[2023-07-07 15:56:57,546][565952] Saving configuration to /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/config.json... [2023-07-07 15:56:57,554][565952] Rollout worker 0 uses device cpu [2023-07-07 15:56:57,554][565952] Rollout worker 1 uses device cpu [2023-07-07 15:56:57,554][565952] Rollout worker 2 uses device cpu [2023-07-07 15:56:57,555][565952] Rollout worker 3 uses device cpu [2023-07-07 15:56:57,555][565952] Rollout worker 4 uses device cpu [2023-07-07 15:56:57,555][565952] Rollout worker 5 uses device cpu [2023-07-07 15:56:57,555][565952] Rollout worker 6 uses device cpu [2023-07-07 15:56:57,555][565952] Rollout worker 7 uses device cpu [2023-07-07 15:56:57,555][565952] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 [2023-07-07 15:56:57,578][565952] InferenceWorker_p0-w0: min num requests: 2 [2023-07-07 15:56:57,596][565952] Starting all processes... [2023-07-07 15:56:57,596][565952] Starting process learner_proc0 [2023-07-07 15:56:57,598][565952] Starting all processes... [2023-07-07 15:56:57,599][565952] Starting process inference_proc0-0 [2023-07-07 15:56:57,599][565952] Starting process rollout_proc0 [2023-07-07 15:56:57,599][565952] Starting process rollout_proc1 [2023-07-07 15:56:57,599][565952] Starting process rollout_proc2 [2023-07-07 15:56:57,600][565952] Starting process rollout_proc3 [2023-07-07 15:56:57,600][565952] Starting process rollout_proc4 [2023-07-07 15:56:57,600][565952] Starting process rollout_proc5 [2023-07-07 15:56:57,600][565952] Starting process rollout_proc6 [2023-07-07 15:56:57,600][565952] Starting process rollout_proc7 [2023-07-07 15:56:59,696][566416] Worker 5 uses CPU cores [20, 21, 22, 23] [2023-07-07 15:56:59,696][566417] Worker 6 uses CPU cores [24, 25, 26, 27] [2023-07-07 15:56:59,757][566418] Worker 7 uses CPU cores [28, 29, 30, 31] [2023-07-07 15:56:59,773][566414] Worker 3 uses CPU cores [12, 13, 14, 15] [2023-07-07 15:56:59,946][566411] Worker 0 uses CPU cores [0, 1, 2, 3] [2023-07-07 15:57:00,213][566415] Worker 4 uses CPU cores [16, 17, 18, 19] [2023-07-07 15:57:00,217][566412] Worker 1 uses CPU cores [4, 5, 6, 7] [2023-07-07 15:57:00,303][566413] Worker 2 uses CPU cores [8, 9, 10, 11] [2023-07-07 15:57:00,413][566397] Starting seed is not provided [2023-07-07 15:57:00,413][566397] Initializing actor-critic model on device cpu [2023-07-07 15:57:00,413][566397] RunningMeanStd input shape: (39,) [2023-07-07 15:57:00,425][566397] RunningMeanStd input shape: (1,) [2023-07-07 15:57:00,496][566397] Created Actor Critic model with architecture: [2023-07-07 15:57:00,496][566397] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): MultiInputEncoder( (encoders): ModuleDict( (obs): MlpEncoder( (mlp_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=Tanh) (2): RecursiveScriptModule(original_name=Linear) (3): RecursiveScriptModule(original_name=Tanh) ) ) ) ) (core): ModelCoreIdentity() (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=64, out_features=1, bias=True) (action_parameterization): ActionParameterizationContinuousNonAdaptiveStddev( (distribution_linear): Linear(in_features=64, out_features=4, bias=True) ) ) [2023-07-07 15:57:00,794][566397] Using optimizer [2023-07-07 15:57:00,795][566397] No checkpoints found [2023-07-07 15:57:00,795][566397] Did not load from checkpoint, starting from scratch! [2023-07-07 15:57:00,800][566397] Initialized policy 0 weights for model version 0 [2023-07-07 15:57:00,801][566397] LearnerWorker_p0 finished initialization! [2023-07-07 15:57:00,803][566410] RunningMeanStd input shape: (39,) [2023-07-07 15:57:00,803][566410] RunningMeanStd input shape: (1,) [2023-07-07 15:57:00,891][565952] Inference worker 0-0 is ready! [2023-07-07 15:57:00,892][565952] All inference workers are ready! Signal rollout workers to start! [2023-07-07 15:57:04,506][565952] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-07-07 15:57:05,038][566411] Decorrelating experience for 0 frames... [2023-07-07 15:57:05,052][566411] Decorrelating experience for 64 frames... [2023-07-07 15:57:05,059][566415] Decorrelating experience for 0 frames... [2023-07-07 15:57:05,073][566415] Decorrelating experience for 64 frames... [2023-07-07 15:57:05,089][566418] Decorrelating experience for 0 frames... [2023-07-07 15:57:05,090][566411] Decorrelating experience for 128 frames... [2023-07-07 15:57:05,103][566418] Decorrelating experience for 64 frames... [2023-07-07 15:57:05,111][566415] Decorrelating experience for 128 frames... [2023-07-07 15:57:05,132][566416] Decorrelating experience for 0 frames... [2023-07-07 15:57:05,143][566418] Decorrelating experience for 128 frames... [2023-07-07 15:57:05,146][566416] Decorrelating experience for 64 frames... [2023-07-07 15:57:05,158][566411] Decorrelating experience for 192 frames... [2023-07-07 15:57:05,170][566417] Decorrelating experience for 0 frames... [2023-07-07 15:57:05,175][566415] Decorrelating experience for 192 frames... [2023-07-07 15:57:05,177][566413] Decorrelating experience for 0 frames... [2023-07-07 15:57:05,184][566417] Decorrelating experience for 64 frames... [2023-07-07 15:57:05,185][566416] Decorrelating experience for 128 frames... [2023-07-07 15:57:05,190][566413] Decorrelating experience for 64 frames... [2023-07-07 15:57:05,207][566418] Decorrelating experience for 192 frames... [2023-07-07 15:57:05,216][566412] Decorrelating experience for 0 frames... [2023-07-07 15:57:05,223][566417] Decorrelating experience for 128 frames... [2023-07-07 15:57:05,229][566413] Decorrelating experience for 128 frames... [2023-07-07 15:57:05,230][566412] Decorrelating experience for 64 frames... [2023-07-07 15:57:05,249][566416] Decorrelating experience for 192 frames... [2023-07-07 15:57:05,269][566412] Decorrelating experience for 128 frames... [2023-07-07 15:57:05,287][566417] Decorrelating experience for 192 frames... [2023-07-07 15:57:05,293][566413] Decorrelating experience for 192 frames... [2023-07-07 15:57:05,333][566412] Decorrelating experience for 192 frames... [2023-07-07 15:57:05,845][566414] Decorrelating experience for 0 frames... [2023-07-07 15:57:05,861][566414] Decorrelating experience for 64 frames... [2023-07-07 15:57:05,906][566414] Decorrelating experience for 128 frames... [2023-07-07 15:57:05,975][566414] Decorrelating experience for 192 frames... [2023-07-07 15:57:09,317][566411] Decorrelating experience for 256 frames... [2023-07-07 15:57:09,324][566415] Decorrelating experience for 256 frames... [2023-07-07 15:57:09,340][566416] Decorrelating experience for 256 frames... [2023-07-07 15:57:09,409][566418] Decorrelating experience for 256 frames... [2023-07-07 15:57:09,417][566412] Decorrelating experience for 256 frames... [2023-07-07 15:57:09,432][566411] Decorrelating experience for 320 frames... [2023-07-07 15:57:09,440][566415] Decorrelating experience for 320 frames... [2023-07-07 15:57:09,453][566416] Decorrelating experience for 320 frames... [2023-07-07 15:57:09,506][565952] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-07-07 15:57:09,508][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000000_0.pth... [2023-07-07 15:57:09,523][566418] Decorrelating experience for 320 frames... [2023-07-07 15:57:09,533][566412] Decorrelating experience for 320 frames... [2023-07-07 15:57:09,578][566411] Decorrelating experience for 384 frames... [2023-07-07 15:57:09,581][566415] Decorrelating experience for 384 frames... [2023-07-07 15:57:09,597][566416] Decorrelating experience for 384 frames... [2023-07-07 15:57:09,660][566418] Decorrelating experience for 384 frames... [2023-07-07 15:57:09,692][566412] Decorrelating experience for 384 frames... [2023-07-07 15:57:09,714][566417] Decorrelating experience for 256 frames... [2023-07-07 15:57:09,754][566415] Decorrelating experience for 448 frames... [2023-07-07 15:57:09,767][566411] Decorrelating experience for 448 frames... [2023-07-07 15:57:09,786][566416] Decorrelating experience for 448 frames... [2023-07-07 15:57:09,828][566418] Decorrelating experience for 448 frames... [2023-07-07 15:57:09,833][566417] Decorrelating experience for 320 frames... [2023-07-07 15:57:09,854][566412] Decorrelating experience for 448 frames... [2023-07-07 15:57:09,866][566413] Decorrelating experience for 256 frames... [2023-07-07 15:57:09,977][566413] Decorrelating experience for 320 frames... [2023-07-07 15:57:09,978][566417] Decorrelating experience for 384 frames... [2023-07-07 15:57:10,115][566413] Decorrelating experience for 384 frames... [2023-07-07 15:57:10,138][566417] Decorrelating experience for 448 frames... [2023-07-07 15:57:10,276][566413] Decorrelating experience for 448 frames... [2023-07-07 15:57:10,741][566414] Decorrelating experience for 256 frames... [2023-07-07 15:57:10,851][566414] Decorrelating experience for 320 frames... [2023-07-07 15:57:10,985][566414] Decorrelating experience for 384 frames... [2023-07-07 15:57:11,145][566414] Decorrelating experience for 448 frames... [2023-07-07 15:57:14,506][565952] Fps is (10 sec: 2457.6, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 24576. Throughput: 0: 1226.8. Samples: 12268. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 15:57:14,506][565952] Avg episode reward: [(0, '3.761')] [2023-07-07 15:57:15,988][566410] Updated weights for policy 0, policy_version 80 (0.0005) [2023-07-07 15:57:17,574][565952] Heartbeat connected on Batcher_0 [2023-07-07 15:57:17,576][565952] Heartbeat connected on LearnerWorker_p0 [2023-07-07 15:57:17,580][565952] Heartbeat connected on InferenceWorker_p0-w0 [2023-07-07 15:57:17,581][565952] Heartbeat connected on RolloutWorker_w0 [2023-07-07 15:57:17,586][565952] Heartbeat connected on RolloutWorker_w1 [2023-07-07 15:57:17,591][565952] Heartbeat connected on RolloutWorker_w2 [2023-07-07 15:57:17,592][565952] Heartbeat connected on RolloutWorker_w3 [2023-07-07 15:57:17,592][565952] Heartbeat connected on RolloutWorker_w4 [2023-07-07 15:57:17,595][565952] Heartbeat connected on RolloutWorker_w5 [2023-07-07 15:57:17,597][565952] Heartbeat connected on RolloutWorker_w7 [2023-07-07 15:57:17,598][565952] Heartbeat connected on RolloutWorker_w6 [2023-07-07 15:57:19,506][565952] Fps is (10 sec: 6963.3, 60 sec: 4642.1, 300 sec: 4642.1). Total num frames: 69632. Throughput: 0: 4456.8. Samples: 66852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:57:19,506][565952] Avg episode reward: [(0, '7.900')] [2023-07-07 15:57:20,488][566410] Updated weights for policy 0, policy_version 160 (0.0005) [2023-07-07 15:57:24,506][565952] Fps is (10 sec: 9011.1, 60 sec: 5734.4, 300 sec: 5734.4). Total num frames: 114688. Throughput: 0: 4763.0. Samples: 95260. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 15:57:24,506][565952] Avg episode reward: [(0, '8.282')] [2023-07-07 15:57:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000232_118784.pth... [2023-07-07 15:57:24,512][566397] Saving new best policy, reward=8.282! [2023-07-07 15:57:24,961][566410] Updated weights for policy 0, policy_version 240 (0.0005) [2023-07-07 15:57:29,307][566410] Updated weights for policy 0, policy_version 320 (0.0005) [2023-07-07 15:57:29,506][565952] Fps is (10 sec: 9420.7, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 163840. Throughput: 0: 6064.6. Samples: 151616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:57:29,507][565952] Avg episode reward: [(0, '11.319')] [2023-07-07 15:57:29,507][566397] Saving new best policy, reward=11.319! [2023-07-07 15:57:33,592][566410] Updated weights for policy 0, policy_version 400 (0.0005) [2023-07-07 15:57:34,506][565952] Fps is (10 sec: 9830.5, 60 sec: 7099.7, 300 sec: 7099.7). Total num frames: 212992. Throughput: 0: 6954.3. Samples: 208628. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 15:57:34,506][565952] Avg episode reward: [(0, '8.452')] [2023-07-07 15:57:37,955][566410] Updated weights for policy 0, policy_version 480 (0.0005) [2023-07-07 15:57:39,506][565952] Fps is (10 sec: 9420.9, 60 sec: 7372.8, 300 sec: 7372.8). Total num frames: 258048. Throughput: 0: 6766.0. Samples: 236808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:57:39,506][565952] Avg episode reward: [(0, '10.447')] [2023-07-07 15:57:39,508][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000504_258048.pth... [2023-07-07 15:57:39,510][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000000_0.pth [2023-07-07 15:57:42,368][566410] Updated weights for policy 0, policy_version 560 (0.0005) [2023-07-07 15:57:44,506][565952] Fps is (10 sec: 9420.8, 60 sec: 7680.0, 300 sec: 7680.0). Total num frames: 307200. Throughput: 0: 7325.7. Samples: 293028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:57:44,506][565952] Avg episode reward: [(0, '14.992')] [2023-07-07 15:57:44,507][566397] Saving new best policy, reward=14.992! [2023-07-07 15:57:46,729][566410] Updated weights for policy 0, policy_version 640 (0.0006) [2023-07-07 15:57:49,506][565952] Fps is (10 sec: 9420.7, 60 sec: 7827.9, 300 sec: 7827.9). Total num frames: 352256. Throughput: 0: 7736.8. Samples: 348156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:57:49,506][565952] Avg episode reward: [(0, '16.919')] [2023-07-07 15:57:49,507][566397] Saving new best policy, reward=16.919! [2023-07-07 15:57:50,947][566410] Updated weights for policy 0, policy_version 720 (0.0005) [2023-07-07 15:57:54,506][565952] Fps is (10 sec: 9420.7, 60 sec: 8028.2, 300 sec: 8028.2). Total num frames: 401408. Throughput: 0: 8414.9. Samples: 378668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:57:54,506][565952] Avg episode reward: [(0, '33.900')] [2023-07-07 15:57:54,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000784_401408.pth... [2023-07-07 15:57:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000232_118784.pth [2023-07-07 15:57:54,513][566397] Saving new best policy, reward=33.900! [2023-07-07 15:57:55,265][566410] Updated weights for policy 0, policy_version 800 (0.0005) [2023-07-07 15:57:59,506][565952] Fps is (10 sec: 9420.8, 60 sec: 8117.5, 300 sec: 8117.5). Total num frames: 446464. Throughput: 0: 9373.1. Samples: 434060. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 15:57:59,506][565952] Avg episode reward: [(0, '56.281')] [2023-07-07 15:57:59,507][566397] Saving new best policy, reward=56.398! [2023-07-07 15:57:59,841][566410] Updated weights for policy 0, policy_version 880 (0.0005) [2023-07-07 15:58:04,151][566410] Updated weights for policy 0, policy_version 960 (0.0005) [2023-07-07 15:58:04,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 491520. Throughput: 0: 9409.4. Samples: 490276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:58:04,506][565952] Avg episode reward: [(0, '57.530')] [2023-07-07 15:58:04,507][566397] Saving new best policy, reward=57.530! [2023-07-07 15:58:08,592][566410] Updated weights for policy 0, policy_version 1040 (0.0005) [2023-07-07 15:58:09,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8943.0, 300 sec: 8255.0). Total num frames: 536576. Throughput: 0: 9388.4. Samples: 517736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:58:09,506][565952] Avg episode reward: [(0, '44.376')] [2023-07-07 15:58:09,526][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001056_540672.pth... [2023-07-07 15:58:09,528][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000504_258048.pth [2023-07-07 15:58:13,004][566410] Updated weights for policy 0, policy_version 1120 (0.0005) [2023-07-07 15:58:14,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 8367.6). Total num frames: 585728. Throughput: 0: 9368.1. Samples: 573180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:58:14,506][565952] Avg episode reward: [(0, '60.734')] [2023-07-07 15:58:14,507][566397] Saving new best policy, reward=60.734! [2023-07-07 15:58:17,540][566410] Updated weights for policy 0, policy_version 1200 (0.0005) [2023-07-07 15:58:19,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 8410.5). Total num frames: 630784. Throughput: 0: 9300.1. Samples: 627132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:58:19,506][565952] Avg episode reward: [(0, '87.449')] [2023-07-07 15:58:19,507][566397] Saving new best policy, reward=87.449! [2023-07-07 15:58:21,926][566410] Updated weights for policy 0, policy_version 1280 (0.0005) [2023-07-07 15:58:24,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9352.6, 300 sec: 8448.0). Total num frames: 675840. Throughput: 0: 9302.6. Samples: 655424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:58:24,506][565952] Avg episode reward: [(0, '207.052')] [2023-07-07 15:58:24,554][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001328_679936.pth... [2023-07-07 15:58:24,556][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000784_401408.pth [2023-07-07 15:58:24,556][566397] Saving new best policy, reward=207.052! [2023-07-07 15:58:26,112][566410] Updated weights for policy 0, policy_version 1360 (0.0005) [2023-07-07 15:58:29,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9352.5, 300 sec: 8529.3). Total num frames: 724992. Throughput: 0: 9370.2. Samples: 714688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:58:29,507][565952] Avg episode reward: [(0, '138.800')] [2023-07-07 15:58:30,442][566410] Updated weights for policy 0, policy_version 1440 (0.0005) [2023-07-07 15:58:34,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 8556.1). Total num frames: 770048. Throughput: 0: 9333.4. Samples: 768160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:58:34,506][565952] Avg episode reward: [(0, '206.381')] [2023-07-07 15:58:35,048][566410] Updated weights for policy 0, policy_version 1520 (0.0005) [2023-07-07 15:58:39,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 8580.0). Total num frames: 815104. Throughput: 0: 9255.0. Samples: 795144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:58:39,506][565952] Avg episode reward: [(0, '106.756')] [2023-07-07 15:58:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001592_815104.pth... [2023-07-07 15:58:39,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001056_540672.pth [2023-07-07 15:58:39,623][566410] Updated weights for policy 0, policy_version 1600 (0.0005) [2023-07-07 15:58:44,101][566410] Updated weights for policy 0, policy_version 1680 (0.0005) [2023-07-07 15:58:44,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 8601.6). Total num frames: 860160. Throughput: 0: 9238.5. Samples: 849792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:58:44,507][565952] Avg episode reward: [(0, '96.031')] [2023-07-07 15:58:48,672][566410] Updated weights for policy 0, policy_version 1760 (0.0005) [2023-07-07 15:58:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 8621.1). Total num frames: 905216. Throughput: 0: 9196.1. Samples: 904100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:58:49,506][565952] Avg episode reward: [(0, '60.104')] [2023-07-07 15:58:52,982][566410] Updated weights for policy 0, policy_version 1840 (0.0005) [2023-07-07 15:58:54,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 8676.1). Total num frames: 954368. Throughput: 0: 9226.9. Samples: 932944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:58:54,506][565952] Avg episode reward: [(0, '64.821')] [2023-07-07 15:58:54,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001864_954368.pth... [2023-07-07 15:58:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001328_679936.pth [2023-07-07 15:58:57,423][566410] Updated weights for policy 0, policy_version 1920 (0.0005) [2023-07-07 15:58:59,506][565952] Fps is (10 sec: 9420.9, 60 sec: 9216.0, 300 sec: 8690.6). Total num frames: 999424. Throughput: 0: 9201.4. Samples: 987244. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 15:58:59,506][565952] Avg episode reward: [(0, '90.593')] [2023-07-07 15:59:01,782][566410] Updated weights for policy 0, policy_version 2000 (0.0005) [2023-07-07 15:59:04,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 8738.1). Total num frames: 1048576. Throughput: 0: 9269.2. Samples: 1044244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:59:04,506][565952] Avg episode reward: [(0, '66.607')] [2023-07-07 15:59:06,147][566410] Updated weights for policy 0, policy_version 2080 (0.0005) [2023-07-07 15:59:09,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 8749.1). Total num frames: 1093632. Throughput: 0: 9275.6. Samples: 1072824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:59:09,506][565952] Avg episode reward: [(0, '70.772')] [2023-07-07 15:59:09,527][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002144_1097728.pth... [2023-07-07 15:59:09,528][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001592_815104.pth [2023-07-07 15:59:10,374][566410] Updated weights for policy 0, policy_version 2160 (0.0005) [2023-07-07 15:59:14,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 8790.6). Total num frames: 1142784. Throughput: 0: 9237.0. Samples: 1130352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:59:14,506][565952] Avg episode reward: [(0, '50.934')] [2023-07-07 15:59:14,806][566410] Updated weights for policy 0, policy_version 2240 (0.0005) [2023-07-07 15:59:19,181][566410] Updated weights for policy 0, policy_version 2320 (0.0005) [2023-07-07 15:59:19,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 8798.8). Total num frames: 1187840. Throughput: 0: 9287.7. Samples: 1186104. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 15:59:19,506][565952] Avg episode reward: [(0, '35.461')] [2023-07-07 15:59:22,429][566397] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000001 [2023-07-07 15:59:23,844][566410] Updated weights for policy 0, policy_version 2400 (0.0006) [2023-07-07 15:59:24,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9284.2, 300 sec: 8806.4). Total num frames: 1232896. Throughput: 0: 9272.9. Samples: 1212424. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 15:59:24,507][565952] Avg episode reward: [(0, '45.873')] [2023-07-07 15:59:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002408_1232896.pth... [2023-07-07 15:59:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001864_954368.pth [2023-07-07 15:59:28,411][566410] Updated weights for policy 0, policy_version 2480 (0.0004) [2023-07-07 15:59:29,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 8813.5). Total num frames: 1277952. Throughput: 0: 9235.2. Samples: 1265376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:59:29,506][565952] Avg episode reward: [(0, '93.104')] [2023-07-07 15:59:32,813][566410] Updated weights for policy 0, policy_version 2560 (0.0005) [2023-07-07 15:59:34,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 8820.0). Total num frames: 1323008. Throughput: 0: 9253.5. Samples: 1320508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:59:34,507][565952] Avg episode reward: [(0, '132.770')] [2023-07-07 15:59:37,568][566410] Updated weights for policy 0, policy_version 2640 (0.0005) [2023-07-07 15:59:39,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 8826.2). Total num frames: 1368064. Throughput: 0: 9196.8. Samples: 1346800. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 15:59:39,506][565952] Avg episode reward: [(0, '154.731')] [2023-07-07 15:59:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002672_1368064.pth... [2023-07-07 15:59:39,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002144_1097728.pth [2023-07-07 15:59:42,086][566410] Updated weights for policy 0, policy_version 2720 (0.0005) [2023-07-07 15:59:44,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 8832.0). Total num frames: 1413120. Throughput: 0: 9189.0. Samples: 1400748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:59:44,506][565952] Avg episode reward: [(0, '213.386')] [2023-07-07 15:59:44,507][566397] Saving new best policy, reward=213.386! [2023-07-07 15:59:46,593][566410] Updated weights for policy 0, policy_version 2800 (0.0005) [2023-07-07 15:59:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 8837.4). Total num frames: 1458176. Throughput: 0: 9145.2. Samples: 1455776. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 15:59:49,506][565952] Avg episode reward: [(0, '126.192')] [2023-07-07 15:59:50,946][566410] Updated weights for policy 0, policy_version 2880 (0.0006) [2023-07-07 15:59:54,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9147.7, 300 sec: 8842.5). Total num frames: 1503232. Throughput: 0: 9125.5. Samples: 1483472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:59:54,507][565952] Avg episode reward: [(0, '165.071')] [2023-07-07 15:59:54,511][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002936_1503232.pth... [2023-07-07 15:59:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002408_1232896.pth [2023-07-07 15:59:55,547][566410] Updated weights for policy 0, policy_version 2960 (0.0005) [2023-07-07 15:59:59,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 8870.8). Total num frames: 1552384. Throughput: 0: 9090.1. Samples: 1539404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 15:59:59,506][565952] Avg episode reward: [(0, '236.596')] [2023-07-07 15:59:59,507][566397] Saving new best policy, reward=236.596! [2023-07-07 15:59:59,760][566410] Updated weights for policy 0, policy_version 3040 (0.0005) [2023-07-07 16:00:04,114][566410] Updated weights for policy 0, policy_version 3120 (0.0005) [2023-07-07 16:00:04,506][565952] Fps is (10 sec: 9420.9, 60 sec: 9147.7, 300 sec: 8874.7). Total num frames: 1597440. Throughput: 0: 9117.0. Samples: 1596368. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:00:04,506][565952] Avg episode reward: [(0, '206.810')] [2023-07-07 16:00:08,451][566410] Updated weights for policy 0, policy_version 3200 (0.0005) [2023-07-07 16:00:09,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 8900.5). Total num frames: 1646592. Throughput: 0: 9160.5. Samples: 1624644. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:00:09,506][565952] Avg episode reward: [(0, '275.701')] [2023-07-07 16:00:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003216_1646592.pth... [2023-07-07 16:00:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002672_1368064.pth [2023-07-07 16:00:09,513][566397] Saving new best policy, reward=275.701! [2023-07-07 16:00:12,673][566410] Updated weights for policy 0, policy_version 3280 (0.0005) [2023-07-07 16:00:14,506][565952] Fps is (10 sec: 9830.2, 60 sec: 9216.0, 300 sec: 8925.0). Total num frames: 1695744. Throughput: 0: 9270.8. Samples: 1682564. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:00:14,507][565952] Avg episode reward: [(0, '194.302')] [2023-07-07 16:00:17,100][566410] Updated weights for policy 0, policy_version 3360 (0.0005) [2023-07-07 16:00:19,506][565952] Fps is (10 sec: 9420.9, 60 sec: 9216.0, 300 sec: 8927.2). Total num frames: 1740800. Throughput: 0: 9250.2. Samples: 1736768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:00:19,506][565952] Avg episode reward: [(0, '143.888')] [2023-07-07 16:00:21,530][566410] Updated weights for policy 0, policy_version 3440 (0.0005) [2023-07-07 16:00:24,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9216.0, 300 sec: 8929.3). Total num frames: 1785856. Throughput: 0: 9299.1. Samples: 1765260. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:00:24,506][565952] Avg episode reward: [(0, '90.510')] [2023-07-07 16:00:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003488_1785856.pth... [2023-07-07 16:00:24,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002936_1503232.pth [2023-07-07 16:00:26,056][566410] Updated weights for policy 0, policy_version 3520 (0.0005) [2023-07-07 16:00:29,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 8931.3). Total num frames: 1830912. Throughput: 0: 9286.3. Samples: 1818632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:00:29,506][565952] Avg episode reward: [(0, '91.729')] [2023-07-07 16:00:30,613][566410] Updated weights for policy 0, policy_version 3600 (0.0006) [2023-07-07 16:00:34,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9216.0, 300 sec: 8933.2). Total num frames: 1875968. Throughput: 0: 9285.0. Samples: 1873600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:00:34,506][565952] Avg episode reward: [(0, '248.163')] [2023-07-07 16:00:35,179][566410] Updated weights for policy 0, policy_version 3680 (0.0005) [2023-07-07 16:00:39,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 8935.0). Total num frames: 1921024. Throughput: 0: 9269.7. Samples: 1900608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:00:39,506][565952] Avg episode reward: [(0, '318.597')] [2023-07-07 16:00:39,541][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003760_1925120.pth... [2023-07-07 16:00:39,542][566410] Updated weights for policy 0, policy_version 3760 (0.0005) [2023-07-07 16:00:39,543][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003216_1646592.pth [2023-07-07 16:00:39,544][566397] Saving new best policy, reward=318.597! [2023-07-07 16:00:44,097][566410] Updated weights for policy 0, policy_version 3840 (0.0006) [2023-07-07 16:00:44,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 8936.7). Total num frames: 1966080. Throughput: 0: 9264.9. Samples: 1956324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:00:44,507][565952] Avg episode reward: [(0, '235.219')] [2023-07-07 16:00:48,599][566410] Updated weights for policy 0, policy_version 3920 (0.0006) [2023-07-07 16:00:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 8938.4). Total num frames: 2011136. Throughput: 0: 9204.8. Samples: 2010584. