2023-03-09 04:04:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10469.1). Total num frames: 43872256. Throughput: 0: 10537.6. Samples: 43871200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:04:35,829][613581] Avg episode reward: [(0, '3919.203')] [2023-03-09 04:04:38,866][613885] Updated weights for policy 0, policy_version 85760 (0.0005) [2023-03-09 04:04:40,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10513.1, 300 sec: 10483.0). Total num frames: 43925504. Throughput: 0: 10593.9. Samples: 43903952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:04:40,829][613581] Avg episode reward: [(0, '4186.439')] [2023-03-09 04:04:42,636][613885] Updated weights for policy 0, policy_version 85840 (0.0005) [2023-03-09 04:04:45,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10649.6, 300 sec: 10496.9). Total num frames: 43982848. Throughput: 0: 10542.2. Samples: 43969184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:04:45,829][613581] Avg episode reward: [(0, '4421.299')] [2023-03-09 04:04:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000085904_43982848.pth... [2023-03-09 04:04:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000085280_43663360.pth [2023-03-09 04:04:46,426][613885] Updated weights for policy 0, policy_version 85920 (0.0005) [2023-03-09 04:04:50,299][613885] Updated weights for policy 0, policy_version 86000 (0.0004) [2023-03-09 04:04:50,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10581.3, 300 sec: 10510.8). Total num frames: 44036096. Throughput: 0: 10553.9. Samples: 44032532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:04:50,829][613581] Avg episode reward: [(0, '4450.272')] [2023-03-09 04:04:54,535][613885] Updated weights for policy 0, policy_version 86080 (0.0005) [2023-03-09 04:04:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10483.0). Total num frames: 44085248. Throughput: 0: 10502.4. Samples: 44061992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:04:55,829][613581] Avg episode reward: [(0, '4368.469')] [2023-03-09 04:04:58,465][613885] Updated weights for policy 0, policy_version 86160 (0.0005) [2023-03-09 04:05:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10496.9). Total num frames: 44138496. Throughput: 0: 10475.3. Samples: 44123552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:05:00,829][613581] Avg episode reward: [(0, '3978.788')] [2023-03-09 04:05:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000086208_44138496.pth... [2023-03-09 04:05:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000085584_43819008.pth [2023-03-09 04:05:02,589][613885] Updated weights for policy 0, policy_version 86240 (0.0004) [2023-03-09 04:05:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10496.9). Total num frames: 44187648. Throughput: 0: 10451.9. Samples: 44186188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:05:05,829][613581] Avg episode reward: [(0, '3679.787')] [2023-03-09 04:05:06,335][613885] Updated weights for policy 0, policy_version 86320 (0.0005) [2023-03-09 04:05:10,219][613885] Updated weights for policy 0, policy_version 86400 (0.0005) [2023-03-09 04:05:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10483.0). Total num frames: 44240896. Throughput: 0: 10433.7. Samples: 44218812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:05:10,829][613581] Avg episode reward: [(0, '3639.084')] [2023-03-09 04:05:14,229][613885] Updated weights for policy 0, policy_version 86480 (0.0004) [2023-03-09 04:05:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10483.0). Total num frames: 44290048. Throughput: 0: 10485.3. Samples: 44279192. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:05:15,829][613581] Avg episode reward: [(0, '3644.249')] [2023-03-09 04:05:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000086504_44290048.pth... [2023-03-09 04:05:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000085904_43982848.pth [2023-03-09 04:05:18,528][613885] Updated weights for policy 0, policy_version 86560 (0.0004) [2023-03-09 04:05:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10376.5, 300 sec: 10455.2). Total num frames: 44339200. Throughput: 0: 10321.7. Samples: 44335676. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:05:20,829][613581] Avg episode reward: [(0, '3964.682')] [2023-03-09 04:05:22,936][613885] Updated weights for policy 0, policy_version 86640 (0.0004) [2023-03-09 04:05:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10308.3, 300 sec: 10441.3). Total num frames: 44388352. Throughput: 0: 10219.9. Samples: 44363848. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:05:25,829][613581] Avg episode reward: [(0, '4259.867')] [2023-03-09 04:05:26,828][613885] Updated weights for policy 0, policy_version 86720 (0.0005) [2023-03-09 04:05:30,805][613885] Updated weights for policy 0, policy_version 86800 (0.0005) [2023-03-09 04:05:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10455.2). Total num frames: 44441600. Throughput: 0: 10207.1. Samples: 44428504. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:05:30,829][613581] Avg episode reward: [(0, '4440.600')] [2023-03-09 04:05:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000086800_44441600.pth... [2023-03-09 04:05:30,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000086208_44138496.pth [2023-03-09 04:05:34,754][613885] Updated weights for policy 0, policy_version 86880 (0.0005) [2023-03-09 04:05:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10441.3). Total num frames: 44490752. Throughput: 0: 10135.9. Samples: 44488648. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:05:35,829][613581] Avg episode reward: [(0, '4234.345')] [2023-03-09 04:05:38,542][613885] Updated weights for policy 0, policy_version 86960 (0.0005) [2023-03-09 04:05:40,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10308.3, 300 sec: 10455.2). Total num frames: 44544000. Throughput: 0: 10227.0. Samples: 44522204. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:05:40,829][613581] Avg episode reward: [(0, '4167.735')] [2023-03-09 04:05:42,591][613885] Updated weights for policy 0, policy_version 87040 (0.0004) [2023-03-09 04:05:45,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10240.0, 300 sec: 10455.2). Total num frames: 44597248. Throughput: 0: 10229.0. Samples: 44583856. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:05:45,829][613581] Avg episode reward: [(0, '4401.022')] [2023-03-09 04:05:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000087104_44597248.pth... [2023-03-09 04:05:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000086504_44290048.pth [2023-03-09 04:05:46,484][613885] Updated weights for policy 0, policy_version 87120 (0.0005) [2023-03-09 04:05:50,554][613885] Updated weights for policy 0, policy_version 87200 (0.0005) [2023-03-09 04:05:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10455.2). Total num frames: 44646400. Throughput: 0: 10198.0. Samples: 44645096. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:05:50,829][613581] Avg episode reward: [(0, '4018.273')] [2023-03-09 04:05:54,447][613885] Updated weights for policy 0, policy_version 87280 (0.0004) [2023-03-09 04:05:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10455.2). Total num frames: 44699648. Throughput: 0: 10145.4. Samples: 44675356. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:05:55,829][613581] Avg episode reward: [(0, '4084.732')] [2023-03-09 04:05:58,471][613885] Updated weights for policy 0, policy_version 87360 (0.0004) [2023-03-09 04:06:00,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10240.0, 300 sec: 10469.1). Total num frames: 44752896. Throughput: 0: 10174.0. Samples: 44737024. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:06:00,829][613581] Avg episode reward: [(0, '4153.772')] [2023-03-09 04:06:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000087408_44752896.pth... [2023-03-09 04:06:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000086800_44441600.pth [2023-03-09 04:06:02,322][613885] Updated weights for policy 0, policy_version 87440 (0.0005) [2023-03-09 04:06:05,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10455.2). Total num frames: 44802048. Throughput: 0: 10343.4. Samples: 44801128. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:06:05,829][613581] Avg episode reward: [(0, '4468.179')] [2023-03-09 04:06:06,271][613885] Updated weights for policy 0, policy_version 87520 (0.0004) [2023-03-09 04:06:10,331][613885] Updated weights for policy 0, policy_version 87600 (0.0005) [2023-03-09 04:06:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10469.1). Total num frames: 44855296. Throughput: 0: 10374.1. Samples: 44830684. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:06:10,829][613581] Avg episode reward: [(0, '4363.701')] [2023-03-09 04:06:14,216][613885] Updated weights for policy 0, policy_version 87680 (0.0004) [2023-03-09 04:06:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10469.1). Total num frames: 44908544. Throughput: 0: 10342.6. Samples: 44893920. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:06:15,829][613581] Avg episode reward: [(0, '4191.106')] [2023-03-09 04:06:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000087712_44908544.pth... [2023-03-09 04:06:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000087104_44597248.pth [2023-03-09 04:06:18,362][613885] Updated weights for policy 0, policy_version 87760 (0.0004) [2023-03-09 04:06:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10455.2). Total num frames: 44957696. Throughput: 0: 10330.4. Samples: 44953516. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:06:20,829][613581] Avg episode reward: [(0, '4346.507')] [2023-03-09 04:06:22,439][613885] Updated weights for policy 0, policy_version 87840 (0.0005) [2023-03-09 04:06:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10308.3, 300 sec: 10455.2). Total num frames: 45006848. Throughput: 0: 10255.1. Samples: 44983684. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:06:25,829][613581] Avg episode reward: [(0, '4171.858')] [2023-03-09 04:06:26,314][613885] Updated weights for policy 0, policy_version 87920 (0.0005) [2023-03-09 04:06:30,246][613885] Updated weights for policy 0, policy_version 88000 (0.0005) [2023-03-09 04:06:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10455.2). Total num frames: 45060096. Throughput: 0: 10308.1. Samples: 45047720. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:06:30,829][613581] Avg episode reward: [(0, '4284.167')] [2023-03-09 04:06:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000088008_45060096.pth... [2023-03-09 04:06:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000087408_44752896.pth [2023-03-09 04:06:34,350][613885] Updated weights for policy 0, policy_version 88080 (0.0005) [2023-03-09 04:06:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10441.3). Total num frames: 45109248. Throughput: 0: 10303.7. Samples: 45108764. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:06:35,829][613581] Avg episode reward: [(0, '4326.828')] [2023-03-09 04:06:37,958][613885] Updated weights for policy 0, policy_version 88160 (0.0005) [2023-03-09 04:06:40,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10376.5, 300 sec: 10469.1). Total num frames: 45166592. Throughput: 0: 10371.6. Samples: 45142080. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:06:40,829][613581] Avg episode reward: [(0, '4251.693')] [2023-03-09 04:06:41,921][613885] Updated weights for policy 0, policy_version 88240 (0.0005) [2023-03-09 04:06:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10469.1). Total num frames: 45215744. Throughput: 0: 10382.8. Samples: 45204248. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:06:45,829][613581] Avg episode reward: [(0, '4286.441')] [2023-03-09 04:06:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000088312_45215744.pth... [2023-03-09 04:06:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000087712_44908544.pth [2023-03-09 04:06:46,019][613885] Updated weights for policy 0, policy_version 88320 (0.0005) [2023-03-09 04:06:50,044][613885] Updated weights for policy 0, policy_version 88400 (0.0004) [2023-03-09 04:06:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10469.1). Total num frames: 45268992. Throughput: 0: 10306.1. Samples: 45264904. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:06:50,829][613581] Avg episode reward: [(0, '4103.648')] [2023-03-09 04:06:54,025][613885] Updated weights for policy 0, policy_version 88480 (0.0004) [2023-03-09 04:06:55,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10455.2). Total num frames: 45318144. Throughput: 0: 10324.0. Samples: 45295264. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:06:55,829][613581] Avg episode reward: [(0, '4130.974')] [2023-03-09 04:06:58,169][613885] Updated weights for policy 0, policy_version 88560 (0.0004) [2023-03-09 04:07:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10441.3). Total num frames: 45367296. Throughput: 0: 10253.8. Samples: 45355340. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:07:00,829][613581] Avg episode reward: [(0, '3623.814')] [2023-03-09 04:07:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000088608_45367296.pth... [2023-03-09 04:07:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000088008_45060096.pth [2023-03-09 04:07:02,094][613885] Updated weights for policy 0, policy_version 88640 (0.0005) [2023-03-09 04:07:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10441.3). Total num frames: 45420544. Throughput: 0: 10319.1. Samples: 45417876. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:07:05,829][613581] Avg episode reward: [(0, '4133.452')] [2023-03-09 04:07:06,074][613885] Updated weights for policy 0, policy_version 88720 (0.0005) [2023-03-09 04:07:09,869][613885] Updated weights for policy 0, policy_version 88800 (0.0005) [2023-03-09 04:07:10,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10441.3). Total num frames: 45473792. Throughput: 0: 10350.1. Samples: 45449440. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:07:10,829][613581] Avg episode reward: [(0, '4329.863')] [2023-03-09 04:07:13,744][613885] Updated weights for policy 0, policy_version 88880 (0.0005) [2023-03-09 04:07:15,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10441.3). Total num frames: 45527040. Throughput: 0: 10335.6. Samples: 45512824. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:07:15,829][613581] Avg episode reward: [(0, '4386.467')] [2023-03-09 04:07:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000088920_45527040.pth... [2023-03-09 04:07:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000088312_45215744.pth [2023-03-09 04:07:17,905][613885] Updated weights for policy 0, policy_version 88960 (0.0005) [2023-03-09 04:07:20,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10441.3). Total num frames: 45576192. Throughput: 0: 10321.0. Samples: 45573208. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:07:20,829][613581] Avg episode reward: [(0, '4427.037')] [2023-03-09 04:07:21,867][613885] Updated weights for policy 0, policy_version 89040 (0.0005) [2023-03-09 04:07:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 10413.6). Total num frames: 45625344. Throughput: 0: 10242.3. Samples: 45602984. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:07:25,829][613581] Avg episode reward: [(0, '4507.645')] [2023-03-09 04:07:26,128][613885] Updated weights for policy 0, policy_version 89120 (0.0005) [2023-03-09 04:07:30,204][613885] Updated weights for policy 0, policy_version 89200 (0.0004) [2023-03-09 04:07:30,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10240.0, 300 sec: 10413.6). Total num frames: 45674496. Throughput: 0: 10174.0. Samples: 45662080. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:07:30,829][613581] Avg episode reward: [(0, '4382.733')] [2023-03-09 04:07:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000089208_45674496.pth... [2023-03-09 04:07:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000088608_45367296.pth [2023-03-09 04:07:34,224][613885] Updated weights for policy 0, policy_version 89280 (0.0005) [2023-03-09 04:07:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10399.7). Total num frames: 45723648. Throughput: 0: 10161.8. Samples: 45722184. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:07:35,829][613581] Avg episode reward: [(0, '4379.468')] [2023-03-09 04:07:38,683][613885] Updated weights for policy 0, policy_version 89360 (0.0005) [2023-03-09 04:07:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10385.8). Total num frames: 45776896. Throughput: 0: 10077.2. Samples: 45748736. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:07:40,829][613581] Avg episode reward: [(0, '4468.363')] [2023-03-09 04:07:42,354][613885] Updated weights for policy 0, policy_version 89440 (0.0004) [2023-03-09 04:07:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10385.8). Total num frames: 45826048. Throughput: 0: 10168.9. Samples: 45812940. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:07:45,829][613581] Avg episode reward: [(0, '4529.513')] [2023-03-09 04:07:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000089504_45826048.pth... [2023-03-09 04:07:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000088920_45527040.pth [2023-03-09 04:07:46,590][613885] Updated weights for policy 0, policy_version 89520 (0.0005) [2023-03-09 04:07:50,460][613885] Updated weights for policy 0, policy_version 89600 (0.0004) [2023-03-09 04:07:50,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10103.5, 300 sec: 10371.9). Total num frames: 45875200. Throughput: 0: 10160.6. Samples: 45875100. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:07:50,829][613581] Avg episode reward: [(0, '4468.958')] [2023-03-09 04:07:54,908][613885] Updated weights for policy 0, policy_version 89680 (0.0004) [2023-03-09 04:07:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10330.3). Total num frames: 45924352. Throughput: 0: 10067.6. Samples: 45902484. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:07:55,829][613581] Avg episode reward: [(0, '4513.414')] [2023-03-09 04:07:58,672][613885] Updated weights for policy 0, policy_version 89760 (0.0005) [2023-03-09 04:08:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 10330.2). Total num frames: 45977600. Throughput: 0: 10055.4. Samples: 45965316. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:08:00,829][613581] Avg episode reward: [(0, '4500.027')] [2023-03-09 04:08:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000089800_45977600.pth... [2023-03-09 04:08:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000089208_45674496.pth [2023-03-09 04:08:02,701][613885] Updated weights for policy 0, policy_version 89840 (0.0005) [2023-03-09 04:08:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 10330.2). Total num frames: 46026752. Throughput: 0: 10039.0. Samples: 46024964. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:08:05,829][613581] Avg episode reward: [(0, '4414.861')] [2023-03-09 04:08:06,829][613885] Updated weights for policy 0, policy_version 89920 (0.0005) [2023-03-09 04:08:10,698][613885] Updated weights for policy 0, policy_version 90000 (0.0005) [2023-03-09 04:08:10,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10103.5, 300 sec: 10330.3). Total num frames: 46080000. Throughput: 0: 10054.4. Samples: 46055432. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:08:10,839][613581] Avg episode reward: [(0, '4431.997')] [2023-03-09 04:08:14,619][613885] Updated weights for policy 0, policy_version 90080 (0.0005) [2023-03-09 04:08:15,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10103.5, 300 sec: 10330.2). Total num frames: 46133248. Throughput: 0: 10116.5. Samples: 46117320. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:08:15,840][613581] Avg episode reward: [(0, '4397.458')] [2023-03-09 04:08:15,843][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000090104_46133248.pth... [2023-03-09 04:08:15,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000089504_45826048.pth [2023-03-09 04:08:18,864][613885] Updated weights for policy 0, policy_version 90160 (0.0005) [2023-03-09 04:08:20,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10302.5). Total num frames: 46178304. Throughput: 0: 10117.0. Samples: 46177448. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:08:20,840][613581] Avg episode reward: [(0, '4496.577')] [2023-03-09 04:08:23,018][613885] Updated weights for policy 0, policy_version 90240 (0.0005) [2023-03-09 04:08:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10316.4). Total num frames: 46231552. Throughput: 0: 10183.4. Samples: 46206988. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:08:25,829][613581] Avg episode reward: [(0, '4475.211')] [2023-03-09 04:08:26,834][613885] Updated weights for policy 0, policy_version 90320 (0.0005) [2023-03-09 04:08:30,698][613885] Updated weights for policy 0, policy_version 90400 (0.0005) [2023-03-09 04:08:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10171.7, 300 sec: 10302.5). Total num frames: 46284800. Throughput: 0: 10210.8. Samples: 46272428. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:08:30,829][613581] Avg episode reward: [(0, '4525.620')] [2023-03-09 04:08:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000090400_46284800.pth... [2023-03-09 04:08:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000089800_45977600.pth [2023-03-09 04:08:34,850][613885] Updated weights for policy 0, policy_version 90480 (0.0006) [2023-03-09 04:08:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10302.5). Total num frames: 46333952. Throughput: 0: 10126.2. Samples: 46330780. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:08:35,829][613581] Avg episode reward: [(0, '4396.828')] [2023-03-09 04:08:38,959][613885] Updated weights for policy 0, policy_version 90560 (0.0005) [2023-03-09 04:08:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10103.5, 300 sec: 10302.5). Total num frames: 46383104. Throughput: 0: 10203.9. Samples: 46361660. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:08:40,829][613581] Avg episode reward: [(0, '4389.007')] [2023-03-09 04:08:42,994][613885] Updated weights for policy 0, policy_version 90640 (0.0005) [2023-03-09 04:08:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10274.7). Total num frames: 46432256. Throughput: 0: 10144.9. Samples: 46421836. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:08:45,829][613581] Avg episode reward: [(0, '4436.093')] [2023-03-09 04:08:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000090688_46432256.pth... [2023-03-09 04:08:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000090104_46133248.pth [2023-03-09 04:08:47,151][613885] Updated weights for policy 0, policy_version 90720 (0.0006) [2023-03-09 04:08:50,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 10274.7). Total num frames: 46485504. Throughput: 0: 10168.9. Samples: 46482564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:08:50,840][613581] Avg episode reward: [(0, '4439.628')] [2023-03-09 04:08:51,062][613885] Updated weights for policy 0, policy_version 90800 (0.0005) [2023-03-09 04:08:55,094][613885] Updated weights for policy 0, policy_version 90880 (0.0005) [2023-03-09 04:08:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 10274.7). Total num frames: 46538752. Throughput: 0: 10178.0. Samples: 46513444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:08:55,840][613581] Avg episode reward: [(0, '4464.588')] [2023-03-09 04:08:58,765][613885] Updated weights for policy 0, policy_version 90960 (0.0005) [2023-03-09 04:09:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 10274.7). Total num frames: 46592000. Throughput: 0: 10233.8. Samples: 46577840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:09:00,840][613581] Avg episode reward: [(0, '4514.399')] [2023-03-09 04:09:00,844][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000091000_46592000.pth... [2023-03-09 04:09:00,847][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000090400_46284800.pth [2023-03-09 04:09:02,684][613885] Updated weights for policy 0, policy_version 91040 (0.0005) [2023-03-09 04:09:05,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10260.8). Total num frames: 46641152. Throughput: 0: 10296.2. Samples: 46640776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:09:05,840][613581] Avg episode reward: [(0, '4507.165')] [2023-03-09 04:09:06,570][613885] Updated weights for policy 0, policy_version 91120 (0.0005) [2023-03-09 04:09:10,587][613885] Updated weights for policy 0, policy_version 91200 (0.0005) [2023-03-09 04:09:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10274.7). Total num frames: 46694400. Throughput: 0: 10326.3. Samples: 46671672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:09:10,840][613581] Avg episode reward: [(0, '4437.281')] [2023-03-09 04:09:14,616][613885] Updated weights for policy 0, policy_version 91280 (0.0005) [2023-03-09 04:09:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10260.8). Total num frames: 46743552. Throughput: 0: 10244.1. Samples: 46733412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:09:15,840][613581] Avg episode reward: [(0, '4426.731')] [2023-03-09 04:09:15,843][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000091296_46743552.pth... [2023-03-09 04:09:15,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000090688_46432256.pth [2023-03-09 04:09:18,685][613885] Updated weights for policy 0, policy_version 91360 (0.0005) [2023-03-09 04:09:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10260.8). Total num frames: 46796800. Throughput: 0: 10276.1. Samples: 46793204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:09:20,840][613581] Avg episode reward: [(0, '4502.969')] [2023-03-09 04:09:22,776][613885] Updated weights for policy 0, policy_version 91440 (0.0006) [2023-03-09 04:09:25,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10260.8). Total num frames: 46845952. Throughput: 0: 10263.3. Samples: 46823508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:09:25,840][613581] Avg episode reward: [(0, '4418.999')] [2023-03-09 04:09:26,730][613885] Updated weights for policy 0, policy_version 91520 (0.0005) [2023-03-09 04:09:30,495][613885] Updated weights for policy 0, policy_version 91600 (0.0005) [2023-03-09 04:09:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10260.8). Total num frames: 46899200. Throughput: 0: 10336.4. Samples: 46886976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:09:30,840][613581] Avg episode reward: [(0, '4402.742')] [2023-03-09 04:09:30,843][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000091600_46899200.pth... [2023-03-09 04:09:30,845][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000091000_46592000.pth [2023-03-09 04:09:34,563][613885] Updated weights for policy 0, policy_version 91680 (0.0006) [2023-03-09 04:09:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10260.8). Total num frames: 46952448. Throughput: 0: 10350.3. Samples: 46948328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:09:35,840][613581] Avg episode reward: [(0, '4292.608')] [2023-03-09 04:09:38,603][613885] Updated weights for policy 0, policy_version 91760 (0.0005) [2023-03-09 04:09:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10233.1). Total num frames: 47001600. Throughput: 0: 10349.2. Samples: 46979156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:09:40,829][613581] Avg episode reward: [(0, '4401.940')] [2023-03-09 04:09:42,708][613885] Updated weights for policy 0, policy_version 91840 (0.0005) [2023-03-09 04:09:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10233.1). Total num frames: 47054848. Throughput: 0: 10282.2. Samples: 47040540. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:09:45,829][613581] Avg episode reward: [(0, '4414.462')] [2023-03-09 04:09:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000091904_47054848.pth... [2023-03-09 04:09:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000091296_46743552.pth [2023-03-09 04:09:46,566][613885] Updated weights for policy 0, policy_version 91920 (0.0006) [2023-03-09 04:09:50,752][613885] Updated weights for policy 0, policy_version 92000 (0.0005) [2023-03-09 04:09:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10233.1). Total num frames: 47104000. Throughput: 0: 10203.0. Samples: 47099912. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:09:50,829][613581] Avg episode reward: [(0, '4076.632')] [2023-03-09 04:09:54,912][613885] Updated weights for policy 0, policy_version 92080 (0.0004) [2023-03-09 04:09:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10219.2). Total num frames: 47153152. Throughput: 0: 10156.8. Samples: 47128728. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:09:55,830][613581] Avg episode reward: [(0, '4254.669')] [2023-03-09 04:09:59,036][613885] Updated weights for policy 0, policy_version 92160 (0.0005) [2023-03-09 04:10:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.7, 300 sec: 10219.2). Total num frames: 47202304. Throughput: 0: 10143.8. Samples: 47189884. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:10:00,829][613581] Avg episode reward: [(0, '4257.807')] [2023-03-09 04:10:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000092192_47202304.pth... [2023-03-09 04:10:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000091600_46899200.pth [2023-03-09 04:10:03,218][613885] Updated weights for policy 0, policy_version 92240 (0.0004) [2023-03-09 04:10:05,829][613581] Fps is (10 sec: 9420.9, 60 sec: 10103.5, 300 sec: 10191.4). Total num frames: 47247360. Throughput: 0: 10090.7. Samples: 47247284. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:10:05,829][613581] Avg episode reward: [(0, '4050.186')] [2023-03-09 04:10:07,133][613885] Updated weights for policy 0, policy_version 92320 (0.0005) [2023-03-09 04:10:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10219.2). Total num frames: 47304704. Throughput: 0: 10176.2. Samples: 47281436. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:10:10,829][613581] Avg episode reward: [(0, '4321.517')] [2023-03-09 04:10:11,159][613885] Updated weights for policy 0, policy_version 92400 (0.0005) [2023-03-09 04:10:15,155][613885] Updated weights for policy 0, policy_version 92480 (0.0005) [2023-03-09 04:10:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10171.7, 300 sec: 10219.2). Total num frames: 47353856. Throughput: 0: 10103.5. Samples: 47341632. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:10:15,829][613581] Avg episode reward: [(0, '4229.714')] [2023-03-09 04:10:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000092488_47353856.pth... [2023-03-09 04:10:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000091904_47054848.pth [2023-03-09 04:10:19,292][613885] Updated weights for policy 0, policy_version 92560 (0.0005) [2023-03-09 04:10:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10219.2). Total num frames: 47403008. Throughput: 0: 10074.1. Samples: 47401664. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:10:20,829][613581] Avg episode reward: [(0, '4420.550')] [2023-03-09 04:10:23,474][613885] Updated weights for policy 0, policy_version 92640 (0.0005) [2023-03-09 04:10:25,829][613581] Fps is (10 sec: 9830.6, 60 sec: 10103.5, 300 sec: 10205.3). Total num frames: 47452160. Throughput: 0: 10039.4. Samples: 47430928. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:10:25,829][613581] Avg episode reward: [(0, '4529.110')] [2023-03-09 04:10:27,536][613885] Updated weights for policy 0, policy_version 92720 (0.0006) [2023-03-09 04:10:30,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10035.2, 300 sec: 10205.3). Total num frames: 47501312. Throughput: 0: 9987.1. Samples: 47489960. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:10:30,829][613581] Avg episode reward: [(0, '4503.179')] [2023-03-09 04:10:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000092776_47501312.pth... [2023-03-09 04:10:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000092192_47202304.pth [2023-03-09 04:10:31,756][613885] Updated weights for policy 0, policy_version 92800 (0.0005) [2023-03-09 04:10:35,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 10191.4). Total num frames: 47550464. Throughput: 0: 9972.0. Samples: 47548652. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:10:35,829][613581] Avg episode reward: [(0, '4528.731')] [2023-03-09 04:10:35,904][613885] Updated weights for policy 0, policy_version 92880 (0.0005) [2023-03-09 04:10:39,942][613885] Updated weights for policy 0, policy_version 92960 (0.0004) [2023-03-09 04:10:40,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10035.2, 300 sec: 10191.4). Total num frames: 47603712. Throughput: 0: 10010.7. Samples: 47579208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:10:40,829][613581] Avg episode reward: [(0, '4524.865')] [2023-03-09 04:10:43,990][613885] Updated weights for policy 0, policy_version 93040 (0.0005) [2023-03-09 04:10:45,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10035.2, 300 sec: 10205.3). Total num frames: 47656960. Throughput: 0: 10016.8. Samples: 47640640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:10:45,829][613581] Avg episode reward: [(0, '4408.590')] [2023-03-09 04:10:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000093080_47656960.pth... [2023-03-09 04:10:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000092488_47353856.pth [2023-03-09 04:10:47,887][613885] Updated weights for policy 0, policy_version 93120 (0.0004) [2023-03-09 04:10:50,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10035.2, 300 sec: 10191.4). Total num frames: 47706112. Throughput: 0: 10186.4. Samples: 47705672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:10:50,829][613581] Avg episode reward: [(0, '4463.374')] [2023-03-09 04:10:51,750][613885] Updated weights for policy 0, policy_version 93200 (0.0005) [2023-03-09 04:10:55,383][613885] Updated weights for policy 0, policy_version 93280 (0.0005) [2023-03-09 04:10:55,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10171.7, 300 sec: 10205.3). Total num frames: 47763456. Throughput: 0: 10100.2. Samples: 47735944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:10:55,830][613581] Avg episode reward: [(0, '4535.357')] [2023-03-09 04:10:59,529][613885] Updated weights for policy 0, policy_version 93360 (0.0005) [2023-03-09 04:11:00,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10171.7, 300 sec: 10205.3). Total num frames: 47812608. Throughput: 0: 10177.0. Samples: 47799596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:11:00,829][613581] Avg episode reward: [(0, '4420.328')] [2023-03-09 04:11:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000093384_47812608.pth... [2023-03-09 04:11:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000092776_47501312.pth [2023-03-09 04:11:03,383][613885] Updated weights for policy 0, policy_version 93440 (0.0005) [2023-03-09 04:11:05,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10240.0, 300 sec: 10191.4). Total num frames: 47861760. Throughput: 0: 10223.4. Samples: 47861716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:11:05,829][613581] Avg episode reward: [(0, '4457.737')] [2023-03-09 04:11:07,428][613885] Updated weights for policy 0, policy_version 93520 (0.0005) [2023-03-09 04:11:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10191.4). Total num frames: 47915008. Throughput: 0: 10284.5. Samples: 47893732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:11:10,829][613581] Avg episode reward: [(0, '4298.917')] [2023-03-09 04:11:11,303][613885] Updated weights for policy 0, policy_version 93600 (0.0004) [2023-03-09 04:11:15,387][613885] Updated weights for policy 0, policy_version 93680 (0.0004) [2023-03-09 04:11:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 10191.4). Total num frames: 47964160. Throughput: 0: 10276.4. Samples: 47952396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:11:15,829][613581] Avg episode reward: [(0, '4333.712')] [2023-03-09 04:11:15,867][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000093688_47968256.pth... [2023-03-09 04:11:15,869][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000093080_47656960.pth [2023-03-09 04:11:19,346][613885] Updated weights for policy 0, policy_version 93760 (0.0005) [2023-03-09 04:11:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10219.2). Total num frames: 48021504. Throughput: 0: 10414.8. Samples: 48017320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:11:20,829][613581] Avg episode reward: [(0, '4436.342')] [2023-03-09 04:11:23,134][613885] Updated weights for policy 0, policy_version 93840 (0.0005) [2023-03-09 04:11:25,829][613581] Fps is (10 sec: 11059.4, 60 sec: 10376.5, 300 sec: 10219.2). Total num frames: 48074752. Throughput: 0: 10437.1. Samples: 48048880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:11:25,829][613581] Avg episode reward: [(0, '4323.808')] [2023-03-09 04:11:26,930][613885] Updated weights for policy 0, policy_version 93920 (0.0005) [2023-03-09 04:11:30,768][613885] Updated weights for policy 0, policy_version 94000 (0.0005) [2023-03-09 04:11:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10233.1). Total num frames: 48128000. Throughput: 0: 10482.6. Samples: 48112356. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:11:30,829][613581] Avg episode reward: [(0, '4423.900')] [2023-03-09 04:11:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000094000_48128000.pth... [2023-03-09 04:11:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000093384_47812608.pth [2023-03-09 04:11:34,696][613885] Updated weights for policy 0, policy_version 94080 (0.0004) [2023-03-09 04:11:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10205.3). Total num frames: 48177152. Throughput: 0: 10466.7. Samples: 48176672. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:11:35,829][613581] Avg episode reward: [(0, '4512.978')] [2023-03-09 04:11:38,641][613885] Updated weights for policy 0, policy_version 94160 (0.0005) [2023-03-09 04:11:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10219.2). Total num frames: 48230400. Throughput: 0: 10478.0. Samples: 48207452. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:11:40,829][613581] Avg episode reward: [(0, '4527.340')] [2023-03-09 04:11:42,650][613885] Updated weights for policy 0, policy_version 94240 (0.0005) [2023-03-09 04:11:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10205.3). Total num frames: 48279552. Throughput: 0: 10403.1. Samples: 48267736. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:11:45,829][613581] Avg episode reward: [(0, '4316.098')] [2023-03-09 04:11:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000094296_48279552.pth... [2023-03-09 04:11:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000093688_47968256.pth [2023-03-09 04:11:46,714][613885] Updated weights for policy 0, policy_version 94320 (0.0005) [2023-03-09 04:11:50,787][613885] Updated weights for policy 0, policy_version 94400 (0.0005) [2023-03-09 04:11:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10219.2). Total num frames: 48332800. Throughput: 0: 10366.9. Samples: 48328228. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:11:50,830][613581] Avg episode reward: [(0, '4489.451')] [2023-03-09 04:11:54,602][613885] Updated weights for policy 0, policy_version 94480 (0.0005) [2023-03-09 04:11:55,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10376.6, 300 sec: 10233.1). Total num frames: 48386048. Throughput: 0: 10389.5. Samples: 48361260. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:11:55,829][613581] Avg episode reward: [(0, '4441.658')] [2023-03-09 04:11:58,665][613885] Updated weights for policy 0, policy_version 94560 (0.0004) [2023-03-09 04:12:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10219.2). Total num frames: 48435200. Throughput: 0: 10433.4. Samples: 48421900. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:12:00,829][613581] Avg episode reward: [(0, '4461.039')] [2023-03-09 04:12:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000094600_48435200.pth... [2023-03-09 04:12:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000094000_48128000.pth [2023-03-09 04:12:02,805][613885] Updated weights for policy 0, policy_version 94640 (0.0005) [2023-03-09 04:12:05,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10376.6, 300 sec: 10205.3). Total num frames: 48484352. Throughput: 0: 10331.7. Samples: 48482244. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:12:05,829][613581] Avg episode reward: [(0, '4454.651')] [2023-03-09 04:12:06,735][613885] Updated weights for policy 0, policy_version 94720 (0.0005) [2023-03-09 04:12:10,818][613885] Updated weights for policy 0, policy_version 94800 (0.0005) [2023-03-09 04:12:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 10205.3). Total num frames: 48537600. Throughput: 0: 10315.7. Samples: 48513088. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:12:10,829][613581] Avg episode reward: [(0, '4480.437')] [2023-03-09 04:12:14,649][613885] Updated weights for policy 0, policy_version 94880 (0.0004) [2023-03-09 04:12:15,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10219.2). Total num frames: 48590848. Throughput: 0: 10299.8. Samples: 48575844. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:12:15,829][613581] Avg episode reward: [(0, '4327.038')] [2023-03-09 04:12:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000094904_48590848.pth... [2023-03-09 04:12:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000094296_48279552.pth [2023-03-09 04:12:18,630][613885] Updated weights for policy 0, policy_version 94960 (0.0005) [2023-03-09 04:12:20,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10219.2). Total num frames: 48640000. Throughput: 0: 10242.9. Samples: 48637600. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:12:20,829][613581] Avg episode reward: [(0, '4548.339')] [2023-03-09 04:12:22,504][613885] Updated weights for policy 0, policy_version 95040 (0.0005) [2023-03-09 04:12:25,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10233.1). Total num frames: 48693248. Throughput: 0: 10271.2. Samples: 48669656. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:12:25,829][613581] Avg episode reward: [(0, '4503.219')] [2023-03-09 04:12:26,270][613885] Updated weights for policy 0, policy_version 95120 (0.0005) [2023-03-09 04:12:30,363][613885] Updated weights for policy 0, policy_version 95200 (0.0005) [2023-03-09 04:12:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10246.9). Total num frames: 48746496. Throughput: 0: 10364.2. Samples: 48734124. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:12:30,829][613581] Avg episode reward: [(0, '4561.603')] [2023-03-09 04:12:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000095208_48746496.pth... [2023-03-09 04:12:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000094600_48435200.pth [2023-03-09 04:12:34,620][613885] Updated weights for policy 0, policy_version 95280 (0.0004) [2023-03-09 04:12:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10233.1). Total num frames: 48795648. Throughput: 0: 10292.0. Samples: 48791368. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:12:35,829][613581] Avg episode reward: [(0, '4509.584')] [2023-03-09 04:12:38,579][613885] Updated weights for policy 0, policy_version 95360 (0.0005) [2023-03-09 04:12:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10240.0, 300 sec: 10233.1). Total num frames: 48844800. Throughput: 0: 10237.4. Samples: 48821944. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:12:40,829][613581] Avg episode reward: [(0, '4456.858')] [2023-03-09 04:12:42,720][613885] Updated weights for policy 0, policy_version 95440 (0.0005) [2023-03-09 04:12:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10233.1). Total num frames: 48893952. Throughput: 0: 10227.4. Samples: 48882132. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:12:45,829][613581] Avg episode reward: [(0, '4449.155')] [2023-03-09 04:12:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000095496_48893952.pth... [2023-03-09 04:12:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000094904_48590848.pth [2023-03-09 04:12:46,724][613885] Updated weights for policy 0, policy_version 95520 (0.0005) [2023-03-09 04:12:50,759][613885] Updated weights for policy 0, policy_version 95600 (0.0005) [2023-03-09 04:12:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10246.9). Total num frames: 48947200. Throughput: 0: 10253.5. Samples: 48943652. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:12:50,829][613581] Avg episode reward: [(0, '4416.128')] [2023-03-09 04:12:54,544][613885] Updated weights for policy 0, policy_version 95680 (0.0005) [2023-03-09 04:12:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 10246.9). Total num frames: 49000448. Throughput: 0: 10284.3. Samples: 48975880. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:12:55,829][613581] Avg episode reward: [(0, '4500.372')] [2023-03-09 04:12:58,494][613885] Updated weights for policy 0, policy_version 95760 (0.0005) [2023-03-09 04:13:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10246.9). Total num frames: 49049600. Throughput: 0: 10262.4. Samples: 49037652. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:13:00,829][613581] Avg episode reward: [(0, '4470.742')] [2023-03-09 04:13:00,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000095800_49049600.pth... [2023-03-09 04:13:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000095208_48746496.pth [2023-03-09 04:13:02,557][613885] Updated weights for policy 0, policy_version 95840 (0.0005) [2023-03-09 04:13:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10233.1). Total num frames: 49098752. Throughput: 0: 10245.9. Samples: 49098668. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:13:05,829][613581] Avg episode reward: [(0, '4518.478')] [2023-03-09 04:13:06,659][613885] Updated weights for policy 0, policy_version 95920 (0.0005) [2023-03-09 04:13:10,658][613885] Updated weights for policy 0, policy_version 96000 (0.0005) [2023-03-09 04:13:10,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10233.1). Total num frames: 49152000. Throughput: 0: 10191.5. Samples: 49128276. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:13:10,829][613581] Avg episode reward: [(0, '4537.253')] [2023-03-09 04:13:14,645][613885] Updated weights for policy 0, policy_version 96080 (0.0005) [2023-03-09 04:13:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10240.0, 300 sec: 10260.8). Total num frames: 49205248. Throughput: 0: 10136.5. Samples: 49190268. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:13:15,829][613581] Avg episode reward: [(0, '4550.360')] [2023-03-09 04:13:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000096104_49205248.pth... [2023-03-09 04:13:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000095496_48893952.pth [2023-03-09 04:13:18,062][613885] Updated weights for policy 0, policy_version 96160 (0.0005) [2023-03-09 04:13:20,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10308.3, 300 sec: 10260.8). Total num frames: 49258496. Throughput: 0: 10309.8. Samples: 49255308. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:13:20,829][613581] Avg episode reward: [(0, '4505.562')] [2023-03-09 04:13:22,205][613885] Updated weights for policy 0, policy_version 96240 (0.0004) [2023-03-09 04:13:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10246.9). Total num frames: 49307648. Throughput: 0: 10334.9. Samples: 49287016. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:13:25,829][613581] Avg episode reward: [(0, '4369.190')] [2023-03-09 04:13:26,472][613885] Updated weights for policy 0, policy_version 96320 (0.0004) [2023-03-09 04:13:30,144][613885] Updated weights for policy 0, policy_version 96400 (0.0005) [2023-03-09 04:13:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10260.8). Total num frames: 49360896. Throughput: 0: 10366.3. Samples: 49348616. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:13:30,829][613581] Avg episode reward: [(0, '4501.570')] [2023-03-09 04:13:30,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000096408_49360896.pth... [2023-03-09 04:13:30,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000095800_49049600.pth [2023-03-09 04:13:34,219][613885] Updated weights for policy 0, policy_version 96480 (0.0004) [2023-03-09 04:13:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10274.7). Total num frames: 49414144. Throughput: 0: 10362.2. Samples: 49409952. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:13:35,829][613581] Avg episode reward: [(0, '4466.003')] [2023-03-09 04:13:38,139][613885] Updated weights for policy 0, policy_version 96560 (0.0005) [2023-03-09 04:13:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10274.7). Total num frames: 49463296. Throughput: 0: 10351.9. Samples: 49441716. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:13:40,829][613581] Avg episode reward: [(0, '4380.482')] [2023-03-09 04:13:42,177][613885] Updated weights for policy 0, policy_version 96640 (0.0004) [2023-03-09 04:13:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10274.7). Total num frames: 49516544. Throughput: 0: 10334.6. Samples: 49502708. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:13:45,830][613581] Avg episode reward: [(0, '4589.516')] [2023-03-09 04:13:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000096712_49516544.pth... [2023-03-09 04:13:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000096104_49205248.pth [2023-03-09 04:13:45,836][613841] Saving new best policy, reward=4589.516! [2023-03-09 04:13:46,225][613885] Updated weights for policy 0, policy_version 96720 (0.0004) [2023-03-09 04:13:50,102][613885] Updated weights for policy 0, policy_version 96800 (0.0004) [2023-03-09 04:13:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10260.8). Total num frames: 49565696. Throughput: 0: 10366.9. Samples: 49565176. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:13:50,829][613581] Avg episode reward: [(0, '4582.610')] [2023-03-09 04:13:53,987][613885] Updated weights for policy 0, policy_version 96880 (0.0005) [2023-03-09 04:13:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10260.8). Total num frames: 49618944. Throughput: 0: 10396.5. Samples: 49596116. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:13:55,829][613581] Avg episode reward: [(0, '4536.078')] [2023-03-09 04:13:57,843][613885] Updated weights for policy 0, policy_version 96960 (0.0005) [2023-03-09 04:14:00,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10376.5, 300 sec: 10274.7). Total num frames: 49672192. Throughput: 0: 10402.1. Samples: 49658364. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:14:00,829][613581] Avg episode reward: [(0, '4400.348')] [2023-03-09 04:14:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000097016_49672192.pth... [2023-03-09 04:14:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000096408_49360896.pth [2023-03-09 04:14:01,904][613885] Updated weights for policy 0, policy_version 97040 (0.0004) [2023-03-09 04:14:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10260.8). Total num frames: 49721344. Throughput: 0: 10348.9. Samples: 49721008. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:14:05,829][613581] Avg episode reward: [(0, '4421.646')] [2023-03-09 04:14:05,844][613885] Updated weights for policy 0, policy_version 97120 (0.0005) [2023-03-09 04:14:09,797][613885] Updated weights for policy 0, policy_version 97200 (0.0005) [2023-03-09 04:14:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10274.7). Total num frames: 49774592. Throughput: 0: 10342.5. Samples: 49752428. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:14:10,829][613581] Avg episode reward: [(0, '4381.972')] [2023-03-09 04:14:13,552][613885] Updated weights for policy 0, policy_version 97280 (0.0005) [2023-03-09 04:14:15,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10274.7). Total num frames: 49827840. Throughput: 0: 10377.8. Samples: 49815616. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:14:15,829][613581] Avg episode reward: [(0, '4501.789')] [2023-03-09 04:14:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000097320_49827840.pth... [2023-03-09 04:14:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000096712_49516544.pth [2023-03-09 04:14:17,620][613885] Updated weights for policy 0, policy_version 97360 (0.0005) [2023-03-09 04:14:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10288.6). Total num frames: 49881088. Throughput: 0: 10380.1. Samples: 49877056. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:14:20,829][613581] Avg episode reward: [(0, '4415.459')] [2023-03-09 04:14:21,419][613885] Updated weights for policy 0, policy_version 97440 (0.0004) [2023-03-09 04:14:25,323][613885] Updated weights for policy 0, policy_version 97520 (0.0005) [2023-03-09 04:14:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10288.6). Total num frames: 49934336. Throughput: 0: 10401.2. Samples: 49909768. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:14:25,829][613581] Avg episode reward: [(0, '4453.288')] [2023-03-09 04:14:29,096][613885] Updated weights for policy 0, policy_version 97600 (0.0004) [2023-03-09 04:14:30,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 10274.7). Total num frames: 49983488. Throughput: 0: 10485.8. Samples: 49974568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:14:30,829][613581] Avg episode reward: [(0, '4418.680')] [2023-03-09 04:14:30,847][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000097632_49987584.pth... [2023-03-09 04:14:30,849][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000097016_49672192.pth [2023-03-09 04:14:33,128][613885] Updated weights for policy 0, policy_version 97680 (0.0005) [2023-03-09 04:14:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.6, 300 sec: 10288.6). Total num frames: 50036736. Throughput: 0: 10452.4. Samples: 50035536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:14:35,829][613581] Avg episode reward: [(0, '4550.105')] [2023-03-09 04:14:37,037][613885] Updated weights for policy 0, policy_version 97760 (0.0005) [2023-03-09 04:14:40,817][613885] Updated weights for policy 0, policy_version 97840 (0.0004) [2023-03-09 04:14:40,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10513.1, 300 sec: 10302.5). Total num frames: 50094080. Throughput: 0: 10489.6. Samples: 50068148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:14:40,829][613581] Avg episode reward: [(0, '4542.333')] [2023-03-09 04:14:44,794][613885] Updated weights for policy 0, policy_version 97920 (0.0006) [2023-03-09 04:14:45,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10444.8, 300 sec: 10302.5). Total num frames: 50143232. Throughput: 0: 10503.2. Samples: 50131008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:14:45,829][613581] Avg episode reward: [(0, '4523.702')] [2023-03-09 04:14:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000097936_50143232.pth... [2023-03-09 04:14:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000097320_49827840.pth [2023-03-09 04:14:48,539][613885] Updated weights for policy 0, policy_version 98000 (0.0005) [2023-03-09 04:14:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10316.4). Total num frames: 50196480. Throughput: 0: 10556.2. Samples: 50196036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:14:50,829][613581] Avg episode reward: [(0, '4570.382')] [2023-03-09 04:14:52,720][613885] Updated weights for policy 0, policy_version 98080 (0.0004) [2023-03-09 04:14:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10316.4). Total num frames: 50245632. Throughput: 0: 10461.2. Samples: 50223184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:14:55,829][613581] Avg episode reward: [(0, '4586.569')] [2023-03-09 04:14:56,674][613885] Updated weights for policy 0, policy_version 98160 (0.0005) [2023-03-09 04:15:00,567][613885] Updated weights for policy 0, policy_version 98240 (0.0004) [2023-03-09 04:15:00,829][613581] Fps is (10 sec: 10239.8, 60 sec: 10444.8, 300 sec: 10344.1). Total num frames: 50298880. Throughput: 0: 10465.5. Samples: 50286564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:15:00,829][613581] Avg episode reward: [(0, '4551.993')] [2023-03-09 04:15:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000098240_50298880.pth... [2023-03-09 04:15:00,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000097632_49987584.pth [2023-03-09 04:15:04,518][613885] Updated weights for policy 0, policy_version 98320 (0.0005) [2023-03-09 04:15:05,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10513.1, 300 sec: 10330.3). Total num frames: 50352128. Throughput: 0: 10467.6. Samples: 50348096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:15:05,829][613581] Avg episode reward: [(0, '4502.396')] [2023-03-09 04:15:08,380][613885] Updated weights for policy 0, policy_version 98400 (0.0004) [2023-03-09 04:15:10,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10513.1, 300 sec: 10344.1). Total num frames: 50405376. Throughput: 0: 10467.4. Samples: 50380800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:15:10,829][613581] Avg episode reward: [(0, '4596.591')] [2023-03-09 04:15:10,830][613841] Saving new best policy, reward=4596.591! [2023-03-09 04:15:12,402][613885] Updated weights for policy 0, policy_version 98480 (0.0006) [2023-03-09 04:15:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10344.1). Total num frames: 50454528. Throughput: 0: 10394.1. Samples: 50442304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:15:15,829][613581] Avg episode reward: [(0, '4576.652')] [2023-03-09 04:15:15,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000098544_50454528.pth... [2023-03-09 04:15:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000097936_50143232.pth [2023-03-09 04:15:16,345][613885] Updated weights for policy 0, policy_version 98560 (0.0004) [2023-03-09 04:15:20,086][613885] Updated weights for policy 0, policy_version 98640 (0.0005) [2023-03-09 04:15:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10358.0). Total num frames: 50507776. Throughput: 0: 10489.0. Samples: 50507540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:15:20,829][613581] Avg episode reward: [(0, '4581.069')] [2023-03-09 04:15:23,964][613885] Updated weights for policy 0, policy_version 98720 (0.0005) [2023-03-09 04:15:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10371.9). Total num frames: 50561024. Throughput: 0: 10445.2. Samples: 50538180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:15:25,829][613581] Avg episode reward: [(0, '4610.528')] [2023-03-09 04:15:25,829][613841] Saving new best policy, reward=4610.528! [2023-03-09 04:15:27,891][613885] Updated weights for policy 0, policy_version 98800 (0.0005) [2023-03-09 04:15:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10385.8). Total num frames: 50614272. Throughput: 0: 10465.9. Samples: 50601972. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:15:30,829][613581] Avg episode reward: [(0, '4604.031')] [2023-03-09 04:15:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000098856_50614272.pth... [2023-03-09 04:15:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000098240_50298880.pth [2023-03-09 04:15:31,878][613885] Updated weights for policy 0, policy_version 98880 (0.0005) [2023-03-09 04:15:35,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10444.8, 300 sec: 10371.9). Total num frames: 50663424. Throughput: 0: 10385.4. Samples: 50663380. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:15:35,829][613581] Avg episode reward: [(0, '4598.336')] [2023-03-09 04:15:35,864][613885] Updated weights for policy 0, policy_version 98960 (0.0004) [2023-03-09 04:15:39,589][613885] Updated weights for policy 0, policy_version 99040 (0.0005) [2023-03-09 04:15:40,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10385.8). Total num frames: 50720768. Throughput: 0: 10512.9. Samples: 50696264. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:15:40,829][613581] Avg episode reward: [(0, '4570.583')] [2023-03-09 04:15:43,500][613885] Updated weights for policy 0, policy_version 99120 (0.0005) [2023-03-09 04:15:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10385.8). Total num frames: 50769920. Throughput: 0: 10469.8. Samples: 50757704. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:15:45,829][613581] Avg episode reward: [(0, '4589.404')] [2023-03-09 04:15:45,839][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000099168_50774016.pth... [2023-03-09 04:15:45,841][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000098544_50454528.pth [2023-03-09 04:15:47,415][613885] Updated weights for policy 0, policy_version 99200 (0.0005) [2023-03-09 04:15:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10371.9). Total num frames: 50823168. Throughput: 0: 10552.0. Samples: 50822936. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:15:50,829][613581] Avg episode reward: [(0, '4542.544')] [2023-03-09 04:15:51,286][613885] Updated weights for policy 0, policy_version 99280 (0.0005) [2023-03-09 04:15:55,285][613885] Updated weights for policy 0, policy_version 99360 (0.0005) [2023-03-09 04:15:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10385.8). Total num frames: 50876416. Throughput: 0: 10495.6. Samples: 50853104. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:15:55,830][613581] Avg episode reward: [(0, '4579.558')] [2023-03-09 04:15:59,134][613885] Updated weights for policy 0, policy_version 99440 (0.0005) [2023-03-09 04:16:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10385.8). Total num frames: 50925568. Throughput: 0: 10532.0. Samples: 50916244. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:16:00,829][613581] Avg episode reward: [(0, '4471.252')] [2023-03-09 04:16:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000099464_50925568.pth... [2023-03-09 04:16:00,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000098856_50614272.pth [2023-03-09 04:16:03,115][613885] Updated weights for policy 0, policy_version 99520 (0.0005) [2023-03-09 04:16:05,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10385.8). Total num frames: 50978816. Throughput: 0: 10459.3. Samples: 50978208. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:16:05,829][613581] Avg episode reward: [(0, '4589.537')] [2023-03-09 04:16:07,054][613885] Updated weights for policy 0, policy_version 99600 (0.0005) [2023-03-09 04:16:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10385.8). Total num frames: 51027968. Throughput: 0: 10429.0. Samples: 51007488. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:16:10,829][613581] Avg episode reward: [(0, '4503.029')] [2023-03-09 04:16:11,430][613885] Updated weights for policy 0, policy_version 99680 (0.0004) [2023-03-09 04:16:15,372][613885] Updated weights for policy 0, policy_version 99760 (0.0005) [2023-03-09 04:16:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10371.9). Total num frames: 51081216. Throughput: 0: 10316.6. Samples: 51066220. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:16:15,829][613581] Avg episode reward: [(0, '4479.056')] [2023-03-09 04:16:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000099768_51081216.pth... [2023-03-09 04:16:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000099168_50774016.pth [2023-03-09 04:16:19,433][613885] Updated weights for policy 0, policy_version 99840 (0.0005) [2023-03-09 04:16:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 51130368. Throughput: 0: 10330.0. Samples: 51128232. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:16:20,829][613581] Avg episode reward: [(0, '4227.694')] [2023-03-09 04:16:23,427][613885] Updated weights for policy 0, policy_version 99920 (0.0004) [2023-03-09 04:16:25,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10371.9). Total num frames: 51187712. Throughput: 0: 10281.9. Samples: 51158948. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:16:25,829][613581] Avg episode reward: [(0, '4471.521')] [2023-03-09 04:16:27,072][613885] Updated weights for policy 0, policy_version 100000 (0.0005) [2023-03-09 04:16:30,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 51236864. Throughput: 0: 10352.5. Samples: 51223564. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:16:30,829][613581] Avg episode reward: [(0, '4475.238')] [2023-03-09 04:16:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000100072_51236864.pth... [2023-03-09 04:16:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000099464_50925568.pth [2023-03-09 04:16:31,122][613885] Updated weights for policy 0, policy_version 100080 (0.0005) [2023-03-09 04:16:35,332][613885] Updated weights for policy 0, policy_version 100160 (0.0005) [2023-03-09 04:16:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 51286016. Throughput: 0: 10201.0. Samples: 51281984. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:16:35,829][613581] Avg episode reward: [(0, '4574.303')] [2023-03-09 04:16:39,368][613885] Updated weights for policy 0, policy_version 100240 (0.0005) [2023-03-09 04:16:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10358.0). Total num frames: 51335168. Throughput: 0: 10217.1. Samples: 51312872. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:16:40,829][613581] Avg episode reward: [(0, '4516.594')] [2023-03-09 04:16:43,153][613885] Updated weights for policy 0, policy_version 100320 (0.0005) [2023-03-09 04:16:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 51392512. Throughput: 0: 10264.9. Samples: 51378164. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:16:45,829][613581] Avg episode reward: [(0, '4551.054')] [2023-03-09 04:16:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000100376_51392512.pth... [2023-03-09 04:16:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000099768_51081216.pth [2023-03-09 04:16:46,831][613885] Updated weights for policy 0, policy_version 100400 (0.0005) [2023-03-09 04:16:50,593][613885] Updated weights for policy 0, policy_version 100480 (0.0006) [2023-03-09 04:16:50,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 51445760. Throughput: 0: 10328.9. Samples: 51443008. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:16:50,829][613581] Avg episode reward: [(0, '4579.963')] [2023-03-09 04:16:54,397][613885] Updated weights for policy 0, policy_version 100560 (0.0005) [2023-03-09 04:16:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10385.8). Total num frames: 51499008. Throughput: 0: 10391.7. Samples: 51475116. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:16:55,829][613581] Avg episode reward: [(0, '4571.894')] [2023-03-09 04:16:58,181][613885] Updated weights for policy 0, policy_version 100640 (0.0005) [2023-03-09 04:17:00,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10399.7). Total num frames: 51552256. Throughput: 0: 10527.9. Samples: 51539976. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:17:00,829][613581] Avg episode reward: [(0, '4553.705')] [2023-03-09 04:17:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000100688_51552256.pth... [2023-03-09 04:17:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000100072_51236864.pth [2023-03-09 04:17:02,423][613885] Updated weights for policy 0, policy_version 100720 (0.0005) [2023-03-09 04:17:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10385.8). Total num frames: 51601408. Throughput: 0: 10423.6. Samples: 51597296. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:17:05,829][613581] Avg episode reward: [(0, '4583.331')] [2023-03-09 04:17:06,628][613885] Updated weights for policy 0, policy_version 100800 (0.0005) [2023-03-09 04:17:10,630][613885] Updated weights for policy 0, policy_version 100880 (0.0005) [2023-03-09 04:17:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 51650560. Throughput: 0: 10406.0. Samples: 51627220. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:17:10,829][613581] Avg episode reward: [(0, '4382.905')] [2023-03-09 04:17:14,751][613885] Updated weights for policy 0, policy_version 100960 (0.0006) [2023-03-09 04:17:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 51699712. Throughput: 0: 10309.4. Samples: 51687488. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:17:15,829][613581] Avg episode reward: [(0, '4556.690')] [2023-03-09 04:17:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000100976_51699712.pth... [2023-03-09 04:17:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000100376_51392512.pth [2023-03-09 04:17:18,811][613885] Updated weights for policy 0, policy_version 101040 (0.0006) [2023-03-09 04:17:20,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10308.3, 300 sec: 10358.0). Total num frames: 51748864. Throughput: 0: 10371.3. Samples: 51748692. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:17:20,829][613581] Avg episode reward: [(0, '4608.044')] [2023-03-09 04:17:22,946][613885] Updated weights for policy 0, policy_version 101120 (0.0005) [2023-03-09 04:17:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10358.0). Total num frames: 51802112. Throughput: 0: 10343.0. Samples: 51778308. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:17:25,829][613581] Avg episode reward: [(0, '4424.974')] [2023-03-09 04:17:26,891][613885] Updated weights for policy 0, policy_version 101200 (0.0005) [2023-03-09 04:17:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10358.0). Total num frames: 51851264. Throughput: 0: 10260.9. Samples: 51839904. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:17:30,829][613581] Avg episode reward: [(0, '4345.259')] [2023-03-09 04:17:30,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000101272_51851264.pth... [2023-03-09 04:17:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000100688_51552256.pth [2023-03-09 04:17:30,883][613885] Updated weights for policy 0, policy_version 101280 (0.0005) [2023-03-09 04:17:34,567][613885] Updated weights for policy 0, policy_version 101360 (0.0005) [2023-03-09 04:17:35,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 10385.8). Total num frames: 51908608. Throughput: 0: 10306.4. Samples: 51906796. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:17:35,829][613581] Avg episode reward: [(0, '4455.583')] [2023-03-09 04:17:38,158][613885] Updated weights for policy 0, policy_version 101440 (0.0004) [2023-03-09 04:17:40,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10444.8, 300 sec: 10399.7). Total num frames: 51961856. Throughput: 0: 10331.0. Samples: 51940012. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:17:40,829][613581] Avg episode reward: [(0, '4568.402')] [2023-03-09 04:17:41,972][613885] Updated weights for policy 0, policy_version 101520 (0.0005) [2023-03-09 04:17:45,825][613885] Updated weights for policy 0, policy_version 101600 (0.0005) [2023-03-09 04:17:45,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10444.8, 300 sec: 10413.6). Total num frames: 52019200. Throughput: 0: 10296.8. Samples: 52003332. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:17:45,829][613581] Avg episode reward: [(0, '4514.121')] [2023-03-09 04:17:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000101600_52019200.pth... [2023-03-09 04:17:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000100976_51699712.pth [2023-03-09 04:17:49,779][613885] Updated weights for policy 0, policy_version 101680 (0.0004) [2023-03-09 04:17:50,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10399.7). Total num frames: 52068352. Throughput: 0: 10418.8. Samples: 52066140. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:17:50,829][613581] Avg episode reward: [(0, '4541.338')] [2023-03-09 04:17:53,685][613885] Updated weights for policy 0, policy_version 101760 (0.0005) [2023-03-09 04:17:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.6, 300 sec: 10413.6). Total num frames: 52121600. Throughput: 0: 10441.5. Samples: 52097088. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:17:55,829][613581] Avg episode reward: [(0, '4454.078')] [2023-03-09 04:17:57,494][613885] Updated weights for policy 0, policy_version 101840 (0.0005) [2023-03-09 04:18:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10413.6). Total num frames: 52170752. Throughput: 0: 10534.3. Samples: 52161532. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:18:00,829][613581] Avg episode reward: [(0, '4510.742')] [2023-03-09 04:18:00,878][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000101904_52174848.pth... [2023-03-09 04:18:00,879][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000101272_51851264.pth [2023-03-09 04:18:01,690][613885] Updated weights for policy 0, policy_version 101920 (0.0005) [2023-03-09 04:18:05,454][613885] Updated weights for policy 0, policy_version 102000 (0.0005) [2023-03-09 04:18:05,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10427.4). Total num frames: 52228096. Throughput: 0: 10557.3. Samples: 52223772. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:18:05,829][613581] Avg episode reward: [(0, '4569.675')] [2023-03-09 04:18:09,258][613885] Updated weights for policy 0, policy_version 102080 (0.0004) [2023-03-09 04:18:10,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10513.1, 300 sec: 10427.4). Total num frames: 52281344. Throughput: 0: 10616.7. Samples: 52256060. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:18:10,829][613581] Avg episode reward: [(0, '4511.804')] [2023-03-09 04:18:13,176][613885] Updated weights for policy 0, policy_version 102160 (0.0005) [2023-03-09 04:18:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10413.6). Total num frames: 52330496. Throughput: 0: 10630.4. Samples: 52318272. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:18:15,829][613581] Avg episode reward: [(0, '4516.044')] [2023-03-09 04:18:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000102208_52330496.pth... [2023-03-09 04:18:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000101600_52019200.pth [2023-03-09 04:18:17,136][613885] Updated weights for policy 0, policy_version 102240 (0.0005) [2023-03-09 04:18:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10581.3, 300 sec: 10427.4). Total num frames: 52383744. Throughput: 0: 10516.5. Samples: 52380040. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:18:20,829][613581] Avg episode reward: [(0, '4310.362')] [2023-03-09 04:18:20,987][613885] Updated weights for policy 0, policy_version 102320 (0.0004) [2023-03-09 04:18:24,794][613885] Updated weights for policy 0, policy_version 102400 (0.0005) [2023-03-09 04:18:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10427.4). Total num frames: 52436992. Throughput: 0: 10537.3. Samples: 52414192. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:18:25,829][613581] Avg episode reward: [(0, '4574.848')] [2023-03-09 04:18:28,911][613885] Updated weights for policy 0, policy_version 102480 (0.0004) [2023-03-09 04:18:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10581.3, 300 sec: 10413.6). Total num frames: 52486144. Throughput: 0: 10472.8. Samples: 52474608. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:18:30,829][613581] Avg episode reward: [(0, '4519.142')] [2023-03-09 04:18:30,866][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000102520_52490240.pth... [2023-03-09 04:18:30,868][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000101904_52174848.pth [2023-03-09 04:18:32,763][613885] Updated weights for policy 0, policy_version 102560 (0.0005) [2023-03-09 04:18:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10427.4). Total num frames: 52539392. Throughput: 0: 10507.8. Samples: 52538992. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:18:35,829][613581] Avg episode reward: [(0, '4565.026')] [2023-03-09 04:18:36,691][613885] Updated weights for policy 0, policy_version 102640 (0.0005) [2023-03-09 04:18:40,735][613885] Updated weights for policy 0, policy_version 102720 (0.0004) [2023-03-09 04:18:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10427.4). Total num frames: 52592640. Throughput: 0: 10467.5. Samples: 52568128. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:18:40,829][613581] Avg episode reward: [(0, '4510.492')] [2023-03-09 04:18:44,624][613885] Updated weights for policy 0, policy_version 102800 (0.0005) [2023-03-09 04:18:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10441.3). Total num frames: 52645888. Throughput: 0: 10446.4. Samples: 52631620. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:18:45,829][613581] Avg episode reward: [(0, '4579.123')] [2023-03-09 04:18:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000102824_52645888.pth... [2023-03-09 04:18:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000102208_52330496.pth [2023-03-09 04:18:48,631][613885] Updated weights for policy 0, policy_version 102880 (0.0005) [2023-03-09 04:18:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10427.4). Total num frames: 52695040. Throughput: 0: 10409.1. Samples: 52692180. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:18:50,829][613581] Avg episode reward: [(0, '4577.238')] [2023-03-09 04:18:52,705][613885] Updated weights for policy 0, policy_version 102960 (0.0005) [2023-03-09 04:18:55,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10444.8, 300 sec: 10427.4). Total num frames: 52748288. Throughput: 0: 10390.9. Samples: 52723652. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:18:55,829][613581] Avg episode reward: [(0, '4599.090')] [2023-03-09 04:18:56,544][613885] Updated weights for policy 0, policy_version 103040 (0.0005) [2023-03-09 04:19:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10376.5, 300 sec: 10413.6). Total num frames: 52793344. Throughput: 0: 10363.8. Samples: 52784644. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:19:00,830][613581] Avg episode reward: [(0, '4608.748')] [2023-03-09 04:19:00,852][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000103120_52797440.pth... [2023-03-09 04:19:00,853][613885] Updated weights for policy 0, policy_version 103120 (0.0005) [2023-03-09 04:19:00,854][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000102520_52490240.pth [2023-03-09 04:19:04,958][613885] Updated weights for policy 0, policy_version 103200 (0.0004) [2023-03-09 04:19:05,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10308.2, 300 sec: 10413.6). Total num frames: 52846592. Throughput: 0: 10276.8. Samples: 52842496. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:19:05,830][613581] Avg episode reward: [(0, '4600.907')] [2023-03-09 04:19:08,981][613885] Updated weights for policy 0, policy_version 103280 (0.0005) [2023-03-09 04:19:10,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10240.0, 300 sec: 10399.7). Total num frames: 52895744. Throughput: 0: 10205.6. Samples: 52873444. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:19:10,829][613581] Avg episode reward: [(0, '4566.644')] [2023-03-09 04:19:12,980][613885] Updated weights for policy 0, policy_version 103360 (0.0005) [2023-03-09 04:19:15,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10399.7). Total num frames: 52948992. Throughput: 0: 10270.4. Samples: 52936776. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:19:15,829][613581] Avg episode reward: [(0, '4554.820')] [2023-03-09 04:19:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000103416_52948992.pth... [2023-03-09 04:19:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000102824_52645888.pth [2023-03-09 04:19:16,717][613885] Updated weights for policy 0, policy_version 103440 (0.0005) [2023-03-09 04:19:20,555][613885] Updated weights for policy 0, policy_version 103520 (0.0005) [2023-03-09 04:19:20,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10399.7). Total num frames: 53002240. Throughput: 0: 10270.9. Samples: 53001184. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:19:20,829][613581] Avg episode reward: [(0, '4611.573')] [2023-03-09 04:19:20,830][613841] Saving new best policy, reward=4611.573! [2023-03-09 04:19:24,547][613885] Updated weights for policy 0, policy_version 103600 (0.0005) [2023-03-09 04:19:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10413.6). Total num frames: 53055488. Throughput: 0: 10285.7. Samples: 53030984. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:19:25,829][613581] Avg episode reward: [(0, '4604.404')] [2023-03-09 04:19:28,457][613885] Updated weights for policy 0, policy_version 103680 (0.0005) [2023-03-09 04:19:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10413.6). Total num frames: 53108736. Throughput: 0: 10258.0. Samples: 53093232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:19:30,829][613581] Avg episode reward: [(0, '4573.676')] [2023-03-09 04:19:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000103728_53108736.pth... [2023-03-09 04:19:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000103120_52797440.pth [2023-03-09 04:19:32,186][613885] Updated weights for policy 0, policy_version 103760 (0.0005) [2023-03-09 04:19:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10385.8). Total num frames: 53157888. Throughput: 0: 10331.5. Samples: 53157096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:19:35,829][613581] Avg episode reward: [(0, '4610.461')] [2023-03-09 04:19:36,375][613885] Updated weights for policy 0, policy_version 103840 (0.0004) [2023-03-09 04:19:40,369][613885] Updated weights for policy 0, policy_version 103920 (0.0004) [2023-03-09 04:19:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10399.7). Total num frames: 53211136. Throughput: 0: 10302.5. Samples: 53187264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:19:40,829][613581] Avg episode reward: [(0, '4564.100')] [2023-03-09 04:19:41,566][613841] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000002 [2023-03-09 04:19:44,124][613885] Updated weights for policy 0, policy_version 104000 (0.0005) [2023-03-09 04:19:45,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.2, 300 sec: 10399.7). Total num frames: 53264384. Throughput: 0: 10372.3. Samples: 53251396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:19:45,829][613581] Avg episode reward: [(0, '4530.871')] [2023-03-09 04:19:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000104032_53264384.pth... [2023-03-09 04:19:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000103416_52948992.pth [2023-03-09 04:19:47,885][613885] Updated weights for policy 0, policy_version 104080 (0.0005) [2023-03-09 04:19:50,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10444.8, 300 sec: 10427.4). Total num frames: 53321728. Throughput: 0: 10557.1. Samples: 53317564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:19:50,829][613581] Avg episode reward: [(0, '4556.999')] [2023-03-09 04:19:51,553][613885] Updated weights for policy 0, policy_version 104160 (0.0005) [2023-03-09 04:19:55,527][613885] Updated weights for policy 0, policy_version 104240 (0.0005) [2023-03-09 04:19:55,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10376.5, 300 sec: 10413.6). Total num frames: 53370880. Throughput: 0: 10574.3. Samples: 53349288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:19:55,829][613581] Avg episode reward: [(0, '4442.463')] [2023-03-09 04:19:59,654][613885] Updated weights for policy 0, policy_version 104320 (0.0004) [2023-03-09 04:20:00,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10513.1, 300 sec: 10413.6). Total num frames: 53424128. Throughput: 0: 10512.1. Samples: 53409820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:20:00,840][613581] Avg episode reward: [(0, '4343.763')] [2023-03-09 04:20:00,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000104344_53424128.pth... [2023-03-09 04:20:00,845][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000103728_53108736.pth [2023-03-09 04:20:03,682][613885] Updated weights for policy 0, policy_version 104400 (0.0005) [2023-03-09 04:20:05,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10399.7). Total num frames: 53473280. Throughput: 0: 10401.4. Samples: 53469248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:20:05,829][613581] Avg episode reward: [(0, '4615.631')] [2023-03-09 04:20:05,830][613841] Saving new best policy, reward=4615.631! [2023-03-09 04:20:07,808][613885] Updated weights for policy 0, policy_version 104480 (0.0004) [2023-03-09 04:20:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 10376.5, 300 sec: 10385.8). Total num frames: 53518336. Throughput: 0: 10404.5. Samples: 53499184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:20:10,840][613581] Avg episode reward: [(0, '4505.864')] [2023-03-09 04:20:12,101][613885] Updated weights for policy 0, policy_version 104560 (0.0004) [2023-03-09 04:20:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 10385.8). Total num frames: 53571584. Throughput: 0: 10342.3. Samples: 53558636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:20:15,840][613581] Avg episode reward: [(0, '4616.587')] [2023-03-09 04:20:15,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000104632_53571584.pth... [2023-03-09 04:20:15,843][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000104032_53264384.pth [2023-03-09 04:20:15,844][613841] Saving new best policy, reward=4616.587! [2023-03-09 04:20:15,971][613885] Updated weights for policy 0, policy_version 104640 (0.0005) [2023-03-09 04:20:20,127][613885] Updated weights for policy 0, policy_version 104720 (0.0005) [2023-03-09 04:20:20,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 53620736. Throughput: 0: 10281.1. Samples: 53619744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:20:20,840][613581] Avg episode reward: [(0, '4372.282')] [2023-03-09 04:20:24,077][613885] Updated weights for policy 0, policy_version 104800 (0.0005) [2023-03-09 04:20:25,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 53673984. Throughput: 0: 10287.9. Samples: 53650220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:20:25,840][613581] Avg episode reward: [(0, '4447.162')] [2023-03-09 04:20:27,902][613885] Updated weights for policy 0, policy_version 104880 (0.0005) [2023-03-09 04:20:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10385.8). Total num frames: 53727232. Throughput: 0: 10259.5. Samples: 53713072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:20:30,840][613581] Avg episode reward: [(0, '4430.913')] [2023-03-09 04:20:30,843][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000104936_53727232.pth... [2023-03-09 04:20:30,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000104344_53424128.pth [2023-03-09 04:20:31,838][613885] Updated weights for policy 0, policy_version 104960 (0.0005) [2023-03-09 04:20:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10358.0). Total num frames: 53776384. Throughput: 0: 10193.6. Samples: 53776276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:20:35,829][613581] Avg episode reward: [(0, '4620.029')] [2023-03-09 04:20:35,868][613841] Saving new best policy, reward=4620.029! [2023-03-09 04:20:35,868][613885] Updated weights for policy 0, policy_version 105040 (0.0005) [2023-03-09 04:20:39,882][613885] Updated weights for policy 0, policy_version 105120 (0.0005) [2023-03-09 04:20:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 53829632. Throughput: 0: 10182.9. Samples: 53807520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:20:40,829][613581] Avg episode reward: [(0, '4489.380')] [2023-03-09 04:20:43,474][613885] Updated weights for policy 0, policy_version 105200 (0.0005) [2023-03-09 04:20:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 53882880. Throughput: 0: 10252.2. Samples: 53871168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:20:45,829][613581] Avg episode reward: [(0, '4608.071')] [2023-03-09 04:20:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000105240_53882880.pth... [2023-03-09 04:20:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000104632_53571584.pth [2023-03-09 04:20:47,456][613885] Updated weights for policy 0, policy_version 105280 (0.0005) [2023-03-09 04:20:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.8, 300 sec: 10358.0). Total num frames: 53932032. Throughput: 0: 10271.3. Samples: 53931456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:20:50,829][613581] Avg episode reward: [(0, '4500.428')] [2023-03-09 04:20:51,787][613885] Updated weights for policy 0, policy_version 105360 (0.0005) [2023-03-09 04:20:55,679][613885] Updated weights for policy 0, policy_version 105440 (0.0005) [2023-03-09 04:20:55,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10240.0, 300 sec: 10371.9). Total num frames: 53985280. Throughput: 0: 10271.8. Samples: 53961416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:20:55,829][613581] Avg episode reward: [(0, '4603.707')] [2023-03-09 04:20:59,557][613885] Updated weights for policy 0, policy_version 105520 (0.0005) [2023-03-09 04:21:00,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10240.0, 300 sec: 10371.9). Total num frames: 54038528. Throughput: 0: 10364.9. Samples: 54025056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:21:00,829][613581] Avg episode reward: [(0, '4431.601')] [2023-03-09 04:21:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000105544_54038528.pth... [2023-03-09 04:21:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000104936_53727232.pth [2023-03-09 04:21:03,464][613885] Updated weights for policy 0, policy_version 105600 (0.0005) [2023-03-09 04:21:05,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10371.9). Total num frames: 54087680. Throughput: 0: 10367.4. Samples: 54086276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:21:05,829][613581] Avg episode reward: [(0, '4457.209')] [2023-03-09 04:21:07,666][613885] Updated weights for policy 0, policy_version 105680 (0.0005) [2023-03-09 04:21:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10308.2, 300 sec: 10358.0). Total num frames: 54136832. Throughput: 0: 10345.0. Samples: 54115744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:21:10,829][613581] Avg episode reward: [(0, '4453.891')] [2023-03-09 04:21:11,803][613885] Updated weights for policy 0, policy_version 105760 (0.0005) [2023-03-09 04:21:15,801][613885] Updated weights for policy 0, policy_version 105840 (0.0005) [2023-03-09 04:21:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 54190080. Throughput: 0: 10307.3. Samples: 54176900. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:21:15,829][613581] Avg episode reward: [(0, '4518.724')] [2023-03-09 04:21:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000105840_54190080.pth... [2023-03-09 04:21:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000105240_53882880.pth [2023-03-09 04:21:19,886][613885] Updated weights for policy 0, policy_version 105920 (0.0004) [2023-03-09 04:21:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10344.1). Total num frames: 54239232. Throughput: 0: 10198.8. Samples: 54235224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:21:20,829][613581] Avg episode reward: [(0, '4105.797')] [2023-03-09 04:21:23,934][613885] Updated weights for policy 0, policy_version 106000 (0.0005) [2023-03-09 04:21:25,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10240.0, 300 sec: 10344.1). Total num frames: 54288384. Throughput: 0: 10196.6. Samples: 54266368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:21:25,829][613581] Avg episode reward: [(0, '4335.640')] [2023-03-09 04:21:27,656][613885] Updated weights for policy 0, policy_version 106080 (0.0004) [2023-03-09 04:21:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 54345728. Throughput: 0: 10181.9. Samples: 54329352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:21:30,829][613581] Avg episode reward: [(0, '4476.844')] [2023-03-09 04:21:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000106144_54345728.pth... [2023-03-09 04:21:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000105544_54038528.pth [2023-03-09 04:21:31,632][613885] Updated weights for policy 0, policy_version 106160 (0.0005) [2023-03-09 04:21:35,516][613885] Updated weights for policy 0, policy_version 106240 (0.0004) [2023-03-09 04:21:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 54394880. Throughput: 0: 10276.0. Samples: 54393876. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:21:35,829][613581] Avg episode reward: [(0, '4297.153')] [2023-03-09 04:21:39,654][613885] Updated weights for policy 0, policy_version 106320 (0.0005) [2023-03-09 04:21:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10344.1). Total num frames: 54444032. Throughput: 0: 10269.1. Samples: 54423528. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:21:40,829][613581] Avg episode reward: [(0, '4518.626')] [2023-03-09 04:21:43,841][613885] Updated weights for policy 0, policy_version 106400 (0.0004) [2023-03-09 04:21:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10344.1). Total num frames: 54497280. Throughput: 0: 10176.5. Samples: 54483000. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:21:45,829][613581] Avg episode reward: [(0, '4583.732')] [2023-03-09 04:21:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000106440_54497280.pth... [2023-03-09 04:21:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000105840_54190080.pth [2023-03-09 04:21:47,569][613885] Updated weights for policy 0, policy_version 106480 (0.0004) [2023-03-09 04:21:50,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.2, 300 sec: 10344.1). Total num frames: 54550528. Throughput: 0: 10231.4. Samples: 54546688. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:21:50,829][613581] Avg episode reward: [(0, '4571.174')] [2023-03-09 04:21:51,539][613885] Updated weights for policy 0, policy_version 106560 (0.0005) [2023-03-09 04:21:55,268][613885] Updated weights for policy 0, policy_version 106640 (0.0004) [2023-03-09 04:21:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.2, 300 sec: 10344.1). Total num frames: 54603776. Throughput: 0: 10300.6. Samples: 54579272. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:21:55,829][613581] Avg episode reward: [(0, '4581.851')] [2023-03-09 04:21:59,138][613885] Updated weights for policy 0, policy_version 106720 (0.0004) [2023-03-09 04:22:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10358.0). Total num frames: 54657024. Throughput: 0: 10371.9. Samples: 54643636. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:22:00,829][613581] Avg episode reward: [(0, '4535.553')] [2023-03-09 04:22:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000106752_54657024.pth... [2023-03-09 04:22:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000106144_54345728.pth [2023-03-09 04:22:02,797][613885] Updated weights for policy 0, policy_version 106800 (0.0005) [2023-03-09 04:22:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 54710272. Throughput: 0: 10481.1. Samples: 54706872. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:22:05,829][613581] Avg episode reward: [(0, '4548.439')] [2023-03-09 04:22:06,854][613885] Updated weights for policy 0, policy_version 106880 (0.0004) [2023-03-09 04:22:10,821][613885] Updated weights for policy 0, policy_version 106960 (0.0005) [2023-03-09 04:22:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10385.8). Total num frames: 54763520. Throughput: 0: 10483.1. Samples: 54738108. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:22:10,830][613581] Avg episode reward: [(0, '4279.704')] [2023-03-09 04:22:14,726][613885] Updated weights for policy 0, policy_version 107040 (0.0005) [2023-03-09 04:22:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10385.8). Total num frames: 54812672. Throughput: 0: 10467.6. Samples: 54800392. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:22:15,829][613581] Avg episode reward: [(0, '4399.545')] [2023-03-09 04:22:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000107056_54812672.pth... [2023-03-09 04:22:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000106440_54497280.pth [2023-03-09 04:22:18,781][613885] Updated weights for policy 0, policy_version 107120 (0.0004) [2023-03-09 04:22:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10385.8). Total num frames: 54865920. Throughput: 0: 10401.2. Samples: 54861928. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:22:20,829][613581] Avg episode reward: [(0, '4442.396')] [2023-03-09 04:22:22,481][613885] Updated weights for policy 0, policy_version 107200 (0.0005) [2023-03-09 04:22:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10513.1, 300 sec: 10399.7). Total num frames: 54919168. Throughput: 0: 10469.7. Samples: 54894664. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:22:25,829][613581] Avg episode reward: [(0, '4577.787')] [2023-03-09 04:22:26,519][613885] Updated weights for policy 0, policy_version 107280 (0.0005) [2023-03-09 04:22:30,742][613885] Updated weights for policy 0, policy_version 107360 (0.0005) [2023-03-09 04:22:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 54968320. Throughput: 0: 10502.0. Samples: 54955588. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:22:30,829][613581] Avg episode reward: [(0, '4483.053')] [2023-03-09 04:22:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000107360_54968320.pth... [2023-03-09 04:22:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000106752_54657024.pth [2023-03-09 04:22:34,601][613885] Updated weights for policy 0, policy_version 107440 (0.0005) [2023-03-09 04:22:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10371.9). Total num frames: 55021568. Throughput: 0: 10461.9. Samples: 55017472. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:22:35,829][613581] Avg episode reward: [(0, '4440.996')] [2023-03-09 04:22:38,501][613885] Updated weights for policy 0, policy_version 107520 (0.0005) [2023-03-09 04:22:40,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10344.1). Total num frames: 55070720. Throughput: 0: 10437.8. Samples: 55048972. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:22:40,829][613581] Avg episode reward: [(0, '4304.754')] [2023-03-09 04:22:42,379][613885] Updated weights for policy 0, policy_version 107600 (0.0005) [2023-03-09 04:22:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10358.0). Total num frames: 55123968. Throughput: 0: 10402.6. Samples: 55111752. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:22:45,829][613581] Avg episode reward: [(0, '4262.560')] [2023-03-09 04:22:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000107664_55123968.pth... [2023-03-09 04:22:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000107056_54812672.pth [2023-03-09 04:22:46,369][613885] Updated weights for policy 0, policy_version 107680 (0.0006) [2023-03-09 04:22:50,309][613885] Updated weights for policy 0, policy_version 107760 (0.0005) [2023-03-09 04:22:50,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10444.8, 300 sec: 10358.0). Total num frames: 55177216. Throughput: 0: 10366.8. Samples: 55173380. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:22:50,830][613581] Avg episode reward: [(0, '4404.722')] [2023-03-09 04:22:54,212][613885] Updated weights for policy 0, policy_version 107840 (0.0004) [2023-03-09 04:22:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 55226368. Throughput: 0: 10385.8. Samples: 55205468. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:22:55,829][613581] Avg episode reward: [(0, '4442.493')] [2023-03-09 04:22:58,374][613885] Updated weights for policy 0, policy_version 107920 (0.0004) [2023-03-09 04:23:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10344.1). Total num frames: 55279616. Throughput: 0: 10376.3. Samples: 55267324. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:23:00,829][613581] Avg episode reward: [(0, '4494.304')] [2023-03-09 04:23:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000107968_55279616.pth... [2023-03-09 04:23:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000107360_54968320.pth [2023-03-09 04:23:02,057][613885] Updated weights for policy 0, policy_version 108000 (0.0004) [2023-03-09 04:23:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10344.1). Total num frames: 55332864. Throughput: 0: 10387.1. Samples: 55329348. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:23:05,829][613581] Avg episode reward: [(0, '4522.298')] [2023-03-09 04:23:06,094][613885] Updated weights for policy 0, policy_version 108080 (0.0004) [2023-03-09 04:23:09,792][613885] Updated weights for policy 0, policy_version 108160 (0.0005) [2023-03-09 04:23:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 55386112. Throughput: 0: 10416.4. Samples: 55363404. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:23:10,829][613581] Avg episode reward: [(0, '4412.086')] [2023-03-09 04:23:13,890][613885] Updated weights for policy 0, policy_version 108240 (0.0004) [2023-03-09 04:23:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10344.1). Total num frames: 55435264. Throughput: 0: 10388.5. Samples: 55423072. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:23:15,829][613581] Avg episode reward: [(0, '4029.224')] [2023-03-09 04:23:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000108272_55435264.pth... [2023-03-09 04:23:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000107664_55123968.pth [2023-03-09 04:23:18,011][613885] Updated weights for policy 0, policy_version 108320 (0.0004) [2023-03-09 04:23:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10344.1). Total num frames: 55488512. Throughput: 0: 10378.1. Samples: 55484488. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:23:20,829][613581] Avg episode reward: [(0, '4446.256')] [2023-03-09 04:23:21,900][613885] Updated weights for policy 0, policy_version 108400 (0.0005) [2023-03-09 04:23:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10344.1). Total num frames: 55537664. Throughput: 0: 10402.1. Samples: 55517068. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:23:25,829][613581] Avg episode reward: [(0, '4301.170')] [2023-03-09 04:23:25,838][613885] Updated weights for policy 0, policy_version 108480 (0.0004) [2023-03-09 04:23:29,483][613885] Updated weights for policy 0, policy_version 108560 (0.0004) [2023-03-09 04:23:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10358.0). Total num frames: 55595008. Throughput: 0: 10460.0. Samples: 55582452. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:23:30,829][613581] Avg episode reward: [(0, '4353.521')] [2023-03-09 04:23:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000108584_55595008.pth... [2023-03-09 04:23:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000107968_55279616.pth [2023-03-09 04:23:33,369][613885] Updated weights for policy 0, policy_version 108640 (0.0005) [2023-03-09 04:23:35,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10344.1). Total num frames: 55644160. Throughput: 0: 10449.5. Samples: 55643608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:23:35,829][613581] Avg episode reward: [(0, '4507.717')] [2023-03-09 04:23:37,602][613885] Updated weights for policy 0, policy_version 108720 (0.0004) [2023-03-09 04:23:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 10330.2). Total num frames: 55693312. Throughput: 0: 10385.1. Samples: 55672796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:23:40,829][613581] Avg episode reward: [(0, '4512.106')] [2023-03-09 04:23:41,657][613885] Updated weights for policy 0, policy_version 108800 (0.0004) [2023-03-09 04:23:45,818][613885] Updated weights for policy 0, policy_version 108880 (0.0005) [2023-03-09 04:23:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10376.5, 300 sec: 10344.1). Total num frames: 55746560. Throughput: 0: 10333.0. Samples: 55732308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:23:45,829][613581] Avg episode reward: [(0, '4581.316')] [2023-03-09 04:23:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000108880_55746560.pth... [2023-03-09 04:23:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000108272_55435264.pth [2023-03-09 04:23:49,782][613885] Updated weights for policy 0, policy_version 108960 (0.0004) [2023-03-09 04:23:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10330.3). Total num frames: 55795712. Throughput: 0: 10317.4. Samples: 55793632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:23:50,829][613581] Avg episode reward: [(0, '4496.042')] [2023-03-09 04:23:53,665][613885] Updated weights for policy 0, policy_version 109040 (0.0005) [2023-03-09 04:23:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 55848960. Throughput: 0: 10269.3. Samples: 55825524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:23:55,829][613581] Avg episode reward: [(0, '4571.057')] [2023-03-09 04:23:57,755][613885] Updated weights for policy 0, policy_version 109120 (0.0005) [2023-03-09 04:24:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10344.1). Total num frames: 55898112. Throughput: 0: 10283.6. Samples: 55885832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:24:00,829][613581] Avg episode reward: [(0, '4584.861')] [2023-03-09 04:24:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000109176_55898112.pth... [2023-03-09 04:24:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000108584_55595008.pth [2023-03-09 04:24:01,930][613885] Updated weights for policy 0, policy_version 109200 (0.0004) [2023-03-09 04:24:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10344.1). Total num frames: 55947264. Throughput: 0: 10200.8. Samples: 55943524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:24:05,829][613581] Avg episode reward: [(0, '4587.150')] [2023-03-09 04:24:06,153][613885] Updated weights for policy 0, policy_version 109280 (0.0005) [2023-03-09 04:24:10,173][613885] Updated weights for policy 0, policy_version 109360 (0.0005) [2023-03-09 04:24:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10171.7, 300 sec: 10330.3). Total num frames: 55996416. Throughput: 0: 10162.7. Samples: 55974388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:24:10,829][613581] Avg episode reward: [(0, '4505.587')] [2023-03-09 04:24:14,233][613885] Updated weights for policy 0, policy_version 109440 (0.0005) [2023-03-09 04:24:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10330.2). Total num frames: 56049664. Throughput: 0: 10050.7. Samples: 56034732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:24:15,829][613581] Avg episode reward: [(0, '4566.905')] [2023-03-09 04:24:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000109472_56049664.pth... [2023-03-09 04:24:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000108880_55746560.pth [2023-03-09 04:24:18,335][613885] Updated weights for policy 0, policy_version 109520 (0.0004) [2023-03-09 04:24:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10302.5). Total num frames: 56094720. Throughput: 0: 10022.4. Samples: 56094616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:24:20,829][613581] Avg episode reward: [(0, '4400.035')] [2023-03-09 04:24:22,501][613885] Updated weights for policy 0, policy_version 109600 (0.0004) [2023-03-09 04:24:25,829][613581] Fps is (10 sec: 9420.9, 60 sec: 10103.5, 300 sec: 10288.6). Total num frames: 56143872. Throughput: 0: 10023.8. Samples: 56123868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:24:25,829][613581] Avg episode reward: [(0, '4125.829')] [2023-03-09 04:24:26,798][613885] Updated weights for policy 0, policy_version 109680 (0.0004) [2023-03-09 04:24:30,707][613885] Updated weights for policy 0, policy_version 109760 (0.0005) [2023-03-09 04:24:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10035.2, 300 sec: 10302.5). Total num frames: 56197120. Throughput: 0: 10034.0. Samples: 56183840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:24:30,829][613581] Avg episode reward: [(0, '4378.828')] [2023-03-09 04:24:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000109760_56197120.pth... [2023-03-09 04:24:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000109176_55898112.pth [2023-03-09 04:24:34,855][613885] Updated weights for policy 0, policy_version 109840 (0.0005) [2023-03-09 04:24:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 10288.6). Total num frames: 56246272. Throughput: 0: 9981.2. Samples: 56242788. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:24:35,829][613581] Avg episode reward: [(0, '4489.924')] [2023-03-09 04:24:38,873][613885] Updated weights for policy 0, policy_version 109920 (0.0004) [2023-03-09 04:24:40,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10103.5, 300 sec: 10288.6). Total num frames: 56299520. Throughput: 0: 9978.0. Samples: 56274536. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:24:40,829][613581] Avg episode reward: [(0, '4288.106')] [2023-03-09 04:24:42,633][613885] Updated weights for policy 0, policy_version 110000 (0.0004) [2023-03-09 04:24:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10103.5, 300 sec: 10274.7). Total num frames: 56352768. Throughput: 0: 10030.8. Samples: 56337216. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:24:45,829][613581] Avg episode reward: [(0, '4528.981')] [2023-03-09 04:24:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000110064_56352768.pth... [2023-03-09 04:24:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000109472_56049664.pth [2023-03-09 04:24:46,394][613885] Updated weights for policy 0, policy_version 110080 (0.0005) [2023-03-09 04:24:50,369][613885] Updated weights for policy 0, policy_version 110160 (0.0005) [2023-03-09 04:24:50,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10171.7, 300 sec: 10288.6). Total num frames: 56406016. Throughput: 0: 10186.8. Samples: 56401928. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:24:50,829][613581] Avg episode reward: [(0, '4197.671')] [2023-03-09 04:24:54,291][613885] Updated weights for policy 0, policy_version 110240 (0.0005) [2023-03-09 04:24:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 10274.7). Total num frames: 56455168. Throughput: 0: 10204.2. Samples: 56433576. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:24:55,829][613581] Avg episode reward: [(0, '4567.264')] [2023-03-09 04:24:58,370][613885] Updated weights for policy 0, policy_version 110320 (0.0005) [2023-03-09 04:25:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10274.7). Total num frames: 56504320. Throughput: 0: 10192.7. Samples: 56493404. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:25:00,829][613581] Avg episode reward: [(0, '4592.363')] [2023-03-09 04:25:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000110360_56504320.pth... [2023-03-09 04:25:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000109760_56197120.pth [2023-03-09 04:25:02,659][613885] Updated weights for policy 0, policy_version 110400 (0.0004) [2023-03-09 04:25:05,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10302.5). Total num frames: 56557568. Throughput: 0: 10201.0. Samples: 56553660. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:25:05,829][613581] Avg episode reward: [(0, '4561.489')] [2023-03-09 04:25:06,561][613885] Updated weights for policy 0, policy_version 110480 (0.0005) [2023-03-09 04:25:10,592][613885] Updated weights for policy 0, policy_version 110560 (0.0005) [2023-03-09 04:25:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10288.6). Total num frames: 56606720. Throughput: 0: 10233.2. Samples: 56584360. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:25:10,829][613581] Avg episode reward: [(0, '4547.714')] [2023-03-09 04:25:14,350][613885] Updated weights for policy 0, policy_version 110640 (0.0005) [2023-03-09 04:25:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 10302.5). Total num frames: 56659968. Throughput: 0: 10309.0. Samples: 56647744. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:25:15,829][613581] Avg episode reward: [(0, '4563.778')] [2023-03-09 04:25:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000110664_56659968.pth... [2023-03-09 04:25:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000110064_56352768.pth [2023-03-09 04:25:18,401][613885] Updated weights for policy 0, policy_version 110720 (0.0004) [2023-03-09 04:25:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 56709120. Throughput: 0: 10354.2. Samples: 56708728. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:25:20,829][613581] Avg episode reward: [(0, '4549.235')] [2023-03-09 04:25:22,551][613885] Updated weights for policy 0, policy_version 110800 (0.0005) [2023-03-09 04:25:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 56762368. Throughput: 0: 10296.0. Samples: 56737856. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:25:25,829][613581] Avg episode reward: [(0, '4532.881')] [2023-03-09 04:25:26,619][613885] Updated weights for policy 0, policy_version 110880 (0.0005) [2023-03-09 04:25:30,394][613885] Updated weights for policy 0, policy_version 110960 (0.0005) [2023-03-09 04:25:30,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 56815616. Throughput: 0: 10265.8. Samples: 56799176. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:25:30,830][613581] Avg episode reward: [(0, '4516.221')] [2023-03-09 04:25:30,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000110968_56815616.pth... [2023-03-09 04:25:30,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000110360_56504320.pth [2023-03-09 04:25:34,494][613885] Updated weights for policy 0, policy_version 111040 (0.0005) [2023-03-09 04:25:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 56864768. Throughput: 0: 10203.8. Samples: 56861100. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:25:35,829][613581] Avg episode reward: [(0, '4445.725')] [2023-03-09 04:25:38,460][613885] Updated weights for policy 0, policy_version 111120 (0.0004) [2023-03-09 04:25:40,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 56918016. Throughput: 0: 10202.1. Samples: 56892668. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:25:40,829][613581] Avg episode reward: [(0, '4417.416')] [2023-03-09 04:25:42,246][613885] Updated weights for policy 0, policy_version 111200 (0.0004) [2023-03-09 04:25:45,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 56967168. Throughput: 0: 10273.6. Samples: 56955716. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:25:45,829][613581] Avg episode reward: [(0, '4574.085')] [2023-03-09 04:25:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000111264_56967168.pth... [2023-03-09 04:25:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000110664_56659968.pth [2023-03-09 04:25:46,295][613885] Updated weights for policy 0, policy_version 111280 (0.0004) [2023-03-09 04:25:50,388][613885] Updated weights for policy 0, policy_version 111360 (0.0004) [2023-03-09 04:25:50,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 57020416. Throughput: 0: 10281.5. Samples: 57016328. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:25:50,830][613581] Avg episode reward: [(0, '4500.617')] [2023-03-09 04:25:54,352][613885] Updated weights for policy 0, policy_version 111440 (0.0005) [2023-03-09 04:25:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10274.7). Total num frames: 57069568. Throughput: 0: 10309.9. Samples: 57048304. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:25:55,829][613581] Avg episode reward: [(0, '4531.426')] [2023-03-09 04:25:58,352][613885] Updated weights for policy 0, policy_version 111520 (0.0004) [2023-03-09 04:26:00,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 57122816. Throughput: 0: 10284.0. Samples: 57110524. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:26:00,840][613581] Avg episode reward: [(0, '4574.399')] [2023-03-09 04:26:00,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000111568_57122816.pth... [2023-03-09 04:26:00,844][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000110968_56815616.pth [2023-03-09 04:26:02,294][613885] Updated weights for policy 0, policy_version 111600 (0.0005) [2023-03-09 04:26:05,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 57171968. Throughput: 0: 10213.9. Samples: 57168356. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:26:05,840][613581] Avg episode reward: [(0, '4408.412')] [2023-03-09 04:26:06,533][613885] Updated weights for policy 0, policy_version 111680 (0.0005) [2023-03-09 04:26:10,732][613885] Updated weights for policy 0, policy_version 111760 (0.0005) [2023-03-09 04:26:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10274.7). Total num frames: 57221120. Throughput: 0: 10267.4. Samples: 57199888. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:26:10,829][613581] Avg episode reward: [(0, '4527.318')] [2023-03-09 04:26:14,595][613885] Updated weights for policy 0, policy_version 111840 (0.0005) [2023-03-09 04:26:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 57274368. Throughput: 0: 10247.6. Samples: 57260316. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:26:15,829][613581] Avg episode reward: [(0, '4587.039')] [2023-03-09 04:26:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000111864_57274368.pth... [2023-03-09 04:26:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000111264_56967168.pth [2023-03-09 04:26:18,556][613885] Updated weights for policy 0, policy_version 111920 (0.0005) [2023-03-09 04:26:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 57323520. Throughput: 0: 10249.5. Samples: 57322324. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:26:20,829][613581] Avg episode reward: [(0, '4535.052')] [2023-03-09 04:26:22,553][613885] Updated weights for policy 0, policy_version 112000 (0.0005) [2023-03-09 04:26:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10274.7). Total num frames: 57376768. Throughput: 0: 10238.4. Samples: 57353396. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:26:25,829][613581] Avg episode reward: [(0, '4567.820')] [2023-03-09 04:26:26,355][613885] Updated weights for policy 0, policy_version 112080 (0.0005) [2023-03-09 04:26:30,251][613885] Updated weights for policy 0, policy_version 112160 (0.0005) [2023-03-09 04:26:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 10288.6). Total num frames: 57430016. Throughput: 0: 10266.9. Samples: 57417728. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:26:30,829][613581] Avg episode reward: [(0, '4318.342')] [2023-03-09 04:26:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000112168_57430016.pth... [2023-03-09 04:26:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000111568_57122816.pth [2023-03-09 04:26:33,936][613885] Updated weights for policy 0, policy_version 112240 (0.0004) [2023-03-09 04:26:35,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 57483264. Throughput: 0: 10350.5. Samples: 57482100. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:26:35,829][613581] Avg episode reward: [(0, '4547.687')] [2023-03-09 04:26:37,851][613885] Updated weights for policy 0, policy_version 112320 (0.0006) [2023-03-09 04:26:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10302.5). Total num frames: 57536512. Throughput: 0: 10341.7. Samples: 57513680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:26:40,829][613581] Avg episode reward: [(0, '4568.213')] [2023-03-09 04:26:41,707][613885] Updated weights for policy 0, policy_version 112400 (0.0005) [2023-03-09 04:26:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 57585664. Throughput: 0: 10294.8. Samples: 57573788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:26:45,829][613581] Avg episode reward: [(0, '4234.676')] [2023-03-09 04:26:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000112472_57585664.pth... [2023-03-09 04:26:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000111864_57274368.pth [2023-03-09 04:26:46,028][613885] Updated weights for policy 0, policy_version 112480 (0.0005) [2023-03-09 04:26:49,814][613885] Updated weights for policy 0, policy_version 112560 (0.0004) [2023-03-09 04:26:50,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10288.6). Total num frames: 57638912. Throughput: 0: 10405.3. Samples: 57636592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:26:50,829][613581] Avg episode reward: [(0, '3975.415')] [2023-03-09 04:26:53,767][613885] Updated weights for policy 0, policy_version 112640 (0.0004) [2023-03-09 04:26:55,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 10288.6). Total num frames: 57692160. Throughput: 0: 10394.6. Samples: 57667648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:26:55,829][613581] Avg episode reward: [(0, '4482.510')] [2023-03-09 04:26:57,807][613885] Updated weights for policy 0, policy_version 112720 (0.0004) [2023-03-09 04:27:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10274.7). Total num frames: 57741312. Throughput: 0: 10417.2. Samples: 57729088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:27:00,829][613581] Avg episode reward: [(0, '4226.615')] [2023-03-09 04:27:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000112776_57741312.pth... [2023-03-09 04:27:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000112168_57430016.pth [2023-03-09 04:27:01,788][613885] Updated weights for policy 0, policy_version 112800 (0.0005) [2023-03-09 04:27:05,826][613885] Updated weights for policy 0, policy_version 112880 (0.0004) [2023-03-09 04:27:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10274.7). Total num frames: 57794560. Throughput: 0: 10402.9. Samples: 57790456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:27:05,829][613581] Avg episode reward: [(0, '4248.465')] [2023-03-09 04:27:10,116][613885] Updated weights for policy 0, policy_version 112960 (0.0004) [2023-03-09 04:27:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10308.3, 300 sec: 10260.8). Total num frames: 57839616. Throughput: 0: 10345.6. Samples: 57818948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:27:10,829][613581] Avg episode reward: [(0, '4377.571')] [2023-03-09 04:27:14,517][613885] Updated weights for policy 0, policy_version 113040 (0.0004) [2023-03-09 04:27:15,829][613581] Fps is (10 sec: 9011.3, 60 sec: 10171.8, 300 sec: 10233.1). Total num frames: 57884672. Throughput: 0: 10184.6. Samples: 57876036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:27:15,829][613581] Avg episode reward: [(0, '4490.326')] [2023-03-09 04:27:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000113056_57884672.pth... [2023-03-09 04:27:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000112472_57585664.pth [2023-03-09 04:27:18,933][613885] Updated weights for policy 0, policy_version 113120 (0.0005) [2023-03-09 04:27:20,829][613581] Fps is (10 sec: 9420.6, 60 sec: 10171.7, 300 sec: 10219.2). Total num frames: 57933824. Throughput: 0: 10038.2. Samples: 57933820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:27:20,830][613581] Avg episode reward: [(0, '4454.161')] [2023-03-09 04:27:23,001][613885] Updated weights for policy 0, policy_version 113200 (0.0005) [2023-03-09 04:27:25,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10103.5, 300 sec: 10219.2). Total num frames: 57982976. Throughput: 0: 9972.2. Samples: 57962428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:27:25,829][613581] Avg episode reward: [(0, '4273.905')] [2023-03-09 04:27:27,205][613885] Updated weights for policy 0, policy_version 113280 (0.0005) [2023-03-09 04:27:30,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10205.3). Total num frames: 58032128. Throughput: 0: 9913.9. Samples: 58019912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:27:30,829][613581] Avg episode reward: [(0, '4405.818')] [2023-03-09 04:27:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000113344_58032128.pth... [2023-03-09 04:27:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000112776_57741312.pth [2023-03-09 04:27:31,442][613885] Updated weights for policy 0, policy_version 113360 (0.0005) [2023-03-09 04:27:35,465][613885] Updated weights for policy 0, policy_version 113440 (0.0004) [2023-03-09 04:27:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10205.3). Total num frames: 58081280. Throughput: 0: 9878.8. Samples: 58081140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:27:35,829][613581] Avg episode reward: [(0, '4436.612')] [2023-03-09 04:27:39,589][613885] Updated weights for policy 0, policy_version 113520 (0.0005) [2023-03-09 04:27:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9898.7, 300 sec: 10191.4). Total num frames: 58130432. Throughput: 0: 9829.2. Samples: 58109960. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:27:40,829][613581] Avg episode reward: [(0, '4432.663')] [2023-03-09 04:27:43,927][613885] Updated weights for policy 0, policy_version 113600 (0.0005) [2023-03-09 04:27:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 10177.5). Total num frames: 58179584. Throughput: 0: 9739.4. Samples: 58167360. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:27:45,829][613581] Avg episode reward: [(0, '4541.797')] [2023-03-09 04:27:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000113632_58179584.pth... [2023-03-09 04:27:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000113056_57884672.pth [2023-03-09 04:27:48,140][613885] Updated weights for policy 0, policy_version 113680 (0.0005) [2023-03-09 04:27:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 10177.5). Total num frames: 58228736. Throughput: 0: 9664.1. Samples: 58225340. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:27:50,829][613581] Avg episode reward: [(0, '4587.629')] [2023-03-09 04:27:52,408][613885] Updated weights for policy 0, policy_version 113760 (0.0005) [2023-03-09 04:27:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 10163.6). Total num frames: 58277888. Throughput: 0: 9695.7. Samples: 58255256. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:27:55,829][613581] Avg episode reward: [(0, '4589.974')] [2023-03-09 04:27:56,549][613885] Updated weights for policy 0, policy_version 113840 (0.0005) [2023-03-09 04:28:00,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 10135.9). Total num frames: 58322944. Throughput: 0: 9728.5. Samples: 58313820. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:28:00,829][613581] Avg episode reward: [(0, '4529.528')] [2023-03-09 04:28:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000113912_58322944.pth... [2023-03-09 04:28:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000113344_58032128.pth [2023-03-09 04:28:00,896][613885] Updated weights for policy 0, policy_version 113920 (0.0005) [2023-03-09 04:28:05,219][613885] Updated weights for policy 0, policy_version 114000 (0.0005) [2023-03-09 04:28:05,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9625.6, 300 sec: 10122.0). Total num frames: 58372096. Throughput: 0: 9686.4. Samples: 58369704. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:28:05,829][613581] Avg episode reward: [(0, '4548.597')] [2023-03-09 04:28:09,105][613885] Updated weights for policy 0, policy_version 114080 (0.0004) [2023-03-09 04:28:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 10122.0). Total num frames: 58421248. Throughput: 0: 9756.2. Samples: 58401456. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:28:10,829][613581] Avg episode reward: [(0, '4583.732')] [2023-03-09 04:28:13,479][613885] Updated weights for policy 0, policy_version 114160 (0.0004) [2023-03-09 04:28:15,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9762.1, 300 sec: 10108.1). Total num frames: 58470400. Throughput: 0: 9748.3. Samples: 58458588. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:28:15,830][613581] Avg episode reward: [(0, '4576.343')] [2023-03-09 04:28:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000114200_58470400.pth... [2023-03-09 04:28:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000113632_58179584.pth [2023-03-09 04:28:17,781][613885] Updated weights for policy 0, policy_version 114240 (0.0005) [2023-03-09 04:28:20,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9693.9, 300 sec: 10094.2). Total num frames: 58515456. Throughput: 0: 9648.2. Samples: 58515308. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:28:20,829][613581] Avg episode reward: [(0, '4533.779')] [2023-03-09 04:28:22,355][613885] Updated weights for policy 0, policy_version 114320 (0.0004) [2023-03-09 04:28:25,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9693.9, 300 sec: 10066.4). Total num frames: 58564608. Throughput: 0: 9614.5. Samples: 58542612. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:28:25,829][613581] Avg episode reward: [(0, '4577.553')] [2023-03-09 04:28:26,555][613885] Updated weights for policy 0, policy_version 114400 (0.0005) [2023-03-09 04:28:30,704][613885] Updated weights for policy 0, policy_version 114480 (0.0004) [2023-03-09 04:28:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 10066.4). Total num frames: 58613760. Throughput: 0: 9646.7. Samples: 58601464. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:28:30,829][613581] Avg episode reward: [(0, '4503.100')] [2023-03-09 04:28:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000114480_58613760.pth... [2023-03-09 04:28:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000113912_58322944.pth [2023-03-09 04:28:35,004][613885] Updated weights for policy 0, policy_version 114560 (0.0005) [2023-03-09 04:28:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 10052.6). Total num frames: 58658816. Throughput: 0: 9631.0. Samples: 58658736. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:28:35,829][613581] Avg episode reward: [(0, '4236.198')] [2023-03-09 04:28:39,345][613885] Updated weights for policy 0, policy_version 114640 (0.0004) [2023-03-09 04:28:40,829][613581] Fps is (10 sec: 9421.0, 60 sec: 9625.6, 300 sec: 10038.7). Total num frames: 58707968. Throughput: 0: 9574.8. Samples: 58686120. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:28:40,829][613581] Avg episode reward: [(0, '4253.264')] [2023-03-09 04:28:43,498][613885] Updated weights for policy 0, policy_version 114720 (0.0005) [2023-03-09 04:28:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 10038.7). Total num frames: 58757120. Throughput: 0: 9578.3. Samples: 58744844. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:28:45,829][613581] Avg episode reward: [(0, '4378.926')] [2023-03-09 04:28:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000114760_58757120.pth... [2023-03-09 04:28:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000114200_58470400.pth [2023-03-09 04:28:47,732][613885] Updated weights for policy 0, policy_version 114800 (0.0005) [2023-03-09 04:28:50,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 10024.8). Total num frames: 58806272. Throughput: 0: 9624.5. Samples: 58802808. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:28:50,829][613581] Avg episode reward: [(0, '4476.207')] [2023-03-09 04:28:51,865][613885] Updated weights for policy 0, policy_version 114880 (0.0004) [2023-03-09 04:28:55,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9557.3, 300 sec: 10010.9). Total num frames: 58851328. Throughput: 0: 9565.4. Samples: 58831900. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:28:55,829][613581] Avg episode reward: [(0, '4340.331')] [2023-03-09 04:28:56,348][613885] Updated weights for policy 0, policy_version 114960 (0.0004) [2023-03-09 04:29:00,361][613885] Updated weights for policy 0, policy_version 115040 (0.0005) [2023-03-09 04:29:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 10024.8). Total num frames: 58904576. Throughput: 0: 9625.1. Samples: 58891716. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:29:00,829][613581] Avg episode reward: [(0, '4308.655')] [2023-03-09 04:29:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000115048_58904576.pth... [2023-03-09 04:29:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000114480_58613760.pth [2023-03-09 04:29:04,601][613885] Updated weights for policy 0, policy_version 115120 (0.0004) [2023-03-09 04:29:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9693.9, 300 sec: 10024.8). Total num frames: 58953728. Throughput: 0: 9646.3. Samples: 58949392. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:29:05,829][613581] Avg episode reward: [(0, '4203.200')] [2023-03-09 04:29:08,482][613885] Updated weights for policy 0, policy_version 115200 (0.0005) [2023-03-09 04:29:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 10010.9). Total num frames: 59002880. Throughput: 0: 9760.5. Samples: 58981836. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:29:10,829][613581] Avg episode reward: [(0, '4413.200')] [2023-03-09 04:29:12,624][613885] Updated weights for policy 0, policy_version 115280 (0.0005) [2023-03-09 04:29:15,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9693.9, 300 sec: 10024.8). Total num frames: 59052032. Throughput: 0: 9739.8. Samples: 59039756. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:29:15,829][613581] Avg episode reward: [(0, '4493.809')] [2023-03-09 04:29:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000115336_59052032.pth... [2023-03-09 04:29:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000114760_58757120.pth [2023-03-09 04:29:16,991][613885] Updated weights for policy 0, policy_version 115360 (0.0005) [2023-03-09 04:29:20,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9693.9, 300 sec: 10010.9). Total num frames: 59097088. Throughput: 0: 9740.7. Samples: 59097068. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:29:20,829][613581] Avg episode reward: [(0, '4519.066')] [2023-03-09 04:29:21,256][613885] Updated weights for policy 0, policy_version 115440 (0.0005) [2023-03-09 04:29:25,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9625.6, 300 sec: 9983.1). Total num frames: 59142144. Throughput: 0: 9769.4. Samples: 59125744. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:29:25,829][613581] Avg episode reward: [(0, '4355.315')] [2023-03-09 04:29:25,834][613885] Updated weights for policy 0, policy_version 115520 (0.0005) [2023-03-09 04:29:30,120][613885] Updated weights for policy 0, policy_version 115600 (0.0005) [2023-03-09 04:29:30,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9983.1). Total num frames: 59191296. Throughput: 0: 9655.0. Samples: 59179320. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:29:30,829][613581] Avg episode reward: [(0, '4441.799')] [2023-03-09 04:29:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000115608_59191296.pth... [2023-03-09 04:29:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000115048_58904576.pth [2023-03-09 04:29:34,243][613885] Updated weights for policy 0, policy_version 115680 (0.0004) [2023-03-09 04:29:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9969.2). Total num frames: 59240448. Throughput: 0: 9705.9. Samples: 59239572. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:29:35,829][613581] Avg episode reward: [(0, '4508.670')] [2023-03-09 04:29:38,378][613885] Updated weights for policy 0, policy_version 115760 (0.0005) [2023-03-09 04:29:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9762.1, 300 sec: 9969.2). Total num frames: 59293696. Throughput: 0: 9716.2. Samples: 59269128. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:29:40,829][613581] Avg episode reward: [(0, '4572.809')] [2023-03-09 04:29:42,417][613885] Updated weights for policy 0, policy_version 115840 (0.0005) [2023-03-09 04:29:45,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9693.8, 300 sec: 9941.5). Total num frames: 59338752. Throughput: 0: 9730.1. Samples: 59329572. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:29:45,830][613581] Avg episode reward: [(0, '4354.912')] [2023-03-09 04:29:45,877][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000115904_59342848.pth... [2023-03-09 04:29:45,878][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000115336_59052032.pth [2023-03-09 04:29:46,681][613885] Updated weights for policy 0, policy_version 115920 (0.0005) [2023-03-09 04:29:50,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9693.9, 300 sec: 9941.5). Total num frames: 59387904. Throughput: 0: 9741.2. Samples: 59387744. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:29:50,829][613581] Avg episode reward: [(0, '4406.200')] [2023-03-09 04:29:50,913][613885] Updated weights for policy 0, policy_version 116000 (0.0005) [2023-03-09 04:29:55,189][613885] Updated weights for policy 0, policy_version 116080 (0.0005) [2023-03-09 04:29:55,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.1, 300 sec: 9941.5). Total num frames: 59437056. Throughput: 0: 9629.6. Samples: 59415168. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:29:55,830][613581] Avg episode reward: [(0, '4589.245')] [2023-03-09 04:29:59,198][613885] Updated weights for policy 0, policy_version 116160 (0.0005) [2023-03-09 04:30:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9927.6). Total num frames: 59486208. Throughput: 0: 9687.3. Samples: 59475684. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:30:00,829][613581] Avg episode reward: [(0, '4490.140')] [2023-03-09 04:30:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000116184_59486208.pth... [2023-03-09 04:30:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000115608_59191296.pth [2023-03-09 04:30:03,429][613885] Updated weights for policy 0, policy_version 116240 (0.0005) [2023-03-09 04:30:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.8, 300 sec: 9927.6). Total num frames: 59535360. Throughput: 0: 9704.2. Samples: 59533756. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:30:05,829][613581] Avg episode reward: [(0, '4507.536')] [2023-03-09 04:30:07,707][613885] Updated weights for policy 0, policy_version 116320 (0.0005) [2023-03-09 04:30:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9913.7). Total num frames: 59584512. Throughput: 0: 9739.7. Samples: 59564032. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:30:10,829][613581] Avg episode reward: [(0, '4582.154')] [2023-03-09 04:30:11,846][613885] Updated weights for policy 0, policy_version 116400 (0.0005) [2023-03-09 04:30:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9913.7). Total num frames: 59633664. Throughput: 0: 9823.6. Samples: 59621384. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:30:15,829][613581] Avg episode reward: [(0, '4560.569')] [2023-03-09 04:30:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000116472_59633664.pth... [2023-03-09 04:30:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000115904_59342848.pth [2023-03-09 04:30:15,984][613885] Updated weights for policy 0, policy_version 116480 (0.0004) [2023-03-09 04:30:19,846][613885] Updated weights for policy 0, policy_version 116560 (0.0004) [2023-03-09 04:30:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9830.4, 300 sec: 9913.7). Total num frames: 59686912. Throughput: 0: 9870.1. Samples: 59683728. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:30:20,829][613581] Avg episode reward: [(0, '4582.026')] [2023-03-09 04:30:23,486][613885] Updated weights for policy 0, policy_version 116640 (0.0004) [2023-03-09 04:30:25,829][613581] Fps is (10 sec: 11059.2, 60 sec: 10035.2, 300 sec: 9927.6). Total num frames: 59744256. Throughput: 0: 9997.6. Samples: 59719020. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:30:25,829][613581] Avg episode reward: [(0, '4569.097')] [2023-03-09 04:30:27,453][613885] Updated weights for policy 0, policy_version 116720 (0.0005) [2023-03-09 04:30:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10035.2, 300 sec: 9927.6). Total num frames: 59793408. Throughput: 0: 10033.3. Samples: 59781068. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:30:30,829][613581] Avg episode reward: [(0, '4468.983')] [2023-03-09 04:30:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000116784_59793408.pth... [2023-03-09 04:30:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000116184_59486208.pth [2023-03-09 04:30:31,472][613885] Updated weights for policy 0, policy_version 116800 (0.0005) [2023-03-09 04:30:35,709][613885] Updated weights for policy 0, policy_version 116880 (0.0004) [2023-03-09 04:30:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 9913.7). Total num frames: 59842560. Throughput: 0: 10031.3. Samples: 59839152. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:30:35,829][613581] Avg episode reward: [(0, '4514.274')] [2023-03-09 04:30:39,624][613885] Updated weights for policy 0, policy_version 116960 (0.0005) [2023-03-09 04:30:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 9927.6). Total num frames: 59895808. Throughput: 0: 10138.7. Samples: 59871408. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:30:40,829][613581] Avg episode reward: [(0, '4583.074')] [2023-03-09 04:30:43,555][613885] Updated weights for policy 0, policy_version 117040 (0.0005) [2023-03-09 04:30:45,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10103.5, 300 sec: 9913.7). Total num frames: 59944960. Throughput: 0: 10172.3. Samples: 59933436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:30:45,829][613581] Avg episode reward: [(0, '4555.712')] [2023-03-09 04:30:45,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000117088_59949056.pth... [2023-03-09 04:30:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000116472_59633664.pth [2023-03-09 04:30:47,372][613885] Updated weights for policy 0, policy_version 117120 (0.0005) [2023-03-09 04:30:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 9927.6). Total num frames: 59998208. Throughput: 0: 10273.6. Samples: 59996068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:30:50,829][613581] Avg episode reward: [(0, '4598.811')] [2023-03-09 04:30:51,467][613885] Updated weights for policy 0, policy_version 117200 (0.0006) [2023-03-09 04:30:55,477][613885] Updated weights for policy 0, policy_version 117280 (0.0005) [2023-03-09 04:30:55,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 9913.7). Total num frames: 60047360. Throughput: 0: 10277.2. Samples: 60026504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:30:55,829][613581] Avg episode reward: [(0, '4514.684')] [2023-03-09 04:30:59,524][613885] Updated weights for policy 0, policy_version 117360 (0.0005) [2023-03-09 04:31:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 9927.6). Total num frames: 60100608. Throughput: 0: 10347.7. Samples: 60087032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:31:00,829][613581] Avg episode reward: [(0, '4574.733')] [2023-03-09 04:31:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000117384_60100608.pth... [2023-03-09 04:31:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000116784_59793408.pth [2023-03-09 04:31:03,369][613885] Updated weights for policy 0, policy_version 117440 (0.0005) [2023-03-09 04:31:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 9941.5). Total num frames: 60153856. Throughput: 0: 10357.7. Samples: 60149824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:31:05,829][613581] Avg episode reward: [(0, '4577.010')] [2023-03-09 04:31:07,414][613885] Updated weights for policy 0, policy_version 117520 (0.0004) [2023-03-09 04:31:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10240.0, 300 sec: 9913.7). Total num frames: 60198912. Throughput: 0: 10210.6. Samples: 60178496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:31:10,829][613581] Avg episode reward: [(0, '4588.195')] [2023-03-09 04:31:11,796][613885] Updated weights for policy 0, policy_version 117600 (0.0004) [2023-03-09 04:31:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 10240.0, 300 sec: 9913.7). Total num frames: 60248064. Throughput: 0: 10121.6. Samples: 60236540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:31:15,829][613581] Avg episode reward: [(0, '4609.656')] [2023-03-09 04:31:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000117672_60248064.pth... [2023-03-09 04:31:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000117088_59949056.pth [2023-03-09 04:31:15,900][613885] Updated weights for policy 0, policy_version 117680 (0.0005) [2023-03-09 04:31:19,670][613885] Updated weights for policy 0, policy_version 117760 (0.0005) [2023-03-09 04:31:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 9913.7). Total num frames: 60301312. Throughput: 0: 10262.2. Samples: 60300952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:31:20,829][613581] Avg episode reward: [(0, '4601.024')] [2023-03-09 04:31:23,550][613885] Updated weights for policy 0, policy_version 117840 (0.0005) [2023-03-09 04:31:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10171.7, 300 sec: 9913.7). Total num frames: 60354560. Throughput: 0: 10237.3. Samples: 60332088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:31:25,829][613581] Avg episode reward: [(0, '4592.825')] [2023-03-09 04:31:27,438][613885] Updated weights for policy 0, policy_version 117920 (0.0005) [2023-03-09 04:31:30,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 9913.7). Total num frames: 60407808. Throughput: 0: 10265.7. Samples: 60395392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:31:30,829][613581] Avg episode reward: [(0, '4493.574')] [2023-03-09 04:31:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000117984_60407808.pth... [2023-03-09 04:31:30,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000117384_60100608.pth [2023-03-09 04:31:31,431][613885] Updated weights for policy 0, policy_version 118000 (0.0005) [2023-03-09 04:31:35,467][613885] Updated weights for policy 0, policy_version 118080 (0.0005) [2023-03-09 04:31:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 9899.8). Total num frames: 60456960. Throughput: 0: 10238.8. Samples: 60456816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:31:35,829][613581] Avg episode reward: [(0, '4421.847')] [2023-03-09 04:31:39,306][613885] Updated weights for policy 0, policy_version 118160 (0.0005) [2023-03-09 04:31:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 9913.7). Total num frames: 60510208. Throughput: 0: 10287.3. Samples: 60489432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:31:40,829][613581] Avg episode reward: [(0, '4549.816')] [2023-03-09 04:31:43,329][613885] Updated weights for policy 0, policy_version 118240 (0.0005) [2023-03-09 04:31:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 9899.8). Total num frames: 60559360. Throughput: 0: 10261.4. Samples: 60548796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:31:45,829][613581] Avg episode reward: [(0, '4597.395')] [2023-03-09 04:31:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000118280_60559360.pth... [2023-03-09 04:31:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000117672_60248064.pth [2023-03-09 04:31:47,305][613885] Updated weights for policy 0, policy_version 118320 (0.0005) [2023-03-09 04:31:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 9899.8). Total num frames: 60612608. Throughput: 0: 10193.3. Samples: 60608524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:31:50,829][613581] Avg episode reward: [(0, '4516.518')] [2023-03-09 04:31:51,484][613885] Updated weights for policy 0, policy_version 118400 (0.0005) [2023-03-09 04:31:55,340][613885] Updated weights for policy 0, policy_version 118480 (0.0005) [2023-03-09 04:31:55,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10308.3, 300 sec: 9913.7). Total num frames: 60665856. Throughput: 0: 10284.3. Samples: 60641288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:31:55,829][613581] Avg episode reward: [(0, '4525.025')] [2023-03-09 04:31:59,130][613885] Updated weights for policy 0, policy_version 118560 (0.0005) [2023-03-09 04:32:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 9913.7). Total num frames: 60719104. Throughput: 0: 10425.9. Samples: 60705708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:32:00,829][613581] Avg episode reward: [(0, '4559.262')] [2023-03-09 04:32:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000118592_60719104.pth... [2023-03-09 04:32:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000117984_60407808.pth [2023-03-09 04:32:03,034][613885] Updated weights for policy 0, policy_version 118640 (0.0005) [2023-03-09 04:32:05,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 9941.5). Total num frames: 60772352. Throughput: 0: 10383.6. Samples: 60768216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:32:05,829][613581] Avg episode reward: [(0, '4344.823')] [2023-03-09 04:32:07,121][613885] Updated weights for policy 0, policy_version 118720 (0.0004) [2023-03-09 04:32:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 9955.4). Total num frames: 60821504. Throughput: 0: 10338.7. Samples: 60797332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:32:10,829][613581] Avg episode reward: [(0, '4469.284')] [2023-03-09 04:32:11,173][613885] Updated weights for policy 0, policy_version 118800 (0.0005) [2023-03-09 04:32:15,221][613885] Updated weights for policy 0, policy_version 118880 (0.0004) [2023-03-09 04:32:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10376.5, 300 sec: 9955.4). Total num frames: 60870656. Throughput: 0: 10291.0. Samples: 60858488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:32:15,829][613581] Avg episode reward: [(0, '4442.613')] [2023-03-09 04:32:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000118888_60870656.pth... [2023-03-09 04:32:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000118280_60559360.pth [2023-03-09 04:32:19,207][613885] Updated weights for policy 0, policy_version 118960 (0.0005) [2023-03-09 04:32:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 9969.2). Total num frames: 60923904. Throughput: 0: 10288.7. Samples: 60919808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:32:20,830][613581] Avg episode reward: [(0, '4574.354')] [2023-03-09 04:32:23,324][613885] Updated weights for policy 0, policy_version 119040 (0.0005) [2023-03-09 04:32:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10240.0, 300 sec: 9955.4). Total num frames: 60968960. Throughput: 0: 10203.4. Samples: 60948584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:32:25,829][613581] Avg episode reward: [(0, '4049.032')] [2023-03-09 04:32:27,519][613885] Updated weights for policy 0, policy_version 119120 (0.0005) [2023-03-09 04:32:30,829][613581] Fps is (10 sec: 9420.8, 60 sec: 10171.7, 300 sec: 9955.4). Total num frames: 61018112. Throughput: 0: 10238.1. Samples: 61009512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:32:30,829][613581] Avg episode reward: [(0, '4164.466')] [2023-03-09 04:32:30,888][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000119184_61022208.pth... [2023-03-09 04:32:30,890][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000118592_60719104.pth [2023-03-09 04:32:31,767][613885] Updated weights for policy 0, policy_version 119200 (0.0005) [2023-03-09 04:32:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10171.7, 300 sec: 9955.4). Total num frames: 61067264. Throughput: 0: 10156.5. Samples: 61065568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:32:35,830][613581] Avg episode reward: [(0, '4159.252')] [2023-03-09 04:32:35,945][613885] Updated weights for policy 0, policy_version 119280 (0.0004) [2023-03-09 04:32:40,242][613885] Updated weights for policy 0, policy_version 119360 (0.0005) [2023-03-09 04:32:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 9955.4). Total num frames: 61116416. Throughput: 0: 10086.8. Samples: 61095196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:32:40,829][613581] Avg episode reward: [(0, '4455.049')] [2023-03-09 04:32:44,271][613885] Updated weights for policy 0, policy_version 119440 (0.0004) [2023-03-09 04:32:45,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10103.5, 300 sec: 9955.4). Total num frames: 61165568. Throughput: 0: 9963.4. Samples: 61154060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:32:45,829][613581] Avg episode reward: [(0, '4541.209')] [2023-03-09 04:32:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000119464_61165568.pth... [2023-03-09 04:32:45,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000118888_60870656.pth [2023-03-09 04:32:48,499][613885] Updated weights for policy 0, policy_version 119520 (0.0005) [2023-03-09 04:32:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 9955.4). Total num frames: 61214720. Throughput: 0: 9874.1. Samples: 61212548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:32:50,829][613581] Avg episode reward: [(0, '4532.182')] [2023-03-09 04:32:52,878][613885] Updated weights for policy 0, policy_version 119600 (0.0005) [2023-03-09 04:32:55,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9898.7, 300 sec: 9955.4). Total num frames: 61259776. Throughput: 0: 9822.9. Samples: 61239360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:32:55,829][613581] Avg episode reward: [(0, '4553.675')] [2023-03-09 04:32:57,204][613885] Updated weights for policy 0, policy_version 119680 (0.0005) [2023-03-09 04:33:00,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9830.4, 300 sec: 9955.4). Total num frames: 61308928. Throughput: 0: 9756.1. Samples: 61297512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:33:00,829][613581] Avg episode reward: [(0, '4400.143')] [2023-03-09 04:33:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000119744_61308928.pth... [2023-03-09 04:33:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000119184_61022208.pth [2023-03-09 04:33:01,319][613885] Updated weights for policy 0, policy_version 119760 (0.0005) [2023-03-09 04:33:05,291][613885] Updated weights for policy 0, policy_version 119840 (0.0005) [2023-03-09 04:33:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9830.4, 300 sec: 9969.2). Total num frames: 61362176. Throughput: 0: 9750.9. Samples: 61358596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:33:05,829][613581] Avg episode reward: [(0, '4123.609')] [2023-03-09 04:33:09,181][613885] Updated weights for policy 0, policy_version 119920 (0.0004) [2023-03-09 04:33:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 9898.7, 300 sec: 9983.1). Total num frames: 61415424. Throughput: 0: 9821.9. Samples: 61390568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:33:10,829][613581] Avg episode reward: [(0, '4301.095')] [2023-03-09 04:33:13,186][613885] Updated weights for policy 0, policy_version 120000 (0.0005) [2023-03-09 04:33:15,829][613581] Fps is (10 sec: 10240.1, 60 sec: 9898.7, 300 sec: 9997.0). Total num frames: 61464576. Throughput: 0: 9840.9. Samples: 61452352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:33:15,829][613581] Avg episode reward: [(0, '4603.426')] [2023-03-09 04:33:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000120048_61464576.pth... [2023-03-09 04:33:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000119464_61165568.pth [2023-03-09 04:33:17,377][613885] Updated weights for policy 0, policy_version 120080 (0.0005) [2023-03-09 04:33:20,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9997.0). Total num frames: 61513728. Throughput: 0: 9947.7. Samples: 61513212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:33:20,829][613581] Avg episode reward: [(0, '4579.764')] [2023-03-09 04:33:21,324][613885] Updated weights for policy 0, policy_version 120160 (0.0004) [2023-03-09 04:33:25,307][613885] Updated weights for policy 0, policy_version 120240 (0.0005) [2023-03-09 04:33:25,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9966.9, 300 sec: 10010.9). Total num frames: 61566976. Throughput: 0: 9973.4. Samples: 61544000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:33:25,829][613581] Avg episode reward: [(0, '4595.813')] [2023-03-09 04:33:29,464][613885] Updated weights for policy 0, policy_version 120320 (0.0005) [2023-03-09 04:33:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9966.9, 300 sec: 10024.8). Total num frames: 61616128. Throughput: 0: 9993.2. Samples: 61603756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:33:30,829][613581] Avg episode reward: [(0, '4588.820')] [2023-03-09 04:33:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000120344_61616128.pth... [2023-03-09 04:33:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000119744_61308928.pth [2023-03-09 04:33:33,437][613885] Updated weights for policy 0, policy_version 120400 (0.0005) [2023-03-09 04:33:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10024.8). Total num frames: 61665280. Throughput: 0: 10025.0. Samples: 61663672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:33:35,829][613581] Avg episode reward: [(0, '4503.313')] [2023-03-09 04:33:37,682][613885] Updated weights for policy 0, policy_version 120480 (0.0005) [2023-03-09 04:33:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9966.9, 300 sec: 10024.8). Total num frames: 61714432. Throughput: 0: 10071.5. Samples: 61692576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:33:40,829][613581] Avg episode reward: [(0, '4484.999')] [2023-03-09 04:33:41,720][613885] Updated weights for policy 0, policy_version 120560 (0.0004) [2023-03-09 04:33:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10024.8). Total num frames: 61763584. Throughput: 0: 10097.6. Samples: 61751904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:33:45,829][613581] Avg episode reward: [(0, '4299.589')] [2023-03-09 04:33:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000120632_61763584.pth... [2023-03-09 04:33:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000120048_61464576.pth [2023-03-09 04:33:45,899][613885] Updated weights for policy 0, policy_version 120640 (0.0005) [2023-03-09 04:33:49,974][613885] Updated weights for policy 0, policy_version 120720 (0.0005) [2023-03-09 04:33:50,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10035.2, 300 sec: 10052.6). Total num frames: 61816832. Throughput: 0: 10091.8. Samples: 61812728. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:33:50,829][613581] Avg episode reward: [(0, '4415.091')] [2023-03-09 04:33:53,921][613885] Updated weights for policy 0, policy_version 120800 (0.0005) [2023-03-09 04:33:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 10038.7). Total num frames: 61865984. Throughput: 0: 10107.1. Samples: 61845388. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:33:55,829][613581] Avg episode reward: [(0, '4344.948')] [2023-03-09 04:33:57,950][613885] Updated weights for policy 0, policy_version 120880 (0.0004) [2023-03-09 04:34:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10038.7). Total num frames: 61915136. Throughput: 0: 10059.1. Samples: 61905012. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:34:00,829][613581] Avg episode reward: [(0, '4363.672')] [2023-03-09 04:34:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000120928_61915136.pth... [2023-03-09 04:34:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000120344_61616128.pth [2023-03-09 04:34:02,247][613885] Updated weights for policy 0, policy_version 120960 (0.0004) [2023-03-09 04:34:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 10038.7). Total num frames: 61964288. Throughput: 0: 9937.2. Samples: 61960388. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:34:05,829][613581] Avg episode reward: [(0, '4490.425')] [2023-03-09 04:34:06,622][613885] Updated weights for policy 0, policy_version 121040 (0.0004) [2023-03-09 04:34:10,713][613885] Updated weights for policy 0, policy_version 121120 (0.0005) [2023-03-09 04:34:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10038.7). Total num frames: 62013440. Throughput: 0: 9925.7. Samples: 61990656. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:34:10,829][613581] Avg episode reward: [(0, '4311.902')] [2023-03-09 04:34:14,721][613885] Updated weights for policy 0, policy_version 121200 (0.0005) [2023-03-09 04:34:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10052.6). Total num frames: 62062592. Throughput: 0: 9924.9. Samples: 62050376. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:34:15,829][613581] Avg episode reward: [(0, '4057.181')] [2023-03-09 04:34:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000121216_62062592.pth... [2023-03-09 04:34:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000120632_61763584.pth [2023-03-09 04:34:18,896][613885] Updated weights for policy 0, policy_version 121280 (0.0005) [2023-03-09 04:34:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10066.4). Total num frames: 62111744. Throughput: 0: 9956.9. Samples: 62111732. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:34:20,829][613581] Avg episode reward: [(0, '3819.567')] [2023-03-09 04:34:23,056][613885] Updated weights for policy 0, policy_version 121360 (0.0005) [2023-03-09 04:34:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 10066.4). Total num frames: 62160896. Throughput: 0: 9949.5. Samples: 62140304. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:34:25,829][613581] Avg episode reward: [(0, '3905.292')] [2023-03-09 04:34:27,159][613885] Updated weights for policy 0, policy_version 121440 (0.0005) [2023-03-09 04:34:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 10066.4). Total num frames: 62210048. Throughput: 0: 9938.6. Samples: 62199140. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:34:30,829][613581] Avg episode reward: [(0, '3521.475')] [2023-03-09 04:34:30,879][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000121512_62214144.pth... [2023-03-09 04:34:30,880][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000120928_61915136.pth [2023-03-09 04:34:31,246][613885] Updated weights for policy 0, policy_version 121520 (0.0005) [2023-03-09 04:34:35,063][613885] Updated weights for policy 0, policy_version 121600 (0.0005) [2023-03-09 04:34:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 10066.4). Total num frames: 62263296. Throughput: 0: 10010.0. Samples: 62263176. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:34:35,829][613581] Avg episode reward: [(0, '3658.378')] [2023-03-09 04:34:39,204][613885] Updated weights for policy 0, policy_version 121680 (0.0004) [2023-03-09 04:34:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10035.2, 300 sec: 10094.2). Total num frames: 62316544. Throughput: 0: 9928.7. Samples: 62292180. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:34:40,829][613581] Avg episode reward: [(0, '3671.751')] [2023-03-09 04:34:43,042][613885] Updated weights for policy 0, policy_version 121760 (0.0005) [2023-03-09 04:34:45,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10103.5, 300 sec: 10108.1). Total num frames: 62369792. Throughput: 0: 10036.4. Samples: 62356652. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:34:45,829][613581] Avg episode reward: [(0, '3810.015')] [2023-03-09 04:34:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000121816_62369792.pth... [2023-03-09 04:34:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000121216_62062592.pth [2023-03-09 04:34:47,101][613885] Updated weights for policy 0, policy_version 121840 (0.0005) [2023-03-09 04:34:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 10108.1). Total num frames: 62418944. Throughput: 0: 10100.5. Samples: 62414912. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:34:50,829][613581] Avg episode reward: [(0, '3411.562')] [2023-03-09 04:34:51,139][613885] Updated weights for policy 0, policy_version 121920 (0.0005) [2023-03-09 04:34:55,103][613885] Updated weights for policy 0, policy_version 122000 (0.0005) [2023-03-09 04:34:55,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10108.1). Total num frames: 62468096. Throughput: 0: 10151.7. Samples: 62447480. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:34:55,829][613581] Avg episode reward: [(0, '4030.171')] [2023-03-09 04:34:59,410][613885] Updated weights for policy 0, policy_version 122080 (0.0004) [2023-03-09 04:35:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10035.2, 300 sec: 10108.1). Total num frames: 62517248. Throughput: 0: 10100.9. Samples: 62504916. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:35:00,829][613581] Avg episode reward: [(0, '4219.491')] [2023-03-09 04:35:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000122104_62517248.pth... [2023-03-09 04:35:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000121512_62214144.pth [2023-03-09 04:35:03,733][613885] Updated weights for policy 0, policy_version 122160 (0.0004) [2023-03-09 04:35:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9966.9, 300 sec: 10094.2). Total num frames: 62562304. Throughput: 0: 10012.3. Samples: 62562284. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:35:05,829][613581] Avg episode reward: [(0, '3878.253')] [2023-03-09 04:35:07,981][613885] Updated weights for policy 0, policy_version 122240 (0.0004) [2023-03-09 04:35:10,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9967.0, 300 sec: 10094.2). Total num frames: 62611456. Throughput: 0: 10013.8. Samples: 62590924. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:35:10,829][613581] Avg episode reward: [(0, '4379.211')] [2023-03-09 04:35:12,217][613885] Updated weights for policy 0, policy_version 122320 (0.0004) [2023-03-09 04:35:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 10094.2). Total num frames: 62664704. Throughput: 0: 10053.3. Samples: 62651540. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:35:15,829][613581] Avg episode reward: [(0, '4389.485')] [2023-03-09 04:35:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000122392_62664704.pth... [2023-03-09 04:35:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000121816_62369792.pth [2023-03-09 04:35:16,100][613885] Updated weights for policy 0, policy_version 122400 (0.0004) [2023-03-09 04:35:20,340][613885] Updated weights for policy 0, policy_version 122480 (0.0006) [2023-03-09 04:35:20,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10035.2, 300 sec: 10066.4). Total num frames: 62713856. Throughput: 0: 9925.7. Samples: 62709832. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:35:20,829][613581] Avg episode reward: [(0, '4273.028')] [2023-03-09 04:35:24,152][613885] Updated weights for policy 0, policy_version 122560 (0.0004) [2023-03-09 04:35:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 10080.3). Total num frames: 62767104. Throughput: 0: 9980.0. Samples: 62741280. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:35:25,829][613581] Avg episode reward: [(0, '4317.232')] [2023-03-09 04:35:28,322][613885] Updated weights for policy 0, policy_version 122640 (0.0006) [2023-03-09 04:35:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10103.5, 300 sec: 10080.3). Total num frames: 62816256. Throughput: 0: 9884.0. Samples: 62801432. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:35:30,829][613581] Avg episode reward: [(0, '4408.466')] [2023-03-09 04:35:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000122688_62816256.pth... [2023-03-09 04:35:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000122104_62517248.pth [2023-03-09 04:35:32,351][613885] Updated weights for policy 0, policy_version 122720 (0.0005) [2023-03-09 04:35:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 10066.4). Total num frames: 62865408. Throughput: 0: 9940.2. Samples: 62862220. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:35:35,829][613581] Avg episode reward: [(0, '4135.305')] [2023-03-09 04:35:36,416][613885] Updated weights for policy 0, policy_version 122800 (0.0005) [2023-03-09 04:35:40,588][613885] Updated weights for policy 0, policy_version 122880 (0.0005) [2023-03-09 04:35:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10066.4). Total num frames: 62914560. Throughput: 0: 9906.7. Samples: 62893280. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:35:40,829][613581] Avg episode reward: [(0, '3584.042')] [2023-03-09 04:35:44,773][613885] Updated weights for policy 0, policy_version 122960 (0.0005) [2023-03-09 04:35:45,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9898.7, 300 sec: 10052.6). Total num frames: 62963712. Throughput: 0: 9922.8. Samples: 62951440. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:35:45,829][613581] Avg episode reward: [(0, '3582.389')] [2023-03-09 04:35:45,835][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000122984_62967808.pth... [2023-03-09 04:35:45,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000122392_62664704.pth [2023-03-09 04:35:48,927][613885] Updated weights for policy 0, policy_version 123040 (0.0004) [2023-03-09 04:35:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 10052.6). Total num frames: 63012864. Throughput: 0: 9948.8. Samples: 63009980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:35:50,829][613581] Avg episode reward: [(0, '3682.755')] [2023-03-09 04:35:53,115][613885] Updated weights for policy 0, policy_version 123120 (0.0005) [2023-03-09 04:35:55,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9898.7, 300 sec: 10038.7). Total num frames: 63062016. Throughput: 0: 9990.5. Samples: 63040496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:35:55,829][613581] Avg episode reward: [(0, '4237.463')] [2023-03-09 04:35:57,280][613885] Updated weights for policy 0, policy_version 123200 (0.0004) [2023-03-09 04:36:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 10024.8). Total num frames: 63111168. Throughput: 0: 9945.1. Samples: 63099068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:36:00,829][613581] Avg episode reward: [(0, '3950.497')] [2023-03-09 04:36:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000123264_63111168.pth... [2023-03-09 04:36:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000122688_62816256.pth [2023-03-09 04:36:01,448][613885] Updated weights for policy 0, policy_version 123280 (0.0005) [2023-03-09 04:36:05,520][613885] Updated weights for policy 0, policy_version 123360 (0.0005) [2023-03-09 04:36:05,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9966.9, 300 sec: 10038.7). Total num frames: 63160320. Throughput: 0: 9973.6. Samples: 63158644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:36:05,829][613581] Avg episode reward: [(0, '4233.009')] [2023-03-09 04:36:09,850][613885] Updated weights for policy 0, policy_version 123440 (0.0005) [2023-03-09 04:36:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9966.9, 300 sec: 10038.7). Total num frames: 63209472. Throughput: 0: 9935.4. Samples: 63188372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:36:10,829][613581] Avg episode reward: [(0, '4272.926')] [2023-03-09 04:36:13,904][613885] Updated weights for policy 0, policy_version 123520 (0.0005) [2023-03-09 04:36:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9898.7, 300 sec: 10024.8). Total num frames: 63258624. Throughput: 0: 9888.5. Samples: 63246416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:36:15,829][613581] Avg episode reward: [(0, '3965.519')] [2023-03-09 04:36:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000123552_63258624.pth... [2023-03-09 04:36:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000122984_62967808.pth [2023-03-09 04:36:18,102][613885] Updated weights for policy 0, policy_version 123600 (0.0005) [2023-03-09 04:36:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 10010.9). Total num frames: 63307776. Throughput: 0: 9811.6. Samples: 63303744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:36:20,829][613581] Avg episode reward: [(0, '3870.432')] [2023-03-09 04:36:22,399][613885] Updated weights for policy 0, policy_version 123680 (0.0004) [2023-03-09 04:36:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9997.0). Total num frames: 63356928. Throughput: 0: 9785.7. Samples: 63333636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:36:25,829][613581] Avg episode reward: [(0, '4232.282')] [2023-03-09 04:36:26,354][613885] Updated weights for policy 0, policy_version 123760 (0.0005) [2023-03-09 04:36:30,501][613885] Updated weights for policy 0, policy_version 123840 (0.0005) [2023-03-09 04:36:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9997.0). Total num frames: 63406080. Throughput: 0: 9844.0. Samples: 63394420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:36:30,829][613581] Avg episode reward: [(0, '4063.234')] [2023-03-09 04:36:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000123840_63406080.pth... [2023-03-09 04:36:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000123264_63111168.pth [2023-03-09 04:36:34,577][613885] Updated weights for policy 0, policy_version 123920 (0.0004) [2023-03-09 04:36:35,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9983.1). Total num frames: 63455232. Throughput: 0: 9884.2. Samples: 63454768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:36:35,829][613581] Avg episode reward: [(0, '4092.583')] [2023-03-09 04:36:38,645][613885] Updated weights for policy 0, policy_version 124000 (0.0005) [2023-03-09 04:36:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9898.7, 300 sec: 9997.0). Total num frames: 63508480. Throughput: 0: 9855.9. Samples: 63484012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:36:40,829][613581] Avg episode reward: [(0, '4085.209')] [2023-03-09 04:36:42,478][613885] Updated weights for policy 0, policy_version 124080 (0.0005) [2023-03-09 04:36:45,829][613581] Fps is (10 sec: 10649.3, 60 sec: 9966.9, 300 sec: 9997.0). Total num frames: 63561728. Throughput: 0: 9969.5. Samples: 63547696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:36:45,830][613581] Avg episode reward: [(0, '4295.810')] [2023-03-09 04:36:45,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000124144_63561728.pth... [2023-03-09 04:36:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000123552_63258624.pth [2023-03-09 04:36:46,463][613885] Updated weights for policy 0, policy_version 124160 (0.0005) [2023-03-09 04:36:50,531][613885] Updated weights for policy 0, policy_version 124240 (0.0005) [2023-03-09 04:36:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 9983.1). Total num frames: 63610880. Throughput: 0: 10022.5. Samples: 63609656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:36:50,829][613581] Avg episode reward: [(0, '4324.142')] [2023-03-09 04:36:54,803][613885] Updated weights for policy 0, policy_version 124320 (0.0005) [2023-03-09 04:36:55,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9966.9, 300 sec: 9969.2). Total num frames: 63660032. Throughput: 0: 10024.3. Samples: 63639464. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:36:55,829][613581] Avg episode reward: [(0, '3942.718')] [2023-03-09 04:36:59,141][613885] Updated weights for policy 0, policy_version 124400 (0.0005) [2023-03-09 04:37:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 9955.4). Total num frames: 63709184. Throughput: 0: 9975.6. Samples: 63695320. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:37:00,829][613581] Avg episode reward: [(0, '3542.702')] [2023-03-09 04:37:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000124432_63709184.pth... [2023-03-09 04:37:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000123840_63406080.pth [2023-03-09 04:37:03,248][613885] Updated weights for policy 0, policy_version 124480 (0.0005) [2023-03-09 04:37:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9898.6, 300 sec: 9941.5). Total num frames: 63754240. Throughput: 0: 10006.9. Samples: 63754056. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:37:05,829][613581] Avg episode reward: [(0, '3317.623')] [2023-03-09 04:37:07,692][613885] Updated weights for policy 0, policy_version 124560 (0.0004) [2023-03-09 04:37:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9898.7, 300 sec: 9941.5). Total num frames: 63803392. Throughput: 0: 9975.0. Samples: 63782512. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:37:10,829][613581] Avg episode reward: [(0, '3058.556')] [2023-03-09 04:37:11,834][613885] Updated weights for policy 0, policy_version 124640 (0.0004) [2023-03-09 04:37:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9927.6). Total num frames: 63852544. Throughput: 0: 9914.3. Samples: 63840564. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:37:15,829][613581] Avg episode reward: [(0, '3935.676')] [2023-03-09 04:37:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000124712_63852544.pth... [2023-03-09 04:37:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000124144_63561728.pth [2023-03-09 04:37:15,990][613885] Updated weights for policy 0, policy_version 124720 (0.0005) [2023-03-09 04:37:20,160][613885] Updated weights for policy 0, policy_version 124800 (0.0005) [2023-03-09 04:37:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9941.5). Total num frames: 63901696. Throughput: 0: 9893.0. Samples: 63899956. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:37:20,835][613581] Avg episode reward: [(0, '3794.114')] [2023-03-09 04:37:24,078][613885] Updated weights for policy 0, policy_version 124880 (0.0005) [2023-03-09 04:37:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 9955.4). Total num frames: 63954944. Throughput: 0: 9936.1. Samples: 63931136. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:37:25,830][613581] Avg episode reward: [(0, '3996.534')] [2023-03-09 04:37:28,025][613885] Updated weights for policy 0, policy_version 124960 (0.0004) [2023-03-09 04:37:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 9955.4). Total num frames: 64004096. Throughput: 0: 9884.0. Samples: 63992476. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:37:30,840][613581] Avg episode reward: [(0, '3599.760')] [2023-03-09 04:37:30,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000125008_64004096.pth... [2023-03-09 04:37:30,844][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000124432_63709184.pth [2023-03-09 04:37:32,190][613885] Updated weights for policy 0, policy_version 125040 (0.0005) [2023-03-09 04:37:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 9955.4). Total num frames: 64053248. Throughput: 0: 9847.3. Samples: 64052784. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:37:35,829][613581] Avg episode reward: [(0, '3956.377')] [2023-03-09 04:37:36,417][613885] Updated weights for policy 0, policy_version 125120 (0.0004) [2023-03-09 04:37:40,428][613885] Updated weights for policy 0, policy_version 125200 (0.0004) [2023-03-09 04:37:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9955.4). Total num frames: 64102400. Throughput: 0: 9815.8. Samples: 64081176. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:37:40,829][613581] Avg episode reward: [(0, '3911.053')] [2023-03-09 04:37:44,429][613885] Updated weights for policy 0, policy_version 125280 (0.0005) [2023-03-09 04:37:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 9969.2). Total num frames: 64155648. Throughput: 0: 9956.4. Samples: 64143360. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:37:45,829][613581] Avg episode reward: [(0, '4024.031')] [2023-03-09 04:37:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000125304_64155648.pth... [2023-03-09 04:37:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000124712_63852544.pth [2023-03-09 04:37:48,653][613885] Updated weights for policy 0, policy_version 125360 (0.0005) [2023-03-09 04:37:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9898.7, 300 sec: 9983.1). Total num frames: 64204800. Throughput: 0: 9935.0. Samples: 64201132. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 04:37:50,829][613581] Avg episode reward: [(0, '3799.539')] [2023-03-09 04:37:52,750][613885] Updated weights for policy 0, policy_version 125440 (0.0004) [2023-03-09 04:37:55,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9898.7, 300 sec: 9983.1). Total num frames: 64253952. Throughput: 0: 9985.0. Samples: 64231836. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:37:55,829][613581] Avg episode reward: [(0, '3788.483')] [2023-03-09 04:37:56,866][613885] Updated weights for policy 0, policy_version 125520 (0.0005) [2023-03-09 04:38:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9969.2). Total num frames: 64303104. Throughput: 0: 10005.9. Samples: 64290828. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:38:00,829][613581] Avg episode reward: [(0, '3855.992')] [2023-03-09 04:38:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000125592_64303104.pth... [2023-03-09 04:38:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000125008_64004096.pth [2023-03-09 04:38:00,989][613885] Updated weights for policy 0, policy_version 125600 (0.0005) [2023-03-09 04:38:04,805][613885] Updated weights for policy 0, policy_version 125680 (0.0004) [2023-03-09 04:38:05,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10035.2, 300 sec: 9969.2). Total num frames: 64356352. Throughput: 0: 10087.1. Samples: 64353876. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:38:05,829][613581] Avg episode reward: [(0, '4274.955')] [2023-03-09 04:38:08,941][613885] Updated weights for policy 0, policy_version 125760 (0.0005) [2023-03-09 04:38:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10035.2, 300 sec: 9969.2). Total num frames: 64405504. Throughput: 0: 10049.3. Samples: 64383352. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:38:10,829][613581] Avg episode reward: [(0, '4257.386')] [2023-03-09 04:38:12,865][613885] Updated weights for policy 0, policy_version 125840 (0.0005) [2023-03-09 04:38:15,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 9969.2). Total num frames: 64454656. Throughput: 0: 10053.9. Samples: 64444900. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:38:15,829][613581] Avg episode reward: [(0, '4108.651')] [2023-03-09 04:38:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000125888_64454656.pth... [2023-03-09 04:38:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000125304_64155648.pth [2023-03-09 04:38:17,131][613885] Updated weights for policy 0, policy_version 125920 (0.0005) [2023-03-09 04:38:20,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10103.5, 300 sec: 9969.2). Total num frames: 64507904. Throughput: 0: 10022.5. Samples: 64503796. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:38:20,829][613581] Avg episode reward: [(0, '4207.913')] [2023-03-09 04:38:21,138][613885] Updated weights for policy 0, policy_version 126000 (0.0005) [2023-03-09 04:38:25,275][613885] Updated weights for policy 0, policy_version 126080 (0.0005) [2023-03-09 04:38:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 9969.2). Total num frames: 64557056. Throughput: 0: 10059.6. Samples: 64533856. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:38:25,829][613581] Avg episode reward: [(0, '4328.210')] [2023-03-09 04:38:29,114][613885] Updated weights for policy 0, policy_version 126160 (0.0005) [2023-03-09 04:38:30,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10103.5, 300 sec: 9983.1). Total num frames: 64610304. Throughput: 0: 10087.1. Samples: 64597280. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:38:30,829][613581] Avg episode reward: [(0, '4180.554')] [2023-03-09 04:38:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000126192_64610304.pth... [2023-03-09 04:38:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000125592_64303104.pth [2023-03-09 04:38:33,137][613885] Updated weights for policy 0, policy_version 126240 (0.0005) [2023-03-09 04:38:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 9983.1). Total num frames: 64659456. Throughput: 0: 10120.6. Samples: 64656560. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:38:35,829][613581] Avg episode reward: [(0, '4204.950')] [2023-03-09 04:38:37,392][613885] Updated weights for policy 0, policy_version 126320 (0.0004) [2023-03-09 04:38:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 9983.1). Total num frames: 64708608. Throughput: 0: 10071.5. Samples: 64685056. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:38:40,829][613581] Avg episode reward: [(0, '4171.212')] [2023-03-09 04:38:41,569][613885] Updated weights for policy 0, policy_version 126400 (0.0005) [2023-03-09 04:38:45,778][613885] Updated weights for policy 0, policy_version 126480 (0.0005) [2023-03-09 04:38:45,829][613581] Fps is (10 sec: 9830.2, 60 sec: 10035.2, 300 sec: 9969.2). Total num frames: 64757760. Throughput: 0: 10069.4. Samples: 64743952. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:38:45,830][613581] Avg episode reward: [(0, '4284.123')] [2023-03-09 04:38:45,835][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000126480_64757760.pth... [2023-03-09 04:38:45,838][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000125888_64454656.pth [2023-03-09 04:38:50,041][613885] Updated weights for policy 0, policy_version 126560 (0.0005) [2023-03-09 04:38:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9966.9, 300 sec: 9955.4). Total num frames: 64802816. Throughput: 0: 9966.4. Samples: 64802364. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:38:50,829][613581] Avg episode reward: [(0, '4154.358')] [2023-03-09 04:38:54,210][613885] Updated weights for policy 0, policy_version 126640 (0.0004) [2023-03-09 04:38:55,829][613581] Fps is (10 sec: 9830.6, 60 sec: 10035.2, 300 sec: 9969.2). Total num frames: 64856064. Throughput: 0: 9960.0. Samples: 64831552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:38:55,829][613581] Avg episode reward: [(0, '4126.699')] [2023-03-09 04:38:58,272][613885] Updated weights for policy 0, policy_version 126720 (0.0004) [2023-03-09 04:39:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 9969.2). Total num frames: 64905216. Throughput: 0: 9931.4. Samples: 64891812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:39:00,829][613581] Avg episode reward: [(0, '4028.839')] [2023-03-09 04:39:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000126768_64905216.pth... [2023-03-09 04:39:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000126192_64610304.pth [2023-03-09 04:39:02,512][613885] Updated weights for policy 0, policy_version 126800 (0.0005) [2023-03-09 04:39:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9898.7, 300 sec: 9955.4). Total num frames: 64950272. Throughput: 0: 9866.6. Samples: 64947792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:39:05,829][613581] Avg episode reward: [(0, '3970.020')] [2023-03-09 04:39:06,870][613885] Updated weights for policy 0, policy_version 126880 (0.0005) [2023-03-09 04:39:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9898.7, 300 sec: 9955.4). Total num frames: 64999424. Throughput: 0: 9844.7. Samples: 64976868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:39:10,829][613581] Avg episode reward: [(0, '3688.545')] [2023-03-09 04:39:11,116][613885] Updated weights for policy 0, policy_version 126960 (0.0004) [2023-03-09 04:39:15,115][613885] Updated weights for policy 0, policy_version 127040 (0.0005) [2023-03-09 04:39:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9955.4). Total num frames: 65048576. Throughput: 0: 9755.9. Samples: 65036296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:39:15,829][613581] Avg episode reward: [(0, '3821.265')] [2023-03-09 04:39:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000127048_65048576.pth... [2023-03-09 04:39:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000126480_64757760.pth [2023-03-09 04:39:19,324][613885] Updated weights for policy 0, policy_version 127120 (0.0004) [2023-03-09 04:39:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9830.4, 300 sec: 9955.4). Total num frames: 65097728. Throughput: 0: 9773.7. Samples: 65096376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:39:20,829][613581] Avg episode reward: [(0, '4204.055')] [2023-03-09 04:39:23,115][613885] Updated weights for policy 0, policy_version 127200 (0.0005) [2023-03-09 04:39:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 9898.7, 300 sec: 9969.3). Total num frames: 65150976. Throughput: 0: 9882.8. Samples: 65129780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:39:25,829][613581] Avg episode reward: [(0, '4348.747')] [2023-03-09 04:39:27,334][613885] Updated weights for policy 0, policy_version 127280 (0.0005) [2023-03-09 04:39:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9830.4, 300 sec: 9955.4). Total num frames: 65200128. Throughput: 0: 9865.8. Samples: 65187912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:39:30,829][613581] Avg episode reward: [(0, '4356.905')] [2023-03-09 04:39:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000127344_65200128.pth... [2023-03-09 04:39:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000126768_64905216.pth [2023-03-09 04:39:31,452][613885] Updated weights for policy 0, policy_version 127360 (0.0005) [2023-03-09 04:39:35,771][613885] Updated weights for policy 0, policy_version 127440 (0.0004) [2023-03-09 04:39:35,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9830.4, 300 sec: 9941.5). Total num frames: 65249280. Throughput: 0: 9840.7. Samples: 65245196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:39:35,829][613581] Avg episode reward: [(0, '4431.613')] [2023-03-09 04:39:39,990][613885] Updated weights for policy 0, policy_version 127520 (0.0004) [2023-03-09 04:39:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9927.6). Total num frames: 65298432. Throughput: 0: 9836.4. Samples: 65274192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:39:40,829][613581] Avg episode reward: [(0, '4389.799')] [2023-03-09 04:39:44,402][613885] Updated weights for policy 0, policy_version 127600 (0.0004) [2023-03-09 04:39:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.2, 300 sec: 9913.7). Total num frames: 65343488. Throughput: 0: 9764.2. Samples: 65331200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:39:45,829][613581] Avg episode reward: [(0, '4174.732')] [2023-03-09 04:39:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000127624_65343488.pth... [2023-03-09 04:39:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000127048_65048576.pth [2023-03-09 04:39:48,695][613885] Updated weights for policy 0, policy_version 127680 (0.0005) [2023-03-09 04:39:50,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9830.4, 300 sec: 9913.7). Total num frames: 65392640. Throughput: 0: 9802.8. Samples: 65388916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:39:50,829][613581] Avg episode reward: [(0, '4409.033')] [2023-03-09 04:39:52,795][613885] Updated weights for policy 0, policy_version 127760 (0.0005) [2023-03-09 04:39:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9913.7). Total num frames: 65441792. Throughput: 0: 9818.8. Samples: 65418716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:39:55,840][613581] Avg episode reward: [(0, '4480.428')] [2023-03-09 04:39:56,872][613885] Updated weights for policy 0, policy_version 127840 (0.0004) [2023-03-09 04:40:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9927.6). Total num frames: 65490944. Throughput: 0: 9831.6. Samples: 65478720. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:40:00,829][613581] Avg episode reward: [(0, '4108.031')] [2023-03-09 04:40:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000127912_65490944.pth... [2023-03-09 04:40:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000127344_65200128.pth [2023-03-09 04:40:00,947][613885] Updated weights for policy 0, policy_version 127920 (0.0004) [2023-03-09 04:40:05,143][613885] Updated weights for policy 0, policy_version 128000 (0.0004) [2023-03-09 04:40:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9927.6). Total num frames: 65540096. Throughput: 0: 9825.5. Samples: 65538524. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:40:05,829][613581] Avg episode reward: [(0, '4451.112')] [2023-03-09 04:40:09,426][613885] Updated weights for policy 0, policy_version 128080 (0.0005) [2023-03-09 04:40:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9913.7). Total num frames: 65589248. Throughput: 0: 9730.2. Samples: 65567640. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:40:10,829][613581] Avg episode reward: [(0, '4526.520')] [2023-03-09 04:40:13,771][613885] Updated weights for policy 0, policy_version 128160 (0.0005) [2023-03-09 04:40:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9899.8). Total num frames: 65634304. Throughput: 0: 9695.8. Samples: 65624224. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:40:15,829][613581] Avg episode reward: [(0, '4362.559')] [2023-03-09 04:40:15,880][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000128200_65638400.pth... [2023-03-09 04:40:15,882][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000127624_65343488.pth [2023-03-09 04:40:17,916][613885] Updated weights for policy 0, policy_version 128240 (0.0005) [2023-03-09 04:40:20,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9899.8). Total num frames: 65687552. Throughput: 0: 9796.0. Samples: 65686016. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:40:20,829][613581] Avg episode reward: [(0, '4558.348')] [2023-03-09 04:40:21,550][613885] Updated weights for policy 0, policy_version 128320 (0.0005) [2023-03-09 04:40:25,768][613885] Updated weights for policy 0, policy_version 128400 (0.0005) [2023-03-09 04:40:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 9830.4, 300 sec: 9913.7). Total num frames: 65740800. Throughput: 0: 9855.8. Samples: 65717704. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:40:25,829][613581] Avg episode reward: [(0, '4334.978')] [2023-03-09 04:40:30,078][613885] Updated weights for policy 0, policy_version 128480 (0.0005) [2023-03-09 04:40:30,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9899.8). Total num frames: 65785856. Throughput: 0: 9846.1. Samples: 65774276. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:40:30,829][613581] Avg episode reward: [(0, '4498.476')] [2023-03-09 04:40:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000128488_65785856.pth... [2023-03-09 04:40:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000127912_65490944.pth [2023-03-09 04:40:34,372][613885] Updated weights for policy 0, policy_version 128560 (0.0005) [2023-03-09 04:40:35,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9762.1, 300 sec: 9899.8). Total num frames: 65835008. Throughput: 0: 9868.7. Samples: 65833008. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:40:35,829][613581] Avg episode reward: [(0, '4552.679')] [2023-03-09 04:40:38,399][613885] Updated weights for policy 0, policy_version 128640 (0.0004) [2023-03-09 04:40:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.1, 300 sec: 9899.8). Total num frames: 65884160. Throughput: 0: 9888.3. Samples: 65863688. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:40:40,829][613581] Avg episode reward: [(0, '4469.700')] [2023-03-09 04:40:42,379][613885] Updated weights for policy 0, policy_version 128720 (0.0005) [2023-03-09 04:40:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9898.7, 300 sec: 9913.7). Total num frames: 65937408. Throughput: 0: 9931.5. Samples: 65925636. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:40:45,829][613581] Avg episode reward: [(0, '4562.559')] [2023-03-09 04:40:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000128784_65937408.pth... [2023-03-09 04:40:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000128200_65638400.pth [2023-03-09 04:40:46,346][613885] Updated weights for policy 0, policy_version 128800 (0.0005) [2023-03-09 04:40:50,546][613885] Updated weights for policy 0, policy_version 128880 (0.0005) [2023-03-09 04:40:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9898.7, 300 sec: 9913.7). Total num frames: 65986560. Throughput: 0: 9922.2. Samples: 65985024. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:40:50,829][613581] Avg episode reward: [(0, '4528.232')] [2023-03-09 04:40:54,690][613885] Updated weights for policy 0, policy_version 128960 (0.0005) [2023-03-09 04:40:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9913.7). Total num frames: 66035712. Throughput: 0: 9945.0. Samples: 66015164. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:40:55,829][613581] Avg episode reward: [(0, '4517.558')] [2023-03-09 04:40:58,775][613885] Updated weights for policy 0, policy_version 129040 (0.0005) [2023-03-09 04:41:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9913.7). Total num frames: 66084864. Throughput: 0: 10007.0. Samples: 66074540. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:41:00,829][613581] Avg episode reward: [(0, '4424.717')] [2023-03-09 04:41:00,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000129072_66084864.pth... [2023-03-09 04:41:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000128488_65785856.pth [2023-03-09 04:41:03,012][613885] Updated weights for policy 0, policy_version 129120 (0.0004) [2023-03-09 04:41:05,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9898.7, 300 sec: 9913.7). Total num frames: 66134016. Throughput: 0: 9866.8. Samples: 66130024. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:41:05,829][613581] Avg episode reward: [(0, '4414.680')] [2023-03-09 04:41:07,455][613885] Updated weights for policy 0, policy_version 129200 (0.0005) [2023-03-09 04:41:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9913.7). Total num frames: 66183168. Throughput: 0: 9824.2. Samples: 66159792. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:41:10,829][613581] Avg episode reward: [(0, '4404.756')] [2023-03-09 04:41:11,654][613885] Updated weights for policy 0, policy_version 129280 (0.0005) [2023-03-09 04:41:15,734][613885] Updated weights for policy 0, policy_version 129360 (0.0004) [2023-03-09 04:41:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 9913.7). Total num frames: 66232320. Throughput: 0: 9903.9. Samples: 66219952. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:41:15,829][613581] Avg episode reward: [(0, '4098.999')] [2023-03-09 04:41:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000129360_66232320.pth... [2023-03-09 04:41:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000128784_65937408.pth [2023-03-09 04:41:19,999][613885] Updated weights for policy 0, policy_version 129440 (0.0005) [2023-03-09 04:41:20,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9830.4, 300 sec: 9899.8). Total num frames: 66277376. Throughput: 0: 9869.9. Samples: 66277152. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:41:20,829][613581] Avg episode reward: [(0, '4260.800')] [2023-03-09 04:41:24,413][613885] Updated weights for policy 0, policy_version 129520 (0.0005) [2023-03-09 04:41:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9899.8). Total num frames: 66326528. Throughput: 0: 9779.9. Samples: 66303784. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:41:25,829][613581] Avg episode reward: [(0, '4322.310')] [2023-03-09 04:41:28,585][613885] Updated weights for policy 0, policy_version 129600 (0.0005) [2023-03-09 04:41:30,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9830.4, 300 sec: 9899.8). Total num frames: 66375680. Throughput: 0: 9718.1. Samples: 66362952. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:41:30,829][613581] Avg episode reward: [(0, '4172.662')] [2023-03-09 04:41:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000129640_66375680.pth... [2023-03-09 04:41:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000129072_66084864.pth [2023-03-09 04:41:32,915][613885] Updated weights for policy 0, policy_version 129680 (0.0005) [2023-03-09 04:41:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9885.9). Total num frames: 66424832. Throughput: 0: 9682.6. Samples: 66420744. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:41:35,829][613581] Avg episode reward: [(0, '4322.451')] [2023-03-09 04:41:37,009][613885] Updated weights for policy 0, policy_version 129760 (0.0005) [2023-03-09 04:41:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9872.1). Total num frames: 66473984. Throughput: 0: 9672.8. Samples: 66450440. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:41:40,829][613581] Avg episode reward: [(0, '4464.007')] [2023-03-09 04:41:41,135][613885] Updated weights for policy 0, policy_version 129840 (0.0004) [2023-03-09 04:41:45,320][613885] Updated weights for policy 0, policy_version 129920 (0.0005) [2023-03-09 04:41:45,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.1, 300 sec: 9872.1). Total num frames: 66523136. Throughput: 0: 9682.5. Samples: 66510252. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:41:45,829][613581] Avg episode reward: [(0, '4426.182')] [2023-03-09 04:41:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000129928_66523136.pth... [2023-03-09 04:41:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000129360_66232320.pth [2023-03-09 04:41:49,522][613885] Updated weights for policy 0, policy_version 130000 (0.0005) [2023-03-09 04:41:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9872.1). Total num frames: 66572288. Throughput: 0: 9750.6. Samples: 66568800. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:41:50,829][613581] Avg episode reward: [(0, '4358.914')] [2023-03-09 04:41:53,920][613885] Updated weights for policy 0, policy_version 130080 (0.0005) [2023-03-09 04:41:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9858.2). Total num frames: 66617344. Throughput: 0: 9710.7. Samples: 66596772. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:41:55,829][613581] Avg episode reward: [(0, '4351.752')] [2023-03-09 04:41:58,039][613885] Updated weights for policy 0, policy_version 130160 (0.0005) [2023-03-09 04:42:00,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9872.1). Total num frames: 66666496. Throughput: 0: 9678.3. Samples: 66655476. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:42:00,829][613581] Avg episode reward: [(0, '4529.403')] [2023-03-09 04:42:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000130208_66666496.pth... [2023-03-09 04:42:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000129640_66375680.pth [2023-03-09 04:42:02,229][613885] Updated weights for policy 0, policy_version 130240 (0.0004) [2023-03-09 04:42:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9872.1). Total num frames: 66715648. Throughput: 0: 9733.2. Samples: 66715148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:42:05,829][613581] Avg episode reward: [(0, '4448.429')] [2023-03-09 04:42:06,404][613885] Updated weights for policy 0, policy_version 130320 (0.0005) [2023-03-09 04:42:10,776][613885] Updated weights for policy 0, policy_version 130400 (0.0005) [2023-03-09 04:42:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9872.1). Total num frames: 66764800. Throughput: 0: 9786.2. Samples: 66744164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:42:10,829][613581] Avg episode reward: [(0, '4423.180')] [2023-03-09 04:42:14,907][613885] Updated weights for policy 0, policy_version 130480 (0.0005) [2023-03-09 04:42:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9872.1). Total num frames: 66813952. Throughput: 0: 9734.2. Samples: 66800992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:42:15,829][613581] Avg episode reward: [(0, '4495.753')] [2023-03-09 04:42:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000130496_66813952.pth... [2023-03-09 04:42:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000129928_66523136.pth [2023-03-09 04:42:19,075][613885] Updated weights for policy 0, policy_version 130560 (0.0005) [2023-03-09 04:42:20,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9693.9, 300 sec: 9844.3). Total num frames: 66859008. Throughput: 0: 9739.2. Samples: 66859008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:42:20,829][613581] Avg episode reward: [(0, '4362.646')] [2023-03-09 04:42:23,440][613885] Updated weights for policy 0, policy_version 130640 (0.0004) [2023-03-09 04:42:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9844.3). Total num frames: 66908160. Throughput: 0: 9714.7. Samples: 66887600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:42:25,829][613581] Avg episode reward: [(0, '4314.030')] [2023-03-09 04:42:27,649][613885] Updated weights for policy 0, policy_version 130720 (0.0004) [2023-03-09 04:42:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9844.3). Total num frames: 66957312. Throughput: 0: 9666.0. Samples: 66945224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:42:30,829][613581] Avg episode reward: [(0, '4355.266')] [2023-03-09 04:42:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000130776_66957312.pth... [2023-03-09 04:42:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000130208_66666496.pth [2023-03-09 04:42:31,866][613885] Updated weights for policy 0, policy_version 130800 (0.0005) [2023-03-09 04:42:35,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9844.3). Total num frames: 67006464. Throughput: 0: 9680.8. Samples: 67004436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:42:35,829][613581] Avg episode reward: [(0, '4554.388')] [2023-03-09 04:42:36,076][613885] Updated weights for policy 0, policy_version 130880 (0.0004) [2023-03-09 04:42:40,386][613885] Updated weights for policy 0, policy_version 130960 (0.0005) [2023-03-09 04:42:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9830.4). Total num frames: 67055616. Throughput: 0: 9664.2. Samples: 67031660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:42:40,829][613581] Avg episode reward: [(0, '4543.990')] [2023-03-09 04:42:44,460][613885] Updated weights for policy 0, policy_version 131040 (0.0004) [2023-03-09 04:42:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9830.4). Total num frames: 67104768. Throughput: 0: 9702.2. Samples: 67092076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:42:45,829][613581] Avg episode reward: [(0, '4496.704')] [2023-03-09 04:42:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000131064_67104768.pth... [2023-03-09 04:42:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000130496_66813952.pth [2023-03-09 04:42:48,544][613885] Updated weights for policy 0, policy_version 131120 (0.0005) [2023-03-09 04:42:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9830.4). Total num frames: 67153920. Throughput: 0: 9686.1. Samples: 67151020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:42:50,829][613581] Avg episode reward: [(0, '4510.446')] [2023-03-09 04:42:52,508][613885] Updated weights for policy 0, policy_version 131200 (0.0004) [2023-03-09 04:42:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9830.4). Total num frames: 67203072. Throughput: 0: 9741.3. Samples: 67182524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:42:55,829][613581] Avg episode reward: [(0, '4424.480')] [2023-03-09 04:42:56,933][613885] Updated weights for policy 0, policy_version 131280 (0.0005) [2023-03-09 04:43:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9816.5). Total num frames: 67252224. Throughput: 0: 9752.8. Samples: 67239868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:43:00,830][613581] Avg episode reward: [(0, '4371.016')] [2023-03-09 04:43:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000131352_67252224.pth... [2023-03-09 04:43:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000130776_66957312.pth [2023-03-09 04:43:01,026][613885] Updated weights for policy 0, policy_version 131360 (0.0005) [2023-03-09 04:43:05,306][613885] Updated weights for policy 0, policy_version 131440 (0.0005) [2023-03-09 04:43:05,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.1, 300 sec: 9816.5). Total num frames: 67301376. Throughput: 0: 9746.2. Samples: 67297588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:43:05,829][613581] Avg episode reward: [(0, '4428.172')] [2023-03-09 04:43:09,306][613885] Updated weights for policy 0, policy_version 131520 (0.0005) [2023-03-09 04:43:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.1, 300 sec: 9816.5). Total num frames: 67350528. Throughput: 0: 9776.2. Samples: 67327528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:43:10,829][613581] Avg episode reward: [(0, '4392.191')] [2023-03-09 04:43:13,591][613885] Updated weights for policy 0, policy_version 131600 (0.0004) [2023-03-09 04:43:15,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9693.9, 300 sec: 9788.7). Total num frames: 67395584. Throughput: 0: 9820.3. Samples: 67387140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:43:15,829][613581] Avg episode reward: [(0, '4531.478')] [2023-03-09 04:43:15,862][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000131640_67399680.pth... [2023-03-09 04:43:15,864][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000131064_67104768.pth [2023-03-09 04:43:17,813][613885] Updated weights for policy 0, policy_version 131680 (0.0004) [2023-03-09 04:43:20,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9762.1, 300 sec: 9788.7). Total num frames: 67444736. Throughput: 0: 9763.4. Samples: 67443788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:43:20,829][613581] Avg episode reward: [(0, '4472.263')] [2023-03-09 04:43:22,365][613885] Updated weights for policy 0, policy_version 131760 (0.0005) [2023-03-09 04:43:25,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9693.9, 300 sec: 9761.0). Total num frames: 67489792. Throughput: 0: 9763.7. Samples: 67471024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:43:25,829][613581] Avg episode reward: [(0, '4464.153')] [2023-03-09 04:43:26,896][613885] Updated weights for policy 0, policy_version 131840 (0.0005) [2023-03-09 04:43:30,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9693.9, 300 sec: 9761.0). Total num frames: 67538944. Throughput: 0: 9671.7. Samples: 67527300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:43:30,829][613581] Avg episode reward: [(0, '4388.454')] [2023-03-09 04:43:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000131912_67538944.pth... [2023-03-09 04:43:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000131352_67252224.pth [2023-03-09 04:43:31,137][613885] Updated weights for policy 0, policy_version 131920 (0.0005) [2023-03-09 04:43:35,472][613885] Updated weights for policy 0, policy_version 132000 (0.0004) [2023-03-09 04:43:35,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9625.6, 300 sec: 9747.1). Total num frames: 67584000. Throughput: 0: 9620.0. Samples: 67583920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:43:35,829][613581] Avg episode reward: [(0, '4519.281')] [2023-03-09 04:43:39,727][613885] Updated weights for policy 0, policy_version 132080 (0.0004) [2023-03-09 04:43:40,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9747.1). Total num frames: 67633152. Throughput: 0: 9552.8. Samples: 67612400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:43:40,829][613581] Avg episode reward: [(0, '4490.959')] [2023-03-09 04:43:43,861][613885] Updated weights for policy 0, policy_version 132160 (0.0005) [2023-03-09 04:43:45,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9625.6, 300 sec: 9761.0). Total num frames: 67682304. Throughput: 0: 9560.5. Samples: 67670092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:43:45,829][613581] Avg episode reward: [(0, '4526.861')] [2023-03-09 04:43:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000132192_67682304.pth... [2023-03-09 04:43:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000131640_67399680.pth [2023-03-09 04:43:48,132][613885] Updated weights for policy 0, policy_version 132240 (0.0004) [2023-03-09 04:43:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9747.1). Total num frames: 67731456. Throughput: 0: 9570.2. Samples: 67728248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:43:50,829][613581] Avg episode reward: [(0, '4528.871')] [2023-03-09 04:43:52,607][613885] Updated weights for policy 0, policy_version 132320 (0.0004) [2023-03-09 04:43:55,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9557.3, 300 sec: 9733.2). Total num frames: 67776512. Throughput: 0: 9519.2. Samples: 67755892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:43:55,829][613581] Avg episode reward: [(0, '4439.833')] [2023-03-09 04:43:56,809][613885] Updated weights for policy 0, policy_version 132400 (0.0005) [2023-03-09 04:44:00,809][613885] Updated weights for policy 0, policy_version 132480 (0.0005) [2023-03-09 04:44:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9761.0). Total num frames: 67829760. Throughput: 0: 9518.4. Samples: 67815468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:44:00,829][613581] Avg episode reward: [(0, '4391.453')] [2023-03-09 04:44:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000132480_67829760.pth... [2023-03-09 04:44:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000131912_67538944.pth [2023-03-09 04:44:04,980][613885] Updated weights for policy 0, policy_version 132560 (0.0005) [2023-03-09 04:44:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9747.1). Total num frames: 67874816. Throughput: 0: 9576.2. Samples: 67874716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:44:05,829][613581] Avg episode reward: [(0, '4386.621')] [2023-03-09 04:44:09,294][613885] Updated weights for policy 0, policy_version 132640 (0.0005) [2023-03-09 04:44:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9747.1). Total num frames: 67923968. Throughput: 0: 9608.3. Samples: 67903396. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:44:10,829][613581] Avg episode reward: [(0, '4305.204')] [2023-03-09 04:44:13,463][613885] Updated weights for policy 0, policy_version 132720 (0.0005) [2023-03-09 04:44:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9747.1). Total num frames: 67973120. Throughput: 0: 9634.2. Samples: 67960840. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:44:15,829][613581] Avg episode reward: [(0, '4316.401')] [2023-03-09 04:44:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000132760_67973120.pth... [2023-03-09 04:44:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000132192_67682304.pth [2023-03-09 04:44:17,777][613885] Updated weights for policy 0, policy_version 132800 (0.0006) [2023-03-09 04:44:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9733.2). Total num frames: 68022272. Throughput: 0: 9724.6. Samples: 68021528. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:44:20,829][613581] Avg episode reward: [(0, '4344.785')] [2023-03-09 04:44:21,660][613885] Updated weights for policy 0, policy_version 132880 (0.0005) [2023-03-09 04:44:25,574][613885] Updated weights for policy 0, policy_version 132960 (0.0005) [2023-03-09 04:44:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 9762.1, 300 sec: 9747.1). Total num frames: 68075520. Throughput: 0: 9783.3. Samples: 68052648. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:44:25,829][613581] Avg episode reward: [(0, '4544.118')] [2023-03-09 04:44:29,858][613885] Updated weights for policy 0, policy_version 133040 (0.0005) [2023-03-09 04:44:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9762.1, 300 sec: 9747.1). Total num frames: 68124672. Throughput: 0: 9828.5. Samples: 68112372. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:44:30,829][613581] Avg episode reward: [(0, '4425.341')] [2023-03-09 04:44:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000133056_68124672.pth... [2023-03-09 04:44:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000132480_67829760.pth [2023-03-09 04:44:34,134][613885] Updated weights for policy 0, policy_version 133120 (0.0005) [2023-03-09 04:44:35,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9762.1, 300 sec: 9733.2). Total num frames: 68169728. Throughput: 0: 9801.6. Samples: 68169320. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:44:35,829][613581] Avg episode reward: [(0, '4467.088')] [2023-03-09 04:44:38,440][613885] Updated weights for policy 0, policy_version 133200 (0.0005) [2023-03-09 04:44:40,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9747.1). Total num frames: 68218880. Throughput: 0: 9822.3. Samples: 68197896. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:44:40,829][613581] Avg episode reward: [(0, '4366.324')] [2023-03-09 04:44:42,700][613885] Updated weights for policy 0, policy_version 133280 (0.0005) [2023-03-09 04:44:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9747.1). Total num frames: 68268032. Throughput: 0: 9783.9. Samples: 68255744. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:44:45,829][613581] Avg episode reward: [(0, '4454.722')] [2023-03-09 04:44:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000133336_68268032.pth... [2023-03-09 04:44:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000132760_67973120.pth [2023-03-09 04:44:47,113][613885] Updated weights for policy 0, policy_version 133360 (0.0005) [2023-03-09 04:44:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9733.2). Total num frames: 68313088. Throughput: 0: 9701.2. Samples: 68311272. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:44:50,829][613581] Avg episode reward: [(0, '4379.404')] [2023-03-09 04:44:51,346][613885] Updated weights for policy 0, policy_version 133440 (0.0005) [2023-03-09 04:44:55,744][613885] Updated weights for policy 0, policy_version 133520 (0.0005) [2023-03-09 04:44:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9733.2). Total num frames: 68362240. Throughput: 0: 9732.8. Samples: 68341372. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:44:55,829][613581] Avg episode reward: [(0, '4522.371')] [2023-03-09 04:45:00,107][613885] Updated weights for policy 0, policy_version 133600 (0.0005) [2023-03-09 04:45:00,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9719.3). Total num frames: 68407296. Throughput: 0: 9669.9. Samples: 68395984. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:45:00,829][613581] Avg episode reward: [(0, '4433.528')] [2023-03-09 04:45:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000133608_68407296.pth... [2023-03-09 04:45:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000133056_68124672.pth [2023-03-09 04:45:04,458][613885] Updated weights for policy 0, policy_version 133680 (0.0005) [2023-03-09 04:45:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9719.3). Total num frames: 68456448. Throughput: 0: 9593.4. Samples: 68453232. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 04:45:05,829][613581] Avg episode reward: [(0, '4529.768')] [2023-03-09 04:45:08,648][613885] Updated weights for policy 0, policy_version 133760 (0.0005) [2023-03-09 04:45:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9733.2). Total num frames: 68505600. Throughput: 0: 9545.8. Samples: 68482208. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:45:10,829][613581] Avg episode reward: [(0, '4512.358')] [2023-03-09 04:45:12,575][613885] Updated weights for policy 0, policy_version 133840 (0.0005) [2023-03-09 04:45:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9719.3). Total num frames: 68554752. Throughput: 0: 9559.2. Samples: 68542536. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:45:15,829][613581] Avg episode reward: [(0, '4496.466')] [2023-03-09 04:45:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000133896_68554752.pth... [2023-03-09 04:45:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000133336_68268032.pth [2023-03-09 04:45:16,767][613885] Updated weights for policy 0, policy_version 133920 (0.0005) [2023-03-09 04:45:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9705.4). Total num frames: 68603904. Throughput: 0: 9655.0. Samples: 68603796. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:45:20,840][613581] Avg episode reward: [(0, '4553.111')] [2023-03-09 04:45:20,903][613885] Updated weights for policy 0, policy_version 134000 (0.0004) [2023-03-09 04:45:25,231][613885] Updated weights for policy 0, policy_version 134080 (0.0005) [2023-03-09 04:45:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9719.3). Total num frames: 68653056. Throughput: 0: 9643.7. Samples: 68631864. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:45:25,840][613581] Avg episode reward: [(0, '4585.990')] [2023-03-09 04:45:29,302][613885] Updated weights for policy 0, policy_version 134160 (0.0005) [2023-03-09 04:45:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9719.3). Total num frames: 68702208. Throughput: 0: 9657.6. Samples: 68690336. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:45:30,840][613581] Avg episode reward: [(0, '4562.283')] [2023-03-09 04:45:30,843][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000134192_68706304.pth... [2023-03-09 04:45:30,845][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000133608_68407296.pth [2023-03-09 04:45:33,177][613885] Updated weights for policy 0, policy_version 134240 (0.0005) [2023-03-09 04:45:35,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9762.1, 300 sec: 9733.2). Total num frames: 68755456. Throughput: 0: 9779.5. Samples: 68751352. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:45:35,840][613581] Avg episode reward: [(0, '4544.949')] [2023-03-09 04:45:37,295][613885] Updated weights for policy 0, policy_version 134320 (0.0005) [2023-03-09 04:45:40,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9762.1, 300 sec: 9719.3). Total num frames: 68804608. Throughput: 0: 9823.6. Samples: 68783436. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:45:40,839][613581] Avg episode reward: [(0, '4486.977')] [2023-03-09 04:45:41,332][613885] Updated weights for policy 0, policy_version 134400 (0.0005) [2023-03-09 04:45:45,507][613885] Updated weights for policy 0, policy_version 134480 (0.0004) [2023-03-09 04:45:45,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.2, 300 sec: 9719.3). Total num frames: 68853760. Throughput: 0: 9904.2. Samples: 68841672. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:45:45,840][613581] Avg episode reward: [(0, '4534.731')] [2023-03-09 04:45:45,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000134480_68853760.pth... [2023-03-09 04:45:45,843][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000133896_68554752.pth [2023-03-09 04:45:49,544][613885] Updated weights for policy 0, policy_version 134560 (0.0005) [2023-03-09 04:45:50,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9719.3). Total num frames: 68902912. Throughput: 0: 9990.3. Samples: 68902796. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:45:50,829][613581] Avg episode reward: [(0, '4490.828')] [2023-03-09 04:45:53,613][613885] Updated weights for policy 0, policy_version 134640 (0.0005) [2023-03-09 04:45:55,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 9733.2). Total num frames: 68956160. Throughput: 0: 10029.3. Samples: 68933528. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:45:55,829][613581] Avg episode reward: [(0, '4568.002')] [2023-03-09 04:45:57,869][613885] Updated weights for policy 0, policy_version 134720 (0.0005) [2023-03-09 04:46:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9966.9, 300 sec: 9733.2). Total num frames: 69005312. Throughput: 0: 9992.4. Samples: 68992196. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:46:00,829][613581] Avg episode reward: [(0, '4512.760')] [2023-03-09 04:46:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000134776_69005312.pth... [2023-03-09 04:46:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000134192_68706304.pth [2023-03-09 04:46:01,993][613885] Updated weights for policy 0, policy_version 134800 (0.0005) [2023-03-09 04:46:05,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9898.7, 300 sec: 9719.3). Total num frames: 69050368. Throughput: 0: 9917.8. Samples: 69050096. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:46:05,829][613581] Avg episode reward: [(0, '4579.933')] [2023-03-09 04:46:06,317][613885] Updated weights for policy 0, policy_version 134880 (0.0005) [2023-03-09 04:46:10,262][613885] Updated weights for policy 0, policy_version 134960 (0.0004) [2023-03-09 04:46:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 9733.2). Total num frames: 69103616. Throughput: 0: 9937.2. Samples: 69079040. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:46:10,829][613581] Avg episode reward: [(0, '4544.795')] [2023-03-09 04:46:14,345][613885] Updated weights for policy 0, policy_version 135040 (0.0005) [2023-03-09 04:46:15,829][613581] Fps is (10 sec: 10239.8, 60 sec: 9966.9, 300 sec: 9747.1). Total num frames: 69152768. Throughput: 0: 10004.8. Samples: 69140552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:46:15,829][613581] Avg episode reward: [(0, '4541.756')] [2023-03-09 04:46:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000135064_69152768.pth... [2023-03-09 04:46:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000134480_68853760.pth [2023-03-09 04:46:18,467][613885] Updated weights for policy 0, policy_version 135120 (0.0003) [2023-03-09 04:46:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 9747.1). Total num frames: 69201920. Throughput: 0: 9921.8. Samples: 69197832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:46:20,829][613581] Avg episode reward: [(0, '4541.356')] [2023-03-09 04:46:22,725][613885] Updated weights for policy 0, policy_version 135200 (0.0005) [2023-03-09 04:46:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9966.9, 300 sec: 9747.1). Total num frames: 69251072. Throughput: 0: 9916.6. Samples: 69229684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:46:25,829][613581] Avg episode reward: [(0, '4541.454')] [2023-03-09 04:46:26,750][613885] Updated weights for policy 0, policy_version 135280 (0.0005) [2023-03-09 04:46:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 9747.1). Total num frames: 69300224. Throughput: 0: 9930.7. Samples: 69288556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:46:30,829][613581] Avg episode reward: [(0, '4388.510')] [2023-03-09 04:46:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000135352_69300224.pth... [2023-03-09 04:46:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000134776_69005312.pth [2023-03-09 04:46:30,924][613885] Updated weights for policy 0, policy_version 135360 (0.0005) [2023-03-09 04:46:35,219][613885] Updated weights for policy 0, policy_version 135440 (0.0005) [2023-03-09 04:46:35,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9898.7, 300 sec: 9747.1). Total num frames: 69349376. Throughput: 0: 9862.6. Samples: 69346616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:46:35,830][613581] Avg episode reward: [(0, '4319.457')] [2023-03-09 04:46:39,382][613885] Updated weights for policy 0, policy_version 135520 (0.0005) [2023-03-09 04:46:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9898.7, 300 sec: 9747.1). Total num frames: 69398528. Throughput: 0: 9839.7. Samples: 69376312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:46:40,829][613581] Avg episode reward: [(0, '3927.019')] [2023-03-09 04:46:43,617][613885] Updated weights for policy 0, policy_version 135600 (0.0004) [2023-03-09 04:46:45,829][613581] Fps is (10 sec: 9421.0, 60 sec: 9830.4, 300 sec: 9733.2). Total num frames: 69443584. Throughput: 0: 9845.9. Samples: 69435260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:46:45,829][613581] Avg episode reward: [(0, '4094.928')] [2023-03-09 04:46:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000135632_69443584.pth... [2023-03-09 04:46:45,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000135064_69152768.pth [2023-03-09 04:46:47,996][613885] Updated weights for policy 0, policy_version 135680 (0.0005) [2023-03-09 04:46:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9830.4, 300 sec: 9747.1). Total num frames: 69492736. Throughput: 0: 9823.5. Samples: 69492152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:46:50,829][613581] Avg episode reward: [(0, '4270.796')] [2023-03-09 04:46:52,124][613885] Updated weights for policy 0, policy_version 135760 (0.0005) [2023-03-09 04:46:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9830.4, 300 sec: 9761.0). Total num frames: 69545984. Throughput: 0: 9830.8. Samples: 69521424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:46:55,829][613581] Avg episode reward: [(0, '4483.970')] [2023-03-09 04:46:56,216][613885] Updated weights for policy 0, policy_version 135840 (0.0005) [2023-03-09 04:47:00,250][613885] Updated weights for policy 0, policy_version 135920 (0.0004) [2023-03-09 04:47:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9830.4, 300 sec: 9761.0). Total num frames: 69595136. Throughput: 0: 9812.1. Samples: 69582096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:47:00,829][613581] Avg episode reward: [(0, '4492.972')] [2023-03-09 04:47:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000135928_69595136.pth... [2023-03-09 04:47:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000135352_69300224.pth [2023-03-09 04:47:04,377][613885] Updated weights for policy 0, policy_version 136000 (0.0005) [2023-03-09 04:47:05,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9898.6, 300 sec: 9761.0). Total num frames: 69644288. Throughput: 0: 9870.7. Samples: 69642012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:47:05,829][613581] Avg episode reward: [(0, '4333.880')] [2023-03-09 04:47:08,414][613885] Updated weights for policy 0, policy_version 136080 (0.0005) [2023-03-09 04:47:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9761.0). Total num frames: 69693440. Throughput: 0: 9848.1. Samples: 69672848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:47:10,829][613581] Avg episode reward: [(0, '4530.256')] [2023-03-09 04:47:12,812][613885] Updated weights for policy 0, policy_version 136160 (0.0005) [2023-03-09 04:47:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9774.9). Total num frames: 69742592. Throughput: 0: 9766.8. Samples: 69728060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:47:15,829][613581] Avg episode reward: [(0, '4400.204')] [2023-03-09 04:47:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000136216_69742592.pth... [2023-03-09 04:47:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000135632_69443584.pth [2023-03-09 04:47:17,018][613885] Updated weights for policy 0, policy_version 136240 (0.0005) [2023-03-09 04:47:20,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9762.1, 300 sec: 9761.0). Total num frames: 69787648. Throughput: 0: 9742.7. Samples: 69785036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:47:20,829][613581] Avg episode reward: [(0, '4442.649')] [2023-03-09 04:47:21,450][613885] Updated weights for policy 0, policy_version 136320 (0.0005) [2023-03-09 04:47:25,756][613885] Updated weights for policy 0, policy_version 136400 (0.0004) [2023-03-09 04:47:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9761.0). Total num frames: 69836800. Throughput: 0: 9716.2. Samples: 69813540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:47:25,829][613581] Avg episode reward: [(0, '4269.497')] [2023-03-09 04:47:30,095][613885] Updated weights for policy 0, policy_version 136480 (0.0005) [2023-03-09 04:47:30,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9747.1). Total num frames: 69881856. Throughput: 0: 9673.2. Samples: 69870556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:47:30,829][613581] Avg episode reward: [(0, '4170.803')] [2023-03-09 04:47:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000136488_69881856.pth... [2023-03-09 04:47:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000135928_69595136.pth [2023-03-09 04:47:34,334][613885] Updated weights for policy 0, policy_version 136560 (0.0005) [2023-03-09 04:47:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9747.1). Total num frames: 69931008. Throughput: 0: 9704.7. Samples: 69928864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:47:35,829][613581] Avg episode reward: [(0, '4123.860')] [2023-03-09 04:47:38,688][613885] Updated weights for policy 0, policy_version 136640 (0.0004) [2023-03-09 04:47:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.8, 300 sec: 9747.1). Total num frames: 69980160. Throughput: 0: 9674.1. Samples: 69956760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:47:40,830][613581] Avg episode reward: [(0, '4170.657')] [2023-03-09 04:47:42,884][613885] Updated weights for policy 0, policy_version 136720 (0.0005) [2023-03-09 04:47:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.8, 300 sec: 9733.2). Total num frames: 70025216. Throughput: 0: 9614.2. Samples: 70014736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:47:45,829][613581] Avg episode reward: [(0, '4463.405')] [2023-03-09 04:47:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000136768_70025216.pth... [2023-03-09 04:47:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000136216_69742592.pth [2023-03-09 04:47:47,199][613885] Updated weights for policy 0, policy_version 136800 (0.0005) [2023-03-09 04:47:50,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9693.9, 300 sec: 9733.2). Total num frames: 70074368. Throughput: 0: 9579.2. Samples: 70073076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:47:50,829][613581] Avg episode reward: [(0, '4496.144')] [2023-03-09 04:47:51,388][613885] Updated weights for policy 0, policy_version 136880 (0.0005) [2023-03-09 04:47:55,688][613885] Updated weights for policy 0, policy_version 136960 (0.0005) [2023-03-09 04:47:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9733.2). Total num frames: 70123520. Throughput: 0: 9533.7. Samples: 70101864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:47:55,829][613581] Avg episode reward: [(0, '4604.169')] [2023-03-09 04:47:59,789][613885] Updated weights for policy 0, policy_version 137040 (0.0005) [2023-03-09 04:48:00,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9625.6, 300 sec: 9733.2). Total num frames: 70172672. Throughput: 0: 9606.4. Samples: 70160348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:48:00,830][613581] Avg episode reward: [(0, '4271.574')] [2023-03-09 04:48:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000137056_70172672.pth... [2023-03-09 04:48:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000136488_69881856.pth [2023-03-09 04:48:03,881][613885] Updated weights for policy 0, policy_version 137120 (0.0005) [2023-03-09 04:48:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9733.2). Total num frames: 70221824. Throughput: 0: 9692.7. Samples: 70221208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:48:05,829][613581] Avg episode reward: [(0, '4478.532')] [2023-03-09 04:48:08,015][613885] Updated weights for policy 0, policy_version 137200 (0.0004) [2023-03-09 04:48:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9625.6, 300 sec: 9747.1). Total num frames: 70270976. Throughput: 0: 9707.7. Samples: 70250388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:48:10,829][613581] Avg episode reward: [(0, '3888.292')] [2023-03-09 04:48:12,248][613885] Updated weights for policy 0, policy_version 137280 (0.0005) [2023-03-09 04:48:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9747.1). Total num frames: 70320128. Throughput: 0: 9717.2. Samples: 70307832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:48:15,829][613581] Avg episode reward: [(0, '3892.130')] [2023-03-09 04:48:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000137344_70320128.pth... [2023-03-09 04:48:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000136768_70025216.pth [2023-03-09 04:48:16,560][613885] Updated weights for policy 0, policy_version 137360 (0.0005) [2023-03-09 04:48:20,532][613885] Updated weights for policy 0, policy_version 137440 (0.0005) [2023-03-09 04:48:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9761.0). Total num frames: 70369280. Throughput: 0: 9759.7. Samples: 70368048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:48:20,829][613581] Avg episode reward: [(0, '4308.767')] [2023-03-09 04:48:24,955][613885] Updated weights for policy 0, policy_version 137520 (0.0005) [2023-03-09 04:48:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9761.0). Total num frames: 70418432. Throughput: 0: 9763.6. Samples: 70396124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:48:25,829][613581] Avg episode reward: [(0, '4433.615')] [2023-03-09 04:48:29,102][613885] Updated weights for policy 0, policy_version 137600 (0.0005) [2023-03-09 04:48:30,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9774.9). Total num frames: 70467584. Throughput: 0: 9766.2. Samples: 70454216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:48:30,829][613581] Avg episode reward: [(0, '4456.479')] [2023-03-09 04:48:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000137632_70467584.pth... [2023-03-09 04:48:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000137056_70172672.pth [2023-03-09 04:48:33,285][613885] Updated weights for policy 0, policy_version 137680 (0.0005) [2023-03-09 04:48:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9774.9). Total num frames: 70516736. Throughput: 0: 9769.7. Samples: 70512712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:48:35,829][613581] Avg episode reward: [(0, '4469.386')] [2023-03-09 04:48:37,125][613885] Updated weights for policy 0, policy_version 137760 (0.0005) [2023-03-09 04:48:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9830.4, 300 sec: 9788.7). Total num frames: 70569984. Throughput: 0: 9918.8. Samples: 70548212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:48:40,829][613581] Avg episode reward: [(0, '4468.591')] [2023-03-09 04:48:40,994][613885] Updated weights for policy 0, policy_version 137840 (0.0004) [2023-03-09 04:48:45,294][613885] Updated weights for policy 0, policy_version 137920 (0.0005) [2023-03-09 04:48:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9898.7, 300 sec: 9788.7). Total num frames: 70619136. Throughput: 0: 9922.4. Samples: 70606856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:48:45,829][613581] Avg episode reward: [(0, '4416.559')] [2023-03-09 04:48:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000137928_70619136.pth... [2023-03-09 04:48:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000137344_70320128.pth [2023-03-09 04:48:49,635][613885] Updated weights for policy 0, policy_version 138000 (0.0005) [2023-03-09 04:48:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9802.6). Total num frames: 70668288. Throughput: 0: 9829.6. Samples: 70663540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:48:50,829][613581] Avg episode reward: [(0, '4562.560')] [2023-03-09 04:48:53,665][613885] Updated weights for policy 0, policy_version 138080 (0.0005) [2023-03-09 04:48:55,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9898.7, 300 sec: 9788.7). Total num frames: 70717440. Throughput: 0: 9836.1. Samples: 70693012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:48:55,830][613581] Avg episode reward: [(0, '4583.109')] [2023-03-09 04:48:57,669][613885] Updated weights for policy 0, policy_version 138160 (0.0005) [2023-03-09 04:49:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9967.0, 300 sec: 9816.5). Total num frames: 70770688. Throughput: 0: 9970.9. Samples: 70756520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:49:00,829][613581] Avg episode reward: [(0, '4563.070')] [2023-03-09 04:49:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000138224_70770688.pth... [2023-03-09 04:49:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000137632_70467584.pth [2023-03-09 04:49:01,437][613885] Updated weights for policy 0, policy_version 138240 (0.0005) [2023-03-09 04:49:05,614][613885] Updated weights for policy 0, policy_version 138320 (0.0004) [2023-03-09 04:49:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 9816.5). Total num frames: 70819840. Throughput: 0: 10002.1. Samples: 70818144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:49:05,829][613581] Avg episode reward: [(0, '4595.780')] [2023-03-09 04:49:09,771][613885] Updated weights for policy 0, policy_version 138400 (0.0005) [2023-03-09 04:49:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 9816.5). Total num frames: 70868992. Throughput: 0: 10025.6. Samples: 70847276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:49:10,829][613581] Avg episode reward: [(0, '4578.694')] [2023-03-09 04:49:14,075][613885] Updated weights for policy 0, policy_version 138480 (0.0005) [2023-03-09 04:49:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9898.7, 300 sec: 9802.6). Total num frames: 70914048. Throughput: 0: 10023.2. Samples: 70905260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:49:15,829][613581] Avg episode reward: [(0, '4517.564')] [2023-03-09 04:49:15,872][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000138512_70918144.pth... [2023-03-09 04:49:15,874][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000137928_70619136.pth [2023-03-09 04:49:18,641][613885] Updated weights for policy 0, policy_version 138560 (0.0005) [2023-03-09 04:49:20,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9830.4, 300 sec: 9774.9). Total num frames: 70959104. Throughput: 0: 9911.8. Samples: 70958744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:49:20,829][613581] Avg episode reward: [(0, '4492.146')] [2023-03-09 04:49:23,064][613885] Updated weights for policy 0, policy_version 138640 (0.0005) [2023-03-09 04:49:25,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9762.2, 300 sec: 9761.0). Total num frames: 71004160. Throughput: 0: 9755.2. Samples: 70987196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:49:25,829][613581] Avg episode reward: [(0, '4466.637')] [2023-03-09 04:49:27,479][613885] Updated weights for policy 0, policy_version 138720 (0.0005) [2023-03-09 04:49:30,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9762.1, 300 sec: 9774.9). Total num frames: 71053312. Throughput: 0: 9697.9. Samples: 71043264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:49:30,829][613581] Avg episode reward: [(0, '4533.179')] [2023-03-09 04:49:30,847][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000138784_71057408.pth... [2023-03-09 04:49:30,848][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000138224_70770688.pth [2023-03-09 04:49:31,742][613885] Updated weights for policy 0, policy_version 138800 (0.0005) [2023-03-09 04:49:35,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9774.9). Total num frames: 71102464. Throughput: 0: 9713.4. Samples: 71100644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:49:35,829][613581] Avg episode reward: [(0, '4604.608')] [2023-03-09 04:49:36,006][613885] Updated weights for policy 0, policy_version 138880 (0.0004) [2023-03-09 04:49:40,593][613885] Updated weights for policy 0, policy_version 138960 (0.0005) [2023-03-09 04:49:40,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9761.0). Total num frames: 71147520. Throughput: 0: 9648.4. Samples: 71127192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:49:40,829][613581] Avg episode reward: [(0, '4530.144')] [2023-03-09 04:49:44,990][613885] Updated weights for policy 0, policy_version 139040 (0.0005) [2023-03-09 04:49:45,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9557.3, 300 sec: 9761.0). Total num frames: 71192576. Throughput: 0: 9465.4. Samples: 71182464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:49:45,829][613581] Avg episode reward: [(0, '4629.367')] [2023-03-09 04:49:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000139048_71192576.pth... [2023-03-09 04:49:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000138512_70918144.pth [2023-03-09 04:49:45,834][613841] Saving new best policy, reward=4629.367! [2023-03-09 04:49:49,284][613885] Updated weights for policy 0, policy_version 139120 (0.0005) [2023-03-09 04:49:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9761.0). Total num frames: 71241728. Throughput: 0: 9402.6. Samples: 71241260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:49:50,829][613581] Avg episode reward: [(0, '4468.071')] [2023-03-09 04:49:53,433][613885] Updated weights for policy 0, policy_version 139200 (0.0005) [2023-03-09 04:49:55,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9557.3, 300 sec: 9774.9). Total num frames: 71290880. Throughput: 0: 9397.2. Samples: 71270152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:49:55,829][613581] Avg episode reward: [(0, '4577.401')] [2023-03-09 04:49:57,811][613885] Updated weights for policy 0, policy_version 139280 (0.0005) [2023-03-09 04:50:00,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9420.8, 300 sec: 9761.0). Total num frames: 71335936. Throughput: 0: 9321.9. Samples: 71324748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:50:00,829][613581] Avg episode reward: [(0, '4559.732')] [2023-03-09 04:50:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000139328_71335936.pth... [2023-03-09 04:50:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000138784_71057408.pth [2023-03-09 04:50:02,334][613885] Updated weights for policy 0, policy_version 139360 (0.0004) [2023-03-09 04:50:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9761.0). Total num frames: 71385088. Throughput: 0: 9404.2. Samples: 71381936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:50:05,830][613581] Avg episode reward: [(0, '4578.864')] [2023-03-09 04:50:06,557][613885] Updated weights for policy 0, policy_version 139440 (0.0004) [2023-03-09 04:50:10,505][613885] Updated weights for policy 0, policy_version 139520 (0.0004) [2023-03-09 04:50:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9420.8, 300 sec: 9761.0). Total num frames: 71434240. Throughput: 0: 9438.4. Samples: 71411924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:50:10,829][613581] Avg episode reward: [(0, '4589.770')] [2023-03-09 04:50:15,130][613885] Updated weights for policy 0, policy_version 139600 (0.0004) [2023-03-09 04:50:15,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9420.8, 300 sec: 9747.1). Total num frames: 71479296. Throughput: 0: 9434.9. Samples: 71467832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:50:15,829][613581] Avg episode reward: [(0, '4518.000')] [2023-03-09 04:50:15,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000139608_71479296.pth... [2023-03-09 04:50:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000139048_71192576.pth [2023-03-09 04:50:19,224][613885] Updated weights for policy 0, policy_version 139680 (0.0005) [2023-03-09 04:50:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9557.3, 300 sec: 9761.0). Total num frames: 71532544. Throughput: 0: 9506.8. Samples: 71528448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:50:20,829][613581] Avg episode reward: [(0, '4544.808')] [2023-03-09 04:50:23,377][613885] Updated weights for policy 0, policy_version 139760 (0.0005) [2023-03-09 04:50:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9625.6, 300 sec: 9761.0). Total num frames: 71581696. Throughput: 0: 9554.2. Samples: 71557132. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:50:25,829][613581] Avg episode reward: [(0, '4568.255')] [2023-03-09 04:50:27,549][613885] Updated weights for policy 0, policy_version 139840 (0.0005) [2023-03-09 04:50:30,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9733.2). Total num frames: 71626752. Throughput: 0: 9637.1. Samples: 71616136. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:50:30,829][613581] Avg episode reward: [(0, '4558.193')] [2023-03-09 04:50:30,860][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000139904_71630848.pth... [2023-03-09 04:50:30,861][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000139328_71335936.pth [2023-03-09 04:50:31,726][613885] Updated weights for policy 0, policy_version 139920 (0.0004) [2023-03-09 04:50:35,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9557.3, 300 sec: 9733.2). Total num frames: 71675904. Throughput: 0: 9626.6. Samples: 71674456. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:50:35,830][613581] Avg episode reward: [(0, '4565.329')] [2023-03-09 04:50:36,037][613885] Updated weights for policy 0, policy_version 140000 (0.0004) [2023-03-09 04:50:40,267][613885] Updated weights for policy 0, policy_version 140080 (0.0005) [2023-03-09 04:50:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9625.6, 300 sec: 9733.2). Total num frames: 71725056. Throughput: 0: 9596.2. Samples: 71701980. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:50:40,829][613581] Avg episode reward: [(0, '4418.986')] [2023-03-09 04:50:44,521][613885] Updated weights for policy 0, policy_version 140160 (0.0005) [2023-03-09 04:50:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9733.2). Total num frames: 71774208. Throughput: 0: 9704.7. Samples: 71761460. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:50:45,829][613581] Avg episode reward: [(0, '4381.555')] [2023-03-09 04:50:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000140184_71774208.pth... [2023-03-09 04:50:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000139608_71479296.pth [2023-03-09 04:50:48,646][613885] Updated weights for policy 0, policy_version 140240 (0.0004) [2023-03-09 04:50:50,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9719.3). Total num frames: 71823360. Throughput: 0: 9734.5. Samples: 71819988. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:50:50,829][613581] Avg episode reward: [(0, '4401.075')] [2023-03-09 04:50:52,872][613885] Updated weights for policy 0, policy_version 140320 (0.0004) [2023-03-09 04:50:55,215][613841] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000005 [2023-03-09 04:50:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9705.4). Total num frames: 71868416. Throughput: 0: 9690.7. Samples: 71848008. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:50:55,829][613581] Avg episode reward: [(0, '4542.820')] [2023-03-09 04:50:57,407][613885] Updated weights for policy 0, policy_version 140400 (0.0005) [2023-03-09 04:51:00,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9693.9, 300 sec: 9719.3). Total num frames: 71917568. Throughput: 0: 9718.5. Samples: 71905164. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:51:00,829][613581] Avg episode reward: [(0, '4613.405')] [2023-03-09 04:51:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000140464_71917568.pth... [2023-03-09 04:51:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000139904_71630848.pth [2023-03-09 04:51:01,375][613885] Updated weights for policy 0, policy_version 140480 (0.0005) [2023-03-09 04:51:05,559][613885] Updated weights for policy 0, policy_version 140560 (0.0005) [2023-03-09 04:51:05,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9705.4). Total num frames: 71966720. Throughput: 0: 9714.0. Samples: 71965576. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:51:05,829][613581] Avg episode reward: [(0, '4584.474')] [2023-03-09 04:51:09,810][613885] Updated weights for policy 0, policy_version 140640 (0.0004) [2023-03-09 04:51:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9705.4). Total num frames: 72015872. Throughput: 0: 9738.2. Samples: 71995352. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:51:10,829][613581] Avg episode reward: [(0, '4567.550')] [2023-03-09 04:51:14,002][613885] Updated weights for policy 0, policy_version 140720 (0.0005) [2023-03-09 04:51:15,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9693.9, 300 sec: 9691.6). Total num frames: 72060928. Throughput: 0: 9700.4. Samples: 72052652. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:51:15,829][613581] Avg episode reward: [(0, '4549.566')] [2023-03-09 04:51:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000140752_72065024.pth... [2023-03-09 04:51:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000140184_71774208.pth [2023-03-09 04:51:18,220][613885] Updated weights for policy 0, policy_version 140800 (0.0005) [2023-03-09 04:51:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9705.4). Total num frames: 72114176. Throughput: 0: 9730.0. Samples: 72112308. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 04:51:20,829][613581] Avg episode reward: [(0, '4529.876')] [2023-03-09 04:51:22,266][613885] Updated weights for policy 0, policy_version 140880 (0.0004) [2023-03-09 04:51:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9693.8, 300 sec: 9705.4). Total num frames: 72163328. Throughput: 0: 9759.9. Samples: 72141176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:51:25,829][613581] Avg episode reward: [(0, '4580.381')] [2023-03-09 04:51:26,662][613885] Updated weights for policy 0, policy_version 140960 (0.0005) [2023-03-09 04:51:30,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9691.6). Total num frames: 72208384. Throughput: 0: 9745.6. Samples: 72200012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:51:30,829][613581] Avg episode reward: [(0, '4611.252')] [2023-03-09 04:51:30,885][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000141040_72212480.pth... [2023-03-09 04:51:30,886][613885] Updated weights for policy 0, policy_version 141040 (0.0005) [2023-03-09 04:51:30,886][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000140464_71917568.pth [2023-03-09 04:51:35,168][613885] Updated weights for policy 0, policy_version 141120 (0.0005) [2023-03-09 04:51:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9691.5). Total num frames: 72257536. Throughput: 0: 9683.7. Samples: 72255756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:51:35,829][613581] Avg episode reward: [(0, '4583.163')] [2023-03-09 04:51:39,808][613885] Updated weights for policy 0, policy_version 141200 (0.0006) [2023-03-09 04:51:40,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9691.5). Total num frames: 72302592. Throughput: 0: 9646.7. Samples: 72282112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:51:40,830][613581] Avg episode reward: [(0, '4473.817')] [2023-03-09 04:51:44,110][613885] Updated weights for policy 0, policy_version 141280 (0.0004) [2023-03-09 04:51:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9691.6). Total num frames: 72351744. Throughput: 0: 9622.8. Samples: 72338188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:51:45,829][613581] Avg episode reward: [(0, '4400.420')] [2023-03-09 04:51:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000141312_72351744.pth... [2023-03-09 04:51:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000140752_72065024.pth [2023-03-09 04:51:48,287][613885] Updated weights for policy 0, policy_version 141360 (0.0004) [2023-03-09 04:51:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9677.7). Total num frames: 72400896. Throughput: 0: 9623.1. Samples: 72398616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:51:50,829][613581] Avg episode reward: [(0, '4590.948')] [2023-03-09 04:51:52,322][613885] Updated weights for policy 0, policy_version 141440 (0.0005) [2023-03-09 04:51:55,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9625.6, 300 sec: 9663.8). Total num frames: 72445952. Throughput: 0: 9588.6. Samples: 72426840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:51:55,829][613581] Avg episode reward: [(0, '4591.569')] [2023-03-09 04:51:56,933][613885] Updated weights for policy 0, policy_version 141520 (0.0005) [2023-03-09 04:52:00,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9557.3, 300 sec: 9649.9). Total num frames: 72491008. Throughput: 0: 9498.4. Samples: 72480080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:52:00,829][613581] Avg episode reward: [(0, '4614.797')] [2023-03-09 04:52:00,865][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000141592_72495104.pth... [2023-03-09 04:52:00,867][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000141040_72212480.pth [2023-03-09 04:52:01,332][613885] Updated weights for policy 0, policy_version 141600 (0.0004) [2023-03-09 04:52:05,646][613885] Updated weights for policy 0, policy_version 141680 (0.0005) [2023-03-09 04:52:05,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9557.3, 300 sec: 9649.9). Total num frames: 72540160. Throughput: 0: 9426.0. Samples: 72536480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:52:05,829][613581] Avg episode reward: [(0, '4601.001')] [2023-03-09 04:52:09,880][613885] Updated weights for policy 0, policy_version 141760 (0.0005) [2023-03-09 04:52:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9557.4, 300 sec: 9649.9). Total num frames: 72589312. Throughput: 0: 9426.6. Samples: 72565372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:52:10,829][613581] Avg episode reward: [(0, '4582.730')] [2023-03-09 04:52:13,931][613885] Updated weights for policy 0, policy_version 141840 (0.0004) [2023-03-09 04:52:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9663.8). Total num frames: 72638464. Throughput: 0: 9471.7. Samples: 72626240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:52:15,829][613581] Avg episode reward: [(0, '4589.316')] [2023-03-09 04:52:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000141872_72638464.pth... [2023-03-09 04:52:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000141312_72351744.pth [2023-03-09 04:52:18,097][613885] Updated weights for policy 0, policy_version 141920 (0.0005) [2023-03-09 04:52:20,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9489.1, 300 sec: 9649.9). Total num frames: 72683520. Throughput: 0: 9505.7. Samples: 72683512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:52:20,829][613581] Avg episode reward: [(0, '4439.235')] [2023-03-09 04:52:22,575][613885] Updated weights for policy 0, policy_version 142000 (0.0005) [2023-03-09 04:52:25,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9489.1, 300 sec: 9663.8). Total num frames: 72732672. Throughput: 0: 9552.3. Samples: 72711964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:52:25,829][613581] Avg episode reward: [(0, '4550.804')] [2023-03-09 04:52:26,932][613885] Updated weights for policy 0, policy_version 142080 (0.0005) [2023-03-09 04:52:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9663.8). Total num frames: 72781824. Throughput: 0: 9625.9. Samples: 72771352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:52:30,829][613581] Avg episode reward: [(0, '4273.534')] [2023-03-09 04:52:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000142152_72781824.pth... [2023-03-09 04:52:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000141592_72495104.pth [2023-03-09 04:52:30,960][613885] Updated weights for policy 0, policy_version 142160 (0.0004) [2023-03-09 04:52:35,164][613885] Updated weights for policy 0, policy_version 142240 (0.0004) [2023-03-09 04:52:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9663.8). Total num frames: 72830976. Throughput: 0: 9569.9. Samples: 72829260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:52:35,829][613581] Avg episode reward: [(0, '4378.672')] [2023-03-09 04:52:38,986][613885] Updated weights for policy 0, policy_version 142320 (0.0005) [2023-03-09 04:52:40,829][613581] Fps is (10 sec: 10240.1, 60 sec: 9693.9, 300 sec: 9691.6). Total num frames: 72884224. Throughput: 0: 9681.4. Samples: 72862504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:52:40,829][613581] Avg episode reward: [(0, '4493.859')] [2023-03-09 04:52:43,291][613885] Updated weights for policy 0, policy_version 142400 (0.0004) [2023-03-09 04:52:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9677.7). Total num frames: 72929280. Throughput: 0: 9774.7. Samples: 72919940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:52:45,829][613581] Avg episode reward: [(0, '4441.060')] [2023-03-09 04:52:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000142440_72929280.pth... [2023-03-09 04:52:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000141872_72638464.pth [2023-03-09 04:52:47,765][613885] Updated weights for policy 0, policy_version 142480 (0.0005) [2023-03-09 04:52:50,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9625.6, 300 sec: 9677.7). Total num frames: 72978432. Throughput: 0: 9736.6. Samples: 72974628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:52:50,830][613581] Avg episode reward: [(0, '4514.104')] [2023-03-09 04:52:52,042][613885] Updated weights for policy 0, policy_version 142560 (0.0005) [2023-03-09 04:52:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9663.8). Total num frames: 73023488. Throughput: 0: 9754.9. Samples: 73004344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:52:55,829][613581] Avg episode reward: [(0, '4567.663')] [2023-03-09 04:52:56,186][613885] Updated weights for policy 0, policy_version 142640 (0.0004) [2023-03-09 04:53:00,289][613885] Updated weights for policy 0, policy_version 142720 (0.0005) [2023-03-09 04:53:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9677.7). Total num frames: 73076736. Throughput: 0: 9739.4. Samples: 73064512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:53:00,829][613581] Avg episode reward: [(0, '4509.228')] [2023-03-09 04:53:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000142728_73076736.pth... [2023-03-09 04:53:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000142152_72781824.pth [2023-03-09 04:53:04,717][613885] Updated weights for policy 0, policy_version 142800 (0.0004) [2023-03-09 04:53:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9663.8). Total num frames: 73121792. Throughput: 0: 9734.2. Samples: 73121552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:53:05,829][613581] Avg episode reward: [(0, '4503.001')] [2023-03-09 04:53:08,876][613885] Updated weights for policy 0, policy_version 142880 (0.0004) [2023-03-09 04:53:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9663.8). Total num frames: 73170944. Throughput: 0: 9731.2. Samples: 73149868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:53:10,829][613581] Avg episode reward: [(0, '4468.275')] [2023-03-09 04:53:13,386][613885] Updated weights for policy 0, policy_version 142960 (0.0004) [2023-03-09 04:53:15,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9625.6, 300 sec: 9649.9). Total num frames: 73216000. Throughput: 0: 9629.7. Samples: 73204688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:53:15,829][613581] Avg episode reward: [(0, '4506.553')] [2023-03-09 04:53:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000143000_73216000.pth... [2023-03-09 04:53:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000142440_72929280.pth [2023-03-09 04:53:17,742][613885] Updated weights for policy 0, policy_version 143040 (0.0004) [2023-03-09 04:53:20,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9625.6, 300 sec: 9636.0). Total num frames: 73261056. Throughput: 0: 9596.9. Samples: 73261120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:53:20,830][613581] Avg episode reward: [(0, '4515.750')] [2023-03-09 04:53:22,238][613885] Updated weights for policy 0, policy_version 143120 (0.0005) [2023-03-09 04:53:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9649.9). Total num frames: 73314304. Throughput: 0: 9491.2. Samples: 73289608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:53:25,829][613581] Avg episode reward: [(0, '4576.082')] [2023-03-09 04:53:26,131][613885] Updated weights for policy 0, policy_version 143200 (0.0006) [2023-03-09 04:53:30,330][613885] Updated weights for policy 0, policy_version 143280 (0.0006) [2023-03-09 04:53:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9693.9, 300 sec: 9649.9). Total num frames: 73363456. Throughput: 0: 9579.5. Samples: 73351016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:53:30,829][613581] Avg episode reward: [(0, '4553.852')] [2023-03-09 04:53:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000143288_73363456.pth... [2023-03-09 04:53:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000142728_73076736.pth [2023-03-09 04:53:34,589][613885] Updated weights for policy 0, policy_version 143360 (0.0005) [2023-03-09 04:53:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9636.0). Total num frames: 73412608. Throughput: 0: 9640.6. Samples: 73408456. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:53:35,829][613581] Avg episode reward: [(0, '4588.597')] [2023-03-09 04:53:38,582][613885] Updated weights for policy 0, policy_version 143440 (0.0005) [2023-03-09 04:53:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9636.0). Total num frames: 73461760. Throughput: 0: 9644.5. Samples: 73438348. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:53:40,829][613581] Avg episode reward: [(0, '4446.755')] [2023-03-09 04:53:43,062][613885] Updated weights for policy 0, policy_version 143520 (0.0005) [2023-03-09 04:53:45,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9625.6, 300 sec: 9622.1). Total num frames: 73506816. Throughput: 0: 9555.4. Samples: 73494504. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:53:45,829][613581] Avg episode reward: [(0, '4537.611')] [2023-03-09 04:53:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000143568_73506816.pth... [2023-03-09 04:53:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000143000_73216000.pth [2023-03-09 04:53:47,319][613885] Updated weights for policy 0, policy_version 143600 (0.0005) [2023-03-09 04:53:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9622.1). Total num frames: 73555968. Throughput: 0: 9556.6. Samples: 73551600. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:53:50,829][613581] Avg episode reward: [(0, '4581.831')] [2023-03-09 04:53:51,586][613885] Updated weights for policy 0, policy_version 143680 (0.0004) [2023-03-09 04:53:55,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9625.6, 300 sec: 9594.4). Total num frames: 73601024. Throughput: 0: 9583.7. Samples: 73581136. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:53:55,829][613581] Avg episode reward: [(0, '4578.479')] [2023-03-09 04:53:56,055][613885] Updated weights for policy 0, policy_version 143760 (0.0004) [2023-03-09 04:54:00,352][613885] Updated weights for policy 0, policy_version 143840 (0.0005) [2023-03-09 04:54:00,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9594.4). Total num frames: 73650176. Throughput: 0: 9623.2. Samples: 73637732. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:54:00,829][613581] Avg episode reward: [(0, '4595.632')] [2023-03-09 04:54:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000143848_73650176.pth... [2023-03-09 04:54:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000143288_73363456.pth [2023-03-09 04:54:04,727][613885] Updated weights for policy 0, policy_version 143920 (0.0004) [2023-03-09 04:54:05,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9557.3, 300 sec: 9580.5). Total num frames: 73695232. Throughput: 0: 9623.7. Samples: 73694184. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:54:05,829][613581] Avg episode reward: [(0, '4518.394')] [2023-03-09 04:54:08,821][613885] Updated weights for policy 0, policy_version 144000 (0.0005) [2023-03-09 04:54:10,829][613581] Fps is (10 sec: 9421.0, 60 sec: 9557.3, 300 sec: 9594.4). Total num frames: 73744384. Throughput: 0: 9651.0. Samples: 73723904. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:54:10,829][613581] Avg episode reward: [(0, '4496.538')] [2023-03-09 04:54:13,124][613885] Updated weights for policy 0, policy_version 144080 (0.0005) [2023-03-09 04:54:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9608.2). Total num frames: 73793536. Throughput: 0: 9559.8. Samples: 73781208. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:54:15,829][613581] Avg episode reward: [(0, '4551.523')] [2023-03-09 04:54:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000144128_73793536.pth... [2023-03-09 04:54:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000143568_73506816.pth [2023-03-09 04:54:17,465][613885] Updated weights for policy 0, policy_version 144160 (0.0005) [2023-03-09 04:54:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9608.2). Total num frames: 73838592. Throughput: 0: 9525.6. Samples: 73837108. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:54:20,829][613581] Avg episode reward: [(0, '4465.167')] [2023-03-09 04:54:21,850][613885] Updated weights for policy 0, policy_version 144240 (0.0005) [2023-03-09 04:54:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9608.2). Total num frames: 73887744. Throughput: 0: 9528.0. Samples: 73867108. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:54:25,829][613581] Avg episode reward: [(0, '4437.194')] [2023-03-09 04:54:26,021][613885] Updated weights for policy 0, policy_version 144320 (0.0005) [2023-03-09 04:54:29,880][613885] Updated weights for policy 0, policy_version 144400 (0.0005) [2023-03-09 04:54:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9625.6, 300 sec: 9622.1). Total num frames: 73940992. Throughput: 0: 9622.1. Samples: 73927496. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 04:54:30,829][613581] Avg episode reward: [(0, '4393.506')] [2023-03-09 04:54:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000144416_73940992.pth... [2023-03-09 04:54:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000143848_73650176.pth [2023-03-09 04:54:34,064][613885] Updated weights for policy 0, policy_version 144480 (0.0005) [2023-03-09 04:54:35,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9557.3, 300 sec: 9622.1). Total num frames: 73986048. Throughput: 0: 9655.8. Samples: 73986112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:54:35,829][613581] Avg episode reward: [(0, '4546.561')] [2023-03-09 04:54:38,337][613885] Updated weights for policy 0, policy_version 144560 (0.0005) [2023-03-09 04:54:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9649.9). Total num frames: 74039296. Throughput: 0: 9636.8. Samples: 74014792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:54:40,829][613581] Avg episode reward: [(0, '4577.772')] [2023-03-09 04:54:42,459][613885] Updated weights for policy 0, policy_version 144640 (0.0005) [2023-03-09 04:54:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9636.0). Total num frames: 74084352. Throughput: 0: 9664.6. Samples: 74072636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:54:45,829][613581] Avg episode reward: [(0, '4596.035')] [2023-03-09 04:54:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000144696_74084352.pth... [2023-03-09 04:54:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000144128_73793536.pth [2023-03-09 04:54:46,803][613885] Updated weights for policy 0, policy_version 144720 (0.0005) [2023-03-09 04:54:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9636.0). Total num frames: 74133504. Throughput: 0: 9698.1. Samples: 74130600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:54:50,829][613581] Avg episode reward: [(0, '4558.016')] [2023-03-09 04:54:51,090][613885] Updated weights for policy 0, policy_version 144800 (0.0004) [2023-03-09 04:54:55,334][613885] Updated weights for policy 0, policy_version 144880 (0.0005) [2023-03-09 04:54:55,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9649.9). Total num frames: 74182656. Throughput: 0: 9679.3. Samples: 74159476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:54:55,830][613581] Avg episode reward: [(0, '4521.557')] [2023-03-09 04:54:59,675][613885] Updated weights for policy 0, policy_version 144960 (0.0004) [2023-03-09 04:55:00,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9636.0). Total num frames: 74227712. Throughput: 0: 9674.1. Samples: 74216544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:55:00,829][613581] Avg episode reward: [(0, '4548.912')] [2023-03-09 04:55:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000144976_74227712.pth... [2023-03-09 04:55:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000144416_73940992.pth [2023-03-09 04:55:03,834][613885] Updated weights for policy 0, policy_version 145040 (0.0005) [2023-03-09 04:55:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9649.9). Total num frames: 74280960. Throughput: 0: 9774.2. Samples: 74276948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:55:05,829][613581] Avg episode reward: [(0, '4499.609')] [2023-03-09 04:55:07,891][613885] Updated weights for policy 0, policy_version 145120 (0.0005) [2023-03-09 04:55:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9649.9). Total num frames: 74326016. Throughput: 0: 9749.4. Samples: 74305828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:55:10,829][613581] Avg episode reward: [(0, '4569.354')] [2023-03-09 04:55:12,199][613885] Updated weights for policy 0, policy_version 145200 (0.0005) [2023-03-09 04:55:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9636.0). Total num frames: 74375168. Throughput: 0: 9673.3. Samples: 74362796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:55:15,829][613581] Avg episode reward: [(0, '4590.554')] [2023-03-09 04:55:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000145264_74375168.pth... [2023-03-09 04:55:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000144696_74084352.pth [2023-03-09 04:55:16,613][613885] Updated weights for policy 0, policy_version 145280 (0.0005) [2023-03-09 04:55:20,775][613885] Updated weights for policy 0, policy_version 145360 (0.0005) [2023-03-09 04:55:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9636.0). Total num frames: 74424320. Throughput: 0: 9651.8. Samples: 74420444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:55:20,830][613581] Avg episode reward: [(0, '4576.151')] [2023-03-09 04:55:24,956][613885] Updated weights for policy 0, policy_version 145440 (0.0005) [2023-03-09 04:55:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.1, 300 sec: 9649.9). Total num frames: 74473472. Throughput: 0: 9666.8. Samples: 74449800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:55:25,829][613581] Avg episode reward: [(0, '4619.441')] [2023-03-09 04:55:29,394][613885] Updated weights for policy 0, policy_version 145520 (0.0005) [2023-03-09 04:55:30,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9636.0). Total num frames: 74518528. Throughput: 0: 9635.8. Samples: 74506248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:55:30,829][613581] Avg episode reward: [(0, '4584.388')] [2023-03-09 04:55:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000145544_74518528.pth... [2023-03-09 04:55:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000144976_74227712.pth [2023-03-09 04:55:33,604][613885] Updated weights for policy 0, policy_version 145600 (0.0005) [2023-03-09 04:55:35,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9625.6, 300 sec: 9622.1). Total num frames: 74563584. Throughput: 0: 9619.0. Samples: 74563452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:55:35,829][613581] Avg episode reward: [(0, '4586.191')] [2023-03-09 04:55:37,950][613885] Updated weights for policy 0, policy_version 145680 (0.0004) [2023-03-09 04:55:40,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9557.3, 300 sec: 9622.1). Total num frames: 74612736. Throughput: 0: 9617.5. Samples: 74592264. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:55:40,829][613581] Avg episode reward: [(0, '4469.683')] [2023-03-09 04:55:42,133][613885] Updated weights for policy 0, policy_version 145760 (0.0005) [2023-03-09 04:55:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9622.1). Total num frames: 74661888. Throughput: 0: 9647.7. Samples: 74650692. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:55:45,829][613581] Avg episode reward: [(0, '4585.474')] [2023-03-09 04:55:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000145824_74661888.pth... [2023-03-09 04:55:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000145264_74375168.pth [2023-03-09 04:55:46,468][613885] Updated weights for policy 0, policy_version 145840 (0.0005) [2023-03-09 04:55:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9622.1). Total num frames: 74706944. Throughput: 0: 9555.0. Samples: 74706924. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:55:50,829][613581] Avg episode reward: [(0, '4584.118')] [2023-03-09 04:55:50,856][613885] Updated weights for policy 0, policy_version 145920 (0.0005) [2023-03-09 04:55:54,868][613885] Updated weights for policy 0, policy_version 146000 (0.0004) [2023-03-09 04:55:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9636.0). Total num frames: 74760192. Throughput: 0: 9552.6. Samples: 74735696. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:55:55,830][613581] Avg episode reward: [(0, '4456.712')] [2023-03-09 04:55:58,880][613885] Updated weights for policy 0, policy_version 146080 (0.0005) [2023-03-09 04:56:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 9762.1, 300 sec: 9649.9). Total num frames: 74813440. Throughput: 0: 9680.0. Samples: 74798396. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:56:00,829][613581] Avg episode reward: [(0, '4512.995')] [2023-03-09 04:56:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000146120_74813440.pth... [2023-03-09 04:56:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000145544_74518528.pth [2023-03-09 04:56:02,874][613885] Updated weights for policy 0, policy_version 146160 (0.0005) [2023-03-09 04:56:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9693.9, 300 sec: 9649.9). Total num frames: 74862592. Throughput: 0: 9765.0. Samples: 74859868. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:56:05,829][613581] Avg episode reward: [(0, '4362.341')] [2023-03-09 04:56:06,882][613885] Updated weights for policy 0, policy_version 146240 (0.0005) [2023-03-09 04:56:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.1, 300 sec: 9663.8). Total num frames: 74911744. Throughput: 0: 9769.5. Samples: 74889428. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:56:10,829][613581] Avg episode reward: [(0, '4492.990')] [2023-03-09 04:56:11,201][613885] Updated weights for policy 0, policy_version 146320 (0.0005) [2023-03-09 04:56:15,756][613885] Updated weights for policy 0, policy_version 146400 (0.0005) [2023-03-09 04:56:15,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9693.9, 300 sec: 9636.0). Total num frames: 74956800. Throughput: 0: 9739.2. Samples: 74944512. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:56:15,829][613581] Avg episode reward: [(0, '4416.696')] [2023-03-09 04:56:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000146400_74956800.pth... [2023-03-09 04:56:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000145824_74661888.pth [2023-03-09 04:56:20,150][613885] Updated weights for policy 0, policy_version 146480 (0.0005) [2023-03-09 04:56:20,829][613581] Fps is (10 sec: 9011.1, 60 sec: 9625.6, 300 sec: 9622.1). Total num frames: 75001856. Throughput: 0: 9704.7. Samples: 75000164. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:56:20,829][613581] Avg episode reward: [(0, '4573.811')] [2023-03-09 04:56:24,143][613885] Updated weights for policy 0, policy_version 146560 (0.0005) [2023-03-09 04:56:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9649.9). Total num frames: 75055104. Throughput: 0: 9739.0. Samples: 75030520. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:56:25,829][613581] Avg episode reward: [(0, '4573.670')] [2023-03-09 04:56:28,389][613885] Updated weights for policy 0, policy_version 146640 (0.0005) [2023-03-09 04:56:30,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9636.0). Total num frames: 75100160. Throughput: 0: 9783.5. Samples: 75090948. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:56:30,829][613581] Avg episode reward: [(0, '4608.595')] [2023-03-09 04:56:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000146680_75100160.pth... [2023-03-09 04:56:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000146120_74813440.pth [2023-03-09 04:56:32,578][613885] Updated weights for policy 0, policy_version 146720 (0.0004) [2023-03-09 04:56:35,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9762.1, 300 sec: 9649.9). Total num frames: 75149312. Throughput: 0: 9789.9. Samples: 75147468. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:56:35,829][613581] Avg episode reward: [(0, '4585.765')] [2023-03-09 04:56:36,869][613885] Updated weights for policy 0, policy_version 146800 (0.0005) [2023-03-09 04:56:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9649.9). Total num frames: 75198464. Throughput: 0: 9799.8. Samples: 75176688. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-09 04:56:40,829][613581] Avg episode reward: [(0, '4588.761')] [2023-03-09 04:56:41,101][613885] Updated weights for policy 0, policy_version 146880 (0.0005) [2023-03-09 04:56:45,319][613885] Updated weights for policy 0, policy_version 146960 (0.0005) [2023-03-09 04:56:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9649.9). Total num frames: 75247616. Throughput: 0: 9684.5. Samples: 75234200. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:56:45,829][613581] Avg episode reward: [(0, '4624.619')] [2023-03-09 04:56:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000146968_75247616.pth... [2023-03-09 04:56:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000146400_74956800.pth [2023-03-09 04:56:49,522][613885] Updated weights for policy 0, policy_version 147040 (0.0005) [2023-03-09 04:56:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9649.9). Total num frames: 75292672. Throughput: 0: 9618.1. Samples: 75292684. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:56:50,829][613581] Avg episode reward: [(0, '4446.213')] [2023-03-09 04:56:53,862][613885] Updated weights for policy 0, policy_version 147120 (0.0005) [2023-03-09 04:56:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9663.8). Total num frames: 75341824. Throughput: 0: 9596.5. Samples: 75321272. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:56:55,829][613581] Avg episode reward: [(0, '4621.447')] [2023-03-09 04:56:58,078][613885] Updated weights for policy 0, policy_version 147200 (0.0005) [2023-03-09 04:57:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9663.8). Total num frames: 75390976. Throughput: 0: 9647.8. Samples: 75378664. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:57:00,829][613581] Avg episode reward: [(0, '4502.215')] [2023-03-09 04:57:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000147248_75390976.pth... [2023-03-09 04:57:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000146680_75100160.pth [2023-03-09 04:57:02,372][613885] Updated weights for policy 0, policy_version 147280 (0.0005) [2023-03-09 04:57:05,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9663.8). Total num frames: 75440128. Throughput: 0: 9686.1. Samples: 75436040. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:57:05,830][613581] Avg episode reward: [(0, '4609.862')] [2023-03-09 04:57:06,606][613885] Updated weights for policy 0, policy_version 147360 (0.0005) [2023-03-09 04:57:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9649.9). Total num frames: 75485184. Throughput: 0: 9648.5. Samples: 75464704. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:57:10,829][613581] Avg episode reward: [(0, '4592.629')] [2023-03-09 04:57:11,120][613885] Updated weights for policy 0, policy_version 147440 (0.0004) [2023-03-09 04:57:15,299][613885] Updated weights for policy 0, policy_version 147520 (0.0004) [2023-03-09 04:57:15,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9625.6, 300 sec: 9663.8). Total num frames: 75534336. Throughput: 0: 9511.0. Samples: 75518944. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:57:15,830][613581] Avg episode reward: [(0, '4559.145')] [2023-03-09 04:57:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000147528_75534336.pth... [2023-03-09 04:57:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000146968_75247616.pth [2023-03-09 04:57:19,257][613885] Updated weights for policy 0, policy_version 147600 (0.0005) [2023-03-09 04:57:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9663.8). Total num frames: 75583488. Throughput: 0: 9649.8. Samples: 75581712. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:57:20,829][613581] Avg episode reward: [(0, '4407.673')] [2023-03-09 04:57:23,596][613885] Updated weights for policy 0, policy_version 147680 (0.0004) [2023-03-09 04:57:25,829][613581] Fps is (10 sec: 9830.6, 60 sec: 9625.6, 300 sec: 9663.8). Total num frames: 75632640. Throughput: 0: 9645.2. Samples: 75610724. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:57:25,829][613581] Avg episode reward: [(0, '4464.242')] [2023-03-09 04:57:27,637][613885] Updated weights for policy 0, policy_version 147760 (0.0005) [2023-03-09 04:57:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.8, 300 sec: 9663.8). Total num frames: 75681792. Throughput: 0: 9684.6. Samples: 75670008. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:57:30,829][613581] Avg episode reward: [(0, '4275.245')] [2023-03-09 04:57:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000147816_75681792.pth... [2023-03-09 04:57:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000147248_75390976.pth [2023-03-09 04:57:31,860][613885] Updated weights for policy 0, policy_version 147840 (0.0005) [2023-03-09 04:57:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9636.0). Total num frames: 75726848. Throughput: 0: 9647.1. Samples: 75726804. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:57:35,829][613581] Avg episode reward: [(0, '4307.202')] [2023-03-09 04:57:36,343][613885] Updated weights for policy 0, policy_version 147920 (0.0005) [2023-03-09 04:57:40,289][613885] Updated weights for policy 0, policy_version 148000 (0.0005) [2023-03-09 04:57:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.8, 300 sec: 9663.8). Total num frames: 75780096. Throughput: 0: 9688.7. Samples: 75757264. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 04:57:40,829][613581] Avg episode reward: [(0, '4380.971')] [2023-03-09 04:57:44,675][613885] Updated weights for policy 0, policy_version 148080 (0.0005) [2023-03-09 04:57:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9649.9). Total num frames: 75825152. Throughput: 0: 9681.5. Samples: 75814332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:57:45,829][613581] Avg episode reward: [(0, '4245.597')] [2023-03-09 04:57:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000148096_75825152.pth... [2023-03-09 04:57:45,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000147528_75534336.pth [2023-03-09 04:57:48,902][613885] Updated weights for policy 0, policy_version 148160 (0.0005) [2023-03-09 04:57:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9663.8). Total num frames: 75874304. Throughput: 0: 9695.7. Samples: 75872344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:57:50,829][613581] Avg episode reward: [(0, '4265.964')] [2023-03-09 04:57:53,297][613885] Updated weights for policy 0, policy_version 148240 (0.0005) [2023-03-09 04:57:55,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9649.9). Total num frames: 75923456. Throughput: 0: 9658.0. Samples: 75899312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:57:55,829][613581] Avg episode reward: [(0, '4493.193')] [2023-03-09 04:57:57,544][613885] Updated weights for policy 0, policy_version 148320 (0.0005) [2023-03-09 04:58:00,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9649.9). Total num frames: 75968512. Throughput: 0: 9719.0. Samples: 75956296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:58:00,829][613581] Avg episode reward: [(0, '4364.345')] [2023-03-09 04:58:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000148376_75968512.pth... [2023-03-09 04:58:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000147816_75681792.pth [2023-03-09 04:58:01,839][613885] Updated weights for policy 0, policy_version 148400 (0.0005) [2023-03-09 04:58:05,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9557.4, 300 sec: 9636.0). Total num frames: 76013568. Throughput: 0: 9559.9. Samples: 76011908. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:58:05,829][613581] Avg episode reward: [(0, '4499.408')] [2023-03-09 04:58:06,498][613885] Updated weights for policy 0, policy_version 148480 (0.0005) [2023-03-09 04:58:10,762][613885] Updated weights for policy 0, policy_version 148560 (0.0005) [2023-03-09 04:58:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9649.9). Total num frames: 76062720. Throughput: 0: 9511.7. Samples: 76038752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:58:10,829][613581] Avg episode reward: [(0, '4321.339')] [2023-03-09 04:58:15,003][613885] Updated weights for policy 0, policy_version 148640 (0.0004) [2023-03-09 04:58:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9663.8). Total num frames: 76111872. Throughput: 0: 9498.2. Samples: 76097428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:58:15,829][613581] Avg episode reward: [(0, '4350.387')] [2023-03-09 04:58:15,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000148656_76111872.pth... [2023-03-09 04:58:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000148096_75825152.pth [2023-03-09 04:58:19,111][613885] Updated weights for policy 0, policy_version 148720 (0.0005) [2023-03-09 04:58:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9636.0). Total num frames: 76156928. Throughput: 0: 9558.0. Samples: 76156916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:58:20,829][613581] Avg episode reward: [(0, '4504.954')] [2023-03-09 04:58:23,414][613885] Updated weights for policy 0, policy_version 148800 (0.0005) [2023-03-09 04:58:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9636.0). Total num frames: 76206080. Throughput: 0: 9517.9. Samples: 76185568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:58:25,829][613581] Avg episode reward: [(0, '4471.719')] [2023-03-09 04:58:27,846][613885] Updated weights for policy 0, policy_version 148880 (0.0005) [2023-03-09 04:58:30,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9489.1, 300 sec: 9622.1). Total num frames: 76251136. Throughput: 0: 9449.2. Samples: 76239548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:58:30,829][613581] Avg episode reward: [(0, '4456.969')] [2023-03-09 04:58:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000148928_76251136.pth... [2023-03-09 04:58:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000148376_75968512.pth [2023-03-09 04:58:32,006][613885] Updated weights for policy 0, policy_version 148960 (0.0005) [2023-03-09 04:58:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9636.0). Total num frames: 76304384. Throughput: 0: 9515.1. Samples: 76300524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:58:35,829][613581] Avg episode reward: [(0, '4572.345')] [2023-03-09 04:58:36,276][613885] Updated weights for policy 0, policy_version 149040 (0.0005) [2023-03-09 04:58:40,639][613885] Updated weights for policy 0, policy_version 149120 (0.0005) [2023-03-09 04:58:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9489.1, 300 sec: 9636.0). Total num frames: 76349440. Throughput: 0: 9545.2. Samples: 76328844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:58:40,829][613581] Avg episode reward: [(0, '4586.235')] [2023-03-09 04:58:44,886][613885] Updated weights for policy 0, policy_version 149200 (0.0005) [2023-03-09 04:58:45,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9557.3, 300 sec: 9636.0). Total num frames: 76398592. Throughput: 0: 9543.4. Samples: 76385748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:58:45,829][613581] Avg episode reward: [(0, '4542.552')] [2023-03-09 04:58:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000149216_76398592.pth... [2023-03-09 04:58:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000148656_76111872.pth [2023-03-09 04:58:49,218][613885] Updated weights for policy 0, policy_version 149280 (0.0004) [2023-03-09 04:58:50,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9489.1, 300 sec: 9636.0). Total num frames: 76443648. Throughput: 0: 9585.1. Samples: 76443240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:58:50,830][613581] Avg episode reward: [(0, '4512.761')] [2023-03-09 04:58:53,447][613885] Updated weights for policy 0, policy_version 149360 (0.0006) [2023-03-09 04:58:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9636.0). Total num frames: 76492800. Throughput: 0: 9630.9. Samples: 76472144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:58:55,829][613581] Avg episode reward: [(0, '4388.311')] [2023-03-09 04:58:57,934][613885] Updated weights for policy 0, policy_version 149440 (0.0005) [2023-03-09 04:59:00,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9489.1, 300 sec: 9636.0). Total num frames: 76537856. Throughput: 0: 9540.2. Samples: 76526736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:59:00,829][613581] Avg episode reward: [(0, '4557.640')] [2023-03-09 04:59:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000149488_76537856.pth... [2023-03-09 04:59:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000148928_76251136.pth [2023-03-09 04:59:02,161][613885] Updated weights for policy 0, policy_version 149520 (0.0005) [2023-03-09 04:59:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9636.0). Total num frames: 76587008. Throughput: 0: 9480.9. Samples: 76583556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:59:05,829][613581] Avg episode reward: [(0, '4573.074')] [2023-03-09 04:59:06,567][613885] Updated weights for policy 0, policy_version 149600 (0.0005) [2023-03-09 04:59:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9622.1). Total num frames: 76632064. Throughput: 0: 9467.0. Samples: 76611584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:59:10,829][613581] Avg episode reward: [(0, '4620.420')] [2023-03-09 04:59:10,852][613885] Updated weights for policy 0, policy_version 149680 (0.0005) [2023-03-09 04:59:15,238][613885] Updated weights for policy 0, policy_version 149760 (0.0005) [2023-03-09 04:59:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9636.0). Total num frames: 76681216. Throughput: 0: 9541.8. Samples: 76668928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:59:15,829][613581] Avg episode reward: [(0, '4574.348')] [2023-03-09 04:59:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000149768_76681216.pth... [2023-03-09 04:59:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000149216_76398592.pth [2023-03-09 04:59:19,587][613885] Updated weights for policy 0, policy_version 149840 (0.0005) [2023-03-09 04:59:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9622.1). Total num frames: 76726272. Throughput: 0: 9447.7. Samples: 76725672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:59:20,829][613581] Avg episode reward: [(0, '4577.402')] [2023-03-09 04:59:24,168][613885] Updated weights for policy 0, policy_version 149920 (0.0005) [2023-03-09 04:59:25,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9420.8, 300 sec: 9594.4). Total num frames: 76771328. Throughput: 0: 9411.2. Samples: 76752348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:59:25,829][613581] Avg episode reward: [(0, '4611.325')] [2023-03-09 04:59:28,641][613885] Updated weights for policy 0, policy_version 150000 (0.0004) [2023-03-09 04:59:30,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9420.8, 300 sec: 9594.4). Total num frames: 76816384. Throughput: 0: 9387.0. Samples: 76808160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:59:30,829][613581] Avg episode reward: [(0, '4617.375')] [2023-03-09 04:59:30,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000150040_76820480.pth... [2023-03-09 04:59:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000149488_76537856.pth [2023-03-09 04:59:32,989][613885] Updated weights for policy 0, policy_version 150080 (0.0005) [2023-03-09 04:59:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9580.5). Total num frames: 76865536. Throughput: 0: 9342.4. Samples: 76863648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:59:35,829][613581] Avg episode reward: [(0, '4624.106')] [2023-03-09 04:59:37,521][613885] Updated weights for policy 0, policy_version 150160 (0.0005) [2023-03-09 04:59:40,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9580.5). Total num frames: 76910592. Throughput: 0: 9286.7. Samples: 76890044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:59:40,829][613581] Avg episode reward: [(0, '4634.322')] [2023-03-09 04:59:40,830][613841] Saving new best policy, reward=4634.322! [2023-03-09 04:59:41,790][613885] Updated weights for policy 0, policy_version 150240 (0.0005) [2023-03-09 04:59:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9580.5). Total num frames: 76959744. Throughput: 0: 9348.6. Samples: 76947424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:59:45,829][613581] Avg episode reward: [(0, '4592.895')] [2023-03-09 04:59:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000150312_76959744.pth... [2023-03-09 04:59:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000149768_76681216.pth [2023-03-09 04:59:46,266][613885] Updated weights for policy 0, policy_version 150320 (0.0005) [2023-03-09 04:59:50,828][613885] Updated weights for policy 0, policy_version 150400 (0.0005) [2023-03-09 04:59:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.6, 300 sec: 9566.6). Total num frames: 77004800. Throughput: 0: 9272.7. Samples: 77000828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 04:59:50,829][613581] Avg episode reward: [(0, '4639.894')] [2023-03-09 04:59:50,830][613841] Saving new best policy, reward=4639.894! [2023-03-09 04:59:55,035][613885] Updated weights for policy 0, policy_version 150480 (0.0005) [2023-03-09 04:59:55,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9284.3, 300 sec: 9566.6). Total num frames: 77049856. Throughput: 0: 9272.9. Samples: 77028864. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 04:59:55,829][613581] Avg episode reward: [(0, '4610.750')] [2023-03-09 04:59:59,523][613885] Updated weights for policy 0, policy_version 150560 (0.0005) [2023-03-09 05:00:00,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9352.5, 300 sec: 9552.7). Total num frames: 77099008. Throughput: 0: 9269.7. Samples: 77086064. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:00:00,829][613581] Avg episode reward: [(0, '4560.951')] [2023-03-09 05:00:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000150584_77099008.pth... [2023-03-09 05:00:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000150040_76820480.pth [2023-03-09 05:00:03,917][613885] Updated weights for policy 0, policy_version 150640 (0.0005) [2023-03-09 05:00:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9552.7). Total num frames: 77144064. Throughput: 0: 9223.1. Samples: 77140712. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:00:05,829][613581] Avg episode reward: [(0, '4639.984')] [2023-03-09 05:00:05,830][613841] Saving new best policy, reward=4639.984! [2023-03-09 05:00:08,140][613885] Updated weights for policy 0, policy_version 150720 (0.0004) [2023-03-09 05:00:10,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9352.5, 300 sec: 9552.7). Total num frames: 77193216. Throughput: 0: 9308.8. Samples: 77171244. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:00:10,830][613581] Avg episode reward: [(0, '4638.970')] [2023-03-09 05:00:12,493][613885] Updated weights for policy 0, policy_version 150800 (0.0004) [2023-03-09 05:00:15,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9538.8). Total num frames: 77238272. Throughput: 0: 9330.3. Samples: 77228024. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:00:15,829][613581] Avg episode reward: [(0, '4579.529')] [2023-03-09 05:00:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000150856_77238272.pth... [2023-03-09 05:00:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000150312_76959744.pth [2023-03-09 05:00:16,927][613885] Updated weights for policy 0, policy_version 150880 (0.0005) [2023-03-09 05:00:20,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9352.5, 300 sec: 9538.8). Total num frames: 77287424. Throughput: 0: 9335.4. Samples: 77283740. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:00:20,829][613581] Avg episode reward: [(0, '4601.783')] [2023-03-09 05:00:21,261][613885] Updated weights for policy 0, policy_version 150960 (0.0004) [2023-03-09 05:00:25,666][613885] Updated weights for policy 0, policy_version 151040 (0.0005) [2023-03-09 05:00:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9538.8). Total num frames: 77332480. Throughput: 0: 9373.7. Samples: 77311860. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:00:25,829][613581] Avg episode reward: [(0, '4619.217')] [2023-03-09 05:00:30,016][613885] Updated weights for policy 0, policy_version 151120 (0.0005) [2023-03-09 05:00:30,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9352.5, 300 sec: 9538.8). Total num frames: 77377536. Throughput: 0: 9352.5. Samples: 77368284. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:00:30,829][613581] Avg episode reward: [(0, '4512.963')] [2023-03-09 05:00:30,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000151128_77377536.pth... [2023-03-09 05:00:30,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000150584_77099008.pth [2023-03-09 05:00:34,382][613885] Updated weights for policy 0, policy_version 151200 (0.0004) [2023-03-09 05:00:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9538.8). Total num frames: 77426688. Throughput: 0: 9408.1. Samples: 77424192. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:00:35,829][613581] Avg episode reward: [(0, '4616.441')] [2023-03-09 05:00:38,914][613885] Updated weights for policy 0, policy_version 151280 (0.0005) [2023-03-09 05:00:40,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9352.5, 300 sec: 9524.9). Total num frames: 77471744. Throughput: 0: 9384.5. Samples: 77451168. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:00:40,829][613581] Avg episode reward: [(0, '4620.598')] [2023-03-09 05:00:43,301][613885] Updated weights for policy 0, policy_version 151360 (0.0006) [2023-03-09 05:00:45,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9524.9). Total num frames: 77516800. Throughput: 0: 9310.4. Samples: 77505032. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:00:45,829][613581] Avg episode reward: [(0, '4616.217')] [2023-03-09 05:00:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000151400_77516800.pth... [2023-03-09 05:00:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000150856_77238272.pth [2023-03-09 05:00:47,932][613885] Updated weights for policy 0, policy_version 151440 (0.0006) [2023-03-09 05:00:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9511.1). Total num frames: 77565952. Throughput: 0: 9360.3. Samples: 77561928. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:00:50,829][613581] Avg episode reward: [(0, '4614.721')] [2023-03-09 05:00:52,063][613885] Updated weights for policy 0, policy_version 151520 (0.0005) [2023-03-09 05:00:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9483.3). Total num frames: 77611008. Throughput: 0: 9319.0. Samples: 77590600. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:00:55,829][613581] Avg episode reward: [(0, '4617.634')] [2023-03-09 05:00:56,337][613885] Updated weights for policy 0, policy_version 151600 (0.0005) [2023-03-09 05:01:00,345][613885] Updated weights for policy 0, policy_version 151680 (0.0005) [2023-03-09 05:01:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9420.8, 300 sec: 9497.2). Total num frames: 77664256. Throughput: 0: 9383.1. Samples: 77650264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:01:00,829][613581] Avg episode reward: [(0, '4605.664')] [2023-03-09 05:01:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000151688_77664256.pth... [2023-03-09 05:01:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000151128_77377536.pth [2023-03-09 05:01:04,793][613885] Updated weights for policy 0, policy_version 151760 (0.0005) [2023-03-09 05:01:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9420.8, 300 sec: 9483.3). Total num frames: 77709312. Throughput: 0: 9382.7. Samples: 77705960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:01:05,829][613581] Avg episode reward: [(0, '4594.271')] [2023-03-09 05:01:09,042][613885] Updated weights for policy 0, policy_version 151840 (0.0005) [2023-03-09 05:01:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9497.2). Total num frames: 77758464. Throughput: 0: 9429.3. Samples: 77736180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:01:10,829][613581] Avg episode reward: [(0, '4616.491')] [2023-03-09 05:01:13,450][613885] Updated weights for policy 0, policy_version 151920 (0.0004) [2023-03-09 05:01:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9497.2). Total num frames: 77803520. Throughput: 0: 9410.8. Samples: 77791772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:01:15,829][613581] Avg episode reward: [(0, '4626.439')] [2023-03-09 05:01:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000151960_77803520.pth... [2023-03-09 05:01:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000151400_77516800.pth [2023-03-09 05:01:17,953][613885] Updated weights for policy 0, policy_version 152000 (0.0004) [2023-03-09 05:01:20,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 9469.4). Total num frames: 77848576. Throughput: 0: 9421.3. Samples: 77848148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:01:20,829][613581] Avg episode reward: [(0, '4619.893')] [2023-03-09 05:01:22,370][613885] Updated weights for policy 0, policy_version 152080 (0.0005) [2023-03-09 05:01:25,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 9469.4). Total num frames: 77893632. Throughput: 0: 9386.9. Samples: 77873576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:01:25,829][613581] Avg episode reward: [(0, '4623.249')] [2023-03-09 05:01:26,809][613885] Updated weights for policy 0, policy_version 152160 (0.0005) [2023-03-09 05:01:30,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9420.8, 300 sec: 9469.4). Total num frames: 77942784. Throughput: 0: 9439.1. Samples: 77929792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:01:30,829][613581] Avg episode reward: [(0, '4619.234')] [2023-03-09 05:01:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000152232_77942784.pth... [2023-03-09 05:01:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000151688_77664256.pth [2023-03-09 05:01:31,102][613885] Updated weights for policy 0, policy_version 152240 (0.0004) [2023-03-09 05:01:35,547][613885] Updated weights for policy 0, policy_version 152320 (0.0005) [2023-03-09 05:01:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9455.5). Total num frames: 77987840. Throughput: 0: 9457.3. Samples: 77987504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:01:35,829][613581] Avg episode reward: [(0, '4627.155')] [2023-03-09 05:01:39,899][613885] Updated weights for policy 0, policy_version 152400 (0.0005) [2023-03-09 05:01:40,829][613581] Fps is (10 sec: 9420.6, 60 sec: 9420.8, 300 sec: 9455.5). Total num frames: 78036992. Throughput: 0: 9410.2. Samples: 78014060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:01:40,830][613581] Avg episode reward: [(0, '4625.914')] [2023-03-09 05:01:44,338][613885] Updated weights for policy 0, policy_version 152480 (0.0005) [2023-03-09 05:01:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9455.5). Total num frames: 78082048. Throughput: 0: 9323.6. Samples: 78069824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:01:45,829][613581] Avg episode reward: [(0, '4628.851')] [2023-03-09 05:01:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000152504_78082048.pth... [2023-03-09 05:01:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000151960_77803520.pth [2023-03-09 05:01:48,703][613885] Updated weights for policy 0, policy_version 152560 (0.0005) [2023-03-09 05:01:50,829][613581] Fps is (10 sec: 9011.4, 60 sec: 9352.5, 300 sec: 9441.6). Total num frames: 78127104. Throughput: 0: 9346.4. Samples: 78126548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:01:50,829][613581] Avg episode reward: [(0, '4628.881')] [2023-03-09 05:01:53,138][613885] Updated weights for policy 0, policy_version 152640 (0.0005) [2023-03-09 05:01:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9441.6). Total num frames: 78176256. Throughput: 0: 9289.9. Samples: 78154224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:01:55,829][613581] Avg episode reward: [(0, '4578.472')] [2023-03-09 05:01:57,547][613885] Updated weights for policy 0, policy_version 152720 (0.0005) [2023-03-09 05:02:00,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9427.7). Total num frames: 78221312. Throughput: 0: 9272.5. Samples: 78209032. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:02:00,829][613581] Avg episode reward: [(0, '4569.677')] [2023-03-09 05:02:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000152776_78221312.pth... [2023-03-09 05:02:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000152232_77942784.pth [2023-03-09 05:02:01,995][613885] Updated weights for policy 0, policy_version 152800 (0.0004) [2023-03-09 05:02:05,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9427.7). Total num frames: 78266368. Throughput: 0: 9289.1. Samples: 78266156. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:02:05,829][613581] Avg episode reward: [(0, '4570.968')] [2023-03-09 05:02:06,319][613885] Updated weights for policy 0, policy_version 152880 (0.0004) [2023-03-09 05:02:10,592][613885] Updated weights for policy 0, policy_version 152960 (0.0004) [2023-03-09 05:02:10,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9427.7). Total num frames: 78315520. Throughput: 0: 9363.9. Samples: 78294952. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:02:10,829][613581] Avg episode reward: [(0, '4589.526')] [2023-03-09 05:02:14,843][613885] Updated weights for policy 0, policy_version 153040 (0.0005) [2023-03-09 05:02:15,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9352.5, 300 sec: 9427.7). Total num frames: 78364672. Throughput: 0: 9391.3. Samples: 78352400. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:02:15,829][613581] Avg episode reward: [(0, '4617.248')] [2023-03-09 05:02:15,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000153056_78364672.pth... [2023-03-09 05:02:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000152504_78082048.pth [2023-03-09 05:02:19,061][613885] Updated weights for policy 0, policy_version 153120 (0.0005) [2023-03-09 05:02:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9420.8, 300 sec: 9427.7). Total num frames: 78413824. Throughput: 0: 9381.0. Samples: 78409648. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:02:20,830][613581] Avg episode reward: [(0, '4608.614')] [2023-03-09 05:02:23,625][613885] Updated weights for policy 0, policy_version 153200 (0.0005) [2023-03-09 05:02:25,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9420.8, 300 sec: 9413.9). Total num frames: 78458880. Throughput: 0: 9380.5. Samples: 78436180. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:02:25,829][613581] Avg episode reward: [(0, '4553.033')] [2023-03-09 05:02:27,968][613885] Updated weights for policy 0, policy_version 153280 (0.0004) [2023-03-09 05:02:30,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 9413.9). Total num frames: 78503936. Throughput: 0: 9403.3. Samples: 78492972. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:02:30,829][613581] Avg episode reward: [(0, '4597.557')] [2023-03-09 05:02:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000153336_78508032.pth... [2023-03-09 05:02:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000152776_78221312.pth [2023-03-09 05:02:32,001][613885] Updated weights for policy 0, policy_version 153360 (0.0005) [2023-03-09 05:02:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9489.1, 300 sec: 9413.9). Total num frames: 78557184. Throughput: 0: 9511.3. Samples: 78554556. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:02:35,829][613581] Avg episode reward: [(0, '4604.549')] [2023-03-09 05:02:36,051][613885] Updated weights for policy 0, policy_version 153440 (0.0004) [2023-03-09 05:02:39,927][613885] Updated weights for policy 0, policy_version 153520 (0.0005) [2023-03-09 05:02:40,829][613581] Fps is (10 sec: 10649.7, 60 sec: 9557.3, 300 sec: 9441.6). Total num frames: 78610432. Throughput: 0: 9583.7. Samples: 78585492. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:02:40,829][613581] Avg episode reward: [(0, '4342.689')] [2023-03-09 05:02:44,185][613885] Updated weights for policy 0, policy_version 153600 (0.0005) [2023-03-09 05:02:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9557.3, 300 sec: 9427.7). Total num frames: 78655488. Throughput: 0: 9688.3. Samples: 78645008. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:02:45,829][613581] Avg episode reward: [(0, '4430.235')] [2023-03-09 05:02:45,858][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000153632_78659584.pth... [2023-03-09 05:02:45,860][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000153056_78364672.pth [2023-03-09 05:02:48,556][613885] Updated weights for policy 0, policy_version 153680 (0.0005) [2023-03-09 05:02:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9427.7). Total num frames: 78704640. Throughput: 0: 9678.5. Samples: 78701688. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:02:50,829][613581] Avg episode reward: [(0, '4583.106')] [2023-03-09 05:02:52,891][613885] Updated weights for policy 0, policy_version 153760 (0.0004) [2023-03-09 05:02:55,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9557.3, 300 sec: 9427.7). Total num frames: 78749696. Throughput: 0: 9659.2. Samples: 78729616. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:02:55,829][613581] Avg episode reward: [(0, '4587.211')] [2023-03-09 05:02:57,478][613885] Updated weights for policy 0, policy_version 153840 (0.0005) [2023-03-09 05:03:00,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9557.3, 300 sec: 9427.7). Total num frames: 78794752. Throughput: 0: 9575.2. Samples: 78783284. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:03:00,829][613581] Avg episode reward: [(0, '4583.095')] [2023-03-09 05:03:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000153896_78794752.pth... [2023-03-09 05:03:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000153336_78508032.pth [2023-03-09 05:03:01,959][613885] Updated weights for policy 0, policy_version 153920 (0.0005) [2023-03-09 05:03:05,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9557.3, 300 sec: 9413.9). Total num frames: 78839808. Throughput: 0: 9539.0. Samples: 78838900. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:03:05,829][613581] Avg episode reward: [(0, '4500.170')] [2023-03-09 05:03:06,374][613885] Updated weights for policy 0, policy_version 154000 (0.0005) [2023-03-09 05:03:10,773][613885] Updated weights for policy 0, policy_version 154080 (0.0005) [2023-03-09 05:03:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9413.9). Total num frames: 78888960. Throughput: 0: 9531.2. Samples: 78865084. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:03:10,829][613581] Avg episode reward: [(0, '4488.446')] [2023-03-09 05:03:14,928][613885] Updated weights for policy 0, policy_version 154160 (0.0005) [2023-03-09 05:03:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9557.3, 300 sec: 9427.7). Total num frames: 78938112. Throughput: 0: 9582.5. Samples: 78924184. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:03:15,829][613581] Avg episode reward: [(0, '4537.972')] [2023-03-09 05:03:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000154176_78938112.pth... [2023-03-09 05:03:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000153632_78659584.pth [2023-03-09 05:03:19,340][613885] Updated weights for policy 0, policy_version 154240 (0.0004) [2023-03-09 05:03:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9413.9). Total num frames: 78983168. Throughput: 0: 9477.3. Samples: 78981036. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:03:20,829][613581] Avg episode reward: [(0, '4555.121')] [2023-03-09 05:03:23,598][613885] Updated weights for policy 0, policy_version 154320 (0.0005) [2023-03-09 05:03:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9427.7). Total num frames: 79032320. Throughput: 0: 9434.7. Samples: 79010052. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:03:25,829][613581] Avg episode reward: [(0, '4540.017')] [2023-03-09 05:03:27,883][613885] Updated weights for policy 0, policy_version 154400 (0.0005) [2023-03-09 05:03:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9413.9). Total num frames: 79081472. Throughput: 0: 9427.6. Samples: 79069248. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:03:30,829][613581] Avg episode reward: [(0, '4519.750')] [2023-03-09 05:03:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000154456_79081472.pth... [2023-03-09 05:03:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000153896_78794752.pth [2023-03-09 05:03:31,756][613885] Updated weights for policy 0, policy_version 154480 (0.0005) [2023-03-09 05:03:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9427.7). Total num frames: 79130624. Throughput: 0: 9531.2. Samples: 79130592. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:03:35,829][613581] Avg episode reward: [(0, '4571.551')] [2023-03-09 05:03:35,848][613885] Updated weights for policy 0, policy_version 154560 (0.0005) [2023-03-09 05:03:40,428][613885] Updated weights for policy 0, policy_version 154640 (0.0005) [2023-03-09 05:03:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9489.1, 300 sec: 9427.7). Total num frames: 79179776. Throughput: 0: 9524.8. Samples: 79158232. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:03:40,829][613581] Avg episode reward: [(0, '4593.396')] [2023-03-09 05:03:44,305][613885] Updated weights for policy 0, policy_version 154720 (0.0005) [2023-03-09 05:03:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9441.6). Total num frames: 79228928. Throughput: 0: 9638.7. Samples: 79217024. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:03:45,840][613581] Avg episode reward: [(0, '4627.618')] [2023-03-09 05:03:45,843][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000154744_79228928.pth... [2023-03-09 05:03:45,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000154176_78938112.pth [2023-03-09 05:03:48,682][613885] Updated weights for policy 0, policy_version 154800 (0.0006) [2023-03-09 05:03:50,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9489.1, 300 sec: 9427.7). Total num frames: 79273984. Throughput: 0: 9668.7. Samples: 79273992. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:03:50,829][613581] Avg episode reward: [(0, '4618.817')] [2023-03-09 05:03:53,046][613885] Updated weights for policy 0, policy_version 154880 (0.0005) [2023-03-09 05:03:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9441.6). Total num frames: 79323136. Throughput: 0: 9717.3. Samples: 79302360. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:03:55,829][613581] Avg episode reward: [(0, '4616.028')] [2023-03-09 05:03:57,414][613885] Updated weights for policy 0, policy_version 154960 (0.0005) [2023-03-09 05:04:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9441.6). Total num frames: 79372288. Throughput: 0: 9685.1. Samples: 79360012. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:04:00,829][613581] Avg episode reward: [(0, '4600.139')] [2023-03-09 05:04:00,836][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000155032_79376384.pth... [2023-03-09 05:04:00,838][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000154456_79081472.pth [2023-03-09 05:04:01,279][613885] Updated weights for policy 0, policy_version 155040 (0.0005) [2023-03-09 05:04:05,578][613885] Updated weights for policy 0, policy_version 155120 (0.0004) [2023-03-09 05:04:05,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9455.5). Total num frames: 79421440. Throughput: 0: 9723.8. Samples: 79418604. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:04:05,829][613581] Avg episode reward: [(0, '4626.010')] [2023-03-09 05:04:09,991][613885] Updated weights for policy 0, policy_version 155200 (0.0005) [2023-03-09 05:04:10,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9625.6, 300 sec: 9441.6). Total num frames: 79466496. Throughput: 0: 9720.6. Samples: 79447476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:04:10,829][613581] Avg episode reward: [(0, '4594.137')] [2023-03-09 05:04:14,435][613885] Updated weights for policy 0, policy_version 155280 (0.0005) [2023-03-09 05:04:15,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9625.6, 300 sec: 9455.5). Total num frames: 79515648. Throughput: 0: 9641.6. Samples: 79503120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:04:15,829][613581] Avg episode reward: [(0, '4560.486')] [2023-03-09 05:04:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000155304_79515648.pth... [2023-03-09 05:04:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000154744_79228928.pth [2023-03-09 05:04:18,596][613885] Updated weights for policy 0, policy_version 155360 (0.0004) [2023-03-09 05:04:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9469.4). Total num frames: 79564800. Throughput: 0: 9559.6. Samples: 79560776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:04:20,830][613581] Avg episode reward: [(0, '4573.349')] [2023-03-09 05:04:22,963][613885] Updated weights for policy 0, policy_version 155440 (0.0005) [2023-03-09 05:04:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9469.4). Total num frames: 79609856. Throughput: 0: 9579.7. Samples: 79589316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:04:25,829][613581] Avg episode reward: [(0, '4584.897')] [2023-03-09 05:04:27,246][613885] Updated weights for policy 0, policy_version 155520 (0.0005) [2023-03-09 05:04:30,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9625.6, 300 sec: 9469.4). Total num frames: 79659008. Throughput: 0: 9564.9. Samples: 79647444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:04:30,829][613581] Avg episode reward: [(0, '4638.641')] [2023-03-09 05:04:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000155584_79659008.pth... [2023-03-09 05:04:30,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000155032_79376384.pth [2023-03-09 05:04:31,203][613885] Updated weights for policy 0, policy_version 155600 (0.0005) [2023-03-09 05:04:35,404][613885] Updated weights for policy 0, policy_version 155680 (0.0004) [2023-03-09 05:04:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9693.9, 300 sec: 9497.2). Total num frames: 79712256. Throughput: 0: 9648.4. Samples: 79708172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:04:35,829][613581] Avg episode reward: [(0, '4601.026')] [2023-03-09 05:04:40,036][613885] Updated weights for policy 0, policy_version 155760 (0.0004) [2023-03-09 05:04:40,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.4, 300 sec: 9469.4). Total num frames: 79753216. Throughput: 0: 9627.1. Samples: 79735580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:04:40,829][613581] Avg episode reward: [(0, '4562.279')] [2023-03-09 05:04:44,492][613885] Updated weights for policy 0, policy_version 155840 (0.0004) [2023-03-09 05:04:45,829][613581] Fps is (10 sec: 8601.4, 60 sec: 9489.0, 300 sec: 9469.4). Total num frames: 79798272. Throughput: 0: 9554.3. Samples: 79789956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:04:45,830][613581] Avg episode reward: [(0, '4584.785')] [2023-03-09 05:04:45,884][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000155864_79802368.pth... [2023-03-09 05:04:45,886][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000155304_79515648.pth [2023-03-09 05:04:48,995][613885] Updated weights for policy 0, policy_version 155920 (0.0005) [2023-03-09 05:04:50,829][613581] Fps is (10 sec: 9011.1, 60 sec: 9489.1, 300 sec: 9469.4). Total num frames: 79843328. Throughput: 0: 9441.1. Samples: 79843456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:04:50,829][613581] Avg episode reward: [(0, '4495.957')] [2023-03-09 05:04:53,435][613885] Updated weights for policy 0, policy_version 156000 (0.0006) [2023-03-09 05:04:55,829][613581] Fps is (10 sec: 9421.0, 60 sec: 9489.1, 300 sec: 9469.4). Total num frames: 79892480. Throughput: 0: 9432.5. Samples: 79871940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:04:55,829][613581] Avg episode reward: [(0, '4570.463')] [2023-03-09 05:04:57,688][613885] Updated weights for policy 0, policy_version 156080 (0.0005) [2023-03-09 05:05:00,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9469.4). Total num frames: 79937536. Throughput: 0: 9450.2. Samples: 79928380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:05:00,829][613581] Avg episode reward: [(0, '4529.841')] [2023-03-09 05:05:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000156128_79937536.pth... [2023-03-09 05:05:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000155584_79659008.pth [2023-03-09 05:05:02,350][613885] Updated weights for policy 0, policy_version 156160 (0.0005) [2023-03-09 05:05:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9469.4). Total num frames: 79986688. Throughput: 0: 9378.4. Samples: 79982804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:05:05,829][613581] Avg episode reward: [(0, '4570.892')] [2023-03-09 05:05:06,712][613885] Updated weights for policy 0, policy_version 156240 (0.0005) [2023-03-09 05:05:10,728][613885] Updated weights for policy 0, policy_version 156320 (0.0004) [2023-03-09 05:05:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9489.1, 300 sec: 9483.3). Total num frames: 80035840. Throughput: 0: 9429.7. Samples: 80013652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:05:10,829][613581] Avg episode reward: [(0, '4519.201')] [2023-03-09 05:05:14,848][613885] Updated weights for policy 0, policy_version 156400 (0.0005) [2023-03-09 05:05:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9489.1, 300 sec: 9483.3). Total num frames: 80084992. Throughput: 0: 9450.2. Samples: 80072704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:05:15,829][613581] Avg episode reward: [(0, '4510.741')] [2023-03-09 05:05:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000156416_80084992.pth... [2023-03-09 05:05:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000155864_79802368.pth [2023-03-09 05:05:19,378][613885] Updated weights for policy 0, policy_version 156480 (0.0005) [2023-03-09 05:05:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9483.3). Total num frames: 80130048. Throughput: 0: 9324.6. Samples: 80127780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:05:20,829][613581] Avg episode reward: [(0, '4625.534')] [2023-03-09 05:05:23,431][613885] Updated weights for policy 0, policy_version 156560 (0.0005) [2023-03-09 05:05:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9497.2). Total num frames: 80179200. Throughput: 0: 9401.8. Samples: 80158664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:05:25,830][613581] Avg episode reward: [(0, '4641.570')] [2023-03-09 05:05:25,830][613841] Saving new best policy, reward=4641.570! [2023-03-09 05:05:27,838][613885] Updated weights for policy 0, policy_version 156640 (0.0005) [2023-03-09 05:05:30,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9420.8, 300 sec: 9483.3). Total num frames: 80224256. Throughput: 0: 9433.5. Samples: 80214460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:05:30,829][613581] Avg episode reward: [(0, '4580.895')] [2023-03-09 05:05:30,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000156688_80224256.pth... [2023-03-09 05:05:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000156128_79937536.pth [2023-03-09 05:05:32,258][613885] Updated weights for policy 0, policy_version 156720 (0.0004) [2023-03-09 05:05:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9497.2). Total num frames: 80273408. Throughput: 0: 9476.0. Samples: 80269876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:05:35,829][613581] Avg episode reward: [(0, '4598.530')] [2023-03-09 05:05:36,653][613885] Updated weights for policy 0, policy_version 156800 (0.0005) [2023-03-09 05:05:40,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9420.8, 300 sec: 9497.2). Total num frames: 80318464. Throughput: 0: 9469.3. Samples: 80298056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:05:40,829][613581] Avg episode reward: [(0, '4611.221')] [2023-03-09 05:05:40,949][613885] Updated weights for policy 0, policy_version 156880 (0.0005) [2023-03-09 05:05:44,966][613885] Updated weights for policy 0, policy_version 156960 (0.0005) [2023-03-09 05:05:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9497.2). Total num frames: 80367616. Throughput: 0: 9550.5. Samples: 80358152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:05:45,829][613581] Avg episode reward: [(0, '4622.030')] [2023-03-09 05:05:45,837][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000156976_80371712.pth... [2023-03-09 05:05:45,838][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000156416_80084992.pth [2023-03-09 05:05:48,947][613885] Updated weights for policy 0, policy_version 157040 (0.0005) [2023-03-09 05:05:50,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9625.6, 300 sec: 9524.9). Total num frames: 80420864. Throughput: 0: 9665.2. Samples: 80417740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:05:50,829][613581] Avg episode reward: [(0, '4592.217')] [2023-03-09 05:05:53,323][613885] Updated weights for policy 0, policy_version 157120 (0.0005) [2023-03-09 05:05:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9497.2). Total num frames: 80465920. Throughput: 0: 9597.9. Samples: 80445556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:05:55,840][613581] Avg episode reward: [(0, '4444.892')] [2023-03-09 05:05:57,700][613885] Updated weights for policy 0, policy_version 157200 (0.0005) [2023-03-09 05:06:00,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9511.1). Total num frames: 80515072. Throughput: 0: 9537.3. Samples: 80501880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:06:00,840][613581] Avg episode reward: [(0, '4435.355')] [2023-03-09 05:06:00,843][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000157256_80515072.pth... [2023-03-09 05:06:00,845][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000156688_80224256.pth [2023-03-09 05:06:01,925][613885] Updated weights for policy 0, policy_version 157280 (0.0005) [2023-03-09 05:06:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9511.1). Total num frames: 80564224. Throughput: 0: 9617.4. Samples: 80560564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:06:05,840][613581] Avg episode reward: [(0, '4628.195')] [2023-03-09 05:06:06,158][613885] Updated weights for policy 0, policy_version 157360 (0.0005) [2023-03-09 05:06:10,513][613885] Updated weights for policy 0, policy_version 157440 (0.0005) [2023-03-09 05:06:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9511.1). Total num frames: 80609280. Throughput: 0: 9558.8. Samples: 80588808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:06:10,829][613581] Avg episode reward: [(0, '4622.522')] [2023-03-09 05:06:14,889][613885] Updated weights for policy 0, policy_version 157520 (0.0005) [2023-03-09 05:06:15,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9489.1, 300 sec: 9511.1). Total num frames: 80654336. Throughput: 0: 9587.1. Samples: 80645880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:06:15,840][613581] Avg episode reward: [(0, '4552.809')] [2023-03-09 05:06:15,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000157528_80654336.pth... [2023-03-09 05:06:15,844][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000156976_80371712.pth [2023-03-09 05:06:19,242][613885] Updated weights for policy 0, policy_version 157600 (0.0005) [2023-03-09 05:06:20,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9557.3, 300 sec: 9524.9). Total num frames: 80703488. Throughput: 0: 9587.3. Samples: 80701304. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:06:20,840][613581] Avg episode reward: [(0, '4557.404')] [2023-03-09 05:06:23,723][613885] Updated weights for policy 0, policy_version 157680 (0.0005) [2023-03-09 05:06:25,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9489.1, 300 sec: 9511.0). Total num frames: 80748544. Throughput: 0: 9559.7. Samples: 80728244. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:06:25,840][613581] Avg episode reward: [(0, '4558.758')] [2023-03-09 05:06:28,143][613885] Updated weights for policy 0, policy_version 157760 (0.0005) [2023-03-09 05:06:30,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9524.9). Total num frames: 80797696. Throughput: 0: 9492.9. Samples: 80785332. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:06:30,840][613581] Avg episode reward: [(0, '4579.006')] [2023-03-09 05:06:30,844][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000157808_80797696.pth... [2023-03-09 05:06:30,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000157256_80515072.pth [2023-03-09 05:06:32,500][613885] Updated weights for policy 0, policy_version 157840 (0.0005) [2023-03-09 05:06:35,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9489.1, 300 sec: 9511.1). Total num frames: 80842752. Throughput: 0: 9355.3. Samples: 80838728. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:06:35,840][613581] Avg episode reward: [(0, '4625.468')] [2023-03-09 05:06:37,134][613885] Updated weights for policy 0, policy_version 157920 (0.0005) [2023-03-09 05:06:40,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9489.1, 300 sec: 9511.0). Total num frames: 80887808. Throughput: 0: 9353.2. Samples: 80866452. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:06:40,840][613581] Avg episode reward: [(0, '4589.111')] [2023-03-09 05:06:41,651][613885] Updated weights for policy 0, policy_version 158000 (0.0005) [2023-03-09 05:06:45,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9420.8, 300 sec: 9511.0). Total num frames: 80932864. Throughput: 0: 9306.4. Samples: 80920668. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:06:45,840][613581] Avg episode reward: [(0, '4446.826')] [2023-03-09 05:06:45,879][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000158080_80936960.pth... [2023-03-09 05:06:45,880][613885] Updated weights for policy 0, policy_version 158080 (0.0005) [2023-03-09 05:06:45,881][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000157528_80654336.pth [2023-03-09 05:06:50,208][613885] Updated weights for policy 0, policy_version 158160 (0.0006) [2023-03-09 05:06:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9511.1). Total num frames: 80982016. Throughput: 0: 9307.6. Samples: 80979404. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:06:50,829][613581] Avg episode reward: [(0, '4618.743')] [2023-03-09 05:06:54,852][613885] Updated weights for policy 0, policy_version 158240 (0.0005) [2023-03-09 05:06:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9511.0). Total num frames: 81027072. Throughput: 0: 9252.8. Samples: 81005184. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:06:55,829][613581] Avg episode reward: [(0, '4525.668')] [2023-03-09 05:06:59,182][613885] Updated weights for policy 0, policy_version 158320 (0.0005) [2023-03-09 05:07:00,829][613581] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9511.0). Total num frames: 81072128. Throughput: 0: 9241.2. Samples: 81061736. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:07:00,829][613581] Avg episode reward: [(0, '4554.709')] [2023-03-09 05:07:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000158344_81072128.pth... [2023-03-09 05:07:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000157808_80797696.pth [2023-03-09 05:07:03,575][613885] Updated weights for policy 0, policy_version 158400 (0.0005) [2023-03-09 05:07:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9511.0). Total num frames: 81121280. Throughput: 0: 9244.4. Samples: 81117300. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:07:05,829][613581] Avg episode reward: [(0, '4438.281')] [2023-03-09 05:07:08,021][613885] Updated weights for policy 0, policy_version 158480 (0.0006) [2023-03-09 05:07:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9497.2). Total num frames: 81166336. Throughput: 0: 9277.0. Samples: 81145708. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:07:10,829][613581] Avg episode reward: [(0, '4515.106')] [2023-03-09 05:07:12,398][613885] Updated weights for policy 0, policy_version 158560 (0.0005) [2023-03-09 05:07:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9497.2). Total num frames: 81215488. Throughput: 0: 9274.7. Samples: 81202692. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:07:15,829][613581] Avg episode reward: [(0, '4545.283')] [2023-03-09 05:07:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000158624_81215488.pth... [2023-03-09 05:07:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000158080_80936960.pth [2023-03-09 05:07:16,537][613885] Updated weights for policy 0, policy_version 158640 (0.0005) [2023-03-09 05:07:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9497.2). Total num frames: 81260544. Throughput: 0: 9373.7. Samples: 81260544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:07:20,829][613581] Avg episode reward: [(0, '4643.454')] [2023-03-09 05:07:20,849][613841] Saving new best policy, reward=4643.454! [2023-03-09 05:07:20,850][613885] Updated weights for policy 0, policy_version 158720 (0.0005) [2023-03-09 05:07:25,198][613885] Updated weights for policy 0, policy_version 158800 (0.0005) [2023-03-09 05:07:25,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9352.6, 300 sec: 9511.1). Total num frames: 81309696. Throughput: 0: 9388.7. Samples: 81288944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:07:25,829][613581] Avg episode reward: [(0, '4584.527')] [2023-03-09 05:07:29,435][613885] Updated weights for policy 0, policy_version 158880 (0.0005) [2023-03-09 05:07:30,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9352.5, 300 sec: 9497.2). Total num frames: 81358848. Throughput: 0: 9463.8. Samples: 81346540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:07:30,829][613581] Avg episode reward: [(0, '4600.238')] [2023-03-09 05:07:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000158904_81358848.pth... [2023-03-09 05:07:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000158344_81072128.pth [2023-03-09 05:07:33,893][613885] Updated weights for policy 0, policy_version 158960 (0.0005) [2023-03-09 05:07:35,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9352.5, 300 sec: 9469.4). Total num frames: 81403904. Throughput: 0: 9389.7. Samples: 81401940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:07:35,830][613581] Avg episode reward: [(0, '4495.468')] [2023-03-09 05:07:38,008][613885] Updated weights for policy 0, policy_version 159040 (0.0005) [2023-03-09 05:07:40,829][613581] Fps is (10 sec: 9421.0, 60 sec: 9420.8, 300 sec: 9483.3). Total num frames: 81453056. Throughput: 0: 9493.3. Samples: 81432380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:07:40,829][613581] Avg episode reward: [(0, '4643.001')] [2023-03-09 05:07:42,218][613885] Updated weights for policy 0, policy_version 159120 (0.0005) [2023-03-09 05:07:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9489.1, 300 sec: 9483.3). Total num frames: 81502208. Throughput: 0: 9535.4. Samples: 81490828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:07:45,829][613581] Avg episode reward: [(0, '4573.800')] [2023-03-09 05:07:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000159184_81502208.pth... [2023-03-09 05:07:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000158624_81215488.pth [2023-03-09 05:07:46,499][613885] Updated weights for policy 0, policy_version 159200 (0.0005) [2023-03-09 05:07:50,727][613885] Updated weights for policy 0, policy_version 159280 (0.0004) [2023-03-09 05:07:50,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9489.1, 300 sec: 9497.2). Total num frames: 81551360. Throughput: 0: 9563.7. Samples: 81547664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:07:50,829][613581] Avg episode reward: [(0, '4382.721')] [2023-03-09 05:07:54,820][613885] Updated weights for policy 0, policy_version 159360 (0.0004) [2023-03-09 05:07:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9511.1). Total num frames: 81600512. Throughput: 0: 9598.6. Samples: 81577644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:07:55,830][613581] Avg episode reward: [(0, '4227.518')] [2023-03-09 05:07:58,978][613885] Updated weights for policy 0, policy_version 159440 (0.0005) [2023-03-09 05:08:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9524.9). Total num frames: 81649664. Throughput: 0: 9658.8. Samples: 81637336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:08:00,829][613581] Avg episode reward: [(0, '4265.002')] [2023-03-09 05:08:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000159472_81649664.pth... [2023-03-09 05:08:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000158904_81358848.pth [2023-03-09 05:08:03,091][613885] Updated weights for policy 0, policy_version 159520 (0.0004) [2023-03-09 05:08:05,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9524.9). Total num frames: 81698816. Throughput: 0: 9677.5. Samples: 81696032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:08:05,830][613581] Avg episode reward: [(0, '3926.283')] [2023-03-09 05:08:07,404][613885] Updated weights for policy 0, policy_version 159600 (0.0004) [2023-03-09 05:08:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9511.1). Total num frames: 81743872. Throughput: 0: 9663.4. Samples: 81723796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:08:10,829][613581] Avg episode reward: [(0, '4317.304')] [2023-03-09 05:08:11,710][613885] Updated weights for policy 0, policy_version 159680 (0.0005) [2023-03-09 05:08:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9524.9). Total num frames: 81793024. Throughput: 0: 9658.3. Samples: 81781164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:08:15,830][613581] Avg episode reward: [(0, '4490.019')] [2023-03-09 05:08:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000159752_81793024.pth... [2023-03-09 05:08:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000159184_81502208.pth [2023-03-09 05:08:16,098][613885] Updated weights for policy 0, policy_version 159760 (0.0004) [2023-03-09 05:08:20,478][613885] Updated weights for policy 0, policy_version 159840 (0.0005) [2023-03-09 05:08:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9511.1). Total num frames: 81838080. Throughput: 0: 9687.5. Samples: 81837876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:08:20,829][613581] Avg episode reward: [(0, '4491.628')] [2023-03-09 05:08:24,804][613885] Updated weights for policy 0, policy_version 159920 (0.0005) [2023-03-09 05:08:25,829][613581] Fps is (10 sec: 9421.0, 60 sec: 9625.6, 300 sec: 9511.1). Total num frames: 81887232. Throughput: 0: 9649.7. Samples: 81866616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:08:25,829][613581] Avg episode reward: [(0, '4325.900')] [2023-03-09 05:08:28,897][613885] Updated weights for policy 0, policy_version 160000 (0.0005) [2023-03-09 05:08:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9511.1). Total num frames: 81936384. Throughput: 0: 9629.8. Samples: 81924168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:08:30,829][613581] Avg episode reward: [(0, '4572.802')] [2023-03-09 05:08:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000160032_81936384.pth... [2023-03-09 05:08:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000159472_81649664.pth [2023-03-09 05:08:33,136][613885] Updated weights for policy 0, policy_version 160080 (0.0005) [2023-03-09 05:08:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9511.1). Total num frames: 81985536. Throughput: 0: 9660.9. Samples: 81982404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:08:35,829][613581] Avg episode reward: [(0, '4279.370')] [2023-03-09 05:08:37,442][613885] Updated weights for policy 0, policy_version 160160 (0.0004) [2023-03-09 05:08:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.8, 300 sec: 9511.1). Total num frames: 82034688. Throughput: 0: 9612.5. Samples: 82010204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:08:40,829][613581] Avg episode reward: [(0, '3901.282')] [2023-03-09 05:08:41,626][613885] Updated weights for policy 0, policy_version 160240 (0.0004) [2023-03-09 05:08:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9511.0). Total num frames: 82079744. Throughput: 0: 9581.4. Samples: 82068500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:08:45,829][613581] Avg episode reward: [(0, '4009.689')] [2023-03-09 05:08:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000160312_82079744.pth... [2023-03-09 05:08:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000159752_81793024.pth [2023-03-09 05:08:45,974][613885] Updated weights for policy 0, policy_version 160320 (0.0005) [2023-03-09 05:08:50,323][613885] Updated weights for policy 0, policy_version 160400 (0.0005) [2023-03-09 05:08:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9511.1). Total num frames: 82128896. Throughput: 0: 9531.0. Samples: 82124924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:08:50,840][613581] Avg episode reward: [(0, '4238.067')] [2023-03-09 05:08:54,533][613885] Updated weights for policy 0, policy_version 160480 (0.0005) [2023-03-09 05:08:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9497.2). Total num frames: 82173952. Throughput: 0: 9592.8. Samples: 82155472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:08:55,840][613581] Avg episode reward: [(0, '4180.359')] [2023-03-09 05:08:58,847][613885] Updated weights for policy 0, policy_version 160560 (0.0005) [2023-03-09 05:09:00,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9557.3, 300 sec: 9497.2). Total num frames: 82223104. Throughput: 0: 9555.7. Samples: 82211168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:09:00,840][613581] Avg episode reward: [(0, '4181.170')] [2023-03-09 05:09:00,844][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000160592_82223104.pth... [2023-03-09 05:09:00,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000160032_81936384.pth [2023-03-09 05:09:03,421][613885] Updated weights for policy 0, policy_version 160640 (0.0005) [2023-03-09 05:09:05,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9489.1, 300 sec: 9497.2). Total num frames: 82268160. Throughput: 0: 9554.7. Samples: 82267836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:09:05,840][613581] Avg episode reward: [(0, '3734.683')] [2023-03-09 05:09:07,718][613885] Updated weights for policy 0, policy_version 160720 (0.0005) [2023-03-09 05:09:10,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9489.1, 300 sec: 9483.3). Total num frames: 82313216. Throughput: 0: 9535.5. Samples: 82295712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:09:10,840][613581] Avg episode reward: [(0, '3678.366')] [2023-03-09 05:09:12,224][613885] Updated weights for policy 0, policy_version 160800 (0.0004) [2023-03-09 05:09:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9483.3). Total num frames: 82362368. Throughput: 0: 9464.9. Samples: 82350088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:09:15,840][613581] Avg episode reward: [(0, '3482.160')] [2023-03-09 05:09:15,843][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000160864_82362368.pth... [2023-03-09 05:09:15,845][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000160312_82079744.pth [2023-03-09 05:09:16,587][613885] Updated weights for policy 0, policy_version 160880 (0.0005) [2023-03-09 05:09:20,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9489.1, 300 sec: 9483.3). Total num frames: 82407424. Throughput: 0: 9406.8. Samples: 82405712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:09:20,829][613581] Avg episode reward: [(0, '3573.989')] [2023-03-09 05:09:20,938][613885] Updated weights for policy 0, policy_version 160960 (0.0005) [2023-03-09 05:09:24,949][613885] Updated weights for policy 0, policy_version 161040 (0.0005) [2023-03-09 05:09:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9557.3, 300 sec: 9497.2). Total num frames: 82460672. Throughput: 0: 9455.5. Samples: 82435700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:09:25,829][613581] Avg episode reward: [(0, '3690.368')] [2023-03-09 05:09:29,242][613885] Updated weights for policy 0, policy_version 161120 (0.0005) [2023-03-09 05:09:30,829][613581] Fps is (10 sec: 10239.8, 60 sec: 9557.3, 300 sec: 9483.3). Total num frames: 82509824. Throughput: 0: 9470.5. Samples: 82494672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:09:30,829][613581] Avg episode reward: [(0, '4004.439')] [2023-03-09 05:09:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000161152_82509824.pth... [2023-03-09 05:09:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000160592_82223104.pth [2023-03-09 05:09:33,346][613885] Updated weights for policy 0, policy_version 161200 (0.0005) [2023-03-09 05:09:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9497.2). Total num frames: 82554880. Throughput: 0: 9506.8. Samples: 82552728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:09:35,829][613581] Avg episode reward: [(0, '3560.650')] [2023-03-09 05:09:36,782][613841] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000004 [2023-03-09 05:09:37,606][613885] Updated weights for policy 0, policy_version 161280 (0.0005) [2023-03-09 05:09:40,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9511.1). Total num frames: 82604032. Throughput: 0: 9514.3. Samples: 82583616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:09:40,829][613581] Avg episode reward: [(0, '4097.501')] [2023-03-09 05:09:42,022][613885] Updated weights for policy 0, policy_version 161360 (0.0005) [2023-03-09 05:09:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9511.1). Total num frames: 82649088. Throughput: 0: 9470.2. Samples: 82637328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:09:45,829][613581] Avg episode reward: [(0, '4128.139')] [2023-03-09 05:09:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000161424_82649088.pth... [2023-03-09 05:09:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000160864_82362368.pth [2023-03-09 05:09:46,413][613885] Updated weights for policy 0, policy_version 161440 (0.0005) [2023-03-09 05:09:50,496][613885] Updated weights for policy 0, policy_version 161520 (0.0005) [2023-03-09 05:09:50,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9489.1, 300 sec: 9511.1). Total num frames: 82698240. Throughput: 0: 9553.2. Samples: 82697728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:09:50,829][613581] Avg episode reward: [(0, '4353.677')] [2023-03-09 05:09:54,765][613885] Updated weights for policy 0, policy_version 161600 (0.0005) [2023-03-09 05:09:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 9524.9). Total num frames: 82747392. Throughput: 0: 9580.1. Samples: 82726816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:09:55,829][613581] Avg episode reward: [(0, '4096.367')] [2023-03-09 05:09:59,011][613885] Updated weights for policy 0, policy_version 161680 (0.0005) [2023-03-09 05:10:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9557.4, 300 sec: 9524.9). Total num frames: 82796544. Throughput: 0: 9649.8. Samples: 82784328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:10:00,829][613581] Avg episode reward: [(0, '4246.413')] [2023-03-09 05:10:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000161712_82796544.pth... [2023-03-09 05:10:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000161152_82509824.pth [2023-03-09 05:10:03,051][613885] Updated weights for policy 0, policy_version 161760 (0.0004) [2023-03-09 05:10:05,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9625.6, 300 sec: 9524.9). Total num frames: 82845696. Throughput: 0: 9777.4. Samples: 82845696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:10:05,829][613581] Avg episode reward: [(0, '4189.864')] [2023-03-09 05:10:07,175][613885] Updated weights for policy 0, policy_version 161840 (0.0005) [2023-03-09 05:10:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9524.9). Total num frames: 82894848. Throughput: 0: 9748.2. Samples: 82874368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:10:10,829][613581] Avg episode reward: [(0, '4149.934')] [2023-03-09 05:10:11,380][613885] Updated weights for policy 0, policy_version 161920 (0.0005) [2023-03-09 05:10:15,286][613885] Updated weights for policy 0, policy_version 162000 (0.0004) [2023-03-09 05:10:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9762.1, 300 sec: 9552.7). Total num frames: 82948096. Throughput: 0: 9750.0. Samples: 82933424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:10:15,829][613581] Avg episode reward: [(0, '4417.775')] [2023-03-09 05:10:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000162008_82948096.pth... [2023-03-09 05:10:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000161424_82649088.pth [2023-03-09 05:10:19,632][613885] Updated weights for policy 0, policy_version 162080 (0.0005) [2023-03-09 05:10:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9538.8). Total num frames: 82993152. Throughput: 0: 9780.7. Samples: 82992860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:10:20,829][613581] Avg episode reward: [(0, '4213.521')] [2023-03-09 05:10:23,626][613885] Updated weights for policy 0, policy_version 162160 (0.0005) [2023-03-09 05:10:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9566.6). Total num frames: 83046400. Throughput: 0: 9746.7. Samples: 83022216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:10:25,840][613581] Avg episode reward: [(0, '4397.767')] [2023-03-09 05:10:27,697][613885] Updated weights for policy 0, policy_version 162240 (0.0005) [2023-03-09 05:10:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9762.2, 300 sec: 9566.6). Total num frames: 83095552. Throughput: 0: 9920.5. Samples: 83083752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:10:30,840][613581] Avg episode reward: [(0, '4228.595')] [2023-03-09 05:10:30,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000162296_83095552.pth... [2023-03-09 05:10:30,844][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000161712_82796544.pth [2023-03-09 05:10:31,780][613885] Updated weights for policy 0, policy_version 162320 (0.0004) [2023-03-09 05:10:35,642][613885] Updated weights for policy 0, policy_version 162400 (0.0005) [2023-03-09 05:10:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 9898.7, 300 sec: 9594.4). Total num frames: 83148800. Throughput: 0: 9964.6. Samples: 83146136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:10:35,829][613581] Avg episode reward: [(0, '4390.959')] [2023-03-09 05:10:39,745][613885] Updated weights for policy 0, policy_version 162480 (0.0005) [2023-03-09 05:10:40,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 9594.4). Total num frames: 83197952. Throughput: 0: 10001.1. Samples: 83176864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:10:40,829][613581] Avg episode reward: [(0, '4518.287')] [2023-03-09 05:10:43,884][613885] Updated weights for policy 0, policy_version 162560 (0.0006) [2023-03-09 05:10:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10035.2, 300 sec: 9594.4). Total num frames: 83251200. Throughput: 0: 10029.7. Samples: 83235664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:10:45,829][613581] Avg episode reward: [(0, '4470.743')] [2023-03-09 05:10:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000162600_83251200.pth... [2023-03-09 05:10:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000162008_82948096.pth [2023-03-09 05:10:47,791][613885] Updated weights for policy 0, policy_version 162640 (0.0005) [2023-03-09 05:10:50,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10035.2, 300 sec: 9608.2). Total num frames: 83300352. Throughput: 0: 10100.7. Samples: 83300228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:10:50,829][613581] Avg episode reward: [(0, '4590.561')] [2023-03-09 05:10:51,556][613885] Updated weights for policy 0, policy_version 162720 (0.0005) [2023-03-09 05:10:55,636][613885] Updated weights for policy 0, policy_version 162800 (0.0005) [2023-03-09 05:10:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 9622.1). Total num frames: 83353600. Throughput: 0: 10119.4. Samples: 83329740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:10:55,829][613581] Avg episode reward: [(0, '4632.938')] [2023-03-09 05:10:59,711][613885] Updated weights for policy 0, policy_version 162880 (0.0006) [2023-03-09 05:11:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10103.5, 300 sec: 9622.1). Total num frames: 83402752. Throughput: 0: 10164.9. Samples: 83390844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:11:00,829][613581] Avg episode reward: [(0, '4573.039')] [2023-03-09 05:11:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000162896_83402752.pth... [2023-03-09 05:11:00,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000162296_83095552.pth [2023-03-09 05:11:03,728][613885] Updated weights for policy 0, policy_version 162960 (0.0005) [2023-03-09 05:11:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 9649.9). Total num frames: 83456000. Throughput: 0: 10202.4. Samples: 83451968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:11:05,829][613581] Avg episode reward: [(0, '4543.906')] [2023-03-09 05:11:07,945][613885] Updated weights for policy 0, policy_version 163040 (0.0005) [2023-03-09 05:11:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 9663.8). Total num frames: 83505152. Throughput: 0: 10187.2. Samples: 83480640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:11:10,829][613581] Avg episode reward: [(0, '4426.788')] [2023-03-09 05:11:11,952][613885] Updated weights for policy 0, policy_version 163120 (0.0004) [2023-03-09 05:11:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 10035.2, 300 sec: 9649.9). Total num frames: 83550208. Throughput: 0: 10129.7. Samples: 83539588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:11:15,829][613581] Avg episode reward: [(0, '4430.968')] [2023-03-09 05:11:15,840][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000163192_83554304.pth... [2023-03-09 05:11:15,841][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000162600_83251200.pth [2023-03-09 05:11:16,248][613885] Updated weights for policy 0, policy_version 163200 (0.0005) [2023-03-09 05:11:20,019][613885] Updated weights for policy 0, policy_version 163280 (0.0004) [2023-03-09 05:11:20,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 9691.6). Total num frames: 83607552. Throughput: 0: 10168.3. Samples: 83603712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:11:20,829][613581] Avg episode reward: [(0, '4386.346')] [2023-03-09 05:11:23,834][613885] Updated weights for policy 0, policy_version 163360 (0.0005) [2023-03-09 05:11:25,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10171.7, 300 sec: 9691.6). Total num frames: 83656704. Throughput: 0: 10208.0. Samples: 83636224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:11:25,829][613581] Avg episode reward: [(0, '4373.426')] [2023-03-09 05:11:27,801][613885] Updated weights for policy 0, policy_version 163440 (0.0005) [2023-03-09 05:11:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 9719.3). Total num frames: 83709952. Throughput: 0: 10265.8. Samples: 83697624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:11:30,829][613581] Avg episode reward: [(0, '4368.726')] [2023-03-09 05:11:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000163496_83709952.pth... [2023-03-09 05:11:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000162896_83402752.pth [2023-03-09 05:11:31,937][613885] Updated weights for policy 0, policy_version 163520 (0.0005) [2023-03-09 05:11:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 9733.2). Total num frames: 83759104. Throughput: 0: 10106.2. Samples: 83755008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:11:35,829][613581] Avg episode reward: [(0, '4403.554')] [2023-03-09 05:11:36,252][613885] Updated weights for policy 0, policy_version 163600 (0.0005) [2023-03-09 05:11:40,427][613885] Updated weights for policy 0, policy_version 163680 (0.0005) [2023-03-09 05:11:40,829][613581] Fps is (10 sec: 9420.9, 60 sec: 10103.5, 300 sec: 9733.2). Total num frames: 83804160. Throughput: 0: 10089.2. Samples: 83783752. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:11:40,829][613581] Avg episode reward: [(0, '4106.245')] [2023-03-09 05:11:44,427][613885] Updated weights for policy 0, policy_version 163760 (0.0005) [2023-03-09 05:11:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 9747.1). Total num frames: 83857408. Throughput: 0: 10094.4. Samples: 83845092. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:11:45,829][613581] Avg episode reward: [(0, '4080.515')] [2023-03-09 05:11:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000163784_83857408.pth... [2023-03-09 05:11:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000163192_83554304.pth [2023-03-09 05:11:48,363][613885] Updated weights for policy 0, policy_version 163840 (0.0005) [2023-03-09 05:11:50,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10171.7, 300 sec: 9774.9). Total num frames: 83910656. Throughput: 0: 10099.5. Samples: 83906448. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:11:50,830][613581] Avg episode reward: [(0, '4154.517')] [2023-03-09 05:11:52,396][613885] Updated weights for policy 0, policy_version 163920 (0.0005) [2023-03-09 05:11:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10103.5, 300 sec: 9788.7). Total num frames: 83959808. Throughput: 0: 10193.4. Samples: 83939344. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:11:55,829][613581] Avg episode reward: [(0, '4435.129')] [2023-03-09 05:11:56,256][613885] Updated weights for policy 0, policy_version 164000 (0.0005) [2023-03-09 05:12:00,168][613885] Updated weights for policy 0, policy_version 164080 (0.0005) [2023-03-09 05:12:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 9802.6). Total num frames: 84013056. Throughput: 0: 10246.7. Samples: 84000688. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:12:00,829][613581] Avg episode reward: [(0, '4443.325')] [2023-03-09 05:12:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000164088_84013056.pth... [2023-03-09 05:12:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000163496_83709952.pth [2023-03-09 05:12:04,183][613885] Updated weights for policy 0, policy_version 164160 (0.0005) [2023-03-09 05:12:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10171.7, 300 sec: 9830.4). Total num frames: 84066304. Throughput: 0: 10194.1. Samples: 84062448. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:12:05,829][613581] Avg episode reward: [(0, '4505.256')] [2023-03-09 05:12:08,170][613885] Updated weights for policy 0, policy_version 164240 (0.0006) [2023-03-09 05:12:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 9830.4). Total num frames: 84115456. Throughput: 0: 10153.2. Samples: 84093120. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:12:10,829][613581] Avg episode reward: [(0, '4523.016')] [2023-03-09 05:12:12,521][613885] Updated weights for policy 0, policy_version 164320 (0.0005) [2023-03-09 05:12:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10240.0, 300 sec: 9844.3). Total num frames: 84164608. Throughput: 0: 10095.7. Samples: 84151932. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:12:15,829][613581] Avg episode reward: [(0, '4529.580')] [2023-03-09 05:12:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000164384_84164608.pth... [2023-03-09 05:12:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000163784_83857408.pth [2023-03-09 05:12:16,492][613885] Updated weights for policy 0, policy_version 164400 (0.0005) [2023-03-09 05:12:20,422][613885] Updated weights for policy 0, policy_version 164480 (0.0005) [2023-03-09 05:12:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 9858.2). Total num frames: 84217856. Throughput: 0: 10187.5. Samples: 84213448. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:12:20,830][613581] Avg episode reward: [(0, '4573.377')] [2023-03-09 05:12:24,212][613885] Updated weights for policy 0, policy_version 164560 (0.0004) [2023-03-09 05:12:25,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10171.7, 300 sec: 9858.2). Total num frames: 84267008. Throughput: 0: 10282.6. Samples: 84246468. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:12:25,829][613581] Avg episode reward: [(0, '4566.217')] [2023-03-09 05:12:28,426][613885] Updated weights for policy 0, policy_version 164640 (0.0005) [2023-03-09 05:12:30,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10103.5, 300 sec: 9872.1). Total num frames: 84316160. Throughput: 0: 10238.9. Samples: 84305840. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:12:30,829][613581] Avg episode reward: [(0, '4397.830')] [2023-03-09 05:12:30,835][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000164688_84320256.pth... [2023-03-09 05:12:30,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000164088_84013056.pth [2023-03-09 05:12:32,489][613885] Updated weights for policy 0, policy_version 164720 (0.0004) [2023-03-09 05:12:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.8, 300 sec: 9885.9). Total num frames: 84369408. Throughput: 0: 10272.3. Samples: 84368700. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:12:35,829][613581] Avg episode reward: [(0, '4261.383')] [2023-03-09 05:12:36,255][613885] Updated weights for policy 0, policy_version 164800 (0.0005) [2023-03-09 05:12:40,103][613885] Updated weights for policy 0, policy_version 164880 (0.0005) [2023-03-09 05:12:40,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 9899.8). Total num frames: 84422656. Throughput: 0: 10257.1. Samples: 84400916. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:12:40,829][613581] Avg episode reward: [(0, '4410.411')] [2023-03-09 05:12:44,209][613885] Updated weights for policy 0, policy_version 164960 (0.0004) [2023-03-09 05:12:45,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 9899.8). Total num frames: 84471808. Throughput: 0: 10241.3. Samples: 84461544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:12:45,829][613581] Avg episode reward: [(0, '4090.859')] [2023-03-09 05:12:45,850][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000164992_84475904.pth... [2023-03-09 05:12:45,852][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000164384_84164608.pth [2023-03-09 05:12:48,086][613885] Updated weights for policy 0, policy_version 165040 (0.0005) [2023-03-09 05:12:50,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 9927.6). Total num frames: 84529152. Throughput: 0: 10281.6. Samples: 84525120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:12:50,830][613581] Avg episode reward: [(0, '4158.402')] [2023-03-09 05:12:51,938][613885] Updated weights for policy 0, policy_version 165120 (0.0005) [2023-03-09 05:12:55,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 9927.6). Total num frames: 84578304. Throughput: 0: 10267.7. Samples: 84555164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:12:55,829][613581] Avg episode reward: [(0, '4185.622')] [2023-03-09 05:12:55,990][613885] Updated weights for policy 0, policy_version 165200 (0.0004) [2023-03-09 05:13:00,003][613885] Updated weights for policy 0, policy_version 165280 (0.0005) [2023-03-09 05:13:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 9941.5). Total num frames: 84631552. Throughput: 0: 10331.7. Samples: 84616860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:13:00,829][613581] Avg episode reward: [(0, '4397.435')] [2023-03-09 05:13:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000165296_84631552.pth... [2023-03-09 05:13:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000164688_84320256.pth [2023-03-09 05:13:04,032][613885] Updated weights for policy 0, policy_version 165360 (0.0004) [2023-03-09 05:13:05,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 9955.4). Total num frames: 84680704. Throughput: 0: 10300.9. Samples: 84676988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:13:05,829][613581] Avg episode reward: [(0, '4372.945')] [2023-03-09 05:13:08,183][613885] Updated weights for policy 0, policy_version 165440 (0.0005) [2023-03-09 05:13:10,829][613581] Fps is (10 sec: 9830.6, 60 sec: 10240.0, 300 sec: 9955.4). Total num frames: 84729856. Throughput: 0: 10244.1. Samples: 84707452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:13:10,829][613581] Avg episode reward: [(0, '4184.663')] [2023-03-09 05:13:12,080][613885] Updated weights for policy 0, policy_version 165520 (0.0005) [2023-03-09 05:13:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 9983.1). Total num frames: 84783104. Throughput: 0: 10292.9. Samples: 84769020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:13:15,829][613581] Avg episode reward: [(0, '4503.593')] [2023-03-09 05:13:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000165592_84783104.pth... [2023-03-09 05:13:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000164992_84475904.pth [2023-03-09 05:13:16,124][613885] Updated weights for policy 0, policy_version 165600 (0.0005) [2023-03-09 05:13:20,111][613885] Updated weights for policy 0, policy_version 165680 (0.0005) [2023-03-09 05:13:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 9983.1). Total num frames: 84832256. Throughput: 0: 10292.2. Samples: 84831848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:13:20,829][613581] Avg episode reward: [(0, '4573.124')] [2023-03-09 05:13:24,024][613885] Updated weights for policy 0, policy_version 165760 (0.0005) [2023-03-09 05:13:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 9997.0). Total num frames: 84885504. Throughput: 0: 10262.7. Samples: 84862736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:13:25,829][613581] Avg episode reward: [(0, '4577.789')] [2023-03-09 05:13:27,956][613885] Updated weights for policy 0, policy_version 165840 (0.0005) [2023-03-09 05:13:30,829][613581] Fps is (10 sec: 10649.3, 60 sec: 10376.5, 300 sec: 10010.9). Total num frames: 84938752. Throughput: 0: 10328.0. Samples: 84926308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:13:30,830][613581] Avg episode reward: [(0, '4492.895')] [2023-03-09 05:13:30,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000165896_84938752.pth... [2023-03-09 05:13:30,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000165296_84631552.pth [2023-03-09 05:13:32,044][613885] Updated weights for policy 0, policy_version 165920 (0.0005) [2023-03-09 05:13:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10010.9). Total num frames: 84987904. Throughput: 0: 10259.3. Samples: 84986788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:13:35,829][613581] Avg episode reward: [(0, '4346.928')] [2023-03-09 05:13:35,991][613885] Updated weights for policy 0, policy_version 166000 (0.0005) [2023-03-09 05:13:40,075][613885] Updated weights for policy 0, policy_version 166080 (0.0005) [2023-03-09 05:13:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10240.0, 300 sec: 10024.8). Total num frames: 85037056. Throughput: 0: 10248.4. Samples: 85016344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:13:40,829][613581] Avg episode reward: [(0, '4531.525')] [2023-03-09 05:13:44,247][613885] Updated weights for policy 0, policy_version 166160 (0.0005) [2023-03-09 05:13:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10240.0, 300 sec: 10024.8). Total num frames: 85086208. Throughput: 0: 10183.4. Samples: 85075112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:13:45,829][613581] Avg episode reward: [(0, '4535.453')] [2023-03-09 05:13:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000166184_85086208.pth... [2023-03-09 05:13:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000165592_84783104.pth [2023-03-09 05:13:48,454][613885] Updated weights for policy 0, policy_version 166240 (0.0004) [2023-03-09 05:13:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10038.7). Total num frames: 85135360. Throughput: 0: 10179.6. Samples: 85135072. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:13:50,829][613581] Avg episode reward: [(0, '4402.681')] [2023-03-09 05:13:52,475][613885] Updated weights for policy 0, policy_version 166320 (0.0005) [2023-03-09 05:13:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10038.7). Total num frames: 85184512. Throughput: 0: 10146.4. Samples: 85164040. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:13:55,829][613581] Avg episode reward: [(0, '4487.604')] [2023-03-09 05:13:56,663][613885] Updated weights for policy 0, policy_version 166400 (0.0005) [2023-03-09 05:14:00,643][613885] Updated weights for policy 0, policy_version 166480 (0.0005) [2023-03-09 05:14:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 10066.4). Total num frames: 85237760. Throughput: 0: 10107.3. Samples: 85223848. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:14:00,829][613581] Avg episode reward: [(0, '4344.457')] [2023-03-09 05:14:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000166480_85237760.pth... [2023-03-09 05:14:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000165896_84938752.pth [2023-03-09 05:14:04,497][613885] Updated weights for policy 0, policy_version 166560 (0.0005) [2023-03-09 05:14:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10171.7, 300 sec: 10094.2). Total num frames: 85291008. Throughput: 0: 10117.5. Samples: 85287136. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:14:05,829][613581] Avg episode reward: [(0, '4200.031')] [2023-03-09 05:14:08,725][613885] Updated weights for policy 0, policy_version 166640 (0.0004) [2023-03-09 05:14:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10103.5, 300 sec: 10080.3). Total num frames: 85336064. Throughput: 0: 10068.1. Samples: 85315800. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:14:10,829][613581] Avg episode reward: [(0, '4405.838')] [2023-03-09 05:14:12,983][613885] Updated weights for policy 0, policy_version 166720 (0.0005) [2023-03-09 05:14:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10103.5, 300 sec: 10108.1). Total num frames: 85389312. Throughput: 0: 9966.1. Samples: 85374780. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:14:15,829][613581] Avg episode reward: [(0, '4164.364')] [2023-03-09 05:14:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000166776_85389312.pth... [2023-03-09 05:14:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000166184_85086208.pth [2023-03-09 05:14:16,979][613885] Updated weights for policy 0, policy_version 166800 (0.0004) [2023-03-09 05:14:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 10094.2). Total num frames: 85438464. Throughput: 0: 9957.6. Samples: 85434880. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:14:20,829][613581] Avg episode reward: [(0, '4445.130')] [2023-03-09 05:14:21,171][613885] Updated weights for policy 0, policy_version 166880 (0.0005) [2023-03-09 05:14:25,252][613885] Updated weights for policy 0, policy_version 166960 (0.0005) [2023-03-09 05:14:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10035.2, 300 sec: 10094.2). Total num frames: 85487616. Throughput: 0: 9960.7. Samples: 85464576. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:14:25,829][613581] Avg episode reward: [(0, '4432.129')] [2023-03-09 05:14:29,399][613885] Updated weights for policy 0, policy_version 167040 (0.0004) [2023-03-09 05:14:30,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 10108.1). Total num frames: 85536768. Throughput: 0: 9985.9. Samples: 85524480. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:14:30,829][613581] Avg episode reward: [(0, '4497.782')] [2023-03-09 05:14:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000167064_85536768.pth... [2023-03-09 05:14:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000166480_85237760.pth [2023-03-09 05:14:33,540][613885] Updated weights for policy 0, policy_version 167120 (0.0005) [2023-03-09 05:14:35,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 10108.1). Total num frames: 85585920. Throughput: 0: 9965.2. Samples: 85583508. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:14:35,829][613581] Avg episode reward: [(0, '4361.579')] [2023-03-09 05:14:37,921][613885] Updated weights for policy 0, policy_version 167200 (0.0005) [2023-03-09 05:14:40,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9898.7, 300 sec: 10108.1). Total num frames: 85630976. Throughput: 0: 9921.6. Samples: 85610512. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:14:40,829][613581] Avg episode reward: [(0, '4068.176')] [2023-03-09 05:14:42,242][613885] Updated weights for policy 0, policy_version 167280 (0.0004) [2023-03-09 05:14:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 10122.0). Total num frames: 85684224. Throughput: 0: 9925.0. Samples: 85670472. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:14:45,829][613581] Avg episode reward: [(0, '4408.296')] [2023-03-09 05:14:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000167352_85684224.pth... [2023-03-09 05:14:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000166776_85389312.pth [2023-03-09 05:14:46,183][613885] Updated weights for policy 0, policy_version 167360 (0.0005) [2023-03-09 05:14:50,347][613885] Updated weights for policy 0, policy_version 167440 (0.0005) [2023-03-09 05:14:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 10122.0). Total num frames: 85733376. Throughput: 0: 9827.0. Samples: 85729352. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:14:50,829][613581] Avg episode reward: [(0, '4571.959')] [2023-03-09 05:14:54,399][613885] Updated weights for policy 0, policy_version 167520 (0.0006) [2023-03-09 05:14:55,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9966.9, 300 sec: 10122.0). Total num frames: 85782528. Throughput: 0: 9870.2. Samples: 85759960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:14:55,830][613581] Avg episode reward: [(0, '4407.996')] [2023-03-09 05:14:58,392][613885] Updated weights for policy 0, policy_version 167600 (0.0005) [2023-03-09 05:15:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 10122.0). Total num frames: 85831680. Throughput: 0: 9916.4. Samples: 85821016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:15:00,829][613581] Avg episode reward: [(0, '4505.909')] [2023-03-09 05:15:00,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000167640_85831680.pth... [2023-03-09 05:15:00,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000167064_85536768.pth [2023-03-09 05:15:02,471][613885] Updated weights for policy 0, policy_version 167680 (0.0005) [2023-03-09 05:15:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 10122.0). Total num frames: 85880832. Throughput: 0: 9907.8. Samples: 85880732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:15:05,829][613581] Avg episode reward: [(0, '4376.699')] [2023-03-09 05:15:06,594][613885] Updated weights for policy 0, policy_version 167760 (0.0005) [2023-03-09 05:15:10,524][613885] Updated weights for policy 0, policy_version 167840 (0.0005) [2023-03-09 05:15:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 10122.0). Total num frames: 85934080. Throughput: 0: 9914.6. Samples: 85910732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:15:10,829][613581] Avg episode reward: [(0, '4572.312')] [2023-03-09 05:15:14,563][613885] Updated weights for policy 0, policy_version 167920 (0.0005) [2023-03-09 05:15:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9898.7, 300 sec: 10135.9). Total num frames: 85983232. Throughput: 0: 9982.2. Samples: 85973676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:15:15,829][613581] Avg episode reward: [(0, '4389.800')] [2023-03-09 05:15:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000167936_85983232.pth... [2023-03-09 05:15:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000167352_85684224.pth [2023-03-09 05:15:18,558][613885] Updated weights for policy 0, policy_version 168000 (0.0004) [2023-03-09 05:15:20,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9966.9, 300 sec: 10135.9). Total num frames: 86036480. Throughput: 0: 10026.3. Samples: 86034692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:15:20,829][613581] Avg episode reward: [(0, '4627.816')] [2023-03-09 05:15:22,679][613885] Updated weights for policy 0, policy_version 168080 (0.0004) [2023-03-09 05:15:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 9966.9, 300 sec: 10135.9). Total num frames: 86085632. Throughput: 0: 10084.1. Samples: 86064296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:15:25,829][613581] Avg episode reward: [(0, '4499.341')] [2023-03-09 05:15:26,769][613885] Updated weights for policy 0, policy_version 168160 (0.0005) [2023-03-09 05:15:30,650][613885] Updated weights for policy 0, policy_version 168240 (0.0005) [2023-03-09 05:15:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 10135.9). Total num frames: 86138880. Throughput: 0: 10087.7. Samples: 86124420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:15:30,829][613581] Avg episode reward: [(0, '4630.851')] [2023-03-09 05:15:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000168240_86138880.pth... [2023-03-09 05:15:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000167640_85831680.pth [2023-03-09 05:15:34,606][613885] Updated weights for policy 0, policy_version 168320 (0.0005) [2023-03-09 05:15:35,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10103.5, 300 sec: 10149.7). Total num frames: 86192128. Throughput: 0: 10193.1. Samples: 86188040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:15:35,829][613581] Avg episode reward: [(0, '4468.481')] [2023-03-09 05:15:38,109][613885] Updated weights for policy 0, policy_version 168400 (0.0004) [2023-03-09 05:15:40,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10240.0, 300 sec: 10149.8). Total num frames: 86245376. Throughput: 0: 10316.6. Samples: 86224204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:15:40,829][613581] Avg episode reward: [(0, '4503.939')] [2023-03-09 05:15:42,096][613885] Updated weights for policy 0, policy_version 168480 (0.0005) [2023-03-09 05:15:45,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10240.0, 300 sec: 10163.6). Total num frames: 86298624. Throughput: 0: 10340.1. Samples: 86286320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:15:45,829][613581] Avg episode reward: [(0, '4544.131')] [2023-03-09 05:15:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000168552_86298624.pth... [2023-03-09 05:15:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000167936_85983232.pth [2023-03-09 05:15:45,876][613885] Updated weights for policy 0, policy_version 168560 (0.0005) [2023-03-09 05:15:49,897][613885] Updated weights for policy 0, policy_version 168640 (0.0005) [2023-03-09 05:15:50,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10163.6). Total num frames: 86351872. Throughput: 0: 10393.2. Samples: 86348428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:15:50,829][613581] Avg episode reward: [(0, '4625.098')] [2023-03-09 05:15:53,901][613885] Updated weights for policy 0, policy_version 168720 (0.0005) [2023-03-09 05:15:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10163.6). Total num frames: 86401024. Throughput: 0: 10407.5. Samples: 86379072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:15:55,829][613581] Avg episode reward: [(0, '4592.444')] [2023-03-09 05:15:57,964][613885] Updated weights for policy 0, policy_version 168800 (0.0005) [2023-03-09 05:16:00,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10163.6). Total num frames: 86454272. Throughput: 0: 10370.5. Samples: 86440348. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:16:00,829][613581] Avg episode reward: [(0, '4501.074')] [2023-03-09 05:16:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000168856_86454272.pth... [2023-03-09 05:16:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000168240_86138880.pth [2023-03-09 05:16:01,984][613885] Updated weights for policy 0, policy_version 168880 (0.0005) [2023-03-09 05:16:05,790][613885] Updated weights for policy 0, policy_version 168960 (0.0005) [2023-03-09 05:16:05,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10177.5). Total num frames: 86507520. Throughput: 0: 10414.9. Samples: 86503364. