[2023-07-16 19:19:40,000][213260] Saving configuration to /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/config.json... [2023-07-16 19:19:40,016][213260] Rollout worker 0 uses device cpu [2023-07-16 19:19:40,016][213260] Rollout worker 1 uses device cpu [2023-07-16 19:19:40,016][213260] Rollout worker 2 uses device cpu [2023-07-16 19:19:40,016][213260] Rollout worker 3 uses device cpu [2023-07-16 19:19:40,016][213260] Rollout worker 4 uses device cpu [2023-07-16 19:19:40,016][213260] Rollout worker 5 uses device cpu [2023-07-16 19:19:40,017][213260] Rollout worker 6 uses device cpu [2023-07-16 19:19:40,017][213260] Rollout worker 7 uses device cpu [2023-07-16 19:19:40,017][213260] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 [2023-07-16 19:19:40,027][213260] InferenceWorker_p0-w0: min num requests: 2 [2023-07-16 19:19:40,044][213260] Starting all processes... [2023-07-16 19:19:40,045][213260] Starting process learner_proc0 [2023-07-16 19:19:40,094][213260] Starting all processes... [2023-07-16 19:19:40,137][213260] Starting process inference_proc0-0 [2023-07-16 19:19:40,146][213260] Starting process rollout_proc0 [2023-07-16 19:19:40,155][213260] Starting process rollout_proc1 [2023-07-16 19:19:40,156][213260] Starting process rollout_proc2 [2023-07-16 19:19:40,156][213260] Starting process rollout_proc3 [2023-07-16 19:19:40,157][213260] Starting process rollout_proc4 [2023-07-16 19:19:40,158][213260] Starting process rollout_proc5 [2023-07-16 19:19:40,158][213260] Starting process rollout_proc6 [2023-07-16 19:19:40,158][213260] Starting process rollout_proc7 [2023-07-16 19:19:41,883][213503] Starting seed is not provided [2023-07-16 19:19:41,884][213503] Initializing actor-critic model on device cpu [2023-07-16 19:19:41,884][213503] RunningMeanStd input shape: (39,) [2023-07-16 19:19:41,884][213503] RunningMeanStd input shape: (1,) [2023-07-16 19:19:41,939][213503] Created Actor Critic model with architecture: [2023-07-16 19:19:41,940][213503] 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) ) ) [2023-07-16 19:19:42,037][213548] Worker 0 uses CPU cores [0, 1, 2, 3] [2023-07-16 19:19:42,061][213584] Worker 5 uses CPU cores [20, 21, 22, 23] [2023-07-16 19:19:42,235][213503] Using optimizer [2023-07-16 19:19:42,235][213503] No checkpoints found [2023-07-16 19:19:42,236][213503] Did not load from checkpoint, starting from scratch! [2023-07-16 19:19:42,236][213503] Initialized policy 0 weights for model version 0 [2023-07-16 19:19:42,237][213503] LearnerWorker_p0 finished initialization! [2023-07-16 19:19:42,272][213648] Worker 7 uses CPU cores [28, 29, 30, 31] [2023-07-16 19:19:42,290][213616] Worker 6 uses CPU cores [24, 25, 26, 27] [2023-07-16 19:19:42,321][213549] Worker 2 uses CPU cores [8, 9, 10, 11] [2023-07-16 19:19:42,427][213551] Worker 3 uses CPU cores [12, 13, 14, 15] [2023-07-16 19:19:42,503][213552] Worker 4 uses CPU cores [16, 17, 18, 19] [2023-07-16 19:19:42,512][213550] Worker 1 uses CPU cores [4, 5, 6, 7] [2023-07-16 19:19:42,651][213547] RunningMeanStd input shape: (39,) [2023-07-16 19:19:42,651][213547] RunningMeanStd input shape: (1,) [2023-07-16 19:19:42,704][213260] Inference worker 0-0 is ready! [2023-07-16 19:19:42,704][213260] All inference workers are ready! Signal rollout workers to start! [2023-07-16 19:19:43,006][213260] 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) [2023-07-16 19:19:44,112][213552] Decorrelating experience for 0 frames... [2023-07-16 19:19:44,116][213548] Decorrelating experience for 0 frames... [2023-07-16 19:19:44,119][213552] Decorrelating experience for 64 frames... [2023-07-16 19:19:44,123][213548] Decorrelating experience for 64 frames... [2023-07-16 19:19:44,129][213584] Decorrelating experience for 0 frames... [2023-07-16 19:19:44,135][213549] Decorrelating experience for 0 frames... [2023-07-16 19:19:44,137][213584] Decorrelating experience for 64 frames... [2023-07-16 19:19:44,142][213549] Decorrelating experience for 64 frames... [2023-07-16 19:19:44,142][213551] Decorrelating experience for 0 frames... [2023-07-16 19:19:44,143][213550] Decorrelating experience for 0 frames... [2023-07-16 19:19:44,143][213648] Decorrelating experience for 0 frames... [2023-07-16 19:19:44,144][213616] Decorrelating experience for 0 frames... [2023-07-16 19:19:44,149][213551] Decorrelating experience for 64 frames... [2023-07-16 19:19:44,150][213550] Decorrelating experience for 64 frames... [2023-07-16 19:19:44,150][213552] Decorrelating experience for 128 frames... [2023-07-16 19:19:44,150][213648] Decorrelating experience for 64 frames... [2023-07-16 19:19:44,151][213616] Decorrelating experience for 64 frames... [2023-07-16 19:19:44,153][213548] Decorrelating experience for 128 frames... [2023-07-16 19:19:44,168][213584] Decorrelating experience for 128 frames... [2023-07-16 19:19:44,173][213549] Decorrelating experience for 128 frames... [2023-07-16 19:19:44,179][213551] Decorrelating experience for 128 frames... [2023-07-16 19:19:44,180][213550] Decorrelating experience for 128 frames... [2023-07-16 19:19:44,181][213616] Decorrelating experience for 128 frames... [2023-07-16 19:19:44,181][213648] Decorrelating experience for 128 frames... [2023-07-16 19:19:44,209][213552] Decorrelating experience for 192 frames... [2023-07-16 19:19:44,212][213548] Decorrelating experience for 192 frames... [2023-07-16 19:19:44,228][213584] Decorrelating experience for 192 frames... [2023-07-16 19:19:44,231][213549] Decorrelating experience for 192 frames... [2023-07-16 19:19:44,239][213551] Decorrelating experience for 192 frames... [2023-07-16 19:19:44,240][213648] Decorrelating experience for 192 frames... [2023-07-16 19:19:44,240][213616] Decorrelating experience for 192 frames... [2023-07-16 19:19:44,241][213550] Decorrelating experience for 192 frames... [2023-07-16 19:19:45,554][213552] Decorrelating experience for 256 frames... [2023-07-16 19:19:45,556][213548] Decorrelating experience for 256 frames... [2023-07-16 19:19:45,569][213584] Decorrelating experience for 256 frames... [2023-07-16 19:19:45,582][213549] Decorrelating experience for 256 frames... [2023-07-16 19:19:45,587][213550] Decorrelating experience for 256 frames... [2023-07-16 19:19:45,601][213648] Decorrelating experience for 256 frames... [2023-07-16 19:19:45,601][213551] Decorrelating experience for 256 frames... [2023-07-16 19:19:45,603][213616] Decorrelating experience for 256 frames... [2023-07-16 19:19:45,665][213552] Decorrelating experience for 320 frames... [2023-07-16 19:19:45,667][213548] Decorrelating experience for 320 frames... [2023-07-16 19:19:45,680][213584] Decorrelating experience for 320 frames... [2023-07-16 19:19:45,695][213549] Decorrelating experience for 320 frames... [2023-07-16 19:19:45,699][213550] Decorrelating experience for 320 frames... [2023-07-16 19:19:45,713][213648] Decorrelating experience for 320 frames... [2023-07-16 19:19:45,713][213551] Decorrelating experience for 320 frames... [2023-07-16 19:19:45,714][213616] Decorrelating experience for 320 frames... [2023-07-16 19:19:45,808][213548] Decorrelating experience for 384 frames... [2023-07-16 19:19:45,808][213552] Decorrelating experience for 384 frames... [2023-07-16 19:19:45,821][213584] Decorrelating experience for 384 frames... [2023-07-16 19:19:45,835][213549] Decorrelating experience for 384 frames... [2023-07-16 19:19:45,841][213550] Decorrelating experience for 384 frames... [2023-07-16 19:19:45,854][213648] Decorrelating experience for 384 frames... [2023-07-16 19:19:45,855][213551] Decorrelating experience for 384 frames... [2023-07-16 19:19:45,855][213616] Decorrelating experience for 384 frames... [2023-07-16 19:19:45,973][213552] Decorrelating experience for 448 frames... [2023-07-16 19:19:45,973][213548] Decorrelating experience for 448 frames... [2023-07-16 19:19:45,985][213584] Decorrelating experience for 448 frames... [2023-07-16 19:19:45,999][213549] Decorrelating experience for 448 frames... [2023-07-16 19:19:46,007][213550] Decorrelating experience for 448 frames... [2023-07-16 19:19:46,019][213648] Decorrelating experience for 448 frames... [2023-07-16 19:19:46,020][213551] Decorrelating experience for 448 frames... [2023-07-16 19:19:46,022][213616] Decorrelating experience for 448 frames... [2023-07-16 19:19:48,006][213260] Fps is (10 sec: 2457.7, 60 sec: 2457.7, 300 sec: 2457.7). Total num frames: 12288. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-16 19:19:48,007][213260] Avg episode reward: [(0, '3.148')] [2023-07-16 19:19:50,156][213547] Updated weights for policy 0, policy_version 80 (0.0005) [2023-07-16 19:19:53,006][213260] Fps is (10 sec: 7372.9, 60 sec: 7372.9, 300 sec: 7372.9). Total num frames: 73728. Throughput: 0: 6122.1. Samples: 61220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:19:53,007][213260] Avg episode reward: [(0, '6.678')] [2023-07-16 19:19:53,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000144_73728.pth... [2023-07-16 19:19:53,452][213547] Updated weights for policy 0, policy_version 160 (0.0005) [2023-07-16 19:19:56,650][213547] Updated weights for policy 0, policy_version 240 (0.0003) [2023-07-16 19:19:58,006][213260] Fps is (10 sec: 12697.6, 60 sec: 9284.4, 300 sec: 9284.4). Total num frames: 139264. Throughput: 0: 9196.1. Samples: 137940. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-16 19:19:58,007][213260] Avg episode reward: [(0, '9.853')] [2023-07-16 19:19:58,007][213503] Saving new best policy, reward=9.853! [2023-07-16 19:19:59,679][213547] Updated weights for policy 0, policy_version 320 (0.0003) [2023-07-16 19:20:00,023][213260] Heartbeat connected on Batcher_0 [2023-07-16 19:20:00,025][213260] Heartbeat connected on LearnerWorker_p0 [2023-07-16 19:20:00,028][213260] Heartbeat connected on InferenceWorker_p0-w0 [2023-07-16 19:20:00,033][213260] Heartbeat connected on RolloutWorker_w0 [2023-07-16 19:20:00,034][213260] Heartbeat connected on RolloutWorker_w1 [2023-07-16 19:20:00,035][213260] Heartbeat connected on RolloutWorker_w2 [2023-07-16 19:20:00,038][213260] Heartbeat connected on RolloutWorker_w3 [2023-07-16 19:20:00,040][213260] Heartbeat connected on RolloutWorker_w4 [2023-07-16 19:20:00,042][213260] Heartbeat connected on RolloutWorker_w5 [2023-07-16 19:20:00,044][213260] Heartbeat connected on RolloutWorker_w6 [2023-07-16 19:20:00,045][213260] Heartbeat connected on RolloutWorker_w7 [2023-07-16 19:20:02,907][213547] Updated weights for policy 0, policy_version 400 (0.0005) [2023-07-16 19:20:03,006][213260] Fps is (10 sec: 13107.3, 60 sec: 10240.1, 300 sec: 10240.1). Total num frames: 204800. Throughput: 0: 8812.3. Samples: 176244. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-16 19:20:03,007][213260] Avg episode reward: [(0, '32.383')] [2023-07-16 19:20:03,007][213503] Saving new best policy, reward=32.383! [2023-07-16 19:20:06,248][213547] Updated weights for policy 0, policy_version 480 (0.0005) [2023-07-16 19:20:08,006][213260] Fps is (10 sec: 12697.5, 60 sec: 10649.6, 300 sec: 10649.6). Total num frames: 266240. Throughput: 0: 10067.9. Samples: 251696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:20:08,007][213260] Avg episode reward: [(0, '83.544')] [2023-07-16 19:20:08,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000520_266240.pth... [2023-07-16 19:20:08,013][213503] Saving new best policy, reward=83.544! [2023-07-16 19:20:09,513][213547] Updated weights for policy 0, policy_version 560 (0.0005) [2023-07-16 19:20:12,752][213547] Updated weights for policy 0, policy_version 640 (0.0004) [2023-07-16 19:20:13,006][213260] Fps is (10 sec: 12288.0, 60 sec: 10922.7, 300 sec: 10922.7). Total num frames: 327680. Throughput: 0: 10923.1. Samples: 327692. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-16 19:20:13,007][213260] Avg episode reward: [(0, '122.661')] [2023-07-16 19:20:13,008][213503] Saving new best policy, reward=122.661! [2023-07-16 19:20:16,234][213547] Updated weights for policy 0, policy_version 720 (0.0005) [2023-07-16 19:20:18,006][213260] Fps is (10 sec: 12287.9, 60 sec: 11117.7, 300 sec: 11117.7). Total num frames: 389120. Throughput: 0: 10394.1. Samples: 363792. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-16 19:20:18,007][213260] Avg episode reward: [(0, '191.948')] [2023-07-16 19:20:18,008][213503] Saving new best policy, reward=191.948! [2023-07-16 19:20:19,662][213547] Updated weights for policy 0, policy_version 800 (0.0005) [2023-07-16 19:20:23,006][213260] Fps is (10 sec: 11878.3, 60 sec: 11161.6, 300 sec: 11161.6). Total num frames: 446464. Throughput: 0: 10854.6. Samples: 434184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:20:23,007][213260] Avg episode reward: [(0, '261.593')] [2023-07-16 19:20:23,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000872_446464.pth... [2023-07-16 19:20:23,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000144_73728.pth [2023-07-16 19:20:23,013][213503] Saving new best policy, reward=261.593! [2023-07-16 19:20:23,118][213547] Updated weights for policy 0, policy_version 880 (0.0005) [2023-07-16 19:20:26,661][213547] Updated weights for policy 0, policy_version 960 (0.0005) [2023-07-16 19:20:28,006][213260] Fps is (10 sec: 11468.9, 60 sec: 11195.8, 300 sec: 11195.8). Total num frames: 503808. Throughput: 0: 11197.2. Samples: 503872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:20:28,007][213260] Avg episode reward: [(0, '292.199')] [2023-07-16 19:20:28,008][213503] Saving new best policy, reward=292.199! [2023-07-16 19:20:30,137][213547] Updated weights for policy 0, policy_version 1040 (0.0005) [2023-07-16 19:20:33,006][213260] Fps is (10 sec: 11878.5, 60 sec: 11305.0, 300 sec: 11305.0). Total num frames: 565248. Throughput: 0: 11998.3. Samples: 539924. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:20:33,007][213260] Avg episode reward: [(0, '308.369')] [2023-07-16 19:20:33,008][213503] Saving new best policy, reward=308.369! [2023-07-16 19:20:33,656][213547] Updated weights for policy 0, policy_version 1120 (0.0005) [2023-07-16 19:20:36,999][213547] Updated weights for policy 0, policy_version 1200 (0.0004) [2023-07-16 19:20:38,006][213260] Fps is (10 sec: 12287.9, 60 sec: 11394.4, 300 sec: 11394.4). Total num frames: 626688. Throughput: 0: 12206.4. Samples: 610508. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-16 19:20:38,007][213260] Avg episode reward: [(0, '396.016')] [2023-07-16 19:20:38,009][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001224_626688.pth... [2023-07-16 19:20:38,012][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000520_266240.pth [2023-07-16 19:20:38,012][213503] Saving new best policy, reward=396.016! [2023-07-16 19:20:40,166][213547] Updated weights for policy 0, policy_version 1280 (0.0004) [2023-07-16 19:20:43,006][213260] Fps is (10 sec: 12288.0, 60 sec: 11468.8, 300 sec: 11468.8). Total num frames: 688128. Throughput: 0: 12227.8. Samples: 688192. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-16 19:20:43,007][213260] Avg episode reward: [(0, '419.048')] [2023-07-16 19:20:43,007][213503] Saving new best policy, reward=419.048! [2023-07-16 19:20:43,396][213547] Updated weights for policy 0, policy_version 1360 (0.0004) [2023-07-16 19:20:46,633][213547] Updated weights for policy 0, policy_version 1440 (0.0004) [2023-07-16 19:20:48,006][213260] Fps is (10 sec: 12697.7, 60 sec: 12356.3, 300 sec: 11594.9). Total num frames: 753664. Throughput: 0: 12206.2. Samples: 725524. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-16 19:20:48,007][213260] Avg episode reward: [(0, '413.218')] [2023-07-16 19:20:49,837][213547] Updated weights for policy 0, policy_version 1520 (0.0004) [2023-07-16 19:20:53,006][213260] Fps is (10 sec: 12697.5, 60 sec: 12356.3, 300 sec: 11644.4). Total num frames: 815104. Throughput: 0: 12242.7. Samples: 802616. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:20:53,007][213260] Avg episode reward: [(0, '420.632')] [2023-07-16 19:20:53,009][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001592_815104.pth... [2023-07-16 19:20:53,011][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000872_446464.pth [2023-07-16 19:20:53,011][213503] Saving new best policy, reward=420.632! [2023-07-16 19:20:53,045][213547] Updated weights for policy 0, policy_version 1600 (0.0004) [2023-07-16 19:20:56,234][213547] Updated weights for policy 0, policy_version 1680 (0.0004) [2023-07-16 19:20:58,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 11741.9). Total num frames: 880640. Throughput: 0: 12269.9. Samples: 879836. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-16 19:20:58,007][213260] Avg episode reward: [(0, '447.864')] [2023-07-16 19:20:58,007][213503] Saving new best policy, reward=447.864! [2023-07-16 19:20:59,374][213547] Updated weights for policy 0, policy_version 1760 (0.0004) [2023-07-16 19:21:02,656][213547] Updated weights for policy 0, policy_version 1840 (0.0004) [2023-07-16 19:21:03,006][213260] Fps is (10 sec: 12697.7, 60 sec: 12288.0, 300 sec: 11776.0). Total num frames: 942080. Throughput: 0: 12317.0. Samples: 918056. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:21:03,007][213260] Avg episode reward: [(0, '430.406')] [2023-07-16 19:21:06,090][213547] Updated weights for policy 0, policy_version 1920 (0.0005) [2023-07-16 19:21:08,006][213260] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 11806.1). Total num frames: 1003520. Throughput: 0: 12379.0. Samples: 991240. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:21:08,007][213260] Avg episode reward: [(0, '470.899')] [2023-07-16 19:21:08,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001960_1003520.pth... [2023-07-16 19:21:08,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001224_626688.pth [2023-07-16 19:21:08,014][213503] Saving new best policy, reward=470.899! [2023-07-16 19:21:09,459][213547] Updated weights for policy 0, policy_version 2000 (0.0004) [2023-07-16 19:21:12,870][213547] Updated weights for policy 0, policy_version 2080 (0.0005) [2023-07-16 19:21:13,006][213260] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 11832.9). Total num frames: 1064960. Throughput: 0: 12434.0. Samples: 1063400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:21:13,007][213260] Avg episode reward: [(0, '476.471')] [2023-07-16 19:21:13,007][213503] Saving new best policy, reward=476.471! [2023-07-16 19:21:16,412][213547] Updated weights for policy 0, policy_version 2160 (0.0005) [2023-07-16 19:21:18,006][213260] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 11856.9). Total num frames: 1126400. Throughput: 0: 12402.1. Samples: 1098016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:21:18,007][213260] Avg episode reward: [(0, '452.376')] [2023-07-16 19:21:19,573][213547] Updated weights for policy 0, policy_version 2240 (0.0004) [2023-07-16 19:21:22,746][213547] Updated weights for policy 0, policy_version 2320 (0.0004) [2023-07-16 19:21:23,006][213260] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 11878.4). Total num frames: 1187840. Throughput: 0: 12542.8. Samples: 1174932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:21:23,007][213260] Avg episode reward: [(0, '502.382')] [2023-07-16 19:21:23,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002320_1187840.pth... [2023-07-16 19:21:23,012][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001592_815104.pth [2023-07-16 19:21:23,012][213503] Saving new best policy, reward=502.382! [2023-07-16 19:21:25,888][213547] Updated weights for policy 0, policy_version 2400 (0.0004) [2023-07-16 19:21:28,006][213260] Fps is (10 sec: 12697.5, 60 sec: 12492.8, 300 sec: 11936.9). Total num frames: 1253376. Throughput: 0: 12546.8. Samples: 1252796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:21:28,007][213260] Avg episode reward: [(0, '499.273')] [2023-07-16 19:21:29,104][213547] Updated weights for policy 0, policy_version 2480 (0.0003) [2023-07-16 19:21:32,492][213547] Updated weights for policy 0, policy_version 2560 (0.0005) [2023-07-16 19:21:33,006][213260] Fps is (10 sec: 12697.7, 60 sec: 12492.8, 300 sec: 11952.9). Total num frames: 1314816. Throughput: 0: 12541.1. Samples: 1289872. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-16 19:21:33,007][213260] Avg episode reward: [(0, '490.673')] [2023-07-16 19:21:36,052][213547] Updated weights for policy 0, policy_version 2640 (0.0005) [2023-07-16 19:21:38,006][213260] Fps is (10 sec: 11878.3, 60 sec: 12424.5, 300 sec: 11931.8). Total num frames: 1372160. Throughput: 0: 12384.9. Samples: 1359936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:21:38,007][213260] Avg episode reward: [(0, '501.084')] [2023-07-16 19:21:38,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002680_1372160.pth... [2023-07-16 19:21:38,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001960_1003520.pth [2023-07-16 19:21:39,414][213547] Updated weights for policy 0, policy_version 2720 (0.0004) [2023-07-16 19:21:42,592][213547] Updated weights for policy 0, policy_version 2800 (0.0004) [2023-07-16 19:21:43,006][213260] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 11980.8). Total num frames: 1437696. Throughput: 0: 12344.6. Samples: 1435344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:21:43,007][213260] Avg episode reward: [(0, '500.869')] [2023-07-16 19:21:45,794][213547] Updated weights for policy 0, policy_version 2880 (0.0004) [2023-07-16 19:21:48,006][213260] Fps is (10 sec: 12697.8, 60 sec: 12424.5, 300 sec: 11993.1). Total num frames: 1499136. Throughput: 0: 12359.1. Samples: 1474216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:21:48,007][213260] Avg episode reward: [(0, '475.553')] [2023-07-16 19:21:49,103][213547] Updated weights for policy 0, policy_version 2960 (0.0004) [2023-07-16 19:21:52,568][213547] Updated weights for policy 0, policy_version 3040 (0.0005) [2023-07-16 19:21:53,006][213260] Fps is (10 sec: 12287.9, 60 sec: 12424.5, 300 sec: 12004.4). Total num frames: 1560576. Throughput: 0: 12352.5. Samples: 1547104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:21:53,007][213260] Avg episode reward: [(0, '527.109')] [2023-07-16 19:21:53,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003048_1560576.pth... [2023-07-16 19:21:53,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002320_1187840.pth [2023-07-16 19:21:53,013][213503] Saving new best policy, reward=527.109! [2023-07-16 19:21:55,813][213547] Updated weights for policy 0, policy_version 3120 (0.0004) [2023-07-16 19:21:58,006][213260] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12015.0). Total num frames: 1622016. Throughput: 0: 12403.4. Samples: 1621552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:21:58,007][213260] Avg episode reward: [(0, '528.551')] [2023-07-16 19:21:58,008][213503] Saving new best policy, reward=528.551! [2023-07-16 19:21:59,168][213547] Updated weights for policy 0, policy_version 3200 (0.0004) [2023-07-16 19:22:02,633][213547] Updated weights for policy 0, policy_version 3280 (0.0005) [2023-07-16 19:22:03,006][213260] Fps is (10 sec: 12287.9, 60 sec: 12356.2, 300 sec: 12024.7). Total num frames: 1683456. Throughput: 0: 12441.5. Samples: 1657888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:22:03,008][213260] Avg episode reward: [(0, '509.410')] [2023-07-16 19:22:06,121][213547] Updated weights for policy 0, policy_version 3360 (0.0005) [2023-07-16 19:22:08,006][213260] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 12005.5). Total num frames: 1740800. Throughput: 0: 12284.3. Samples: 1727724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:22:08,007][213260] Avg episode reward: [(0, '523.022')] [2023-07-16 19:22:08,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003400_1740800.pth... [2023-07-16 19:22:08,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002680_1372160.pth [2023-07-16 19:22:09,631][213547] Updated weights for policy 0, policy_version 3440 (0.0005) [2023-07-16 19:22:13,006][213260] Fps is (10 sec: 11469.0, 60 sec: 12219.7, 300 sec: 11987.6). Total num frames: 1798144. Throughput: 0: 12107.9. Samples: 1797652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:22:13,008][213260] Avg episode reward: [(0, '521.375')] [2023-07-16 19:22:13,186][213547] Updated weights for policy 0, policy_version 3520 (0.0005) [2023-07-16 19:22:16,675][213547] Updated weights for policy 0, policy_version 3600 (0.0005) [2023-07-16 19:22:18,006][213260] Fps is (10 sec: 11468.9, 60 sec: 12151.5, 300 sec: 11970.9). Total num frames: 1855488. Throughput: 0: 12055.6. Samples: 1832376. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-16 19:22:18,007][213260] Avg episode reward: [(0, '525.602')] [2023-07-16 19:22:20,084][213547] Updated weights for policy 0, policy_version 3680 (0.0005) [2023-07-16 19:22:23,006][213260] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 11980.8). Total num frames: 1916928. Throughput: 0: 12092.9. Samples: 1904116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:22:23,007][213260] Avg episode reward: [(0, '515.063')] [2023-07-16 19:22:23,011][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003744_1916928.pth... [2023-07-16 19:22:23,014][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003048_1560576.pth [2023-07-16 19:22:23,506][213547] Updated weights for policy 0, policy_version 3760 (0.0004) [2023-07-16 19:22:26,936][213547] Updated weights for policy 0, policy_version 3840 (0.0005) [2023-07-16 19:22:28,006][213260] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 11990.1). Total num frames: 1978368. Throughput: 0: 11990.2. Samples: 1974904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:22:28,006][213260] Avg episode reward: [(0, '519.962')] [2023-07-16 19:22:30,231][213547] Updated weights for policy 0, policy_version 3920 (0.0004) [2023-07-16 19:22:33,006][213260] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11998.9). Total num frames: 2039808. Throughput: 0: 11983.5. Samples: 2013472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:22:33,007][213260] Avg episode reward: [(0, '544.182')] [2023-07-16 19:22:33,027][213503] Saving new best policy, reward=544.182! [2023-07-16 19:22:33,331][213547] Updated weights for policy 0, policy_version 4000 (0.0004) [2023-07-16 19:22:36,696][213547] Updated weights for policy 0, policy_version 4080 (0.0005) [2023-07-16 19:22:38,006][213260] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 12007.1). Total num frames: 2101248. Throughput: 0: 12045.5. Samples: 2089152. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:22:38,006][213260] Avg episode reward: [(0, '541.280')] [2023-07-16 19:22:38,055][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004112_2105344.pth... [2023-07-16 19:22:38,057][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003400_1740800.pth [2023-07-16 19:22:40,087][213547] Updated weights for policy 0, policy_version 4160 (0.0005) [2023-07-16 19:22:43,006][213260] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12014.9). Total num frames: 2162688. Throughput: 0: 12025.5. Samples: 2162700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:22:43,007][213260] Avg episode reward: [(0, '548.306')] [2023-07-16 19:22:43,008][213503] Saving new best policy, reward=548.306! [2023-07-16 19:22:43,451][213547] Updated weights for policy 0, policy_version 4240 (0.0005) [2023-07-16 19:22:46,916][213547] Updated weights for policy 0, policy_version 4320 (0.0005) [2023-07-16 19:22:48,006][213260] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 12022.3). Total num frames: 2224128. Throughput: 0: 12015.8. Samples: 2198600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:22:48,007][213260] Avg episode reward: [(0, '547.759')] [2023-07-16 19:22:50,349][213547] Updated weights for policy 0, policy_version 4400 (0.0005) [2023-07-16 19:22:53,006][213260] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12007.8). Total num frames: 2281472. Throughput: 0: 12032.6. Samples: 2269192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:22:53,007][213260] Avg episode reward: [(0, '529.800')] [2023-07-16 19:22:53,011][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004456_2281472.pth... [2023-07-16 19:22:53,014][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003744_1916928.pth [2023-07-16 19:22:53,806][213547] Updated weights for policy 0, policy_version 4480 (0.0005) [2023-07-16 19:22:57,189][213547] Updated weights for policy 0, policy_version 4560 (0.0005) [2023-07-16 19:22:58,006][213260] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12014.9). Total num frames: 2342912. Throughput: 0: 12082.8. Samples: 2341380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:22:58,007][213260] Avg episode reward: [(0, '564.175')] [2023-07-16 19:22:58,008][213503] Saving new best policy, reward=564.175! [2023-07-16 19:23:00,529][213547] Updated weights for policy 0, policy_version 4640 (0.0005) [2023-07-16 19:23:03,006][213260] Fps is (10 sec: 12288.1, 60 sec: 12015.0, 300 sec: 12021.8). Total num frames: 2404352. Throughput: 0: 12135.3. Samples: 2378464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:23:03,111][213260] Avg episode reward: [(0, '555.997')] [2023-07-16 19:23:04,001][213547] Updated weights for policy 0, policy_version 4720 (0.0005) [2023-07-16 19:23:07,358][213547] Updated weights for policy 0, policy_version 4800 (0.0005) [2023-07-16 19:23:08,006][213260] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12008.3). Total num frames: 2461696. Throughput: 0: 12122.1. Samples: 2449612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:23:08,007][213260] Avg episode reward: [(0, '545.994')] [2023-07-16 19:23:08,024][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004816_2465792.pth... [2023-07-16 19:23:08,027][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004112_2105344.pth [2023-07-16 19:23:10,738][213547] Updated weights for policy 0, policy_version 4880 (0.0005) [2023-07-16 19:23:13,006][213260] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12014.9). Total num frames: 2523136. Throughput: 0: 12184.3. Samples: 2523200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:23:13,007][213260] Avg episode reward: [(0, '553.603')] [2023-07-16 19:23:13,916][213547] Updated weights for policy 0, policy_version 4960 (0.0004) [2023-07-16 19:23:16,971][213547] Updated weights for policy 0, policy_version 5040 (0.0003) [2023-07-16 19:23:18,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 12040.3). Total num frames: 2588672. Throughput: 0: 12232.7. Samples: 2563944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:23:18,007][213260] Avg episode reward: [(0, '549.114')] [2023-07-16 19:23:20,349][213547] Updated weights for policy 0, policy_version 5120 (0.0005) [2023-07-16 19:23:23,006][213260] Fps is (10 sec: 12697.5, 60 sec: 12219.7, 300 sec: 12046.0). Total num frames: 2650112. Throughput: 0: 12207.7. Samples: 2638500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:23:23,007][213260] Avg episode reward: [(0, '554.016')] [2023-07-16 19:23:23,016][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005184_2654208.pth... [2023-07-16 19:23:23,018][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004456_2281472.pth [2023-07-16 19:23:23,672][213547] Updated weights for policy 0, policy_version 5200 (0.0005) [2023-07-16 19:23:27,020][213547] Updated weights for policy 0, policy_version 5280 (0.0004) [2023-07-16 19:23:28,006][213260] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12051.4). Total num frames: 2711552. Throughput: 0: 12203.0. Samples: 2711836. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-16 19:23:28,007][213260] Avg episode reward: [(0, '559.281')] [2023-07-16 19:23:30,348][213547] Updated weights for policy 0, policy_version 5360 (0.0005) [2023-07-16 19:23:33,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 12074.3). Total num frames: 2777088. Throughput: 0: 12229.4. Samples: 2748924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:23:33,007][213260] Avg episode reward: [(0, '536.748')] [2023-07-16 19:23:33,648][213547] Updated weights for policy 0, policy_version 5440 (0.0005) [2023-07-16 19:23:36,926][213547] Updated weights for policy 0, policy_version 5520 (0.0005) [2023-07-16 19:23:38,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 12078.8). Total num frames: 2838528. Throughput: 0: 12326.2. Samples: 2823872. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-16 19:23:38,007][213260] Avg episode reward: [(0, '546.939')] [2023-07-16 19:23:38,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005544_2838528.pth... [2023-07-16 19:23:38,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004816_2465792.pth [2023-07-16 19:23:40,124][213547] Updated weights for policy 0, policy_version 5600 (0.0004) [2023-07-16 19:23:43,006][213260] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12083.2). Total num frames: 2899968. Throughput: 0: 12424.0. Samples: 2900460. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-16 19:23:43,007][213260] Avg episode reward: [(0, '551.251')] [2023-07-16 19:23:43,354][213547] Updated weights for policy 0, policy_version 5680 (0.0004) [2023-07-16 19:23:46,753][213547] Updated weights for policy 0, policy_version 5760 (0.0005) [2023-07-16 19:23:48,006][213260] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12087.4). Total num frames: 2961408. Throughput: 0: 12409.8. Samples: 2936904. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-16 19:23:48,007][213260] Avg episode reward: [(0, '542.144')] [2023-07-16 19:23:50,075][213547] Updated weights for policy 0, policy_version 5840 (0.0004) [2023-07-16 19:23:53,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12424.5, 300 sec: 12107.8). Total num frames: 3026944. Throughput: 0: 12466.9. Samples: 3010624. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-16 19:23:53,007][213260] Avg episode reward: [(0, '522.474')] [2023-07-16 19:23:53,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005912_3026944.pth... [2023-07-16 19:23:53,012][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005184_2654208.pth [2023-07-16 19:23:53,270][213547] Updated weights for policy 0, policy_version 5920 (0.0004) [2023-07-16 19:23:56,442][213547] Updated weights for policy 0, policy_version 6000 (0.0004) [2023-07-16 19:23:58,006][213260] Fps is (10 sec: 12697.7, 60 sec: 12424.5, 300 sec: 12111.3). Total num frames: 3088384. Throughput: 0: 12565.2. Samples: 3088632. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-16 19:23:58,007][213260] Avg episode reward: [(0, '550.336')] [2023-07-16 19:23:59,690][213547] Updated weights for policy 0, policy_version 6080 (0.0005) [2023-07-16 19:24:02,869][213547] Updated weights for policy 0, policy_version 6160 (0.0005) [2023-07-16 19:24:03,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12130.5). Total num frames: 3153920. Throughput: 0: 12491.7. Samples: 3126072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:24:03,007][213260] Avg episode reward: [(0, '558.955')] [2023-07-16 19:24:06,024][213547] Updated weights for policy 0, policy_version 6240 (0.0004) [2023-07-16 19:24:08,006][213260] Fps is (10 sec: 13107.0, 60 sec: 12629.3, 300 sec: 12148.9). Total num frames: 3219456. Throughput: 0: 12572.9. Samples: 3204280. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:24:08,007][213260] Avg episode reward: [(0, '532.297')] [2023-07-16 19:24:08,011][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006288_3219456.pth... [2023-07-16 19:24:08,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005544_2838528.pth [2023-07-16 19:24:09,085][213547] Updated weights for policy 0, policy_version 6320 (0.0004) [2023-07-16 19:24:12,174][213547] Updated weights for policy 0, policy_version 6400 (0.0004) [2023-07-16 19:24:13,006][213260] Fps is (10 sec: 13107.2, 60 sec: 12697.6, 300 sec: 12166.6). Total num frames: 3284992. Throughput: 0: 12722.1. Samples: 3284332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:24:13,007][213260] Avg episode reward: [(0, '535.402')] [2023-07-16 19:24:15,367][213547] Updated weights for policy 0, policy_version 6480 (0.0004) [2023-07-16 19:24:18,006][213260] Fps is (10 sec: 13107.3, 60 sec: 12697.6, 300 sec: 12183.7). Total num frames: 3350528. Throughput: 0: 12734.8. Samples: 3321988. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-16 19:24:18,007][213260] Avg episode reward: [(0, '555.472')] [2023-07-16 19:24:18,625][213547] Updated weights for policy 0, policy_version 6560 (0.0005) [2023-07-16 19:24:21,804][213547] Updated weights for policy 0, policy_version 6640 (0.0004) [2023-07-16 19:24:23,006][213260] Fps is (10 sec: 12697.5, 60 sec: 12697.6, 300 sec: 12185.6). Total num frames: 3411968. Throughput: 0: 12777.1. Samples: 3398840. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-16 19:24:23,007][213260] Avg episode reward: [(0, '554.958')] [2023-07-16 19:24:23,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006664_3411968.pth... [2023-07-16 19:24:23,012][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005912_3026944.pth [2023-07-16 19:24:25,014][213547] Updated weights for policy 0, policy_version 6720 (0.0004) [2023-07-16 19:24:28,006][213260] Fps is (10 sec: 12697.7, 60 sec: 12765.9, 300 sec: 12201.8). Total num frames: 3477504. Throughput: 0: 12771.7. Samples: 3475188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:24:28,007][213260] Avg episode reward: [(0, '555.161')] [2023-07-16 19:24:28,235][213547] Updated weights for policy 0, policy_version 6800 (0.0004) [2023-07-16 19:24:31,490][213547] Updated weights for policy 0, policy_version 6880 (0.0004) [2023-07-16 19:24:33,006][213260] Fps is (10 sec: 12697.7, 60 sec: 12697.6, 300 sec: 12203.3). Total num frames: 3538944. Throughput: 0: 12797.8. Samples: 3512804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:24:33,007][213260] Avg episode reward: [(0, '545.677')] [2023-07-16 19:24:34,757][213547] Updated weights for policy 0, policy_version 6960 (0.0004) [2023-07-16 19:24:38,006][213260] Fps is (10 sec: 12287.9, 60 sec: 12697.6, 300 sec: 12204.7). Total num frames: 3600384. Throughput: 0: 12837.7. Samples: 3588320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:24:38,007][213260] Avg episode reward: [(0, '542.930')] [2023-07-16 19:24:38,009][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007032_3600384.pth... [2023-07-16 19:24:38,011][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006288_3219456.pth [2023-07-16 19:24:38,047][213547] Updated weights for policy 0, policy_version 7040 (0.0004) [2023-07-16 19:24:41,356][213547] Updated weights for policy 0, policy_version 7120 (0.0004) [2023-07-16 19:24:43,006][213260] Fps is (10 sec: 12288.0, 60 sec: 12697.6, 300 sec: 12371.3). Total num frames: 3661824. Throughput: 0: 12739.0. Samples: 3661888. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-16 19:24:43,007][213260] Avg episode reward: [(0, '549.069')] [2023-07-16 19:24:44,806][213547] Updated weights for policy 0, policy_version 7200 (0.0006) [2023-07-16 19:24:48,006][213260] Fps is (10 sec: 12288.0, 60 sec: 12697.6, 300 sec: 12371.3). Total num frames: 3723264. Throughput: 0: 12697.5. Samples: 3697460. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-16 19:24:48,007][213260] Avg episode reward: [(0, '548.998')] [2023-07-16 19:24:48,252][213547] Updated weights for policy 0, policy_version 7280 (0.0005) [2023-07-16 19:24:51,745][213547] Updated weights for policy 0, policy_version 7360 (0.0006) [2023-07-16 19:24:53,006][213260] Fps is (10 sec: 11878.3, 60 sec: 12561.1, 300 sec: 12343.5). Total num frames: 3780608. Throughput: 0: 12534.5. Samples: 3768332. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-16 19:24:53,007][213260] Avg episode reward: [(0, '541.079')] [2023-07-16 19:24:53,011][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007384_3780608.pth... [2023-07-16 19:24:53,012][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006664_3411968.pth [2023-07-16 19:24:55,242][213547] Updated weights for policy 0, policy_version 7440 (0.0005) [2023-07-16 19:24:58,006][213260] Fps is (10 sec: 11468.8, 60 sec: 12492.8, 300 sec: 12315.8). Total num frames: 3837952. Throughput: 0: 12304.1. Samples: 3838016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:24:58,031][213260] Avg episode reward: [(0, '542.794')] [2023-07-16 19:24:58,765][213547] Updated weights for policy 0, policy_version 7520 (0.0005) [2023-07-16 19:25:02,181][213547] Updated weights for policy 0, policy_version 7600 (0.0005) [2023-07-16 19:25:03,006][213260] Fps is (10 sec: 11878.5, 60 sec: 12424.5, 300 sec: 12315.8). Total num frames: 3899392. Throughput: 0: 12248.5. Samples: 3873172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:25:03,007][213260] Avg episode reward: [(0, '526.762')] [2023-07-16 19:25:05,366][213547] Updated weights for policy 0, policy_version 7680 (0.0004) [2023-07-16 19:25:08,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12424.5, 300 sec: 12329.7). Total num frames: 3964928. Throughput: 0: 12239.4. Samples: 3949612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:25:08,020][213260] Avg episode reward: [(0, '521.677')] [2023-07-16 19:25:08,023][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007744_3964928.pth... [2023-07-16 19:25:08,026][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007032_3600384.pth [2023-07-16 19:25:08,552][213547] Updated weights for policy 0, policy_version 7760 (0.0004) [2023-07-16 19:25:11,765][213547] Updated weights for policy 0, policy_version 7840 (0.0004) [2023-07-16 19:25:13,006][213260] Fps is (10 sec: 12697.7, 60 sec: 12356.3, 300 sec: 12329.7). Total num frames: 4026368. Throughput: 0: 12249.9. Samples: 4026432. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-16 19:25:13,007][213260] Avg episode reward: [(0, '540.145')] [2023-07-16 19:25:14,916][213547] Updated weights for policy 0, policy_version 7920 (0.0004) [2023-07-16 19:25:18,006][213260] Fps is (10 sec: 12697.7, 60 sec: 12356.3, 300 sec: 12357.4). Total num frames: 4091904. Throughput: 0: 12277.3. Samples: 4065284. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:25:18,007][213260] Avg episode reward: [(0, '536.432')] [2023-07-16 19:25:18,217][213547] Updated weights for policy 0, policy_version 8000 (0.0005) [2023-07-16 19:25:21,808][213547] Updated weights for policy 0, policy_version 8080 (0.0005) [2023-07-16 19:25:23,006][213260] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12357.4). Total num frames: 4149248. Throughput: 0: 12182.1. Samples: 4136516. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:25:23,007][213260] Avg episode reward: [(0, '559.944')] [2023-07-16 19:25:23,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008104_4149248.pth... [2023-07-16 19:25:23,012][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007384_3780608.pth [2023-07-16 19:25:25,242][213547] Updated weights for policy 0, policy_version 8160 (0.0005) [2023-07-16 19:25:28,006][213260] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12357.4). Total num frames: 4210688. Throughput: 0: 12180.4. Samples: 4210008. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:25:28,007][213260] Avg episode reward: [(0, '534.786')] [2023-07-16 19:25:28,509][213547] Updated weights for policy 0, policy_version 8240 (0.0005) [2023-07-16 19:25:32,059][213547] Updated weights for policy 0, policy_version 8320 (0.0005) [2023-07-16 19:25:33,006][213260] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 12343.5). Total num frames: 4268032. Throughput: 0: 12163.1. Samples: 4244800. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-16 19:25:33,007][213260] Avg episode reward: [(0, '522.368')] [2023-07-16 19:25:35,552][213547] Updated weights for policy 0, policy_version 8400 (0.0006) [2023-07-16 19:25:38,006][213260] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12343.5). Total num frames: 4329472. Throughput: 0: 12141.3. Samples: 4314688. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-16 19:25:38,007][213260] Avg episode reward: [(0, '544.149')] [2023-07-16 19:25:38,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008456_4329472.pth... [2023-07-16 19:25:38,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007744_3964928.pth [2023-07-16 19:25:39,043][213547] Updated weights for policy 0, policy_version 8480 (0.0006) [2023-07-16 19:25:42,335][213547] Updated weights for policy 0, policy_version 8560 (0.0005) [2023-07-16 19:25:43,006][213260] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12315.8). Total num frames: 4386816. Throughput: 0: 12201.3. Samples: 4387072. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-16 19:25:43,007][213260] Avg episode reward: [(0, '543.436')] [2023-07-16 19:25:45,836][213547] Updated weights for policy 0, policy_version 8640 (0.0005) [2023-07-16 19:25:48,006][213260] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12315.8). Total num frames: 4448256. Throughput: 0: 12213.2. Samples: 4422764. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:25:48,007][213260] Avg episode reward: [(0, '523.495')] [2023-07-16 19:25:49,348][213547] Updated weights for policy 0, policy_version 8720 (0.0004) [2023-07-16 19:25:52,931][213547] Updated weights for policy 0, policy_version 8800 (0.0006) [2023-07-16 19:25:53,006][213260] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12288.0). Total num frames: 4505600. Throughput: 0: 12055.1. Samples: 4492092. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-16 19:25:53,007][213260] Avg episode reward: [(0, '528.543')] [2023-07-16 19:25:53,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008800_4505600.pth... [2023-07-16 19:25:53,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008104_4149248.pth [2023-07-16 19:25:56,439][213547] Updated weights for policy 0, policy_version 8880 (0.0005) [2023-07-16 19:25:58,006][213260] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 12274.1). Total num frames: 4562944. Throughput: 0: 11895.3. Samples: 4561720. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-16 19:25:58,007][213260] Avg episode reward: [(0, '537.471')] [2023-07-16 19:26:00,002][213547] Updated weights for policy 0, policy_version 8960 (0.0005) [2023-07-16 19:26:03,006][213260] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 12260.2). Total num frames: 4620288. Throughput: 0: 11789.6. Samples: 4595816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:26:03,007][213260] Avg episode reward: [(0, '535.008')] [2023-07-16 19:26:03,444][213547] Updated weights for policy 0, policy_version 9040 (0.0005) [2023-07-16 19:26:06,895][213547] Updated weights for policy 0, policy_version 9120 (0.0005) [2023-07-16 19:26:08,006][213260] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 12260.2). Total num frames: 4681728. Throughput: 0: 11805.2. Samples: 4667748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:26:08,007][213260] Avg episode reward: [(0, '522.561')] [2023-07-16 19:26:08,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009144_4681728.pth... [2023-07-16 19:26:08,012][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008456_4329472.pth [2023-07-16 19:26:10,425][213547] Updated weights for policy 0, policy_version 9200 (0.0005) [2023-07-16 19:26:13,006][213260] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 12246.3). Total num frames: 4739072. Throughput: 0: 11691.0. Samples: 4736100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:26:13,007][213260] Avg episode reward: [(0, '507.076')] [2023-07-16 19:26:14,005][213547] Updated weights for policy 0, policy_version 9280 (0.0005) [2023-07-16 19:26:17,575][213547] Updated weights for policy 0, policy_version 9360 (0.0005) [2023-07-16 19:26:18,006][213260] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 12232.5). Total num frames: 4796416. Throughput: 0: 11712.2. Samples: 4771848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:26:18,007][213260] Avg episode reward: [(0, '517.457')] [2023-07-16 19:26:20,913][213547] Updated weights for policy 0, policy_version 9440 (0.0004) [2023-07-16 19:26:23,006][213260] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 12218.6). Total num frames: 4857856. Throughput: 0: 11754.0. Samples: 4843620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:26:23,007][213260] Avg episode reward: [(0, '503.305')] [2023-07-16 19:26:23,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009488_4857856.pth... [2023-07-16 19:26:23,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008800_4505600.pth [2023-07-16 19:26:24,226][213547] Updated weights for policy 0, policy_version 9520 (0.0004) [2023-07-16 19:26:27,686][213547] Updated weights for policy 0, policy_version 9600 (0.0005) [2023-07-16 19:26:28,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 12204.7). Total num frames: 4915200. Throughput: 0: 11743.6. Samples: 4915532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:26:28,007][213260] Avg episode reward: [(0, '522.370')] [2023-07-16 19:26:31,223][213547] Updated weights for policy 0, policy_version 9680 (0.0005) [2023-07-16 19:26:33,006][213260] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 12218.6). Total num frames: 4976640. Throughput: 0: 11740.2. Samples: 4951072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:26:33,007][213260] Avg episode reward: [(0, '501.389')] [2023-07-16 19:26:34,695][213547] Updated weights for policy 0, policy_version 9760 (0.0005) [2023-07-16 19:26:38,006][213260] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 12190.8). Total num frames: 5033984. Throughput: 0: 11769.3. Samples: 5021708. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:26:38,006][213260] Avg episode reward: [(0, '522.348')] [2023-07-16 19:26:38,009][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009832_5033984.pth... [2023-07-16 19:26:38,012][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009144_4681728.pth [2023-07-16 19:26:38,123][213547] Updated weights for policy 0, policy_version 9840 (0.0005) [2023-07-16 19:26:41,294][213547] Updated weights for policy 0, policy_version 9920 (0.0004) [2023-07-16 19:26:43,006][213260] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 12204.7). Total num frames: 5099520. Throughput: 0: 11891.1. Samples: 5096820. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:26:43,007][213260] Avg episode reward: [(0, '504.045')] [2023-07-16 19:26:44,471][213547] Updated weights for policy 0, policy_version 10000 (0.0004) [2023-07-16 19:26:47,694][213547] Updated weights for policy 0, policy_version 10080 (0.0004) [2023-07-16 19:26:48,006][213260] Fps is (10 sec: 12697.5, 60 sec: 11878.4, 300 sec: 12204.7). Total num frames: 5160960. Throughput: 0: 12012.3. Samples: 5136368. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:26:48,007][213260] Avg episode reward: [(0, '507.405')] [2023-07-16 19:26:51,051][213547] Updated weights for policy 0, policy_version 10160 (0.0005) [2023-07-16 19:26:53,006][213260] Fps is (10 sec: 12697.5, 60 sec: 12014.9, 300 sec: 12218.6). Total num frames: 5226496. Throughput: 0: 12063.1. Samples: 5210588. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:26:53,007][213260] Avg episode reward: [(0, '523.964')] [2023-07-16 19:26:53,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010208_5226496.pth... [2023-07-16 19:26:53,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009488_4857856.pth [2023-07-16 19:26:54,291][213547] Updated weights for policy 0, policy_version 10240 (0.0004) [2023-07-16 19:26:57,524][213547] Updated weights for policy 0, policy_version 10320 (0.0004) [2023-07-16 19:26:58,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12083.2, 300 sec: 12218.6). Total num frames: 5287936. Throughput: 0: 12233.7. Samples: 5286616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:26:58,007][213260] Avg episode reward: [(0, '519.354')] [2023-07-16 19:27:00,741][213547] Updated weights for policy 0, policy_version 10400 (0.0004) [2023-07-16 19:27:03,006][213260] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 12232.5). Total num frames: 5349376. Throughput: 0: 12288.0. Samples: 5324808. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-16 19:27:03,007][213260] Avg episode reward: [(0, '522.129')] [2023-07-16 19:27:04,062][213547] Updated weights for policy 0, policy_version 10480 (0.0004) [2023-07-16 19:27:07,348][213547] Updated weights for policy 0, policy_version 10560 (0.0005) [2023-07-16 19:27:08,006][213260] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 12246.3). Total num frames: 5410816. Throughput: 0: 12332.7. Samples: 5398592. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-16 19:27:08,007][213260] Avg episode reward: [(0, '529.144')] [2023-07-16 19:27:08,017][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010576_5414912.pth... [2023-07-16 19:27:08,019][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009832_5033984.pth [2023-07-16 19:27:10,620][213547] Updated weights for policy 0, policy_version 10640 (0.0004) [2023-07-16 19:27:13,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 12274.1). Total num frames: 5476352. Throughput: 0: 12418.3. Samples: 5474356. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:27:13,007][213260] Avg episode reward: [(0, '531.956')] [2023-07-16 19:27:13,848][213547] Updated weights for policy 0, policy_version 10720 (0.0004) [2023-07-16 19:27:17,129][213547] Updated weights for policy 0, policy_version 10800 (0.0005) [2023-07-16 19:27:18,006][213260] Fps is (10 sec: 12697.7, 60 sec: 12356.3, 300 sec: 12274.1). Total num frames: 5537792. Throughput: 0: 12475.7. Samples: 5512480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:27:18,007][213260] Avg episode reward: [(0, '548.870')] [2023-07-16 19:27:20,358][213547] Updated weights for policy 0, policy_version 10880 (0.0004) [2023-07-16 19:27:23,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12424.5, 300 sec: 12288.0). Total num frames: 5603328. Throughput: 0: 12579.7. Samples: 5587796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:27:23,007][213260] Avg episode reward: [(0, '521.348')] [2023-07-16 19:27:23,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010944_5603328.pth... [2023-07-16 19:27:23,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010208_5226496.pth [2023-07-16 19:27:23,632][213547] Updated weights for policy 0, policy_version 10960 (0.0004) [2023-07-16 19:27:26,824][213547] Updated weights for policy 0, policy_version 11040 (0.0004) [2023-07-16 19:27:28,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12288.0). Total num frames: 5664768. Throughput: 0: 12610.7. Samples: 5664300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:27:28,007][213260] Avg episode reward: [(0, '531.397')] [2023-07-16 19:27:30,022][213547] Updated weights for policy 0, policy_version 11120 (0.0004) [2023-07-16 19:27:33,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 12301.9). Total num frames: 5730304. Throughput: 0: 12582.8. Samples: 5702596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:27:33,007][213260] Avg episode reward: [(0, '516.631')] [2023-07-16 19:27:33,225][213547] Updated weights for policy 0, policy_version 11200 (0.0004) [2023-07-16 19:27:36,497][213547] Updated weights for policy 0, policy_version 11280 (0.0005) [2023-07-16 19:27:38,006][213260] Fps is (10 sec: 12697.5, 60 sec: 12629.3, 300 sec: 12301.9). Total num frames: 5791744. Throughput: 0: 12621.1. Samples: 5778536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:27:38,007][213260] Avg episode reward: [(0, '508.752')] [2023-07-16 19:27:38,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011312_5791744.pth... [2023-07-16 19:27:38,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010576_5414912.pth [2023-07-16 19:27:39,978][213547] Updated weights for policy 0, policy_version 11360 (0.0005) [2023-07-16 19:27:43,006][213260] Fps is (10 sec: 11878.5, 60 sec: 12492.8, 300 sec: 12288.0). Total num frames: 5849088. Throughput: 0: 12499.7. Samples: 5849100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:27:43,007][213260] Avg episode reward: [(0, '501.129')] [2023-07-16 19:27:43,461][213547] Updated weights for policy 0, policy_version 11440 (0.0006) [2023-07-16 19:27:46,901][213547] Updated weights for policy 0, policy_version 11520 (0.0005) [2023-07-16 19:27:48,006][213260] Fps is (10 sec: 11878.5, 60 sec: 12492.8, 300 sec: 12301.9). Total num frames: 5910528. Throughput: 0: 12427.9. Samples: 5884064. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:27:48,007][213260] Avg episode reward: [(0, '494.763')] [2023-07-16 19:27:50,423][213547] Updated weights for policy 0, policy_version 11600 (0.0006) [2023-07-16 19:27:53,006][213260] Fps is (10 sec: 11878.3, 60 sec: 12356.3, 300 sec: 12288.0). Total num frames: 5967872. Throughput: 0: 12363.0. Samples: 5954928. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:27:53,007][213260] Avg episode reward: [(0, '526.558')] [2023-07-16 19:27:53,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011656_5967872.pth... [2023-07-16 19:27:53,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010944_5603328.pth [2023-07-16 19:27:53,992][213547] Updated weights for policy 0, policy_version 11680 (0.0005) [2023-07-16 19:27:57,528][213547] Updated weights for policy 0, policy_version 11760 (0.0005) [2023-07-16 19:27:58,006][213260] Fps is (10 sec: 11468.8, 60 sec: 12288.0, 300 sec: 12274.1). Total num frames: 6025216. Throughput: 0: 12209.1. Samples: 6023764. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-16 19:27:58,007][213260] Avg episode reward: [(0, '512.605')] [2023-07-16 19:28:01,028][213547] Updated weights for policy 0, policy_version 11840 (0.0006) [2023-07-16 19:28:03,006][213260] Fps is (10 sec: 11468.9, 60 sec: 12219.7, 300 sec: 12274.1). Total num frames: 6082560. Throughput: 0: 12136.0. Samples: 6058600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:28:03,007][213260] Avg episode reward: [(0, '513.472')] [2023-07-16 19:28:04,480][213547] Updated weights for policy 0, policy_version 11920 (0.0005) [2023-07-16 19:28:07,939][213547] Updated weights for policy 0, policy_version 12000 (0.0006) [2023-07-16 19:28:08,006][213260] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12274.1). Total num frames: 6144000. Throughput: 0: 12046.1. Samples: 6129872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:28:08,007][213260] Avg episode reward: [(0, '522.758')] [2023-07-16 19:28:08,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012000_6144000.pth... [2023-07-16 19:28:08,012][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011312_5791744.pth [2023-07-16 19:28:11,421][213547] Updated weights for policy 0, policy_version 12080 (0.0005) [2023-07-16 19:28:13,006][213260] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12246.3). Total num frames: 6201344. Throughput: 0: 11925.9. Samples: 6200964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:28:13,007][213260] Avg episode reward: [(0, '522.737')] [2023-07-16 19:28:14,944][213547] Updated weights for policy 0, policy_version 12160 (0.0005) [2023-07-16 19:28:18,006][213260] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 12232.5). Total num frames: 6258688. Throughput: 0: 11836.6. Samples: 6235244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:28:18,007][213260] Avg episode reward: [(0, '525.807')] [2023-07-16 19:28:18,429][213547] Updated weights for policy 0, policy_version 12240 (0.0006) [2023-07-16 19:28:21,985][213547] Updated weights for policy 0, policy_version 12320 (0.0005) [2023-07-16 19:28:23,006][213260] Fps is (10 sec: 11468.7, 60 sec: 11878.4, 300 sec: 12218.6). Total num frames: 6316032. Throughput: 0: 11689.2. Samples: 6304548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:28:23,007][213260] Avg episode reward: [(0, '519.265')] [2023-07-16 19:28:23,024][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012344_6320128.pth... [2023-07-16 19:28:23,026][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011656_5967872.pth [2023-07-16 19:28:25,392][213547] Updated weights for policy 0, policy_version 12400 (0.0005) [2023-07-16 19:28:28,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12204.7). Total num frames: 6377472. Throughput: 0: 11741.8. Samples: 6377480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:28:28,007][213260] Avg episode reward: [(0, '515.376')] [2023-07-16 19:28:28,773][213547] Updated weights for policy 0, policy_version 12480 (0.0005) [2023-07-16 19:28:32,215][213547] Updated weights for policy 0, policy_version 12560 (0.0006) [2023-07-16 19:28:33,006][213260] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 12204.7). Total num frames: 6438912. Throughput: 0: 11770.5. Samples: 6413736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:28:33,007][213260] Avg episode reward: [(0, '509.599')] [2023-07-16 19:28:35,670][213547] Updated weights for policy 0, policy_version 12640 (0.0006) [2023-07-16 19:28:38,006][213260] Fps is (10 sec: 11878.2, 60 sec: 11741.8, 300 sec: 12190.8). Total num frames: 6496256. Throughput: 0: 11758.0. Samples: 6484040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:28:38,007][213260] Avg episode reward: [(0, '506.499')] [2023-07-16 19:28:38,011][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012688_6496256.pth... [2023-07-16 19:28:38,014][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012000_6144000.pth [2023-07-16 19:28:39,235][213547] Updated weights for policy 0, policy_version 12720 (0.0006) [2023-07-16 19:28:42,724][213547] Updated weights for policy 0, policy_version 12800 (0.0005) [2023-07-16 19:28:43,006][213260] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 12176.9). Total num frames: 6553600. Throughput: 0: 11775.6. Samples: 6553664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:28:43,007][213260] Avg episode reward: [(0, '552.128')] [2023-07-16 19:28:46,237][213547] Updated weights for policy 0, policy_version 12880 (0.0005) [2023-07-16 19:28:48,006][213260] Fps is (10 sec: 11878.6, 60 sec: 11741.9, 300 sec: 12163.0). Total num frames: 6615040. Throughput: 0: 11783.8. Samples: 6588872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:28:48,007][213260] Avg episode reward: [(0, '533.852')] [2023-07-16 19:28:49,777][213547] Updated weights for policy 0, policy_version 12960 (0.0005) [2023-07-16 19:28:53,006][213260] Fps is (10 sec: 11878.3, 60 sec: 11741.9, 300 sec: 12149.1). Total num frames: 6672384. Throughput: 0: 11756.1. Samples: 6658896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:28:53,007][213260] Avg episode reward: [(0, '541.600')] [2023-07-16 19:28:53,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013032_6672384.pth... [2023-07-16 19:28:53,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012344_6320128.pth [2023-07-16 19:28:53,313][213547] Updated weights for policy 0, policy_version 13040 (0.0006) [2023-07-16 19:28:56,833][213547] Updated weights for policy 0, policy_version 13120 (0.0005) [2023-07-16 19:28:58,006][213260] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 12121.4). Total num frames: 6729728. Throughput: 0: 11719.2. Samples: 6728328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:28:58,007][213260] Avg episode reward: [(0, '554.882')] [2023-07-16 19:29:00,302][213547] Updated weights for policy 0, policy_version 13200 (0.0006) [2023-07-16 19:29:03,006][213260] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 12093.6). Total num frames: 6787072. Throughput: 0: 11737.8. Samples: 6763444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:29:03,007][213260] Avg episode reward: [(0, '519.060')] [2023-07-16 19:29:03,854][213547] Updated weights for policy 0, policy_version 13280 (0.0005) [2023-07-16 19:29:07,243][213547] Updated weights for policy 0, policy_version 13360 (0.0005) [2023-07-16 19:29:08,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 12079.7). Total num frames: 6848512. Throughput: 0: 11765.1. Samples: 6833976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:29:08,025][213260] Avg episode reward: [(0, '530.660')] [2023-07-16 19:29:08,028][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013376_6848512.pth... [2023-07-16 19:29:08,031][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012688_6496256.pth [2023-07-16 19:29:10,559][213547] Updated weights for policy 0, policy_version 13440 (0.0005) [2023-07-16 19:29:13,006][213260] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 12065.8). Total num frames: 6909952. Throughput: 0: 11809.6. Samples: 6908912. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:29:13,007][213260] Avg episode reward: [(0, '520.519')] [2023-07-16 19:29:13,899][213547] Updated weights for policy 0, policy_version 13520 (0.0004) [2023-07-16 19:29:17,365][213547] Updated weights for policy 0, policy_version 13600 (0.0006) [2023-07-16 19:29:18,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12052.0). Total num frames: 6967296. Throughput: 0: 11784.0. Samples: 6944016. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:29:18,007][213260] Avg episode reward: [(0, '536.930')] [2023-07-16 19:29:20,876][213547] Updated weights for policy 0, policy_version 13680 (0.0005) [2023-07-16 19:29:23,006][213260] Fps is (10 sec: 11468.7, 60 sec: 11810.1, 300 sec: 12024.2). Total num frames: 7024640. Throughput: 0: 11788.1. Samples: 7014504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:29:23,007][213260] Avg episode reward: [(0, '536.552')] [2023-07-16 19:29:23,013][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013728_7028736.pth... [2023-07-16 19:29:23,016][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013032_6672384.pth [2023-07-16 19:29:24,404][213547] Updated weights for policy 0, policy_version 13760 (0.0005) [2023-07-16 19:29:27,855][213547] Updated weights for policy 0, policy_version 13840 (0.0006) [2023-07-16 19:29:28,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12024.2). Total num frames: 7086080. Throughput: 0: 11803.7. Samples: 7084832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:29:28,007][213260] Avg episode reward: [(0, '522.125')] [2023-07-16 19:29:31,448][213547] Updated weights for policy 0, policy_version 13920 (0.0005) [2023-07-16 19:29:33,006][213260] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 12010.3). Total num frames: 7143424. Throughput: 0: 11778.7. Samples: 7118912. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-16 19:29:33,007][213260] Avg episode reward: [(0, '538.345')] [2023-07-16 19:29:34,961][213547] Updated weights for policy 0, policy_version 14000 (0.0006) [2023-07-16 19:29:38,006][213260] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11996.4). Total num frames: 7200768. Throughput: 0: 11771.7. Samples: 7188624. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-16 19:29:38,007][213260] Avg episode reward: [(0, '530.268')] [2023-07-16 19:29:38,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014064_7200768.pth... [2023-07-16 19:29:38,011][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013376_6848512.pth [2023-07-16 19:29:38,436][213547] Updated weights for policy 0, policy_version 14080 (0.0005) [2023-07-16 19:29:41,891][213547] Updated weights for policy 0, policy_version 14160 (0.0005) [2023-07-16 19:29:43,006][213260] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11996.4). Total num frames: 7262208. Throughput: 0: 11827.5. Samples: 7260564. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-16 19:29:43,007][213260] Avg episode reward: [(0, '531.514')] [2023-07-16 19:29:45,195][213547] Updated weights for policy 0, policy_version 14240 (0.0004) [2023-07-16 19:29:48,006][213260] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 12010.3). Total num frames: 7323648. Throughput: 0: 11865.5. Samples: 7297392. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-16 19:29:48,007][213260] Avg episode reward: [(0, '525.108')] [2023-07-16 19:29:48,507][213547] Updated weights for policy 0, policy_version 14320 (0.0005) [2023-07-16 19:29:51,818][213547] Updated weights for policy 0, policy_version 14400 (0.0004) [2023-07-16 19:29:53,006][213260] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 12024.2). Total num frames: 7385088. Throughput: 0: 11955.2. Samples: 7371960. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:29:53,007][213260] Avg episode reward: [(0, '522.828')] [2023-07-16 19:29:53,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014424_7385088.pth... [2023-07-16 19:29:53,012][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013728_7028736.pth [2023-07-16 19:29:55,080][213547] Updated weights for policy 0, policy_version 14480 (0.0003) [2023-07-16 19:29:58,006][213260] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12024.2). Total num frames: 7446528. Throughput: 0: 11951.2. Samples: 7446716. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:29:58,007][213260] Avg episode reward: [(0, '511.140')] [2023-07-16 19:29:58,372][213547] Updated weights for policy 0, policy_version 14560 (0.0004) [2023-07-16 19:30:01,587][213547] Updated weights for policy 0, policy_version 14640 (0.0003) [2023-07-16 19:30:03,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12083.2, 300 sec: 12024.2). Total num frames: 7512064. Throughput: 0: 12009.9. Samples: 7484460. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:30:03,007][213260] Avg episode reward: [(0, '506.501')] [2023-07-16 19:30:04,883][213547] Updated weights for policy 0, policy_version 14720 (0.0004) [2023-07-16 19:30:08,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12083.2, 300 sec: 12024.2). Total num frames: 7573504. Throughput: 0: 12128.1. Samples: 7560268. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:30:08,007][213260] Avg episode reward: [(0, '493.856')] [2023-07-16 19:30:08,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014792_7573504.pth... [2023-07-16 19:30:08,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014064_7200768.pth [2023-07-16 19:30:08,119][213547] Updated weights for policy 0, policy_version 14800 (0.0004) [2023-07-16 19:30:11,313][213547] Updated weights for policy 0, policy_version 14880 (0.0003) [2023-07-16 19:30:13,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 12024.2). Total num frames: 7639040. Throughput: 0: 12250.5. Samples: 7636104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:30:13,007][213260] Avg episode reward: [(0, '511.961')] [2023-07-16 19:30:14,584][213547] Updated weights for policy 0, policy_version 14960 (0.0004) [2023-07-16 19:30:17,827][213547] Updated weights for policy 0, policy_version 15040 (0.0004) [2023-07-16 19:30:18,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 12038.1). Total num frames: 7700480. Throughput: 0: 12332.3. Samples: 7673868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:30:18,007][213260] Avg episode reward: [(0, '496.579')] [2023-07-16 19:30:21,052][213547] Updated weights for policy 0, policy_version 15120 (0.0004) [2023-07-16 19:30:23,006][213260] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12038.1). Total num frames: 7761920. Throughput: 0: 12468.4. Samples: 7749704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:30:23,007][213260] Avg episode reward: [(0, '496.689')] [2023-07-16 19:30:23,015][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015168_7766016.pth... [2023-07-16 19:30:23,017][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014424_7385088.pth [2023-07-16 19:30:24,288][213547] Updated weights for policy 0, policy_version 15200 (0.0004) [2023-07-16 19:30:27,542][213547] Updated weights for policy 0, policy_version 15280 (0.0004) [2023-07-16 19:30:28,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 12065.8). Total num frames: 7827456. Throughput: 0: 12562.2. Samples: 7825864. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-16 19:30:28,007][213260] Avg episode reward: [(0, '500.642')] [2023-07-16 19:30:30,952][213547] Updated weights for policy 0, policy_version 15360 (0.0005) [2023-07-16 19:30:33,006][213260] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12052.0). Total num frames: 7884800. Throughput: 0: 12547.7. Samples: 7862036. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-16 19:30:33,007][213260] Avg episode reward: [(0, '529.940')] [2023-07-16 19:30:34,462][213547] Updated weights for policy 0, policy_version 15440 (0.0005) [2023-07-16 19:30:37,954][213547] Updated weights for policy 0, policy_version 15520 (0.0005) [2023-07-16 19:30:38,006][213260] Fps is (10 sec: 11878.4, 60 sec: 12424.5, 300 sec: 12065.8). Total num frames: 7946240. Throughput: 0: 12455.6. Samples: 7932460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:30:38,007][213260] Avg episode reward: [(0, '530.558')] [2023-07-16 19:30:38,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015520_7946240.pth... [2023-07-16 19:30:38,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014792_7573504.pth [2023-07-16 19:30:41,419][213547] Updated weights for policy 0, policy_version 15600 (0.0005) [2023-07-16 19:30:43,006][213260] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12052.0). Total num frames: 8003584. Throughput: 0: 12362.7. Samples: 8003036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:30:43,007][213260] Avg episode reward: [(0, '528.410')] [2023-07-16 19:30:44,955][213547] Updated weights for policy 0, policy_version 15680 (0.0005) [2023-07-16 19:30:48,006][213260] Fps is (10 sec: 11468.9, 60 sec: 12288.0, 300 sec: 12052.0). Total num frames: 8060928. Throughput: 0: 12282.3. Samples: 8037164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:30:48,006][213260] Avg episode reward: [(0, '513.102')] [2023-07-16 19:30:48,445][213547] Updated weights for policy 0, policy_version 15760 (0.0005) [2023-07-16 19:30:51,939][213547] Updated weights for policy 0, policy_version 15840 (0.0005) [2023-07-16 19:30:53,006][213260] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12065.8). Total num frames: 8122368. Throughput: 0: 12169.9. Samples: 8107912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:30:53,007][213260] Avg episode reward: [(0, '539.056')] [2023-07-16 19:30:53,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015864_8122368.pth... [2023-07-16 19:30:53,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015168_7766016.pth [2023-07-16 19:30:55,434][213547] Updated weights for policy 0, policy_version 15920 (0.0005) [2023-07-16 19:30:58,006][213260] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12065.8). Total num frames: 8179712. Throughput: 0: 12069.4. Samples: 8179228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:30:58,007][213260] Avg episode reward: [(0, '504.306')] [2023-07-16 19:30:58,868][213547] Updated weights for policy 0, policy_version 16000 (0.0005) [2023-07-16 19:31:02,327][213547] Updated weights for policy 0, policy_version 16080 (0.0005) [2023-07-16 19:31:03,006][213260] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 12052.0). Total num frames: 8237056. Throughput: 0: 12008.9. Samples: 8214268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:31:03,007][213260] Avg episode reward: [(0, '553.921')] [2023-07-16 19:31:05,867][213547] Updated weights for policy 0, policy_version 16160 (0.0005) [2023-07-16 19:31:08,006][213260] Fps is (10 sec: 11878.2, 60 sec: 12083.2, 300 sec: 12065.8). Total num frames: 8298496. Throughput: 0: 11873.9. Samples: 8284032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:31:08,007][213260] Avg episode reward: [(0, '538.154')] [2023-07-16 19:31:08,011][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016208_8298496.pth... [2023-07-16 19:31:08,014][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015520_7946240.pth [2023-07-16 19:31:09,287][213547] Updated weights for policy 0, policy_version 16240 (0.0005) [2023-07-16 19:31:12,858][213547] Updated weights for policy 0, policy_version 16320 (0.0005) [2023-07-16 19:31:13,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12065.8). Total num frames: 8355840. Throughput: 0: 11757.1. Samples: 8354936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:31:13,007][213260] Avg episode reward: [(0, '543.617')] [2023-07-16 19:31:16,021][213547] Updated weights for policy 0, policy_version 16400 (0.0004) [2023-07-16 19:31:18,006][213260] Fps is (10 sec: 12288.2, 60 sec: 12014.9, 300 sec: 12079.7). Total num frames: 8421376. Throughput: 0: 11794.2. Samples: 8392776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:31:18,007][213260] Avg episode reward: [(0, '539.390')] [2023-07-16 19:31:19,228][213547] Updated weights for policy 0, policy_version 16480 (0.0004) [2023-07-16 19:31:22,401][213547] Updated weights for policy 0, policy_version 16560 (0.0004) [2023-07-16 19:31:23,006][213260] Fps is (10 sec: 12697.6, 60 sec: 12014.9, 300 sec: 12093.6). Total num frames: 8482816. Throughput: 0: 11957.1. Samples: 8470528. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-16 19:31:23,007][213260] Avg episode reward: [(0, '538.507')] [2023-07-16 19:31:23,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016568_8482816.pth... [2023-07-16 19:31:23,012][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015864_8122368.pth [2023-07-16 19:31:25,686][213547] Updated weights for policy 0, policy_version 16640 (0.0004) [2023-07-16 19:31:28,006][213260] Fps is (10 sec: 12288.1, 60 sec: 11946.7, 300 sec: 12093.6). Total num frames: 8544256. Throughput: 0: 12028.7. Samples: 8544328. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-16 19:31:28,007][213260] Avg episode reward: [(0, '533.157')] [2023-07-16 19:31:29,092][213547] Updated weights for policy 0, policy_version 16720 (0.0005) [2023-07-16 19:31:32,500][213547] Updated weights for policy 0, policy_version 16800 (0.0005) [2023-07-16 19:31:33,006][213260] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 12107.5). Total num frames: 8605696. Throughput: 0: 12080.3. Samples: 8580776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:31:33,007][213260] Avg episode reward: [(0, '528.947')] [2023-07-16 19:31:35,908][213547] Updated weights for policy 0, policy_version 16880 (0.0005) [2023-07-16 19:31:38,006][213260] Fps is (10 sec: 12287.8, 60 sec: 12014.9, 300 sec: 12093.6). Total num frames: 8667136. Throughput: 0: 12120.9. Samples: 8653352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:31:38,007][213260] Avg episode reward: [(0, '538.502')] [2023-07-16 19:31:38,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016928_8667136.pth... [2023-07-16 19:31:38,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016208_8298496.pth [2023-07-16 19:31:39,254][213547] Updated weights for policy 0, policy_version 16960 (0.0005) [2023-07-16 19:31:42,632][213547] Updated weights for policy 0, policy_version 17040 (0.0005) [2023-07-16 19:31:43,006][213260] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12093.6). Total num frames: 8728576. Throughput: 0: 12141.8. Samples: 8725608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:31:43,007][213260] Avg episode reward: [(0, '548.874')] [2023-07-16 19:31:46,130][213547] Updated weights for policy 0, policy_version 17120 (0.0005) [2023-07-16 19:31:48,006][213260] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12065.8). Total num frames: 8785920. Throughput: 0: 12149.9. Samples: 8761012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:31:48,007][213260] Avg episode reward: [(0, '533.208')] [2023-07-16 19:31:49,564][213547] Updated weights for policy 0, policy_version 17200 (0.0005) [2023-07-16 19:31:53,006][213260] Fps is (10 sec: 11468.7, 60 sec: 12014.9, 300 sec: 12052.0). Total num frames: 8843264. Throughput: 0: 12175.3. Samples: 8831920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:31:53,007][213260] Avg episode reward: [(0, '529.795')] [2023-07-16 19:31:53,040][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017280_8847360.pth... [2023-07-16 19:31:53,040][213547] Updated weights for policy 0, policy_version 17280 (0.0005) [2023-07-16 19:31:53,042][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016568_8482816.pth [2023-07-16 19:31:56,495][213547] Updated weights for policy 0, policy_version 17360 (0.0005) [2023-07-16 19:31:58,006][213260] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12052.0). Total num frames: 8904704. Throughput: 0: 12188.7. Samples: 8903428. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-16 19:31:58,007][213260] Avg episode reward: [(0, '529.614')] [2023-07-16 19:31:59,984][213547] Updated weights for policy 0, policy_version 17440 (0.0005) [2023-07-16 19:32:03,006][213260] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12038.1). Total num frames: 8962048. Throughput: 0: 12126.3. Samples: 8938460. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-16 19:32:03,007][213260] Avg episode reward: [(0, '542.682')] [2023-07-16 19:32:03,398][213547] Updated weights for policy 0, policy_version 17520 (0.0005) [2023-07-16 19:32:06,813][213547] Updated weights for policy 0, policy_version 17600 (0.0005) [2023-07-16 19:32:08,006][213260] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12024.2). Total num frames: 9023488. Throughput: 0: 12008.3. Samples: 9010900. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-16 19:32:08,007][213260] Avg episode reward: [(0, '532.665')] [2023-07-16 19:32:08,009][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017624_9023488.pth... [2023-07-16 19:32:08,012][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016928_8667136.pth [2023-07-16 19:32:10,215][213547] Updated weights for policy 0, policy_version 17680 (0.0005) [2023-07-16 19:32:13,006][213260] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12010.3). Total num frames: 9080832. Throughput: 0: 11924.1. Samples: 9080912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:32:13,006][213260] Avg episode reward: [(0, '532.120')] [2023-07-16 19:32:13,727][213547] Updated weights for policy 0, policy_version 17760 (0.0005) [2023-07-16 19:32:17,128][213547] Updated weights for policy 0, policy_version 17840 (0.0005) [2023-07-16 19:32:18,006][213260] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 11996.4). Total num frames: 9142272. Throughput: 0: 11931.7. Samples: 9117704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:32:18,007][213260] Avg episode reward: [(0, '551.761')] [2023-07-16 19:32:20,636][213547] Updated weights for policy 0, policy_version 17920 (0.0005) [2023-07-16 19:32:23,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11982.5). Total num frames: 9199616. Throughput: 0: 11881.4. Samples: 9188012. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:32:23,007][213260] Avg episode reward: [(0, '524.372')] [2023-07-16 19:32:23,022][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017976_9203712.pth... [2023-07-16 19:32:23,025][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017280_8847360.pth [2023-07-16 19:32:24,053][213547] Updated weights for policy 0, policy_version 18000 (0.0005) [2023-07-16 19:32:27,554][213547] Updated weights for policy 0, policy_version 18080 (0.0005) [2023-07-16 19:32:28,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11968.7). Total num frames: 9261056. Throughput: 0: 11859.5. Samples: 9259284. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:32:28,007][213260] Avg episode reward: [(0, '536.282')] [2023-07-16 19:32:31,070][213547] Updated weights for policy 0, policy_version 18160 (0.0005) [2023-07-16 19:32:33,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11954.8). Total num frames: 9318400. Throughput: 0: 11841.9. Samples: 9293896. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-16 19:32:33,007][213260] Avg episode reward: [(0, '552.094')] [2023-07-16 19:32:34,508][213547] Updated weights for policy 0, policy_version 18240 (0.0005) [2023-07-16 19:32:37,902][213547] Updated weights for policy 0, policy_version 18320 (0.0005) [2023-07-16 19:32:38,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11968.6). Total num frames: 9379840. Throughput: 0: 11867.9. Samples: 9365976. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:32:38,007][213260] Avg episode reward: [(0, '528.604')] [2023-07-16 19:32:38,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018320_9379840.pth... [2023-07-16 19:32:38,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017624_9023488.pth [2023-07-16 19:32:41,368][213547] Updated weights for policy 0, policy_version 18400 (0.0005) [2023-07-16 19:32:43,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11954.8). Total num frames: 9437184. Throughput: 0: 11861.3. Samples: 9437184. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:32:43,007][213260] Avg episode reward: [(0, '531.382')] [2023-07-16 19:32:44,854][213547] Updated weights for policy 0, policy_version 18480 (0.0005) [2023-07-16 19:32:48,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11968.7). Total num frames: 9498624. Throughput: 0: 11875.0. Samples: 9472836. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-16 19:32:48,007][213260] Avg episode reward: [(0, '522.087')] [2023-07-16 19:32:48,281][213547] Updated weights for policy 0, policy_version 18560 (0.0005) [2023-07-16 19:32:51,535][213547] Updated weights for policy 0, policy_version 18640 (0.0005) [2023-07-16 19:32:53,006][213260] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11982.5). Total num frames: 9560064. Throughput: 0: 11899.0. Samples: 9546356. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:32:53,007][213260] Avg episode reward: [(0, '516.954')] [2023-07-16 19:32:53,010][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018672_9560064.pth... [2023-07-16 19:32:53,013][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017976_9203712.pth [2023-07-16 19:32:54,968][213547] Updated weights for policy 0, policy_version 18720 (0.0004) [2023-07-16 19:32:58,006][213260] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11982.5). Total num frames: 9617408. Throughput: 0: 11923.6. Samples: 9617472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:32:58,007][213260] Avg episode reward: [(0, '527.065')] [2023-07-16 19:32:58,432][213547] Updated weights for policy 0, policy_version 18800 (0.0005) [2023-07-16 19:33:01,830][213547] Updated weights for policy 0, policy_version 18880 (0.0005) [2023-07-16 19:33:03,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11982.5). Total num frames: 9678848. Throughput: 0: 11919.1. Samples: 9654064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:33:03,007][213260] Avg episode reward: [(0, '514.918')] [2023-07-16 19:33:05,335][213547] Updated weights for policy 0, policy_version 18960 (0.0005) [2023-07-16 19:33:08,006][213260] Fps is (10 sec: 11878.2, 60 sec: 11878.4, 300 sec: 11982.5). Total num frames: 9736192. Throughput: 0: 11912.4. Samples: 9724072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:33:08,007][213260] Avg episode reward: [(0, '545.762')] [2023-07-16 19:33:08,047][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019024_9740288.pth... [2023-07-16 19:33:08,050][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018320_9379840.pth [2023-07-16 19:33:08,743][213547] Updated weights for policy 0, policy_version 19040 (0.0005) [2023-07-16 19:33:12,232][213547] Updated weights for policy 0, policy_version 19120 (0.0005) [2023-07-16 19:33:13,006][213260] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11996.4). Total num frames: 9797632. Throughput: 0: 11921.0. Samples: 9795728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:33:13,007][213260] Avg episode reward: [(0, '523.678')] [2023-07-16 19:33:15,385][213547] Updated weights for policy 0, policy_version 19200 (0.0004) [2023-07-16 19:33:18,006][213260] Fps is (10 sec: 12697.7, 60 sec: 12014.9, 300 sec: 12024.2). Total num frames: 9863168. Throughput: 0: 12019.3. Samples: 9834764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:33:18,007][213260] Avg episode reward: [(0, '537.796')] [2023-07-16 19:33:18,577][213547] Updated weights for policy 0, policy_version 19280 (0.0004) [2023-07-16 19:33:22,077][213547] Updated weights for policy 0, policy_version 19360 (0.0005) [2023-07-16 19:33:23,006][213260] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 12010.3). Total num frames: 9920512. Throughput: 0: 12051.5. Samples: 9908296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:33:23,007][213260] Avg episode reward: [(0, '545.265')] [2023-07-16 19:33:23,011][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019376_9920512.pth... [2023-07-16 19:33:23,014][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018672_9560064.pth [2023-07-16 19:33:25,485][213547] Updated weights for policy 0, policy_version 19440 (0.0005) [2023-07-16 19:33:28,006][213260] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12010.3). Total num frames: 9981952. Throughput: 0: 12073.1. Samples: 9980472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-16 19:33:28,007][213260] Avg episode reward: [(0, '536.135')] [2023-07-16 19:33:28,856][213547] Updated weights for policy 0, policy_version 19520 (0.0005) [2023-07-16 19:33:29,897][213503] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 [2023-07-16 19:33:29,898][213552] Stopping RolloutWorker_w4... [2023-07-16 19:33:29,898][213584] Stopping RolloutWorker_w5... [2023-07-16 19:33:29,898][213503] Stopping Batcher_0... [2023-07-16 19:33:29,898][213552] Loop rollout_proc4_evt_loop terminating... [2023-07-16 19:33:29,898][213551] Stopping RolloutWorker_w3... [2023-07-16 19:33:29,898][213548] Stopping RolloutWorker_w0... [2023-07-16 19:33:29,898][213550] Stopping RolloutWorker_w1... [2023-07-16 19:33:29,898][213584] Loop rollout_proc5_evt_loop terminating... [2023-07-16 19:33:29,898][213551] Loop rollout_proc3_evt_loop terminating... [2023-07-16 19:33:29,898][213548] Loop rollout_proc0_evt_loop terminating... [2023-07-16 19:33:29,898][213550] Loop rollout_proc1_evt_loop terminating... [2023-07-16 19:33:29,898][213549] Stopping RolloutWorker_w2... [2023-07-16 19:33:29,898][213616] Stopping RolloutWorker_w6... [2023-07-16 19:33:29,898][213648] Stopping RolloutWorker_w7... [2023-07-16 19:33:29,898][213260] Component RolloutWorker_w4 stopped! [2023-07-16 19:33:29,899][213549] Loop rollout_proc2_evt_loop terminating... [2023-07-16 19:33:29,899][213503] Loop batcher_evt_loop terminating... [2023-07-16 19:33:29,899][213616] Loop rollout_proc6_evt_loop terminating... [2023-07-16 19:33:29,899][213648] Loop rollout_proc7_evt_loop terminating... [2023-07-16 19:33:29,899][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... [2023-07-16 19:33:29,899][213260] Component RolloutWorker_w5 stopped! [2023-07-16 19:33:29,899][213260] Component RolloutWorker_w3 stopped! [2023-07-16 19:33:29,899][213260] Component RolloutWorker_w0 stopped! [2023-07-16 19:33:29,900][213260] Component Batcher_0 stopped! [2023-07-16 19:33:29,900][213260] Component RolloutWorker_w1 stopped! [2023-07-16 19:33:29,900][213260] Component RolloutWorker_w2 stopped! [2023-07-16 19:33:29,900][213260] Component RolloutWorker_w6 stopped! [2023-07-16 19:33:29,900][213260] Component RolloutWorker_w7 stopped! [2023-07-16 19:33:29,902][213503] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019024_9740288.pth [2023-07-16 19:33:29,902][213503] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... [2023-07-16 19:33:29,905][213503] Stopping LearnerWorker_p0... [2023-07-16 19:33:29,905][213503] Loop learner_proc0_evt_loop terminating... [2023-07-16 19:33:29,905][213260] Component LearnerWorker_p0 stopped! [2023-07-16 19:33:29,932][213547] Weights refcount: 2 0 [2023-07-16 19:33:29,933][213547] Stopping InferenceWorker_p0-w0... [2023-07-16 19:33:29,933][213547] Loop inference_proc0-0_evt_loop terminating... [2023-07-16 19:33:29,933][213260] Component InferenceWorker_p0-w0 stopped! [2023-07-16 19:33:29,934][213260] Waiting for process learner_proc0 to stop... [2023-07-16 19:33:30,501][213260] Waiting for process inference_proc0-0 to join... [2023-07-16 19:33:30,505][213260] Waiting for process rollout_proc0 to join... [2023-07-16 19:33:30,505][213260] Waiting for process rollout_proc1 to join... [2023-07-16 19:33:30,506][213260] Waiting for process rollout_proc2 to join... [2023-07-16 19:33:30,506][213260] Waiting for process rollout_proc3 to join... [2023-07-16 19:33:30,506][213260] Waiting for process rollout_proc4 to join... [2023-07-16 19:33:30,506][213260] Waiting for process rollout_proc5 to join... [2023-07-16 19:33:30,506][213260] Waiting for process rollout_proc6 to join... [2023-07-16 19:33:30,508][213260] Waiting for process rollout_proc7 to join... [2023-07-16 19:33:30,509][213260] Batcher 0 profile tree view: batching: 1.7492, releasing_batches: 1.4875 [2023-07-16 19:33:30,509][213260] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0000 wait_policy_total: 272.1282 update_model: 10.7865 weight_update: 0.0005 one_step: 0.0010 handle_policy_step: 487.2929 deserialize: 20.6812, stack: 5.2650, obs_to_device_normalize: 88.1839, forward: 240.2190, send_messages: 36.2609 prepare_outputs: 55.5595 to_cpu: 8.3192 [2023-07-16 19:33:30,509][213260] Learner 0 profile tree view: misc: 0.0100, prepare_batch: 10.0392 train: 103.8959 epoch_init: 0.0379, minibatch_init: 1.4223, losses_postprocess: 1.3884, kl_divergence: 0.4756, after_optimizer: 0.6382 calculate_losses: 44.3784 losses_init: 0.0339, forward_head: 17.4271, bptt_initial: 0.1494, bptt: 0.1376, tail: 12.4326, advantages_returns: 0.9522, losses: 11.7028 update: 53.8368 clip: 6.3762 [2023-07-16 19:33:30,509][213260] RolloutWorker_w0 profile tree view: wait_for_trajectories: 0.2719, enqueue_policy_requests: 12.3823, env_step: 559.1779, overhead: 19.4146, complete_rollouts: 0.3166 save_policy_outputs: 38.9434 split_output_tensors: 13.3109 [2023-07-16 19:33:30,509][213260] RolloutWorker_w7 profile tree view: wait_for_trajectories: 0.2714, enqueue_policy_requests: 12.4598, env_step: 557.0473, overhead: 19.3580, complete_rollouts: 0.3124 save_policy_outputs: 38.0894 split_output_tensors: 13.0903 [2023-07-16 19:33:30,510][213260] Loop Runner_EvtLoop terminating... [2023-07-16 19:33:30,510][213260] Runner profile tree view: main_loop: 830.4665 [2023-07-16 19:33:30,510][213260] Collected {0: 10006528}, FPS: 12049.3