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:00:49,506][565952] Avg episode reward: [(0, '192.028')] [2023-07-07 16:00:52,992][566410] Updated weights for policy 0, policy_version 4000 (0.0006) [2023-07-07 16:00:54,506][565952] Fps is (10 sec: 9421.0, 60 sec: 9284.3, 300 sec: 8957.8). Total num frames: 2060288. Throughput: 0: 9198.4. Samples: 2038572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:00:54,506][565952] Avg episode reward: [(0, '141.129')] [2023-07-07 16:00:54,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004024_2060288.pth... [2023-07-07 16:00:54,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003488_1785856.pth [2023-07-07 16:00:57,446][566410] Updated weights for policy 0, policy_version 4080 (0.0005) [2023-07-07 16:00:59,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 8958.9). Total num frames: 2105344. Throughput: 0: 9125.5. Samples: 2093208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:00:59,506][565952] Avg episode reward: [(0, '301.566')] [2023-07-07 16:01:01,995][566410] Updated weights for policy 0, policy_version 4160 (0.0005) [2023-07-07 16:01:04,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 8960.0). Total num frames: 2150400. Throughput: 0: 9142.0. Samples: 2148160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:01:04,506][565952] Avg episode reward: [(0, '201.877')] [2023-07-07 16:01:06,429][566410] Updated weights for policy 0, policy_version 4240 (0.0005) [2023-07-07 16:01:09,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9216.0, 300 sec: 8977.8). Total num frames: 2199552. Throughput: 0: 9125.9. Samples: 2175924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:01:09,506][565952] Avg episode reward: [(0, '337.420')] [2023-07-07 16:01:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004296_2199552.pth... [2023-07-07 16:01:09,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003760_1925120.pth [2023-07-07 16:01:09,513][566397] Saving new best policy, reward=337.420! [2023-07-07 16:01:10,859][566410] Updated weights for policy 0, policy_version 4320 (0.0005) [2023-07-07 16:01:14,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9147.8, 300 sec: 8978.4). Total num frames: 2244608. Throughput: 0: 9176.4. Samples: 2231572. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-07 16:01:14,506][565952] Avg episode reward: [(0, '209.756')] [2023-07-07 16:01:15,260][566410] Updated weights for policy 0, policy_version 4400 (0.0005) [2023-07-07 16:01:19,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9147.7, 300 sec: 8979.1). Total num frames: 2289664. Throughput: 0: 9197.9. Samples: 2287508. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:01:19,507][565952] Avg episode reward: [(0, '414.743')] [2023-07-07 16:01:19,507][566397] Saving new best policy, reward=414.743! [2023-07-07 16:01:19,576][566410] Updated weights for policy 0, policy_version 4480 (0.0005) [2023-07-07 16:01:23,839][566410] Updated weights for policy 0, policy_version 4560 (0.0005) [2023-07-07 16:01:24,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 8995.4). Total num frames: 2338816. Throughput: 0: 9276.2. Samples: 2318036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:01:24,506][565952] Avg episode reward: [(0, '296.812')] [2023-07-07 16:01:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004568_2338816.pth... [2023-07-07 16:01:24,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004024_2060288.pth [2023-07-07 16:01:28,166][566410] Updated weights for policy 0, policy_version 4640 (0.0005) [2023-07-07 16:01:29,506][565952] Fps is (10 sec: 9421.0, 60 sec: 9216.0, 300 sec: 8995.7). Total num frames: 2383872. Throughput: 0: 9283.6. Samples: 2374084. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:01:29,506][565952] Avg episode reward: [(0, '378.163')] [2023-07-07 16:01:32,611][566410] Updated weights for policy 0, policy_version 4720 (0.0006) [2023-07-07 16:01:34,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9011.2). Total num frames: 2433024. Throughput: 0: 9297.9. Samples: 2428992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:01:34,506][565952] Avg episode reward: [(0, '365.999')] [2023-07-07 16:01:37,111][566410] Updated weights for policy 0, policy_version 4800 (0.0005) [2023-07-07 16:01:39,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9011.2). Total num frames: 2478080. Throughput: 0: 9283.1. Samples: 2456312. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:01:39,507][565952] Avg episode reward: [(0, '180.080')] [2023-07-07 16:01:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004840_2478080.pth... [2023-07-07 16:01:39,516][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004296_2199552.pth [2023-07-07 16:01:41,706][566410] Updated weights for policy 0, policy_version 4880 (0.0005) [2023-07-07 16:01:44,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9011.2). Total num frames: 2523136. Throughput: 0: 9282.3. Samples: 2510912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:01:44,506][565952] Avg episode reward: [(0, '162.456')] [2023-07-07 16:01:45,989][566410] Updated weights for policy 0, policy_version 4960 (0.0005) [2023-07-07 16:01:49,506][565952] Fps is (10 sec: 9420.9, 60 sec: 9352.5, 300 sec: 9025.6). Total num frames: 2572288. Throughput: 0: 9335.5. Samples: 2568256. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:01:49,506][565952] Avg episode reward: [(0, '518.536')] [2023-07-07 16:01:49,507][566397] Saving new best policy, reward=518.536! [2023-07-07 16:01:50,254][566410] Updated weights for policy 0, policy_version 5040 (0.0004) [2023-07-07 16:01:54,470][566410] Updated weights for policy 0, policy_version 5120 (0.0005) [2023-07-07 16:01:54,506][565952] Fps is (10 sec: 9830.4, 60 sec: 9352.5, 300 sec: 9039.4). Total num frames: 2621440. Throughput: 0: 9355.6. Samples: 2596928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:01:54,507][565952] Avg episode reward: [(0, '605.406')] [2023-07-07 16:01:54,511][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005120_2621440.pth... [2023-07-07 16:01:54,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004568_2338816.pth [2023-07-07 16:01:54,514][566397] Saving new best policy, reward=605.406! [2023-07-07 16:01:58,792][566410] Updated weights for policy 0, policy_version 5200 (0.0005) [2023-07-07 16:01:59,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9039.0). Total num frames: 2666496. Throughput: 0: 9413.3. Samples: 2655168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:01:59,506][565952] Avg episode reward: [(0, '463.825')] [2023-07-07 16:02:03,252][566410] Updated weights for policy 0, policy_version 5280 (0.0005) [2023-07-07 16:02:04,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9352.6, 300 sec: 9191.7). Total num frames: 2711552. Throughput: 0: 9387.0. Samples: 2709920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:02:04,506][565952] Avg episode reward: [(0, '394.126')] [2023-07-07 16:02:07,564][566410] Updated weights for policy 0, policy_version 5360 (0.0005) [2023-07-07 16:02:09,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9275.0). Total num frames: 2760704. Throughput: 0: 9359.8. Samples: 2739228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:02:09,506][565952] Avg episode reward: [(0, '365.562')] [2023-07-07 16:02:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005392_2760704.pth... [2023-07-07 16:02:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004840_2478080.pth [2023-07-07 16:02:12,094][566410] Updated weights for policy 0, policy_version 5440 (0.0005) [2023-07-07 16:02:14,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9275.0). Total num frames: 2805760. Throughput: 0: 9313.5. Samples: 2793192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:02:14,506][565952] Avg episode reward: [(0, '352.437')] [2023-07-07 16:02:16,487][566410] Updated weights for policy 0, policy_version 5520 (0.0005) [2023-07-07 16:02:19,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9288.9). Total num frames: 2854912. Throughput: 0: 9370.9. Samples: 2850680. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:02:19,506][565952] Avg episode reward: [(0, '426.067')] [2023-07-07 16:02:20,754][566410] Updated weights for policy 0, policy_version 5600 (0.0006) [2023-07-07 16:02:24,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9275.0). Total num frames: 2899968. Throughput: 0: 9386.1. Samples: 2878684. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:02:24,506][565952] Avg episode reward: [(0, '623.172')] [2023-07-07 16:02:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005664_2899968.pth... [2023-07-07 16:02:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005120_2621440.pth [2023-07-07 16:02:24,512][566397] Saving new best policy, reward=623.172! [2023-07-07 16:02:25,192][566410] Updated weights for policy 0, policy_version 5680 (0.0005) [2023-07-07 16:02:29,390][566410] Updated weights for policy 0, policy_version 5760 (0.0004) [2023-07-07 16:02:29,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9275.0). Total num frames: 2949120. Throughput: 0: 9446.0. Samples: 2935980. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:02:29,506][565952] Avg episode reward: [(0, '814.146')] [2023-07-07 16:02:29,507][566397] Saving new best policy, reward=814.146! [2023-07-07 16:02:33,814][566410] Updated weights for policy 0, policy_version 5840 (0.0005) [2023-07-07 16:02:34,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9275.0). Total num frames: 2994176. Throughput: 0: 9393.8. Samples: 2990976. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:02:34,506][565952] Avg episode reward: [(0, '1409.028')] [2023-07-07 16:02:34,507][566397] Saving new best policy, reward=1409.028! [2023-07-07 16:02:38,307][566410] Updated weights for policy 0, policy_version 5920 (0.0006) [2023-07-07 16:02:39,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 9261.1). Total num frames: 3039232. Throughput: 0: 9375.3. Samples: 3018816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:02:39,506][565952] Avg episode reward: [(0, '568.402')] [2023-07-07 16:02:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005936_3039232.pth... [2023-07-07 16:02:39,515][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005392_2760704.pth [2023-07-07 16:02:42,809][566410] Updated weights for policy 0, policy_version 6000 (0.0005) [2023-07-07 16:02:44,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 9261.1). Total num frames: 3084288. Throughput: 0: 9281.8. Samples: 3072848. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:02:44,506][565952] Avg episode reward: [(0, '600.018')] [2023-07-07 16:02:47,132][566410] Updated weights for policy 0, policy_version 6080 (0.0005) [2023-07-07 16:02:49,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9261.1). Total num frames: 3133440. Throughput: 0: 9325.7. Samples: 3129576. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:02:49,506][565952] Avg episode reward: [(0, '707.739')] [2023-07-07 16:02:51,701][566410] Updated weights for policy 0, policy_version 6160 (0.0005) [2023-07-07 16:02:54,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9261.1). Total num frames: 3178496. Throughput: 0: 9272.5. Samples: 3156492. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:02:54,506][565952] Avg episode reward: [(0, '1043.274')] [2023-07-07 16:02:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006208_3178496.pth... [2023-07-07 16:02:54,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005664_2899968.pth [2023-07-07 16:02:56,294][566410] Updated weights for policy 0, policy_version 6240 (0.0005) [2023-07-07 16:02:59,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9261.1). Total num frames: 3223552. Throughput: 0: 9279.6. Samples: 3210776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:02:59,506][565952] Avg episode reward: [(0, '977.647')] [2023-07-07 16:03:00,713][566410] Updated weights for policy 0, policy_version 6320 (0.0005) [2023-07-07 16:03:04,506][565952] Fps is (10 sec: 9011.4, 60 sec: 9284.3, 300 sec: 9261.1). Total num frames: 3268608. Throughput: 0: 9240.6. Samples: 3266508. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:03:04,506][565952] Avg episode reward: [(0, '1118.017')] [2023-07-07 16:03:05,000][566410] Updated weights for policy 0, policy_version 6400 (0.0005) [2023-07-07 16:03:09,267][566410] Updated weights for policy 0, policy_version 6480 (0.0006) [2023-07-07 16:03:09,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9261.1). Total num frames: 3317760. Throughput: 0: 9262.8. Samples: 3295508. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:03:09,506][565952] Avg episode reward: [(0, '1138.556')] [2023-07-07 16:03:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006480_3317760.pth... [2023-07-07 16:03:09,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005936_3039232.pth [2023-07-07 16:03:13,741][566410] Updated weights for policy 0, policy_version 6560 (0.0005) [2023-07-07 16:03:14,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9261.1). Total num frames: 3362816. Throughput: 0: 9229.7. Samples: 3351316. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:03:14,506][565952] Avg episode reward: [(0, '897.694')] [2023-07-07 16:03:18,600][566410] Updated weights for policy 0, policy_version 6640 (0.0005) [2023-07-07 16:03:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 9147.7, 300 sec: 9247.2). Total num frames: 3403776. Throughput: 0: 9165.5. Samples: 3403424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:03:19,507][565952] Avg episode reward: [(0, '916.499')] [2023-07-07 16:03:23,262][566410] Updated weights for policy 0, policy_version 6720 (0.0005) [2023-07-07 16:03:24,506][565952] Fps is (10 sec: 8601.5, 60 sec: 9147.7, 300 sec: 9233.4). Total num frames: 3448832. Throughput: 0: 9100.3. Samples: 3428332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:03:24,506][565952] Avg episode reward: [(0, '980.754')] [2023-07-07 16:03:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006736_3448832.pth... [2023-07-07 16:03:24,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006208_3178496.pth [2023-07-07 16:03:27,811][566410] Updated weights for policy 0, policy_version 6800 (0.0005) [2023-07-07 16:03:29,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9233.4). Total num frames: 3493888. Throughput: 0: 9107.3. Samples: 3482676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:03:29,506][565952] Avg episode reward: [(0, '768.335')] [2023-07-07 16:03:32,220][566410] Updated weights for policy 0, policy_version 6880 (0.0005) [2023-07-07 16:03:34,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9233.4). Total num frames: 3538944. Throughput: 0: 9082.9. Samples: 3538308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:03:34,506][565952] Avg episode reward: [(0, '577.548')] [2023-07-07 16:03:36,863][566410] Updated weights for policy 0, policy_version 6960 (0.0005) [2023-07-07 16:03:39,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9233.4). Total num frames: 3584000. Throughput: 0: 9053.0. Samples: 3563876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:03:39,506][565952] Avg episode reward: [(0, '1130.607')] [2023-07-07 16:03:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007000_3584000.pth... [2023-07-07 16:03:39,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006480_3317760.pth [2023-07-07 16:03:41,376][566410] Updated weights for policy 0, policy_version 7040 (0.0005) [2023-07-07 16:03:44,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9233.4). Total num frames: 3629056. Throughput: 0: 9064.1. Samples: 3618660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:03:44,506][565952] Avg episode reward: [(0, '1041.260')] [2023-07-07 16:03:46,069][566410] Updated weights for policy 0, policy_version 7120 (0.0005) [2023-07-07 16:03:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9219.5). Total num frames: 3674112. Throughput: 0: 8998.6. Samples: 3671448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:03:49,506][565952] Avg episode reward: [(0, '1055.232')] [2023-07-07 16:03:50,513][566410] Updated weights for policy 0, policy_version 7200 (0.0005) [2023-07-07 16:03:54,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9079.5, 300 sec: 9233.4). Total num frames: 3723264. Throughput: 0: 8998.8. Samples: 3700456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:03:54,506][565952] Avg episode reward: [(0, '1204.360')] [2023-07-07 16:03:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007272_3723264.pth... [2023-07-07 16:03:54,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006736_3448832.pth [2023-07-07 16:03:54,818][566410] Updated weights for policy 0, policy_version 7280 (0.0005) [2023-07-07 16:03:59,345][566410] Updated weights for policy 0, policy_version 7360 (0.0005) [2023-07-07 16:03:59,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 9219.5). Total num frames: 3768320. Throughput: 0: 8989.2. Samples: 3755828. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:03:59,506][565952] Avg episode reward: [(0, '1088.314')] [2023-07-07 16:04:04,047][566410] Updated weights for policy 0, policy_version 7440 (0.0005) [2023-07-07 16:04:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 9011.2, 300 sec: 9205.6). Total num frames: 3809280. Throughput: 0: 9002.1. Samples: 3808520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:04:04,506][565952] Avg episode reward: [(0, '1049.383')] [2023-07-07 16:04:08,606][566410] Updated weights for policy 0, policy_version 7520 (0.0005) [2023-07-07 16:04:09,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9205.6). Total num frames: 3858432. Throughput: 0: 9044.1. Samples: 3835316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:04:09,506][565952] Avg episode reward: [(0, '1066.444')] [2023-07-07 16:04:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007536_3858432.pth... [2023-07-07 16:04:09,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007000_3584000.pth [2023-07-07 16:04:12,992][566410] Updated weights for policy 0, policy_version 7600 (0.0005) [2023-07-07 16:04:14,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9011.2, 300 sec: 9205.6). Total num frames: 3903488. Throughput: 0: 9073.2. Samples: 3890972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:04:14,506][565952] Avg episode reward: [(0, '1019.674')] [2023-07-07 16:04:17,780][566410] Updated weights for policy 0, policy_version 7680 (0.0005) [2023-07-07 16:04:19,506][565952] Fps is (10 sec: 8601.7, 60 sec: 9011.2, 300 sec: 9191.7). Total num frames: 3944448. Throughput: 0: 8980.7. Samples: 3942440. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:04:19,506][565952] Avg episode reward: [(0, '1331.465')] [2023-07-07 16:04:22,468][566410] Updated weights for policy 0, policy_version 7760 (0.0005) [2023-07-07 16:04:24,506][565952] Fps is (10 sec: 8601.7, 60 sec: 9011.2, 300 sec: 9191.7). Total num frames: 3989504. Throughput: 0: 8997.7. Samples: 3968772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:04:24,506][565952] Avg episode reward: [(0, '1066.475')] [2023-07-07 16:04:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007792_3989504.pth... [2023-07-07 16:04:24,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007272_3723264.pth [2023-07-07 16:04:26,881][566410] Updated weights for policy 0, policy_version 7840 (0.0005) [2023-07-07 16:04:29,506][565952] Fps is (10 sec: 9420.6, 60 sec: 9079.5, 300 sec: 9205.6). Total num frames: 4038656. Throughput: 0: 8991.1. Samples: 4023260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:04:29,507][565952] Avg episode reward: [(0, '1136.328')] [2023-07-07 16:04:31,174][566410] Updated weights for policy 0, policy_version 7920 (0.0005) [2023-07-07 16:04:34,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9079.5, 300 sec: 9205.6). Total num frames: 4083712. Throughput: 0: 9070.6. Samples: 4079624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:04:34,506][565952] Avg episode reward: [(0, '1271.119')] [2023-07-07 16:04:35,688][566410] Updated weights for policy 0, policy_version 8000 (0.0005) [2023-07-07 16:04:39,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9205.6). Total num frames: 4128768. Throughput: 0: 9051.0. Samples: 4107752. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:04:39,506][565952] Avg episode reward: [(0, '1000.808')] [2023-07-07 16:04:39,511][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008064_4128768.pth... [2023-07-07 16:04:39,514][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007536_3858432.pth [2023-07-07 16:04:40,305][566410] Updated weights for policy 0, policy_version 8080 (0.0005) [2023-07-07 16:04:44,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9205.6). Total num frames: 4173824. Throughput: 0: 9040.4. Samples: 4162644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:04:44,506][565952] Avg episode reward: [(0, '1217.611')] [2023-07-07 16:04:44,543][566410] Updated weights for policy 0, policy_version 8160 (0.0005) [2023-07-07 16:04:49,271][566410] Updated weights for policy 0, policy_version 8240 (0.0005) [2023-07-07 16:04:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9205.6). Total num frames: 4218880. Throughput: 0: 9063.4. Samples: 4216372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:04:49,506][565952] Avg episode reward: [(0, '1278.895')] [2023-07-07 16:04:53,779][566410] Updated weights for policy 0, policy_version 8320 (0.0005) [2023-07-07 16:04:54,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 9191.7). Total num frames: 4263936. Throughput: 0: 9069.5. Samples: 4243444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:04:54,507][565952] Avg episode reward: [(0, '1826.912')] [2023-07-07 16:04:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008328_4263936.pth... [2023-07-07 16:04:54,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007792_3989504.pth [2023-07-07 16:04:54,513][566397] Saving new best policy, reward=1826.912! [2023-07-07 16:04:58,276][566410] Updated weights for policy 0, policy_version 8400 (0.0005) [2023-07-07 16:04:59,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 9191.7). Total num frames: 4308992. Throughput: 0: 9045.5. Samples: 4298020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:04:59,506][565952] Avg episode reward: [(0, '1663.241')] [2023-07-07 16:05:03,040][566410] Updated weights for policy 0, policy_version 8480 (0.0005) [2023-07-07 16:05:04,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 4354048. Throughput: 0: 9056.0. Samples: 4349960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:05:04,506][565952] Avg episode reward: [(0, '2069.360')] [2023-07-07 16:05:04,507][566397] Saving new best policy, reward=2069.360! [2023-07-07 16:05:07,573][566410] Updated weights for policy 0, policy_version 8560 (0.0005) [2023-07-07 16:05:09,506][565952] Fps is (10 sec: 9011.0, 60 sec: 9011.2, 300 sec: 9163.9). Total num frames: 4399104. Throughput: 0: 9084.1. Samples: 4377560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:05:09,507][565952] Avg episode reward: [(0, '1835.282')] [2023-07-07 16:05:09,511][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008592_4399104.pth... [2023-07-07 16:05:09,514][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008064_4128768.pth [2023-07-07 16:05:12,200][566410] Updated weights for policy 0, policy_version 8640 (0.0005) [2023-07-07 16:05:14,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 9163.9). Total num frames: 4444160. Throughput: 0: 9057.7. Samples: 4430856. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:05:14,506][565952] Avg episode reward: [(0, '2765.896')] [2023-07-07 16:05:14,507][566397] Saving new best policy, reward=2765.896! [2023-07-07 16:05:16,685][566410] Updated weights for policy 0, policy_version 8720 (0.0005) [2023-07-07 16:05:19,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9079.4, 300 sec: 9163.9). Total num frames: 4489216. Throughput: 0: 9004.4. Samples: 4484820. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:05:19,506][565952] Avg episode reward: [(0, '2668.779')] [2023-07-07 16:05:21,271][566410] Updated weights for policy 0, policy_version 8800 (0.0005) [2023-07-07 16:05:24,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9163.9). Total num frames: 4534272. Throughput: 0: 8980.1. Samples: 4511856. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:05:24,506][565952] Avg episode reward: [(0, '2673.991')] [2023-07-07 16:05:24,508][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008856_4534272.pth... [2023-07-07 16:05:24,510][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008328_4263936.pth [2023-07-07 16:05:25,862][566410] Updated weights for policy 0, policy_version 8880 (0.0005) [2023-07-07 16:05:29,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8943.0, 300 sec: 9150.0). Total num frames: 4575232. Throughput: 0: 8910.8. Samples: 4563628. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:05:29,506][565952] Avg episode reward: [(0, '2089.219')] [2023-07-07 16:05:30,712][566410] Updated weights for policy 0, policy_version 8960 (0.0006) [2023-07-07 16:05:34,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8942.9, 300 sec: 9150.0). Total num frames: 4620288. Throughput: 0: 8884.9. Samples: 4616192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:05:34,506][565952] Avg episode reward: [(0, '2282.005')] [2023-07-07 16:05:35,363][566410] Updated weights for policy 0, policy_version 9040 (0.0005) [2023-07-07 16:05:39,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8874.7, 300 sec: 9136.2). Total num frames: 4661248. Throughput: 0: 8870.2. Samples: 4642600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:05:39,506][565952] Avg episode reward: [(0, '2370.148')] [2023-07-07 16:05:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009104_4661248.pth... [2023-07-07 16:05:39,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008592_4399104.pth [2023-07-07 16:05:40,144][566410] Updated weights for policy 0, policy_version 9120 (0.0006) [2023-07-07 16:05:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8874.7, 300 sec: 9136.2). Total num frames: 4706304. Throughput: 0: 8827.5. Samples: 4695256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:05:44,506][565952] Avg episode reward: [(0, '2424.887')] [2023-07-07 16:05:44,613][566410] Updated weights for policy 0, policy_version 9200 (0.0005) [2023-07-07 16:05:49,180][566410] Updated weights for policy 0, policy_version 9280 (0.0005) [2023-07-07 16:05:49,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8874.7, 300 sec: 9122.3). Total num frames: 4751360. Throughput: 0: 8889.9. Samples: 4750008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:05:49,506][565952] Avg episode reward: [(0, '2543.060')] [2023-07-07 16:05:54,230][566410] Updated weights for policy 0, policy_version 9360 (0.0005) [2023-07-07 16:05:54,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8806.4, 300 sec: 9108.4). Total num frames: 4792320. Throughput: 0: 8798.1. Samples: 4773476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:05:54,506][565952] Avg episode reward: [(0, '1620.694')] [2023-07-07 16:05:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009360_4792320.pth... [2023-07-07 16:05:54,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008856_4534272.pth [2023-07-07 16:05:58,999][566410] Updated weights for policy 0, policy_version 9440 (0.0005) [2023-07-07 16:05:59,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8806.4, 300 sec: 9108.4). Total num frames: 4837376. Throughput: 0: 8755.7. Samples: 4824864. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:05:59,506][565952] Avg episode reward: [(0, '2222.946')] [2023-07-07 16:06:03,801][566410] Updated weights for policy 0, policy_version 9520 (0.0005) [2023-07-07 16:06:04,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8738.1, 300 sec: 9080.6). Total num frames: 4878336. Throughput: 0: 8676.1. Samples: 4875244. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:06:04,506][565952] Avg episode reward: [(0, '2394.652')] [2023-07-07 16:06:08,637][566410] Updated weights for policy 0, policy_version 9600 (0.0005) [2023-07-07 16:06:09,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8738.2, 300 sec: 9080.6). Total num frames: 4923392. Throughput: 0: 8627.6. Samples: 4900100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:06:09,506][565952] Avg episode reward: [(0, '2705.407')] [2023-07-07 16:06:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009616_4923392.pth... [2023-07-07 16:06:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009104_4661248.pth [2023-07-07 16:06:13,341][566410] Updated weights for policy 0, policy_version 9680 (0.0005) [2023-07-07 16:06:14,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 9066.7). Total num frames: 4964352. Throughput: 0: 8646.1. Samples: 4952704. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:06:14,506][565952] Avg episode reward: [(0, '2951.227')] [2023-07-07 16:06:14,507][566397] Saving new best policy, reward=2951.227! [2023-07-07 16:06:18,018][566410] Updated weights for policy 0, policy_version 9760 (0.0005) [2023-07-07 16:06:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 9052.9). Total num frames: 5009408. Throughput: 0: 8647.1. Samples: 5005312. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:06:19,507][565952] Avg episode reward: [(0, '3672.327')] [2023-07-07 16:06:19,507][566397] Saving new best policy, reward=3672.327! [2023-07-07 16:06:22,571][566410] Updated weights for policy 0, policy_version 9840 (0.0005) [2023-07-07 16:06:24,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8669.8, 300 sec: 9052.9). Total num frames: 5054464. Throughput: 0: 8659.6. Samples: 5032284. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:06:24,507][565952] Avg episode reward: [(0, '3567.053')] [2023-07-07 16:06:24,511][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009872_5054464.pth... [2023-07-07 16:06:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009360_4792320.pth [2023-07-07 16:06:27,382][566410] Updated weights for policy 0, policy_version 9920 (0.0005) [2023-07-07 16:06:29,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.8, 300 sec: 9025.1). Total num frames: 5095424. Throughput: 0: 8633.7. Samples: 5083772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:06:29,507][565952] Avg episode reward: [(0, '3226.278')] [2023-07-07 16:06:32,094][566410] Updated weights for policy 0, policy_version 10000 (0.0005) [2023-07-07 16:06:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 9025.1). Total num frames: 5140480. Throughput: 0: 8602.4. Samples: 5137116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:06:34,507][565952] Avg episode reward: [(0, '2664.687')] [2023-07-07 16:06:36,549][566410] Updated weights for policy 0, policy_version 10080 (0.0005) [2023-07-07 16:06:39,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8738.1, 300 sec: 9025.1). Total num frames: 5185536. Throughput: 0: 8698.5. Samples: 5164908. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:06:39,506][565952] Avg episode reward: [(0, '2889.613')] [2023-07-07 16:06:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010128_5185536.pth... [2023-07-07 16:06:39,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009616_4923392.pth [2023-07-07 16:06:41,170][566410] Updated weights for policy 0, policy_version 10160 (0.0005) [2023-07-07 16:06:44,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8669.9, 300 sec: 8997.3). Total num frames: 5226496. Throughput: 0: 8734.0. Samples: 5217892. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:06:44,506][565952] Avg episode reward: [(0, '2885.042')] [2023-07-07 16:06:45,950][566410] Updated weights for policy 0, policy_version 10240 (0.0005) [2023-07-07 16:06:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8997.3). Total num frames: 5275648. Throughput: 0: 8796.6. Samples: 5271092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:06:49,506][565952] Avg episode reward: [(0, '2908.390')] [2023-07-07 16:06:50,440][566410] Updated weights for policy 0, policy_version 10320 (0.0005) [2023-07-07 16:06:54,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8738.2, 300 sec: 8983.4). Total num frames: 5316608. Throughput: 0: 8836.8. Samples: 5297756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:06:54,506][565952] Avg episode reward: [(0, '3494.232')] [2023-07-07 16:06:54,508][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010384_5316608.pth... [2023-07-07 16:06:54,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009872_5054464.pth [2023-07-07 16:06:55,145][566410] Updated weights for policy 0, policy_version 10400 (0.0005) [2023-07-07 16:06:59,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8738.1, 300 sec: 8983.4). Total num frames: 5361664. Throughput: 0: 8808.9. Samples: 5349104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:06:59,507][565952] Avg episode reward: [(0, '3302.741')] [2023-07-07 16:06:59,936][566410] Updated weights for policy 0, policy_version 10480 (0.0005) [2023-07-07 16:07:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8955.7). Total num frames: 5402624. Throughput: 0: 8801.8. Samples: 5401392. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:07:04,506][565952] Avg episode reward: [(0, '3431.228')] [2023-07-07 16:07:04,507][566410] Updated weights for policy 0, policy_version 10560 (0.0005) [2023-07-07 16:07:09,040][566410] Updated weights for policy 0, policy_version 10640 (0.0005) [2023-07-07 16:07:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8955.7). Total num frames: 5447680. Throughput: 0: 8803.6. Samples: 5428444. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:07:09,506][565952] Avg episode reward: [(0, '3736.342')] [2023-07-07 16:07:09,518][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010648_5451776.pth... [2023-07-07 16:07:09,520][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010128_5185536.pth [2023-07-07 16:07:09,520][566397] Saving new best policy, reward=3736.342! [2023-07-07 16:07:13,745][566410] Updated weights for policy 0, policy_version 10720 (0.0005) [2023-07-07 16:07:14,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8941.8). Total num frames: 5492736. Throughput: 0: 8827.1. Samples: 5480988. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:07:14,506][565952] Avg episode reward: [(0, '3044.307')] [2023-07-07 16:07:18,474][566410] Updated weights for policy 0, policy_version 10800 (0.0005) [2023-07-07 16:07:19,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8806.4, 300 sec: 8941.8). Total num frames: 5537792. Throughput: 0: 8814.5. Samples: 5533768. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:07:19,506][565952] Avg episode reward: [(0, '3246.326')] [2023-07-07 16:07:23,253][566410] Updated weights for policy 0, policy_version 10880 (0.0005) [2023-07-07 16:07:24,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8738.1, 300 sec: 8914.0). Total num frames: 5578752. Throughput: 0: 8771.5. Samples: 5559624. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:07:24,506][565952] Avg episode reward: [(0, '3651.968')] [2023-07-07 16:07:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010896_5578752.pth... [2023-07-07 16:07:24,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010384_5316608.pth [2023-07-07 16:07:27,919][566410] Updated weights for policy 0, policy_version 10960 (0.0005) [2023-07-07 16:07:29,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8806.4, 300 sec: 8914.0). Total num frames: 5623808. Throughput: 0: 8748.7. Samples: 5611584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:07:29,506][565952] Avg episode reward: [(0, '3457.588')] [2023-07-07 16:07:32,597][566410] Updated weights for policy 0, policy_version 11040 (0.0005) [2023-07-07 16:07:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8900.1). Total num frames: 5664768. Throughput: 0: 8730.6. Samples: 5663968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:07:34,506][565952] Avg episode reward: [(0, '4025.132')] [2023-07-07 16:07:34,540][566397] Saving new best policy, reward=4025.132! [2023-07-07 16:07:37,375][566410] Updated weights for policy 0, policy_version 11120 (0.0006) [2023-07-07 16:07:39,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8738.1, 300 sec: 8900.1). Total num frames: 5709824. Throughput: 0: 8702.1. Samples: 5689352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:07:39,506][565952] Avg episode reward: [(0, '3945.577')] [2023-07-07 16:07:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011152_5709824.pth... [2023-07-07 16:07:39,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010648_5451776.pth [2023-07-07 16:07:42,208][566410] Updated weights for policy 0, policy_version 11200 (0.0005) [2023-07-07 16:07:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8872.4). Total num frames: 5750784. Throughput: 0: 8700.4. Samples: 5740620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:07:44,506][565952] Avg episode reward: [(0, '3915.795')] [2023-07-07 16:07:46,957][566410] Updated weights for policy 0, policy_version 11280 (0.0005) [2023-07-07 16:07:49,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8872.4). Total num frames: 5795840. Throughput: 0: 8682.6. Samples: 5792108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:07:49,506][565952] Avg episode reward: [(0, '3273.440')] [2023-07-07 16:07:51,457][566410] Updated weights for policy 0, policy_version 11360 (0.0005) [2023-07-07 16:07:54,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8738.1, 300 sec: 8872.3). Total num frames: 5840896. Throughput: 0: 8710.5. Samples: 5820416. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:07:54,507][565952] Avg episode reward: [(0, '3378.716')] [2023-07-07 16:07:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011408_5840896.pth... [2023-07-07 16:07:54,514][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010896_5578752.pth [2023-07-07 16:07:56,043][566410] Updated weights for policy 0, policy_version 11440 (0.0005) [2023-07-07 16:07:59,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8738.1, 300 sec: 8872.4). Total num frames: 5885952. Throughput: 0: 8726.1. Samples: 5873664. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:07:59,506][565952] Avg episode reward: [(0, '3558.257')] [2023-07-07 16:08:00,753][566410] Updated weights for policy 0, policy_version 11520 (0.0006) [2023-07-07 16:08:04,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8738.1, 300 sec: 8844.6). Total num frames: 5926912. Throughput: 0: 8685.6. Samples: 5924620. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:08:04,506][565952] Avg episode reward: [(0, '3899.170')] [2023-07-07 16:08:05,671][566410] Updated weights for policy 0, policy_version 11600 (0.0005) [2023-07-07 16:08:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8844.6). Total num frames: 5971968. Throughput: 0: 8699.6. Samples: 5951104. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:08:09,506][565952] Avg episode reward: [(0, '2886.548')] [2023-07-07 16:08:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011664_5971968.pth... [2023-07-07 16:08:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011152_5709824.pth [2023-07-07 16:08:10,402][566410] Updated weights for policy 0, policy_version 11680 (0.0005) [2023-07-07 16:08:14,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8844.6). Total num frames: 6012928. Throughput: 0: 8706.5. Samples: 6003376. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:08:14,506][565952] Avg episode reward: [(0, '3621.605')] [2023-07-07 16:08:15,099][566410] Updated weights for policy 0, policy_version 11760 (0.0005) [2023-07-07 16:08:19,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8601.6, 300 sec: 8830.7). Total num frames: 6053888. Throughput: 0: 8631.2. Samples: 6052372. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:08:19,506][565952] Avg episode reward: [(0, '3193.143')] [2023-07-07 16:08:20,149][566410] Updated weights for policy 0, policy_version 11840 (0.0006) [2023-07-07 16:08:24,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8830.7). Total num frames: 6098944. Throughput: 0: 8646.1. Samples: 6078428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:08:24,506][565952] Avg episode reward: [(0, '3008.205')] [2023-07-07 16:08:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011912_6098944.pth... [2023-07-07 16:08:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011408_5840896.pth [2023-07-07 16:08:24,905][566410] Updated weights for policy 0, policy_version 11920 (0.0005) [2023-07-07 16:08:29,459][566410] Updated weights for policy 0, policy_version 12000 (0.0004) [2023-07-07 16:08:29,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8669.9, 300 sec: 8830.7). Total num frames: 6144000. Throughput: 0: 8667.6. Samples: 6130664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:08:29,506][565952] Avg episode reward: [(0, '1832.395')] [2023-07-07 16:08:34,106][566410] Updated weights for policy 0, policy_version 12080 (0.0005) [2023-07-07 16:08:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8816.8). Total num frames: 6184960. Throughput: 0: 8705.1. Samples: 6183836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:08:34,506][565952] Avg episode reward: [(0, '1840.778')] [2023-07-07 16:08:38,846][566410] Updated weights for policy 0, policy_version 12160 (0.0005) [2023-07-07 16:08:39,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8816.8). Total num frames: 6230016. Throughput: 0: 8644.6. Samples: 6209420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:08:39,506][565952] Avg episode reward: [(0, '2227.321')] [2023-07-07 16:08:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012168_6230016.pth... [2023-07-07 16:08:39,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011664_5971968.pth [2023-07-07 16:08:43,518][566410] Updated weights for policy 0, policy_version 12240 (0.0005) [2023-07-07 16:08:44,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8738.1, 300 sec: 8816.8). Total num frames: 6275072. Throughput: 0: 8635.7. Samples: 6262272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:08:44,507][565952] Avg episode reward: [(0, '1440.223')] [2023-07-07 16:08:48,097][566410] Updated weights for policy 0, policy_version 12320 (0.0004) [2023-07-07 16:08:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8802.9). Total num frames: 6320128. Throughput: 0: 8694.3. Samples: 6315864. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:08:49,506][565952] Avg episode reward: [(0, '1886.223')] [2023-07-07 16:08:53,028][566410] Updated weights for policy 0, policy_version 12400 (0.0005) [2023-07-07 16:08:54,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8669.9, 300 sec: 8789.0). Total num frames: 6361088. Throughput: 0: 8655.6. Samples: 6340608. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:08:54,506][565952] Avg episode reward: [(0, '2317.161')] [2023-07-07 16:08:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012424_6361088.pth... [2023-07-07 16:08:54,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011912_6098944.pth [2023-07-07 16:08:57,787][566410] Updated weights for policy 0, policy_version 12480 (0.0005) [2023-07-07 16:08:59,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8601.6, 300 sec: 8789.0). Total num frames: 6402048. Throughput: 0: 8617.7. Samples: 6391172. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:08:59,506][565952] Avg episode reward: [(0, '2465.854')] [2023-07-07 16:09:02,275][566410] Updated weights for policy 0, policy_version 12560 (0.0005) [2023-07-07 16:09:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8775.2). Total num frames: 6447104. Throughput: 0: 8741.1. Samples: 6445720. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:09:04,506][565952] Avg episode reward: [(0, '2916.289')] [2023-07-07 16:09:06,932][566410] Updated weights for policy 0, policy_version 12640 (0.0005) [2023-07-07 16:09:09,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8669.9, 300 sec: 8775.2). Total num frames: 6492160. Throughput: 0: 8739.1. Samples: 6471688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:09:09,506][565952] Avg episode reward: [(0, '2496.012')] [2023-07-07 16:09:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012680_6492160.pth... [2023-07-07 16:09:09,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012168_6230016.pth [2023-07-07 16:09:11,454][566410] Updated weights for policy 0, policy_version 12720 (0.0005) [2023-07-07 16:09:14,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8738.1, 300 sec: 8789.0). Total num frames: 6537216. Throughput: 0: 8763.0. Samples: 6525000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:09:14,506][565952] Avg episode reward: [(0, '2005.699')] [2023-07-07 16:09:16,171][566410] Updated weights for policy 0, policy_version 12800 (0.0005) [2023-07-07 16:09:19,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8806.4, 300 sec: 8789.0). Total num frames: 6582272. Throughput: 0: 8746.6. Samples: 6577432. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:09:19,506][565952] Avg episode reward: [(0, '2101.343')] [2023-07-07 16:09:20,807][566410] Updated weights for policy 0, policy_version 12880 (0.0005) [2023-07-07 16:09:24,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8806.4, 300 sec: 8775.2). Total num frames: 6627328. Throughput: 0: 8783.9. Samples: 6604696. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:09:24,506][565952] Avg episode reward: [(0, '2192.017')] [2023-07-07 16:09:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012944_6627328.pth... [2023-07-07 16:09:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012424_6361088.pth [2023-07-07 16:09:25,353][566410] Updated weights for policy 0, policy_version 12960 (0.0005) [2023-07-07 16:09:29,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8806.4, 300 sec: 8775.2). Total num frames: 6672384. Throughput: 0: 8825.5. Samples: 6659420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:09:29,506][565952] Avg episode reward: [(0, '2503.897')] [2023-07-07 16:09:29,872][566410] Updated weights for policy 0, policy_version 13040 (0.0005) [2023-07-07 16:09:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8761.3). Total num frames: 6713344. Throughput: 0: 8822.4. Samples: 6712872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:09:34,506][565952] Avg episode reward: [(0, '3246.805')] [2023-07-07 16:09:34,516][566410] Updated weights for policy 0, policy_version 13120 (0.0005) [2023-07-07 16:09:39,033][566410] Updated weights for policy 0, policy_version 13200 (0.0005) [2023-07-07 16:09:39,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8761.3). Total num frames: 6758400. Throughput: 0: 8862.0. Samples: 6739396. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-07 16:09:39,506][565952] Avg episode reward: [(0, '2724.433')] [2023-07-07 16:09:39,543][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013208_6762496.pth... [2023-07-07 16:09:39,545][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012680_6492160.pth [2023-07-07 16:09:43,847][566410] Updated weights for policy 0, policy_version 13280 (0.0006) [2023-07-07 16:09:44,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8761.3). Total num frames: 6803456. Throughput: 0: 8889.0. Samples: 6791176. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-07 16:09:44,506][565952] Avg episode reward: [(0, '2863.014')] [2023-07-07 16:09:48,679][566410] Updated weights for policy 0, policy_version 13360 (0.0005) [2023-07-07 16:09:49,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8747.4). Total num frames: 6844416. Throughput: 0: 8827.1. Samples: 6842940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:09:49,506][565952] Avg episode reward: [(0, '3086.559')] [2023-07-07 16:09:53,512][566410] Updated weights for policy 0, policy_version 13440 (0.0005) [2023-07-07 16:09:54,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8806.4, 300 sec: 8747.4). Total num frames: 6889472. Throughput: 0: 8818.5. Samples: 6868524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:09:54,506][565952] Avg episode reward: [(0, '3254.974')] [2023-07-07 16:09:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013456_6889472.pth... [2023-07-07 16:09:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012944_6627328.pth [2023-07-07 16:09:58,218][566410] Updated weights for policy 0, policy_version 13520 (0.0005) [2023-07-07 16:09:59,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8733.5). Total num frames: 6930432. Throughput: 0: 8774.1. Samples: 6919836. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:09:59,506][565952] Avg episode reward: [(0, '3759.233')] [2023-07-07 16:10:02,903][566410] Updated weights for policy 0, policy_version 13600 (0.0006) [2023-07-07 16:10:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8733.5). Total num frames: 6975488. Throughput: 0: 8757.0. Samples: 6971496. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:10:04,506][565952] Avg episode reward: [(0, '3998.551')] [2023-07-07 16:10:07,718][566410] Updated weights for policy 0, policy_version 13680 (0.0005) [2023-07-07 16:10:09,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8738.1, 300 sec: 8719.6). Total num frames: 7016448. Throughput: 0: 8733.3. Samples: 6997696. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:10:09,506][565952] Avg episode reward: [(0, '3705.733')] [2023-07-07 16:10:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013704_7016448.pth... [2023-07-07 16:10:09,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013208_6762496.pth [2023-07-07 16:10:12,644][566410] Updated weights for policy 0, policy_version 13760 (0.0006) [2023-07-07 16:10:14,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8669.9, 300 sec: 8705.7). Total num frames: 7057408. Throughput: 0: 8634.1. Samples: 7047956. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:10:14,506][565952] Avg episode reward: [(0, '3612.773')] [2023-07-07 16:10:17,551][566410] Updated weights for policy 0, policy_version 13840 (0.0005) [2023-07-07 16:10:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8705.7). Total num frames: 7102464. Throughput: 0: 8559.6. Samples: 7098056. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:10:19,507][565952] Avg episode reward: [(0, '3681.291')] [2023-07-07 16:10:22,213][566410] Updated weights for policy 0, policy_version 13920 (0.0005) [2023-07-07 16:10:24,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8669.9, 300 sec: 8719.6). Total num frames: 7147520. Throughput: 0: 8564.8. Samples: 7124812. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:10:24,506][565952] Avg episode reward: [(0, '2772.534')] [2023-07-07 16:10:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013960_7147520.pth... [2023-07-07 16:10:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013456_6889472.pth [2023-07-07 16:10:26,798][566410] Updated weights for policy 0, policy_version 14000 (0.0005) [2023-07-07 16:10:29,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8669.8, 300 sec: 8719.6). Total num frames: 7192576. Throughput: 0: 8620.5. Samples: 7179100. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:10:29,506][565952] Avg episode reward: [(0, '3679.862')] [2023-07-07 16:10:31,291][566410] Updated weights for policy 0, policy_version 14080 (0.0005) [2023-07-07 16:10:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8719.6). Total num frames: 7233536. Throughput: 0: 8643.7. Samples: 7231908. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:10:34,506][565952] Avg episode reward: [(0, '3836.946')] [2023-07-07 16:10:36,028][566410] Updated weights for policy 0, policy_version 14160 (0.0005) [2023-07-07 16:10:39,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8669.9, 300 sec: 8719.6). Total num frames: 7278592. Throughput: 0: 8652.9. Samples: 7257904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:10:39,506][565952] Avg episode reward: [(0, '3883.995')] [2023-07-07 16:10:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014216_7278592.pth... [2023-07-07 16:10:39,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013704_7016448.pth [2023-07-07 16:10:40,954][566410] Updated weights for policy 0, policy_version 14240 (0.0005) [2023-07-07 16:10:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8705.7). Total num frames: 7319552. Throughput: 0: 8614.2. Samples: 7307476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:10:44,506][565952] Avg episode reward: [(0, '4327.452')] [2023-07-07 16:10:44,507][566397] Saving new best policy, reward=4327.452! [2023-07-07 16:10:45,837][566410] Updated weights for policy 0, policy_version 14320 (0.0005) [2023-07-07 16:10:49,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8601.6, 300 sec: 8705.7). Total num frames: 7360512. Throughput: 0: 8554.0. Samples: 7356424. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:10:49,506][565952] Avg episode reward: [(0, '4102.191')] [2023-07-07 16:10:50,943][566410] Updated weights for policy 0, policy_version 14400 (0.0005) [2023-07-07 16:10:54,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 8691.8). Total num frames: 7401472. Throughput: 0: 8519.1. Samples: 7381056. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:10:54,506][565952] Avg episode reward: [(0, '4061.807')] [2023-07-07 16:10:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014456_7401472.pth... [2023-07-07 16:10:54,514][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013960_7147520.pth [2023-07-07 16:10:55,745][566410] Updated weights for policy 0, policy_version 14480 (0.0005) [2023-07-07 16:10:59,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 8691.8). Total num frames: 7442432. Throughput: 0: 8564.3. Samples: 7433352. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:10:59,506][565952] Avg episode reward: [(0, '3986.838')] [2023-07-07 16:11:00,506][566410] Updated weights for policy 0, policy_version 14560 (0.0005) [2023-07-07 16:11:04,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8533.3, 300 sec: 8691.9). Total num frames: 7487488. Throughput: 0: 8559.0. Samples: 7483212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:11:04,506][565952] Avg episode reward: [(0, '4353.953')] [2023-07-07 16:11:04,507][566397] Saving new best policy, reward=4353.953! [2023-07-07 16:11:05,445][566410] Updated weights for policy 0, policy_version 14640 (0.0005) [2023-07-07 16:11:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8691.8). Total num frames: 7528448. Throughput: 0: 8514.6. Samples: 7507968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:11:09,507][565952] Avg episode reward: [(0, '4108.351')] [2023-07-07 16:11:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014704_7528448.pth... [2023-07-07 16:11:09,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014216_7278592.pth [2023-07-07 16:11:10,387][566410] Updated weights for policy 0, policy_version 14720 (0.0005) [2023-07-07 16:11:14,506][565952] Fps is (10 sec: 8191.9, 60 sec: 8533.3, 300 sec: 8678.0). Total num frames: 7569408. Throughput: 0: 8417.8. Samples: 7557900. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:11:14,506][565952] Avg episode reward: [(0, '3650.464')] [2023-07-07 16:11:15,326][566410] Updated weights for policy 0, policy_version 14800 (0.0006) [2023-07-07 16:11:19,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8664.1). Total num frames: 7610368. Throughput: 0: 8339.2. Samples: 7607172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:11:19,506][565952] Avg episode reward: [(0, '3199.222')] [2023-07-07 16:11:20,247][566410] Updated weights for policy 0, policy_version 14880 (0.0005) [2023-07-07 16:11:24,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8664.1). Total num frames: 7651328. Throughput: 0: 8314.5. Samples: 7632056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:11:24,506][565952] Avg episode reward: [(0, '3680.271')] [2023-07-07 16:11:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014944_7651328.pth... [2023-07-07 16:11:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014456_7401472.pth [2023-07-07 16:11:25,217][566410] Updated weights for policy 0, policy_version 14960 (0.0005) [2023-07-07 16:11:29,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8650.2). Total num frames: 7692288. Throughput: 0: 8319.7. Samples: 7681864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:11:29,507][565952] Avg episode reward: [(0, '4078.216')] [2023-07-07 16:11:30,241][566410] Updated weights for policy 0, policy_version 15040 (0.0005) [2023-07-07 16:11:34,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8636.3). Total num frames: 7733248. Throughput: 0: 8284.4. Samples: 7729224. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:11:34,506][565952] Avg episode reward: [(0, '4079.658')] [2023-07-07 16:11:35,334][566410] Updated weights for policy 0, policy_version 15120 (0.0005) [2023-07-07 16:11:39,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8636.3). Total num frames: 7774208. Throughput: 0: 8305.3. Samples: 7754796. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:11:39,506][565952] Avg episode reward: [(0, '3925.221')] [2023-07-07 16:11:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015184_7774208.pth... [2023-07-07 16:11:39,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014704_7528448.pth [2023-07-07 16:11:40,367][566410] Updated weights for policy 0, policy_version 15200 (0.0005) [2023-07-07 16:11:44,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8608.5). Total num frames: 7815168. Throughput: 0: 8209.7. Samples: 7802788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:11:44,506][565952] Avg episode reward: [(0, '3787.058')] [2023-07-07 16:11:45,358][566410] Updated weights for policy 0, policy_version 15280 (0.0005) [2023-07-07 16:11:49,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8608.5). Total num frames: 7856128. Throughput: 0: 8220.4. Samples: 7853132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:11:49,506][565952] Avg episode reward: [(0, '3870.654')] [2023-07-07 16:11:50,358][566410] Updated weights for policy 0, policy_version 15360 (0.0005) [2023-07-07 16:11:54,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8594.7). Total num frames: 7897088. Throughput: 0: 8192.3. Samples: 7876620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:11:54,506][565952] Avg episode reward: [(0, '4384.497')] [2023-07-07 16:11:54,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015424_7897088.pth... [2023-07-07 16:11:54,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014944_7651328.pth [2023-07-07 16:11:54,511][566397] Saving new best policy, reward=4384.497! [2023-07-07 16:11:55,596][566410] Updated weights for policy 0, policy_version 15440 (0.0005) [2023-07-07 16:11:59,506][565952] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 8580.8). Total num frames: 7933952. Throughput: 0: 8121.5. Samples: 7923368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:11:59,506][565952] Avg episode reward: [(0, '4110.875')] [2023-07-07 16:12:00,900][566410] Updated weights for policy 0, policy_version 15520 (0.0005) [2023-07-07 16:12:04,506][565952] Fps is (10 sec: 7782.5, 60 sec: 8123.7, 300 sec: 8566.9). Total num frames: 7974912. Throughput: 0: 8102.8. Samples: 7971796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:12:04,506][565952] Avg episode reward: [(0, '3764.468')] [2023-07-07 16:12:05,789][566410] Updated weights for policy 0, policy_version 15600 (0.0005) [2023-07-07 16:12:09,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8123.7, 300 sec: 8553.0). Total num frames: 8015872. Throughput: 0: 8097.8. Samples: 7996456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:12:09,506][565952] Avg episode reward: [(0, '3759.785')] [2023-07-07 16:12:09,511][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015656_8015872.pth... [2023-07-07 16:12:09,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015184_7774208.pth [2023-07-07 16:12:10,715][566410] Updated weights for policy 0, policy_version 15680 (0.0005) [2023-07-07 16:12:14,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8123.7, 300 sec: 8539.1). Total num frames: 8056832. Throughput: 0: 8106.8. Samples: 8046672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:12:14,509][565952] Avg episode reward: [(0, '4248.236')] [2023-07-07 16:12:15,715][566410] Updated weights for policy 0, policy_version 15760 (0.0005) [2023-07-07 16:12:19,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8123.7, 300 sec: 8539.1). Total num frames: 8097792. Throughput: 0: 8134.3. Samples: 8095268. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:12:19,507][565952] Avg episode reward: [(0, '3950.772')] [2023-07-07 16:12:20,684][566410] Updated weights for policy 0, policy_version 15840 (0.0005) [2023-07-07 16:12:24,506][565952] Fps is (10 sec: 8191.9, 60 sec: 8123.7, 300 sec: 8525.2). Total num frames: 8138752. Throughput: 0: 8152.0. Samples: 8121636. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:12:24,507][565952] Avg episode reward: [(0, '4191.949')] [2023-07-07 16:12:24,511][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015896_8138752.pth... [2023-07-07 16:12:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015424_7897088.pth [2023-07-07 16:12:25,739][566410] Updated weights for policy 0, policy_version 15920 (0.0005) [2023-07-07 16:12:29,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8123.7, 300 sec: 8525.2). Total num frames: 8179712. Throughput: 0: 8132.9. Samples: 8168768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:12:29,506][565952] Avg episode reward: [(0, '4250.103')] [2023-07-07 16:12:30,723][566410] Updated weights for policy 0, policy_version 16000 (0.0005) [2023-07-07 16:12:34,506][565952] Fps is (10 sec: 8192.1, 60 sec: 8123.7, 300 sec: 8511.3). Total num frames: 8220672. Throughput: 0: 8112.5. Samples: 8218192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:12:34,506][565952] Avg episode reward: [(0, '4330.262')] [2023-07-07 16:12:35,709][566410] Updated weights for policy 0, policy_version 16080 (0.0005) [2023-07-07 16:12:39,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8192.0, 300 sec: 8525.2). Total num frames: 8265728. Throughput: 0: 8182.0. Samples: 8244808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:12:39,506][565952] Avg episode reward: [(0, '3962.685')] [2023-07-07 16:12:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016144_8265728.pth... [2023-07-07 16:12:39,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015656_8015872.pth [2023-07-07 16:12:40,403][566410] Updated weights for policy 0, policy_version 16160 (0.0005) [2023-07-07 16:12:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 8511.3). Total num frames: 8306688. Throughput: 0: 8258.3. Samples: 8294992. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:12:44,506][565952] Avg episode reward: [(0, '4219.302')] [2023-07-07 16:12:45,175][566410] Updated weights for policy 0, policy_version 16240 (0.0005) [2023-07-07 16:12:49,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8260.3, 300 sec: 8511.4). Total num frames: 8351744. Throughput: 0: 8353.7. Samples: 8347712. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:12:49,506][565952] Avg episode reward: [(0, '3964.130')] [2023-07-07 16:12:49,859][566410] Updated weights for policy 0, policy_version 16320 (0.0005) [2023-07-07 16:12:54,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 8497.5). Total num frames: 8392704. Throughput: 0: 8371.7. Samples: 8373184. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:12:54,506][565952] Avg episode reward: [(0, '3759.454')] [2023-07-07 16:12:54,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016392_8392704.pth... [2023-07-07 16:12:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015896_8138752.pth [2023-07-07 16:12:54,566][566410] Updated weights for policy 0, policy_version 16400 (0.0005) [2023-07-07 16:12:59,479][566410] Updated weights for policy 0, policy_version 16480 (0.0006) [2023-07-07 16:12:59,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8396.8, 300 sec: 8511.4). Total num frames: 8437760. Throughput: 0: 8400.8. Samples: 8424708. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:12:59,506][565952] Avg episode reward: [(0, '3938.747')] [2023-07-07 16:13:04,105][566410] Updated weights for policy 0, policy_version 16560 (0.0005) [2023-07-07 16:13:04,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8396.8, 300 sec: 8497.5). Total num frames: 8478720. Throughput: 0: 8498.5. Samples: 8477700. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:13:04,506][565952] Avg episode reward: [(0, '3964.731')] [2023-07-07 16:13:08,788][566410] Updated weights for policy 0, policy_version 16640 (0.0005) [2023-07-07 16:13:09,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8465.1, 300 sec: 8511.3). Total num frames: 8523776. Throughput: 0: 8509.3. Samples: 8504556. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:13:09,506][565952] Avg episode reward: [(0, '3866.175')] [2023-07-07 16:13:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016648_8523776.pth... [2023-07-07 16:13:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016144_8265728.pth [2023-07-07 16:13:13,388][566410] Updated weights for policy 0, policy_version 16720 (0.0005) [2023-07-07 16:13:14,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8533.3, 300 sec: 8525.2). Total num frames: 8568832. Throughput: 0: 8618.8. Samples: 8556616. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:13:14,506][565952] Avg episode reward: [(0, '3906.375')] [2023-07-07 16:13:18,074][566410] Updated weights for policy 0, policy_version 16800 (0.0005) [2023-07-07 16:13:19,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8601.6, 300 sec: 8525.2). Total num frames: 8613888. Throughput: 0: 8699.3. Samples: 8609660. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:13:19,507][565952] Avg episode reward: [(0, '4123.281')] [2023-07-07 16:13:22,951][566410] Updated weights for policy 0, policy_version 16880 (0.0005) [2023-07-07 16:13:24,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8511.3). Total num frames: 8654848. Throughput: 0: 8658.3. Samples: 8634432. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:13:24,506][565952] Avg episode reward: [(0, '4119.964')] [2023-07-07 16:13:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016904_8654848.pth... [2023-07-07 16:13:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016392_8392704.pth [2023-07-07 16:13:27,817][566410] Updated weights for policy 0, policy_version 16960 (0.0005) [2023-07-07 16:13:29,506][565952] Fps is (10 sec: 8192.1, 60 sec: 8601.6, 300 sec: 8511.4). Total num frames: 8695808. Throughput: 0: 8656.4. Samples: 8684528. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:13:29,506][565952] Avg episode reward: [(0, '3879.886')] [2023-07-07 16:13:32,652][566410] Updated weights for policy 0, policy_version 17040 (0.0005) [2023-07-07 16:13:34,506][565952] Fps is (10 sec: 8192.1, 60 sec: 8601.6, 300 sec: 8497.5). Total num frames: 8736768. Throughput: 0: 8623.0. Samples: 8735748. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:13:34,506][565952] Avg episode reward: [(0, '4108.386')] [2023-07-07 16:13:37,597][566410] Updated weights for policy 0, policy_version 17120 (0.0005) [2023-07-07 16:13:39,506][565952] Fps is (10 sec: 8191.9, 60 sec: 8533.3, 300 sec: 8483.6). Total num frames: 8777728. Throughput: 0: 8605.9. Samples: 8760448. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:13:39,506][565952] Avg episode reward: [(0, '4146.006')] [2023-07-07 16:13:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017144_8777728.pth... [2023-07-07 16:13:39,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016648_8523776.pth [2023-07-07 16:13:42,344][566410] Updated weights for policy 0, policy_version 17200 (0.0005) [2023-07-07 16:13:44,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8601.6, 300 sec: 8483.6). Total num frames: 8822784. Throughput: 0: 8589.1. Samples: 8811220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:13:44,506][565952] Avg episode reward: [(0, '3996.001')] [2023-07-07 16:13:47,027][566410] Updated weights for policy 0, policy_version 17280 (0.0005) [2023-07-07 16:13:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8601.6, 300 sec: 8497.5). Total num frames: 8867840. Throughput: 0: 8585.2. Samples: 8864036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:13:49,506][565952] Avg episode reward: [(0, '4150.831')] [2023-07-07 16:13:51,716][566410] Updated weights for policy 0, policy_version 17360 (0.0005) [2023-07-07 16:13:54,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8601.6, 300 sec: 8497.5). Total num frames: 8908800. Throughput: 0: 8583.0. Samples: 8890792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:13:54,506][565952] Avg episode reward: [(0, '3953.056')] [2023-07-07 16:13:54,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017400_8908800.pth... [2023-07-07 16:13:54,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016904_8654848.pth [2023-07-07 16:13:56,444][566410] Updated weights for policy 0, policy_version 17440 (0.0005) [2023-07-07 16:13:59,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8601.6, 300 sec: 8497.5). Total num frames: 8953856. Throughput: 0: 8556.1. Samples: 8941640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:13:59,506][565952] Avg episode reward: [(0, '3703.326')] [2023-07-07 16:14:01,137][566410] Updated weights for policy 0, policy_version 17520 (0.0005) [2023-07-07 16:14:04,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8669.8, 300 sec: 8497.5). Total num frames: 8998912. Throughput: 0: 8562.1. Samples: 8994956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:14:04,506][565952] Avg episode reward: [(0, '3250.960')] [2023-07-07 16:14:05,696][566410] Updated weights for policy 0, policy_version 17600 (0.0005) [2023-07-07 16:14:09,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8669.9, 300 sec: 8497.5). Total num frames: 9043968. Throughput: 0: 8625.7. Samples: 9022588. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:14:09,506][565952] Avg episode reward: [(0, '3921.349')] [2023-07-07 16:14:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017664_9043968.pth... [2023-07-07 16:14:09,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017144_8777728.pth [2023-07-07 16:14:10,219][566410] Updated weights for policy 0, policy_version 17680 (0.0005) [2023-07-07 16:14:14,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8669.9, 300 sec: 8497.5). Total num frames: 9089024. Throughput: 0: 8717.1. Samples: 9076800. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:14:14,506][565952] Avg episode reward: [(0, '3960.260')] [2023-07-07 16:14:14,859][566410] Updated weights for policy 0, policy_version 17760 (0.0005) [2023-07-07 16:14:19,453][566410] Updated weights for policy 0, policy_version 17840 (0.0005) [2023-07-07 16:14:19,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8669.9, 300 sec: 8497.5). Total num frames: 9134080. Throughput: 0: 8760.5. Samples: 9129972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:14:19,506][565952] Avg episode reward: [(0, '4287.624')] [2023-07-07 16:14:24,049][566410] Updated weights for policy 0, policy_version 17920 (0.0005) [2023-07-07 16:14:24,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8738.1, 300 sec: 8497.5). Total num frames: 9179136. Throughput: 0: 8790.1. Samples: 9156004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:14:24,506][565952] Avg episode reward: [(0, '4286.626')] [2023-07-07 16:14:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017928_9179136.pth... [2023-07-07 16:14:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017400_8908800.pth [2023-07-07 16:14:28,703][566410] Updated weights for policy 0, policy_version 18000 (0.0005) [2023-07-07 16:14:29,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8497.5). Total num frames: 9220096. Throughput: 0: 8838.9. Samples: 9208972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:14:29,506][565952] Avg episode reward: [(0, '4255.258')] [2023-07-07 16:14:33,311][566410] Updated weights for policy 0, policy_version 18080 (0.0005) [2023-07-07 16:14:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8497.5). Total num frames: 9265152. Throughput: 0: 8841.9. Samples: 9261920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:14:34,506][565952] Avg episode reward: [(0, '3987.568')] [2023-07-07 16:14:38,023][566410] Updated weights for policy 0, policy_version 18160 (0.0005) [2023-07-07 16:14:39,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8874.7, 300 sec: 8497.5). Total num frames: 9310208. Throughput: 0: 8825.6. Samples: 9287944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:14:39,506][565952] Avg episode reward: [(0, '4259.601')] [2023-07-07 16:14:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018184_9310208.pth... [2023-07-07 16:14:39,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017664_9043968.pth [2023-07-07 16:14:42,744][566410] Updated weights for policy 0, policy_version 18240 (0.0005) [2023-07-07 16:14:44,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8806.4, 300 sec: 8497.5). Total num frames: 9351168. Throughput: 0: 8862.1. Samples: 9340436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:14:44,506][565952] Avg episode reward: [(0, '3973.788')] [2023-07-07 16:14:47,547][566410] Updated weights for policy 0, policy_version 18320 (0.0005) [2023-07-07 16:14:49,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8806.4, 300 sec: 8497.5). Total num frames: 9396224. Throughput: 0: 8826.0. Samples: 9392124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:14:49,506][565952] Avg episode reward: [(0, '3987.272')] [2023-07-07 16:14:52,216][566410] Updated weights for policy 0, policy_version 18400 (0.0005) [2023-07-07 16:14:54,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8874.7, 300 sec: 8511.3). Total num frames: 9441280. Throughput: 0: 8797.4. Samples: 9418472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:14:54,506][565952] Avg episode reward: [(0, '3411.618')] [2023-07-07 16:14:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018440_9441280.pth... [2023-07-07 16:14:54,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017928_9179136.pth [2023-07-07 16:14:56,892][566410] Updated weights for policy 0, policy_version 18480 (0.0005) [2023-07-07 16:14:59,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8497.5). Total num frames: 9482240. Throughput: 0: 8736.9. Samples: 9469960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:14:59,506][565952] Avg episode reward: [(0, '3574.593')] [2023-07-07 16:15:01,819][566410] Updated weights for policy 0, policy_version 18560 (0.0005) [2023-07-07 16:15:04,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8738.1, 300 sec: 8497.5). Total num frames: 9523200. Throughput: 0: 8668.1. Samples: 9520036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:15:04,506][565952] Avg episode reward: [(0, '4077.757')] [2023-07-07 16:15:06,670][566410] Updated weights for policy 0, policy_version 18640 (0.0005) [2023-07-07 16:15:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8511.3). Total num frames: 9568256. Throughput: 0: 8683.4. Samples: 9546756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:15:09,506][565952] Avg episode reward: [(0, '3659.460')] [2023-07-07 16:15:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018688_9568256.pth... [2023-07-07 16:15:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018184_9310208.pth [2023-07-07 16:15:11,233][566410] Updated weights for policy 0, policy_version 18720 (0.0006) [2023-07-07 16:15:14,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8497.5). Total num frames: 9609216. Throughput: 0: 8706.3. Samples: 9600756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:15:14,506][565952] Avg episode reward: [(0, '3064.589')] [2023-07-07 16:15:15,879][566410] Updated weights for policy 0, policy_version 18800 (0.0006) [2023-07-07 16:15:19,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8669.9, 300 sec: 8497.5). Total num frames: 9654272. Throughput: 0: 8686.0. Samples: 9652788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:15:19,506][565952] Avg episode reward: [(0, '2776.976')] [2023-07-07 16:15:20,537][566410] Updated weights for policy 0, policy_version 18880 (0.0005) [2023-07-07 16:15:24,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8669.9, 300 sec: 8497.5). Total num frames: 9699328. Throughput: 0: 8681.7. Samples: 9678620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:15:24,506][565952] Avg episode reward: [(0, '4272.388')] [2023-07-07 16:15:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018944_9699328.pth... [2023-07-07 16:15:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018440_9441280.pth [2023-07-07 16:15:25,359][566410] Updated weights for policy 0, policy_version 18960 (0.0005) [2023-07-07 16:15:29,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8738.1, 300 sec: 8511.3). Total num frames: 9744384. Throughput: 0: 8703.5. Samples: 9732096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:15:29,506][565952] Avg episode reward: [(0, '3949.614')] [2023-07-07 16:15:29,747][566410] Updated weights for policy 0, policy_version 19040 (0.0005) [2023-07-07 16:15:34,266][566410] Updated weights for policy 0, policy_version 19120 (0.0005) [2023-07-07 16:15:34,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8511.3). Total num frames: 9789440. Throughput: 0: 8751.9. Samples: 9785960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:15:34,506][565952] Avg episode reward: [(0, '4297.591')] [2023-07-07 16:15:39,020][566410] Updated weights for policy 0, policy_version 19200 (0.0006) [2023-07-07 16:15:39,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8525.2). Total num frames: 9834496. Throughput: 0: 8780.6. Samples: 9813600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:15:39,507][565952] Avg episode reward: [(0, '3879.715')] [2023-07-07 16:15:39,511][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019208_9834496.pth... [2023-07-07 16:15:39,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018688_9568256.pth [2023-07-07 16:15:43,543][566410] Updated weights for policy 0, policy_version 19280 (0.0005) [2023-07-07 16:15:44,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8806.4, 300 sec: 8539.1). Total num frames: 9879552. Throughput: 0: 8819.3. Samples: 9866828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:15:44,507][565952] Avg episode reward: [(0, '3810.656')] [2023-07-07 16:15:48,107][566410] Updated weights for policy 0, policy_version 19360 (0.0005) [2023-07-07 16:15:49,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8806.4, 300 sec: 8553.0). Total num frames: 9924608. Throughput: 0: 8897.7. Samples: 9920432. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:15:49,506][565952] Avg episode reward: [(0, '3965.810')] [2023-07-07 16:15:52,592][566410] Updated weights for policy 0, policy_version 19440 (0.0005) [2023-07-07 16:15:54,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8566.9). Total num frames: 9969664. Throughput: 0: 8912.5. Samples: 9947820. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:15:54,506][565952] Avg episode reward: [(0, '3891.647')] [2023-07-07 16:15:54,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019472_9969664.pth... [2023-07-07 16:15:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018944_9699328.pth [2023-07-07 16:15:57,115][566410] Updated weights for policy 0, policy_version 19520 (0.0005) [2023-07-07 16:15:59,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8553.0). Total num frames: 10010624. Throughput: 0: 8920.0. Samples: 10002156. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:15:59,506][565952] Avg episode reward: [(0, '3935.879')] [2023-07-07 16:16:01,876][566410] Updated weights for policy 0, policy_version 19600 (0.0005) [2023-07-07 16:16:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8874.7, 300 sec: 8566.9). Total num frames: 10055680. Throughput: 0: 8910.4. Samples: 10053756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:16:04,506][565952] Avg episode reward: [(0, '4236.297')] [2023-07-07 16:16:06,494][566410] Updated weights for policy 0, policy_version 19680 (0.0005) [2023-07-07 16:16:09,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8874.7, 300 sec: 8580.8). Total num frames: 10100736. Throughput: 0: 8922.7. Samples: 10080140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:16:09,506][565952] Avg episode reward: [(0, '4168.355')] [2023-07-07 16:16:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019728_10100736.pth... [2023-07-07 16:16:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019208_9834496.pth [2023-07-07 16:16:11,210][566410] Updated weights for policy 0, policy_version 19760 (0.0005) [2023-07-07 16:16:14,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8942.9, 300 sec: 8594.7). Total num frames: 10145792. Throughput: 0: 8902.8. Samples: 10132720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:16:14,506][565952] Avg episode reward: [(0, '4111.500')] [2023-07-07 16:16:15,719][566410] Updated weights for policy 0, policy_version 19840 (0.0005) [2023-07-07 16:16:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8874.6, 300 sec: 8594.7). Total num frames: 10186752. Throughput: 0: 8892.6. Samples: 10186128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:16:19,507][565952] Avg episode reward: [(0, '4323.436')] [2023-07-07 16:16:20,447][566410] Updated weights for policy 0, policy_version 19920 (0.0005) [2023-07-07 16:16:24,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8874.7, 300 sec: 8608.5). Total num frames: 10231808. Throughput: 0: 8838.0. Samples: 10211312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:16:24,506][565952] Avg episode reward: [(0, '4227.907')] [2023-07-07 16:16:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019984_10231808.pth... [2023-07-07 16:16:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019472_9969664.pth [2023-07-07 16:16:25,341][566410] Updated weights for policy 0, policy_version 20000 (0.0005) [2023-07-07 16:16:29,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8806.4, 300 sec: 8608.5). Total num frames: 10272768. Throughput: 0: 8817.5. Samples: 10263616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:16:29,506][565952] Avg episode reward: [(0, '4044.834')] [2023-07-07 16:16:30,063][566410] Updated weights for policy 0, policy_version 20080 (0.0005) [2023-07-07 16:16:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8622.4). Total num frames: 10317824. Throughput: 0: 8740.1. Samples: 10313736. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:16:34,506][565952] Avg episode reward: [(0, '4365.394')] [2023-07-07 16:16:34,885][566410] Updated weights for policy 0, policy_version 20160 (0.0005) [2023-07-07 16:16:39,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8738.1, 300 sec: 8622.4). Total num frames: 10358784. Throughput: 0: 8707.9. Samples: 10339676. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:16:39,506][565952] Avg episode reward: [(0, '3242.514')] [2023-07-07 16:16:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000020232_10358784.pth... [2023-07-07 16:16:39,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019728_10100736.pth [2023-07-07 16:16:39,643][566410] Updated weights for policy 0, policy_version 20240 (0.0005) [2023-07-07 16:16:44,034][566410] Updated weights for policy 0, policy_version 20320 (0.0005) [2023-07-07 16:16:44,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8738.2, 300 sec: 8636.3). Total num frames: 10403840. Throughput: 0: 8720.1. Samples: 10394560. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:16:44,506][565952] Avg episode reward: [(0, '3682.583')] [2023-07-07 16:16:48,584][566410] Updated weights for policy 0, policy_version 20400 (0.0005) [2023-07-07 16:16:49,506][565952] Fps is (10 sec: 9420.9, 60 sec: 8806.4, 300 sec: 8664.1). Total num frames: 10452992. Throughput: 0: 8777.3. Samples: 10448736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:16:49,506][565952] Avg episode reward: [(0, '3967.586')] [2023-07-07 16:16:53,203][566410] Updated weights for policy 0, policy_version 20480 (0.0005) [2023-07-07 16:16:54,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8738.1, 300 sec: 8678.0). Total num frames: 10493952. Throughput: 0: 8757.0. Samples: 10474204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:16:54,506][565952] Avg episode reward: [(0, '4326.514')] [2023-07-07 16:16:54,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000020496_10493952.pth... [2023-07-07 16:16:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019984_10231808.pth [2023-07-07 16:16:57,917][566410] Updated weights for policy 0, policy_version 20560 (0.0005) [2023-07-07 16:16:59,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8691.9). Total num frames: 10539008. Throughput: 0: 8757.0. Samples: 10526784. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:16:59,506][565952] Avg episode reward: [(0, '4153.367')] [2023-07-07 16:17:02,563][566410] Updated weights for policy 0, policy_version 20640 (0.0006) [2023-07-07 16:17:04,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8705.7). Total num frames: 10584064. Throughput: 0: 8751.1. Samples: 10579928. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:17:04,506][565952] Avg episode reward: [(0, '3867.560')] [2023-07-07 16:17:07,332][566410] Updated weights for policy 0, policy_version 20720 (0.0005) [2023-07-07 16:17:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8705.7). Total num frames: 10625024. Throughput: 0: 8739.9. Samples: 10604608. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:17:09,506][565952] Avg episode reward: [(0, '3788.807')] [2023-07-07 16:17:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000020752_10625024.pth... [2023-07-07 16:17:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000020232_10358784.pth [2023-07-07 16:17:12,129][566410] Updated weights for policy 0, policy_version 20800 (0.0006) [2023-07-07 16:17:14,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8669.9, 300 sec: 8705.7). Total num frames: 10665984. Throughput: 0: 8742.7. Samples: 10657040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:17:14,506][565952] Avg episode reward: [(0, '4054.129')] [2023-07-07 16:17:17,038][566410] Updated weights for policy 0, policy_version 20880 (0.0005) [2023-07-07 16:17:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8719.6). Total num frames: 10711040. Throughput: 0: 8742.0. Samples: 10707124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:17:19,506][565952] Avg episode reward: [(0, '3731.034')] [2023-07-07 16:17:21,672][566410] Updated weights for policy 0, policy_version 20960 (0.0005) [2023-07-07 16:17:24,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8733.5). Total num frames: 10756096. Throughput: 0: 8774.5. Samples: 10734528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:17:24,507][565952] Avg episode reward: [(0, '3504.045')] [2023-07-07 16:17:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000021008_10756096.pth... [2023-07-07 16:17:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000020496_10493952.pth [2023-07-07 16:17:26,203][566410] Updated weights for policy 0, policy_version 21040 (0.0005) [2023-07-07 16:17:29,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8733.5). Total num frames: 10797056. Throughput: 0: 8735.6. Samples: 10787664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:17:29,506][565952] Avg episode reward: [(0, '2809.922')] [2023-07-07 16:17:30,928][566410] Updated weights for policy 0, policy_version 21120 (0.0005) [2023-07-07 16:17:34,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8738.1, 300 sec: 8733.5). Total num frames: 10842112. Throughput: 0: 8689.6. Samples: 10839768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:17:34,506][565952] Avg episode reward: [(0, '2849.071')] [2023-07-07 16:17:35,746][566410] Updated weights for policy 0, policy_version 21200 (0.0005) [2023-07-07 16:17:39,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8733.5). Total num frames: 10883072. Throughput: 0: 8668.5. Samples: 10864284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:17:39,506][565952] Avg episode reward: [(0, '2694.401')] [2023-07-07 16:17:39,533][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000021264_10887168.pth... [2023-07-07 16:17:39,535][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000020752_10625024.pth [2023-07-07 16:17:40,543][566410] Updated weights for policy 0, policy_version 21280 (0.0005) [2023-07-07 16:17:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8733.5). Total num frames: 10928128. Throughput: 0: 8696.6. Samples: 10918132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:17:44,506][565952] Avg episode reward: [(0, '2306.106')] [2023-07-07 16:17:45,081][566410] Updated weights for policy 0, policy_version 21360 (0.0005) [2023-07-07 16:17:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8669.9, 300 sec: 8747.4). Total num frames: 10973184. Throughput: 0: 8649.6. Samples: 10969160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:17:49,506][565952] Avg episode reward: [(0, '2359.209')] [2023-07-07 16:17:49,889][566410] Updated weights for policy 0, policy_version 21440 (0.0005) [2023-07-07 16:17:54,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8669.9, 300 sec: 8733.5). Total num frames: 11014144. Throughput: 0: 8685.0. Samples: 10995432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:17:54,506][565952] Avg episode reward: [(0, '2845.277')] [2023-07-07 16:17:54,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000021512_11014144.pth... [2023-07-07 16:17:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000021008_10756096.pth [2023-07-07 16:17:54,682][566410] Updated weights for policy 0, policy_version 21520 (0.0005) [2023-07-07 16:17:59,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8601.6, 300 sec: 8733.5). Total num frames: 11055104. Throughput: 0: 8613.6. Samples: 11044652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:17:59,506][565952] Avg episode reward: [(0, '3523.921')] [2023-07-07 16:17:59,842][566410] Updated weights for policy 0, policy_version 21600 (0.0005) [2023-07-07 16:18:04,506][565952] Fps is (10 sec: 8192.1, 60 sec: 8533.3, 300 sec: 8719.6). Total num frames: 11096064. Throughput: 0: 8611.6. Samples: 11094644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:18:04,506][565952] Avg episode reward: [(0, '2928.849')] [2023-07-07 16:18:04,674][566410] Updated weights for policy 0, policy_version 21680 (0.0005) [2023-07-07 16:18:09,283][566410] Updated weights for policy 0, policy_version 21760 (0.0005) [2023-07-07 16:18:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8719.6). Total num frames: 11141120. Throughput: 0: 8574.5. Samples: 11120380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:18:09,506][565952] Avg episode reward: [(0, '3937.177')] [2023-07-07 16:18:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000021760_11141120.pth... [2023-07-07 16:18:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000021264_10887168.pth [2023-07-07 16:18:13,933][566410] Updated weights for policy 0, policy_version 21840 (0.0005) [2023-07-07 16:18:14,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8669.9, 300 sec: 8719.6). Total num frames: 11186176. Throughput: 0: 8581.3. Samples: 11173824. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:18:14,506][565952] Avg episode reward: [(0, '3921.646')] [2023-07-07 16:18:18,607][566410] Updated weights for policy 0, policy_version 21920 (0.0005) [2023-07-07 16:18:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8719.6). Total num frames: 11227136. Throughput: 0: 8589.5. Samples: 11226296. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:18:19,506][565952] Avg episode reward: [(0, '3792.803')] [2023-07-07 16:18:23,543][566410] Updated weights for policy 0, policy_version 22000 (0.0005) [2023-07-07 16:18:24,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8733.5). Total num frames: 11272192. Throughput: 0: 8578.1. Samples: 11250300. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:18:24,506][565952] Avg episode reward: [(0, '3987.455')] [2023-07-07 16:18:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000022016_11272192.pth... [2023-07-07 16:18:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000021512_11014144.pth [2023-07-07 16:18:28,165][566410] Updated weights for policy 0, policy_version 22080 (0.0005) [2023-07-07 16:18:29,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8733.5). Total num frames: 11313152. Throughput: 0: 8550.8. Samples: 11302916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:18:29,506][565952] Avg episode reward: [(0, '4452.111')] [2023-07-07 16:18:29,507][566397] Saving new best policy, reward=4452.111! [2023-07-07 16:18:32,973][566410] Updated weights for policy 0, policy_version 22160 (0.0005) [2023-07-07 16:18:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8747.4). Total num frames: 11358208. Throughput: 0: 8556.1. Samples: 11354184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:18:34,506][565952] Avg episode reward: [(0, '4154.893')] [2023-07-07 16:18:37,800][566410] Updated weights for policy 0, policy_version 22240 (0.0005) [2023-07-07 16:18:39,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8733.5). Total num frames: 11399168. Throughput: 0: 8518.9. Samples: 11378780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:18:39,506][565952] Avg episode reward: [(0, '3923.139')] [2023-07-07 16:18:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000022264_11399168.pth... [2023-07-07 16:18:39,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000021760_11141120.pth [2023-07-07 16:18:42,463][566410] Updated weights for policy 0, policy_version 22320 (0.0005) [2023-07-07 16:18:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8733.5). Total num frames: 11444224. Throughput: 0: 8606.6. Samples: 11431948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:18:44,506][565952] Avg episode reward: [(0, '4185.248')] [2023-07-07 16:18:46,972][566410] Updated weights for policy 0, policy_version 22400 (0.0005) [2023-07-07 16:18:49,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8601.6, 300 sec: 8747.4). Total num frames: 11489280. Throughput: 0: 8743.4. Samples: 11488096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:18:49,506][565952] Avg episode reward: [(0, '3824.516')] [2023-07-07 16:18:51,438][566410] Updated weights for policy 0, policy_version 22480 (0.0005) [2023-07-07 16:18:54,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8669.9, 300 sec: 8747.4). Total num frames: 11534336. Throughput: 0: 8745.4. Samples: 11513920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:18:54,506][565952] Avg episode reward: [(0, '2995.157')] [2023-07-07 16:18:54,508][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000022528_11534336.pth... [2023-07-07 16:18:54,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000022016_11272192.pth [2023-07-07 16:18:56,213][566410] Updated weights for policy 0, policy_version 22560 (0.0005) [2023-07-07 16:18:59,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8669.9, 300 sec: 8733.5). Total num frames: 11575296. Throughput: 0: 8714.1. Samples: 11565960. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:18:59,506][565952] Avg episode reward: [(0, '3557.632')] [2023-07-07 16:19:01,111][566410] Updated weights for policy 0, policy_version 22640 (0.0006) [2023-07-07 16:19:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8733.5). Total num frames: 11620352. Throughput: 0: 8665.3. Samples: 11616236. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:19:04,506][565952] Avg episode reward: [(0, '3273.707')] [2023-07-07 16:19:05,848][566410] Updated weights for policy 0, policy_version 22720 (0.0005) [2023-07-07 16:19:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8719.6). Total num frames: 11661312. Throughput: 0: 8726.2. Samples: 11642980. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:19:09,506][565952] Avg episode reward: [(0, '3097.254')] [2023-07-07 16:19:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000022776_11661312.pth... [2023-07-07 16:19:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000022264_11399168.pth [2023-07-07 16:19:10,553][566410] Updated weights for policy 0, policy_version 22800 (0.0005) [2023-07-07 16:19:14,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8719.6). Total num frames: 11706368. Throughput: 0: 8696.9. Samples: 11694276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:19:14,506][565952] Avg episode reward: [(0, '3785.965')] [2023-07-07 16:19:15,290][566410] Updated weights for policy 0, policy_version 22880 (0.0005) [2023-07-07 16:19:19,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8738.2, 300 sec: 8719.6). Total num frames: 11751424. Throughput: 0: 8762.4. Samples: 11748492. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:19:19,506][565952] Avg episode reward: [(0, '4054.551')] [2023-07-07 16:19:19,668][566410] Updated weights for policy 0, policy_version 22960 (0.0005) [2023-07-07 16:19:24,193][566410] Updated weights for policy 0, policy_version 23040 (0.0006) [2023-07-07 16:19:24,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8738.1, 300 sec: 8733.5). Total num frames: 11796480. Throughput: 0: 8824.4. Samples: 11775876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:19:24,506][565952] Avg episode reward: [(0, '4168.525')] [2023-07-07 16:19:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000023040_11796480.pth... [2023-07-07 16:19:24,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000022528_11534336.pth [2023-07-07 16:19:28,905][566410] Updated weights for policy 0, policy_version 23120 (0.0005) [2023-07-07 16:19:29,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8733.5). Total num frames: 11841536. Throughput: 0: 8828.9. Samples: 11829248. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-07 16:19:29,506][565952] Avg episode reward: [(0, '4083.690')] [2023-07-07 16:19:33,608][566410] Updated weights for policy 0, policy_version 23200 (0.0005) [2023-07-07 16:19:34,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8733.5). Total num frames: 11886592. Throughput: 0: 8747.1. Samples: 11881716. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-07 16:19:34,506][565952] Avg episode reward: [(0, '4235.729')] [2023-07-07 16:19:38,193][566410] Updated weights for policy 0, policy_version 23280 (0.0005) [2023-07-07 16:19:39,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8806.4, 300 sec: 8733.5). Total num frames: 11927552. Throughput: 0: 8750.0. Samples: 11907672. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-07 16:19:39,506][565952] Avg episode reward: [(0, '4254.103')] [2023-07-07 16:19:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000023296_11927552.pth... [2023-07-07 16:19:39,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000022776_11661312.pth [2023-07-07 16:19:42,865][566410] Updated weights for policy 0, policy_version 23360 (0.0005) [2023-07-07 16:19:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8733.5). Total num frames: 11972608. Throughput: 0: 8771.7. Samples: 11960688. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-07 16:19:44,506][565952] Avg episode reward: [(0, '4267.292')] [2023-07-07 16:19:47,330][566410] Updated weights for policy 0, policy_version 23440 (0.0005) [2023-07-07 16:19:49,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8806.4, 300 sec: 8733.5). Total num frames: 12017664. Throughput: 0: 8880.3. Samples: 12015848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:19:49,506][565952] Avg episode reward: [(0, '4194.086')] [2023-07-07 16:19:52,014][566410] Updated weights for policy 0, policy_version 23520 (0.0005) [2023-07-07 16:19:54,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8806.4, 300 sec: 8747.4). Total num frames: 12062720. Throughput: 0: 8869.1. Samples: 12042088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:19:54,507][565952] Avg episode reward: [(0, '4270.038')] [2023-07-07 16:19:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000023560_12062720.pth... [2023-07-07 16:19:54,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000023040_11796480.pth [2023-07-07 16:19:56,761][566410] Updated weights for policy 0, policy_version 23600 (0.0006) [2023-07-07 16:19:59,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8747.4). Total num frames: 12103680. Throughput: 0: 8870.8. Samples: 12093460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:19:59,506][565952] Avg episode reward: [(0, '4116.932')] [2023-07-07 16:20:01,674][566410] Updated weights for policy 0, policy_version 23680 (0.0005) [2023-07-07 16:20:04,506][565952] Fps is (10 sec: 8192.1, 60 sec: 8738.1, 300 sec: 8733.5). Total num frames: 12144640. Throughput: 0: 8788.6. Samples: 12143980. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:20:04,506][565952] Avg episode reward: [(0, '4088.014')] [2023-07-07 16:20:06,377][566410] Updated weights for policy 0, policy_version 23760 (0.0005) [2023-07-07 16:20:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8747.4). Total num frames: 12189696. Throughput: 0: 8747.3. Samples: 12169504. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:20:09,506][565952] Avg episode reward: [(0, '3783.468')] [2023-07-07 16:20:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000023808_12189696.pth... [2023-07-07 16:20:09,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000023296_11927552.pth [2023-07-07 16:20:11,225][566410] Updated weights for policy 0, policy_version 23840 (0.0005) [2023-07-07 16:20:14,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8738.2, 300 sec: 8733.5). Total num frames: 12230656. Throughput: 0: 8727.9. Samples: 12222004. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:20:14,506][565952] Avg episode reward: [(0, '4186.488')] [2023-07-07 16:20:15,946][566410] Updated weights for policy 0, policy_version 23920 (0.0005) [2023-07-07 16:20:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8733.5). Total num frames: 12275712. Throughput: 0: 8688.3. Samples: 12272688. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:20:19,506][565952] Avg episode reward: [(0, '4058.576')] [2023-07-07 16:20:20,745][566410] Updated weights for policy 0, policy_version 24000 (0.0005) [2023-07-07 16:20:24,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8719.6). Total num frames: 12316672. Throughput: 0: 8670.8. Samples: 12297856. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:20:24,506][565952] Avg episode reward: [(0, '4134.981')] [2023-07-07 16:20:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000024056_12316672.pth... [2023-07-07 16:20:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000023560_12062720.pth [2023-07-07 16:20:25,708][566410] Updated weights for policy 0, policy_version 24080 (0.0005) [2023-07-07 16:20:29,506][565952] Fps is (10 sec: 8192.1, 60 sec: 8601.6, 300 sec: 8705.7). Total num frames: 12357632. Throughput: 0: 8615.7. Samples: 12348392. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:20:29,506][565952] Avg episode reward: [(0, '4398.065')] [2023-07-07 16:20:30,544][566410] Updated weights for policy 0, policy_version 24160 (0.0005) [2023-07-07 16:20:34,506][565952] Fps is (10 sec: 8191.9, 60 sec: 8533.3, 300 sec: 8691.9). Total num frames: 12398592. Throughput: 0: 8469.1. Samples: 12396960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:20:34,507][565952] Avg episode reward: [(0, '3821.802')] [2023-07-07 16:20:35,834][566410] Updated weights for policy 0, policy_version 24240 (0.0005) [2023-07-07 16:20:39,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 8678.0). Total num frames: 12439552. Throughput: 0: 8382.2. Samples: 12419288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:20:39,506][565952] Avg episode reward: [(0, '4118.840')] [2023-07-07 16:20:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000024296_12439552.pth... [2023-07-07 16:20:39,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000023808_12189696.pth [2023-07-07 16:20:40,826][566410] Updated weights for policy 0, policy_version 24320 (0.0006) [2023-07-07 16:20:44,506][565952] Fps is (10 sec: 8192.1, 60 sec: 8465.1, 300 sec: 8664.1). Total num frames: 12480512. Throughput: 0: 8362.6. Samples: 12469776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:20:44,506][565952] Avg episode reward: [(0, '4051.771')] [2023-07-07 16:20:45,733][566410] Updated weights for policy 0, policy_version 24400 (0.0005) [2023-07-07 16:20:49,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8650.2). Total num frames: 12521472. Throughput: 0: 8347.2. Samples: 12519604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:20:49,506][565952] Avg episode reward: [(0, '4110.817')] [2023-07-07 16:20:50,583][566410] Updated weights for policy 0, policy_version 24480 (0.0005) [2023-07-07 16:20:54,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8396.8, 300 sec: 8664.1). Total num frames: 12566528. Throughput: 0: 8367.3. Samples: 12546032. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:20:54,507][565952] Avg episode reward: [(0, '2685.002')] [2023-07-07 16:20:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000024544_12566528.pth... [2023-07-07 16:20:54,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000024056_12316672.pth [2023-07-07 16:20:55,291][566410] Updated weights for policy 0, policy_version 24560 (0.0005) [2023-07-07 16:20:59,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8650.2). Total num frames: 12607488. Throughput: 0: 8316.9. Samples: 12596264. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:20:59,507][565952] Avg episode reward: [(0, '3302.350')] [2023-07-07 16:21:00,253][566410] Updated weights for policy 0, policy_version 24640 (0.0005) [2023-07-07 16:21:04,506][565952] Fps is (10 sec: 8192.1, 60 sec: 8396.8, 300 sec: 8636.3). Total num frames: 12648448. Throughput: 0: 8285.8. Samples: 12645548. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:21:04,506][565952] Avg episode reward: [(0, '3935.907')] [2023-07-07 16:21:05,291][566410] Updated weights for policy 0, policy_version 24720 (0.0005) [2023-07-07 16:21:09,506][565952] Fps is (10 sec: 8192.1, 60 sec: 8328.5, 300 sec: 8622.4). Total num frames: 12689408. Throughput: 0: 8291.0. Samples: 12670952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:21:09,506][565952] Avg episode reward: [(0, '3673.029')] [2023-07-07 16:21:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000024784_12689408.pth... [2023-07-07 16:21:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000024296_12439552.pth [2023-07-07 16:21:10,031][566410] Updated weights for policy 0, policy_version 24800 (0.0005) [2023-07-07 16:21:14,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8636.3). Total num frames: 12734464. Throughput: 0: 8304.2. Samples: 12722080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:21:14,506][565952] Avg episode reward: [(0, '3484.219')] [2023-07-07 16:21:14,784][566410] Updated weights for policy 0, policy_version 24880 (0.0005) [2023-07-07 16:21:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8328.5, 300 sec: 8622.4). Total num frames: 12775424. Throughput: 0: 8405.4. Samples: 12775204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:21:19,506][565952] Avg episode reward: [(0, '4335.564')] [2023-07-07 16:21:19,547][566410] Updated weights for policy 0, policy_version 24960 (0.0005) [2023-07-07 16:21:24,183][566410] Updated weights for policy 0, policy_version 25040 (0.0005) [2023-07-07 16:21:24,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8636.3). Total num frames: 12820480. Throughput: 0: 8513.9. Samples: 12802412. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:21:24,506][565952] Avg episode reward: [(0, '4438.016')] [2023-07-07 16:21:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000025040_12820480.pth... [2023-07-07 16:21:24,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000024544_12566528.pth [2023-07-07 16:21:28,825][566410] Updated weights for policy 0, policy_version 25120 (0.0005) [2023-07-07 16:21:29,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8465.1, 300 sec: 8636.3). Total num frames: 12865536. Throughput: 0: 8521.8. Samples: 12853256. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:21:29,507][565952] Avg episode reward: [(0, '3981.926')] [2023-07-07 16:21:33,603][566410] Updated weights for policy 0, policy_version 25200 (0.0005) [2023-07-07 16:21:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8636.3). Total num frames: 12906496. Throughput: 0: 8590.0. Samples: 12906156. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:21:34,506][565952] Avg episode reward: [(0, '3787.448')] [2023-07-07 16:21:38,335][566410] Updated weights for policy 0, policy_version 25280 (0.0006) [2023-07-07 16:21:39,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 12951552. Throughput: 0: 8559.1. Samples: 12931192. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:21:39,507][565952] Avg episode reward: [(0, '4068.448')] [2023-07-07 16:21:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000025296_12951552.pth... [2023-07-07 16:21:39,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000024784_12689408.pth [2023-07-07 16:21:43,071][566410] Updated weights for policy 0, policy_version 25360 (0.0005) [2023-07-07 16:21:44,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8533.3, 300 sec: 8608.5). Total num frames: 12992512. Throughput: 0: 8607.2. Samples: 12983588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:21:44,506][565952] Avg episode reward: [(0, '4043.834')] [2023-07-07 16:21:47,902][566410] Updated weights for policy 0, policy_version 25440 (0.0005) [2023-07-07 16:21:49,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8622.4). Total num frames: 13037568. Throughput: 0: 8622.1. Samples: 13033544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:21:49,506][565952] Avg episode reward: [(0, '4048.323')] [2023-07-07 16:21:52,595][566410] Updated weights for policy 0, policy_version 25520 (0.0005) [2023-07-07 16:21:54,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8601.6, 300 sec: 8622.4). Total num frames: 13082624. Throughput: 0: 8671.2. Samples: 13061156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:21:54,506][565952] Avg episode reward: [(0, '4130.054')] [2023-07-07 16:21:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000025552_13082624.pth... [2023-07-07 16:21:54,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000025040_12820480.pth [2023-07-07 16:21:57,398][566410] Updated weights for policy 0, policy_version 25600 (0.0005) [2023-07-07 16:21:59,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8608.5). Total num frames: 13123584. Throughput: 0: 8650.8. Samples: 13111368. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:21:59,506][565952] Avg episode reward: [(0, '3819.358')] [2023-07-07 16:22:02,307][566410] Updated weights for policy 0, policy_version 25680 (0.0005) [2023-07-07 16:22:04,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8601.6, 300 sec: 8608.5). Total num frames: 13164544. Throughput: 0: 8626.9. Samples: 13163416. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:22:04,506][565952] Avg episode reward: [(0, '3831.898')] [2023-07-07 16:22:07,078][566410] Updated weights for policy 0, policy_version 25760 (0.0005) [2023-07-07 16:22:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8622.4). Total num frames: 13209600. Throughput: 0: 8583.5. Samples: 13188668. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:22:09,506][565952] Avg episode reward: [(0, '4076.727')] [2023-07-07 16:22:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000025800_13209600.pth... [2023-07-07 16:22:09,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000025296_12951552.pth [2023-07-07 16:22:11,646][566410] Updated weights for policy 0, policy_version 25840 (0.0005) [2023-07-07 16:22:14,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8608.5). Total num frames: 13250560. Throughput: 0: 8632.6. Samples: 13241724. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:22:14,506][565952] Avg episode reward: [(0, '3366.039')] [2023-07-07 16:22:16,461][566410] Updated weights for policy 0, policy_version 25920 (0.0005) [2023-07-07 16:22:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8608.5). Total num frames: 13295616. Throughput: 0: 8575.0. Samples: 13292032. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-07 16:22:19,506][565952] Avg episode reward: [(0, '3676.914')] [2023-07-07 16:22:21,287][566410] Updated weights for policy 0, policy_version 26000 (0.0005) [2023-07-07 16:22:24,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8608.5). Total num frames: 13336576. Throughput: 0: 8574.2. Samples: 13317032. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-07 16:22:24,506][565952] Avg episode reward: [(0, '3553.897')] [2023-07-07 16:22:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000026048_13336576.pth... [2023-07-07 16:22:24,514][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000025552_13082624.pth [2023-07-07 16:22:26,080][566410] Updated weights for policy 0, policy_version 26080 (0.0005) [2023-07-07 16:22:29,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8601.6, 300 sec: 8608.5). Total num frames: 13381632. Throughput: 0: 8583.2. Samples: 13369832. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-07 16:22:29,506][565952] Avg episode reward: [(0, '3687.699')] [2023-07-07 16:22:30,798][566410] Updated weights for policy 0, policy_version 26160 (0.0005) [2023-07-07 16:22:34,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8601.6, 300 sec: 8608.5). Total num frames: 13422592. Throughput: 0: 8577.1. Samples: 13419512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:22:34,506][565952] Avg episode reward: [(0, '3767.525')] [2023-07-07 16:22:35,724][566410] Updated weights for policy 0, policy_version 26240 (0.0006) [2023-07-07 16:22:39,506][565952] Fps is (10 sec: 8191.9, 60 sec: 8533.3, 300 sec: 8594.7). Total num frames: 13463552. Throughput: 0: 8550.4. Samples: 13445924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:22:39,506][565952] Avg episode reward: [(0, '3690.053')] [2023-07-07 16:22:39,558][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000026304_13467648.pth... [2023-07-07 16:22:39,561][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000025800_13209600.pth [2023-07-07 16:22:40,576][566410] Updated weights for policy 0, policy_version 26320 (0.0006) [2023-07-07 16:22:44,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 8580.8). Total num frames: 13504512. Throughput: 0: 8519.8. Samples: 13494760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:22:44,506][565952] Avg episode reward: [(0, '4184.864')] [2023-07-07 16:22:45,527][566410] Updated weights for policy 0, policy_version 26400 (0.0005) [2023-07-07 16:22:49,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8594.7). Total num frames: 13549568. Throughput: 0: 8490.1. Samples: 13545472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:22:49,507][565952] Avg episode reward: [(0, '4029.395')] [2023-07-07 16:22:50,391][566410] Updated weights for policy 0, policy_version 26480 (0.0005) [2023-07-07 16:22:54,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8594.7). Total num frames: 13590528. Throughput: 0: 8474.3. Samples: 13570012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:22:54,506][565952] Avg episode reward: [(0, '3905.549')] [2023-07-07 16:22:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000026544_13590528.pth... [2023-07-07 16:22:54,514][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000026048_13336576.pth [2023-07-07 16:22:55,349][566410] Updated weights for policy 0, policy_version 26560 (0.0005) [2023-07-07 16:22:59,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8594.7). Total num frames: 13631488. Throughput: 0: 8425.0. Samples: 13620848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:22:59,506][565952] Avg episode reward: [(0, '2958.940')] [2023-07-07 16:23:00,130][566410] Updated weights for policy 0, policy_version 26640 (0.0005) [2023-07-07 16:23:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8594.7). Total num frames: 13676544. Throughput: 0: 8453.9. Samples: 13672456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:23:04,507][565952] Avg episode reward: [(0, '3409.944')] [2023-07-07 16:23:04,860][566410] Updated weights for policy 0, policy_version 26720 (0.0005) [2023-07-07 16:23:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8580.8). Total num frames: 13717504. Throughput: 0: 8497.8. Samples: 13699432. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:23:09,506][565952] Avg episode reward: [(0, '3629.554')] [2023-07-07 16:23:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000026792_13717504.pth... [2023-07-07 16:23:09,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000026304_13467648.pth [2023-07-07 16:23:09,590][566410] Updated weights for policy 0, policy_version 26800 (0.0005) [2023-07-07 16:23:14,447][566410] Updated weights for policy 0, policy_version 26880 (0.0005) [2023-07-07 16:23:14,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8594.7). Total num frames: 13762560. Throughput: 0: 8455.6. Samples: 13750336. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:23:14,506][565952] Avg episode reward: [(0, '3625.093')] [2023-07-07 16:23:19,353][566410] Updated weights for policy 0, policy_version 26960 (0.0005) [2023-07-07 16:23:19,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8465.1, 300 sec: 8580.8). Total num frames: 13803520. Throughput: 0: 8443.9. Samples: 13799488. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:23:19,506][565952] Avg episode reward: [(0, '4102.307')] [2023-07-07 16:23:24,303][566410] Updated weights for policy 0, policy_version 27040 (0.0005) [2023-07-07 16:23:24,506][565952] Fps is (10 sec: 8191.9, 60 sec: 8465.0, 300 sec: 8580.8). Total num frames: 13844480. Throughput: 0: 8443.6. Samples: 13825888. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:23:24,507][565952] Avg episode reward: [(0, '3689.797')] [2023-07-07 16:23:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000027040_13844480.pth... [2023-07-07 16:23:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000026544_13590528.pth [2023-07-07 16:23:29,391][566410] Updated weights for policy 0, policy_version 27120 (0.0006) [2023-07-07 16:23:29,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8566.9). Total num frames: 13885440. Throughput: 0: 8411.5. Samples: 13873276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:23:29,507][565952] Avg episode reward: [(0, '4156.494')] [2023-07-07 16:23:34,432][566410] Updated weights for policy 0, policy_version 27200 (0.0005) [2023-07-07 16:23:34,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8566.9). Total num frames: 13926400. Throughput: 0: 8374.2. Samples: 13922312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:23:34,506][565952] Avg episode reward: [(0, '4238.321')] [2023-07-07 16:23:39,488][566410] Updated weights for policy 0, policy_version 27280 (0.0005) [2023-07-07 16:23:39,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8553.0). Total num frames: 13967360. Throughput: 0: 8376.4. Samples: 13946952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:23:39,506][565952] Avg episode reward: [(0, '4332.287')] [2023-07-07 16:23:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000027280_13967360.pth... [2023-07-07 16:23:39,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000026792_13717504.pth [2023-07-07 16:23:44,293][566410] Updated weights for policy 0, policy_version 27360 (0.0005) [2023-07-07 16:23:44,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8539.1). Total num frames: 14008320. Throughput: 0: 8338.8. Samples: 13996096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:23:44,506][565952] Avg episode reward: [(0, '4340.670')] [2023-07-07 16:23:49,138][566410] Updated weights for policy 0, policy_version 27440 (0.0005) [2023-07-07 16:23:49,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8525.2). Total num frames: 14049280. Throughput: 0: 8345.8. Samples: 14048016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:23:49,506][565952] Avg episode reward: [(0, '4080.084')] [2023-07-07 16:23:54,201][566410] Updated weights for policy 0, policy_version 27520 (0.0006) [2023-07-07 16:23:54,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8525.2). Total num frames: 14090240. Throughput: 0: 8297.1. Samples: 14072800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:23:54,506][565952] Avg episode reward: [(0, '4319.527')] [2023-07-07 16:23:54,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000027520_14090240.pth... [2023-07-07 16:23:54,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000027040_13844480.pth [2023-07-07 16:23:58,808][566410] Updated weights for policy 0, policy_version 27600 (0.0005) [2023-07-07 16:23:59,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8396.8, 300 sec: 8525.2). Total num frames: 14135296. Throughput: 0: 8290.1. Samples: 14123392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:23:59,506][565952] Avg episode reward: [(0, '4153.697')] [2023-07-07 16:24:03,880][566410] Updated weights for policy 0, policy_version 27680 (0.0005) [2023-07-07 16:24:04,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8328.5, 300 sec: 8525.2). Total num frames: 14176256. Throughput: 0: 8285.6. Samples: 14172340. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:24:04,507][565952] Avg episode reward: [(0, '4197.658')] [2023-07-07 16:24:08,576][566410] Updated weights for policy 0, policy_version 27760 (0.0005) [2023-07-07 16:24:09,506][565952] Fps is (10 sec: 8191.9, 60 sec: 8328.5, 300 sec: 8511.3). Total num frames: 14217216. Throughput: 0: 8306.7. Samples: 14199688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:24:09,507][565952] Avg episode reward: [(0, '4330.178')] [2023-07-07 16:24:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000027768_14217216.pth... [2023-07-07 16:24:09,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000027280_13967360.pth [2023-07-07 16:24:13,431][566410] Updated weights for policy 0, policy_version 27840 (0.0005) [2023-07-07 16:24:14,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8328.5, 300 sec: 8511.3). Total num frames: 14262272. Throughput: 0: 8371.3. Samples: 14249984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:24:14,506][565952] Avg episode reward: [(0, '4082.114')] [2023-07-07 16:24:18,342][566410] Updated weights for policy 0, policy_version 27920 (0.0005) [2023-07-07 16:24:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8328.5, 300 sec: 8497.5). Total num frames: 14303232. Throughput: 0: 8397.6. Samples: 14300204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:24:19,506][565952] Avg episode reward: [(0, '3968.605')] [2023-07-07 16:24:23,142][566410] Updated weights for policy 0, policy_version 28000 (0.0005) [2023-07-07 16:24:24,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8483.6). Total num frames: 14344192. Throughput: 0: 8428.2. Samples: 14326220. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:24:24,506][565952] Avg episode reward: [(0, '4118.259')] [2023-07-07 16:24:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000028016_14344192.pth... [2023-07-07 16:24:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000027520_14090240.pth [2023-07-07 16:24:28,188][566410] Updated weights for policy 0, policy_version 28080 (0.0005) [2023-07-07 16:24:29,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8469.7). Total num frames: 14385152. Throughput: 0: 8431.0. Samples: 14375492. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:24:29,506][565952] Avg episode reward: [(0, '3655.185')] [2023-07-07 16:24:32,657][566410] Updated weights for policy 0, policy_version 28160 (0.0006) [2023-07-07 16:24:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8483.6). Total num frames: 14430208. Throughput: 0: 8476.9. Samples: 14429476. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:24:34,506][565952] Avg episode reward: [(0, '3378.704')] [2023-07-07 16:24:37,444][566410] Updated weights for policy 0, policy_version 28240 (0.0006) [2023-07-07 16:24:39,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8465.1, 300 sec: 8483.6). Total num frames: 14475264. Throughput: 0: 8488.7. Samples: 14454792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:24:39,506][565952] Avg episode reward: [(0, '2925.697')] [2023-07-07 16:24:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000028272_14475264.pth... [2023-07-07 16:24:39,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000027768_14217216.pth [2023-07-07 16:24:42,323][566410] Updated weights for policy 0, policy_version 28320 (0.0005) [2023-07-07 16:24:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8469.7). Total num frames: 14516224. Throughput: 0: 8497.2. Samples: 14505768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:24:44,506][565952] Avg episode reward: [(0, '4112.744')] [2023-07-07 16:24:47,288][566410] Updated weights for policy 0, policy_version 28400 (0.0005) [2023-07-07 16:24:49,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 14557184. Throughput: 0: 8474.7. Samples: 14553700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:24:49,507][565952] Avg episode reward: [(0, '4131.370')] [2023-07-07 16:24:52,382][566410] Updated weights for policy 0, policy_version 28480 (0.0005) [2023-07-07 16:24:54,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 14598144. Throughput: 0: 8401.1. Samples: 14577736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:24:54,506][565952] Avg episode reward: [(0, '4105.188')] [2023-07-07 16:24:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000028512_14598144.pth... [2023-07-07 16:24:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000028016_14344192.pth [2023-07-07 16:24:57,258][566410] Updated weights for policy 0, policy_version 28560 (0.0005) [2023-07-07 16:24:59,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8455.8). Total num frames: 14639104. Throughput: 0: 8414.5. Samples: 14628636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:24:59,506][565952] Avg episode reward: [(0, '4130.791')] [2023-07-07 16:25:01,920][566410] Updated weights for policy 0, policy_version 28640 (0.0005) [2023-07-07 16:25:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 14684160. Throughput: 0: 8451.6. Samples: 14680528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:25:04,506][565952] Avg episode reward: [(0, '3788.201')] [2023-07-07 16:25:06,769][566410] Updated weights for policy 0, policy_version 28720 (0.0006) [2023-07-07 16:25:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 14725120. Throughput: 0: 8448.3. Samples: 14706392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:25:09,506][565952] Avg episode reward: [(0, '4164.413')] [2023-07-07 16:25:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000028760_14725120.pth... [2023-07-07 16:25:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000028272_14475264.pth [2023-07-07 16:25:11,475][566410] Updated weights for policy 0, policy_version 28800 (0.0005) [2023-07-07 16:25:14,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 14770176. Throughput: 0: 8506.2. Samples: 14758268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:25:14,506][565952] Avg episode reward: [(0, '3525.702')] [2023-07-07 16:25:16,204][566410] Updated weights for policy 0, policy_version 28880 (0.0005) [2023-07-07 16:25:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 14811136. Throughput: 0: 8458.4. Samples: 14810104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:25:19,506][565952] Avg episode reward: [(0, '4160.047')] [2023-07-07 16:25:21,004][566410] Updated weights for policy 0, policy_version 28960 (0.0005) [2023-07-07 16:25:24,506][565952] Fps is (10 sec: 8601.4, 60 sec: 8533.3, 300 sec: 8469.7). Total num frames: 14856192. Throughput: 0: 8466.3. Samples: 14835776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:25:24,506][565952] Avg episode reward: [(0, '4245.186')] [2023-07-07 16:25:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000029016_14856192.pth... [2023-07-07 16:25:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000028512_14598144.pth [2023-07-07 16:25:25,766][566410] Updated weights for policy 0, policy_version 29040 (0.0005) [2023-07-07 16:25:29,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8601.6, 300 sec: 8483.6). Total num frames: 14901248. Throughput: 0: 8490.4. Samples: 14887836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:25:29,506][565952] Avg episode reward: [(0, '4420.489')] [2023-07-07 16:25:30,430][566410] Updated weights for policy 0, policy_version 29120 (0.0005) [2023-07-07 16:25:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8483.6). Total num frames: 14942208. Throughput: 0: 8545.7. Samples: 14938256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:25:34,506][565952] Avg episode reward: [(0, '4089.768')] [2023-07-07 16:25:35,235][566410] Updated weights for policy 0, policy_version 29200 (0.0005) [2023-07-07 16:25:39,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8497.5). Total num frames: 14987264. Throughput: 0: 8643.6. Samples: 14966696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:25:39,506][565952] Avg episode reward: [(0, '3919.408')] [2023-07-07 16:25:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000029272_14987264.pth... [2023-07-07 16:25:39,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000028760_14725120.pth [2023-07-07 16:25:39,848][566410] Updated weights for policy 0, policy_version 29280 (0.0005) [2023-07-07 16:25:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8497.5). Total num frames: 15028224. Throughput: 0: 8672.5. Samples: 15018900. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:25:44,506][565952] Avg episode reward: [(0, '3690.908')] [2023-07-07 16:25:44,517][566410] Updated weights for policy 0, policy_version 29360 (0.0005) [2023-07-07 16:25:49,428][566410] Updated weights for policy 0, policy_version 29440 (0.0005) [2023-07-07 16:25:49,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8497.5). Total num frames: 15073280. Throughput: 0: 8635.7. Samples: 15069136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:25:49,506][565952] Avg episode reward: [(0, '4081.824')] [2023-07-07 16:25:54,217][566410] Updated weights for policy 0, policy_version 29520 (0.0005) [2023-07-07 16:25:54,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8497.5). Total num frames: 15114240. Throughput: 0: 8619.3. Samples: 15094260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:25:54,507][565952] Avg episode reward: [(0, '3634.183')] [2023-07-07 16:25:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000029520_15114240.pth... [2023-07-07 16:25:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000029016_14856192.pth [2023-07-07 16:25:58,926][566410] Updated weights for policy 0, policy_version 29600 (0.0005) [2023-07-07 16:25:59,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8511.4). Total num frames: 15159296. Throughput: 0: 8637.2. Samples: 15146944. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:25:59,506][565952] Avg episode reward: [(0, '3481.504')] [2023-07-07 16:26:03,672][566410] Updated weights for policy 0, policy_version 29680 (0.0005) [2023-07-07 16:26:04,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8601.6, 300 sec: 8511.4). Total num frames: 15200256. Throughput: 0: 8645.0. Samples: 15199128. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:26:04,506][565952] Avg episode reward: [(0, '3821.515')] [2023-07-07 16:26:08,622][566410] Updated weights for policy 0, policy_version 29760 (0.0005) [2023-07-07 16:26:09,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8601.6, 300 sec: 8497.5). Total num frames: 15241216. Throughput: 0: 8618.9. Samples: 15223628. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:26:09,506][565952] Avg episode reward: [(0, '3952.953')] [2023-07-07 16:26:09,508][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000029768_15241216.pth... [2023-07-07 16:26:09,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000029272_14987264.pth [2023-07-07 16:26:13,767][566410] Updated weights for policy 0, policy_version 29840 (0.0005) [2023-07-07 16:26:14,506][565952] Fps is (10 sec: 8191.9, 60 sec: 8533.3, 300 sec: 8497.5). Total num frames: 15282176. Throughput: 0: 8549.8. Samples: 15272576. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:26:14,506][565952] Avg episode reward: [(0, '4205.168')] [2023-07-07 16:26:18,912][566410] Updated weights for policy 0, policy_version 29920 (0.0005) [2023-07-07 16:26:19,506][565952] Fps is (10 sec: 8191.9, 60 sec: 8533.3, 300 sec: 8483.6). Total num frames: 15323136. Throughput: 0: 8463.3. Samples: 15319104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:26:19,507][565952] Avg episode reward: [(0, '4263.885')] [2023-07-07 16:26:23,685][566410] Updated weights for policy 0, policy_version 30000 (0.0005) [2023-07-07 16:26:24,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8469.7). Total num frames: 15364096. Throughput: 0: 8392.8. Samples: 15344372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:26:24,506][565952] Avg episode reward: [(0, '3968.405')] [2023-07-07 16:26:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000030008_15364096.pth... [2023-07-07 16:26:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000029520_15114240.pth [2023-07-07 16:26:28,539][566410] Updated weights for policy 0, policy_version 30080 (0.0005) [2023-07-07 16:26:29,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8465.1, 300 sec: 8483.6). Total num frames: 15409152. Throughput: 0: 8386.2. Samples: 15396280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:26:29,506][565952] Avg episode reward: [(0, '4138.227')] [2023-07-07 16:26:33,270][566410] Updated weights for policy 0, policy_version 30160 (0.0005) [2023-07-07 16:26:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8469.7). Total num frames: 15450112. Throughput: 0: 8419.3. Samples: 15448004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:26:34,506][565952] Avg episode reward: [(0, '3867.748')] [2023-07-07 16:26:38,123][566410] Updated weights for policy 0, policy_version 30240 (0.0005) [2023-07-07 16:26:39,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8469.7). Total num frames: 15491072. Throughput: 0: 8440.6. Samples: 15474088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:26:39,506][565952] Avg episode reward: [(0, '4149.772')] [2023-07-07 16:26:39,550][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000030264_15495168.pth... [2023-07-07 16:26:39,552][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000029768_15241216.pth [2023-07-07 16:26:42,987][566410] Updated weights for policy 0, policy_version 30320 (0.0005) [2023-07-07 16:26:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8469.7). Total num frames: 15536128. Throughput: 0: 8374.6. Samples: 15523800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:26:44,506][565952] Avg episode reward: [(0, '4106.477')] [2023-07-07 16:26:47,718][566410] Updated weights for policy 0, policy_version 30400 (0.0006) [2023-07-07 16:26:49,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8455.8). Total num frames: 15577088. Throughput: 0: 8371.6. Samples: 15575852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:26:49,506][565952] Avg episode reward: [(0, '4362.882')] [2023-07-07 16:26:52,536][566410] Updated weights for policy 0, policy_version 30480 (0.0005) [2023-07-07 16:26:54,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8455.8). Total num frames: 15618048. Throughput: 0: 8400.8. Samples: 15601664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:26:54,506][565952] Avg episode reward: [(0, '4291.904')] [2023-07-07 16:26:54,519][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000030512_15622144.pth... [2023-07-07 16:26:54,520][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000030008_15364096.pth [2023-07-07 16:26:57,624][566410] Updated weights for policy 0, policy_version 30560 (0.0005) [2023-07-07 16:26:59,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8469.7). Total num frames: 15663104. Throughput: 0: 8384.3. Samples: 15649872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:26:59,507][565952] Avg episode reward: [(0, '4542.259')] [2023-07-07 16:26:59,507][566397] Saving new best policy, reward=4542.259! [2023-07-07 16:27:02,326][566410] Updated weights for policy 0, policy_version 30640 (0.0005) [2023-07-07 16:27:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8455.8). Total num frames: 15704064. Throughput: 0: 8465.3. Samples: 15700040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:27:04,506][565952] Avg episode reward: [(0, '4253.238')] [2023-07-07 16:27:07,322][566410] Updated weights for policy 0, policy_version 30720 (0.0005) [2023-07-07 16:27:09,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8455.8). Total num frames: 15745024. Throughput: 0: 8465.7. Samples: 15725328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:27:09,507][565952] Avg episode reward: [(0, '4133.151')] [2023-07-07 16:27:09,511][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000030752_15745024.pth... [2023-07-07 16:27:09,514][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000030264_15495168.pth [2023-07-07 16:27:12,167][566410] Updated weights for policy 0, policy_version 30800 (0.0005) [2023-07-07 16:27:14,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8441.9). Total num frames: 15785984. Throughput: 0: 8447.7. Samples: 15776428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:27:14,506][565952] Avg episode reward: [(0, '4047.494')] [2023-07-07 16:27:16,990][566410] Updated weights for policy 0, policy_version 30880 (0.0005) [2023-07-07 16:27:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 15831040. Throughput: 0: 8422.3. Samples: 15827008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:27:19,507][565952] Avg episode reward: [(0, '4149.676')] [2023-07-07 16:27:22,040][566410] Updated weights for policy 0, policy_version 30960 (0.0005) [2023-07-07 16:27:24,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8465.1, 300 sec: 8441.9). Total num frames: 15872000. Throughput: 0: 8382.6. Samples: 15851304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:27:24,506][565952] Avg episode reward: [(0, '4266.557')] [2023-07-07 16:27:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000031000_15872000.pth... [2023-07-07 16:27:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000030512_15622144.pth [2023-07-07 16:27:26,800][566410] Updated weights for policy 0, policy_version 31040 (0.0005) [2023-07-07 16:27:29,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8441.9). Total num frames: 15912960. Throughput: 0: 8401.6. Samples: 15901872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:27:29,506][565952] Avg episode reward: [(0, '3469.332')] [2023-07-07 16:27:31,550][566410] Updated weights for policy 0, policy_version 31120 (0.0005) [2023-07-07 16:27:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 15958016. Throughput: 0: 8400.4. Samples: 15953868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:27:34,506][565952] Avg episode reward: [(0, '3850.718')] [2023-07-07 16:27:36,441][566410] Updated weights for policy 0, policy_version 31200 (0.0005) [2023-07-07 16:27:39,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 15998976. Throughput: 0: 8374.2. Samples: 15978504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:27:39,506][565952] Avg episode reward: [(0, '3457.747')] [2023-07-07 16:27:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000031248_15998976.pth... [2023-07-07 16:27:39,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000030752_15745024.pth [2023-07-07 16:27:41,294][566410] Updated weights for policy 0, policy_version 31280 (0.0005) [2023-07-07 16:27:44,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8441.9). Total num frames: 16039936. Throughput: 0: 8436.3. Samples: 16029504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:27:44,506][565952] Avg episode reward: [(0, '3568.080')] [2023-07-07 16:27:45,905][566410] Updated weights for policy 0, policy_version 31360 (0.0005) [2023-07-07 16:27:49,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 16084992. Throughput: 0: 8513.2. Samples: 16083136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:27:49,506][565952] Avg episode reward: [(0, '3991.038')] [2023-07-07 16:27:50,722][566410] Updated weights for policy 0, policy_version 31440 (0.0006) [2023-07-07 16:27:54,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8533.3, 300 sec: 8469.7). Total num frames: 16130048. Throughput: 0: 8496.8. Samples: 16107684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:27:54,506][565952] Avg episode reward: [(0, '4145.654')] [2023-07-07 16:27:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000031504_16130048.pth... [2023-07-07 16:27:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000031000_15872000.pth [2023-07-07 16:27:55,407][566410] Updated weights for policy 0, policy_version 31520 (0.0005) [2023-07-07 16:27:59,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 16171008. Throughput: 0: 8522.8. Samples: 16159952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:27:59,507][565952] Avg episode reward: [(0, '3775.757')] [2023-07-07 16:28:00,111][566410] Updated weights for policy 0, policy_version 31600 (0.0005) [2023-07-07 16:28:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8469.7). Total num frames: 16216064. Throughput: 0: 8553.7. Samples: 16211924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:28:04,506][565952] Avg episode reward: [(0, '4268.235')] [2023-07-07 16:28:04,972][566410] Updated weights for policy 0, policy_version 31680 (0.0005) [2023-07-07 16:28:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8455.8). Total num frames: 16257024. Throughput: 0: 8568.9. Samples: 16236904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:28:09,506][565952] Avg episode reward: [(0, '4354.766')] [2023-07-07 16:28:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000031752_16257024.pth... [2023-07-07 16:28:09,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000031248_15998976.pth [2023-07-07 16:28:09,821][566410] Updated weights for policy 0, policy_version 31760 (0.0005) [2023-07-07 16:28:14,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 8455.8). Total num frames: 16297984. Throughput: 0: 8560.0. Samples: 16287072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:28:14,506][565952] Avg episode reward: [(0, '4073.902')] [2023-07-07 16:28:14,640][566410] Updated weights for policy 0, policy_version 31840 (0.0005) [2023-07-07 16:28:19,300][566410] Updated weights for policy 0, policy_version 31920 (0.0005) [2023-07-07 16:28:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8469.7). Total num frames: 16343040. Throughput: 0: 8579.2. Samples: 16339932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:28:19,506][565952] Avg episode reward: [(0, '4321.862')] [2023-07-07 16:28:23,935][566410] Updated weights for policy 0, policy_version 32000 (0.0005) [2023-07-07 16:28:24,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8601.6, 300 sec: 8483.6). Total num frames: 16388096. Throughput: 0: 8638.2. Samples: 16367224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:28:24,507][565952] Avg episode reward: [(0, '4046.824')] [2023-07-07 16:28:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000032008_16388096.pth... [2023-07-07 16:28:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000031504_16130048.pth [2023-07-07 16:28:28,630][566410] Updated weights for policy 0, policy_version 32080 (0.0005) [2023-07-07 16:28:29,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8601.6, 300 sec: 8483.6). Total num frames: 16429056. Throughput: 0: 8648.4. Samples: 16418680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:28:29,506][565952] Avg episode reward: [(0, '4302.772')] [2023-07-07 16:28:33,381][566410] Updated weights for policy 0, policy_version 32160 (0.0006) [2023-07-07 16:28:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8497.5). Total num frames: 16474112. Throughput: 0: 8627.8. Samples: 16471388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:28:34,507][565952] Avg episode reward: [(0, '4394.726')] [2023-07-07 16:28:37,822][566410] Updated weights for policy 0, policy_version 32240 (0.0005) [2023-07-07 16:28:39,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8669.9, 300 sec: 8511.3). Total num frames: 16519168. Throughput: 0: 8682.5. Samples: 16498396. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:28:39,506][565952] Avg episode reward: [(0, '4228.150')] [2023-07-07 16:28:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000032264_16519168.pth... [2023-07-07 16:28:39,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000031752_16257024.pth [2023-07-07 16:28:42,471][566410] Updated weights for policy 0, policy_version 32320 (0.0005) [2023-07-07 16:28:44,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8525.2). Total num frames: 16564224. Throughput: 0: 8709.1. Samples: 16551860. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:28:44,506][565952] Avg episode reward: [(0, '3903.050')] [2023-07-07 16:28:47,027][566410] Updated weights for policy 0, policy_version 32400 (0.0004) [2023-07-07 16:28:49,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8738.1, 300 sec: 8539.1). Total num frames: 16609280. Throughput: 0: 8754.7. Samples: 16605884. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:28:49,506][565952] Avg episode reward: [(0, '4261.717')] [2023-07-07 16:28:51,602][566410] Updated weights for policy 0, policy_version 32480 (0.0005) [2023-07-07 16:28:54,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8738.1, 300 sec: 8539.1). Total num frames: 16654336. Throughput: 0: 8803.8. Samples: 16633076. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:28:54,507][565952] Avg episode reward: [(0, '3905.227')] [2023-07-07 16:28:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000032528_16654336.pth... [2023-07-07 16:28:54,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000032008_16388096.pth [2023-07-07 16:28:56,272][566410] Updated weights for policy 0, policy_version 32560 (0.0005) [2023-07-07 16:28:59,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8539.1). Total num frames: 16695296. Throughput: 0: 8852.0. Samples: 16685412. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:28:59,506][565952] Avg episode reward: [(0, '4062.312')] [2023-07-07 16:29:01,302][566410] Updated weights for policy 0, policy_version 32640 (0.0006) [2023-07-07 16:29:04,506][565952] Fps is (10 sec: 8192.1, 60 sec: 8669.9, 300 sec: 8539.1). Total num frames: 16736256. Throughput: 0: 8765.8. Samples: 16734392. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:29:04,506][565952] Avg episode reward: [(0, '4282.227')] [2023-07-07 16:29:06,037][566410] Updated weights for policy 0, policy_version 32720 (0.0006) [2023-07-07 16:29:09,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8738.1, 300 sec: 8539.1). Total num frames: 16781312. Throughput: 0: 8755.1. Samples: 16761204. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:29:09,507][565952] Avg episode reward: [(0, '4300.188')] [2023-07-07 16:29:09,539][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000032784_16785408.pth... [2023-07-07 16:29:09,540][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000032264_16519168.pth [2023-07-07 16:29:10,458][566410] Updated weights for policy 0, policy_version 32800 (0.0005) [2023-07-07 16:29:14,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8806.4, 300 sec: 8553.0). Total num frames: 16826368. Throughput: 0: 8822.5. Samples: 16815692. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:29:14,506][565952] Avg episode reward: [(0, '4171.363')] [2023-07-07 16:29:15,045][566410] Updated weights for policy 0, policy_version 32880 (0.0006) [2023-07-07 16:29:19,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8806.4, 300 sec: 8566.9). Total num frames: 16871424. Throughput: 0: 8810.8. Samples: 16867872. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:29:19,506][565952] Avg episode reward: [(0, '4081.282')] [2023-07-07 16:29:19,703][566410] Updated weights for policy 0, policy_version 32960 (0.0006) [2023-07-07 16:29:24,277][566410] Updated weights for policy 0, policy_version 33040 (0.0005) [2023-07-07 16:29:24,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8580.8). Total num frames: 16916480. Throughput: 0: 8824.1. Samples: 16895480. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:29:24,506][565952] Avg episode reward: [(0, '4210.087')] [2023-07-07 16:29:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000033040_16916480.pth... [2023-07-07 16:29:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000032528_16654336.pth [2023-07-07 16:29:28,803][566410] Updated weights for policy 0, policy_version 33120 (0.0005) [2023-07-07 16:29:29,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8874.7, 300 sec: 8580.8). Total num frames: 16961536. Throughput: 0: 8832.5. Samples: 16949320. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:29:29,506][565952] Avg episode reward: [(0, '3191.852')] [2023-07-07 16:29:33,363][566410] Updated weights for policy 0, policy_version 33200 (0.0005) [2023-07-07 16:29:34,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8874.7, 300 sec: 8580.8). Total num frames: 17006592. Throughput: 0: 8833.1. Samples: 17003376. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:29:34,506][565952] Avg episode reward: [(0, '3677.557')] [2023-07-07 16:29:38,082][566410] Updated weights for policy 0, policy_version 33280 (0.0005) [2023-07-07 16:29:39,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8806.4, 300 sec: 8580.8). Total num frames: 17047552. Throughput: 0: 8809.1. Samples: 17029484. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:29:39,506][565952] Avg episode reward: [(0, '4215.558')] [2023-07-07 16:29:39,511][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000033304_17051648.pth... [2023-07-07 16:29:39,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000032784_16785408.pth [2023-07-07 16:29:42,856][566410] Updated weights for policy 0, policy_version 33360 (0.0005) [2023-07-07 16:29:44,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8806.4, 300 sec: 8594.7). Total num frames: 17092608. Throughput: 0: 8783.5. Samples: 17080668. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:29:44,506][565952] Avg episode reward: [(0, '3928.466')] [2023-07-07 16:29:47,147][566410] Updated weights for policy 0, policy_version 33440 (0.0005) [2023-07-07 16:29:49,506][565952] Fps is (10 sec: 9420.8, 60 sec: 8874.7, 300 sec: 8622.4). Total num frames: 17141760. Throughput: 0: 8961.1. Samples: 17137644. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:29:49,507][565952] Avg episode reward: [(0, '4110.663')] [2023-07-07 16:29:51,682][566410] Updated weights for policy 0, policy_version 33520 (0.0005) [2023-07-07 16:29:54,506][565952] Fps is (10 sec: 9420.7, 60 sec: 8874.7, 300 sec: 8636.3). Total num frames: 17186816. Throughput: 0: 8969.2. Samples: 17164820. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:29:54,507][565952] Avg episode reward: [(0, '4143.228')] [2023-07-07 16:29:54,511][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000033568_17186816.pth... [2023-07-07 16:29:54,519][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000033040_16916480.pth [2023-07-07 16:29:56,182][566410] Updated weights for policy 0, policy_version 33600 (0.0005) [2023-07-07 16:29:59,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8942.9, 300 sec: 8636.3). Total num frames: 17231872. Throughput: 0: 8969.6. Samples: 17219324. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:29:59,506][565952] Avg episode reward: [(0, '3968.918')] [2023-07-07 16:30:00,888][566410] Updated weights for policy 0, policy_version 33680 (0.0005) [2023-07-07 16:30:04,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 8650.2). Total num frames: 17276928. Throughput: 0: 8996.4. Samples: 17272712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:30:04,506][565952] Avg episode reward: [(0, '4155.778')] [2023-07-07 16:30:05,237][566410] Updated weights for policy 0, policy_version 33760 (0.0005) [2023-07-07 16:30:09,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 8650.2). Total num frames: 17321984. Throughput: 0: 9001.7. Samples: 17300556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:30:09,506][565952] Avg episode reward: [(0, '4049.108')] [2023-07-07 16:30:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000033832_17321984.pth... [2023-07-07 16:30:09,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000033304_17051648.pth [2023-07-07 16:30:10,000][566410] Updated weights for policy 0, policy_version 33840 (0.0005) [2023-07-07 16:30:14,397][566410] Updated weights for policy 0, policy_version 33920 (0.0005) [2023-07-07 16:30:14,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 8664.1). Total num frames: 17367040. Throughput: 0: 8991.7. Samples: 17353948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:30:14,506][565952] Avg episode reward: [(0, '3731.926')] [2023-07-07 16:30:18,996][566410] Updated weights for policy 0, policy_version 34000 (0.0005) [2023-07-07 16:30:19,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 8664.1). Total num frames: 17412096. Throughput: 0: 8989.9. Samples: 17407920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:30:19,506][565952] Avg episode reward: [(0, '4234.312')] [2023-07-07 16:30:23,558][566410] Updated weights for policy 0, policy_version 34080 (0.0005) [2023-07-07 16:30:24,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 8664.1). Total num frames: 17457152. Throughput: 0: 9038.8. Samples: 17436232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:30:24,506][565952] Avg episode reward: [(0, '4304.449')] [2023-07-07 16:30:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000034096_17457152.pth... [2023-07-07 16:30:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000033568_17186816.pth [2023-07-07 16:30:27,789][566410] Updated weights for policy 0, policy_version 34160 (0.0005) [2023-07-07 16:30:29,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 8678.0). Total num frames: 17502208. Throughput: 0: 9123.9. Samples: 17491244. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:30:29,506][565952] Avg episode reward: [(0, '4173.091')] [2023-07-07 16:30:32,259][566410] Updated weights for policy 0, policy_version 34240 (0.0005) [2023-07-07 16:30:34,506][565952] Fps is (10 sec: 9420.9, 60 sec: 9079.5, 300 sec: 8691.9). Total num frames: 17551360. Throughput: 0: 9095.2. Samples: 17546928. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:30:34,506][565952] Avg episode reward: [(0, '3911.108')] [2023-07-07 16:30:36,852][566410] Updated weights for policy 0, policy_version 34320 (0.0005) [2023-07-07 16:30:39,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 8691.9). Total num frames: 17592320. Throughput: 0: 9056.6. Samples: 17572364. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:30:39,506][565952] Avg episode reward: [(0, '4028.137')] [2023-07-07 16:30:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000034360_17592320.pth... [2023-07-07 16:30:39,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000033832_17321984.pth [2023-07-07 16:30:41,425][566410] Updated weights for policy 0, policy_version 34400 (0.0005) [2023-07-07 16:30:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 9079.5, 300 sec: 8691.9). Total num frames: 17637376. Throughput: 0: 9018.4. Samples: 17625152. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-07 16:30:44,506][565952] Avg episode reward: [(0, '4011.312')] [2023-07-07 16:30:46,169][566410] Updated weights for policy 0, policy_version 34480 (0.0005) [2023-07-07 16:30:49,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8942.9, 300 sec: 8691.9). Total num frames: 17678336. Throughput: 0: 8968.7. Samples: 17676304. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:30:49,506][565952] Avg episode reward: [(0, '3527.351')] [2023-07-07 16:30:51,158][566410] Updated weights for policy 0, policy_version 34560 (0.0006) [2023-07-07 16:30:54,506][565952] Fps is (10 sec: 8192.0, 60 sec: 8874.7, 300 sec: 8678.0). Total num frames: 17719296. Throughput: 0: 8896.5. Samples: 17700900. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:30:54,506][565952] Avg episode reward: [(0, '4084.975')] [2023-07-07 16:30:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000034608_17719296.pth... [2023-07-07 16:30:54,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000034096_17457152.pth [2023-07-07 16:30:55,926][566410] Updated weights for policy 0, policy_version 34640 (0.0005) [2023-07-07 16:30:59,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8942.9, 300 sec: 8705.7). Total num frames: 17768448. Throughput: 0: 8909.0. Samples: 17754852. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:30:59,506][565952] Avg episode reward: [(0, '4193.829')] [2023-07-07 16:31:00,407][566410] Updated weights for policy 0, policy_version 34720 (0.0005) [2023-07-07 16:31:04,506][565952] Fps is (10 sec: 9420.7, 60 sec: 8942.9, 300 sec: 8719.6). Total num frames: 17813504. Throughput: 0: 8907.2. Samples: 17808744. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:31:04,506][565952] Avg episode reward: [(0, '4216.706')] [2023-07-07 16:31:04,918][566410] Updated weights for policy 0, policy_version 34800 (0.0005) [2023-07-07 16:31:09,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8874.7, 300 sec: 8719.6). Total num frames: 17854464. Throughput: 0: 8900.6. Samples: 17836760. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:31:09,507][565952] Avg episode reward: [(0, '4056.361')] [2023-07-07 16:31:09,528][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000034880_17858560.pth... [2023-07-07 16:31:09,528][566410] Updated weights for policy 0, policy_version 34880 (0.0005) [2023-07-07 16:31:09,529][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000034360_17592320.pth [2023-07-07 16:31:14,346][566410] Updated weights for policy 0, policy_version 34960 (0.0006) [2023-07-07 16:31:14,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8874.7, 300 sec: 8733.5). Total num frames: 17899520. Throughput: 0: 8801.1. Samples: 17887296. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:31:14,506][565952] Avg episode reward: [(0, '4020.554')] [2023-07-07 16:31:18,955][566410] Updated weights for policy 0, policy_version 35040 (0.0006) [2023-07-07 16:31:19,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8874.7, 300 sec: 8747.4). Total num frames: 17944576. Throughput: 0: 8745.6. Samples: 17940480. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:31:19,506][565952] Avg episode reward: [(0, '3720.521')] [2023-07-07 16:31:23,790][566410] Updated weights for policy 0, policy_version 35120 (0.0005) [2023-07-07 16:31:24,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8733.5). Total num frames: 17985536. Throughput: 0: 8755.3. Samples: 17966352. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:31:24,506][565952] Avg episode reward: [(0, '3582.793')] [2023-07-07 16:31:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000035128_17985536.pth... [2023-07-07 16:31:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000034608_17719296.pth [2023-07-07 16:31:28,441][566410] Updated weights for policy 0, policy_version 35200 (0.0006) [2023-07-07 16:31:29,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8806.4, 300 sec: 8747.4). Total num frames: 18030592. Throughput: 0: 8737.0. Samples: 18018316. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:31:29,506][565952] Avg episode reward: [(0, '3366.065')] [2023-07-07 16:31:33,045][566410] Updated weights for policy 0, policy_version 35280 (0.0004) [2023-07-07 16:31:34,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8761.3). Total num frames: 18075648. Throughput: 0: 8783.4. Samples: 18071560. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:31:34,507][565952] Avg episode reward: [(0, '4115.338')] [2023-07-07 16:31:37,701][566410] Updated weights for policy 0, policy_version 35360 (0.0005) [2023-07-07 16:31:39,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8761.3). Total num frames: 18120704. Throughput: 0: 8827.7. Samples: 18098148. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:31:39,506][565952] Avg episode reward: [(0, '4219.668')] [2023-07-07 16:31:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000035392_18120704.pth... [2023-07-07 16:31:39,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000034880_17858560.pth [2023-07-07 16:31:42,353][566410] Updated weights for policy 0, policy_version 35440 (0.0004) [2023-07-07 16:31:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8761.3). Total num frames: 18161664. Throughput: 0: 8789.9. Samples: 18150396. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:31:44,506][565952] Avg episode reward: [(0, '4333.719')] [2023-07-07 16:31:46,858][566410] Updated weights for policy 0, policy_version 35520 (0.0005) [2023-07-07 16:31:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8874.7, 300 sec: 8789.0). Total num frames: 18210816. Throughput: 0: 8841.4. Samples: 18206608. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:31:49,506][565952] Avg episode reward: [(0, '4360.032')] [2023-07-07 16:31:51,247][566410] Updated weights for policy 0, policy_version 35600 (0.0005) [2023-07-07 16:31:54,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8874.7, 300 sec: 8775.2). Total num frames: 18251776. Throughput: 0: 8791.0. Samples: 18232352. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:31:54,506][565952] Avg episode reward: [(0, '4245.882')] [2023-07-07 16:31:54,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000035648_18251776.pth... [2023-07-07 16:31:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000035128_17985536.pth [2023-07-07 16:31:56,064][566410] Updated weights for policy 0, policy_version 35680 (0.0005) [2023-07-07 16:31:59,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8789.0). Total num frames: 18296832. Throughput: 0: 8824.0. Samples: 18284376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:31:59,506][565952] Avg episode reward: [(0, '4440.221')] [2023-07-07 16:32:00,822][566410] Updated weights for policy 0, policy_version 35760 (0.0005) [2023-07-07 16:32:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.2, 300 sec: 8789.0). Total num frames: 18337792. Throughput: 0: 8791.1. Samples: 18336080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:32:04,506][565952] Avg episode reward: [(0, '4402.317')] [2023-07-07 16:32:05,443][566410] Updated weights for policy 0, policy_version 35840 (0.0005) [2023-07-07 16:32:09,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8806.4, 300 sec: 8802.9). Total num frames: 18382848. Throughput: 0: 8821.4. Samples: 18363316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:32:09,506][565952] Avg episode reward: [(0, '4116.403')] [2023-07-07 16:32:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000035904_18382848.pth... [2023-07-07 16:32:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000035392_18120704.pth [2023-07-07 16:32:10,293][566410] Updated weights for policy 0, policy_version 35920 (0.0005) [2023-07-07 16:32:14,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8806.4, 300 sec: 8802.9). Total num frames: 18427904. Throughput: 0: 8829.2. Samples: 18415632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:32:14,506][565952] Avg episode reward: [(0, '3247.659')] [2023-07-07 16:32:14,770][566410] Updated weights for policy 0, policy_version 36000 (0.0005) [2023-07-07 16:32:19,171][566410] Updated weights for policy 0, policy_version 36080 (0.0005) [2023-07-07 16:32:19,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8806.4, 300 sec: 8816.8). Total num frames: 18472960. Throughput: 0: 8873.7. Samples: 18470876. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:32:19,506][565952] Avg episode reward: [(0, '4332.109')] [2023-07-07 16:32:23,901][566410] Updated weights for policy 0, policy_version 36160 (0.0005) [2023-07-07 16:32:24,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8874.7, 300 sec: 8830.7). Total num frames: 18518016. Throughput: 0: 8872.8. Samples: 18497424. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:32:24,507][565952] Avg episode reward: [(0, '3682.445')] [2023-07-07 16:32:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000036168_18518016.pth... [2023-07-07 16:32:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000035648_18251776.pth [2023-07-07 16:32:28,706][566410] Updated weights for policy 0, policy_version 36240 (0.0005) [2023-07-07 16:32:29,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8816.8). Total num frames: 18558976. Throughput: 0: 8859.9. Samples: 18549092. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:32:29,506][565952] Avg episode reward: [(0, '4028.162')] [2023-07-07 16:32:33,401][566410] Updated weights for policy 0, policy_version 36320 (0.0005) [2023-07-07 16:32:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8830.7). Total num frames: 18604032. Throughput: 0: 8742.0. Samples: 18600000. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:32:34,506][565952] Avg episode reward: [(0, '3521.565')] [2023-07-07 16:32:37,747][566410] Updated weights for policy 0, policy_version 36400 (0.0005) [2023-07-07 16:32:39,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8806.4, 300 sec: 8844.6). Total num frames: 18649088. Throughput: 0: 8807.1. Samples: 18628672. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:32:39,506][565952] Avg episode reward: [(0, '3342.819')] [2023-07-07 16:32:39,514][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000036432_18653184.pth... [2023-07-07 16:32:39,516][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000035904_18382848.pth [2023-07-07 16:32:42,249][566410] Updated weights for policy 0, policy_version 36480 (0.0005) [2023-07-07 16:32:44,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8874.7, 300 sec: 8844.6). Total num frames: 18694144. Throughput: 0: 8874.1. Samples: 18683712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:32:44,507][565952] Avg episode reward: [(0, '3497.323')] [2023-07-07 16:32:47,004][566410] Updated weights for policy 0, policy_version 36560 (0.0006) [2023-07-07 16:32:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8844.6). Total num frames: 18739200. Throughput: 0: 8905.8. Samples: 18736840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:32:49,506][565952] Avg episode reward: [(0, '3881.605')] [2023-07-07 16:32:51,716][566410] Updated weights for policy 0, policy_version 36640 (0.0005) [2023-07-07 16:32:54,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8844.6). Total num frames: 18780160. Throughput: 0: 8861.5. Samples: 18762084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:32:54,506][565952] Avg episode reward: [(0, '4488.553')] [2023-07-07 16:32:54,525][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000036688_18784256.pth... [2023-07-07 16:32:54,526][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000036168_18518016.pth [2023-07-07 16:32:56,514][566410] Updated weights for policy 0, policy_version 36720 (0.0005) [2023-07-07 16:32:59,506][565952] Fps is (10 sec: 8191.9, 60 sec: 8738.1, 300 sec: 8830.7). Total num frames: 18821120. Throughput: 0: 8827.2. Samples: 18812856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:32:59,506][565952] Avg episode reward: [(0, '4493.281')] [2023-07-07 16:33:01,324][566410] Updated weights for policy 0, policy_version 36800 (0.0005) [2023-07-07 16:33:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8844.6). Total num frames: 18866176. Throughput: 0: 8735.3. Samples: 18863964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:33:04,506][565952] Avg episode reward: [(0, '3917.558')] [2023-07-07 16:33:06,085][566410] Updated weights for policy 0, policy_version 36880 (0.0005) [2023-07-07 16:33:09,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8806.4, 300 sec: 8858.5). Total num frames: 18911232. Throughput: 0: 8734.7. Samples: 18890484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:33:09,506][565952] Avg episode reward: [(0, '3420.382')] [2023-07-07 16:33:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000036936_18911232.pth... [2023-07-07 16:33:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000036432_18653184.pth [2023-07-07 16:33:10,826][566410] Updated weights for policy 0, policy_version 36960 (0.0005) [2023-07-07 16:33:14,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8844.6). Total num frames: 18952192. Throughput: 0: 8773.9. Samples: 18943916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:33:14,506][565952] Avg episode reward: [(0, '3755.749')] [2023-07-07 16:33:15,582][566410] Updated weights for policy 0, policy_version 37040 (0.0005) [2023-07-07 16:33:19,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8844.6). Total num frames: 18997248. Throughput: 0: 8782.1. Samples: 18995192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:33:19,506][565952] Avg episode reward: [(0, '4143.605')] [2023-07-07 16:33:20,194][566410] Updated weights for policy 0, policy_version 37120 (0.0006) [2023-07-07 16:33:24,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8858.5). Total num frames: 19042304. Throughput: 0: 8736.7. Samples: 19021824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:33:24,506][565952] Avg episode reward: [(0, '4011.079')] [2023-07-07 16:33:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000037192_19042304.pth... [2023-07-07 16:33:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000036688_18784256.pth [2023-07-07 16:33:24,703][566410] Updated weights for policy 0, policy_version 37200 (0.0005) [2023-07-07 16:33:29,106][566410] Updated weights for policy 0, policy_version 37280 (0.0005) [2023-07-07 16:33:29,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8806.4, 300 sec: 8858.5). Total num frames: 19087360. Throughput: 0: 8736.1. Samples: 19076836. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:33:29,506][565952] Avg episode reward: [(0, '4439.908')] [2023-07-07 16:33:33,514][566410] Updated weights for policy 0, policy_version 37360 (0.0005) [2023-07-07 16:33:34,506][565952] Fps is (10 sec: 9420.8, 60 sec: 8874.7, 300 sec: 8872.4). Total num frames: 19136512. Throughput: 0: 8789.7. Samples: 19132376. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:33:34,506][565952] Avg episode reward: [(0, '3719.911')] [2023-07-07 16:33:38,287][566410] Updated weights for policy 0, policy_version 37440 (0.0005) [2023-07-07 16:33:39,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8858.5). Total num frames: 19177472. Throughput: 0: 8786.6. Samples: 19157480. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:33:39,506][565952] Avg episode reward: [(0, '3298.962')] [2023-07-07 16:33:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000037456_19177472.pth... [2023-07-07 16:33:39,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000036936_18911232.pth [2023-07-07 16:33:42,877][566410] Updated weights for policy 0, policy_version 37520 (0.0005) [2023-07-07 16:33:44,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8858.5). Total num frames: 19222528. Throughput: 0: 8834.9. Samples: 19210428. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:33:44,506][565952] Avg episode reward: [(0, '3033.359')] [2023-07-07 16:33:47,474][566410] Updated weights for policy 0, policy_version 37600 (0.0005) [2023-07-07 16:33:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8858.5). Total num frames: 19267584. Throughput: 0: 8878.6. Samples: 19263500. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:33:49,507][565952] Avg episode reward: [(0, '3636.282')] [2023-07-07 16:33:52,210][566410] Updated weights for policy 0, policy_version 37680 (0.0005) [2023-07-07 16:33:54,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8858.5). Total num frames: 19308544. Throughput: 0: 8879.7. Samples: 19290072. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:33:54,506][565952] Avg episode reward: [(0, '4035.286')] [2023-07-07 16:33:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000037712_19308544.pth... [2023-07-07 16:33:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000037192_19042304.pth [2023-07-07 16:33:57,103][566410] Updated weights for policy 0, policy_version 37760 (0.0005) [2023-07-07 16:33:59,506][565952] Fps is (10 sec: 8192.1, 60 sec: 8806.4, 300 sec: 8858.5). Total num frames: 19349504. Throughput: 0: 8820.6. Samples: 19340840. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:33:59,506][565952] Avg episode reward: [(0, '3920.988')] [2023-07-07 16:34:01,894][566410] Updated weights for policy 0, policy_version 37840 (0.0005) [2023-07-07 16:34:04,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8858.5). Total num frames: 19394560. Throughput: 0: 8816.3. Samples: 19391928. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:34:04,506][565952] Avg episode reward: [(0, '3406.568')] [2023-07-07 16:34:06,767][566410] Updated weights for policy 0, policy_version 37920 (0.0005) [2023-07-07 16:34:09,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8738.1, 300 sec: 8844.6). Total num frames: 19435520. Throughput: 0: 8773.2. Samples: 19416620. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:34:09,506][565952] Avg episode reward: [(0, '3810.661')] [2023-07-07 16:34:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000037960_19435520.pth... [2023-07-07 16:34:09,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000037456_19177472.pth [2023-07-07 16:34:11,414][566410] Updated weights for policy 0, policy_version 38000 (0.0005) [2023-07-07 16:34:14,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8844.6). Total num frames: 19480576. Throughput: 0: 8738.7. Samples: 19470076. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-07 16:34:14,506][565952] Avg episode reward: [(0, '3956.073')] [2023-07-07 16:34:15,995][566410] Updated weights for policy 0, policy_version 38080 (0.0005) [2023-07-07 16:34:19,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8844.6). Total num frames: 19525632. Throughput: 0: 8729.9. Samples: 19525220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:34:19,507][565952] Avg episode reward: [(0, '4184.842')] [2023-07-07 16:34:20,490][566410] Updated weights for policy 0, policy_version 38160 (0.0005) [2023-07-07 16:34:24,506][565952] Fps is (10 sec: 9011.0, 60 sec: 8806.4, 300 sec: 8844.6). Total num frames: 19570688. Throughput: 0: 8728.9. Samples: 19550280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:34:24,507][565952] Avg episode reward: [(0, '3674.105')] [2023-07-07 16:34:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000038224_19570688.pth... [2023-07-07 16:34:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000037712_19308544.pth [2023-07-07 16:34:25,228][566410] Updated weights for policy 0, policy_version 38240 (0.0005) [2023-07-07 16:34:29,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8844.6). Total num frames: 19615744. Throughput: 0: 8733.4. Samples: 19603432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:34:29,506][565952] Avg episode reward: [(0, '3577.116')] [2023-07-07 16:34:29,817][566410] Updated weights for policy 0, policy_version 38320 (0.0006) [2023-07-07 16:34:34,506][565952] Fps is (10 sec: 8601.7, 60 sec: 8669.9, 300 sec: 8844.6). Total num frames: 19656704. Throughput: 0: 8724.0. Samples: 19656080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:34:34,506][565952] Avg episode reward: [(0, '3933.152')] [2023-07-07 16:34:34,609][566410] Updated weights for policy 0, policy_version 38400 (0.0006) [2023-07-07 16:34:39,060][566410] Updated weights for policy 0, policy_version 38480 (0.0005) [2023-07-07 16:34:39,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8738.1, 300 sec: 8844.6). Total num frames: 19701760. Throughput: 0: 8695.5. Samples: 19681372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:34:39,507][565952] Avg episode reward: [(0, '4026.845')] [2023-07-07 16:34:39,531][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000038488_19705856.pth... [2023-07-07 16:34:39,533][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000037960_19435520.pth [2023-07-07 16:34:43,775][566410] Updated weights for policy 0, policy_version 38560 (0.0006) [2023-07-07 16:34:44,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8830.7). Total num frames: 19746816. Throughput: 0: 8769.3. Samples: 19735460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:34:44,506][565952] Avg episode reward: [(0, '3621.092')] [2023-07-07 16:34:48,306][566410] Updated weights for policy 0, policy_version 38640 (0.0005) [2023-07-07 16:34:49,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8738.2, 300 sec: 8830.7). Total num frames: 19791872. Throughput: 0: 8836.4. Samples: 19789564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:34:49,506][565952] Avg episode reward: [(0, '3949.315')] [2023-07-07 16:34:52,885][566410] Updated weights for policy 0, policy_version 38720 (0.0005) [2023-07-07 16:34:54,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8830.7). Total num frames: 19836928. Throughput: 0: 8886.5. Samples: 19816512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:34:54,506][565952] Avg episode reward: [(0, '4279.597')] [2023-07-07 16:34:54,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000038744_19836928.pth... [2023-07-07 16:34:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000038224_19570688.pth [2023-07-07 16:34:57,372][566410] Updated weights for policy 0, policy_version 38800 (0.0006) [2023-07-07 16:34:59,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8874.7, 300 sec: 8830.7). Total num frames: 19881984. Throughput: 0: 8914.1. Samples: 19871212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:34:59,506][565952] Avg episode reward: [(0, '3876.343')] [2023-07-07 16:35:01,772][566410] Updated weights for policy 0, policy_version 38880 (0.0005) [2023-07-07 16:35:04,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8874.7, 300 sec: 8830.7). Total num frames: 19927040. Throughput: 0: 8925.0. Samples: 19926844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:35:04,506][565952] Avg episode reward: [(0, '4204.964')] [2023-07-07 16:35:06,365][566410] Updated weights for policy 0, policy_version 38960 (0.0005) [2023-07-07 16:35:09,506][565952] Fps is (10 sec: 9420.9, 60 sec: 9011.2, 300 sec: 8844.6). Total num frames: 19976192. Throughput: 0: 8930.6. Samples: 19952156. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:35:09,506][565952] Avg episode reward: [(0, '3965.766')] [2023-07-07 16:35:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000039016_19976192.pth... [2023-07-07 16:35:09,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000038488_19705856.pth [2023-07-07 16:35:10,664][566410] Updated weights for policy 0, policy_version 39040 (0.0005) [2023-07-07 16:35:14,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8942.9, 300 sec: 8830.7). Total num frames: 20017152. Throughput: 0: 8990.9. Samples: 20008020. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:35:14,506][565952] Avg episode reward: [(0, '4380.895')] [2023-07-07 16:35:15,403][566410] Updated weights for policy 0, policy_version 39120 (0.0005) [2023-07-07 16:35:19,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 8844.6). Total num frames: 20066304. Throughput: 0: 9038.9. Samples: 20062832. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:35:19,506][565952] Avg episode reward: [(0, '4223.290')] [2023-07-07 16:35:19,720][566410] Updated weights for policy 0, policy_version 39200 (0.0005) [2023-07-07 16:35:24,337][566410] Updated weights for policy 0, policy_version 39280 (0.0005) [2023-07-07 16:35:24,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9011.2, 300 sec: 8844.6). Total num frames: 20111360. Throughput: 0: 9100.3. Samples: 20090884. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:35:24,506][565952] Avg episode reward: [(0, '3682.784')] [2023-07-07 16:35:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000039280_20111360.pth... [2023-07-07 16:35:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000038744_19836928.pth [2023-07-07 16:35:29,221][566410] Updated weights for policy 0, policy_version 39360 (0.0005) [2023-07-07 16:35:29,506][565952] Fps is (10 sec: 8601.6, 60 sec: 8942.9, 300 sec: 8816.8). Total num frames: 20152320. Throughput: 0: 8999.9. Samples: 20140456. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:35:29,506][565952] Avg episode reward: [(0, '4001.282')] [2023-07-07 16:35:33,738][566410] Updated weights for policy 0, policy_version 39440 (0.0005) [2023-07-07 16:35:34,506][565952] Fps is (10 sec: 8601.6, 60 sec: 9011.2, 300 sec: 8830.7). Total num frames: 20197376. Throughput: 0: 9014.3. Samples: 20195208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:35:34,506][565952] Avg episode reward: [(0, '4194.788')] [2023-07-07 16:35:38,236][566410] Updated weights for policy 0, policy_version 39520 (0.0005) [2023-07-07 16:35:39,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 8830.7). Total num frames: 20242432. Throughput: 0: 9011.4. Samples: 20222024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:35:39,506][565952] Avg episode reward: [(0, '4139.414')] [2023-07-07 16:35:39,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000039536_20242432.pth... [2023-07-07 16:35:39,510][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000039016_19976192.pth [2023-07-07 16:35:42,658][566410] Updated weights for policy 0, policy_version 39600 (0.0005) [2023-07-07 16:35:44,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 8858.5). Total num frames: 20291584. Throughput: 0: 9048.3. Samples: 20278384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:35:44,507][565952] Avg episode reward: [(0, '4333.407')] [2023-07-07 16:35:47,183][566410] Updated weights for policy 0, policy_version 39680 (0.0005) [2023-07-07 16:35:49,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9079.5, 300 sec: 8872.3). Total num frames: 20336640. Throughput: 0: 9017.0. Samples: 20332608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:35:49,507][565952] Avg episode reward: [(0, '3964.357')] [2023-07-07 16:35:51,498][566410] Updated weights for policy 0, policy_version 39760 (0.0005) [2023-07-07 16:35:54,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 8858.5). Total num frames: 20381696. Throughput: 0: 9090.5. Samples: 20361228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:35:54,506][565952] Avg episode reward: [(0, '3737.016')] [2023-07-07 16:35:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000039808_20381696.pth... [2023-07-07 16:35:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000039280_20111360.pth [2023-07-07 16:35:56,032][566410] Updated weights for policy 0, policy_version 39840 (0.0005) [2023-07-07 16:35:59,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 8858.5). Total num frames: 20426752. Throughput: 0: 9076.1. Samples: 20416444. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:35:59,506][565952] Avg episode reward: [(0, '2934.165')] [2023-07-07 16:36:00,584][566410] Updated weights for policy 0, policy_version 39920 (0.0005) [2023-07-07 16:36:04,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 8872.4). Total num frames: 20471808. Throughput: 0: 8998.8. Samples: 20467776. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:36:04,506][565952] Avg episode reward: [(0, '3529.051')] [2023-07-07 16:36:05,241][566410] Updated weights for policy 0, policy_version 40000 (0.0005) [2023-07-07 16:36:09,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 8872.4). Total num frames: 20516864. Throughput: 0: 9003.7. Samples: 20496052. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:36:09,506][565952] Avg episode reward: [(0, '4020.300')] [2023-07-07 16:36:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000040072_20516864.pth... [2023-07-07 16:36:09,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000039536_20242432.pth [2023-07-07 16:36:09,887][566410] Updated weights for policy 0, policy_version 40080 (0.0005) [2023-07-07 16:36:14,334][566410] Updated weights for policy 0, policy_version 40160 (0.0005) [2023-07-07 16:36:14,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 8872.4). Total num frames: 20561920. Throughput: 0: 9092.0. Samples: 20549596. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:36:14,506][565952] Avg episode reward: [(0, '3279.856')] [2023-07-07 16:36:18,936][566410] Updated weights for policy 0, policy_version 40240 (0.0005) [2023-07-07 16:36:19,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 8886.2). Total num frames: 20606976. Throughput: 0: 9060.8. Samples: 20602944. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:36:19,506][565952] Avg episode reward: [(0, '3811.167')] [2023-07-07 16:36:23,614][566410] Updated weights for policy 0, policy_version 40320 (0.0006) [2023-07-07 16:36:24,506][565952] Fps is (10 sec: 8601.5, 60 sec: 8942.9, 300 sec: 8872.3). Total num frames: 20647936. Throughput: 0: 9017.3. Samples: 20627804. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:36:24,506][565952] Avg episode reward: [(0, '4087.653')] [2023-07-07 16:36:24,528][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000040336_20652032.pth... [2023-07-07 16:36:24,530][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000039808_20381696.pth [2023-07-07 16:36:28,362][566410] Updated weights for policy 0, policy_version 40400 (0.0005) [2023-07-07 16:36:29,506][565952] Fps is (10 sec: 8601.6, 60 sec: 9011.2, 300 sec: 8872.4). Total num frames: 20692992. Throughput: 0: 8942.0. Samples: 20680776. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:36:29,506][565952] Avg episode reward: [(0, '4003.813')] [2023-07-07 16:36:32,831][566410] Updated weights for policy 0, policy_version 40480 (0.0005) [2023-07-07 16:36:34,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 8872.4). Total num frames: 20738048. Throughput: 0: 8963.3. Samples: 20735956. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:36:34,506][565952] Avg episode reward: [(0, '3650.511')] [2023-07-07 16:36:37,339][566410] Updated weights for policy 0, policy_version 40560 (0.0005) [2023-07-07 16:36:39,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 8900.1). Total num frames: 20787200. Throughput: 0: 8938.6. Samples: 20763468. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:36:39,506][565952] Avg episode reward: [(0, '3791.787')] [2023-07-07 16:36:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000040600_20787200.pth... [2023-07-07 16:36:39,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000040072_20516864.pth [2023-07-07 16:36:41,720][566410] Updated weights for policy 0, policy_version 40640 (0.0005) [2023-07-07 16:36:44,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9011.2, 300 sec: 8886.2). Total num frames: 20832256. Throughput: 0: 8958.3. Samples: 20819568. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:36:44,506][565952] Avg episode reward: [(0, '4078.404')] [2023-07-07 16:36:46,179][566410] Updated weights for policy 0, policy_version 40720 (0.0005) [2023-07-07 16:36:49,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 8900.1). Total num frames: 20877312. Throughput: 0: 9020.3. Samples: 20873688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:36:49,506][565952] Avg episode reward: [(0, '4045.107')] [2023-07-07 16:36:50,704][566410] Updated weights for policy 0, policy_version 40800 (0.0005) [2023-07-07 16:36:54,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 8900.1). Total num frames: 20922368. Throughput: 0: 9017.7. Samples: 20901848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:36:54,506][565952] Avg episode reward: [(0, '4061.586')] [2023-07-07 16:36:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000040864_20922368.pth... [2023-07-07 16:36:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000040336_20652032.pth [2023-07-07 16:36:55,096][566410] Updated weights for policy 0, policy_version 40880 (0.0005) [2023-07-07 16:36:59,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 8914.0). Total num frames: 20967424. Throughput: 0: 9031.2. Samples: 20956000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:36:59,506][565952] Avg episode reward: [(0, '4259.422')] [2023-07-07 16:36:59,750][566410] Updated weights for policy 0, policy_version 40960 (0.0005) [2023-07-07 16:37:04,349][566410] Updated weights for policy 0, policy_version 41040 (0.0005) [2023-07-07 16:37:04,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 8914.0). Total num frames: 21012480. Throughput: 0: 9020.4. Samples: 21008860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:37:04,507][565952] Avg episode reward: [(0, '4440.061')] [2023-07-07 16:37:08,811][566410] Updated weights for policy 0, policy_version 41120 (0.0005) [2023-07-07 16:37:09,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 8914.0). Total num frames: 21057536. Throughput: 0: 9095.9. Samples: 21037120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:37:09,506][565952] Avg episode reward: [(0, '3909.062')] [2023-07-07 16:37:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000041128_21057536.pth... [2023-07-07 16:37:09,511][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000040600_20787200.pth [2023-07-07 16:37:13,242][566410] Updated weights for policy 0, policy_version 41200 (0.0005) [2023-07-07 16:37:14,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 8914.0). Total num frames: 21102592. Throughput: 0: 9133.2. Samples: 21091772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:37:14,506][565952] Avg episode reward: [(0, '4018.886')] [2023-07-07 16:37:17,620][566410] Updated weights for policy 0, policy_version 41280 (0.0004) [2023-07-07 16:37:19,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 8927.9). Total num frames: 21151744. Throughput: 0: 9146.8. Samples: 21147564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:37:19,506][565952] Avg episode reward: [(0, '4272.676')] [2023-07-07 16:37:22,130][566410] Updated weights for policy 0, policy_version 41360 (0.0005) [2023-07-07 16:37:24,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 8941.8). Total num frames: 21196800. Throughput: 0: 9156.6. Samples: 21175512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:37:24,506][565952] Avg episode reward: [(0, '4426.961')] [2023-07-07 16:37:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000041400_21196800.pth... [2023-07-07 16:37:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000040864_20922368.pth [2023-07-07 16:37:26,659][566410] Updated weights for policy 0, policy_version 41440 (0.0005) [2023-07-07 16:37:29,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9147.7, 300 sec: 8941.8). Total num frames: 21241856. Throughput: 0: 9117.4. Samples: 21229852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:37:29,506][565952] Avg episode reward: [(0, '4136.606')] [2023-07-07 16:37:30,770][566410] Updated weights for policy 0, policy_version 41520 (0.0005) [2023-07-07 16:37:34,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9216.0, 300 sec: 8955.7). Total num frames: 21291008. Throughput: 0: 9184.3. Samples: 21286984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:37:34,506][565952] Avg episode reward: [(0, '3859.567')] [2023-07-07 16:37:35,126][566410] Updated weights for policy 0, policy_version 41600 (0.0005) [2023-07-07 16:37:39,466][566410] Updated weights for policy 0, policy_version 41680 (0.0005) [2023-07-07 16:37:39,506][565952] Fps is (10 sec: 9830.3, 60 sec: 9216.0, 300 sec: 8969.5). Total num frames: 21340160. Throughput: 0: 9195.6. Samples: 21315648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:37:39,507][565952] Avg episode reward: [(0, '4245.455')] [2023-07-07 16:37:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000041680_21340160.pth... [2023-07-07 16:37:39,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000041128_21057536.pth [2023-07-07 16:37:44,040][566410] Updated weights for policy 0, policy_version 41760 (0.0005) [2023-07-07 16:37:44,506][565952] Fps is (10 sec: 9420.9, 60 sec: 9216.0, 300 sec: 8969.5). Total num frames: 21385216. Throughput: 0: 9222.4. Samples: 21371008. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:37:44,506][565952] Avg episode reward: [(0, '3627.695')] [2023-07-07 16:37:48,480][566410] Updated weights for policy 0, policy_version 41840 (0.0005) [2023-07-07 16:37:49,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 8983.4). Total num frames: 21430272. Throughput: 0: 9285.4. Samples: 21426704. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:37:49,506][565952] Avg episode reward: [(0, '3782.755')] [2023-07-07 16:37:52,959][566410] Updated weights for policy 0, policy_version 41920 (0.0006) [2023-07-07 16:37:54,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 8997.3). Total num frames: 21475328. Throughput: 0: 9282.8. Samples: 21454848. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:37:54,507][565952] Avg episode reward: [(0, '4295.287')] [2023-07-07 16:37:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000041944_21475328.pth... [2023-07-07 16:37:54,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000041400_21196800.pth [2023-07-07 16:37:57,377][566410] Updated weights for policy 0, policy_version 42000 (0.0005) [2023-07-07 16:37:59,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 8997.3). Total num frames: 21520384. Throughput: 0: 9287.1. Samples: 21509692. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:37:59,506][565952] Avg episode reward: [(0, '3889.037')] [2023-07-07 16:38:01,817][566410] Updated weights for policy 0, policy_version 42080 (0.0005) [2023-07-07 16:38:04,506][565952] Fps is (10 sec: 9420.9, 60 sec: 9284.3, 300 sec: 9011.2). Total num frames: 21569536. Throughput: 0: 9286.3. Samples: 21565448. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-07 16:38:04,506][565952] Avg episode reward: [(0, '4235.523')] [2023-07-07 16:38:06,218][566410] Updated weights for policy 0, policy_version 42160 (0.0005) [2023-07-07 16:38:09,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9025.1). Total num frames: 21614592. Throughput: 0: 9262.9. Samples: 21592344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:38:09,506][565952] Avg episode reward: [(0, '4241.389')] [2023-07-07 16:38:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000042216_21614592.pth... [2023-07-07 16:38:09,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000041680_21340160.pth [2023-07-07 16:38:10,618][566410] Updated weights for policy 0, policy_version 42240 (0.0005) [2023-07-07 16:38:14,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9025.1). Total num frames: 21659648. Throughput: 0: 9289.2. Samples: 21647868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:38:14,506][565952] Avg episode reward: [(0, '3767.382')] [2023-07-07 16:38:15,199][566410] Updated weights for policy 0, policy_version 42320 (0.0006) [2023-07-07 16:38:19,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9216.0, 300 sec: 9025.1). Total num frames: 21704704. Throughput: 0: 9229.2. Samples: 21702296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:38:19,506][565952] Avg episode reward: [(0, '4241.191')] [2023-07-07 16:38:19,823][566410] Updated weights for policy 0, policy_version 42400 (0.0005) [2023-07-07 16:38:24,187][566410] Updated weights for policy 0, policy_version 42480 (0.0006) [2023-07-07 16:38:24,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9216.0, 300 sec: 9025.1). Total num frames: 21749760. Throughput: 0: 9178.5. Samples: 21728680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:38:24,506][565952] Avg episode reward: [(0, '4158.845')] [2023-07-07 16:38:24,508][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000042480_21749760.pth... [2023-07-07 16:38:24,510][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000041944_21475328.pth [2023-07-07 16:38:28,899][566410] Updated weights for policy 0, policy_version 42560 (0.0005) [2023-07-07 16:38:29,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9011.2). Total num frames: 21794816. Throughput: 0: 9142.5. Samples: 21782420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:38:29,506][565952] Avg episode reward: [(0, '3984.482')] [2023-07-07 16:38:33,280][566410] Updated weights for policy 0, policy_version 42640 (0.0006) [2023-07-07 16:38:34,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9147.7, 300 sec: 9025.1). Total num frames: 21839872. Throughput: 0: 9150.8. Samples: 21838492. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:38:34,506][565952] Avg episode reward: [(0, '4140.439')] [2023-07-07 16:38:37,565][566410] Updated weights for policy 0, policy_version 42720 (0.0005) [2023-07-07 16:38:39,506][565952] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 9039.0). Total num frames: 21889024. Throughput: 0: 9168.1. Samples: 21867412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:38:39,506][565952] Avg episode reward: [(0, '4138.131')] [2023-07-07 16:38:39,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000042752_21889024.pth... [2023-07-07 16:38:39,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000042216_21614592.pth [2023-07-07 16:38:42,070][566410] Updated weights for policy 0, policy_version 42800 (0.0005) [2023-07-07 16:38:44,506][565952] Fps is (10 sec: 9830.4, 60 sec: 9216.0, 300 sec: 9052.9). Total num frames: 21938176. Throughput: 0: 9184.5. Samples: 21922996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:38:44,506][565952] Avg episode reward: [(0, '4406.825')] [2023-07-07 16:38:46,180][566410] Updated weights for policy 0, policy_version 42880 (0.0005) [2023-07-07 16:38:49,506][565952] Fps is (10 sec: 9420.9, 60 sec: 9216.0, 300 sec: 9066.7). Total num frames: 21983232. Throughput: 0: 9227.5. Samples: 21980684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:38:49,506][565952] Avg episode reward: [(0, '3955.514')] [2023-07-07 16:38:50,620][566410] Updated weights for policy 0, policy_version 42960 (0.0005) [2023-07-07 16:38:54,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9094.5). Total num frames: 22032384. Throughput: 0: 9242.5. Samples: 22008256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:38:54,506][565952] Avg episode reward: [(0, '4252.507')] [2023-07-07 16:38:54,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000043032_22032384.pth... [2023-07-07 16:38:54,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000042480_21749760.pth [2023-07-07 16:38:54,858][566410] Updated weights for policy 0, policy_version 43040 (0.0005) [2023-07-07 16:38:59,420][566410] Updated weights for policy 0, policy_version 43120 (0.0005) [2023-07-07 16:38:59,506][565952] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9094.5). Total num frames: 22077440. Throughput: 0: 9256.7. Samples: 22064420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:38:59,506][565952] Avg episode reward: [(0, '3962.369')] [2023-07-07 16:39:03,890][566410] Updated weights for policy 0, policy_version 43200 (0.0005) [2023-07-07 16:39:04,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9108.4). Total num frames: 22122496. Throughput: 0: 9248.3. Samples: 22118472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:39:04,507][565952] Avg episode reward: [(0, '4101.918')] [2023-07-07 16:39:08,550][566410] Updated weights for policy 0, policy_version 43280 (0.0005) [2023-07-07 16:39:09,506][565952] Fps is (10 sec: 8601.6, 60 sec: 9147.8, 300 sec: 9094.5). Total num frames: 22163456. Throughput: 0: 9235.1. Samples: 22144260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:39:09,506][565952] Avg episode reward: [(0, '4185.421')] [2023-07-07 16:39:09,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000043296_22167552.pth... [2023-07-07 16:39:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000042752_21889024.pth [2023-07-07 16:39:13,214][566410] Updated weights for policy 0, policy_version 43360 (0.0005) [2023-07-07 16:39:14,506][565952] Fps is (10 sec: 8601.6, 60 sec: 9147.7, 300 sec: 9094.5). Total num frames: 22208512. Throughput: 0: 9231.3. Samples: 22197828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:39:14,506][565952] Avg episode reward: [(0, '4135.064')] [2023-07-07 16:39:17,817][566410] Updated weights for policy 0, policy_version 43440 (0.0006) [2023-07-07 16:39:19,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9147.7, 300 sec: 9094.5). Total num frames: 22253568. Throughput: 0: 9189.6. Samples: 22252024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:39:19,506][565952] Avg episode reward: [(0, '4350.914')] [2023-07-07 16:39:22,429][566410] Updated weights for policy 0, policy_version 43520 (0.0005) [2023-07-07 16:39:24,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9147.7, 300 sec: 9094.5). Total num frames: 22298624. Throughput: 0: 9127.7. Samples: 22278160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:39:24,506][565952] Avg episode reward: [(0, '4492.010')] [2023-07-07 16:39:24,510][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000043552_22298624.pth... [2023-07-07 16:39:24,513][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000043032_22032384.pth [2023-07-07 16:39:26,946][566410] Updated weights for policy 0, policy_version 43600 (0.0005) [2023-07-07 16:39:29,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9147.7, 300 sec: 9108.4). Total num frames: 22343680. Throughput: 0: 9083.0. Samples: 22331732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-07 16:39:29,506][565952] Avg episode reward: [(0, '3818.585')] [2023-07-07 16:39:31,602][566410] Updated weights for policy 0, policy_version 43680 (0.0005) [2023-07-07 16:39:34,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9147.7, 300 sec: 9108.4). Total num frames: 22388736. Throughput: 0: 8989.1. Samples: 22385196. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:39:34,506][565952] Avg episode reward: [(0, '4511.160')] [2023-07-07 16:39:36,226][566410] Updated weights for policy 0, policy_version 43760 (0.0005) [2023-07-07 16:39:39,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9108.4). Total num frames: 22433792. Throughput: 0: 8986.1. Samples: 22412628. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:39:39,506][565952] Avg episode reward: [(0, '4349.358')] [2023-07-07 16:39:39,593][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000043816_22433792.pth... [2023-07-07 16:39:39,596][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000043296_22167552.pth [2023-07-07 16:39:40,714][566410] Updated weights for policy 0, policy_version 43840 (0.0005) [2023-07-07 16:39:44,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9108.4). Total num frames: 22478848. Throughput: 0: 8954.0. Samples: 22467352. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:39:44,506][565952] Avg episode reward: [(0, '4345.118')] [2023-07-07 16:39:45,134][566410] Updated weights for policy 0, policy_version 43920 (0.0005) [2023-07-07 16:39:49,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 9108.4). Total num frames: 22523904. Throughput: 0: 8936.4. Samples: 22520612. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:39:49,506][565952] Avg episode reward: [(0, '3447.438')] [2023-07-07 16:39:49,695][566410] Updated weights for policy 0, policy_version 44000 (0.0005) [2023-07-07 16:39:54,262][566410] Updated weights for policy 0, policy_version 44080 (0.0005) [2023-07-07 16:39:54,506][565952] Fps is (10 sec: 9011.1, 60 sec: 8942.9, 300 sec: 9108.4). Total num frames: 22568960. Throughput: 0: 8982.8. Samples: 22548488. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-07 16:39:54,506][565952] Avg episode reward: [(0, '3710.826')] [2023-07-07 16:39:54,514][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000044080_22568960.pth... [2023-07-07 16:39:54,517][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000043552_22298624.pth [2023-07-07 16:39:58,911][566410] Updated weights for policy 0, policy_version 44160 (0.0005) [2023-07-07 16:39:59,506][565952] Fps is (10 sec: 9011.2, 60 sec: 8942.9, 300 sec: 9108.4). Total num frames: 22614016. Throughput: 0: 8973.4. Samples: 22601632. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:39:59,506][565952] Avg episode reward: [(0, '4069.492')] [2023-07-07 16:40:03,337][566410] Updated weights for policy 0, policy_version 44240 (0.0005) [2023-07-07 16:40:04,506][565952] Fps is (10 sec: 9011.3, 60 sec: 8942.9, 300 sec: 9094.5). Total num frames: 22659072. Throughput: 0: 8989.9. Samples: 22656572. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:40:04,506][565952] Avg episode reward: [(0, '4373.032')] [2023-07-07 16:40:07,707][566410] Updated weights for policy 0, policy_version 44320 (0.0005) [2023-07-07 16:40:09,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9108.4). Total num frames: 22704128. Throughput: 0: 9054.4. Samples: 22685608. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:40:09,506][565952] Avg episode reward: [(0, '3907.949')] [2023-07-07 16:40:09,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000044344_22704128.pth... [2023-07-07 16:40:09,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000043816_22433792.pth [2023-07-07 16:40:12,335][566410] Updated weights for policy 0, policy_version 44400 (0.0005) [2023-07-07 16:40:14,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9094.5). Total num frames: 22749184. Throughput: 0: 9040.1. Samples: 22738536. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:40:14,507][565952] Avg episode reward: [(0, '4245.779')] [2023-07-07 16:40:16,790][566410] Updated weights for policy 0, policy_version 44480 (0.0005) [2023-07-07 16:40:19,506][565952] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 9094.5). Total num frames: 22794240. Throughput: 0: 9070.8. Samples: 22793384. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:40:19,507][565952] Avg episode reward: [(0, '4075.496')] [2023-07-07 16:40:21,576][566410] Updated weights for policy 0, policy_version 44560 (0.0005) [2023-07-07 16:40:24,506][565952] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9108.4). Total num frames: 22839296. Throughput: 0: 9022.6. Samples: 22818648. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-07 16:40:24,506][565952] Avg episode reward: [(0, '4335.462')] [2023-07-07 16:40:24,509][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000044608_22839296.pth... [2023-07-07 16:40:24,512][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000044080_22568960.pth [2023-07-07 16:40:26,155][566410] Updated weights for policy 0, policy_version 44640 (0.0005) [2023-07-07 16:40:29,506][565952] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 9108.4). Total num frames: 22884352. Throughput: 0: 8991.9. Samples: 22871988. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-07 16:40:29,506][565952] Avg episode reward: [(0, '4156.804')] [2023-07-07 16:40:30,087][565952] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 565952], exiting... [2023-07-07 16:40:30,088][565952] Runner profile tree view: main_loop: 2612.4920 [2023-07-07 16:40:30,088][566416] Stopping RolloutWorker_w5... [2023-07-07 16:40:30,088][565952] Collected {0: 22888448}, FPS: 8761.2 [2023-07-07 16:40:30,088][566416] Loop rollout_proc5_evt_loop terminating... [2023-07-07 16:40:30,088][566397] Stopping Batcher_0... [2023-07-07 16:40:30,089][566397] Loop batcher_evt_loop terminating... [2023-07-07 16:40:30,089][566397] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000044704_22888448.pth... [2023-07-07 16:40:30,090][566415] Stopping RolloutWorker_w4... [2023-07-07 16:40:30,090][566417] Stopping RolloutWorker_w6... [2023-07-07 16:40:30,090][566415] Loop rollout_proc4_evt_loop terminating... [2023-07-07 16:40:30,090][566418] Stopping RolloutWorker_w7... [2023-07-07 16:40:30,090][566417] Loop rollout_proc6_evt_loop terminating... [2023-07-07 16:40:30,090][566418] Loop rollout_proc7_evt_loop terminating... [2023-07-07 16:40:30,091][566413] Stopping RolloutWorker_w2... [2023-07-07 16:40:30,091][566413] Loop rollout_proc2_evt_loop terminating... [2023-07-07 16:40:30,091][566397] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000044344_22704128.pth [2023-07-07 16:40:30,092][566397] Stopping LearnerWorker_p0... [2023-07-07 16:40:30,092][566414] Stopping RolloutWorker_w3... [2023-07-07 16:40:30,092][566397] Loop learner_proc0_evt_loop terminating... [2023-07-07 16:40:30,092][566414] Loop rollout_proc3_evt_loop terminating... [2023-07-07 16:40:30,092][566411] Stopping RolloutWorker_w0... [2023-07-07 16:40:30,092][566411] Loop rollout_proc0_evt_loop terminating... [2023-07-07 16:40:30,093][566412] Stopping RolloutWorker_w1... [2023-07-07 16:40:30,093][566412] Loop rollout_proc1_evt_loop terminating... [2023-07-07 16:40:30,115][566410] Weights refcount: 2 0 [2023-07-07 16:40:30,116][566410] Stopping InferenceWorker_p0-w0... [2023-07-07 16:40:30,116][566410] Loop inference_proc0-0_evt_loop terminating...