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:16:05,829][613581] Avg episode reward: [(0, '4281.692')] [2023-03-09 05:16:09,677][613885] Updated weights for policy 0, policy_version 169040 (0.0005) [2023-03-09 05:16:10,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10205.3). Total num frames: 86560768. Throughput: 0: 10480.8. Samples: 86535936. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:16:10,830][613581] Avg episode reward: [(0, '4256.835')] [2023-03-09 05:16:13,440][613885] Updated weights for policy 0, policy_version 169120 (0.0005) [2023-03-09 05:16:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10444.8, 300 sec: 10177.5). Total num frames: 86609920. Throughput: 0: 10541.0. Samples: 86598764. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:16:15,829][613581] Avg episode reward: [(0, '4431.041')] [2023-03-09 05:16:15,855][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000169168_86614016.pth... [2023-03-09 05:16:15,857][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000168552_86298624.pth [2023-03-09 05:16:17,358][613885] Updated weights for policy 0, policy_version 169200 (0.0006) [2023-03-09 05:16:20,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10444.8, 300 sec: 10191.4). Total num frames: 86663168. Throughput: 0: 10486.7. Samples: 86659940. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:16:20,829][613581] Avg episode reward: [(0, '4391.820')] [2023-03-09 05:16:21,486][613885] Updated weights for policy 0, policy_version 169280 (0.0005) [2023-03-09 05:16:25,701][613885] Updated weights for policy 0, policy_version 169360 (0.0005) [2023-03-09 05:16:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10444.8, 300 sec: 10177.5). Total num frames: 86712320. Throughput: 0: 10366.9. Samples: 86690716. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:16:25,829][613581] Avg episode reward: [(0, '4370.173')] [2023-03-09 05:16:29,516][613885] Updated weights for policy 0, policy_version 169440 (0.0005) [2023-03-09 05:16:30,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10376.5, 300 sec: 10177.5). Total num frames: 86761472. Throughput: 0: 10369.2. Samples: 86752932. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:16:30,829][613581] Avg episode reward: [(0, '4629.660')] [2023-03-09 05:16:30,861][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000169464_86765568.pth... [2023-03-09 05:16:30,863][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000168856_86454272.pth [2023-03-09 05:16:33,566][613885] Updated weights for policy 0, policy_version 169520 (0.0005) [2023-03-09 05:16:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.6, 300 sec: 10205.3). Total num frames: 86814720. Throughput: 0: 10339.1. Samples: 86813688. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:16:35,829][613581] Avg episode reward: [(0, '4608.940')] [2023-03-09 05:16:37,438][613885] Updated weights for policy 0, policy_version 169600 (0.0005) [2023-03-09 05:16:40,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10205.3). Total num frames: 86867968. Throughput: 0: 10331.6. Samples: 86843992. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:16:40,829][613581] Avg episode reward: [(0, '4604.209')] [2023-03-09 05:16:41,250][613885] Updated weights for policy 0, policy_version 169680 (0.0005) [2023-03-09 05:16:45,141][613885] Updated weights for policy 0, policy_version 169760 (0.0004) [2023-03-09 05:16:45,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10376.5, 300 sec: 10205.3). Total num frames: 86921216. Throughput: 0: 10412.9. Samples: 86908928. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:16:45,829][613581] Avg episode reward: [(0, '4484.030')] [2023-03-09 05:16:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000169768_86921216.pth... [2023-03-09 05:16:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000169168_86614016.pth [2023-03-09 05:16:49,165][613885] Updated weights for policy 0, policy_version 169840 (0.0005) [2023-03-09 05:16:50,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10376.5, 300 sec: 10219.2). Total num frames: 86974464. Throughput: 0: 10378.1. Samples: 86970376. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:16:50,829][613581] Avg episode reward: [(0, '4621.490')] [2023-03-09 05:16:53,310][613885] Updated weights for policy 0, policy_version 169920 (0.0005) [2023-03-09 05:16:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10205.3). Total num frames: 87023616. Throughput: 0: 10299.0. Samples: 86999388. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:16:55,829][613581] Avg episode reward: [(0, '4519.328')] [2023-03-09 05:16:57,362][613885] Updated weights for policy 0, policy_version 170000 (0.0005) [2023-03-09 05:17:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10308.3, 300 sec: 10191.4). Total num frames: 87072768. Throughput: 0: 10262.0. Samples: 87060552. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:17:00,829][613581] Avg episode reward: [(0, '4470.305')] [2023-03-09 05:17:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000170064_87072768.pth... [2023-03-09 05:17:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000169464_86765568.pth [2023-03-09 05:17:01,581][613885] Updated weights for policy 0, policy_version 170080 (0.0004) [2023-03-09 05:17:05,681][613885] Updated weights for policy 0, policy_version 170160 (0.0004) [2023-03-09 05:17:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10191.4). Total num frames: 87121920. Throughput: 0: 10216.0. Samples: 87119660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:17:05,829][613581] Avg episode reward: [(0, '4496.132')] [2023-03-09 05:17:09,813][613885] Updated weights for policy 0, policy_version 170240 (0.0005) [2023-03-09 05:17:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10171.7, 300 sec: 10191.4). Total num frames: 87171072. Throughput: 0: 10178.2. Samples: 87148736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:17:10,829][613581] Avg episode reward: [(0, '4406.278')] [2023-03-09 05:17:13,818][613885] Updated weights for policy 0, policy_version 170320 (0.0005) [2023-03-09 05:17:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10191.4). Total num frames: 87224320. Throughput: 0: 10169.3. Samples: 87210552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:17:15,829][613581] Avg episode reward: [(0, '4376.914')] [2023-03-09 05:17:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000170360_87224320.pth... [2023-03-09 05:17:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000169768_86921216.pth [2023-03-09 05:17:17,814][613885] Updated weights for policy 0, policy_version 170400 (0.0005) [2023-03-09 05:17:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10191.4). Total num frames: 87273472. Throughput: 0: 10149.8. Samples: 87270432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:17:20,829][613581] Avg episode reward: [(0, '4549.924')] [2023-03-09 05:17:21,929][613885] Updated weights for policy 0, policy_version 170480 (0.0005) [2023-03-09 05:17:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10171.7, 300 sec: 10191.4). Total num frames: 87322624. Throughput: 0: 10159.6. Samples: 87301176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:17:25,829][613581] Avg episode reward: [(0, '4570.707')] [2023-03-09 05:17:25,980][613885] Updated weights for policy 0, policy_version 170560 (0.0005) [2023-03-09 05:17:29,796][613885] Updated weights for policy 0, policy_version 170640 (0.0005) [2023-03-09 05:17:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10191.4). Total num frames: 87375872. Throughput: 0: 10103.4. Samples: 87363584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:17:30,829][613581] Avg episode reward: [(0, '4585.304')] [2023-03-09 05:17:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000170656_87375872.pth... [2023-03-09 05:17:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000170064_87072768.pth [2023-03-09 05:17:33,849][613885] Updated weights for policy 0, policy_version 170720 (0.0005) [2023-03-09 05:17:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10171.7, 300 sec: 10177.5). Total num frames: 87425024. Throughput: 0: 10074.5. Samples: 87423728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:17:35,829][613581] Avg episode reward: [(0, '4528.632')] [2023-03-09 05:17:38,082][613885] Updated weights for policy 0, policy_version 170800 (0.0005) [2023-03-09 05:17:40,829][613581] Fps is (10 sec: 9830.6, 60 sec: 10103.5, 300 sec: 10177.5). Total num frames: 87474176. Throughput: 0: 10092.1. Samples: 87453532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:17:40,829][613581] Avg episode reward: [(0, '4580.253')] [2023-03-09 05:17:42,083][613885] Updated weights for policy 0, policy_version 170880 (0.0005) [2023-03-09 05:17:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10103.5, 300 sec: 10163.6). Total num frames: 87527424. Throughput: 0: 10136.6. Samples: 87516700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:17:45,829][613581] Avg episode reward: [(0, '4492.413')] [2023-03-09 05:17:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000170960_87531520.pth... [2023-03-09 05:17:45,833][613885] Updated weights for policy 0, policy_version 170960 (0.0005) [2023-03-09 05:17:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000170360_87224320.pth [2023-03-09 05:17:49,858][613885] Updated weights for policy 0, policy_version 171040 (0.0005) [2023-03-09 05:17:50,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10103.4, 300 sec: 10177.5). Total num frames: 87580672. Throughput: 0: 10175.0. Samples: 87577536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:17:50,829][613581] Avg episode reward: [(0, '4433.019')] [2023-03-09 05:17:54,035][613885] Updated weights for policy 0, policy_version 171120 (0.0004) [2023-03-09 05:17:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10103.5, 300 sec: 10163.6). Total num frames: 87629824. Throughput: 0: 10181.4. Samples: 87606896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:17:55,829][613581] Avg episode reward: [(0, '4562.321')] [2023-03-09 05:17:58,188][613885] Updated weights for policy 0, policy_version 171200 (0.0004) [2023-03-09 05:18:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10103.5, 300 sec: 10163.6). Total num frames: 87678976. Throughput: 0: 10137.8. Samples: 87666752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:18:00,829][613581] Avg episode reward: [(0, '4390.761')] [2023-03-09 05:18:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000171248_87678976.pth... [2023-03-09 05:18:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000170656_87375872.pth [2023-03-09 05:18:02,386][613885] Updated weights for policy 0, policy_version 171280 (0.0004) [2023-03-09 05:18:05,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10171.7, 300 sec: 10177.5). Total num frames: 87732224. Throughput: 0: 10192.1. Samples: 87729076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:18:05,829][613581] Avg episode reward: [(0, '4465.411')] [2023-03-09 05:18:06,024][613885] Updated weights for policy 0, policy_version 171360 (0.0004) [2023-03-09 05:18:09,775][613885] Updated weights for policy 0, policy_version 171440 (0.0006) [2023-03-09 05:18:10,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10240.0, 300 sec: 10177.5). Total num frames: 87785472. Throughput: 0: 10239.3. Samples: 87761944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:18:10,829][613581] Avg episode reward: [(0, '4388.231')] [2023-03-09 05:18:13,649][613885] Updated weights for policy 0, policy_version 171520 (0.0005) [2023-03-09 05:18:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10240.0, 300 sec: 10191.4). Total num frames: 87838720. Throughput: 0: 10284.0. Samples: 87826364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:18:15,829][613581] Avg episode reward: [(0, '4366.578')] [2023-03-09 05:18:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000171560_87838720.pth... [2023-03-09 05:18:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000170960_87531520.pth [2023-03-09 05:18:17,412][613885] Updated weights for policy 0, policy_version 171600 (0.0005) [2023-03-09 05:18:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10191.4). Total num frames: 87891968. Throughput: 0: 10365.1. Samples: 87890156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:18:20,829][613581] Avg episode reward: [(0, '3882.051')] [2023-03-09 05:18:21,442][613885] Updated weights for policy 0, policy_version 171680 (0.0005) [2023-03-09 05:18:25,678][613885] Updated weights for policy 0, policy_version 171760 (0.0005) [2023-03-09 05:18:25,829][613581] Fps is (10 sec: 10240.2, 60 sec: 10308.3, 300 sec: 10177.5). Total num frames: 87941120. Throughput: 0: 10357.4. Samples: 87919616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:18:25,829][613581] Avg episode reward: [(0, '4133.949')] [2023-03-09 05:18:29,640][613885] Updated weights for policy 0, policy_version 171840 (0.0004) [2023-03-09 05:18:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10191.4). Total num frames: 87994368. Throughput: 0: 10287.1. Samples: 87979620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:18:30,829][613581] Avg episode reward: [(0, '4199.444')] [2023-03-09 05:18:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000171864_87994368.pth... [2023-03-09 05:18:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000171248_87678976.pth [2023-03-09 05:18:33,301][613885] Updated weights for policy 0, policy_version 171920 (0.0005) [2023-03-09 05:18:35,829][613581] Fps is (10 sec: 10649.4, 60 sec: 10376.5, 300 sec: 10205.3). Total num frames: 88047616. Throughput: 0: 10391.7. Samples: 88045164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:18:35,829][613581] Avg episode reward: [(0, '4390.206')] [2023-03-09 05:18:37,241][613885] Updated weights for policy 0, policy_version 172000 (0.0005) [2023-03-09 05:18:40,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 10205.3). Total num frames: 88096768. Throughput: 0: 10429.4. Samples: 88076220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:18:40,829][613581] Avg episode reward: [(0, '4431.877')] [2023-03-09 05:18:41,414][613885] Updated weights for policy 0, policy_version 172080 (0.0005) [2023-03-09 05:18:45,507][613885] Updated weights for policy 0, policy_version 172160 (0.0004) [2023-03-09 05:18:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 10205.3). Total num frames: 88145920. Throughput: 0: 10375.3. Samples: 88133640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:18:45,829][613581] Avg episode reward: [(0, '4403.726')] [2023-03-09 05:18:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000172160_88145920.pth... [2023-03-09 05:18:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000171560_87838720.pth [2023-03-09 05:18:49,514][613885] Updated weights for policy 0, policy_version 172240 (0.0005) [2023-03-09 05:18:50,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10240.0, 300 sec: 10205.3). Total num frames: 88195072. Throughput: 0: 10355.4. Samples: 88195068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:18:50,829][613581] Avg episode reward: [(0, '4360.985')] [2023-03-09 05:18:53,419][613885] Updated weights for policy 0, policy_version 172320 (0.0004) [2023-03-09 05:18:55,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10205.3). Total num frames: 88248320. Throughput: 0: 10350.9. Samples: 88227736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:18:55,829][613581] Avg episode reward: [(0, '4486.030')] [2023-03-09 05:18:57,574][613885] Updated weights for policy 0, policy_version 172400 (0.0004) [2023-03-09 05:19:00,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10205.3). Total num frames: 88301568. Throughput: 0: 10213.5. Samples: 88285972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:19:00,829][613581] Avg episode reward: [(0, '4437.655')] [2023-03-09 05:19:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000172464_88301568.pth... [2023-03-09 05:19:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000171864_87994368.pth [2023-03-09 05:19:01,556][613885] Updated weights for policy 0, policy_version 172480 (0.0004) [2023-03-09 05:19:05,489][613885] Updated weights for policy 0, policy_version 172560 (0.0005) [2023-03-09 05:19:05,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10219.2). Total num frames: 88350720. Throughput: 0: 10220.2. Samples: 88350064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:19:05,829][613581] Avg episode reward: [(0, '4458.056')] [2023-03-09 05:19:09,293][613885] Updated weights for policy 0, policy_version 172640 (0.0005) [2023-03-09 05:19:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10219.2). Total num frames: 88403968. Throughput: 0: 10270.7. Samples: 88381800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:19:10,829][613581] Avg episode reward: [(0, '4351.409')] [2023-03-09 05:19:13,420][613885] Updated weights for policy 0, policy_version 172720 (0.0004) [2023-03-09 05:19:15,829][613581] Fps is (10 sec: 10649.5, 60 sec: 10308.3, 300 sec: 10233.1). Total num frames: 88457216. Throughput: 0: 10311.8. Samples: 88443652. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:19:15,829][613581] Avg episode reward: [(0, '4482.225')] [2023-03-09 05:19:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000172768_88457216.pth... [2023-03-09 05:19:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000172160_88145920.pth [2023-03-09 05:19:16,970][613885] Updated weights for policy 0, policy_version 172800 (0.0005) [2023-03-09 05:19:20,829][613581] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10246.9). Total num frames: 88510464. Throughput: 0: 10260.5. Samples: 88506888. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:19:20,829][613581] Avg episode reward: [(0, '4348.490')] [2023-03-09 05:19:21,108][613885] Updated weights for policy 0, policy_version 172880 (0.0005) [2023-03-09 05:19:25,200][613885] Updated weights for policy 0, policy_version 172960 (0.0005) [2023-03-09 05:19:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10308.2, 300 sec: 10246.9). Total num frames: 88559616. Throughput: 0: 10238.8. Samples: 88536968. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:19:25,829][613581] Avg episode reward: [(0, '4177.197')] [2023-03-09 05:19:29,143][613885] Updated weights for policy 0, policy_version 173040 (0.0005) [2023-03-09 05:19:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10260.8). Total num frames: 88612864. Throughput: 0: 10353.7. Samples: 88599556. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:19:30,829][613581] Avg episode reward: [(0, '4321.423')] [2023-03-09 05:19:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000173072_88612864.pth... [2023-03-09 05:19:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000172464_88301568.pth [2023-03-09 05:19:33,145][613885] Updated weights for policy 0, policy_version 173120 (0.0005) [2023-03-09 05:19:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10274.7). Total num frames: 88662016. Throughput: 0: 10299.2. Samples: 88658532. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:19:35,829][613581] Avg episode reward: [(0, '4423.597')] [2023-03-09 05:19:37,402][613885] Updated weights for policy 0, policy_version 173200 (0.0005) [2023-03-09 05:19:40,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10274.7). Total num frames: 88715264. Throughput: 0: 10259.5. Samples: 88689416. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:19:40,829][613581] Avg episode reward: [(0, '4304.312')] [2023-03-09 05:19:41,169][613885] Updated weights for policy 0, policy_version 173280 (0.0005) [2023-03-09 05:19:45,237][613885] Updated weights for policy 0, policy_version 173360 (0.0005) [2023-03-09 05:19:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 10308.3, 300 sec: 10274.7). Total num frames: 88764416. Throughput: 0: 10360.4. Samples: 88752192. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:19:45,829][613581] Avg episode reward: [(0, '4116.875')] [2023-03-09 05:19:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000173368_88764416.pth... [2023-03-09 05:19:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000172768_88457216.pth [2023-03-09 05:19:49,305][613885] Updated weights for policy 0, policy_version 173440 (0.0005) [2023-03-09 05:19:50,829][613581] Fps is (10 sec: 9830.3, 60 sec: 10308.2, 300 sec: 10274.7). Total num frames: 88813568. Throughput: 0: 10254.3. Samples: 88811508. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:19:50,830][613581] Avg episode reward: [(0, '4253.458')] [2023-03-09 05:19:53,383][613885] Updated weights for policy 0, policy_version 173520 (0.0005) [2023-03-09 05:19:55,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10240.0, 300 sec: 10274.7). Total num frames: 88862720. Throughput: 0: 10231.7. Samples: 88842224. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:19:55,829][613581] Avg episode reward: [(0, '4211.939')] [2023-03-09 05:19:57,559][613885] Updated weights for policy 0, policy_version 173600 (0.0005) [2023-03-09 05:20:00,829][613581] Fps is (10 sec: 9830.5, 60 sec: 10171.7, 300 sec: 10274.7). Total num frames: 88911872. Throughput: 0: 10131.8. Samples: 88899584. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:20:00,829][613581] Avg episode reward: [(0, '4341.555')] [2023-03-09 05:20:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000173656_88911872.pth... [2023-03-09 05:20:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000173072_88612864.pth [2023-03-09 05:20:01,904][613885] Updated weights for policy 0, policy_version 173680 (0.0005) [2023-03-09 05:20:05,829][613581] Fps is (10 sec: 9420.7, 60 sec: 10103.5, 300 sec: 10246.9). Total num frames: 88956928. Throughput: 0: 9995.9. Samples: 88956704. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:20:05,829][613581] Avg episode reward: [(0, '4237.034')] [2023-03-09 05:20:06,368][613885] Updated weights for policy 0, policy_version 173760 (0.0005) [2023-03-09 05:20:10,665][613885] Updated weights for policy 0, policy_version 173840 (0.0005) [2023-03-09 05:20:10,829][613581] Fps is (10 sec: 9420.9, 60 sec: 10035.2, 300 sec: 10246.9). Total num frames: 89006080. Throughput: 0: 9925.2. Samples: 88983600. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:20:10,829][613581] Avg episode reward: [(0, '4035.188')] [2023-03-09 05:20:14,715][613885] Updated weights for policy 0, policy_version 173920 (0.0005) [2023-03-09 05:20:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 10233.1). Total num frames: 89055232. Throughput: 0: 9869.8. Samples: 89043696. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 05:20:15,829][613581] Avg episode reward: [(0, '4341.543')] [2023-03-09 05:20:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000173936_89055232.pth... [2023-03-09 05:20:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000173368_88764416.pth [2023-03-09 05:20:18,883][613885] Updated weights for policy 0, policy_version 174000 (0.0005) [2023-03-09 05:20:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 10246.9). Total num frames: 89108480. Throughput: 0: 9923.1. Samples: 89105072. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:20:20,829][613581] Avg episode reward: [(0, '4183.287')] [2023-03-09 05:20:22,680][613885] Updated weights for policy 0, policy_version 174080 (0.0005) [2023-03-09 05:20:25,829][613581] Fps is (10 sec: 10240.2, 60 sec: 9967.0, 300 sec: 10233.1). Total num frames: 89157632. Throughput: 0: 9918.1. Samples: 89135728. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:20:25,829][613581] Avg episode reward: [(0, '4218.429')] [2023-03-09 05:20:26,864][613885] Updated weights for policy 0, policy_version 174160 (0.0004) [2023-03-09 05:20:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 10219.2). Total num frames: 89206784. Throughput: 0: 9844.6. Samples: 89195200. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:20:30,829][613581] Avg episode reward: [(0, '4174.364')] [2023-03-09 05:20:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000174232_89206784.pth... [2023-03-09 05:20:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000173656_88911872.pth [2023-03-09 05:20:31,066][613885] Updated weights for policy 0, policy_version 174240 (0.0005) [2023-03-09 05:20:34,906][613885] Updated weights for policy 0, policy_version 174320 (0.0005) [2023-03-09 05:20:35,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9966.9, 300 sec: 10219.2). Total num frames: 89260032. Throughput: 0: 9912.6. Samples: 89257572. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:20:35,829][613581] Avg episode reward: [(0, '4246.074')] [2023-03-09 05:20:38,964][613885] Updated weights for policy 0, policy_version 174400 (0.0005) [2023-03-09 05:20:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9898.7, 300 sec: 10205.3). Total num frames: 89309184. Throughput: 0: 9919.8. Samples: 89288616. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:20:40,829][613581] Avg episode reward: [(0, '4351.848')] [2023-03-09 05:20:42,906][613885] Updated weights for policy 0, policy_version 174480 (0.0005) [2023-03-09 05:20:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9966.9, 300 sec: 10205.3). Total num frames: 89362432. Throughput: 0: 9955.3. Samples: 89347572. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:20:45,830][613581] Avg episode reward: [(0, '4267.744')] [2023-03-09 05:20:45,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000174536_89362432.pth... [2023-03-09 05:20:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000173936_89055232.pth [2023-03-09 05:20:47,089][613885] Updated weights for policy 0, policy_version 174560 (0.0005) [2023-03-09 05:20:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 10191.4). Total num frames: 89407488. Throughput: 0: 9978.3. Samples: 89405728. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:20:50,829][613581] Avg episode reward: [(0, '4318.180')] [2023-03-09 05:20:51,524][613885] Updated weights for policy 0, policy_version 174640 (0.0004) [2023-03-09 05:20:55,606][613885] Updated weights for policy 0, policy_version 174720 (0.0005) [2023-03-09 05:20:55,829][613581] Fps is (10 sec: 9421.0, 60 sec: 9898.7, 300 sec: 10177.5). Total num frames: 89456640. Throughput: 0: 9974.0. Samples: 89432428. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:20:55,829][613581] Avg episode reward: [(0, '4434.389')] [2023-03-09 05:20:59,731][613885] Updated weights for policy 0, policy_version 174800 (0.0005) [2023-03-09 05:21:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9898.7, 300 sec: 10163.6). Total num frames: 89505792. Throughput: 0: 9997.2. Samples: 89493568. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:21:00,829][613581] Avg episode reward: [(0, '4416.938')] [2023-03-09 05:21:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000174816_89505792.pth... [2023-03-09 05:21:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000174232_89206784.pth [2023-03-09 05:21:03,933][613885] Updated weights for policy 0, policy_version 174880 (0.0004) [2023-03-09 05:21:05,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 10149.8). Total num frames: 89554944. Throughput: 0: 9945.2. Samples: 89552604. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:21:05,829][613581] Avg episode reward: [(0, '4271.268')] [2023-03-09 05:21:08,396][613885] Updated weights for policy 0, policy_version 174960 (0.0005) [2023-03-09 05:21:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9898.7, 300 sec: 10135.9). Total num frames: 89600000. Throughput: 0: 9862.0. Samples: 89579520. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:21:10,830][613581] Avg episode reward: [(0, '4567.451')] [2023-03-09 05:21:12,711][613885] Updated weights for policy 0, policy_version 175040 (0.0005) [2023-03-09 05:21:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9898.7, 300 sec: 10122.0). Total num frames: 89649152. Throughput: 0: 9810.0. Samples: 89636652. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:21:15,829][613581] Avg episode reward: [(0, '4450.592')] [2023-03-09 05:21:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000175096_89649152.pth... [2023-03-09 05:21:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000174536_89362432.pth [2023-03-09 05:21:16,761][613885] Updated weights for policy 0, policy_version 175120 (0.0005) [2023-03-09 05:21:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 10122.0). Total num frames: 89698304. Throughput: 0: 9792.4. Samples: 89698228. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-09 05:21:20,829][613581] Avg episode reward: [(0, '4455.299')] [2023-03-09 05:21:20,914][613885] Updated weights for policy 0, policy_version 175200 (0.0005) [2023-03-09 05:21:25,112][613885] Updated weights for policy 0, policy_version 175280 (0.0005) [2023-03-09 05:21:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 10122.0). Total num frames: 89747456. Throughput: 0: 9742.8. Samples: 89727040. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:21:25,829][613581] Avg episode reward: [(0, '4415.537')] [2023-03-09 05:21:29,311][613885] Updated weights for policy 0, policy_version 175360 (0.0005) [2023-03-09 05:21:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 10108.1). Total num frames: 89796608. Throughput: 0: 9711.2. Samples: 89784576. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:21:30,829][613581] Avg episode reward: [(0, '4511.283')] [2023-03-09 05:21:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000175384_89796608.pth... [2023-03-09 05:21:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000174816_89505792.pth [2023-03-09 05:21:33,262][613885] Updated weights for policy 0, policy_version 175440 (0.0005) [2023-03-09 05:21:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9830.4, 300 sec: 10108.1). Total num frames: 89849856. Throughput: 0: 9792.1. Samples: 89846372. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:21:35,829][613581] Avg episode reward: [(0, '4556.740')] [2023-03-09 05:21:37,359][613885] Updated weights for policy 0, policy_version 175520 (0.0005) [2023-03-09 05:21:40,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9830.4, 300 sec: 10094.2). Total num frames: 89899008. Throughput: 0: 9884.1. Samples: 89877212. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:21:40,829][613581] Avg episode reward: [(0, '4528.118')] [2023-03-09 05:21:41,417][613885] Updated weights for policy 0, policy_version 175600 (0.0005) [2023-03-09 05:21:45,410][613885] Updated weights for policy 0, policy_version 175680 (0.0005) [2023-03-09 05:21:45,829][613581] Fps is (10 sec: 10239.8, 60 sec: 9830.4, 300 sec: 10094.2). Total num frames: 89952256. Throughput: 0: 9852.4. Samples: 89936928. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:21:45,840][613581] Avg episode reward: [(0, '4537.749')] [2023-03-09 05:21:45,844][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000175688_89952256.pth... [2023-03-09 05:21:45,847][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000175096_89649152.pth [2023-03-09 05:21:49,561][613885] Updated weights for policy 0, policy_version 175760 (0.0005) [2023-03-09 05:21:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 10080.3). Total num frames: 89997312. Throughput: 0: 9879.8. Samples: 89997196. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:21:50,840][613581] Avg episode reward: [(0, '4591.990')] [2023-03-09 05:21:53,742][613885] Updated weights for policy 0, policy_version 175840 (0.0005) [2023-03-09 05:21:55,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9898.6, 300 sec: 10094.2). Total num frames: 90050560. Throughput: 0: 9929.1. Samples: 90026328. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:21:55,840][613581] Avg episode reward: [(0, '4565.863')] [2023-03-09 05:21:57,943][613885] Updated weights for policy 0, policy_version 175920 (0.0005) [2023-03-09 05:22:00,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 10094.2). Total num frames: 90099712. Throughput: 0: 10015.9. Samples: 90087368. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:22:00,840][613581] Avg episode reward: [(0, '4574.007')] [2023-03-09 05:22:00,843][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000175976_90099712.pth... [2023-03-09 05:22:00,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000175384_89796608.pth [2023-03-09 05:22:01,992][613885] Updated weights for policy 0, policy_version 176000 (0.0005) [2023-03-09 05:22:05,829][613581] Fps is (10 sec: 9830.6, 60 sec: 9898.7, 300 sec: 10094.2). Total num frames: 90148864. Throughput: 0: 9924.6. Samples: 90144832. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:22:05,840][613581] Avg episode reward: [(0, '4563.381')] [2023-03-09 05:22:06,213][613885] Updated weights for policy 0, policy_version 176080 (0.0004) [2023-03-09 05:22:10,398][613885] Updated weights for policy 0, policy_version 176160 (0.0006) [2023-03-09 05:22:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10080.3). Total num frames: 90198016. Throughput: 0: 9941.4. Samples: 90174404. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:22:10,840][613581] Avg episode reward: [(0, '4536.748')] [2023-03-09 05:22:14,586][613885] Updated weights for policy 0, policy_version 176240 (0.0006) [2023-03-09 05:22:15,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9898.7, 300 sec: 10066.4). Total num frames: 90243072. Throughput: 0: 9971.3. Samples: 90233284. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:22:15,840][613581] Avg episode reward: [(0, '4587.350')] [2023-03-09 05:22:15,843][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000176256_90243072.pth... [2023-03-09 05:22:15,845][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000175688_89952256.pth [2023-03-09 05:22:18,834][613885] Updated weights for policy 0, policy_version 176320 (0.0005) [2023-03-09 05:22:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10080.3). Total num frames: 90296320. Throughput: 0: 9905.4. Samples: 90292116. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:22:20,840][613581] Avg episode reward: [(0, '4586.371')] [2023-03-09 05:22:22,954][613885] Updated weights for policy 0, policy_version 176400 (0.0005) [2023-03-09 05:22:25,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 10066.4). Total num frames: 90345472. Throughput: 0: 9859.6. Samples: 90320896. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-09 05:22:25,840][613581] Avg episode reward: [(0, '4588.925')] [2023-03-09 05:22:26,948][613885] Updated weights for policy 0, policy_version 176480 (0.0005) [2023-03-09 05:22:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10066.4). Total num frames: 90394624. Throughput: 0: 9898.3. Samples: 90382348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:22:30,840][613581] Avg episode reward: [(0, '4630.212')] [2023-03-09 05:22:30,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000176552_90394624.pth... [2023-03-09 05:22:30,844][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000175976_90099712.pth [2023-03-09 05:22:30,952][613885] Updated weights for policy 0, policy_version 176560 (0.0005) [2023-03-09 05:22:34,972][613885] Updated weights for policy 0, policy_version 176640 (0.0005) [2023-03-09 05:22:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 10080.3). Total num frames: 90447872. Throughput: 0: 9925.6. Samples: 90443848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:22:35,840][613581] Avg episode reward: [(0, '4573.846')] [2023-03-09 05:22:39,095][613885] Updated weights for policy 0, policy_version 176720 (0.0005) [2023-03-09 05:22:40,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9966.9, 300 sec: 10066.4). Total num frames: 90497024. Throughput: 0: 9937.0. Samples: 90473492. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:22:40,829][613581] Avg episode reward: [(0, '4597.374')] [2023-03-09 05:22:43,105][613885] Updated weights for policy 0, policy_version 176800 (0.0005) [2023-03-09 05:22:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 10052.6). Total num frames: 90546176. Throughput: 0: 9926.6. Samples: 90534064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:22:45,829][613581] Avg episode reward: [(0, '4619.934')] [2023-03-09 05:22:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000176848_90546176.pth... [2023-03-09 05:22:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000176256_90243072.pth [2023-03-09 05:22:47,283][613885] Updated weights for policy 0, policy_version 176880 (0.0005) [2023-03-09 05:22:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 10066.4). Total num frames: 90599424. Throughput: 0: 10010.3. Samples: 90595296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:22:50,829][613581] Avg episode reward: [(0, '4612.589')] [2023-03-09 05:22:51,227][613885] Updated weights for policy 0, policy_version 176960 (0.0005) [2023-03-09 05:22:55,347][613885] Updated weights for policy 0, policy_version 177040 (0.0005) [2023-03-09 05:22:55,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9966.9, 300 sec: 10066.4). Total num frames: 90648576. Throughput: 0: 10060.4. Samples: 90627120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:22:55,829][613581] Avg episode reward: [(0, '4596.263')] [2023-03-09 05:22:59,371][613885] Updated weights for policy 0, policy_version 177120 (0.0005) [2023-03-09 05:23:00,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9967.0, 300 sec: 10052.6). Total num frames: 90697728. Throughput: 0: 10049.4. Samples: 90685504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:23:00,840][613581] Avg episode reward: [(0, '4494.722')] [2023-03-09 05:23:00,842][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000177144_90697728.pth... [2023-03-09 05:23:00,845][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000176552_90394624.pth [2023-03-09 05:23:03,490][613885] Updated weights for policy 0, policy_version 177200 (0.0005) [2023-03-09 05:23:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 10038.7). Total num frames: 90746880. Throughput: 0: 10078.7. Samples: 90745660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:23:05,829][613581] Avg episode reward: [(0, '4486.129')] [2023-03-09 05:23:07,686][613885] Updated weights for policy 0, policy_version 177280 (0.0004) [2023-03-09 05:23:10,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 10024.8). Total num frames: 90796032. Throughput: 0: 10094.7. Samples: 90775156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:23:10,829][613581] Avg episode reward: [(0, '4614.644')] [2023-03-09 05:23:11,900][613885] Updated weights for policy 0, policy_version 177360 (0.0005) [2023-03-09 05:23:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 10010.9). Total num frames: 90845184. Throughput: 0: 10011.7. Samples: 90832876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:23:15,829][613581] Avg episode reward: [(0, '4531.054')] [2023-03-09 05:23:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000177432_90845184.pth... [2023-03-09 05:23:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000176848_90546176.pth [2023-03-09 05:23:15,972][613885] Updated weights for policy 0, policy_version 177440 (0.0005) [2023-03-09 05:23:19,847][613885] Updated weights for policy 0, policy_version 177520 (0.0005) [2023-03-09 05:23:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 10024.8). Total num frames: 90898432. Throughput: 0: 10024.3. Samples: 90894940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:23:20,829][613581] Avg episode reward: [(0, '4356.721')] [2023-03-09 05:23:23,901][613885] Updated weights for policy 0, policy_version 177600 (0.0005) [2023-03-09 05:23:25,829][613581] Fps is (10 sec: 10649.7, 60 sec: 10103.5, 300 sec: 10024.8). Total num frames: 90951680. Throughput: 0: 10046.6. Samples: 90925588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:23:25,829][613581] Avg episode reward: [(0, '4594.230')] [2023-03-09 05:23:27,954][613885] Updated weights for policy 0, policy_version 177680 (0.0004) [2023-03-09 05:23:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 10035.2, 300 sec: 9997.0). Total num frames: 90996736. Throughput: 0: 10047.9. Samples: 90986220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:23:30,829][613581] Avg episode reward: [(0, '4587.361')] [2023-03-09 05:23:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000177728_90996736.pth... [2023-03-09 05:23:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000177144_90697728.pth [2023-03-09 05:23:32,259][613885] Updated weights for policy 0, policy_version 177760 (0.0005) [2023-03-09 05:23:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9966.9, 300 sec: 9997.0). Total num frames: 91045888. Throughput: 0: 9973.0. Samples: 91044080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:23:35,829][613581] Avg episode reward: [(0, '4636.363')] [2023-03-09 05:23:36,467][613885] Updated weights for policy 0, policy_version 177840 (0.0004) [2023-03-09 05:23:40,615][613885] Updated weights for policy 0, policy_version 177920 (0.0005) [2023-03-09 05:23:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9966.9, 300 sec: 9997.0). Total num frames: 91095040. Throughput: 0: 9883.8. Samples: 91071892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:23:40,829][613581] Avg episode reward: [(0, '4591.539')] [2023-03-09 05:23:44,871][613885] Updated weights for policy 0, policy_version 178000 (0.0005) [2023-03-09 05:23:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 9997.0). Total num frames: 91144192. Throughput: 0: 9906.4. Samples: 91131292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:23:45,830][613581] Avg episode reward: [(0, '4590.901')] [2023-03-09 05:23:45,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000178016_91144192.pth... [2023-03-09 05:23:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000177432_90845184.pth [2023-03-09 05:23:49,124][613885] Updated weights for policy 0, policy_version 178080 (0.0004) [2023-03-09 05:23:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9983.1). Total num frames: 91193344. Throughput: 0: 9857.8. Samples: 91189260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:23:50,830][613581] Avg episode reward: [(0, '4618.953')] [2023-03-09 05:23:53,385][613885] Updated weights for policy 0, policy_version 178160 (0.0005) [2023-03-09 05:23:55,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9830.4, 300 sec: 9955.4). Total num frames: 91238400. Throughput: 0: 9839.4. Samples: 91217928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:23:55,829][613581] Avg episode reward: [(0, '4632.118')] [2023-03-09 05:23:57,766][613885] Updated weights for policy 0, policy_version 178240 (0.0005) [2023-03-09 05:24:00,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9830.4, 300 sec: 9955.4). Total num frames: 91287552. Throughput: 0: 9828.8. Samples: 91275172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:24:00,829][613581] Avg episode reward: [(0, '4501.664')] [2023-03-09 05:24:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000178296_91287552.pth... [2023-03-09 05:24:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000177728_90996736.pth [2023-03-09 05:24:01,808][613885] Updated weights for policy 0, policy_version 178320 (0.0006) [2023-03-09 05:24:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9941.5). Total num frames: 91336704. Throughput: 0: 9770.0. Samples: 91334592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:24:05,829][613581] Avg episode reward: [(0, '4605.132')] [2023-03-09 05:24:06,007][613885] Updated weights for policy 0, policy_version 178400 (0.0005) [2023-03-09 05:24:10,239][613885] Updated weights for policy 0, policy_version 178480 (0.0005) [2023-03-09 05:24:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9927.6). Total num frames: 91385856. Throughput: 0: 9713.4. Samples: 91362688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:24:10,829][613581] Avg episode reward: [(0, '4543.750')] [2023-03-09 05:24:14,151][613885] Updated weights for policy 0, policy_version 178560 (0.0005) [2023-03-09 05:24:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9898.7, 300 sec: 9927.6). Total num frames: 91439104. Throughput: 0: 9754.2. Samples: 91425160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:24:15,829][613581] Avg episode reward: [(0, '4466.357')] [2023-03-09 05:24:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000178592_91439104.pth... [2023-03-09 05:24:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000178016_91144192.pth [2023-03-09 05:24:18,311][613885] Updated weights for policy 0, policy_version 178640 (0.0005) [2023-03-09 05:24:20,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9830.4, 300 sec: 9927.6). Total num frames: 91488256. Throughput: 0: 9781.6. Samples: 91484252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:24:20,829][613581] Avg episode reward: [(0, '4476.043')] [2023-03-09 05:24:22,444][613885] Updated weights for policy 0, policy_version 178720 (0.0005) [2023-03-09 05:24:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9913.7). Total num frames: 91537408. Throughput: 0: 9815.7. Samples: 91513600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:24:25,829][613581] Avg episode reward: [(0, '4530.097')] [2023-03-09 05:24:26,653][613885] Updated weights for policy 0, policy_version 178800 (0.0005) [2023-03-09 05:24:30,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9899.8). Total num frames: 91582464. Throughput: 0: 9822.7. Samples: 91573312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:24:30,829][613581] Avg episode reward: [(0, '4424.119')] [2023-03-09 05:24:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000178872_91582464.pth... [2023-03-09 05:24:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000178296_91287552.pth [2023-03-09 05:24:30,924][613885] Updated weights for policy 0, policy_version 178880 (0.0004) [2023-03-09 05:24:35,098][613885] Updated weights for policy 0, policy_version 178960 (0.0005) [2023-03-09 05:24:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9885.9). Total num frames: 91631616. Throughput: 0: 9820.4. Samples: 91631176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:24:35,830][613581] Avg episode reward: [(0, '4145.026')] [2023-03-09 05:24:39,138][613885] Updated weights for policy 0, policy_version 179040 (0.0005) [2023-03-09 05:24:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.1, 300 sec: 9885.9). Total num frames: 91680768. Throughput: 0: 9836.0. Samples: 91660548. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:24:40,829][613581] Avg episode reward: [(0, '4368.001')] [2023-03-09 05:24:43,475][613885] Updated weights for policy 0, policy_version 179120 (0.0005) [2023-03-09 05:24:45,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.2, 300 sec: 9885.9). Total num frames: 91729920. Throughput: 0: 9834.6. Samples: 91717728. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:24:45,829][613581] Avg episode reward: [(0, '4307.820')] [2023-03-09 05:24:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000179160_91729920.pth... [2023-03-09 05:24:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000178592_91439104.pth [2023-03-09 05:24:47,591][613885] Updated weights for policy 0, policy_version 179200 (0.0005) [2023-03-09 05:24:50,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9885.9). Total num frames: 91779072. Throughput: 0: 9808.6. Samples: 91775980. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:24:50,830][613581] Avg episode reward: [(0, '4465.247')] [2023-03-09 05:24:51,995][613885] Updated weights for policy 0, policy_version 179280 (0.0005) [2023-03-09 05:24:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9885.9). Total num frames: 91828224. Throughput: 0: 9830.7. Samples: 91805072. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:24:55,829][613581] Avg episode reward: [(0, '4455.898')] [2023-03-09 05:24:56,152][613885] Updated weights for policy 0, policy_version 179360 (0.0005) [2023-03-09 05:25:00,212][613885] Updated weights for policy 0, policy_version 179440 (0.0004) [2023-03-09 05:25:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9899.8). Total num frames: 91877376. Throughput: 0: 9776.2. Samples: 91865088. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:25:00,829][613581] Avg episode reward: [(0, '4401.789')] [2023-03-09 05:25:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000179448_91877376.pth... [2023-03-09 05:25:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000178872_91582464.pth [2023-03-09 05:25:04,503][613885] Updated weights for policy 0, policy_version 179520 (0.0004) [2023-03-09 05:25:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9885.9). Total num frames: 91922432. Throughput: 0: 9737.3. Samples: 91922432. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:25:05,829][613581] Avg episode reward: [(0, '4402.807')] [2023-03-09 05:25:08,736][613885] Updated weights for policy 0, policy_version 179600 (0.0005) [2023-03-09 05:25:10,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9762.1, 300 sec: 9885.9). Total num frames: 91971584. Throughput: 0: 9737.0. Samples: 91951764. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:25:10,829][613581] Avg episode reward: [(0, '4271.251')] [2023-03-09 05:25:12,771][613885] Updated weights for policy 0, policy_version 179680 (0.0004) [2023-03-09 05:25:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9762.1, 300 sec: 9885.9). Total num frames: 92024832. Throughput: 0: 9760.9. Samples: 92012552. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:25:15,829][613581] Avg episode reward: [(0, '4035.688')] [2023-03-09 05:25:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000179736_92024832.pth... [2023-03-09 05:25:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000179160_91729920.pth [2023-03-09 05:25:17,065][613885] Updated weights for policy 0, policy_version 179760 (0.0005) [2023-03-09 05:25:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9872.1). Total num frames: 92069888. Throughput: 0: 9722.6. Samples: 92068692. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:25:20,829][613581] Avg episode reward: [(0, '4107.767')] [2023-03-09 05:25:21,467][613885] Updated weights for policy 0, policy_version 179840 (0.0004) [2023-03-09 05:25:25,610][613885] Updated weights for policy 0, policy_version 179920 (0.0005) [2023-03-09 05:25:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9872.1). Total num frames: 92119040. Throughput: 0: 9699.8. Samples: 92097040. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:25:25,829][613581] Avg episode reward: [(0, '4069.878')] [2023-03-09 05:25:29,499][613885] Updated weights for policy 0, policy_version 180000 (0.0005) [2023-03-09 05:25:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9830.4, 300 sec: 9872.1). Total num frames: 92172288. Throughput: 0: 9795.3. Samples: 92158520. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:25:30,829][613581] Avg episode reward: [(0, '4228.309')] [2023-03-09 05:25:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000180024_92172288.pth... [2023-03-09 05:25:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000179448_91877376.pth [2023-03-09 05:25:33,600][613885] Updated weights for policy 0, policy_version 180080 (0.0005) [2023-03-09 05:25:35,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9830.4, 300 sec: 9872.1). Total num frames: 92221440. Throughput: 0: 9817.1. Samples: 92217748. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:25:35,829][613581] Avg episode reward: [(0, '4450.360')] [2023-03-09 05:25:37,881][613885] Updated weights for policy 0, policy_version 180160 (0.0005) [2023-03-09 05:25:40,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9762.1, 300 sec: 9844.3). Total num frames: 92266496. Throughput: 0: 9806.8. Samples: 92246380. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-09 05:25:40,829][613581] Avg episode reward: [(0, '4422.853')] [2023-03-09 05:25:42,265][613885] Updated weights for policy 0, policy_version 180240 (0.0005) [2023-03-09 05:25:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9858.2). Total num frames: 92315648. Throughput: 0: 9739.6. Samples: 92303368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:25:45,829][613581] Avg episode reward: [(0, '4406.861')] [2023-03-09 05:25:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000180304_92315648.pth... [2023-03-09 05:25:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000179736_92024832.pth [2023-03-09 05:25:46,666][613885] Updated weights for policy 0, policy_version 180320 (0.0005) [2023-03-09 05:25:50,666][613885] Updated weights for policy 0, policy_version 180400 (0.0004) [2023-03-09 05:25:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.2, 300 sec: 9858.2). Total num frames: 92364800. Throughput: 0: 9773.5. Samples: 92362240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:25:50,829][613581] Avg episode reward: [(0, '4537.908')] [2023-03-09 05:25:54,874][613885] Updated weights for policy 0, policy_version 180480 (0.0005) [2023-03-09 05:25:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9858.2). Total num frames: 92413952. Throughput: 0: 9734.6. Samples: 92389824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:25:55,829][613581] Avg episode reward: [(0, '4520.400')] [2023-03-09 05:25:58,936][613885] Updated weights for policy 0, policy_version 180560 (0.0005) [2023-03-09 05:26:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9858.2). Total num frames: 92463104. Throughput: 0: 9739.4. Samples: 92450824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:26:00,829][613581] Avg episode reward: [(0, '4473.141')] [2023-03-09 05:26:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000180592_92463104.pth... [2023-03-09 05:26:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000180024_92172288.pth [2023-03-09 05:26:03,409][613885] Updated weights for policy 0, policy_version 180640 (0.0004) [2023-03-09 05:26:05,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9762.1, 300 sec: 9858.2). Total num frames: 92508160. Throughput: 0: 9746.9. Samples: 92507304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:26:05,829][613581] Avg episode reward: [(0, '4563.018')] [2023-03-09 05:26:07,560][613885] Updated weights for policy 0, policy_version 180720 (0.0005) [2023-03-09 05:26:10,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9830.4, 300 sec: 9872.1). Total num frames: 92561408. Throughput: 0: 9773.3. Samples: 92536840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:26:10,829][613581] Avg episode reward: [(0, '4596.014')] [2023-03-09 05:26:11,297][613885] Updated weights for policy 0, policy_version 180800 (0.0005) [2023-03-09 05:26:15,378][613885] Updated weights for policy 0, policy_version 180880 (0.0004) [2023-03-09 05:26:15,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9762.2, 300 sec: 9872.1). Total num frames: 92610560. Throughput: 0: 9842.5. Samples: 92601432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:26:15,829][613581] Avg episode reward: [(0, '4590.816')] [2023-03-09 05:26:15,838][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000180888_92614656.pth... [2023-03-09 05:26:15,840][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000180304_92315648.pth [2023-03-09 05:26:19,626][613885] Updated weights for policy 0, policy_version 180960 (0.0005) [2023-03-09 05:26:20,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9872.1). Total num frames: 92659712. Throughput: 0: 9818.6. Samples: 92659584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:26:20,829][613581] Avg episode reward: [(0, '4603.259')] [2023-03-09 05:26:23,676][613885] Updated weights for policy 0, policy_version 181040 (0.0005) [2023-03-09 05:26:25,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 9885.9). Total num frames: 92712960. Throughput: 0: 9834.2. Samples: 92688920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:26:25,830][613581] Avg episode reward: [(0, '4645.302')] [2023-03-09 05:26:25,830][613841] Saving new best policy, reward=4645.302! [2023-03-09 05:26:27,639][613885] Updated weights for policy 0, policy_version 181120 (0.0005) [2023-03-09 05:26:30,829][613581] Fps is (10 sec: 10649.5, 60 sec: 9898.7, 300 sec: 9885.9). Total num frames: 92766208. Throughput: 0: 9925.4. Samples: 92750012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:26:30,829][613581] Avg episode reward: [(0, '4642.229')] [2023-03-09 05:26:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000181184_92766208.pth... [2023-03-09 05:26:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000180592_92463104.pth [2023-03-09 05:26:31,670][613885] Updated weights for policy 0, policy_version 181200 (0.0005) [2023-03-09 05:26:35,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9872.1). Total num frames: 92811264. Throughput: 0: 9976.8. Samples: 92811196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:26:35,829][613581] Avg episode reward: [(0, '4549.926')] [2023-03-09 05:26:35,900][613885] Updated weights for policy 0, policy_version 181280 (0.0005) [2023-03-09 05:26:40,436][613885] Updated weights for policy 0, policy_version 181360 (0.0005) [2023-03-09 05:26:40,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9830.4, 300 sec: 9844.3). Total num frames: 92856320. Throughput: 0: 9992.1. Samples: 92839468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:26:40,829][613581] Avg episode reward: [(0, '4535.479')] [2023-03-09 05:26:44,700][613885] Updated weights for policy 0, policy_version 181440 (0.0005) [2023-03-09 05:26:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9830.4, 300 sec: 9858.2). Total num frames: 92905472. Throughput: 0: 9849.3. Samples: 92894044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:26:45,829][613581] Avg episode reward: [(0, '4640.045')] [2023-03-09 05:26:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000181456_92905472.pth... [2023-03-09 05:26:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000180888_92614656.pth [2023-03-09 05:26:48,900][613885] Updated weights for policy 0, policy_version 181520 (0.0005) [2023-03-09 05:26:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9844.3). Total num frames: 92954624. Throughput: 0: 9873.6. Samples: 92951616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:26:50,829][613581] Avg episode reward: [(0, '4642.610')] [2023-03-09 05:26:52,943][613885] Updated weights for policy 0, policy_version 181600 (0.0005) [2023-03-09 05:26:55,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9844.3). Total num frames: 93003776. Throughput: 0: 9928.6. Samples: 92983624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:26:55,829][613581] Avg episode reward: [(0, '4508.865')] [2023-03-09 05:26:57,155][613885] Updated weights for policy 0, policy_version 181680 (0.0005) [2023-03-09 05:27:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9844.3). Total num frames: 93052928. Throughput: 0: 9819.5. Samples: 93043308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:27:00,829][613581] Avg episode reward: [(0, '4564.991')] [2023-03-09 05:27:00,845][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000181752_93057024.pth... [2023-03-09 05:27:00,846][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000181184_92766208.pth [2023-03-09 05:27:01,277][613885] Updated weights for policy 0, policy_version 181760 (0.0005) [2023-03-09 05:27:05,586][613885] Updated weights for policy 0, policy_version 181840 (0.0005) [2023-03-09 05:27:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9844.3). Total num frames: 93102080. Throughput: 0: 9796.6. Samples: 93100432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:27:05,829][613581] Avg episode reward: [(0, '4504.572')] [2023-03-09 05:27:09,626][613885] Updated weights for policy 0, policy_version 181920 (0.0005) [2023-03-09 05:27:10,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 9872.1). Total num frames: 93155328. Throughput: 0: 9802.7. Samples: 93130040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:27:10,829][613581] Avg episode reward: [(0, '4609.077')] [2023-03-09 05:27:13,629][613885] Updated weights for policy 0, policy_version 182000 (0.0005) [2023-03-09 05:27:15,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 9858.2). Total num frames: 93204480. Throughput: 0: 9824.7. Samples: 93192124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:27:15,829][613581] Avg episode reward: [(0, '4531.351')] [2023-03-09 05:27:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000182040_93204480.pth... [2023-03-09 05:27:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000181456_92905472.pth [2023-03-09 05:27:17,848][613885] Updated weights for policy 0, policy_version 182080 (0.0005) [2023-03-09 05:27:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9858.2). Total num frames: 93253632. Throughput: 0: 9742.3. Samples: 93249600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:27:20,829][613581] Avg episode reward: [(0, '4585.371')] [2023-03-09 05:27:21,743][613885] Updated weights for policy 0, policy_version 182160 (0.0005) [2023-03-09 05:27:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9858.2). Total num frames: 93302784. Throughput: 0: 9840.1. Samples: 93282272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:27:25,829][613581] Avg episode reward: [(0, '4588.664')] [2023-03-09 05:27:25,954][613885] Updated weights for policy 0, policy_version 182240 (0.0005) [2023-03-09 05:27:30,358][613885] Updated weights for policy 0, policy_version 182320 (0.0005) [2023-03-09 05:27:30,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9830.4). Total num frames: 93347840. Throughput: 0: 9902.3. Samples: 93339648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:27:30,829][613581] Avg episode reward: [(0, '4432.022')] [2023-03-09 05:27:30,851][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000182328_93351936.pth... [2023-03-09 05:27:30,853][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000181752_93057024.pth [2023-03-09 05:27:34,657][613885] Updated weights for policy 0, policy_version 182400 (0.0005) [2023-03-09 05:27:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9830.4). Total num frames: 93396992. Throughput: 0: 9896.8. Samples: 93396972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:27:35,829][613581] Avg episode reward: [(0, '4586.376')] [2023-03-09 05:27:38,978][613885] Updated weights for policy 0, policy_version 182480 (0.0006) [2023-03-09 05:27:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9830.4). Total num frames: 93446144. Throughput: 0: 9784.5. Samples: 93423928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:27:40,829][613581] Avg episode reward: [(0, '4538.067')] [2023-03-09 05:27:43,371][613885] Updated weights for policy 0, policy_version 182560 (0.0005) [2023-03-09 05:27:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9802.6). Total num frames: 93491200. Throughput: 0: 9687.4. Samples: 93479240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:27:45,829][613581] Avg episode reward: [(0, '4536.890')] [2023-03-09 05:27:45,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000182600_93491200.pth... [2023-03-09 05:27:45,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000182040_93204480.pth [2023-03-09 05:27:47,682][613885] Updated weights for policy 0, policy_version 182640 (0.0005) [2023-03-09 05:27:50,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9762.1, 300 sec: 9802.6). Total num frames: 93540352. Throughput: 0: 9766.9. Samples: 93539944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:27:50,829][613581] Avg episode reward: [(0, '4539.668')] [2023-03-09 05:27:51,850][613885] Updated weights for policy 0, policy_version 182720 (0.0005) [2023-03-09 05:27:55,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9802.6). Total num frames: 93589504. Throughput: 0: 9753.6. Samples: 93568952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:27:55,829][613581] Avg episode reward: [(0, '4594.789')] [2023-03-09 05:27:56,181][613885] Updated weights for policy 0, policy_version 182800 (0.0005) [2023-03-09 05:28:00,210][613885] Updated weights for policy 0, policy_version 182880 (0.0005) [2023-03-09 05:28:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9802.6). Total num frames: 93638656. Throughput: 0: 9648.6. Samples: 93626312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:28:00,829][613581] Avg episode reward: [(0, '4608.424')] [2023-03-09 05:28:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000182888_93638656.pth... [2023-03-09 05:28:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000182328_93351936.pth [2023-03-09 05:28:04,588][613885] Updated weights for policy 0, policy_version 182960 (0.0005) [2023-03-09 05:28:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9802.6). Total num frames: 93687808. Throughput: 0: 9669.0. Samples: 93684704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:28:05,829][613581] Avg episode reward: [(0, '4630.217')] [2023-03-09 05:28:08,438][613885] Updated weights for policy 0, policy_version 183040 (0.0005) [2023-03-09 05:28:10,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9762.1, 300 sec: 9816.5). Total num frames: 93741056. Throughput: 0: 9632.5. Samples: 93715736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:28:10,829][613581] Avg episode reward: [(0, '4635.117')] [2023-03-09 05:28:12,527][613885] Updated weights for policy 0, policy_version 183120 (0.0006) [2023-03-09 05:28:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9788.7). Total num frames: 93786112. Throughput: 0: 9650.3. Samples: 93773912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:28:15,829][613581] Avg episode reward: [(0, '4625.512')] [2023-03-09 05:28:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000183176_93786112.pth... [2023-03-09 05:28:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000182600_93491200.pth [2023-03-09 05:28:16,863][613885] Updated weights for policy 0, policy_version 183200 (0.0005) [2023-03-09 05:28:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9774.9). Total num frames: 93835264. Throughput: 0: 9673.1. Samples: 93832264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:28:20,829][613581] Avg episode reward: [(0, '4573.579')] [2023-03-09 05:28:21,125][613885] Updated weights for policy 0, policy_version 183280 (0.0005) [2023-03-09 05:28:25,284][613885] Updated weights for policy 0, policy_version 183360 (0.0005) [2023-03-09 05:28:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9788.7). Total num frames: 93884416. Throughput: 0: 9734.9. Samples: 93862000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:28:25,829][613581] Avg episode reward: [(0, '4565.302')] [2023-03-09 05:28:29,310][613885] Updated weights for policy 0, policy_version 183440 (0.0005) [2023-03-09 05:28:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9788.7). Total num frames: 93933568. Throughput: 0: 9829.6. Samples: 93921572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:28:30,829][613581] Avg episode reward: [(0, '4525.383')] [2023-03-09 05:28:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000183464_93933568.pth... [2023-03-09 05:28:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000182888_93638656.pth [2023-03-09 05:28:33,512][613885] Updated weights for policy 0, policy_version 183520 (0.0005) [2023-03-09 05:28:35,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.1, 300 sec: 9788.7). Total num frames: 93982720. Throughput: 0: 9819.3. Samples: 93981812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:28:35,829][613581] Avg episode reward: [(0, '4524.541')] [2023-03-09 05:28:37,535][613885] Updated weights for policy 0, policy_version 183600 (0.0005) [2023-03-09 05:28:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.1, 300 sec: 9788.8). Total num frames: 94031872. Throughput: 0: 9833.4. Samples: 94011456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:28:40,829][613581] Avg episode reward: [(0, '4629.892')] [2023-03-09 05:28:41,724][613885] Updated weights for policy 0, policy_version 183680 (0.0005) [2023-03-09 05:28:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9788.7). Total num frames: 94081024. Throughput: 0: 9876.3. Samples: 94070744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:28:45,829][613581] Avg episode reward: [(0, '4580.806')] [2023-03-09 05:28:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000183752_94081024.pth... [2023-03-09 05:28:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000183176_93786112.pth [2023-03-09 05:28:45,918][613885] Updated weights for policy 0, policy_version 183760 (0.0004) [2023-03-09 05:28:49,840][613885] Updated weights for policy 0, policy_version 183840 (0.0005) [2023-03-09 05:28:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9898.7, 300 sec: 9816.5). Total num frames: 94134272. Throughput: 0: 9938.2. Samples: 94131924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:28:50,829][613581] Avg episode reward: [(0, '4540.302')] [2023-03-09 05:28:53,892][613885] Updated weights for policy 0, policy_version 183920 (0.0005) [2023-03-09 05:28:55,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 9816.5). Total num frames: 94183424. Throughput: 0: 9901.6. Samples: 94161308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:28:55,829][613581] Avg episode reward: [(0, '4491.809')] [2023-03-09 05:28:58,223][613885] Updated weights for policy 0, policy_version 184000 (0.0004) [2023-03-09 05:29:00,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9898.6, 300 sec: 9816.5). Total num frames: 94232576. Throughput: 0: 9898.7. Samples: 94219356. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:29:00,830][613581] Avg episode reward: [(0, '4462.203')] [2023-03-09 05:29:00,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000184048_94232576.pth... [2023-03-09 05:29:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000183464_93933568.pth [2023-03-09 05:29:02,433][613885] Updated weights for policy 0, policy_version 184080 (0.0005) [2023-03-09 05:29:05,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9830.4, 300 sec: 9802.6). Total num frames: 94277632. Throughput: 0: 9880.9. Samples: 94276904. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:29:05,829][613581] Avg episode reward: [(0, '4399.264')] [2023-03-09 05:29:06,838][613885] Updated weights for policy 0, policy_version 184160 (0.0005) [2023-03-09 05:29:10,829][613581] Fps is (10 sec: 9421.0, 60 sec: 9762.1, 300 sec: 9788.7). Total num frames: 94326784. Throughput: 0: 9848.9. Samples: 94305200. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:29:10,829][613581] Avg episode reward: [(0, '4536.450')] [2023-03-09 05:29:11,057][613885] Updated weights for policy 0, policy_version 184240 (0.0005) [2023-03-09 05:29:15,215][613885] Updated weights for policy 0, policy_version 184320 (0.0005) [2023-03-09 05:29:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9788.7). Total num frames: 94375936. Throughput: 0: 9820.6. Samples: 94363500. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:29:15,829][613581] Avg episode reward: [(0, '4545.431')] [2023-03-09 05:29:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000184328_94375936.pth... [2023-03-09 05:29:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000183752_94081024.pth [2023-03-09 05:29:19,263][613885] Updated weights for policy 0, policy_version 184400 (0.0005) [2023-03-09 05:29:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9788.7). Total num frames: 94425088. Throughput: 0: 9833.6. Samples: 94424324. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:29:20,829][613581] Avg episode reward: [(0, '4573.602')] [2023-03-09 05:29:23,342][613885] Updated weights for policy 0, policy_version 184480 (0.0006) [2023-03-09 05:29:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9802.6). Total num frames: 94474240. Throughput: 0: 9830.6. Samples: 94453832. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:29:25,829][613581] Avg episode reward: [(0, '4582.334')] [2023-03-09 05:29:27,362][613885] Updated weights for policy 0, policy_version 184560 (0.0005) [2023-03-09 05:29:30,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 9816.5). Total num frames: 94527488. Throughput: 0: 9866.9. Samples: 94514756. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:29:30,829][613581] Avg episode reward: [(0, '4611.393')] [2023-03-09 05:29:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000184624_94527488.pth... [2023-03-09 05:29:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000184048_94232576.pth [2023-03-09 05:29:31,706][613885] Updated weights for policy 0, policy_version 184640 (0.0005) [2023-03-09 05:29:35,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9830.4, 300 sec: 9802.6). Total num frames: 94572544. Throughput: 0: 9778.4. Samples: 94571952. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:29:35,829][613581] Avg episode reward: [(0, '4589.472')] [2023-03-09 05:29:35,950][613885] Updated weights for policy 0, policy_version 184720 (0.0005) [2023-03-09 05:29:40,145][613885] Updated weights for policy 0, policy_version 184800 (0.0005) [2023-03-09 05:29:40,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9830.4, 300 sec: 9802.6). Total num frames: 94621696. Throughput: 0: 9773.7. Samples: 94601124. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:29:40,829][613581] Avg episode reward: [(0, '4603.985')] [2023-03-09 05:29:44,325][613885] Updated weights for policy 0, policy_version 184880 (0.0005) [2023-03-09 05:29:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9830.4, 300 sec: 9802.6). Total num frames: 94670848. Throughput: 0: 9762.3. Samples: 94658660. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:29:45,829][613581] Avg episode reward: [(0, '4597.404')] [2023-03-09 05:29:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000184904_94670848.pth... [2023-03-09 05:29:45,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000184328_94375936.pth [2023-03-09 05:29:48,824][613885] Updated weights for policy 0, policy_version 184960 (0.0006) [2023-03-09 05:29:50,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9693.9, 300 sec: 9788.7). Total num frames: 94715904. Throughput: 0: 9720.9. Samples: 94714344. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:29:50,829][613581] Avg episode reward: [(0, '4616.162')] [2023-03-09 05:29:53,099][613885] Updated weights for policy 0, policy_version 185040 (0.0005) [2023-03-09 05:29:55,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9693.9, 300 sec: 9788.7). Total num frames: 94765056. Throughput: 0: 9739.5. Samples: 94743476. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:29:55,829][613581] Avg episode reward: [(0, '4619.927')] [2023-03-09 05:29:57,325][613885] Updated weights for policy 0, policy_version 185120 (0.0005) [2023-03-09 05:30:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9802.6). Total num frames: 94814208. Throughput: 0: 9724.4. Samples: 94801096. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:30:00,829][613581] Avg episode reward: [(0, '4625.935')] [2023-03-09 05:30:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000185184_94814208.pth... [2023-03-09 05:30:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000184624_94527488.pth [2023-03-09 05:30:01,637][613885] Updated weights for policy 0, policy_version 185200 (0.0005) [2023-03-09 05:30:05,697][613885] Updated weights for policy 0, policy_version 185280 (0.0005) [2023-03-09 05:30:05,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9802.6). Total num frames: 94863360. Throughput: 0: 9667.0. Samples: 94859340. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-09 05:30:05,829][613581] Avg episode reward: [(0, '4589.775')] [2023-03-09 05:30:09,955][613885] Updated weights for policy 0, policy_version 185360 (0.0005) [2023-03-09 05:30:10,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9693.9, 300 sec: 9774.9). Total num frames: 94908416. Throughput: 0: 9683.4. Samples: 94889584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:30:10,829][613581] Avg episode reward: [(0, '4602.721')] [2023-03-09 05:30:14,085][613885] Updated weights for policy 0, policy_version 185440 (0.0005) [2023-03-09 05:30:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9802.6). Total num frames: 94961664. Throughput: 0: 9638.8. Samples: 94948500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:30:15,829][613581] Avg episode reward: [(0, '4549.608')] [2023-03-09 05:30:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000185472_94961664.pth... [2023-03-09 05:30:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000184904_94670848.pth [2023-03-09 05:30:18,521][613885] Updated weights for policy 0, policy_version 185520 (0.0004) [2023-03-09 05:30:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9788.7). Total num frames: 95006720. Throughput: 0: 9590.2. Samples: 95003512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:30:20,829][613581] Avg episode reward: [(0, '4606.422')] [2023-03-09 05:30:22,723][613885] Updated weights for policy 0, policy_version 185600 (0.0005) [2023-03-09 05:30:25,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9693.9, 300 sec: 9774.9). Total num frames: 95055872. Throughput: 0: 9604.1. Samples: 95033308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:30:25,829][613581] Avg episode reward: [(0, '4585.004')] [2023-03-09 05:30:26,917][613885] Updated weights for policy 0, policy_version 185680 (0.0005) [2023-03-09 05:30:30,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9625.6, 300 sec: 9774.9). Total num frames: 95105024. Throughput: 0: 9642.9. Samples: 95092588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:30:30,829][613581] Avg episode reward: [(0, '4568.511')] [2023-03-09 05:30:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000185752_95105024.pth... [2023-03-09 05:30:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000185184_94814208.pth [2023-03-09 05:30:31,011][613885] Updated weights for policy 0, policy_version 185760 (0.0005) [2023-03-09 05:30:35,173][613885] Updated weights for policy 0, policy_version 185840 (0.0005) [2023-03-09 05:30:35,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9788.7). Total num frames: 95154176. Throughput: 0: 9729.2. Samples: 95152160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:30:35,829][613581] Avg episode reward: [(0, '4584.962')] [2023-03-09 05:30:39,228][613885] Updated weights for policy 0, policy_version 185920 (0.0005) [2023-03-09 05:30:40,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9788.7). Total num frames: 95203328. Throughput: 0: 9763.8. Samples: 95182848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:30:40,829][613581] Avg episode reward: [(0, '4581.989')] [2023-03-09 05:30:43,389][613885] Updated weights for policy 0, policy_version 186000 (0.0005) [2023-03-09 05:30:45,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9788.7). Total num frames: 95252480. Throughput: 0: 9793.7. Samples: 95241812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:30:45,829][613581] Avg episode reward: [(0, '4601.771')] [2023-03-09 05:30:45,887][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000186048_95256576.pth... [2023-03-09 05:30:45,890][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000185472_94961664.pth [2023-03-09 05:30:47,649][613885] Updated weights for policy 0, policy_version 186080 (0.0005) [2023-03-09 05:30:50,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9788.7). Total num frames: 95301632. Throughput: 0: 9808.0. Samples: 95300700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:30:50,829][613581] Avg episode reward: [(0, '4585.781')] [2023-03-09 05:30:51,758][613885] Updated weights for policy 0, policy_version 186160 (0.0005) [2023-03-09 05:30:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9788.7). Total num frames: 95350784. Throughput: 0: 9792.4. Samples: 95330244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:30:55,829][613581] Avg episode reward: [(0, '4602.697')] [2023-03-09 05:30:55,966][613885] Updated weights for policy 0, policy_version 186240 (0.0005) [2023-03-09 05:31:00,303][613885] Updated weights for policy 0, policy_version 186320 (0.0005) [2023-03-09 05:31:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9802.6). Total num frames: 95399936. Throughput: 0: 9760.4. Samples: 95387720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:31:00,829][613581] Avg episode reward: [(0, '4622.161')] [2023-03-09 05:31:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000186328_95399936.pth... [2023-03-09 05:31:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000185752_95105024.pth [2023-03-09 05:31:04,531][613885] Updated weights for policy 0, policy_version 186400 (0.0005) [2023-03-09 05:31:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9788.7). Total num frames: 95449088. Throughput: 0: 9810.0. Samples: 95444964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:31:05,829][613581] Avg episode reward: [(0, '4607.730')] [2023-03-09 05:31:08,772][613885] Updated weights for policy 0, policy_version 186480 (0.0005) [2023-03-09 05:31:10,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9762.1, 300 sec: 9774.9). Total num frames: 95494144. Throughput: 0: 9785.7. Samples: 95473664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:31:10,829][613581] Avg episode reward: [(0, '4597.352')] [2023-03-09 05:31:12,930][613885] Updated weights for policy 0, policy_version 186560 (0.0004) [2023-03-09 05:31:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9774.9). Total num frames: 95543296. Throughput: 0: 9765.7. Samples: 95532044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:31:15,829][613581] Avg episode reward: [(0, '4586.392')] [2023-03-09 05:31:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000186608_95543296.pth... [2023-03-09 05:31:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000186048_95256576.pth [2023-03-09 05:31:17,240][613885] Updated weights for policy 0, policy_version 186640 (0.0004) [2023-03-09 05:31:20,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9761.0). Total num frames: 95592448. Throughput: 0: 9699.8. Samples: 95588652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:31:20,829][613581] Avg episode reward: [(0, '4616.531')] [2023-03-09 05:31:21,682][613885] Updated weights for policy 0, policy_version 186720 (0.0004) [2023-03-09 05:31:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9733.2). Total num frames: 95637504. Throughput: 0: 9625.5. Samples: 95615996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:31:25,829][613581] Avg episode reward: [(0, '4575.603')] [2023-03-09 05:31:26,142][613885] Updated weights for policy 0, policy_version 186800 (0.0005) [2023-03-09 05:31:30,170][613885] Updated weights for policy 0, policy_version 186880 (0.0005) [2023-03-09 05:31:30,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9747.1). Total num frames: 95686656. Throughput: 0: 9613.9. Samples: 95674440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:31:30,829][613581] Avg episode reward: [(0, '4584.058')] [2023-03-09 05:31:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000186888_95686656.pth... [2023-03-09 05:31:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000186328_95399936.pth [2023-03-09 05:31:34,445][613885] Updated weights for policy 0, policy_version 186960 (0.0005) [2023-03-09 05:31:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9761.0). Total num frames: 95735808. Throughput: 0: 9623.7. Samples: 95733768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:31:35,829][613581] Avg episode reward: [(0, '4443.538')] [2023-03-09 05:31:38,597][613885] Updated weights for policy 0, policy_version 187040 (0.0004) [2023-03-09 05:31:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9761.0). Total num frames: 95784960. Throughput: 0: 9615.7. Samples: 95762952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:31:40,829][613581] Avg episode reward: [(0, '4629.438')] [2023-03-09 05:31:42,652][613885] Updated weights for policy 0, policy_version 187120 (0.0005) [2023-03-09 05:31:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.8, 300 sec: 9761.0). Total num frames: 95834112. Throughput: 0: 9646.9. Samples: 95821832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:31:45,830][613581] Avg episode reward: [(0, '4609.219')] [2023-03-09 05:31:45,835][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000187176_95834112.pth... [2023-03-09 05:31:45,838][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000186608_95543296.pth [2023-03-09 05:31:46,960][613885] Updated weights for policy 0, policy_version 187200 (0.0005) [2023-03-09 05:31:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9747.1). Total num frames: 95879168. Throughput: 0: 9648.5. Samples: 95879148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:31:50,829][613581] Avg episode reward: [(0, '4517.800')] [2023-03-09 05:31:51,349][613885] Updated weights for policy 0, policy_version 187280 (0.0005) [2023-03-09 05:31:55,345][613885] Updated weights for policy 0, policy_version 187360 (0.0004) [2023-03-09 05:31:55,829][613581] Fps is (10 sec: 9830.6, 60 sec: 9693.9, 300 sec: 9761.0). Total num frames: 95932416. Throughput: 0: 9675.5. Samples: 95909060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:31:55,829][613581] Avg episode reward: [(0, '4621.549')] [2023-03-09 05:31:59,629][613885] Updated weights for policy 0, policy_version 187440 (0.0004) [2023-03-09 05:32:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9747.1). Total num frames: 95977472. Throughput: 0: 9681.3. Samples: 95967704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:32:00,829][613581] Avg episode reward: [(0, '4553.796')] [2023-03-09 05:32:00,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000187456_95977472.pth... [2023-03-09 05:32:00,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000186888_95686656.pth [2023-03-09 05:32:04,106][613885] Updated weights for policy 0, policy_version 187520 (0.0005) [2023-03-09 05:32:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9733.2). Total num frames: 96026624. Throughput: 0: 9643.3. Samples: 96022600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:32:05,829][613581] Avg episode reward: [(0, '4597.229')] [2023-03-09 05:32:08,252][613885] Updated weights for policy 0, policy_version 187600 (0.0005) [2023-03-09 05:32:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9733.2). Total num frames: 96075776. Throughput: 0: 9690.7. Samples: 96052076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:32:10,829][613581] Avg episode reward: [(0, '4633.417')] [2023-03-09 05:32:12,530][613885] Updated weights for policy 0, policy_version 187680 (0.0005) [2023-03-09 05:32:15,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9625.6, 300 sec: 9719.3). Total num frames: 96120832. Throughput: 0: 9669.0. Samples: 96109544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:32:15,829][613581] Avg episode reward: [(0, '4571.256')] [2023-03-09 05:32:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000187736_96120832.pth... [2023-03-09 05:32:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000187176_95834112.pth [2023-03-09 05:32:16,755][613885] Updated weights for policy 0, policy_version 187760 (0.0005) [2023-03-09 05:32:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9719.3). Total num frames: 96169984. Throughput: 0: 9648.5. Samples: 96167948. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:32:20,829][613581] Avg episode reward: [(0, '4514.068')] [2023-03-09 05:32:20,958][613885] Updated weights for policy 0, policy_version 187840 (0.0005) [2023-03-09 05:32:25,183][613885] Updated weights for policy 0, policy_version 187920 (0.0005) [2023-03-09 05:32:25,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9733.2). Total num frames: 96219136. Throughput: 0: 9664.7. Samples: 96197864. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:32:25,829][613581] Avg episode reward: [(0, '4481.741')] [2023-03-09 05:32:29,318][613885] Updated weights for policy 0, policy_version 188000 (0.0005) [2023-03-09 05:32:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9733.2). Total num frames: 96268288. Throughput: 0: 9652.1. Samples: 96256176. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:32:30,829][613581] Avg episode reward: [(0, '4582.769')] [2023-03-09 05:32:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000188024_96268288.pth... [2023-03-09 05:32:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000187456_95977472.pth [2023-03-09 05:32:33,406][613885] Updated weights for policy 0, policy_version 188080 (0.0005) [2023-03-09 05:32:35,829][613581] Fps is (10 sec: 10240.1, 60 sec: 9762.2, 300 sec: 9747.1). Total num frames: 96321536. Throughput: 0: 9737.2. Samples: 96317320. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:32:35,829][613581] Avg episode reward: [(0, '4573.697')] [2023-03-09 05:32:37,494][613885] Updated weights for policy 0, policy_version 188160 (0.0004) [2023-03-09 05:32:40,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9747.1). Total num frames: 96366592. Throughput: 0: 9712.4. Samples: 96346120. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:32:40,829][613581] Avg episode reward: [(0, '4554.978')] [2023-03-09 05:32:41,791][613885] Updated weights for policy 0, policy_version 188240 (0.0005) [2023-03-09 05:32:45,814][613885] Updated weights for policy 0, policy_version 188320 (0.0005) [2023-03-09 05:32:45,829][613581] Fps is (10 sec: 9830.2, 60 sec: 9762.2, 300 sec: 9761.0). Total num frames: 96419840. Throughput: 0: 9747.2. Samples: 96406328. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:32:45,829][613581] Avg episode reward: [(0, '4528.156')] [2023-03-09 05:32:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000188320_96419840.pth... [2023-03-09 05:32:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000187736_96120832.pth [2023-03-09 05:32:49,793][613885] Updated weights for policy 0, policy_version 188400 (0.0004) [2023-03-09 05:32:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9830.4, 300 sec: 9761.0). Total num frames: 96468992. Throughput: 0: 9857.9. Samples: 96466208. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:32:50,829][613581] Avg episode reward: [(0, '4480.815')] [2023-03-09 05:32:54,003][613885] Updated weights for policy 0, policy_version 188480 (0.0004) [2023-03-09 05:32:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9761.0). Total num frames: 96518144. Throughput: 0: 9865.9. Samples: 96496040. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:32:55,829][613581] Avg episode reward: [(0, '4550.481')] [2023-03-09 05:32:58,006][613885] Updated weights for policy 0, policy_version 188560 (0.0005) [2023-03-09 05:33:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9761.0). Total num frames: 96567296. Throughput: 0: 9973.2. Samples: 96558336. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:33:00,829][613581] Avg episode reward: [(0, '4603.309')] [2023-03-09 05:33:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000188616_96571392.pth... [2023-03-09 05:33:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000188024_96268288.pth [2023-03-09 05:33:02,138][613885] Updated weights for policy 0, policy_version 188640 (0.0005) [2023-03-09 05:33:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9747.1). Total num frames: 96616448. Throughput: 0: 9904.6. Samples: 96613656. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:33:05,829][613581] Avg episode reward: [(0, '4422.902')] [2023-03-09 05:33:06,581][613885] Updated weights for policy 0, policy_version 188720 (0.0004) [2023-03-09 05:33:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9747.1). Total num frames: 96661504. Throughput: 0: 9849.6. Samples: 96641096. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:33:10,829][613581] Avg episode reward: [(0, '4483.589')] [2023-03-09 05:33:10,913][613885] Updated weights for policy 0, policy_version 188800 (0.0005) [2023-03-09 05:33:14,919][613885] Updated weights for policy 0, policy_version 188880 (0.0005) [2023-03-09 05:33:15,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9898.7, 300 sec: 9761.0). Total num frames: 96714752. Throughput: 0: 9876.9. Samples: 96700640. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:33:15,830][613581] Avg episode reward: [(0, '4546.355')] [2023-03-09 05:33:15,834][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000188896_96714752.pth... [2023-03-09 05:33:15,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000188320_96419840.pth [2023-03-09 05:33:19,053][613885] Updated weights for policy 0, policy_version 188960 (0.0005) [2023-03-09 05:33:20,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9898.7, 300 sec: 9761.0). Total num frames: 96763904. Throughput: 0: 9853.8. Samples: 96760744. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:33:20,829][613581] Avg episode reward: [(0, '4457.861')] [2023-03-09 05:33:23,221][613885] Updated weights for policy 0, policy_version 189040 (0.0005) [2023-03-09 05:33:25,829][613581] Fps is (10 sec: 9830.6, 60 sec: 9898.7, 300 sec: 9761.0). Total num frames: 96813056. Throughput: 0: 9865.5. Samples: 96790064. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:33:25,829][613581] Avg episode reward: [(0, '4548.189')] [2023-03-09 05:33:27,311][613885] Updated weights for policy 0, policy_version 189120 (0.0005) [2023-03-09 05:33:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9761.0). Total num frames: 96862208. Throughput: 0: 9858.0. Samples: 96849936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:33:30,829][613581] Avg episode reward: [(0, '4520.081')] [2023-03-09 05:33:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000189184_96862208.pth... [2023-03-09 05:33:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000188616_96571392.pth [2023-03-09 05:33:31,319][613885] Updated weights for policy 0, policy_version 189200 (0.0005) [2023-03-09 05:33:35,532][613885] Updated weights for policy 0, policy_version 189280 (0.0005) [2023-03-09 05:33:35,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9830.4, 300 sec: 9761.0). Total num frames: 96911360. Throughput: 0: 9872.3. Samples: 96910460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:33:35,829][613581] Avg episode reward: [(0, '4533.885')] [2023-03-09 05:33:39,754][613885] Updated weights for policy 0, policy_version 189360 (0.0005) [2023-03-09 05:33:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9898.7, 300 sec: 9761.0). Total num frames: 96960512. Throughput: 0: 9828.6. Samples: 96938328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:33:40,829][613581] Avg episode reward: [(0, '4580.803')] [2023-03-09 05:33:43,547][613885] Updated weights for policy 0, policy_version 189440 (0.0005) [2023-03-09 05:33:45,829][613581] Fps is (10 sec: 10239.9, 60 sec: 9898.7, 300 sec: 9761.0). Total num frames: 97013760. Throughput: 0: 9849.1. Samples: 97001544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:33:45,829][613581] Avg episode reward: [(0, '4471.031')] [2023-03-09 05:33:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000189480_97013760.pth... [2023-03-09 05:33:45,837][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000188896_96714752.pth [2023-03-09 05:33:47,466][613885] Updated weights for policy 0, policy_version 189520 (0.0005) [2023-03-09 05:33:50,829][613581] Fps is (10 sec: 11059.1, 60 sec: 10035.2, 300 sec: 9788.7). Total num frames: 97071104. Throughput: 0: 10071.1. Samples: 97066856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:33:50,829][613581] Avg episode reward: [(0, '4591.278')] [2023-03-09 05:33:51,235][613885] Updated weights for policy 0, policy_version 189600 (0.0005) [2023-03-09 05:33:55,484][613885] Updated weights for policy 0, policy_version 189680 (0.0005) [2023-03-09 05:33:55,829][613581] Fps is (10 sec: 10240.2, 60 sec: 9967.0, 300 sec: 9774.9). Total num frames: 97116160. Throughput: 0: 10101.9. Samples: 97095680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:33:55,829][613581] Avg episode reward: [(0, '4636.882')] [2023-03-09 05:33:59,792][613885] Updated weights for policy 0, policy_version 189760 (0.0005) [2023-03-09 05:34:00,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9966.9, 300 sec: 9788.7). Total num frames: 97165312. Throughput: 0: 10054.8. Samples: 97153108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:34:00,829][613581] Avg episode reward: [(0, '4536.148')] [2023-03-09 05:34:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000189776_97165312.pth... [2023-03-09 05:34:00,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000189184_96862208.pth [2023-03-09 05:34:03,841][613885] Updated weights for policy 0, policy_version 189840 (0.0005) [2023-03-09 05:34:05,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 9788.7). Total num frames: 97214464. Throughput: 0: 10067.1. Samples: 97213764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:34:05,829][613581] Avg episode reward: [(0, '4541.184')] [2023-03-09 05:34:07,868][613885] Updated weights for policy 0, policy_version 189920 (0.0005) [2023-03-09 05:34:10,829][613581] Fps is (10 sec: 10240.1, 60 sec: 10103.5, 300 sec: 9802.6). Total num frames: 97267712. Throughput: 0: 10084.4. Samples: 97243864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:34:10,829][613581] Avg episode reward: [(0, '4567.357')] [2023-03-09 05:34:12,106][613885] Updated weights for policy 0, policy_version 190000 (0.0005) [2023-03-09 05:34:15,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9967.0, 300 sec: 9788.7). Total num frames: 97312768. Throughput: 0: 10085.0. Samples: 97303760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:34:15,829][613581] Avg episode reward: [(0, '4458.169')] [2023-03-09 05:34:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000190072_97316864.pth... [2023-03-09 05:34:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000189480_97013760.pth [2023-03-09 05:34:16,288][613885] Updated weights for policy 0, policy_version 190080 (0.0005) [2023-03-09 05:34:20,685][613885] Updated weights for policy 0, policy_version 190160 (0.0006) [2023-03-09 05:34:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9966.9, 300 sec: 9788.7). Total num frames: 97361920. Throughput: 0: 9967.6. Samples: 97359000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:34:20,829][613581] Avg episode reward: [(0, '4495.998')] [2023-03-09 05:34:24,996][613885] Updated weights for policy 0, policy_version 190240 (0.0004) [2023-03-09 05:34:25,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9966.9, 300 sec: 9774.9). Total num frames: 97411072. Throughput: 0: 9960.7. Samples: 97386560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:34:25,830][613581] Avg episode reward: [(0, '4496.963')] [2023-03-09 05:34:29,158][613885] Updated weights for policy 0, policy_version 190320 (0.0005) [2023-03-09 05:34:30,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9898.7, 300 sec: 9774.9). Total num frames: 97456128. Throughput: 0: 9879.6. Samples: 97446124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:34:30,829][613581] Avg episode reward: [(0, '4587.830')] [2023-03-09 05:34:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000190344_97456128.pth... [2023-03-09 05:34:30,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000189776_97165312.pth [2023-03-09 05:34:33,359][613885] Updated weights for policy 0, policy_version 190400 (0.0005) [2023-03-09 05:34:35,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9898.7, 300 sec: 9774.9). Total num frames: 97505280. Throughput: 0: 9733.0. Samples: 97504840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:34:35,829][613581] Avg episode reward: [(0, '4505.779')] [2023-03-09 05:34:37,673][613885] Updated weights for policy 0, policy_version 190480 (0.0005) [2023-03-09 05:34:40,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9898.7, 300 sec: 9774.9). Total num frames: 97554432. Throughput: 0: 9713.0. Samples: 97532764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:34:40,829][613581] Avg episode reward: [(0, '4497.344')] [2023-03-09 05:34:41,806][613885] Updated weights for policy 0, policy_version 190560 (0.0004) [2023-03-09 05:34:45,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9788.7). Total num frames: 97603584. Throughput: 0: 9760.7. Samples: 97592340. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:34:45,829][613581] Avg episode reward: [(0, '4502.960')] [2023-03-09 05:34:45,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000190632_97603584.pth... [2023-03-09 05:34:45,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000190072_97316864.pth [2023-03-09 05:34:46,006][613885] Updated weights for policy 0, policy_version 190640 (0.0005) [2023-03-09 05:34:50,365][613885] Updated weights for policy 0, policy_version 190720 (0.0005) [2023-03-09 05:34:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9774.9). Total num frames: 97648640. Throughput: 0: 9665.3. Samples: 97648704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:34:50,829][613581] Avg episode reward: [(0, '4625.513')] [2023-03-09 05:34:54,813][613885] Updated weights for policy 0, policy_version 190800 (0.0005) [2023-03-09 05:34:55,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9693.8, 300 sec: 9774.9). Total num frames: 97697792. Throughput: 0: 9596.0. Samples: 97675684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:34:55,829][613581] Avg episode reward: [(0, '4439.898')] [2023-03-09 05:34:59,040][613885] Updated weights for policy 0, policy_version 190880 (0.0005) [2023-03-09 05:35:00,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9693.9, 300 sec: 9774.9). Total num frames: 97746944. Throughput: 0: 9570.6. Samples: 97734436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:35:00,829][613581] Avg episode reward: [(0, '4493.205')] [2023-03-09 05:35:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000190912_97746944.pth... [2023-03-09 05:35:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000190344_97456128.pth [2023-03-09 05:35:03,278][613885] Updated weights for policy 0, policy_version 190960 (0.0005) [2023-03-09 05:35:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9788.7). Total num frames: 97796096. Throughput: 0: 9621.3. Samples: 97791960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:35:05,829][613581] Avg episode reward: [(0, '4587.649')] [2023-03-09 05:35:07,566][613885] Updated weights for policy 0, policy_version 191040 (0.0006) [2023-03-09 05:35:10,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9761.0). Total num frames: 97841152. Throughput: 0: 9645.8. Samples: 97820620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:35:10,829][613581] Avg episode reward: [(0, '4629.644')] [2023-03-09 05:35:11,790][613885] Updated weights for policy 0, policy_version 191120 (0.0005) [2023-03-09 05:35:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9774.9). Total num frames: 97890304. Throughput: 0: 9607.2. Samples: 97878448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:35:15,829][613581] Avg episode reward: [(0, '4634.325')] [2023-03-09 05:35:15,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000191192_97890304.pth... [2023-03-09 05:35:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000190632_97603584.pth [2023-03-09 05:35:15,937][613885] Updated weights for policy 0, policy_version 191200 (0.0005) [2023-03-09 05:35:20,034][613885] Updated weights for policy 0, policy_version 191280 (0.0006) [2023-03-09 05:35:20,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9774.9). Total num frames: 97939456. Throughput: 0: 9651.9. Samples: 97939176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:35:20,829][613581] Avg episode reward: [(0, '4582.705')] [2023-03-09 05:35:23,951][613885] Updated weights for policy 0, policy_version 191360 (0.0005) [2023-03-09 05:35:25,829][613581] Fps is (10 sec: 10240.1, 60 sec: 9693.9, 300 sec: 9788.7). Total num frames: 97992704. Throughput: 0: 9707.0. Samples: 97969576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:35:25,829][613581] Avg episode reward: [(0, '4637.794')] [2023-03-09 05:35:28,030][613885] Updated weights for policy 0, policy_version 191440 (0.0005) [2023-03-09 05:35:30,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9762.1, 300 sec: 9788.7). Total num frames: 98041856. Throughput: 0: 9720.3. Samples: 98029756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:35:30,829][613581] Avg episode reward: [(0, '4625.605')] [2023-03-09 05:35:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000191488_98041856.pth... [2023-03-09 05:35:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000190912_97746944.pth [2023-03-09 05:35:32,297][613885] Updated weights for policy 0, policy_version 191520 (0.0005) [2023-03-09 05:35:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9788.7). Total num frames: 98091008. Throughput: 0: 9737.4. Samples: 98086888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:35:35,840][613581] Avg episode reward: [(0, '4625.427')] [2023-03-09 05:35:36,702][613885] Updated weights for policy 0, policy_version 191600 (0.0005) [2023-03-09 05:35:40,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9774.9). Total num frames: 98136064. Throughput: 0: 9775.0. Samples: 98115560. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:35:40,840][613581] Avg episode reward: [(0, '4622.267')] [2023-03-09 05:35:40,952][613885] Updated weights for policy 0, policy_version 191680 (0.0005) [2023-03-09 05:35:45,260][613885] Updated weights for policy 0, policy_version 191760 (0.0004) [2023-03-09 05:35:45,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9774.9). Total num frames: 98185216. Throughput: 0: 9744.6. Samples: 98172944. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:35:45,840][613581] Avg episode reward: [(0, '4614.574')] [2023-03-09 05:35:45,844][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000191768_98185216.pth... [2023-03-09 05:35:45,847][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000191192_97890304.pth [2023-03-09 05:35:49,740][613885] Updated weights for policy 0, policy_version 191840 (0.0005) [2023-03-09 05:35:50,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9693.9, 300 sec: 9761.0). Total num frames: 98230272. Throughput: 0: 9694.5. Samples: 98228212. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:35:50,829][613581] Avg episode reward: [(0, '4542.206')] [2023-03-09 05:35:53,852][613885] Updated weights for policy 0, policy_version 191920 (0.0005) [2023-03-09 05:35:55,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9693.9, 300 sec: 9761.0). Total num frames: 98279424. Throughput: 0: 9737.9. Samples: 98258824. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:35:55,829][613581] Avg episode reward: [(0, '4626.976')] [2023-03-09 05:35:58,320][613885] Updated weights for policy 0, policy_version 192000 (0.0005) [2023-03-09 05:36:00,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9761.0). Total num frames: 98328576. Throughput: 0: 9699.5. Samples: 98314924. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:36:00,829][613581] Avg episode reward: [(0, '4532.338')] [2023-03-09 05:36:00,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000192048_98328576.pth... [2023-03-09 05:36:00,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000191488_98041856.pth [2023-03-09 05:36:02,493][613885] Updated weights for policy 0, policy_version 192080 (0.0004) [2023-03-09 05:36:05,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9625.6, 300 sec: 9761.0). Total num frames: 98373632. Throughput: 0: 9634.7. Samples: 98372736. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:36:05,829][613581] Avg episode reward: [(0, '4636.634')] [2023-03-09 05:36:06,769][613885] Updated weights for policy 0, policy_version 192160 (0.0005) [2023-03-09 05:36:10,551][613885] Updated weights for policy 0, policy_version 192240 (0.0005) [2023-03-09 05:36:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9762.1, 300 sec: 9774.9). Total num frames: 98426880. Throughput: 0: 9610.8. Samples: 98402064. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:36:10,829][613581] Avg episode reward: [(0, '4464.022')] [2023-03-09 05:36:14,709][613885] Updated weights for policy 0, policy_version 192320 (0.0005) [2023-03-09 05:36:15,829][613581] Fps is (10 sec: 10239.8, 60 sec: 9762.1, 300 sec: 9774.9). Total num frames: 98476032. Throughput: 0: 9674.5. Samples: 98465108. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:36:15,829][613581] Avg episode reward: [(0, '4509.291')] [2023-03-09 05:36:15,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000192336_98476032.pth... [2023-03-09 05:36:15,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000191768_98185216.pth [2023-03-09 05:36:19,326][613885] Updated weights for policy 0, policy_version 192400 (0.0004) [2023-03-09 05:36:20,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9774.9). Total num frames: 98521088. Throughput: 0: 9616.6. Samples: 98519636. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:36:20,829][613581] Avg episode reward: [(0, '4587.077')] [2023-03-09 05:36:23,356][613885] Updated weights for policy 0, policy_version 192480 (0.0005) [2023-03-09 05:36:25,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9774.9). Total num frames: 98570240. Throughput: 0: 9650.3. Samples: 98549824. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:36:25,829][613581] Avg episode reward: [(0, '4595.019')] [2023-03-09 05:36:27,577][613885] Updated weights for policy 0, policy_version 192560 (0.0004) [2023-03-09 05:36:30,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9774.9). Total num frames: 98619392. Throughput: 0: 9672.3. Samples: 98608200. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:36:30,830][613581] Avg episode reward: [(0, '4547.997')] [2023-03-09 05:36:30,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000192616_98619392.pth... [2023-03-09 05:36:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000192048_98328576.pth [2023-03-09 05:36:32,061][613885] Updated weights for policy 0, policy_version 192640 (0.0005) [2023-03-09 05:36:35,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9557.3, 300 sec: 9761.0). Total num frames: 98664448. Throughput: 0: 9662.4. Samples: 98663020. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:36:35,829][613581] Avg episode reward: [(0, '4505.092')] [2023-03-09 05:36:36,336][613885] Updated weights for policy 0, policy_version 192720 (0.0004) [2023-03-09 05:36:40,829][613581] Fps is (10 sec: 9011.3, 60 sec: 9557.3, 300 sec: 9747.1). Total num frames: 98709504. Throughput: 0: 9633.3. Samples: 98692324. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:36:40,829][613581] Avg episode reward: [(0, '4639.950')] [2023-03-09 05:36:40,845][613885] Updated weights for policy 0, policy_version 192800 (0.0005) [2023-03-09 05:36:44,764][613885] Updated weights for policy 0, policy_version 192880 (0.0005) [2023-03-09 05:36:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9774.9). Total num frames: 98762752. Throughput: 0: 9680.1. Samples: 98750528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:36:45,829][613581] Avg episode reward: [(0, '4449.020')] [2023-03-09 05:36:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000192896_98762752.pth... [2023-03-09 05:36:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000192336_98476032.pth [2023-03-09 05:36:48,856][613885] Updated weights for policy 0, policy_version 192960 (0.0004) [2023-03-09 05:36:50,829][613581] Fps is (10 sec: 10240.0, 60 sec: 9693.9, 300 sec: 9761.0). Total num frames: 98811904. Throughput: 0: 9727.3. Samples: 98810464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:36:50,829][613581] Avg episode reward: [(0, '4492.085')] [2023-03-09 05:36:53,106][613885] Updated weights for policy 0, policy_version 193040 (0.0005) [2023-03-09 05:36:55,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9774.9). Total num frames: 98861056. Throughput: 0: 9729.0. Samples: 98839868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:36:55,829][613581] Avg episode reward: [(0, '4600.743')] [2023-03-09 05:36:57,185][613885] Updated weights for policy 0, policy_version 193120 (0.0005) [2023-03-09 05:37:00,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9774.9). Total num frames: 98910208. Throughput: 0: 9656.4. Samples: 98899644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:37:00,829][613581] Avg episode reward: [(0, '4524.600')] [2023-03-09 05:37:00,869][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000193192_98914304.pth... [2023-03-09 05:37:00,870][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000192616_98619392.pth [2023-03-09 05:37:01,270][613885] Updated weights for policy 0, policy_version 193200 (0.0005) [2023-03-09 05:37:05,499][613885] Updated weights for policy 0, policy_version 193280 (0.0004) [2023-03-09 05:37:05,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9774.9). Total num frames: 98959360. Throughput: 0: 9750.6. Samples: 98958412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:37:05,829][613581] Avg episode reward: [(0, '4593.516')] [2023-03-09 05:37:09,840][613885] Updated weights for policy 0, policy_version 193360 (0.0004) [2023-03-09 05:37:10,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9788.7). Total num frames: 99008512. Throughput: 0: 9720.2. Samples: 98987232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:37:10,829][613581] Avg episode reward: [(0, '4569.287')] [2023-03-09 05:37:14,132][613885] Updated weights for policy 0, policy_version 193440 (0.0005) [2023-03-09 05:37:15,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9625.6, 300 sec: 9774.9). Total num frames: 99053568. Throughput: 0: 9677.8. Samples: 99043700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:37:15,829][613581] Avg episode reward: [(0, '4552.294')] [2023-03-09 05:37:15,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000193464_99053568.pth... [2023-03-09 05:37:15,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000192896_98762752.pth [2023-03-09 05:37:18,473][613885] Updated weights for policy 0, policy_version 193520 (0.0004) [2023-03-09 05:37:20,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9693.9, 300 sec: 9774.9). Total num frames: 99102720. Throughput: 0: 9756.3. Samples: 99102052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:37:20,829][613581] Avg episode reward: [(0, '4594.175')] [2023-03-09 05:37:22,560][613885] Updated weights for policy 0, policy_version 193600 (0.0005) [2023-03-09 05:37:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 9774.9). Total num frames: 99151872. Throughput: 0: 9761.6. Samples: 99131596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:37:25,829][613581] Avg episode reward: [(0, '4615.132')] [2023-03-09 05:37:26,660][613885] Updated weights for policy 0, policy_version 193680 (0.0005) [2023-03-09 05:37:30,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9693.9, 300 sec: 9761.0). Total num frames: 99201024. Throughput: 0: 9765.4. Samples: 99189972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:37:30,829][613581] Avg episode reward: [(0, '4550.660')] [2023-03-09 05:37:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000193752_99201024.pth... [2023-03-09 05:37:30,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000193192_98914304.pth [2023-03-09 05:37:31,015][613885] Updated weights for policy 0, policy_version 193760 (0.0006) [2023-03-09 05:37:35,298][613885] Updated weights for policy 0, policy_version 193840 (0.0005) [2023-03-09 05:37:35,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9774.9). Total num frames: 99250176. Throughput: 0: 9689.1. Samples: 99246472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:37:35,829][613581] Avg episode reward: [(0, '4542.053')] [2023-03-09 05:37:39,552][613885] Updated weights for policy 0, policy_version 193920 (0.0005) [2023-03-09 05:37:40,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9830.4, 300 sec: 9761.0). Total num frames: 99299328. Throughput: 0: 9669.5. Samples: 99274996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:37:40,829][613581] Avg episode reward: [(0, '4595.863')] [2023-03-09 05:37:43,674][613885] Updated weights for policy 0, policy_version 194000 (0.0005) [2023-03-09 05:37:45,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9762.1, 300 sec: 9761.0). Total num frames: 99348480. Throughput: 0: 9695.0. Samples: 99335920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:37:45,829][613581] Avg episode reward: [(0, '4589.740')] [2023-03-09 05:37:45,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000194040_99348480.pth... [2023-03-09 05:37:45,835][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000193464_99053568.pth [2023-03-09 05:37:47,860][613885] Updated weights for policy 0, policy_version 194080 (0.0005) [2023-03-09 05:37:50,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9747.1). Total num frames: 99393536. Throughput: 0: 9665.4. Samples: 99393356. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-09 05:37:50,829][613581] Avg episode reward: [(0, '4638.939')] [2023-03-09 05:37:52,175][613885] Updated weights for policy 0, policy_version 194160 (0.0006) [2023-03-09 05:37:55,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9693.9, 300 sec: 9747.1). Total num frames: 99442688. Throughput: 0: 9652.1. Samples: 99421576. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:37:55,829][613581] Avg episode reward: [(0, '4618.957')] [2023-03-09 05:37:56,713][613885] Updated weights for policy 0, policy_version 194240 (0.0004) [2023-03-09 05:38:00,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9625.6, 300 sec: 9733.2). Total num frames: 99487744. Throughput: 0: 9625.7. Samples: 99476856. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:38:00,829][613581] Avg episode reward: [(0, '4550.717')] [2023-03-09 05:38:00,832][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000194312_99487744.pth... [2023-03-09 05:38:00,834][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000193752_99201024.pth [2023-03-09 05:38:00,956][613885] Updated weights for policy 0, policy_version 194320 (0.0005) [2023-03-09 05:38:05,278][613885] Updated weights for policy 0, policy_version 194400 (0.0005) [2023-03-09 05:38:05,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9747.1). Total num frames: 99536896. Throughput: 0: 9586.0. Samples: 99533424. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:38:05,829][613581] Avg episode reward: [(0, '4501.076')] [2023-03-09 05:38:09,573][613885] Updated weights for policy 0, policy_version 194480 (0.0005) [2023-03-09 05:38:10,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9625.6, 300 sec: 9733.2). Total num frames: 99586048. Throughput: 0: 9552.4. Samples: 99561452. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:38:10,829][613581] Avg episode reward: [(0, '4467.797')] [2023-03-09 05:38:13,766][613885] Updated weights for policy 0, policy_version 194560 (0.0005) [2023-03-09 05:38:15,829][613581] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 9719.3). Total num frames: 99631104. Throughput: 0: 9556.2. Samples: 99620000. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:38:15,829][613581] Avg episode reward: [(0, '4545.742')] [2023-03-09 05:38:15,831][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000194592_99631104.pth... [2023-03-09 05:38:15,833][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000194040_99348480.pth [2023-03-09 05:38:18,182][613885] Updated weights for policy 0, policy_version 194640 (0.0005) [2023-03-09 05:38:20,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9625.6, 300 sec: 9719.3). Total num frames: 99680256. Throughput: 0: 9586.0. Samples: 99677844. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:38:20,829][613581] Avg episode reward: [(0, '4633.807')] [2023-03-09 05:38:22,240][613885] Updated weights for policy 0, policy_version 194720 (0.0005) [2023-03-09 05:38:25,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9719.3). Total num frames: 99729408. Throughput: 0: 9616.7. Samples: 99707748. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:38:25,830][613581] Avg episode reward: [(0, '4557.358')] [2023-03-09 05:38:26,386][613885] Updated weights for policy 0, policy_version 194800 (0.0005) [2023-03-09 05:38:30,595][613885] Updated weights for policy 0, policy_version 194880 (0.0005) [2023-03-09 05:38:30,829][613581] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 9719.3). Total num frames: 99778560. Throughput: 0: 9540.5. Samples: 99765244. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:38:30,829][613581] Avg episode reward: [(0, '4550.941')] [2023-03-09 05:38:30,833][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000194880_99778560.pth... [2023-03-09 05:38:30,836][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000194312_99487744.pth [2023-03-09 05:38:34,892][613885] Updated weights for policy 0, policy_version 194960 (0.0005) [2023-03-09 05:38:35,829][613581] Fps is (10 sec: 9830.5, 60 sec: 9625.6, 300 sec: 9719.3). Total num frames: 99827712. Throughput: 0: 9562.8. Samples: 99823680. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:38:35,829][613581] Avg episode reward: [(0, '4593.358')] [2023-03-09 05:38:39,083][613885] Updated weights for policy 0, policy_version 195040 (0.0005) [2023-03-09 05:38:40,829][613581] Fps is (10 sec: 9420.9, 60 sec: 9557.3, 300 sec: 9691.6). Total num frames: 99872768. Throughput: 0: 9573.0. Samples: 99852360. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:38:40,829][613581] Avg episode reward: [(0, '4638.928')] [2023-03-09 05:38:43,474][613885] Updated weights for policy 0, policy_version 195120 (0.0005) [2023-03-09 05:38:45,829][613581] Fps is (10 sec: 9420.7, 60 sec: 9557.3, 300 sec: 9663.8). Total num frames: 99921920. Throughput: 0: 9655.7. Samples: 99911364. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:38:45,829][613581] Avg episode reward: [(0, '4597.405')] [2023-03-09 05:38:45,850][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000195168_99926016.pth... [2023-03-09 05:38:45,851][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000194592_99631104.pth [2023-03-09 05:38:47,610][613885] Updated weights for policy 0, policy_version 195200 (0.0005) [2023-03-09 05:38:50,829][613581] Fps is (10 sec: 9830.3, 60 sec: 9625.6, 300 sec: 9677.7). Total num frames: 99971072. Throughput: 0: 9658.6. Samples: 99968060. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-09 05:38:50,829][613581] Avg episode reward: [(0, '4567.199')] [2023-03-09 05:38:51,868][613885] Updated weights for policy 0, policy_version 195280 (0.0005) [2023-03-09 05:38:54,137][613841] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 [2023-03-09 05:38:54,620][613841] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 [2023-03-09 05:38:54,621][613889] Stopping RolloutWorker_w3... [2023-03-09 05:38:54,621][613954] Stopping RolloutWorker_w6... [2023-03-09 05:38:54,621][613887] Stopping RolloutWorker_w1... [2023-03-09 05:38:54,621][613921] Stopping RolloutWorker_w4... [2023-03-09 05:38:54,621][613886] Stopping RolloutWorker_w0... [2023-03-09 05:38:54,621][613986] Stopping RolloutWorker_w7... [2023-03-09 05:38:54,621][613889] Loop rollout_proc3_evt_loop terminating... [2023-03-09 05:38:54,621][613888] Stopping RolloutWorker_w2... [2023-03-09 05:38:54,621][613954] Loop rollout_proc6_evt_loop terminating... [2023-03-09 05:38:54,621][613887] Loop rollout_proc1_evt_loop terminating... [2023-03-09 05:38:54,621][613886] Loop rollout_proc0_evt_loop terminating... [2023-03-09 05:38:54,621][613921] Loop rollout_proc4_evt_loop terminating... [2023-03-09 05:38:54,621][613986] Loop rollout_proc7_evt_loop terminating... [2023-03-09 05:38:54,621][613581] Component RolloutWorker_w3 stopped! [2023-03-09 05:38:54,621][613888] Loop rollout_proc2_evt_loop terminating... [2023-03-09 05:38:54,621][613922] Stopping RolloutWorker_w5... [2023-03-09 05:38:54,621][613581] Component RolloutWorker_w6 stopped! [2023-03-09 05:38:54,622][613922] Loop rollout_proc5_evt_loop terminating... [2023-03-09 05:38:54,622][613581] Component RolloutWorker_w4 stopped! [2023-03-09 05:38:54,622][613841] Stopping Batcher_0... [2023-03-09 05:38:54,622][613581] Component RolloutWorker_w1 stopped! [2023-03-09 05:38:54,622][613581] Component RolloutWorker_w7 stopped! [2023-03-09 05:38:54,622][613841] Loop batcher_evt_loop terminating... [2023-03-09 05:38:54,622][613581] Component RolloutWorker_w0 stopped! [2023-03-09 05:38:54,623][613581] Component RolloutWorker_w2 stopped! [2023-03-09 05:38:54,623][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000195328_100007936.pth... [2023-03-09 05:38:54,623][613581] Component RolloutWorker_w5 stopped! [2023-03-09 05:38:54,623][613581] Component Batcher_0 stopped! [2023-03-09 05:38:54,626][613841] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000194880_99778560.pth [2023-03-09 05:38:54,627][613841] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000195328_100007936.pth... [2023-03-09 05:38:54,629][613841] Stopping LearnerWorker_p0... [2023-03-09 05:38:54,630][613841] Loop learner_proc0_evt_loop terminating... [2023-03-09 05:38:54,630][613581] Component LearnerWorker_p0 stopped! [2023-03-09 05:38:54,679][613885] Weights refcount: 2 0 [2023-03-09 05:38:54,680][613885] Stopping InferenceWorker_p0-w0... [2023-03-09 05:38:54,681][613885] Loop inference_proc0-0_evt_loop terminating... [2023-03-09 05:38:54,681][613581] Component InferenceWorker_p0-w0 stopped! [2023-03-09 05:38:54,682][613581] Waiting for process learner_proc0 to stop... [2023-03-09 05:38:55,152][613581] Waiting for process inference_proc0-0 to join... [2023-03-09 05:38:55,174][613581] Waiting for process rollout_proc0 to join... [2023-03-09 05:38:55,174][613581] Waiting for process rollout_proc1 to join... [2023-03-09 05:38:55,174][613581] Waiting for process rollout_proc2 to join... [2023-03-09 05:38:55,174][613581] Waiting for process rollout_proc3 to join... [2023-03-09 05:38:55,175][613581] Waiting for process rollout_proc4 to join... [2023-03-09 05:38:55,175][613581] Waiting for process rollout_proc5 to join... [2023-03-09 05:38:55,175][613581] Waiting for process rollout_proc6 to join... [2023-03-09 05:38:55,175][613581] Waiting for process rollout_proc7 to join... [2023-03-09 05:38:55,175][613581] Batcher 0 profile tree view: batching: 17.4714, releasing_batches: 14.8013 [2023-03-09 05:38:55,176][613581] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0052 wait_policy_total: 3540.1822 update_model: 110.5180 weight_update: 0.0005 one_step: 0.0006 handle_policy_step: 5605.2868 deserialize: 234.4299, stack: 58.6299, obs_to_device_normalize: 993.4734, forward: 2785.3750, send_messages: 440.2947 prepare_outputs: 606.9567 to_cpu: 94.9577 [2023-03-09 05:38:55,176][613581] Learner 0 profile tree view: misc: 0.0929, prepare_batch: 79.1323 train: 1017.8113 epoch_init: 0.3711, minibatch_init: 10.8482, losses_postprocess: 12.3406, kl_divergence: 3.8835, after_optimizer: 5.6799 calculate_losses: 414.7940 losses_init: 0.3532, forward_head: 199.6714, bptt_initial: 1.1147, bptt: 1.1716, tail: 102.2976, advantages_returns: 8.2142, losses: 89.3617 update: 555.5969 clip: 50.3418 [2023-03-09 05:38:55,176][613581] RolloutWorker_w0 profile tree view: wait_for_trajectories: 4.3584, enqueue_policy_requests: 160.2597, env_step: 5652.9315, overhead: 335.4747, complete_rollouts: 3.8018 save_policy_outputs: 375.2071 split_output_tensors: 184.2002 [2023-03-09 05:38:55,176][613581] RolloutWorker_w7 profile tree view: wait_for_trajectories: 4.1329, enqueue_policy_requests: 155.2767, env_step: 5564.5059, overhead: 333.0365, complete_rollouts: 3.6338 save_policy_outputs: 366.0366 split_output_tensors: 179.2746 [2023-03-09 05:38:55,176][613581] Loop Runner_EvtLoop terminating... [2023-03-09 05:38:55,177][613581] Runner profile tree view: main_loop: 9936.9824 [2023-03-09 05:38:55,177][613581] Collected {0: 100007936}, FPS: 10064.2