diff --git "a/sf_log.txt" "b/sf_log.txt" --- "a/sf_log.txt" +++ "b/sf_log.txt" @@ -1,37 +1,33 @@ -[2023-07-08 17:25:37,963][1025936] Saving configuration to /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/config.json... -[2023-07-08 17:25:37,981][1025936] Rollout worker 0 uses device cpu -[2023-07-08 17:25:37,982][1025936] Rollout worker 1 uses device cpu -[2023-07-08 17:25:37,982][1025936] Rollout worker 2 uses device cpu -[2023-07-08 17:25:37,982][1025936] Rollout worker 3 uses device cpu -[2023-07-08 17:25:37,982][1025936] Rollout worker 4 uses device cpu -[2023-07-08 17:25:37,982][1025936] Rollout worker 5 uses device cpu -[2023-07-08 17:25:37,982][1025936] Rollout worker 6 uses device cpu -[2023-07-08 17:25:37,983][1025936] Rollout worker 7 uses device cpu -[2023-07-08 17:25:37,983][1025936] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 -[2023-07-08 17:25:37,995][1025936] InferenceWorker_p0-w0: min num requests: 2 -[2023-07-08 17:25:38,015][1025936] Starting all processes... -[2023-07-08 17:25:38,015][1025936] Starting process learner_proc0 -[2023-07-08 17:25:38,023][1025936] Starting all processes... -[2023-07-08 17:25:38,027][1025936] Starting process inference_proc0-0 -[2023-07-08 17:25:38,027][1025936] Starting process rollout_proc0 -[2023-07-08 17:25:38,028][1025936] Starting process rollout_proc1 -[2023-07-08 17:25:38,028][1025936] Starting process rollout_proc2 -[2023-07-08 17:25:38,028][1025936] Starting process rollout_proc3 -[2023-07-08 17:25:38,028][1025936] Starting process rollout_proc4 -[2023-07-08 17:25:38,028][1025936] Starting process rollout_proc5 -[2023-07-08 17:25:38,029][1025936] Starting process rollout_proc6 -[2023-07-08 17:25:38,036][1025936] Starting process rollout_proc7 -[2023-07-08 17:25:40,196][1026289] Worker 7 uses CPU cores [28, 29, 30, 31] -[2023-07-08 17:25:40,266][1026256] Worker 4 uses CPU cores [16, 17, 18, 19] -[2023-07-08 17:25:40,381][1026291] Worker 6 uses CPU cores [24, 25, 26, 27] -[2023-07-08 17:25:40,567][1026257] Worker 5 uses CPU cores [20, 21, 22, 23] -[2023-07-08 17:25:40,681][1026224] Worker 2 uses CPU cores [8, 9, 10, 11] -[2023-07-08 17:25:40,789][1026177] Starting seed is not provided -[2023-07-08 17:25:40,789][1026177] Initializing actor-critic model on device cpu -[2023-07-08 17:25:40,790][1026177] RunningMeanStd input shape: (39,) -[2023-07-08 17:25:40,790][1026177] RunningMeanStd input shape: (1,) -[2023-07-08 17:25:40,847][1026177] Created Actor Critic model with architecture: -[2023-07-08 17:25:40,847][1026177] ActorCriticSharedWeights( +[2023-07-16 22:38:29,977][253751] Saving configuration to /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/config.json... +[2023-07-16 22:38:29,992][253751] Rollout worker 0 uses device cpu +[2023-07-16 22:38:29,993][253751] Rollout worker 1 uses device cpu +[2023-07-16 22:38:29,993][253751] Rollout worker 2 uses device cpu +[2023-07-16 22:38:29,993][253751] Rollout worker 3 uses device cpu +[2023-07-16 22:38:29,993][253751] Rollout worker 4 uses device cpu +[2023-07-16 22:38:29,993][253751] Rollout worker 5 uses device cpu +[2023-07-16 22:38:29,993][253751] Rollout worker 6 uses device cpu +[2023-07-16 22:38:29,993][253751] Rollout worker 7 uses device cpu +[2023-07-16 22:38:29,993][253751] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 +[2023-07-16 22:38:30,004][253751] InferenceWorker_p0-w0: min num requests: 2 +[2023-07-16 22:38:30,021][253751] Starting all processes... +[2023-07-16 22:38:30,021][253751] Starting process learner_proc0 +[2023-07-16 22:38:30,070][253751] Starting all processes... +[2023-07-16 22:38:30,104][253751] Starting process inference_proc0-0 +[2023-07-16 22:38:30,104][253751] Starting process rollout_proc0 +[2023-07-16 22:38:30,104][253751] Starting process rollout_proc1 +[2023-07-16 22:38:30,104][253751] Starting process rollout_proc2 +[2023-07-16 22:38:30,105][253751] Starting process rollout_proc3 +[2023-07-16 22:38:30,105][253751] Starting process rollout_proc4 +[2023-07-16 22:38:30,105][253751] Starting process rollout_proc5 +[2023-07-16 22:38:30,105][253751] Starting process rollout_proc6 +[2023-07-16 22:38:30,106][253751] Starting process rollout_proc7 +[2023-07-16 22:38:32,002][253989] Starting seed is not provided +[2023-07-16 22:38:32,002][253989] Initializing actor-critic model on device cpu +[2023-07-16 22:38:32,002][253989] RunningMeanStd input shape: (39,) +[2023-07-16 22:38:32,003][253989] RunningMeanStd input shape: (1,) +[2023-07-16 22:38:32,026][254036] Worker 2 uses CPU cores [8, 9, 10, 11] +[2023-07-16 22:38:32,059][253989] Created Actor Critic model with architecture: +[2023-07-16 22:38:32,059][253989] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( @@ -62,1078 +58,874 @@ (distribution_linear): Linear(in_features=64, out_features=4, bias=True) ) ) -[2023-07-08 17:25:40,952][1026192] Worker 1 uses CPU cores [4, 5, 6, 7] -[2023-07-08 17:25:41,075][1026191] Worker 0 uses CPU cores [0, 1, 2, 3] -[2023-07-08 17:25:41,152][1026177] Using optimizer -[2023-07-08 17:25:41,153][1026177] No checkpoints found -[2023-07-08 17:25:41,153][1026177] Did not load from checkpoint, starting from scratch! -[2023-07-08 17:25:41,153][1026177] Initialized policy 0 weights for model version 0 -[2023-07-08 17:25:41,154][1026177] LearnerWorker_p0 finished initialization! -[2023-07-08 17:25:41,156][1026190] RunningMeanStd input shape: (39,) -[2023-07-08 17:25:41,156][1026190] RunningMeanStd input shape: (1,) -[2023-07-08 17:25:41,224][1025936] Inference worker 0-0 is ready! -[2023-07-08 17:25:41,225][1025936] All inference workers are ready! Signal rollout workers to start! -[2023-07-08 17:25:41,277][1026290] Worker 3 uses CPU cores [12, 13, 14, 15] -[2023-07-08 17:25:45,022][1025936] 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) -[2023-07-08 17:25:45,705][1026191] Decorrelating experience for 0 frames... -[2023-07-08 17:25:45,720][1026191] Decorrelating experience for 64 frames... -[2023-07-08 17:25:45,756][1026191] Decorrelating experience for 128 frames... -[2023-07-08 17:25:45,758][1026256] Decorrelating experience for 0 frames... -[2023-07-08 17:25:45,761][1026291] Decorrelating experience for 0 frames... -[2023-07-08 17:25:45,767][1026257] Decorrelating experience for 0 frames... -[2023-07-08 17:25:45,773][1026256] Decorrelating experience for 64 frames... -[2023-07-08 17:25:45,777][1026291] Decorrelating experience for 64 frames... -[2023-07-08 17:25:45,782][1026257] Decorrelating experience for 64 frames... -[2023-07-08 17:25:45,783][1026289] Decorrelating experience for 0 frames... -[2023-07-08 17:25:45,795][1026224] Decorrelating experience for 0 frames... -[2023-07-08 17:25:45,799][1026289] Decorrelating experience for 64 frames... -[2023-07-08 17:25:45,807][1026256] Decorrelating experience for 128 frames... -[2023-07-08 17:25:45,809][1026224] Decorrelating experience for 64 frames... -[2023-07-08 17:25:45,815][1026291] Decorrelating experience for 128 frames... -[2023-07-08 17:25:45,818][1026257] Decorrelating experience for 128 frames... -[2023-07-08 17:25:45,825][1026191] Decorrelating experience for 192 frames... -[2023-07-08 17:25:45,833][1026289] Decorrelating experience for 128 frames... -[2023-07-08 17:25:45,846][1026224] Decorrelating experience for 128 frames... -[2023-07-08 17:25:45,877][1026256] Decorrelating experience for 192 frames... -[2023-07-08 17:25:45,886][1026291] Decorrelating experience for 192 frames... -[2023-07-08 17:25:45,893][1026257] Decorrelating experience for 192 frames... -[2023-07-08 17:25:45,907][1026289] Decorrelating experience for 192 frames... -[2023-07-08 17:25:45,914][1026290] Decorrelating experience for 0 frames... -[2023-07-08 17:25:45,918][1026224] Decorrelating experience for 192 frames... -[2023-07-08 17:25:45,929][1026290] Decorrelating experience for 64 frames... -[2023-07-08 17:25:45,964][1026290] Decorrelating experience for 128 frames... -[2023-07-08 17:25:46,034][1026290] Decorrelating experience for 192 frames... -[2023-07-08 17:25:46,047][1026192] Decorrelating experience for 0 frames... -[2023-07-08 17:25:46,062][1026192] Decorrelating experience for 64 frames... -[2023-07-08 17:25:46,098][1026192] Decorrelating experience for 128 frames... -[2023-07-08 17:25:46,169][1026192] Decorrelating experience for 192 frames... -[2023-07-08 17:25:50,022][1025936] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-07-08 17:25:50,024][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000000_0.pth... -[2023-07-08 17:25:50,244][1026191] Decorrelating experience for 256 frames... -[2023-07-08 17:25:50,323][1026256] Decorrelating experience for 256 frames... -[2023-07-08 17:25:50,339][1026291] Decorrelating experience for 256 frames... -[2023-07-08 17:25:50,369][1026191] Decorrelating experience for 320 frames... -[2023-07-08 17:25:50,389][1026289] Decorrelating experience for 256 frames... -[2023-07-08 17:25:50,431][1026224] Decorrelating experience for 256 frames... -[2023-07-08 17:25:50,449][1026256] Decorrelating experience for 320 frames... -[2023-07-08 17:25:50,469][1026291] Decorrelating experience for 320 frames... -[2023-07-08 17:25:50,521][1026289] Decorrelating experience for 320 frames... -[2023-07-08 17:25:50,531][1026191] Decorrelating experience for 384 frames... -[2023-07-08 17:25:50,539][1026257] Decorrelating experience for 256 frames... -[2023-07-08 17:25:50,542][1026290] Decorrelating experience for 256 frames... -[2023-07-08 17:25:50,554][1026224] Decorrelating experience for 320 frames... -[2023-07-08 17:25:50,606][1026256] Decorrelating experience for 384 frames... -[2023-07-08 17:25:50,637][1026291] Decorrelating experience for 384 frames... -[2023-07-08 17:25:50,663][1026257] Decorrelating experience for 320 frames... -[2023-07-08 17:25:50,668][1026192] Decorrelating experience for 256 frames... -[2023-07-08 17:25:50,671][1026290] Decorrelating experience for 320 frames... -[2023-07-08 17:25:50,684][1026289] Decorrelating experience for 384 frames... -[2023-07-08 17:25:50,715][1026191] Decorrelating experience for 448 frames... -[2023-07-08 17:25:50,720][1026224] Decorrelating experience for 384 frames... -[2023-07-08 17:25:50,786][1026256] Decorrelating experience for 448 frames... -[2023-07-08 17:25:50,801][1026192] Decorrelating experience for 320 frames... -[2023-07-08 17:25:50,813][1026291] Decorrelating experience for 448 frames... -[2023-07-08 17:25:50,823][1026257] Decorrelating experience for 384 frames... -[2023-07-08 17:25:50,849][1026290] Decorrelating experience for 384 frames... -[2023-07-08 17:25:50,868][1026289] Decorrelating experience for 448 frames... -[2023-07-08 17:25:50,907][1026224] Decorrelating experience for 448 frames... -[2023-07-08 17:25:50,978][1026192] Decorrelating experience for 384 frames... -[2023-07-08 17:25:51,006][1026257] Decorrelating experience for 448 frames... -[2023-07-08 17:25:51,034][1026290] Decorrelating experience for 448 frames... -[2023-07-08 17:25:51,238][1026192] Decorrelating experience for 448 frames... -[2023-07-08 17:25:55,022][1025936] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2867.2). Total num frames: 28672. Throughput: 0: 1334.8. Samples: 13348. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:25:55,027][1025936] Avg episode reward: [(0, '150.673')] -[2023-07-08 17:25:56,355][1026190] Updated weights for policy 0, policy_version 80 (0.0005) -[2023-07-08 17:25:57,990][1025936] Heartbeat connected on Batcher_0 -[2023-07-08 17:25:57,993][1025936] Heartbeat connected on LearnerWorker_p0 -[2023-07-08 17:25:57,997][1025936] Heartbeat connected on InferenceWorker_p0-w0 -[2023-07-08 17:25:58,002][1025936] Heartbeat connected on RolloutWorker_w0 -[2023-07-08 17:25:58,006][1025936] Heartbeat connected on RolloutWorker_w2 -[2023-07-08 17:25:58,008][1025936] Heartbeat connected on RolloutWorker_w1 -[2023-07-08 17:25:58,009][1025936] Heartbeat connected on RolloutWorker_w4 -[2023-07-08 17:25:58,012][1025936] Heartbeat connected on RolloutWorker_w5 -[2023-07-08 17:25:58,014][1025936] Heartbeat connected on RolloutWorker_w6 -[2023-07-08 17:25:58,017][1025936] Heartbeat connected on RolloutWorker_w7 -[2023-07-08 17:25:58,022][1025936] Heartbeat connected on RolloutWorker_w3 -[2023-07-08 17:26:00,022][1025936] Fps is (10 sec: 6963.2, 60 sec: 4642.1, 300 sec: 4642.1). Total num frames: 69632. Throughput: 0: 4460.8. Samples: 66912. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:26:00,023][1025936] Avg episode reward: [(0, '245.871')] -[2023-07-08 17:26:01,184][1026190] Updated weights for policy 0, policy_version 160 (0.0005) -[2023-07-08 17:26:05,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 5529.6, 300 sec: 5529.6). Total num frames: 110592. Throughput: 0: 4528.8. Samples: 90576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:26:05,023][1025936] Avg episode reward: [(0, '287.633')] -[2023-07-08 17:26:05,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000216_110592.pth... -[2023-07-08 17:26:05,029][1026177] Saving new best policy, reward=287.633! -[2023-07-08 17:26:06,352][1026190] Updated weights for policy 0, policy_version 240 (0.0005) -[2023-07-08 17:26:10,022][1025936] Fps is (10 sec: 7782.4, 60 sec: 5898.2, 300 sec: 5898.2). Total num frames: 147456. Throughput: 0: 5551.8. Samples: 138796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:26:10,022][1025936] Avg episode reward: [(0, '311.011')] -[2023-07-08 17:26:10,044][1026177] Saving new best policy, reward=311.011! -[2023-07-08 17:26:11,648][1026190] Updated weights for policy 0, policy_version 320 (0.0005) -[2023-07-08 17:26:15,022][1025936] Fps is (10 sec: 7782.5, 60 sec: 6280.6, 300 sec: 6280.6). Total num frames: 188416. Throughput: 0: 6179.5. Samples: 185384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:26:15,022][1025936] Avg episode reward: [(0, '356.638')] -[2023-07-08 17:26:15,023][1026177] Saving new best policy, reward=356.638! -[2023-07-08 17:26:16,545][1026190] Updated weights for policy 0, policy_version 400 (0.0005) -[2023-07-08 17:26:20,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 229376. Throughput: 0: 6034.1. Samples: 211192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:26:20,022][1025936] Avg episode reward: [(0, '362.905')] -[2023-07-08 17:26:20,060][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000456_233472.pth... -[2023-07-08 17:26:20,133][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000000_0.pth -[2023-07-08 17:26:20,133][1026177] Saving new best policy, reward=362.905! -[2023-07-08 17:26:21,643][1026190] Updated weights for policy 0, policy_version 480 (0.0005) -[2023-07-08 17:26:25,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 6860.8, 300 sec: 6860.8). Total num frames: 274432. Throughput: 0: 6463.3. Samples: 258532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:26:25,023][1025936] Avg episode reward: [(0, '382.950')] -[2023-07-08 17:26:25,023][1026177] Saving new best policy, reward=382.950! -[2023-07-08 17:26:26,458][1026190] Updated weights for policy 0, policy_version 560 (0.0006) -[2023-07-08 17:26:30,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 7008.7, 300 sec: 7008.7). Total num frames: 315392. Throughput: 0: 6915.0. Samples: 311176. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:26:30,022][1025936] Avg episode reward: [(0, '382.048')] -[2023-07-08 17:26:31,274][1026190] Updated weights for policy 0, policy_version 640 (0.0005) -[2023-07-08 17:26:35,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 7127.0, 300 sec: 7127.0). Total num frames: 356352. Throughput: 0: 7462.0. Samples: 335788. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:26:35,022][1025936] Avg episode reward: [(0, '398.407')] -[2023-07-08 17:26:35,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000696_356352.pth... -[2023-07-08 17:26:35,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000216_110592.pth -[2023-07-08 17:26:35,028][1026177] Saving new best policy, reward=398.407! -[2023-07-08 17:26:36,276][1026190] Updated weights for policy 0, policy_version 720 (0.0005) -[2023-07-08 17:26:40,022][1025936] Fps is (10 sec: 8191.9, 60 sec: 7223.9, 300 sec: 7223.9). Total num frames: 397312. Throughput: 0: 8258.8. Samples: 384996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:26:40,023][1025936] Avg episode reward: [(0, '415.273')] -[2023-07-08 17:26:40,023][1026177] Saving new best policy, reward=415.273! -[2023-07-08 17:26:41,366][1026190] Updated weights for policy 0, policy_version 800 (0.0005) -[2023-07-08 17:26:45,022][1025936] Fps is (10 sec: 7782.4, 60 sec: 7236.3, 300 sec: 7236.3). Total num frames: 434176. Throughput: 0: 8105.6. Samples: 431664. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:26:45,022][1025936] Avg episode reward: [(0, '436.217')] -[2023-07-08 17:26:45,023][1026177] Saving new best policy, reward=436.217! -[2023-07-08 17:26:46,663][1026190] Updated weights for policy 0, policy_version 880 (0.0005) -[2023-07-08 17:26:50,022][1025936] Fps is (10 sec: 7782.4, 60 sec: 7918.9, 300 sec: 7309.8). Total num frames: 475136. Throughput: 0: 8098.8. Samples: 455024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:26:50,022][1025936] Avg episode reward: [(0, '509.231')] -[2023-07-08 17:26:50,050][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000936_479232.pth... -[2023-07-08 17:26:50,052][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000456_233472.pth -[2023-07-08 17:26:50,052][1026177] Saving new best policy, reward=509.231! -[2023-07-08 17:26:51,495][1026190] Updated weights for policy 0, policy_version 960 (0.0005) -[2023-07-08 17:26:55,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8192.0, 300 sec: 7431.3). Total num frames: 520192. Throughput: 0: 8174.5. Samples: 506648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:26:55,022][1025936] Avg episode reward: [(0, '500.906')] -[2023-07-08 17:26:56,274][1026190] Updated weights for policy 0, policy_version 1040 (0.0005) -[2023-07-08 17:27:00,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8192.0, 300 sec: 7482.0). Total num frames: 561152. Throughput: 0: 8280.0. Samples: 557984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:27:00,022][1025936] Avg episode reward: [(0, '539.167')] -[2023-07-08 17:27:00,054][1026177] Saving new best policy, reward=539.167! -[2023-07-08 17:27:00,941][1026190] Updated weights for policy 0, policy_version 1120 (0.0005) -[2023-07-08 17:27:05,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8260.3, 300 sec: 7577.6). Total num frames: 606208. Throughput: 0: 8299.8. Samples: 584684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:27:05,022][1025936] Avg episode reward: [(0, '577.382')] -[2023-07-08 17:27:05,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001184_606208.pth... -[2023-07-08 17:27:05,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000696_356352.pth -[2023-07-08 17:27:05,028][1026177] Saving new best policy, reward=577.382! -[2023-07-08 17:27:05,718][1026190] Updated weights for policy 0, policy_version 1200 (0.0005) -[2023-07-08 17:27:10,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8396.8, 300 sec: 7661.9). Total num frames: 651264. Throughput: 0: 8373.7. Samples: 635348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:27:10,022][1025936] Avg episode reward: [(0, '600.346')] -[2023-07-08 17:27:10,023][1026177] Saving new best policy, reward=600.346! -[2023-07-08 17:27:10,562][1026190] Updated weights for policy 0, policy_version 1280 (0.0005) -[2023-07-08 17:27:15,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8328.5, 300 sec: 7645.9). Total num frames: 688128. Throughput: 0: 8313.7. Samples: 685292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:27:15,022][1025936] Avg episode reward: [(0, '645.004')] -[2023-07-08 17:27:15,023][1026177] Saving new best policy, reward=645.004! -[2023-07-08 17:27:15,589][1026190] Updated weights for policy 0, policy_version 1360 (0.0005) -[2023-07-08 17:27:20,022][1025936] Fps is (10 sec: 8191.9, 60 sec: 8396.8, 300 sec: 7717.7). Total num frames: 733184. Throughput: 0: 8358.8. Samples: 711932. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 17:27:20,022][1025936] Avg episode reward: [(0, '658.724')] -[2023-07-08 17:27:20,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001432_733184.pth... -[2023-07-08 17:27:20,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000936_479232.pth -[2023-07-08 17:27:20,029][1026177] Saving new best policy, reward=658.724! -[2023-07-08 17:27:20,337][1026190] Updated weights for policy 0, policy_version 1440 (0.0005) -[2023-07-08 17:27:25,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8328.5, 300 sec: 7741.4). Total num frames: 774144. Throughput: 0: 8374.9. Samples: 761864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:27:25,022][1025936] Avg episode reward: [(0, '655.734')] -[2023-07-08 17:27:25,362][1026190] Updated weights for policy 0, policy_version 1520 (0.0005) -[2023-07-08 17:27:30,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 7762.9). Total num frames: 815104. Throughput: 0: 8424.4. Samples: 810760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:27:30,022][1025936] Avg episode reward: [(0, '676.758')] -[2023-07-08 17:27:30,023][1026177] Saving new best policy, reward=676.758! -[2023-07-08 17:27:30,411][1026190] Updated weights for policy 0, policy_version 1600 (0.0005) -[2023-07-08 17:27:35,022][1025936] Fps is (10 sec: 7782.3, 60 sec: 8260.3, 300 sec: 7745.2). Total num frames: 851968. Throughput: 0: 8437.3. Samples: 834704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:27:35,022][1025936] Avg episode reward: [(0, '686.556')] -[2023-07-08 17:27:35,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001664_851968.pth... -[2023-07-08 17:27:35,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001184_606208.pth -[2023-07-08 17:27:35,029][1026177] Saving new best policy, reward=686.556! -[2023-07-08 17:27:35,669][1026190] Updated weights for policy 0, policy_version 1680 (0.0006) -[2023-07-08 17:27:40,022][1025936] Fps is (10 sec: 7782.4, 60 sec: 8260.3, 300 sec: 7764.6). Total num frames: 892928. Throughput: 0: 8312.5. Samples: 880712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:27:40,023][1025936] Avg episode reward: [(0, '696.761')] -[2023-07-08 17:27:40,023][1026177] Saving new best policy, reward=696.761! -[2023-07-08 17:27:40,917][1026190] Updated weights for policy 0, policy_version 1760 (0.0006) -[2023-07-08 17:27:45,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8328.5, 300 sec: 7782.4). Total num frames: 933888. Throughput: 0: 8263.8. Samples: 929856. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:27:45,022][1025936] Avg episode reward: [(0, '698.160')] -[2023-07-08 17:27:45,023][1026177] Saving new best policy, reward=698.160! -[2023-07-08 17:27:45,767][1026190] Updated weights for policy 0, policy_version 1840 (0.0005) -[2023-07-08 17:27:50,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8328.6, 300 sec: 7798.8). Total num frames: 974848. Throughput: 0: 8222.1. Samples: 954676. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:27:50,022][1025936] Avg episode reward: [(0, '691.421')] -[2023-07-08 17:27:50,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001904_974848.pth... -[2023-07-08 17:27:50,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001432_733184.pth -[2023-07-08 17:27:50,892][1026190] Updated weights for policy 0, policy_version 1920 (0.0005) -[2023-07-08 17:27:55,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 7813.9). Total num frames: 1015808. Throughput: 0: 8172.5. Samples: 1003112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:27:55,022][1025936] Avg episode reward: [(0, '712.494')] -[2023-07-08 17:27:55,023][1026177] Saving new best policy, reward=712.494! -[2023-07-08 17:27:56,013][1026190] Updated weights for policy 0, policy_version 2000 (0.0005) -[2023-07-08 17:28:00,022][1025936] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 7797.6). Total num frames: 1052672. Throughput: 0: 8097.4. Samples: 1049676. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:28:00,022][1025936] Avg episode reward: [(0, '711.970')] -[2023-07-08 17:28:00,965][1026190] Updated weights for policy 0, policy_version 2080 (0.0005) -[2023-07-08 17:28:05,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 7840.9). Total num frames: 1097728. Throughput: 0: 8091.3. Samples: 1076040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:28:05,022][1025936] Avg episode reward: [(0, '721.414')] -[2023-07-08 17:28:05,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000002144_1097728.pth... -[2023-07-08 17:28:05,027][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001664_851968.pth -[2023-07-08 17:28:05,028][1026177] Saving new best policy, reward=721.414! -[2023-07-08 17:28:05,908][1026190] Updated weights for policy 0, policy_version 2160 (0.0005) -[2023-07-08 17:28:10,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8192.0, 300 sec: 7881.3). Total num frames: 1142784. Throughput: 0: 8149.6. Samples: 1128596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:28:10,022][1025936] Avg episode reward: [(0, '724.731')] -[2023-07-08 17:28:10,023][1026177] Saving new best policy, reward=724.731! -[2023-07-08 17:28:10,358][1026190] Updated weights for policy 0, policy_version 2240 (0.0005) -[2023-07-08 17:28:15,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 7891.6). Total num frames: 1183744. Throughput: 0: 8199.1. Samples: 1179720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:28:15,022][1025936] Avg episode reward: [(0, '723.292')] -[2023-07-08 17:28:15,154][1026190] Updated weights for policy 0, policy_version 2320 (0.0005) -[2023-07-08 17:28:19,858][1026190] Updated weights for policy 0, policy_version 2400 (0.0005) -[2023-07-08 17:28:20,022][1025936] Fps is (10 sec: 8601.4, 60 sec: 8260.2, 300 sec: 7927.7). Total num frames: 1228800. Throughput: 0: 8263.0. Samples: 1206540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:28:20,023][1025936] Avg episode reward: [(0, '714.938')] -[2023-07-08 17:28:20,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000002400_1228800.pth... -[2023-07-08 17:28:20,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001904_974848.pth -[2023-07-08 17:28:24,518][1026190] Updated weights for policy 0, policy_version 2480 (0.0005) -[2023-07-08 17:28:25,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8328.5, 300 sec: 7961.6). Total num frames: 1273856. Throughput: 0: 8398.9. Samples: 1258664. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:28:25,022][1025936] Avg episode reward: [(0, '743.022')] -[2023-07-08 17:28:25,023][1026177] Saving new best policy, reward=743.022! -[2023-07-08 17:28:29,077][1026190] Updated weights for policy 0, policy_version 2560 (0.0005) -[2023-07-08 17:28:30,022][1025936] Fps is (10 sec: 8601.9, 60 sec: 8328.6, 300 sec: 7968.6). Total num frames: 1314816. Throughput: 0: 8502.8. Samples: 1312480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:28:30,022][1025936] Avg episode reward: [(0, '728.652')] -[2023-07-08 17:28:33,587][1026190] Updated weights for policy 0, policy_version 2640 (0.0005) -[2023-07-08 17:28:35,022][1025936] Fps is (10 sec: 9011.1, 60 sec: 8533.3, 300 sec: 8023.3). Total num frames: 1363968. Throughput: 0: 8572.6. Samples: 1340444. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:28:35,023][1025936] Avg episode reward: [(0, '732.692')] -[2023-07-08 17:28:35,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000002664_1363968.pth... -[2023-07-08 17:28:35,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000002144_1097728.pth -[2023-07-08 17:28:37,816][1026190] Updated weights for policy 0, policy_version 2720 (0.0005) -[2023-07-08 17:28:40,022][1025936] Fps is (10 sec: 9420.8, 60 sec: 8601.6, 300 sec: 8051.6). Total num frames: 1409024. Throughput: 0: 8748.8. Samples: 1396808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:28:40,022][1025936] Avg episode reward: [(0, '739.504')] -[2023-07-08 17:28:42,484][1026190] Updated weights for policy 0, policy_version 2800 (0.0006) -[2023-07-08 17:28:45,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8669.9, 300 sec: 8078.2). Total num frames: 1454080. Throughput: 0: 8866.7. Samples: 1448676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:28:45,023][1025936] Avg episode reward: [(0, '750.675')] -[2023-07-08 17:28:45,023][1026177] Saving new best policy, reward=750.675! -[2023-07-08 17:28:47,336][1026190] Updated weights for policy 0, policy_version 2880 (0.0005) -[2023-07-08 17:28:50,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8669.9, 300 sec: 8081.3). Total num frames: 1495040. Throughput: 0: 8854.2. Samples: 1474480. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:28:50,023][1025936] Avg episode reward: [(0, '735.018')] -[2023-07-08 17:28:50,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000002920_1495040.pth... -[2023-07-08 17:28:50,030][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000002400_1228800.pth -[2023-07-08 17:28:52,186][1026190] Updated weights for policy 0, policy_version 2960 (0.0005) -[2023-07-08 17:28:55,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8669.9, 300 sec: 8084.2). Total num frames: 1536000. Throughput: 0: 8817.3. Samples: 1525376. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:28:55,022][1025936] Avg episode reward: [(0, '740.004')] -[2023-07-08 17:28:56,918][1026190] Updated weights for policy 0, policy_version 3040 (0.0005) -[2023-07-08 17:29:00,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8108.0). Total num frames: 1581056. Throughput: 0: 8807.5. Samples: 1576056. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:29:00,022][1025936] Avg episode reward: [(0, '750.620')] -[2023-07-08 17:29:02,005][1026190] Updated weights for policy 0, policy_version 3120 (0.0005) -[2023-07-08 17:29:05,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8110.1). Total num frames: 1622016. Throughput: 0: 8747.9. Samples: 1600196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:29:05,022][1025936] Avg episode reward: [(0, '757.530')] -[2023-07-08 17:29:05,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003168_1622016.pth... -[2023-07-08 17:29:05,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000002664_1363968.pth -[2023-07-08 17:29:05,028][1026177] Saving new best policy, reward=757.530! -[2023-07-08 17:29:06,835][1026190] Updated weights for policy 0, policy_version 3200 (0.0005) -[2023-07-08 17:29:10,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8669.9, 300 sec: 8112.1). Total num frames: 1662976. Throughput: 0: 8709.9. Samples: 1650612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:29:10,022][1025936] Avg episode reward: [(0, '769.791')] -[2023-07-08 17:29:10,023][1026177] Saving new best policy, reward=769.791! -[2023-07-08 17:29:11,682][1026190] Updated weights for policy 0, policy_version 3280 (0.0005) -[2023-07-08 17:29:15,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8669.9, 300 sec: 8114.0). Total num frames: 1703936. Throughput: 0: 8620.8. Samples: 1700416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:29:15,022][1025936] Avg episode reward: [(0, '764.937')] -[2023-07-08 17:29:16,538][1026190] Updated weights for policy 0, policy_version 3360 (0.0006) -[2023-07-08 17:29:20,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8669.9, 300 sec: 8134.9). Total num frames: 1748992. Throughput: 0: 8610.0. Samples: 1727892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:29:20,022][1025936] Avg episode reward: [(0, '745.630')] -[2023-07-08 17:29:20,024][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003416_1748992.pth... -[2023-07-08 17:29:20,026][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000002920_1495040.pth -[2023-07-08 17:29:21,129][1026190] Updated weights for policy 0, policy_version 3440 (0.0006) -[2023-07-08 17:29:25,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8136.1). Total num frames: 1789952. Throughput: 0: 8520.2. Samples: 1780216. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:29:25,023][1025936] Avg episode reward: [(0, '775.314')] -[2023-07-08 17:29:25,045][1026177] Saving new best policy, reward=775.314! -[2023-07-08 17:29:26,127][1026190] Updated weights for policy 0, policy_version 3520 (0.0006) -[2023-07-08 17:29:30,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8601.6, 300 sec: 8137.4). Total num frames: 1830912. Throughput: 0: 8411.2. Samples: 1827180. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:29:30,022][1025936] Avg episode reward: [(0, '766.854')] -[2023-07-08 17:29:31,045][1026190] Updated weights for policy 0, policy_version 3600 (0.0005) -[2023-07-08 17:29:35,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8156.4). Total num frames: 1875968. Throughput: 0: 8445.9. Samples: 1854544. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:29:35,023][1025936] Avg episode reward: [(0, '770.466')] -[2023-07-08 17:29:35,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003664_1875968.pth... -[2023-07-08 17:29:35,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003168_1622016.pth -[2023-07-08 17:29:35,654][1026190] Updated weights for policy 0, policy_version 3680 (0.0005) -[2023-07-08 17:29:40,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8465.0, 300 sec: 8157.1). Total num frames: 1916928. Throughput: 0: 8460.7. Samples: 1906108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:29:40,023][1025936] Avg episode reward: [(0, '780.130')] -[2023-07-08 17:29:40,024][1026177] Saving new best policy, reward=780.130! -[2023-07-08 17:29:40,658][1026190] Updated weights for policy 0, policy_version 3760 (0.0005) -[2023-07-08 17:29:45,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8174.9). Total num frames: 1961984. Throughput: 0: 8483.6. Samples: 1957820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:29:45,023][1025936] Avg episode reward: [(0, '773.427')] -[2023-07-08 17:29:45,241][1026190] Updated weights for policy 0, policy_version 3840 (0.0005) -[2023-07-08 17:29:49,996][1026190] Updated weights for policy 0, policy_version 3920 (0.0005) -[2023-07-08 17:29:50,022][1025936] Fps is (10 sec: 9011.1, 60 sec: 8533.3, 300 sec: 8192.0). Total num frames: 2007040. Throughput: 0: 8543.3. Samples: 1984644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:29:50,023][1025936] Avg episode reward: [(0, '768.898')] -[2023-07-08 17:29:50,027][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003920_2007040.pth... -[2023-07-08 17:29:50,030][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003416_1748992.pth -[2023-07-08 17:29:54,540][1026190] Updated weights for policy 0, policy_version 4000 (0.0005) -[2023-07-08 17:29:55,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8601.6, 300 sec: 8208.4). Total num frames: 2052096. Throughput: 0: 8570.1. Samples: 2036268. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:29:55,023][1025936] Avg episode reward: [(0, '769.425')] -[2023-07-08 17:29:59,391][1026190] Updated weights for policy 0, policy_version 4080 (0.0005) -[2023-07-08 17:30:00,022][1025936] Fps is (10 sec: 8601.8, 60 sec: 8533.3, 300 sec: 8208.1). Total num frames: 2093056. Throughput: 0: 8612.9. Samples: 2087996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:30:00,023][1025936] Avg episode reward: [(0, '776.483')] -[2023-07-08 17:30:04,170][1026190] Updated weights for policy 0, policy_version 4160 (0.0005) -[2023-07-08 17:30:05,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 8207.8). Total num frames: 2134016. Throughput: 0: 8568.8. Samples: 2113488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:30:05,024][1025936] Avg episode reward: [(0, '784.168')] -[2023-07-08 17:30:05,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004168_2134016.pth... -[2023-07-08 17:30:05,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003664_1875968.pth -[2023-07-08 17:30:05,029][1026177] Saving new best policy, reward=784.168! -[2023-07-08 17:30:08,697][1026190] Updated weights for policy 0, policy_version 4240 (0.0005) -[2023-07-08 17:30:10,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8669.9, 300 sec: 8238.4). Total num frames: 2183168. Throughput: 0: 8591.8. Samples: 2166848. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:30:10,023][1025936] Avg episode reward: [(0, '774.266')] -[2023-07-08 17:30:13,461][1026190] Updated weights for policy 0, policy_version 4320 (0.0005) -[2023-07-08 17:30:15,022][1025936] Fps is (10 sec: 9011.3, 60 sec: 8669.9, 300 sec: 8237.5). Total num frames: 2224128. Throughput: 0: 8707.6. Samples: 2219020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:30:15,022][1025936] Avg episode reward: [(0, '785.433')] -[2023-07-08 17:30:15,023][1026177] Saving new best policy, reward=785.433! -[2023-07-08 17:30:18,171][1026190] Updated weights for policy 0, policy_version 4400 (0.0005) -[2023-07-08 17:30:20,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8601.6, 300 sec: 8236.7). Total num frames: 2265088. Throughput: 0: 8676.5. Samples: 2244988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:30:20,022][1025936] Avg episode reward: [(0, '788.508')] -[2023-07-08 17:30:20,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004432_2269184.pth... -[2023-07-08 17:30:20,027][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003920_2007040.pth -[2023-07-08 17:30:20,027][1026177] Saving new best policy, reward=788.508! -[2023-07-08 17:30:22,935][1026190] Updated weights for policy 0, policy_version 4480 (0.0006) -[2023-07-08 17:30:25,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8250.5). Total num frames: 2310144. Throughput: 0: 8696.2. Samples: 2297436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:30:25,022][1025936] Avg episode reward: [(0, '779.229')] -[2023-07-08 17:30:27,888][1026190] Updated weights for policy 0, policy_version 4560 (0.0005) -[2023-07-08 17:30:30,022][1025936] Fps is (10 sec: 8601.4, 60 sec: 8669.8, 300 sec: 8249.5). Total num frames: 2351104. Throughput: 0: 8646.7. Samples: 2346924. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 17:30:30,023][1025936] Avg episode reward: [(0, '780.596')] -[2023-07-08 17:30:32,717][1026190] Updated weights for policy 0, policy_version 4640 (0.0005) -[2023-07-08 17:30:35,022][1025936] Fps is (10 sec: 8191.9, 60 sec: 8601.6, 300 sec: 8248.5). Total num frames: 2392064. Throughput: 0: 8598.9. Samples: 2371592. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:30:35,022][1025936] Avg episode reward: [(0, '777.169')] -[2023-07-08 17:30:35,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004672_2392064.pth... -[2023-07-08 17:30:35,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004168_2134016.pth -[2023-07-08 17:30:37,598][1026190] Updated weights for policy 0, policy_version 4720 (0.0005) -[2023-07-08 17:30:40,022][1025936] Fps is (10 sec: 8192.2, 60 sec: 8601.6, 300 sec: 8247.5). Total num frames: 2433024. Throughput: 0: 8573.3. Samples: 2422068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:30:40,022][1025936] Avg episode reward: [(0, '781.749')] -[2023-07-08 17:30:42,216][1026190] Updated weights for policy 0, policy_version 4800 (0.0005) -[2023-07-08 17:30:45,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8669.9, 300 sec: 8414.2). Total num frames: 2482176. Throughput: 0: 8617.1. Samples: 2475764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:30:45,022][1025936] Avg episode reward: [(0, '776.986')] -[2023-07-08 17:30:46,710][1026190] Updated weights for policy 0, policy_version 4880 (0.0005) -[2023-07-08 17:30:50,022][1025936] Fps is (10 sec: 9420.7, 60 sec: 8669.9, 300 sec: 8469.7). Total num frames: 2527232. Throughput: 0: 8674.9. Samples: 2503860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:30:50,022][1025936] Avg episode reward: [(0, '787.947')] -[2023-07-08 17:30:50,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004936_2527232.pth... -[2023-07-08 17:30:50,027][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004432_2269184.pth -[2023-07-08 17:30:51,497][1026190] Updated weights for policy 0, policy_version 4960 (0.0006) -[2023-07-08 17:30:55,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8469.7). Total num frames: 2568192. Throughput: 0: 8638.9. Samples: 2555600. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:30:55,022][1025936] Avg episode reward: [(0, '793.348')] -[2023-07-08 17:30:55,023][1026177] Saving new best policy, reward=793.348! -[2023-07-08 17:30:56,283][1026190] Updated weights for policy 0, policy_version 5040 (0.0006) -[2023-07-08 17:31:00,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8601.6, 300 sec: 8469.7). Total num frames: 2609152. Throughput: 0: 8615.3. Samples: 2606708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:31:00,022][1025936] Avg episode reward: [(0, '792.543')] -[2023-07-08 17:31:01,029][1026190] Updated weights for policy 0, policy_version 5120 (0.0005) -[2023-07-08 17:31:05,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8669.9, 300 sec: 8497.5). Total num frames: 2654208. Throughput: 0: 8583.6. Samples: 2631252. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:31:05,022][1025936] Avg episode reward: [(0, '784.464')] -[2023-07-08 17:31:05,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000005184_2654208.pth... -[2023-07-08 17:31:05,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004672_2392064.pth -[2023-07-08 17:31:05,657][1026190] Updated weights for policy 0, policy_version 5200 (0.0006) -[2023-07-08 17:31:10,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8533.3, 300 sec: 8497.5). Total num frames: 2695168. Throughput: 0: 8590.9. Samples: 2684028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:31:10,022][1025936] Avg episode reward: [(0, '788.195')] -[2023-07-08 17:31:10,625][1026190] Updated weights for policy 0, policy_version 5280 (0.0005) -[2023-07-08 17:31:15,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8601.6, 300 sec: 8511.3). Total num frames: 2740224. Throughput: 0: 8639.2. Samples: 2735688. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:31:15,022][1025936] Avg episode reward: [(0, '789.553')] -[2023-07-08 17:31:15,303][1026190] Updated weights for policy 0, policy_version 5360 (0.0005) -[2023-07-08 17:31:20,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8601.6, 300 sec: 8497.5). Total num frames: 2781184. Throughput: 0: 8660.0. Samples: 2761292. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:31:20,022][1025936] Avg episode reward: [(0, '785.035')] -[2023-07-08 17:31:20,044][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000005440_2785280.pth... -[2023-07-08 17:31:20,045][1026190] Updated weights for policy 0, policy_version 5440 (0.0005) -[2023-07-08 17:31:20,046][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004936_2527232.pth -[2023-07-08 17:31:24,746][1026190] Updated weights for policy 0, policy_version 5520 (0.0006) -[2023-07-08 17:31:25,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8511.3). Total num frames: 2826240. Throughput: 0: 8708.7. Samples: 2813960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:31:25,022][1025936] Avg episode reward: [(0, '791.157')] -[2023-07-08 17:31:29,525][1026190] Updated weights for policy 0, policy_version 5600 (0.0006) -[2023-07-08 17:31:30,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8601.6, 300 sec: 8511.4). Total num frames: 2867200. Throughput: 0: 8630.7. Samples: 2864148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:31:30,023][1025936] Avg episode reward: [(0, '788.506')] -[2023-07-08 17:31:34,218][1026190] Updated weights for policy 0, policy_version 5680 (0.0005) -[2023-07-08 17:31:35,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8669.9, 300 sec: 8525.2). Total num frames: 2912256. Throughput: 0: 8608.6. Samples: 2891248. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:31:35,023][1025936] Avg episode reward: [(0, '792.431')] -[2023-07-08 17:31:35,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000005688_2912256.pth... -[2023-07-08 17:31:35,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000005184_2654208.pth -[2023-07-08 17:31:39,377][1026190] Updated weights for policy 0, policy_version 5760 (0.0005) -[2023-07-08 17:31:40,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8669.9, 300 sec: 8539.1). Total num frames: 2953216. Throughput: 0: 8551.5. Samples: 2940420. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 17:31:40,023][1025936] Avg episode reward: [(0, '784.299')] -[2023-07-08 17:31:44,218][1026190] Updated weights for policy 0, policy_version 5840 (0.0005) -[2023-07-08 17:31:45,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8533.3, 300 sec: 8539.1). Total num frames: 2994176. Throughput: 0: 8522.1. Samples: 2990204. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:31:45,022][1025936] Avg episode reward: [(0, '791.871')] -[2023-07-08 17:31:48,834][1026190] Updated weights for policy 0, policy_version 5920 (0.0005) -[2023-07-08 17:31:50,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8539.1). Total num frames: 3039232. Throughput: 0: 8555.5. Samples: 3016248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:31:50,022][1025936] Avg episode reward: [(0, '791.308')] -[2023-07-08 17:31:50,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000005936_3039232.pth... -[2023-07-08 17:31:50,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000005440_2785280.pth -[2023-07-08 17:31:53,567][1026190] Updated weights for policy 0, policy_version 6000 (0.0005) -[2023-07-08 17:31:55,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8533.3, 300 sec: 8539.1). Total num frames: 3080192. Throughput: 0: 8550.0. Samples: 3068776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:31:55,022][1025936] Avg episode reward: [(0, '786.900')] -[2023-07-08 17:31:58,373][1026190] Updated weights for policy 0, policy_version 6080 (0.0005) -[2023-07-08 17:32:00,022][1025936] Fps is (10 sec: 9011.3, 60 sec: 8669.9, 300 sec: 8553.0). Total num frames: 3129344. Throughput: 0: 8572.7. Samples: 3121460. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:32:00,022][1025936] Avg episode reward: [(0, '783.756')] -[2023-07-08 17:32:02,696][1026190] Updated weights for policy 0, policy_version 6160 (0.0005) -[2023-07-08 17:32:05,022][1025936] Fps is (10 sec: 9420.8, 60 sec: 8669.9, 300 sec: 8553.0). Total num frames: 3174400. Throughput: 0: 8651.4. Samples: 3150604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:32:05,022][1025936] Avg episode reward: [(0, '788.886')] -[2023-07-08 17:32:05,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006200_3174400.pth... -[2023-07-08 17:32:05,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000005688_2912256.pth -[2023-07-08 17:32:07,364][1026190] Updated weights for policy 0, policy_version 6240 (0.0005) -[2023-07-08 17:32:10,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8669.9, 300 sec: 8566.9). Total num frames: 3215360. Throughput: 0: 8644.9. Samples: 3202980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:32:10,022][1025936] Avg episode reward: [(0, '796.439')] -[2023-07-08 17:32:10,023][1026177] Saving new best policy, reward=796.439! -[2023-07-08 17:32:12,081][1026190] Updated weights for policy 0, policy_version 6320 (0.0005) -[2023-07-08 17:32:15,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8601.6, 300 sec: 8553.0). Total num frames: 3256320. Throughput: 0: 8643.1. Samples: 3253088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:32:15,022][1025936] Avg episode reward: [(0, '790.887')] -[2023-07-08 17:32:17,137][1026190] Updated weights for policy 0, policy_version 6400 (0.0005) -[2023-07-08 17:32:20,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8566.9). Total num frames: 3301376. Throughput: 0: 8590.2. Samples: 3277808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:32:20,022][1025936] Avg episode reward: [(0, '799.404')] -[2023-07-08 17:32:20,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006448_3301376.pth... -[2023-07-08 17:32:20,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000005936_3039232.pth -[2023-07-08 17:32:20,028][1026177] Saving new best policy, reward=799.404! -[2023-07-08 17:32:21,475][1026190] Updated weights for policy 0, policy_version 6480 (0.0005) -[2023-07-08 17:32:25,022][1025936] Fps is (10 sec: 9420.8, 60 sec: 8738.1, 300 sec: 8594.7). Total num frames: 3350528. Throughput: 0: 8770.3. Samples: 3335084. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:32:25,022][1025936] Avg episode reward: [(0, '794.931')] -[2023-07-08 17:32:25,756][1026190] Updated weights for policy 0, policy_version 6560 (0.0006) -[2023-07-08 17:32:30,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8608.5). Total num frames: 3391488. Throughput: 0: 8839.1. Samples: 3387964. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:32:30,022][1025936] Avg episode reward: [(0, '794.722')] -[2023-07-08 17:32:30,644][1026190] Updated weights for policy 0, policy_version 6640 (0.0005) -[2023-07-08 17:32:35,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8622.4). Total num frames: 3436544. Throughput: 0: 8849.3. Samples: 3414464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:32:35,022][1025936] Avg episode reward: [(0, '793.764')] -[2023-07-08 17:32:35,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006712_3436544.pth... -[2023-07-08 17:32:35,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006200_3174400.pth -[2023-07-08 17:32:35,356][1026190] Updated weights for policy 0, policy_version 6720 (0.0005) -[2023-07-08 17:32:40,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8738.2, 300 sec: 8622.4). Total num frames: 3477504. Throughput: 0: 8814.0. Samples: 3465404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:32:40,022][1025936] Avg episode reward: [(0, '795.279')] -[2023-07-08 17:32:40,030][1026190] Updated weights for policy 0, policy_version 6800 (0.0005) -[2023-07-08 17:32:44,802][1026190] Updated weights for policy 0, policy_version 6880 (0.0005) -[2023-07-08 17:32:45,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8636.3). Total num frames: 3522560. Throughput: 0: 8822.0. Samples: 3518452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:32:45,022][1025936] Avg episode reward: [(0, '795.113')] -[2023-07-08 17:32:49,199][1026190] Updated weights for policy 0, policy_version 6960 (0.0005) -[2023-07-08 17:32:50,022][1025936] Fps is (10 sec: 9011.1, 60 sec: 8806.4, 300 sec: 8650.2). Total num frames: 3567616. Throughput: 0: 8807.9. Samples: 3546960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:32:50,023][1025936] Avg episode reward: [(0, '796.173')] -[2023-07-08 17:32:50,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006968_3567616.pth... -[2023-07-08 17:32:50,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006448_3301376.pth -[2023-07-08 17:32:54,246][1026190] Updated weights for policy 0, policy_version 7040 (0.0004) -[2023-07-08 17:32:55,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8664.1). Total num frames: 3608576. Throughput: 0: 8754.2. Samples: 3596920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:32:55,022][1025936] Avg episode reward: [(0, '794.928')] -[2023-07-08 17:32:59,318][1026190] Updated weights for policy 0, policy_version 7120 (0.0005) -[2023-07-08 17:33:00,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8669.9, 300 sec: 8650.2). Total num frames: 3649536. Throughput: 0: 8715.7. Samples: 3645296. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:33:00,022][1025936] Avg episode reward: [(0, '795.531')] -[2023-07-08 17:33:03,855][1026190] Updated weights for policy 0, policy_version 7200 (0.0005) -[2023-07-08 17:33:05,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8650.2). Total num frames: 3694592. Throughput: 0: 8717.3. Samples: 3670088. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:33:05,022][1025936] Avg episode reward: [(0, '794.409')] -[2023-07-08 17:33:05,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007216_3694592.pth... -[2023-07-08 17:33:05,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006712_3436544.pth -[2023-07-08 17:33:08,270][1026190] Updated weights for policy 0, policy_version 7280 (0.0004) -[2023-07-08 17:33:10,022][1025936] Fps is (10 sec: 9011.1, 60 sec: 8738.1, 300 sec: 8664.1). Total num frames: 3739648. Throughput: 0: 8717.2. Samples: 3727360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:33:10,022][1025936] Avg episode reward: [(0, '790.112')] -[2023-07-08 17:33:13,099][1026190] Updated weights for policy 0, policy_version 7360 (0.0006) -[2023-07-08 17:33:15,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8664.1). Total num frames: 3784704. Throughput: 0: 8678.7. Samples: 3778504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:33:15,022][1025936] Avg episode reward: [(0, '797.227')] -[2023-07-08 17:33:17,552][1026190] Updated weights for policy 0, policy_version 7440 (0.0005) -[2023-07-08 17:33:20,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8664.1). Total num frames: 3829760. Throughput: 0: 8724.8. Samples: 3807080. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:33:20,022][1025936] Avg episode reward: [(0, '790.397')] -[2023-07-08 17:33:20,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007480_3829760.pth... -[2023-07-08 17:33:20,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006968_3567616.pth -[2023-07-08 17:33:22,138][1026190] Updated weights for policy 0, policy_version 7520 (0.0005) -[2023-07-08 17:33:25,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8669.9, 300 sec: 8664.1). Total num frames: 3870720. Throughput: 0: 8779.4. Samples: 3860476. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:33:25,022][1025936] Avg episode reward: [(0, '792.547')] -[2023-07-08 17:33:27,041][1026190] Updated weights for policy 0, policy_version 7600 (0.0005) -[2023-07-08 17:33:30,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8650.2). Total num frames: 3915776. Throughput: 0: 8717.6. Samples: 3910744. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:33:30,022][1025936] Avg episode reward: [(0, '795.912')] -[2023-07-08 17:33:31,918][1026190] Updated weights for policy 0, policy_version 7680 (0.0005) -[2023-07-08 17:33:35,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8669.9, 300 sec: 8636.3). Total num frames: 3956736. Throughput: 0: 8640.2. Samples: 3935768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:33:35,022][1025936] Avg episode reward: [(0, '794.911')] -[2023-07-08 17:33:35,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007728_3956736.pth... -[2023-07-08 17:33:35,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007216_3694592.pth -[2023-07-08 17:33:36,848][1026190] Updated weights for policy 0, policy_version 7760 (0.0005) -[2023-07-08 17:33:40,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8636.3). Total num frames: 4001792. Throughput: 0: 8697.8. Samples: 3988320. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:33:40,022][1025936] Avg episode reward: [(0, '790.471')] -[2023-07-08 17:33:40,987][1026190] Updated weights for policy 0, policy_version 7840 (0.0005) -[2023-07-08 17:33:45,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8650.2). Total num frames: 4046848. Throughput: 0: 8836.4. Samples: 4042936. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:33:45,022][1025936] Avg episode reward: [(0, '793.103')] -[2023-07-08 17:33:45,801][1026190] Updated weights for policy 0, policy_version 7920 (0.0006) -[2023-07-08 17:33:50,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8650.2). Total num frames: 4087808. Throughput: 0: 8837.7. Samples: 4067784. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:33:50,022][1025936] Avg episode reward: [(0, '787.967')] -[2023-07-08 17:33:50,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007984_4087808.pth... -[2023-07-08 17:33:50,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007480_3829760.pth -[2023-07-08 17:33:50,791][1026190] Updated weights for policy 0, policy_version 8000 (0.0005) -[2023-07-08 17:33:55,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8650.2). Total num frames: 4132864. Throughput: 0: 8713.1. Samples: 4119448. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:33:55,023][1025936] Avg episode reward: [(0, '790.541')] -[2023-07-08 17:33:55,227][1026190] Updated weights for policy 0, policy_version 8080 (0.0005) -[2023-07-08 17:34:00,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8650.2). Total num frames: 4173824. Throughput: 0: 8695.5. Samples: 4169800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:34:00,022][1025936] Avg episode reward: [(0, '784.112')] -[2023-07-08 17:34:00,253][1026190] Updated weights for policy 0, policy_version 8160 (0.0005) -[2023-07-08 17:34:04,669][1026190] Updated weights for policy 0, policy_version 8240 (0.0005) -[2023-07-08 17:34:05,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8664.1). Total num frames: 4218880. Throughput: 0: 8693.1. Samples: 4198268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:34:05,022][1025936] Avg episode reward: [(0, '787.944')] -[2023-07-08 17:34:05,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000008240_4218880.pth... -[2023-07-08 17:34:05,027][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007728_3956736.pth -[2023-07-08 17:34:09,537][1026190] Updated weights for policy 0, policy_version 8320 (0.0005) -[2023-07-08 17:34:10,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8664.1). Total num frames: 4259840. Throughput: 0: 8640.9. Samples: 4249316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:34:10,022][1025936] Avg episode reward: [(0, '788.989')] -[2023-07-08 17:34:14,618][1026190] Updated weights for policy 0, policy_version 8400 (0.0005) -[2023-07-08 17:34:15,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8601.6, 300 sec: 8650.2). Total num frames: 4300800. Throughput: 0: 8619.4. Samples: 4298616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:34:15,022][1025936] Avg episode reward: [(0, '791.142')] -[2023-07-08 17:34:19,392][1026190] Updated weights for policy 0, policy_version 8480 (0.0005) -[2023-07-08 17:34:20,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8664.1). Total num frames: 4345856. Throughput: 0: 8579.9. Samples: 4321864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:34:20,022][1025936] Avg episode reward: [(0, '793.584')] -[2023-07-08 17:34:20,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000008488_4345856.pth... -[2023-07-08 17:34:20,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007984_4087808.pth -[2023-07-08 17:34:24,379][1026190] Updated weights for policy 0, policy_version 8560 (0.0005) -[2023-07-08 17:34:25,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8664.1). Total num frames: 4386816. Throughput: 0: 8579.9. Samples: 4374416. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 17:34:25,022][1025936] Avg episode reward: [(0, '794.513')] -[2023-07-08 17:34:28,943][1026190] Updated weights for policy 0, policy_version 8640 (0.0005) -[2023-07-08 17:34:30,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8664.1). Total num frames: 4431872. Throughput: 0: 8539.6. Samples: 4427220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:34:30,022][1025936] Avg episode reward: [(0, '791.869')] -[2023-07-08 17:34:33,777][1026190] Updated weights for policy 0, policy_version 8720 (0.0005) -[2023-07-08 17:34:35,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8664.1). Total num frames: 4472832. Throughput: 0: 8545.7. Samples: 4452340. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:34:35,022][1025936] Avg episode reward: [(0, '790.979')] -[2023-07-08 17:34:35,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000008736_4472832.pth... -[2023-07-08 17:34:35,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000008240_4218880.pth -[2023-07-08 17:34:38,560][1026190] Updated weights for policy 0, policy_version 8800 (0.0005) -[2023-07-08 17:34:40,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8664.1). Total num frames: 4517888. Throughput: 0: 8508.0. Samples: 4502308. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:34:40,023][1025936] Avg episode reward: [(0, '791.425')] -[2023-07-08 17:34:43,088][1026190] Updated weights for policy 0, policy_version 8880 (0.0005) -[2023-07-08 17:34:45,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8601.6, 300 sec: 8664.1). Total num frames: 4562944. Throughput: 0: 8629.2. Samples: 4558112. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:34:45,022][1025936] Avg episode reward: [(0, '793.792')] -[2023-07-08 17:34:47,699][1026190] Updated weights for policy 0, policy_version 8960 (0.0005) -[2023-07-08 17:34:50,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8650.2). Total num frames: 4603904. Throughput: 0: 8576.2. Samples: 4584196. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:34:50,105][1025936] Avg episode reward: [(0, '796.590')] -[2023-07-08 17:34:50,109][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009000_4608000.pth... -[2023-07-08 17:34:50,112][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000008488_4345856.pth -[2023-07-08 17:34:52,524][1026190] Updated weights for policy 0, policy_version 9040 (0.0005) -[2023-07-08 17:34:55,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 8650.2). Total num frames: 4644864. Throughput: 0: 8574.0. Samples: 4635144. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:34:55,023][1025936] Avg episode reward: [(0, '794.531')] -[2023-07-08 17:34:57,476][1026190] Updated weights for policy 0, policy_version 9120 (0.0005) -[2023-07-08 17:35:00,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8664.1). Total num frames: 4689920. Throughput: 0: 8590.1. Samples: 4685172. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:35:00,023][1025936] Avg episode reward: [(0, '793.261')] -[2023-07-08 17:35:02,302][1026190] Updated weights for policy 0, policy_version 9200 (0.0005) -[2023-07-08 17:35:05,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 4730880. Throughput: 0: 8634.2. Samples: 4710400. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:35:05,022][1025936] Avg episode reward: [(0, '792.456')] -[2023-07-08 17:35:05,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009240_4730880.pth... -[2023-07-08 17:35:05,026][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000008736_4472832.pth -[2023-07-08 17:35:07,102][1026190] Updated weights for policy 0, policy_version 9280 (0.0006) -[2023-07-08 17:35:10,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 4771840. Throughput: 0: 8576.6. Samples: 4760364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:35:10,023][1025936] Avg episode reward: [(0, '798.281')] -[2023-07-08 17:35:12,153][1026190] Updated weights for policy 0, policy_version 9360 (0.0006) -[2023-07-08 17:35:15,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 4812800. Throughput: 0: 8503.7. Samples: 4809884. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:35:15,023][1025936] Avg episode reward: [(0, '796.054')] -[2023-07-08 17:35:16,808][1026190] Updated weights for policy 0, policy_version 9440 (0.0005) -[2023-07-08 17:35:20,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 4857856. Throughput: 0: 8556.6. Samples: 4837388. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:35:20,022][1025936] Avg episode reward: [(0, '800.149')] -[2023-07-08 17:35:20,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009488_4857856.pth... -[2023-07-08 17:35:20,026][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009000_4608000.pth -[2023-07-08 17:35:20,027][1026177] Saving new best policy, reward=800.149! -[2023-07-08 17:35:21,718][1026190] Updated weights for policy 0, policy_version 9520 (0.0005) -[2023-07-08 17:35:25,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 4898816. Throughput: 0: 8536.6. Samples: 4886456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:35:25,023][1025936] Avg episode reward: [(0, '794.201')] -[2023-07-08 17:35:26,565][1026190] Updated weights for policy 0, policy_version 9600 (0.0005) -[2023-07-08 17:35:30,022][1025936] Fps is (10 sec: 9011.1, 60 sec: 8601.6, 300 sec: 8664.1). Total num frames: 4947968. Throughput: 0: 8510.4. Samples: 4941080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:35:30,023][1025936] Avg episode reward: [(0, '796.160')] -[2023-07-08 17:35:30,713][1026190] Updated weights for policy 0, policy_version 9680 (0.0005) -[2023-07-08 17:35:35,022][1025936] Fps is (10 sec: 9420.9, 60 sec: 8669.9, 300 sec: 8678.0). Total num frames: 4993024. Throughput: 0: 8592.7. Samples: 4970868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:35:35,022][1025936] Avg episode reward: [(0, '799.499')] -[2023-07-08 17:35:35,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009752_4993024.pth... -[2023-07-08 17:35:35,027][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009240_4730880.pth -[2023-07-08 17:35:35,448][1026190] Updated weights for policy 0, policy_version 9760 (0.0005) -[2023-07-08 17:35:40,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8601.6, 300 sec: 8650.2). Total num frames: 5033984. Throughput: 0: 8617.1. Samples: 5022912. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:35:40,023][1025936] Avg episode reward: [(0, '790.047')] -[2023-07-08 17:35:40,148][1026190] Updated weights for policy 0, policy_version 9840 (0.0005) -[2023-07-08 17:35:44,785][1026190] Updated weights for policy 0, policy_version 9920 (0.0005) -[2023-07-08 17:35:45,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8650.2). Total num frames: 5079040. Throughput: 0: 8660.2. Samples: 5074880. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 17:35:45,023][1025936] Avg episode reward: [(0, '791.660')] -[2023-07-08 17:35:49,641][1026190] Updated weights for policy 0, policy_version 10000 (0.0005) -[2023-07-08 17:35:50,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8601.6, 300 sec: 8650.2). Total num frames: 5120000. Throughput: 0: 8648.5. Samples: 5099584. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 17:35:50,022][1025936] Avg episode reward: [(0, '791.742')] -[2023-07-08 17:35:50,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010000_5120000.pth... -[2023-07-08 17:35:50,027][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009488_4857856.pth -[2023-07-08 17:35:54,375][1026190] Updated weights for policy 0, policy_version 10080 (0.0006) -[2023-07-08 17:35:55,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8669.9, 300 sec: 8664.1). Total num frames: 5165056. Throughput: 0: 8680.5. Samples: 5150984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:35:55,023][1025936] Avg episode reward: [(0, '797.257')] -[2023-07-08 17:35:59,116][1026190] Updated weights for policy 0, policy_version 10160 (0.0005) -[2023-07-08 17:36:00,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8650.2). Total num frames: 5206016. Throughput: 0: 8742.8. Samples: 5203312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:36:00,023][1025936] Avg episode reward: [(0, '796.964')] -[2023-07-08 17:36:03,345][1026190] Updated weights for policy 0, policy_version 10240 (0.0005) -[2023-07-08 17:36:05,022][1025936] Fps is (10 sec: 9011.1, 60 sec: 8738.1, 300 sec: 8678.0). Total num frames: 5255168. Throughput: 0: 8801.1. Samples: 5233440. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:36:05,022][1025936] Avg episode reward: [(0, '795.085')] -[2023-07-08 17:36:05,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010264_5255168.pth... -[2023-07-08 17:36:05,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009752_4993024.pth -[2023-07-08 17:36:08,404][1026190] Updated weights for policy 0, policy_version 10320 (0.0006) -[2023-07-08 17:36:10,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8664.1). Total num frames: 5296128. Throughput: 0: 8814.9. Samples: 5283128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:36:10,023][1025936] Avg episode reward: [(0, '797.883')] -[2023-07-08 17:36:13,004][1026190] Updated weights for policy 0, policy_version 10400 (0.0005) -[2023-07-08 17:36:15,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8806.4, 300 sec: 8678.0). Total num frames: 5341184. Throughput: 0: 8811.9. Samples: 5337616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:36:15,023][1025936] Avg episode reward: [(0, '792.930')] -[2023-07-08 17:36:17,520][1026190] Updated weights for policy 0, policy_version 10480 (0.0005) -[2023-07-08 17:36:20,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8678.0). Total num frames: 5386240. Throughput: 0: 8729.5. Samples: 5363696. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:36:20,022][1025936] Avg episode reward: [(0, '788.341')] -[2023-07-08 17:36:20,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010520_5386240.pth... -[2023-07-08 17:36:20,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010000_5120000.pth -[2023-07-08 17:36:22,438][1026190] Updated weights for policy 0, policy_version 10560 (0.0005) -[2023-07-08 17:36:25,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8806.4, 300 sec: 8678.0). Total num frames: 5427200. Throughput: 0: 8689.9. Samples: 5413960. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:36:25,023][1025936] Avg episode reward: [(0, '799.130')] -[2023-07-08 17:36:27,160][1026190] Updated weights for policy 0, policy_version 10640 (0.0005) -[2023-07-08 17:36:30,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8669.9, 300 sec: 8664.1). Total num frames: 5468160. Throughput: 0: 8693.6. Samples: 5466092. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:36:30,022][1025936] Avg episode reward: [(0, '795.567')] -[2023-07-08 17:36:32,080][1026190] Updated weights for policy 0, policy_version 10720 (0.0005) -[2023-07-08 17:36:35,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8678.0). Total num frames: 5513216. Throughput: 0: 8679.6. Samples: 5490168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:36:35,022][1025936] Avg episode reward: [(0, '795.586')] -[2023-07-08 17:36:35,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010768_5513216.pth... -[2023-07-08 17:36:35,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010264_5255168.pth -[2023-07-08 17:36:36,735][1026190] Updated weights for policy 0, policy_version 10800 (0.0005) -[2023-07-08 17:36:40,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8678.0). Total num frames: 5554176. Throughput: 0: 8686.9. Samples: 5541896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:36:40,022][1025936] Avg episode reward: [(0, '797.641')] -[2023-07-08 17:36:41,520][1026190] Updated weights for policy 0, policy_version 10880 (0.0005) -[2023-07-08 17:36:45,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8678.0). Total num frames: 5599232. Throughput: 0: 8632.5. Samples: 5591776. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:36:45,022][1025936] Avg episode reward: [(0, '796.669')] -[2023-07-08 17:36:46,260][1026190] Updated weights for policy 0, policy_version 10960 (0.0005) -[2023-07-08 17:36:50,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8678.0). Total num frames: 5640192. Throughput: 0: 8585.4. Samples: 5619784. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:36:50,022][1025936] Avg episode reward: [(0, '797.098')] -[2023-07-08 17:36:50,024][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000011016_5640192.pth... -[2023-07-08 17:36:50,026][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010520_5386240.pth -[2023-07-08 17:36:51,138][1026190] Updated weights for policy 0, policy_version 11040 (0.0005) -[2023-07-08 17:36:55,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8664.1). Total num frames: 5685248. Throughput: 0: 8662.9. Samples: 5672960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:36:55,022][1025936] Avg episode reward: [(0, '798.296')] -[2023-07-08 17:36:55,582][1026190] Updated weights for policy 0, policy_version 11120 (0.0006) -[2023-07-08 17:37:00,022][1025936] Fps is (10 sec: 9011.1, 60 sec: 8738.1, 300 sec: 8664.1). Total num frames: 5730304. Throughput: 0: 8637.0. Samples: 5726280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:37:00,022][1025936] Avg episode reward: [(0, '799.417')] -[2023-07-08 17:37:00,148][1026190] Updated weights for policy 0, policy_version 11200 (0.0005) -[2023-07-08 17:37:04,457][1026190] Updated weights for policy 0, policy_version 11280 (0.0005) -[2023-07-08 17:37:05,022][1025936] Fps is (10 sec: 9420.7, 60 sec: 8738.1, 300 sec: 8691.8). Total num frames: 5779456. Throughput: 0: 8694.4. Samples: 5754944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:37:05,023][1025936] Avg episode reward: [(0, '799.314')] -[2023-07-08 17:37:05,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000011288_5779456.pth... -[2023-07-08 17:37:05,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010768_5513216.pth -[2023-07-08 17:37:09,421][1026190] Updated weights for policy 0, policy_version 11360 (0.0005) -[2023-07-08 17:37:10,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8691.8). Total num frames: 5820416. Throughput: 0: 8754.7. Samples: 5807920. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 17:37:10,022][1025936] Avg episode reward: [(0, '798.277')] -[2023-07-08 17:37:14,222][1026190] Updated weights for policy 0, policy_version 11440 (0.0005) -[2023-07-08 17:37:15,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8669.9, 300 sec: 8678.0). Total num frames: 5861376. Throughput: 0: 8694.8. Samples: 5857360. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 17:37:15,022][1025936] Avg episode reward: [(0, '798.257')] -[2023-07-08 17:37:18,829][1026190] Updated weights for policy 0, policy_version 11520 (0.0005) -[2023-07-08 17:37:20,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8669.9, 300 sec: 8664.1). Total num frames: 5906432. Throughput: 0: 8756.7. Samples: 5884220. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:37:20,022][1025936] Avg episode reward: [(0, '797.581')] -[2023-07-08 17:37:20,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000011536_5906432.pth... -[2023-07-08 17:37:20,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000011016_5640192.pth -[2023-07-08 17:37:23,583][1026190] Updated weights for policy 0, policy_version 11600 (0.0005) -[2023-07-08 17:37:25,022][1025936] Fps is (10 sec: 9011.1, 60 sec: 8738.1, 300 sec: 8678.0). Total num frames: 5951488. Throughput: 0: 8761.8. Samples: 5936176. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:37:25,022][1025936] Avg episode reward: [(0, '800.028')] -[2023-07-08 17:37:28,195][1026190] Updated weights for policy 0, policy_version 11680 (0.0005) -[2023-07-08 17:37:30,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8664.1). Total num frames: 5992448. Throughput: 0: 8819.4. Samples: 5988648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:37:30,022][1025936] Avg episode reward: [(0, '799.267')] -[2023-07-08 17:37:33,104][1026190] Updated weights for policy 0, policy_version 11760 (0.0005) -[2023-07-08 17:37:35,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8678.0). Total num frames: 6037504. Throughput: 0: 8742.9. Samples: 6013216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:37:35,022][1025936] Avg episode reward: [(0, '801.617')] -[2023-07-08 17:37:35,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000011792_6037504.pth... -[2023-07-08 17:37:35,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000011288_5779456.pth -[2023-07-08 17:37:35,029][1026177] Saving new best policy, reward=801.617! -[2023-07-08 17:37:37,562][1026190] Updated weights for policy 0, policy_version 11840 (0.0006) -[2023-07-08 17:37:40,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 8678.0). Total num frames: 6082560. Throughput: 0: 8764.6. Samples: 6067368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:37:40,022][1025936] Avg episode reward: [(0, '800.465')] -[2023-07-08 17:37:42,450][1026190] Updated weights for policy 0, policy_version 11920 (0.0005) -[2023-07-08 17:37:45,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8664.1). Total num frames: 6123520. Throughput: 0: 8738.0. Samples: 6119488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:37:45,022][1025936] Avg episode reward: [(0, '798.233')] -[2023-07-08 17:37:47,107][1026190] Updated weights for policy 0, policy_version 12000 (0.0005) -[2023-07-08 17:37:50,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 8678.0). Total num frames: 6168576. Throughput: 0: 8674.5. Samples: 6145296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:37:50,022][1025936] Avg episode reward: [(0, '800.359')] -[2023-07-08 17:37:50,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012048_6168576.pth... -[2023-07-08 17:37:50,027][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000011536_5906432.pth -[2023-07-08 17:37:51,814][1026190] Updated weights for policy 0, policy_version 12080 (0.0006) -[2023-07-08 17:37:55,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8738.1, 300 sec: 8678.0). Total num frames: 6209536. Throughput: 0: 8650.3. Samples: 6197184. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:37:55,022][1025936] Avg episode reward: [(0, '802.649')] -[2023-07-08 17:37:55,023][1026177] Saving new best policy, reward=802.649! -[2023-07-08 17:37:56,957][1026190] Updated weights for policy 0, policy_version 12160 (0.0005) -[2023-07-08 17:38:00,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8669.9, 300 sec: 8664.1). Total num frames: 6250496. Throughput: 0: 8661.3. Samples: 6247120. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:38:00,022][1025936] Avg episode reward: [(0, '801.656')] -[2023-07-08 17:38:01,515][1026190] Updated weights for policy 0, policy_version 12240 (0.0005) -[2023-07-08 17:38:05,022][1025936] Fps is (10 sec: 8601.3, 60 sec: 8601.6, 300 sec: 8664.1). Total num frames: 6295552. Throughput: 0: 8673.7. Samples: 6274540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:38:05,023][1025936] Avg episode reward: [(0, '801.299')] -[2023-07-08 17:38:05,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012296_6295552.pth... -[2023-07-08 17:38:05,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000011792_6037504.pth -[2023-07-08 17:38:06,424][1026190] Updated weights for policy 0, policy_version 12320 (0.0005) -[2023-07-08 17:38:10,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8601.6, 300 sec: 8650.2). Total num frames: 6336512. Throughput: 0: 8624.9. Samples: 6324296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:38:10,023][1025936] Avg episode reward: [(0, '801.761')] -[2023-07-08 17:38:11,187][1026190] Updated weights for policy 0, policy_version 12400 (0.0006) -[2023-07-08 17:38:15,022][1025936] Fps is (10 sec: 8601.8, 60 sec: 8669.9, 300 sec: 8650.2). Total num frames: 6381568. Throughput: 0: 8595.9. Samples: 6375464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:38:15,022][1025936] Avg episode reward: [(0, '803.348')] -[2023-07-08 17:38:15,023][1026177] Saving new best policy, reward=803.348! -[2023-07-08 17:38:15,929][1026190] Updated weights for policy 0, policy_version 12480 (0.0005) -[2023-07-08 17:38:20,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8601.6, 300 sec: 8650.2). Total num frames: 6422528. Throughput: 0: 8639.3. Samples: 6401984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:38:20,022][1025936] Avg episode reward: [(0, '799.736')] -[2023-07-08 17:38:20,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012544_6422528.pth... -[2023-07-08 17:38:20,027][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012048_6168576.pth -[2023-07-08 17:38:20,792][1026190] Updated weights for policy 0, policy_version 12560 (0.0005) -[2023-07-08 17:38:25,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 6463488. Throughput: 0: 8531.2. Samples: 6451272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:38:25,022][1025936] Avg episode reward: [(0, '798.709')] -[2023-07-08 17:38:25,637][1026190] Updated weights for policy 0, policy_version 12640 (0.0005) -[2023-07-08 17:38:30,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8650.2). Total num frames: 6508544. Throughput: 0: 8516.5. Samples: 6502728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:38:30,022][1025936] Avg episode reward: [(0, '799.095')] -[2023-07-08 17:38:30,263][1026190] Updated weights for policy 0, policy_version 12720 (0.0005) -[2023-07-08 17:38:34,838][1026190] Updated weights for policy 0, policy_version 12800 (0.0005) -[2023-07-08 17:38:35,022][1025936] Fps is (10 sec: 9011.0, 60 sec: 8601.6, 300 sec: 8650.2). Total num frames: 6553600. Throughput: 0: 8535.1. Samples: 6529376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:38:35,023][1025936] Avg episode reward: [(0, '798.701')] -[2023-07-08 17:38:35,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012800_6553600.pth... -[2023-07-08 17:38:35,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012296_6295552.pth -[2023-07-08 17:38:39,892][1026190] Updated weights for policy 0, policy_version 12880 (0.0005) -[2023-07-08 17:38:40,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 6594560. Throughput: 0: 8554.0. Samples: 6582116. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:38:40,022][1025936] Avg episode reward: [(0, '798.221')] -[2023-07-08 17:38:44,557][1026190] Updated weights for policy 0, policy_version 12960 (0.0005) -[2023-07-08 17:38:45,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 6635520. Throughput: 0: 8581.1. Samples: 6633268. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:38:45,022][1025936] Avg episode reward: [(0, '794.153')] -[2023-07-08 17:38:49,311][1026190] Updated weights for policy 0, policy_version 13040 (0.0005) -[2023-07-08 17:38:50,022][1025936] Fps is (10 sec: 8601.4, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 6680576. Throughput: 0: 8505.8. Samples: 6657300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:38:50,023][1025936] Avg episode reward: [(0, '804.412')] -[2023-07-08 17:38:50,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013048_6680576.pth... -[2023-07-08 17:38:50,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012544_6422528.pth -[2023-07-08 17:38:50,029][1026177] Saving new best policy, reward=804.412! -[2023-07-08 17:38:54,344][1026190] Updated weights for policy 0, policy_version 13120 (0.0005) -[2023-07-08 17:38:55,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 6721536. Throughput: 0: 8553.3. Samples: 6709192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:38:55,022][1025936] Avg episode reward: [(0, '797.855')] -[2023-07-08 17:38:59,061][1026190] Updated weights for policy 0, policy_version 13200 (0.0006) -[2023-07-08 17:39:00,022][1025936] Fps is (10 sec: 8192.2, 60 sec: 8533.3, 300 sec: 8622.4). Total num frames: 6762496. Throughput: 0: 8557.1. Samples: 6760532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:39:00,022][1025936] Avg episode reward: [(0, '799.743')] -[2023-07-08 17:39:04,022][1026190] Updated weights for policy 0, policy_version 13280 (0.0005) -[2023-07-08 17:39:05,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8533.4, 300 sec: 8636.3). Total num frames: 6807552. Throughput: 0: 8492.2. Samples: 6784136. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 17:39:05,023][1025936] Avg episode reward: [(0, '795.976')] -[2023-07-08 17:39:05,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013296_6807552.pth... -[2023-07-08 17:39:05,027][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012800_6553600.pth -[2023-07-08 17:39:08,944][1026190] Updated weights for policy 0, policy_version 13360 (0.0005) -[2023-07-08 17:39:10,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 6848512. Throughput: 0: 8542.2. Samples: 6835672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:39:10,023][1025936] Avg episode reward: [(0, '802.695')] -[2023-07-08 17:39:13,848][1026190] Updated weights for policy 0, policy_version 13440 (0.0005) -[2023-07-08 17:39:15,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8622.4). Total num frames: 6889472. Throughput: 0: 8503.0. Samples: 6885364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:39:15,022][1025936] Avg episode reward: [(0, '800.820')] -[2023-07-08 17:39:18,794][1026190] Updated weights for policy 0, policy_version 13520 (0.0004) -[2023-07-08 17:39:20,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8465.1, 300 sec: 8622.4). Total num frames: 6930432. Throughput: 0: 8451.9. Samples: 6909712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:39:20,022][1025936] Avg episode reward: [(0, '800.895')] -[2023-07-08 17:39:20,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013536_6930432.pth... -[2023-07-08 17:39:20,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013048_6680576.pth -[2023-07-08 17:39:23,280][1026190] Updated weights for policy 0, policy_version 13600 (0.0005) -[2023-07-08 17:39:25,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8622.4). Total num frames: 6975488. Throughput: 0: 8468.5. Samples: 6963200. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:39:25,022][1025936] Avg episode reward: [(0, '802.080')] -[2023-07-08 17:39:27,858][1026190] Updated weights for policy 0, policy_version 13680 (0.0005) -[2023-07-08 17:39:30,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8533.3, 300 sec: 8636.3). Total num frames: 7020544. Throughput: 0: 8513.4. Samples: 7016372. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:39:30,022][1025936] Avg episode reward: [(0, '800.067')] -[2023-07-08 17:39:32,564][1026190] Updated weights for policy 0, policy_version 13760 (0.0005) -[2023-07-08 17:39:35,022][1025936] Fps is (10 sec: 9420.8, 60 sec: 8601.6, 300 sec: 8650.2). Total num frames: 7069696. Throughput: 0: 8540.7. Samples: 7041628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:39:35,023][1025936] Avg episode reward: [(0, '802.370')] -[2023-07-08 17:39:35,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013808_7069696.pth... -[2023-07-08 17:39:35,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013296_6807552.pth -[2023-07-08 17:39:36,869][1026190] Updated weights for policy 0, policy_version 13840 (0.0005) -[2023-07-08 17:39:40,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8601.6, 300 sec: 8636.3). Total num frames: 7110656. Throughput: 0: 8645.5. Samples: 7098240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:39:40,022][1025936] Avg episode reward: [(0, '797.445')] -[2023-07-08 17:39:41,530][1026190] Updated weights for policy 0, policy_version 13920 (0.0005) -[2023-07-08 17:39:45,022][1025936] Fps is (10 sec: 9011.3, 60 sec: 8738.1, 300 sec: 8664.1). Total num frames: 7159808. Throughput: 0: 8703.9. Samples: 7152208. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:39:45,022][1025936] Avg episode reward: [(0, '803.767')] -[2023-07-08 17:39:45,704][1026190] Updated weights for policy 0, policy_version 14000 (0.0005) -[2023-07-08 17:39:50,022][1025936] Fps is (10 sec: 9011.1, 60 sec: 8669.9, 300 sec: 8664.1). Total num frames: 7200768. Throughput: 0: 8820.1. Samples: 7181040. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:39:50,023][1025936] Avg episode reward: [(0, '802.190')] -[2023-07-08 17:39:50,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014064_7200768.pth... -[2023-07-08 17:39:50,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013536_6930432.pth -[2023-07-08 17:39:50,655][1026190] Updated weights for policy 0, policy_version 14080 (0.0005) -[2023-07-08 17:39:55,022][1025936] Fps is (10 sec: 8191.9, 60 sec: 8669.9, 300 sec: 8650.2). Total num frames: 7241728. Throughput: 0: 8751.8. Samples: 7229504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:39:55,022][1025936] Avg episode reward: [(0, '801.236')] -[2023-07-08 17:39:55,813][1026190] Updated weights for policy 0, policy_version 14160 (0.0005) -[2023-07-08 17:40:00,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8669.9, 300 sec: 8650.2). Total num frames: 7282688. Throughput: 0: 8747.5. Samples: 7279000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:40:00,022][1025936] Avg episode reward: [(0, '798.518')] -[2023-07-08 17:40:00,727][1026190] Updated weights for policy 0, policy_version 14240 (0.0005) -[2023-07-08 17:40:05,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8664.1). Total num frames: 7327744. Throughput: 0: 8745.1. Samples: 7303240. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:40:05,023][1025936] Avg episode reward: [(0, '801.489')] -[2023-07-08 17:40:05,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014312_7327744.pth... -[2023-07-08 17:40:05,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013808_7069696.pth -[2023-07-08 17:40:05,388][1026190] Updated weights for policy 0, policy_version 14320 (0.0005) -[2023-07-08 17:40:09,946][1026190] Updated weights for policy 0, policy_version 14400 (0.0005) -[2023-07-08 17:40:10,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 8678.0). Total num frames: 7372800. Throughput: 0: 8739.5. Samples: 7356480. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:40:10,023][1025936] Avg episode reward: [(0, '802.292')] -[2023-07-08 17:40:14,804][1026190] Updated weights for policy 0, policy_version 14480 (0.0005) -[2023-07-08 17:40:15,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 8664.1). Total num frames: 7413760. Throughput: 0: 8731.6. Samples: 7409296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:40:15,023][1025936] Avg episode reward: [(0, '798.581')] -[2023-07-08 17:40:19,744][1026190] Updated weights for policy 0, policy_version 14560 (0.0005) -[2023-07-08 17:40:20,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8738.1, 300 sec: 8664.1). Total num frames: 7454720. Throughput: 0: 8724.9. Samples: 7434248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:40:20,023][1025936] Avg episode reward: [(0, '797.534')] -[2023-07-08 17:40:20,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014560_7454720.pth... -[2023-07-08 17:40:20,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014064_7200768.pth -[2023-07-08 17:40:24,702][1026190] Updated weights for policy 0, policy_version 14640 (0.0005) -[2023-07-08 17:40:25,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8669.9, 300 sec: 8636.3). Total num frames: 7495680. Throughput: 0: 8573.9. Samples: 7484064. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:40:25,023][1025936] Avg episode reward: [(0, '797.610')] -[2023-07-08 17:40:29,803][1026190] Updated weights for policy 0, policy_version 14720 (0.0005) -[2023-07-08 17:40:30,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8601.6, 300 sec: 8622.4). Total num frames: 7536640. Throughput: 0: 8449.4. Samples: 7532432. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:40:30,023][1025936] Avg episode reward: [(0, '796.074')] -[2023-07-08 17:40:34,623][1026190] Updated weights for policy 0, policy_version 14800 (0.0005) -[2023-07-08 17:40:35,022][1025936] Fps is (10 sec: 8191.9, 60 sec: 8465.1, 300 sec: 8622.4). Total num frames: 7577600. Throughput: 0: 8358.8. Samples: 7557184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:40:35,023][1025936] Avg episode reward: [(0, '800.454')] -[2023-07-08 17:40:35,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014800_7577600.pth... -[2023-07-08 17:40:35,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014312_7327744.pth -[2023-07-08 17:40:39,655][1026190] Updated weights for policy 0, policy_version 14880 (0.0004) -[2023-07-08 17:40:40,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8465.1, 300 sec: 8608.5). Total num frames: 7618560. Throughput: 0: 8402.1. Samples: 7607596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:40:40,023][1025936] Avg episode reward: [(0, '799.346')] -[2023-07-08 17:40:44,744][1026190] Updated weights for policy 0, policy_version 14960 (0.0005) -[2023-07-08 17:40:45,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8328.5, 300 sec: 8608.5). Total num frames: 7659520. Throughput: 0: 8366.4. Samples: 7655488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:40:45,023][1025936] Avg episode reward: [(0, '803.495')] -[2023-07-08 17:40:49,554][1026190] Updated weights for policy 0, policy_version 15040 (0.0005) -[2023-07-08 17:40:50,022][1025936] Fps is (10 sec: 8191.9, 60 sec: 8328.5, 300 sec: 8594.7). Total num frames: 7700480. Throughput: 0: 8390.2. Samples: 7680800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:40:50,023][1025936] Avg episode reward: [(0, '800.207')] -[2023-07-08 17:40:50,027][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015048_7704576.pth... -[2023-07-08 17:40:50,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014560_7454720.pth -[2023-07-08 17:40:54,108][1026190] Updated weights for policy 0, policy_version 15120 (0.0005) -[2023-07-08 17:40:55,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8396.8, 300 sec: 8608.5). Total num frames: 7745536. Throughput: 0: 8387.8. Samples: 7733932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:40:55,023][1025936] Avg episode reward: [(0, '801.665')] -[2023-07-08 17:40:59,043][1026190] Updated weights for policy 0, policy_version 15200 (0.0005) -[2023-07-08 17:41:00,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8465.1, 300 sec: 8594.7). Total num frames: 7790592. Throughput: 0: 8338.9. Samples: 7784548. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:41:00,022][1025936] Avg episode reward: [(0, '801.513')] -[2023-07-08 17:41:04,000][1026190] Updated weights for policy 0, policy_version 15280 (0.0005) -[2023-07-08 17:41:05,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8594.7). Total num frames: 7831552. Throughput: 0: 8352.6. Samples: 7810116. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 17:41:05,022][1025936] Avg episode reward: [(0, '800.329')] -[2023-07-08 17:41:05,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015296_7831552.pth... -[2023-07-08 17:41:05,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014800_7577600.pth -[2023-07-08 17:41:08,813][1026190] Updated weights for policy 0, policy_version 15360 (0.0005) -[2023-07-08 17:41:10,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8328.5, 300 sec: 8580.8). Total num frames: 7872512. Throughput: 0: 8336.9. Samples: 7859224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:41:10,022][1025936] Avg episode reward: [(0, '798.133')] -[2023-07-08 17:41:13,313][1026190] Updated weights for policy 0, policy_version 15440 (0.0005) -[2023-07-08 17:41:15,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8396.8, 300 sec: 8580.8). Total num frames: 7917568. Throughput: 0: 8463.8. Samples: 7913304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:41:15,022][1025936] Avg episode reward: [(0, '802.757')] -[2023-07-08 17:41:18,143][1026190] Updated weights for policy 0, policy_version 15520 (0.0004) -[2023-07-08 17:41:20,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8580.8). Total num frames: 7958528. Throughput: 0: 8487.7. Samples: 7939128. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:41:20,022][1025936] Avg episode reward: [(0, '796.970')] -[2023-07-08 17:41:20,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015544_7958528.pth... -[2023-07-08 17:41:20,027][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015048_7704576.pth -[2023-07-08 17:41:22,921][1026190] Updated weights for policy 0, policy_version 15600 (0.0005) -[2023-07-08 17:41:25,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8594.7). Total num frames: 8003584. Throughput: 0: 8510.9. Samples: 7990588. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:41:25,022][1025936] Avg episode reward: [(0, '801.811')] -[2023-07-08 17:41:27,616][1026190] Updated weights for policy 0, policy_version 15680 (0.0005) -[2023-07-08 17:41:30,022][1025936] Fps is (10 sec: 9011.1, 60 sec: 8533.3, 300 sec: 8594.7). Total num frames: 8048640. Throughput: 0: 8595.4. Samples: 8042284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:41:30,023][1025936] Avg episode reward: [(0, '801.837')] -[2023-07-08 17:41:32,564][1026190] Updated weights for policy 0, policy_version 15760 (0.0005) -[2023-07-08 17:41:35,022][1025936] Fps is (10 sec: 8191.9, 60 sec: 8465.1, 300 sec: 8580.8). Total num frames: 8085504. Throughput: 0: 8586.7. Samples: 8067200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:41:35,022][1025936] Avg episode reward: [(0, '802.691')] -[2023-07-08 17:41:35,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015792_8085504.pth... -[2023-07-08 17:41:35,027][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015296_7831552.pth -[2023-07-08 17:41:37,631][1026190] Updated weights for policy 0, policy_version 15840 (0.0005) -[2023-07-08 17:41:40,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 8580.8). Total num frames: 8130560. Throughput: 0: 8503.4. Samples: 8116584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:41:40,022][1025936] Avg episode reward: [(0, '800.584')] -[2023-07-08 17:41:42,468][1026190] Updated weights for policy 0, policy_version 15920 (0.0006) -[2023-07-08 17:41:45,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8465.1, 300 sec: 8566.9). Total num frames: 8167424. Throughput: 0: 8451.4. Samples: 8164860. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:41:45,022][1025936] Avg episode reward: [(0, '805.321')] -[2023-07-08 17:41:45,023][1026177] Saving new best policy, reward=805.321! -[2023-07-08 17:41:47,228][1026190] Updated weights for policy 0, policy_version 16000 (0.0005) -[2023-07-08 17:41:50,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 8566.9). Total num frames: 8212480. Throughput: 0: 8487.9. Samples: 8192072. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:41:50,022][1025936] Avg episode reward: [(0, '798.448')] -[2023-07-08 17:41:50,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000016040_8212480.pth... -[2023-07-08 17:41:50,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015544_7958528.pth -[2023-07-08 17:41:52,248][1026190] Updated weights for policy 0, policy_version 16080 (0.0005) -[2023-07-08 17:41:55,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8465.1, 300 sec: 8553.0). Total num frames: 8253440. Throughput: 0: 8521.1. Samples: 8242676. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:41:55,022][1025936] Avg episode reward: [(0, '797.590')] -[2023-07-08 17:41:56,960][1026190] Updated weights for policy 0, policy_version 16160 (0.0006) -[2023-07-08 17:42:00,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8533.3, 300 sec: 8553.0). Total num frames: 8302592. Throughput: 0: 8503.1. Samples: 8295944. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 17:42:00,023][1025936] Avg episode reward: [(0, '804.224')] -[2023-07-08 17:42:01,442][1026190] Updated weights for policy 0, policy_version 16240 (0.0006) -[2023-07-08 17:42:05,022][1025936] Fps is (10 sec: 9011.1, 60 sec: 8533.3, 300 sec: 8553.0). Total num frames: 8343552. Throughput: 0: 8532.2. Samples: 8323080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:42:05,023][1025936] Avg episode reward: [(0, '803.775')] -[2023-07-08 17:42:05,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000016296_8343552.pth... -[2023-07-08 17:42:05,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015792_8085504.pth -[2023-07-08 17:42:06,268][1026190] Updated weights for policy 0, policy_version 16320 (0.0005) -[2023-07-08 17:42:10,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8533.3, 300 sec: 8553.0). Total num frames: 8384512. Throughput: 0: 8478.8. Samples: 8372136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:42:10,022][1025936] Avg episode reward: [(0, '804.635')] -[2023-07-08 17:42:11,341][1026190] Updated weights for policy 0, policy_version 16400 (0.0004) -[2023-07-08 17:42:15,022][1025936] Fps is (10 sec: 8192.2, 60 sec: 8465.1, 300 sec: 8539.1). Total num frames: 8425472. Throughput: 0: 8420.9. Samples: 8421224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:42:15,022][1025936] Avg episode reward: [(0, '803.283')] -[2023-07-08 17:42:16,283][1026190] Updated weights for policy 0, policy_version 16480 (0.0005) -[2023-07-08 17:42:20,022][1025936] Fps is (10 sec: 8191.9, 60 sec: 8465.1, 300 sec: 8525.2). Total num frames: 8466432. Throughput: 0: 8416.1. Samples: 8445924. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:42:20,023][1025936] Avg episode reward: [(0, '801.492')] -[2023-07-08 17:42:20,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000016536_8466432.pth... -[2023-07-08 17:42:20,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000016040_8212480.pth -[2023-07-08 17:42:21,292][1026190] Updated weights for policy 0, policy_version 16560 (0.0005) -[2023-07-08 17:42:25,022][1025936] Fps is (10 sec: 8191.9, 60 sec: 8396.8, 300 sec: 8525.2). Total num frames: 8507392. Throughput: 0: 8409.5. Samples: 8495012. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:42:25,023][1025936] Avg episode reward: [(0, '801.168')] -[2023-07-08 17:42:26,281][1026190] Updated weights for policy 0, policy_version 16640 (0.0005) -[2023-07-08 17:42:30,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8511.3). Total num frames: 8548352. Throughput: 0: 8445.2. Samples: 8544896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:42:30,022][1025936] Avg episode reward: [(0, '798.899')] -[2023-07-08 17:42:31,220][1026190] Updated weights for policy 0, policy_version 16720 (0.0005) -[2023-07-08 17:42:35,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8465.1, 300 sec: 8511.3). Total num frames: 8593408. Throughput: 0: 8389.1. Samples: 8569580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:42:35,023][1025936] Avg episode reward: [(0, '801.395')] -[2023-07-08 17:42:35,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000016784_8593408.pth... -[2023-07-08 17:42:35,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000016296_8343552.pth -[2023-07-08 17:42:35,826][1026190] Updated weights for policy 0, policy_version 16800 (0.0005) -[2023-07-08 17:42:40,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8465.1, 300 sec: 8525.2). Total num frames: 8638464. Throughput: 0: 8454.1. Samples: 8623112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:42:40,022][1025936] Avg episode reward: [(0, '804.262')] -[2023-07-08 17:42:40,339][1026190] Updated weights for policy 0, policy_version 16880 (0.0005) -[2023-07-08 17:42:45,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8533.3, 300 sec: 8511.3). Total num frames: 8679424. Throughput: 0: 8461.2. Samples: 8676696. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 17:42:45,022][1025936] Avg episode reward: [(0, '804.048')] -[2023-07-08 17:42:45,116][1026190] Updated weights for policy 0, policy_version 16960 (0.0005) -[2023-07-08 17:42:49,866][1026190] Updated weights for policy 0, policy_version 17040 (0.0006) -[2023-07-08 17:42:50,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8525.2). Total num frames: 8724480. Throughput: 0: 8431.0. Samples: 8702476. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 17:42:50,022][1025936] Avg episode reward: [(0, '804.764')] -[2023-07-08 17:42:50,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017040_8724480.pth... -[2023-07-08 17:42:50,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000016536_8466432.pth -[2023-07-08 17:42:54,491][1026190] Updated weights for policy 0, policy_version 17120 (0.0005) -[2023-07-08 17:42:55,022][1025936] Fps is (10 sec: 9011.1, 60 sec: 8601.6, 300 sec: 8539.1). Total num frames: 8769536. Throughput: 0: 8512.4. Samples: 8755196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:42:55,023][1025936] Avg episode reward: [(0, '804.665')] -[2023-07-08 17:42:59,321][1026190] Updated weights for policy 0, policy_version 17200 (0.0006) -[2023-07-08 17:43:00,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8525.2). Total num frames: 8810496. Throughput: 0: 8557.1. Samples: 8806292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:43:00,022][1025936] Avg episode reward: [(0, '805.688')] -[2023-07-08 17:43:00,023][1026177] Saving new best policy, reward=805.688! -[2023-07-08 17:43:04,185][1026190] Updated weights for policy 0, policy_version 17280 (0.0005) -[2023-07-08 17:43:05,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8465.1, 300 sec: 8525.2). Total num frames: 8851456. Throughput: 0: 8554.6. Samples: 8830880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:43:05,022][1025936] Avg episode reward: [(0, '802.554')] -[2023-07-08 17:43:05,024][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017288_8851456.pth... -[2023-07-08 17:43:05,026][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000016784_8593408.pth -[2023-07-08 17:43:09,090][1026190] Updated weights for policy 0, policy_version 17360 (0.0005) -[2023-07-08 17:43:10,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8465.1, 300 sec: 8511.4). Total num frames: 8892416. Throughput: 0: 8570.4. Samples: 8880680. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:43:10,022][1025936] Avg episode reward: [(0, '803.534')] -[2023-07-08 17:43:13,628][1026190] Updated weights for policy 0, policy_version 17440 (0.0005) -[2023-07-08 17:43:15,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8525.2). Total num frames: 8937472. Throughput: 0: 8644.1. Samples: 8933880. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 17:43:15,022][1025936] Avg episode reward: [(0, '805.910')] -[2023-07-08 17:43:15,023][1026177] Saving new best policy, reward=805.910! -[2023-07-08 17:43:18,616][1026190] Updated weights for policy 0, policy_version 17520 (0.0005) -[2023-07-08 17:43:20,022][1025936] Fps is (10 sec: 9011.0, 60 sec: 8601.6, 300 sec: 8539.1). Total num frames: 8982528. Throughput: 0: 8661.9. Samples: 8959364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:43:20,023][1025936] Avg episode reward: [(0, '802.751')] -[2023-07-08 17:43:20,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017544_8982528.pth... -[2023-07-08 17:43:20,030][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017040_8724480.pth -[2023-07-08 17:43:23,211][1026190] Updated weights for policy 0, policy_version 17600 (0.0005) -[2023-07-08 17:43:25,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8525.2). Total num frames: 9023488. Throughput: 0: 8629.5. Samples: 9011440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:43:25,022][1025936] Avg episode reward: [(0, '804.406')] -[2023-07-08 17:43:28,151][1026190] Updated weights for policy 0, policy_version 17680 (0.0005) -[2023-07-08 17:43:30,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8669.9, 300 sec: 8525.2). Total num frames: 9068544. Throughput: 0: 8544.5. Samples: 9061196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:43:30,022][1025936] Avg episode reward: [(0, '800.786')] -[2023-07-08 17:43:32,485][1026190] Updated weights for policy 0, policy_version 17760 (0.0005) -[2023-07-08 17:43:35,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8669.9, 300 sec: 8539.1). Total num frames: 9113600. Throughput: 0: 8641.6. Samples: 9091348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:43:35,022][1025936] Avg episode reward: [(0, '803.984')] -[2023-07-08 17:43:35,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017800_9113600.pth... -[2023-07-08 17:43:35,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017288_8851456.pth -[2023-07-08 17:43:37,367][1026190] Updated weights for policy 0, policy_version 17840 (0.0005) -[2023-07-08 17:43:40,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8539.1). Total num frames: 9154560. Throughput: 0: 8601.7. Samples: 9142272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:43:40,022][1025936] Avg episode reward: [(0, '802.130')] -[2023-07-08 17:43:42,214][1026190] Updated weights for policy 0, policy_version 17920 (0.0005) -[2023-07-08 17:43:45,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8601.6, 300 sec: 8525.2). Total num frames: 9195520. Throughput: 0: 8595.8. Samples: 9193104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:43:45,022][1025936] Avg episode reward: [(0, '799.856')] -[2023-07-08 17:43:47,063][1026190] Updated weights for policy 0, policy_version 18000 (0.0005) -[2023-07-08 17:43:50,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8539.1). Total num frames: 9240576. Throughput: 0: 8605.2. Samples: 9218116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:43:50,023][1025936] Avg episode reward: [(0, '800.815')] -[2023-07-08 17:43:50,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018048_9240576.pth... -[2023-07-08 17:43:50,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017544_8982528.pth -[2023-07-08 17:43:51,720][1026190] Updated weights for policy 0, policy_version 18080 (0.0005) -[2023-07-08 17:43:55,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8533.3, 300 sec: 8539.1). Total num frames: 9281536. Throughput: 0: 8641.3. Samples: 9269540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:43:55,023][1025936] Avg episode reward: [(0, '798.323')] -[2023-07-08 17:43:56,630][1026190] Updated weights for policy 0, policy_version 18160 (0.0005) -[2023-07-08 17:44:00,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8539.1). Total num frames: 9326592. Throughput: 0: 8630.4. Samples: 9322248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:44:00,023][1025936] Avg episode reward: [(0, '800.464')] -[2023-07-08 17:44:01,262][1026190] Updated weights for policy 0, policy_version 18240 (0.0005) -[2023-07-08 17:44:05,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8669.9, 300 sec: 8553.0). Total num frames: 9371648. Throughput: 0: 8662.4. Samples: 9349172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:44:05,023][1025936] Avg episode reward: [(0, '801.273')] -[2023-07-08 17:44:05,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018304_9371648.pth... -[2023-07-08 17:44:05,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017800_9113600.pth -[2023-07-08 17:44:05,783][1026190] Updated weights for policy 0, policy_version 18320 (0.0005) -[2023-07-08 17:44:10,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8669.9, 300 sec: 8553.0). Total num frames: 9412608. Throughput: 0: 8643.2. Samples: 9400384. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:44:10,023][1025936] Avg episode reward: [(0, '802.443')] -[2023-07-08 17:44:10,646][1026190] Updated weights for policy 0, policy_version 18400 (0.0005) -[2023-07-08 17:44:15,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8669.9, 300 sec: 8566.9). Total num frames: 9457664. Throughput: 0: 8718.7. Samples: 9453536. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:44:15,023][1025936] Avg episode reward: [(0, '802.791')] -[2023-07-08 17:44:15,271][1026190] Updated weights for policy 0, policy_version 18480 (0.0005) -[2023-07-08 17:44:20,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8553.0). Total num frames: 9498624. Throughput: 0: 8595.7. Samples: 9478156. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:44:20,023][1025936] Avg episode reward: [(0, '802.807')] -[2023-07-08 17:44:20,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018552_9498624.pth... -[2023-07-08 17:44:20,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018048_9240576.pth -[2023-07-08 17:44:20,337][1026190] Updated weights for policy 0, policy_version 18560 (0.0005) -[2023-07-08 17:44:25,022][1025936] Fps is (10 sec: 8192.0, 60 sec: 8601.6, 300 sec: 8539.1). Total num frames: 9539584. Throughput: 0: 8568.5. Samples: 9527856. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:44:25,023][1025936] Avg episode reward: [(0, '801.982')] -[2023-07-08 17:44:25,125][1026190] Updated weights for policy 0, policy_version 18640 (0.0005) -[2023-07-08 17:44:29,940][1026190] Updated weights for policy 0, policy_version 18720 (0.0005) -[2023-07-08 17:44:30,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8525.2). Total num frames: 9584640. Throughput: 0: 8548.8. Samples: 9577800. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 17:44:30,023][1025936] Avg episode reward: [(0, '801.408')] -[2023-07-08 17:44:34,715][1026190] Updated weights for policy 0, policy_version 18800 (0.0005) -[2023-07-08 17:44:35,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8533.3, 300 sec: 8525.2). Total num frames: 9625600. Throughput: 0: 8600.3. Samples: 9605128. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:44:35,023][1025936] Avg episode reward: [(0, '801.883')] -[2023-07-08 17:44:35,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018800_9625600.pth... -[2023-07-08 17:44:35,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018304_9371648.pth -[2023-07-08 17:44:39,481][1026190] Updated weights for policy 0, policy_version 18880 (0.0005) -[2023-07-08 17:44:40,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8601.6, 300 sec: 8511.3). Total num frames: 9670656. Throughput: 0: 8580.5. Samples: 9655664. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:44:40,023][1025936] Avg episode reward: [(0, '801.634')] -[2023-07-08 17:44:44,226][1026190] Updated weights for policy 0, policy_version 18960 (0.0005) -[2023-07-08 17:44:45,022][1025936] Fps is (10 sec: 8601.7, 60 sec: 8601.6, 300 sec: 8511.4). Total num frames: 9711616. Throughput: 0: 8563.2. Samples: 9707592. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 17:44:45,022][1025936] Avg episode reward: [(0, '802.557')] -[2023-07-08 17:44:49,037][1026190] Updated weights for policy 0, policy_version 19040 (0.0006) -[2023-07-08 17:44:50,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8525.2). Total num frames: 9756672. Throughput: 0: 8567.9. Samples: 9734728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:44:50,023][1025936] Avg episode reward: [(0, '801.932')] -[2023-07-08 17:44:50,025][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000019056_9756672.pth... -[2023-07-08 17:44:50,028][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018552_9498624.pth -[2023-07-08 17:44:53,651][1026190] Updated weights for policy 0, policy_version 19120 (0.0005) -[2023-07-08 17:44:55,022][1025936] Fps is (10 sec: 8601.5, 60 sec: 8601.6, 300 sec: 8525.2). Total num frames: 9797632. Throughput: 0: 8570.4. Samples: 9786052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:44:55,022][1025936] Avg episode reward: [(0, '801.098')] -[2023-07-08 17:44:58,783][1026190] Updated weights for policy 0, policy_version 19200 (0.0006) -[2023-07-08 17:45:00,022][1025936] Fps is (10 sec: 8192.1, 60 sec: 8533.3, 300 sec: 8511.3). Total num frames: 9838592. Throughput: 0: 8467.4. Samples: 9834568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:45:00,023][1025936] Avg episode reward: [(0, '804.221')] -[2023-07-08 17:45:03,218][1026190] Updated weights for policy 0, policy_version 19280 (0.0005) -[2023-07-08 17:45:05,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8511.3). Total num frames: 9883648. Throughput: 0: 8556.0. Samples: 9863176. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:45:05,023][1025936] Avg episode reward: [(0, '804.144')] -[2023-07-08 17:45:05,026][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000019304_9883648.pth... -[2023-07-08 17:45:05,029][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018800_9625600.pth -[2023-07-08 17:45:08,097][1026190] Updated weights for policy 0, policy_version 19360 (0.0005) -[2023-07-08 17:45:10,022][1025936] Fps is (10 sec: 9011.2, 60 sec: 8601.6, 300 sec: 8525.2). Total num frames: 9928704. Throughput: 0: 8579.7. Samples: 9913944. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 17:45:10,023][1025936] Avg episode reward: [(0, '801.634')] -[2023-07-08 17:45:12,782][1026190] Updated weights for policy 0, policy_version 19440 (0.0004) -[2023-07-08 17:45:15,022][1025936] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8525.2). Total num frames: 9969664. Throughput: 0: 8617.2. Samples: 9965576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 17:45:15,023][1025936] Avg episode reward: [(0, '802.558')] -[2023-07-08 17:45:17,744][1026190] Updated weights for policy 0, policy_version 19520 (0.0005) -[2023-07-08 17:45:18,747][1026177] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000008 -[2023-07-08 17:45:19,282][1026177] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 -[2023-07-08 17:45:19,283][1026257] Stopping RolloutWorker_w5... -[2023-07-08 17:45:19,283][1026290] Stopping RolloutWorker_w3... -[2023-07-08 17:45:19,283][1026256] Stopping RolloutWorker_w4... -[2023-07-08 17:45:19,283][1026291] Stopping RolloutWorker_w6... -[2023-07-08 17:45:19,283][1026289] Stopping RolloutWorker_w7... -[2023-07-08 17:45:19,283][1026191] Stopping RolloutWorker_w0... -[2023-07-08 17:45:19,283][1026192] Stopping RolloutWorker_w1... -[2023-07-08 17:45:19,283][1026256] Loop rollout_proc4_evt_loop terminating... -[2023-07-08 17:45:19,283][1026290] Loop rollout_proc3_evt_loop terminating... -[2023-07-08 17:45:19,283][1026257] Loop rollout_proc5_evt_loop terminating... -[2023-07-08 17:45:19,283][1026291] Loop rollout_proc6_evt_loop terminating... -[2023-07-08 17:45:19,283][1026289] Loop rollout_proc7_evt_loop terminating... -[2023-07-08 17:45:19,283][1026224] Stopping RolloutWorker_w2... -[2023-07-08 17:45:19,283][1026191] Loop rollout_proc0_evt_loop terminating... -[2023-07-08 17:45:19,283][1025936] Component RolloutWorker_w5 stopped! -[2023-07-08 17:45:19,283][1026192] Loop rollout_proc1_evt_loop terminating... -[2023-07-08 17:45:19,283][1026224] Loop rollout_proc2_evt_loop terminating... -[2023-07-08 17:45:19,283][1025936] Component RolloutWorker_w3 stopped! -[2023-07-08 17:45:19,284][1025936] Component RolloutWorker_w6 stopped! -[2023-07-08 17:45:19,284][1025936] Component RolloutWorker_w4 stopped! -[2023-07-08 17:45:19,283][1026177] Stopping Batcher_0... -[2023-07-08 17:45:19,284][1025936] Component RolloutWorker_w1 stopped! -[2023-07-08 17:45:19,284][1025936] Component RolloutWorker_w7 stopped! -[2023-07-08 17:45:19,284][1026177] Loop batcher_evt_loop terminating... -[2023-07-08 17:45:19,284][1025936] Component RolloutWorker_w2 stopped! -[2023-07-08 17:45:19,284][1025936] Component RolloutWorker_w0 stopped! -[2023-07-08 17:45:19,284][1025936] Component Batcher_0 stopped! -[2023-07-08 17:45:19,284][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... -[2023-07-08 17:45:19,288][1026177] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000019056_9756672.pth -[2023-07-08 17:45:19,289][1026177] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... -[2023-07-08 17:45:19,292][1026177] Stopping LearnerWorker_p0... -[2023-07-08 17:45:19,292][1026177] Loop learner_proc0_evt_loop terminating... -[2023-07-08 17:45:19,292][1025936] Component LearnerWorker_p0 stopped! -[2023-07-08 17:45:19,354][1026190] Weights refcount: 2 0 -[2023-07-08 17:45:19,355][1026190] Stopping InferenceWorker_p0-w0... -[2023-07-08 17:45:19,355][1026190] Loop inference_proc0-0_evt_loop terminating... -[2023-07-08 17:45:19,355][1025936] Component InferenceWorker_p0-w0 stopped! -[2023-07-08 17:45:19,356][1025936] Waiting for process learner_proc0 to stop... -[2023-07-08 17:45:19,937][1025936] Waiting for process inference_proc0-0 to join... -[2023-07-08 17:45:20,058][1025936] Waiting for process rollout_proc0 to join... -[2023-07-08 17:45:20,058][1025936] Waiting for process rollout_proc1 to join... -[2023-07-08 17:45:20,058][1025936] Waiting for process rollout_proc2 to join... -[2023-07-08 17:45:20,059][1025936] Waiting for process rollout_proc3 to join... -[2023-07-08 17:45:20,059][1025936] Waiting for process rollout_proc4 to join... -[2023-07-08 17:45:20,059][1025936] Waiting for process rollout_proc5 to join... -[2023-07-08 17:45:20,060][1025936] Waiting for process rollout_proc6 to join... -[2023-07-08 17:45:20,060][1025936] Waiting for process rollout_proc7 to join... -[2023-07-08 17:45:20,060][1025936] Batcher 0 profile tree view: -batching: 1.8440, releasing_batches: 1.6418 -[2023-07-08 17:45:20,060][1025936] InferenceWorker_p0-w0 profile tree view: +[2023-07-16 22:38:32,068][254134] Worker 7 uses CPU cores [28, 29, 30, 31] +[2023-07-16 22:38:32,192][254038] Worker 3 uses CPU cores [12, 13, 14, 15] +[2023-07-16 22:38:32,349][254037] Worker 4 uses CPU cores [16, 17, 18, 19] +[2023-07-16 22:38:32,379][253989] Using optimizer +[2023-07-16 22:38:32,380][253989] No checkpoints found +[2023-07-16 22:38:32,380][253989] Did not load from checkpoint, starting from scratch! +[2023-07-16 22:38:32,381][253989] Initialized policy 0 weights for model version 0 +[2023-07-16 22:38:32,382][253989] LearnerWorker_p0 finished initialization! +[2023-07-16 22:38:32,383][254034] Worker 0 uses CPU cores [0, 1, 2, 3] +[2023-07-16 22:38:32,427][254033] RunningMeanStd input shape: (39,) +[2023-07-16 22:38:32,427][254033] RunningMeanStd input shape: (1,) +[2023-07-16 22:38:32,482][253751] Inference worker 0-0 is ready! +[2023-07-16 22:38:32,482][253751] All inference workers are ready! Signal rollout workers to start! +[2023-07-16 22:38:32,545][254035] Worker 1 uses CPU cores [4, 5, 6, 7] +[2023-07-16 22:38:32,644][254040] Worker 6 uses CPU cores [24, 25, 26, 27] +[2023-07-16 22:38:32,692][254039] Worker 5 uses CPU cores [20, 21, 22, 23] +[2023-07-16 22:38:32,971][253751] 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 22:38:33,917][254037] Decorrelating experience for 0 frames... +[2023-07-16 22:38:33,925][254037] Decorrelating experience for 64 frames... +[2023-07-16 22:38:33,931][254036] Decorrelating experience for 0 frames... +[2023-07-16 22:38:33,939][254036] Decorrelating experience for 64 frames... +[2023-07-16 22:38:33,940][254034] Decorrelating experience for 0 frames... +[2023-07-16 22:38:33,943][254038] Decorrelating experience for 0 frames... +[2023-07-16 22:38:33,943][254134] Decorrelating experience for 0 frames... +[2023-07-16 22:38:33,948][254034] Decorrelating experience for 64 frames... +[2023-07-16 22:38:33,950][254038] Decorrelating experience for 64 frames... +[2023-07-16 22:38:33,950][254134] Decorrelating experience for 64 frames... +[2023-07-16 22:38:33,953][254037] Decorrelating experience for 128 frames... +[2023-07-16 22:38:33,967][254036] Decorrelating experience for 128 frames... +[2023-07-16 22:38:33,976][254034] Decorrelating experience for 128 frames... +[2023-07-16 22:38:33,978][254038] Decorrelating experience for 128 frames... +[2023-07-16 22:38:33,979][254134] Decorrelating experience for 128 frames... +[2023-07-16 22:38:34,007][254037] Decorrelating experience for 192 frames... +[2023-07-16 22:38:34,030][254034] Decorrelating experience for 192 frames... +[2023-07-16 22:38:34,031][254036] Decorrelating experience for 192 frames... +[2023-07-16 22:38:34,036][254038] Decorrelating experience for 192 frames... +[2023-07-16 22:38:34,039][254134] Decorrelating experience for 192 frames... +[2023-07-16 22:38:34,061][254035] Decorrelating experience for 0 frames... +[2023-07-16 22:38:34,068][254035] Decorrelating experience for 64 frames... +[2023-07-16 22:38:34,095][254040] Decorrelating experience for 0 frames... +[2023-07-16 22:38:34,096][254035] Decorrelating experience for 128 frames... +[2023-07-16 22:38:34,102][254040] Decorrelating experience for 64 frames... +[2023-07-16 22:38:34,129][254040] Decorrelating experience for 128 frames... +[2023-07-16 22:38:34,153][254035] Decorrelating experience for 192 frames... +[2023-07-16 22:38:34,173][254039] Decorrelating experience for 0 frames... +[2023-07-16 22:38:34,180][254039] Decorrelating experience for 64 frames... +[2023-07-16 22:38:34,183][254040] Decorrelating experience for 192 frames... +[2023-07-16 22:38:34,207][254039] Decorrelating experience for 128 frames... +[2023-07-16 22:38:34,268][254039] Decorrelating experience for 192 frames... +[2023-07-16 22:38:35,415][254037] Decorrelating experience for 256 frames... +[2023-07-16 22:38:35,439][254034] Decorrelating experience for 256 frames... +[2023-07-16 22:38:35,442][254036] Decorrelating experience for 256 frames... +[2023-07-16 22:38:35,484][254038] Decorrelating experience for 256 frames... +[2023-07-16 22:38:35,486][254134] Decorrelating experience for 256 frames... +[2023-07-16 22:38:35,517][254037] Decorrelating experience for 320 frames... +[2023-07-16 22:38:35,545][254036] Decorrelating experience for 320 frames... +[2023-07-16 22:38:35,548][254034] Decorrelating experience for 320 frames... +[2023-07-16 22:38:35,589][254134] Decorrelating experience for 320 frames... +[2023-07-16 22:38:35,591][254038] Decorrelating experience for 320 frames... +[2023-07-16 22:38:35,595][254040] Decorrelating experience for 256 frames... +[2023-07-16 22:38:35,596][254035] Decorrelating experience for 256 frames... +[2023-07-16 22:38:35,646][254037] Decorrelating experience for 384 frames... +[2023-07-16 22:38:35,676][254036] Decorrelating experience for 384 frames... +[2023-07-16 22:38:35,678][254034] Decorrelating experience for 384 frames... +[2023-07-16 22:38:35,696][254040] Decorrelating experience for 320 frames... +[2023-07-16 22:38:35,702][254039] Decorrelating experience for 256 frames... +[2023-07-16 22:38:35,702][254035] Decorrelating experience for 320 frames... +[2023-07-16 22:38:35,720][254134] Decorrelating experience for 384 frames... +[2023-07-16 22:38:35,724][254038] Decorrelating experience for 384 frames... +[2023-07-16 22:38:35,792][254037] Decorrelating experience for 448 frames... +[2023-07-16 22:38:35,803][254039] Decorrelating experience for 320 frames... +[2023-07-16 22:38:35,829][254034] Decorrelating experience for 448 frames... +[2023-07-16 22:38:35,829][254036] Decorrelating experience for 448 frames... +[2023-07-16 22:38:35,830][254040] Decorrelating experience for 384 frames... +[2023-07-16 22:38:35,836][254035] Decorrelating experience for 384 frames... +[2023-07-16 22:38:35,872][254038] Decorrelating experience for 448 frames... +[2023-07-16 22:38:35,872][254134] Decorrelating experience for 448 frames... +[2023-07-16 22:38:35,931][254039] Decorrelating experience for 384 frames... +[2023-07-16 22:38:35,984][254040] Decorrelating experience for 448 frames... +[2023-07-16 22:38:35,989][254035] Decorrelating experience for 448 frames... +[2023-07-16 22:38:36,087][254039] Decorrelating experience for 448 frames... +[2023-07-16 22:38:37,971][253751] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3276.8). Total num frames: 16384. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:38:37,972][253751] Avg episode reward: [(0, '90.381')] +[2023-07-16 22:38:39,905][254033] Updated weights for policy 0, policy_version 80 (0.0005) +[2023-07-16 22:38:42,971][253751] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 7782.4). Total num frames: 77824. Throughput: 0: 6108.8. Samples: 61088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:38:42,971][253751] Avg episode reward: [(0, '207.043')] +[2023-07-16 22:38:42,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000152_77824.pth... +[2023-07-16 22:38:43,174][254033] Updated weights for policy 0, policy_version 160 (0.0004) +[2023-07-16 22:38:46,534][254033] Updated weights for policy 0, policy_version 240 (0.0004) +[2023-07-16 22:38:47,971][253751] Fps is (10 sec: 12288.0, 60 sec: 9284.3, 300 sec: 9284.3). Total num frames: 139264. Throughput: 0: 9010.4. Samples: 135156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:38:47,971][253751] Avg episode reward: [(0, '261.017')] +[2023-07-16 22:38:47,972][253989] Saving new best policy, reward=261.017! +[2023-07-16 22:38:50,000][253751] Heartbeat connected on Batcher_0 +[2023-07-16 22:38:50,007][253751] Heartbeat connected on RolloutWorker_w0 +[2023-07-16 22:38:50,009][253751] Heartbeat connected on RolloutWorker_w1 +[2023-07-16 22:38:50,010][253751] Heartbeat connected on RolloutWorker_w2 +[2023-07-16 22:38:50,012][253751] Heartbeat connected on RolloutWorker_w3 +[2023-07-16 22:38:50,014][253751] Heartbeat connected on RolloutWorker_w4 +[2023-07-16 22:38:50,016][253751] Heartbeat connected on RolloutWorker_w5 +[2023-07-16 22:38:50,017][253751] Heartbeat connected on LearnerWorker_p0 +[2023-07-16 22:38:50,018][253751] Heartbeat connected on RolloutWorker_w6 +[2023-07-16 22:38:50,018][254033] Updated weights for policy 0, policy_version 320 (0.0005) +[2023-07-16 22:38:50,019][253751] Heartbeat connected on InferenceWorker_p0-w0 +[2023-07-16 22:38:50,024][253751] Heartbeat connected on RolloutWorker_w7 +[2023-07-16 22:38:52,971][253751] Fps is (10 sec: 11878.5, 60 sec: 9830.4, 300 sec: 9830.4). Total num frames: 196608. Throughput: 0: 8470.6. Samples: 169412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:38:52,971][253751] Avg episode reward: [(0, '312.447')] +[2023-07-16 22:38:52,972][253989] Saving new best policy, reward=312.447! +[2023-07-16 22:38:53,491][254033] Updated weights for policy 0, policy_version 400 (0.0005) +[2023-07-16 22:38:56,995][254033] Updated weights for policy 0, policy_version 480 (0.0004) +[2023-07-16 22:38:57,971][253751] Fps is (10 sec: 11468.7, 60 sec: 10158.1, 300 sec: 10158.1). Total num frames: 253952. Throughput: 0: 9589.1. Samples: 239728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:38:57,972][253751] Avg episode reward: [(0, '364.364')] +[2023-07-16 22:38:57,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000496_253952.pth... +[2023-07-16 22:38:57,977][253989] Saving new best policy, reward=364.364! +[2023-07-16 22:39:00,553][254033] Updated weights for policy 0, policy_version 560 (0.0004) +[2023-07-16 22:39:02,971][253751] Fps is (10 sec: 11468.8, 60 sec: 10376.6, 300 sec: 10376.6). Total num frames: 311296. Throughput: 0: 10283.6. Samples: 308508. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-16 22:39:02,972][253751] Avg episode reward: [(0, '478.527')] +[2023-07-16 22:39:02,973][253989] Saving new best policy, reward=478.527! +[2023-07-16 22:39:04,283][254033] Updated weights for policy 0, policy_version 640 (0.0005) +[2023-07-16 22:39:07,971][253751] Fps is (10 sec: 11059.3, 60 sec: 10415.6, 300 sec: 10415.6). Total num frames: 364544. Throughput: 0: 9754.0. Samples: 341388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:39:07,975][253751] Avg episode reward: [(0, '531.365')] +[2023-07-16 22:39:07,976][253989] Saving new best policy, reward=531.365! +[2023-07-16 22:39:08,104][254033] Updated weights for policy 0, policy_version 720 (0.0006) +[2023-07-16 22:39:11,750][254033] Updated weights for policy 0, policy_version 800 (0.0006) +[2023-07-16 22:39:12,971][253751] Fps is (10 sec: 11059.2, 60 sec: 10547.2, 300 sec: 10547.2). Total num frames: 421888. Throughput: 0: 10171.9. Samples: 406876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:39:12,972][253751] Avg episode reward: [(0, '597.024')] +[2023-07-16 22:39:12,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000824_421888.pth... +[2023-07-16 22:39:12,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000152_77824.pth +[2023-07-16 22:39:12,978][253989] Saving new best policy, reward=597.024! +[2023-07-16 22:39:15,155][254033] Updated weights for policy 0, policy_version 880 (0.0005) +[2023-07-16 22:39:17,971][253751] Fps is (10 sec: 11878.3, 60 sec: 10740.6, 300 sec: 10740.6). Total num frames: 483328. Throughput: 0: 10703.0. Samples: 481636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:39:17,972][253751] Avg episode reward: [(0, '563.232')] +[2023-07-16 22:39:18,298][254033] Updated weights for policy 0, policy_version 960 (0.0004) +[2023-07-16 22:39:21,280][254033] Updated weights for policy 0, policy_version 1040 (0.0004) +[2023-07-16 22:39:22,971][253751] Fps is (10 sec: 13107.2, 60 sec: 11059.2, 300 sec: 11059.2). Total num frames: 552960. Throughput: 0: 11608.4. Samples: 522380. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-16 22:39:22,972][253751] Avg episode reward: [(0, '723.085')] +[2023-07-16 22:39:22,972][253989] Saving new best policy, reward=723.085! +[2023-07-16 22:39:24,257][254033] Updated weights for policy 0, policy_version 1120 (0.0004) +[2023-07-16 22:39:27,479][254033] Updated weights for policy 0, policy_version 1200 (0.0005) +[2023-07-16 22:39:27,971][253751] Fps is (10 sec: 13516.8, 60 sec: 11245.4, 300 sec: 11245.4). Total num frames: 618496. Throughput: 0: 12022.9. Samples: 602120. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:39:27,972][253751] Avg episode reward: [(0, '721.450')] +[2023-07-16 22:39:27,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001208_618496.pth... +[2023-07-16 22:39:27,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000496_253952.pth +[2023-07-16 22:39:30,476][254033] Updated weights for policy 0, policy_version 1280 (0.0005) +[2023-07-16 22:39:32,971][253751] Fps is (10 sec: 13516.8, 60 sec: 11468.8, 300 sec: 11468.8). Total num frames: 688128. Throughput: 0: 12198.7. Samples: 684096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:39:32,971][253751] Avg episode reward: [(0, '743.557')] +[2023-07-16 22:39:32,972][253989] Saving new best policy, reward=743.557! +[2023-07-16 22:39:33,402][254033] Updated weights for policy 0, policy_version 1360 (0.0004) +[2023-07-16 22:39:36,616][254033] Updated weights for policy 0, policy_version 1440 (0.0005) +[2023-07-16 22:39:37,971][253751] Fps is (10 sec: 13516.8, 60 sec: 12288.0, 300 sec: 11594.8). Total num frames: 753664. Throughput: 0: 12325.9. Samples: 724080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:39:37,971][253751] Avg episode reward: [(0, '728.302')] +[2023-07-16 22:39:39,895][254033] Updated weights for policy 0, policy_version 1520 (0.0005) +[2023-07-16 22:39:42,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 11644.3). Total num frames: 815104. Throughput: 0: 12423.7. Samples: 798792. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-16 22:39:42,971][253751] Avg episode reward: [(0, '763.395')] +[2023-07-16 22:39:42,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001592_815104.pth... +[2023-07-16 22:39:42,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000000824_421888.pth +[2023-07-16 22:39:42,978][253989] Saving new best policy, reward=763.395! +[2023-07-16 22:39:43,073][254033] Updated weights for policy 0, policy_version 1600 (0.0005) +[2023-07-16 22:39:46,287][254033] Updated weights for policy 0, policy_version 1680 (0.0005) +[2023-07-16 22:39:47,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 11741.9). Total num frames: 880640. Throughput: 0: 12612.5. Samples: 876072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:39:47,971][253751] Avg episode reward: [(0, '764.118')] +[2023-07-16 22:39:47,972][253989] Saving new best policy, reward=764.118! +[2023-07-16 22:39:49,502][254033] Updated weights for policy 0, policy_version 1760 (0.0005) +[2023-07-16 22:39:52,710][254033] Updated weights for policy 0, policy_version 1840 (0.0005) +[2023-07-16 22:39:52,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12424.5, 300 sec: 11776.0). Total num frames: 942080. Throughput: 0: 12723.6. Samples: 913948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:39:52,971][253751] Avg episode reward: [(0, '771.159')] +[2023-07-16 22:39:53,022][253989] Saving new best policy, reward=771.159! +[2023-07-16 22:39:55,903][254033] Updated weights for policy 0, policy_version 1920 (0.0005) +[2023-07-16 22:39:57,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 11854.3). Total num frames: 1007616. Throughput: 0: 12985.7. Samples: 991232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:39:57,971][253751] Avg episode reward: [(0, '769.573')] +[2023-07-16 22:39:57,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001968_1007616.pth... +[2023-07-16 22:39:57,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001208_618496.pth +[2023-07-16 22:39:59,208][254033] Updated weights for policy 0, policy_version 2000 (0.0005) +[2023-07-16 22:40:02,398][254033] Updated weights for policy 0, policy_version 2080 (0.0005) +[2023-07-16 22:40:02,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12629.3, 300 sec: 11878.4). Total num frames: 1069056. Throughput: 0: 12992.9. Samples: 1066316. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-16 22:40:02,971][253751] Avg episode reward: [(0, '767.131')] +[2023-07-16 22:40:05,655][254033] Updated weights for policy 0, policy_version 2160 (0.0005) +[2023-07-16 22:40:07,971][253751] Fps is (10 sec: 12697.7, 60 sec: 12834.1, 300 sec: 11943.1). Total num frames: 1134592. Throughput: 0: 12937.8. Samples: 1104580. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-16 22:40:07,971][253751] Avg episode reward: [(0, '775.030')] +[2023-07-16 22:40:07,972][253989] Saving new best policy, reward=775.030! +[2023-07-16 22:40:08,896][254033] Updated weights for policy 0, policy_version 2240 (0.0005) +[2023-07-16 22:40:12,190][254033] Updated weights for policy 0, policy_version 2320 (0.0005) +[2023-07-16 22:40:12,971][253751] Fps is (10 sec: 12697.5, 60 sec: 12902.4, 300 sec: 11960.3). Total num frames: 1196032. Throughput: 0: 12834.0. Samples: 1179648. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-16 22:40:12,972][253751] Avg episode reward: [(0, '776.812')] +[2023-07-16 22:40:12,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000002336_1196032.pth... +[2023-07-16 22:40:12,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001592_815104.pth +[2023-07-16 22:40:12,978][253989] Saving new best policy, reward=776.812! +[2023-07-16 22:40:15,335][254033] Updated weights for policy 0, policy_version 2400 (0.0005) +[2023-07-16 22:40:17,971][253751] Fps is (10 sec: 12697.5, 60 sec: 12970.7, 300 sec: 12014.9). Total num frames: 1261568. Throughput: 0: 12737.1. Samples: 1257268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:40:17,971][253751] Avg episode reward: [(0, '775.141')] +[2023-07-16 22:40:18,551][254033] Updated weights for policy 0, policy_version 2480 (0.0004) +[2023-07-16 22:40:21,842][254033] Updated weights for policy 0, policy_version 2560 (0.0005) +[2023-07-16 22:40:22,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12834.1, 300 sec: 12027.3). Total num frames: 1323008. Throughput: 0: 12673.8. Samples: 1294400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:40:22,972][253751] Avg episode reward: [(0, '768.579')] +[2023-07-16 22:40:25,119][254033] Updated weights for policy 0, policy_version 2640 (0.0005) +[2023-07-16 22:40:27,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12765.9, 300 sec: 12038.7). Total num frames: 1384448. Throughput: 0: 12671.1. Samples: 1368992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:40:27,972][253751] Avg episode reward: [(0, '762.805')] +[2023-07-16 22:40:27,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000002704_1384448.pth... +[2023-07-16 22:40:27,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000001968_1007616.pth +[2023-07-16 22:40:28,363][254033] Updated weights for policy 0, policy_version 2720 (0.0005) +[2023-07-16 22:40:31,416][254033] Updated weights for policy 0, policy_version 2800 (0.0005) +[2023-07-16 22:40:32,971][253751] Fps is (10 sec: 13107.3, 60 sec: 12765.9, 300 sec: 12117.3). Total num frames: 1454080. Throughput: 0: 12737.5. Samples: 1449260. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-16 22:40:32,971][253751] Avg episode reward: [(0, '757.673')] +[2023-07-16 22:40:34,551][254033] Updated weights for policy 0, policy_version 2880 (0.0004) +[2023-07-16 22:40:37,735][254033] Updated weights for policy 0, policy_version 2960 (0.0005) +[2023-07-16 22:40:37,971][253751] Fps is (10 sec: 13107.3, 60 sec: 12697.6, 300 sec: 12124.2). Total num frames: 1515520. Throughput: 0: 12731.4. Samples: 1486860. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-16 22:40:37,971][253751] Avg episode reward: [(0, '782.088')] +[2023-07-16 22:40:37,972][253989] Saving new best policy, reward=782.088! +[2023-07-16 22:40:40,883][254033] Updated weights for policy 0, policy_version 3040 (0.0005) +[2023-07-16 22:40:42,971][253751] Fps is (10 sec: 12697.5, 60 sec: 12765.9, 300 sec: 12162.0). Total num frames: 1581056. Throughput: 0: 12743.3. Samples: 1564680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:40:42,971][253751] Avg episode reward: [(0, '779.504')] +[2023-07-16 22:40:42,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003088_1581056.pth... +[2023-07-16 22:40:42,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000002336_1196032.pth +[2023-07-16 22:40:44,186][254033] Updated weights for policy 0, policy_version 3120 (0.0005) +[2023-07-16 22:40:47,351][254033] Updated weights for policy 0, policy_version 3200 (0.0005) +[2023-07-16 22:40:47,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12166.6). Total num frames: 1642496. Throughput: 0: 12763.7. Samples: 1640684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:40:47,972][253751] Avg episode reward: [(0, '781.677')] +[2023-07-16 22:40:50,655][254033] Updated weights for policy 0, policy_version 3280 (0.0005) +[2023-07-16 22:40:52,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12200.2). Total num frames: 1708032. Throughput: 0: 12735.1. Samples: 1677660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:40:52,992][253751] Avg episode reward: [(0, '781.893')] +[2023-07-16 22:40:53,893][254033] Updated weights for policy 0, policy_version 3360 (0.0005) +[2023-07-16 22:40:57,160][254033] Updated weights for policy 0, policy_version 3440 (0.0005) +[2023-07-16 22:40:57,971][253751] Fps is (10 sec: 12697.5, 60 sec: 12697.6, 300 sec: 12203.3). Total num frames: 1769472. Throughput: 0: 12744.5. Samples: 1753152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:40:57,972][253751] Avg episode reward: [(0, '787.350')] +[2023-07-16 22:40:57,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003456_1769472.pth... +[2023-07-16 22:40:57,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000002704_1384448.pth +[2023-07-16 22:40:57,978][253989] Saving new best policy, reward=787.350! +[2023-07-16 22:41:00,375][254033] Updated weights for policy 0, policy_version 3520 (0.0005) +[2023-07-16 22:41:02,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12697.6, 300 sec: 12206.1). Total num frames: 1830912. Throughput: 0: 12721.3. Samples: 1829724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:41:02,972][253751] Avg episode reward: [(0, '779.903')] +[2023-07-16 22:41:03,625][254033] Updated weights for policy 0, policy_version 3600 (0.0005) +[2023-07-16 22:41:06,883][254033] Updated weights for policy 0, policy_version 3680 (0.0005) +[2023-07-16 22:41:07,971][253751] Fps is (10 sec: 12697.7, 60 sec: 12697.6, 300 sec: 12235.2). Total num frames: 1896448. Throughput: 0: 12727.1. Samples: 1867120. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-16 22:41:07,972][253751] Avg episode reward: [(0, '787.765')] +[2023-07-16 22:41:07,972][253989] Saving new best policy, reward=787.765! +[2023-07-16 22:41:10,070][254033] Updated weights for policy 0, policy_version 3760 (0.0005) +[2023-07-16 22:41:12,971][253751] Fps is (10 sec: 12697.5, 60 sec: 12697.6, 300 sec: 12236.8). Total num frames: 1957888. Throughput: 0: 12761.0. Samples: 1943236. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-16 22:41:12,971][253751] Avg episode reward: [(0, '788.820')] +[2023-07-16 22:41:13,012][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003832_1961984.pth... +[2023-07-16 22:41:13,014][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003088_1581056.pth +[2023-07-16 22:41:13,015][253989] Saving new best policy, reward=788.820! +[2023-07-16 22:41:13,359][254033] Updated weights for policy 0, policy_version 3840 (0.0006) +[2023-07-16 22:41:16,705][254033] Updated weights for policy 0, policy_version 3920 (0.0005) +[2023-07-16 22:41:17,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12238.4). Total num frames: 2019328. Throughput: 0: 12613.2. Samples: 2016856. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:41:17,971][253751] Avg episode reward: [(0, '789.835')] +[2023-07-16 22:41:17,972][253989] Saving new best policy, reward=789.835! +[2023-07-16 22:41:19,910][254033] Updated weights for policy 0, policy_version 4000 (0.0005) +[2023-07-16 22:41:22,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12263.9). Total num frames: 2084864. Throughput: 0: 12652.2. Samples: 2056208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:41:22,971][253751] Avg episode reward: [(0, '793.813')] +[2023-07-16 22:41:22,972][253989] Saving new best policy, reward=793.813! +[2023-07-16 22:41:23,139][254033] Updated weights for policy 0, policy_version 4080 (0.0005) +[2023-07-16 22:41:26,433][254033] Updated weights for policy 0, policy_version 4160 (0.0005) +[2023-07-16 22:41:27,971][253751] Fps is (10 sec: 12697.5, 60 sec: 12697.6, 300 sec: 12264.6). Total num frames: 2146304. Throughput: 0: 12581.5. Samples: 2130848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:41:27,971][253751] Avg episode reward: [(0, '784.885')] +[2023-07-16 22:41:27,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004192_2146304.pth... +[2023-07-16 22:41:27,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003456_1769472.pth +[2023-07-16 22:41:29,737][254033] Updated weights for policy 0, policy_version 4240 (0.0004) +[2023-07-16 22:41:32,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12265.2). Total num frames: 2207744. Throughput: 0: 12549.0. Samples: 2205388. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-16 22:41:32,971][253751] Avg episode reward: [(0, '788.845')] +[2023-07-16 22:41:33,066][254033] Updated weights for policy 0, policy_version 4320 (0.0005) +[2023-07-16 22:41:36,074][254033] Updated weights for policy 0, policy_version 4400 (0.0004) +[2023-07-16 22:41:37,971][253751] Fps is (10 sec: 13107.2, 60 sec: 12697.6, 300 sec: 12310.1). Total num frames: 2277376. Throughput: 0: 12600.4. Samples: 2244680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:41:37,972][253751] Avg episode reward: [(0, '790.059')] +[2023-07-16 22:41:39,112][254033] Updated weights for policy 0, policy_version 4480 (0.0003) +[2023-07-16 22:41:42,148][254033] Updated weights for policy 0, policy_version 4560 (0.0003) +[2023-07-16 22:41:42,971][253751] Fps is (10 sec: 13516.7, 60 sec: 12697.6, 300 sec: 12331.1). Total num frames: 2342912. Throughput: 0: 12737.3. Samples: 2326332. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-16 22:41:42,971][253751] Avg episode reward: [(0, '788.773')] +[2023-07-16 22:41:42,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004576_2342912.pth... +[2023-07-16 22:41:42,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000003832_1961984.pth +[2023-07-16 22:41:45,182][254033] Updated weights for policy 0, policy_version 4640 (0.0004) +[2023-07-16 22:41:47,971][253751] Fps is (10 sec: 13107.2, 60 sec: 12765.9, 300 sec: 12351.0). Total num frames: 2408448. Throughput: 0: 12816.1. Samples: 2406448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:41:47,971][253751] Avg episode reward: [(0, '792.746')] +[2023-07-16 22:41:48,340][254033] Updated weights for policy 0, policy_version 4720 (0.0004) +[2023-07-16 22:41:51,757][254033] Updated weights for policy 0, policy_version 4800 (0.0005) +[2023-07-16 22:41:52,971][253751] Fps is (10 sec: 12697.7, 60 sec: 12697.6, 300 sec: 12349.4). Total num frames: 2469888. Throughput: 0: 12787.9. Samples: 2442576. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:41:52,971][253751] Avg episode reward: [(0, '780.836')] +[2023-07-16 22:41:55,156][254033] Updated weights for policy 0, policy_version 4880 (0.0005) +[2023-07-16 22:41:57,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12697.6, 300 sec: 12347.9). Total num frames: 2531328. Throughput: 0: 12717.2. Samples: 2515508. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-16 22:41:57,971][253751] Avg episode reward: [(0, '792.809')] +[2023-07-16 22:41:57,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004944_2531328.pth... +[2023-07-16 22:41:57,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004192_2146304.pth +[2023-07-16 22:41:58,353][254033] Updated weights for policy 0, policy_version 4960 (0.0005) +[2023-07-16 22:42:01,493][254033] Updated weights for policy 0, policy_version 5040 (0.0005) +[2023-07-16 22:42:02,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12366.0). Total num frames: 2596864. Throughput: 0: 12811.0. Samples: 2593352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:42:02,972][253751] Avg episode reward: [(0, '783.807')] +[2023-07-16 22:42:04,729][254033] Updated weights for policy 0, policy_version 5120 (0.0004) +[2023-07-16 22:42:07,971][253751] Fps is (10 sec: 12697.7, 60 sec: 12697.6, 300 sec: 12364.2). Total num frames: 2658304. Throughput: 0: 12769.4. Samples: 2630832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:42:07,972][253751] Avg episode reward: [(0, '792.401')] +[2023-07-16 22:42:08,052][254033] Updated weights for policy 0, policy_version 5200 (0.0005) +[2023-07-16 22:42:11,262][254033] Updated weights for policy 0, policy_version 5280 (0.0005) +[2023-07-16 22:42:12,971][253751] Fps is (10 sec: 12697.5, 60 sec: 12765.9, 300 sec: 12381.1). Total num frames: 2723840. Throughput: 0: 12803.2. Samples: 2706992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:42:12,972][253751] Avg episode reward: [(0, '788.362')] +[2023-07-16 22:42:12,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000005320_2723840.pth... +[2023-07-16 22:42:12,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004576_2342912.pth +[2023-07-16 22:42:14,556][254033] Updated weights for policy 0, policy_version 5360 (0.0005) +[2023-07-16 22:42:17,773][254033] Updated weights for policy 0, policy_version 5440 (0.0005) +[2023-07-16 22:42:17,971][253751] Fps is (10 sec: 12697.5, 60 sec: 12765.9, 300 sec: 12379.0). Total num frames: 2785280. Throughput: 0: 12806.3. Samples: 2781672. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-16 22:42:17,972][253751] Avg episode reward: [(0, '786.188')] +[2023-07-16 22:42:21,152][254033] Updated weights for policy 0, policy_version 5520 (0.0005) +[2023-07-16 22:42:22,971][253751] Fps is (10 sec: 12288.1, 60 sec: 12697.6, 300 sec: 12377.0). Total num frames: 2846720. Throughput: 0: 12742.9. Samples: 2818112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:42:22,972][253751] Avg episode reward: [(0, '792.120')] +[2023-07-16 22:42:24,353][254033] Updated weights for policy 0, policy_version 5600 (0.0005) +[2023-07-16 22:42:27,592][254033] Updated weights for policy 0, policy_version 5680 (0.0005) +[2023-07-16 22:42:27,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12392.6). Total num frames: 2912256. Throughput: 0: 12620.2. Samples: 2894240. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-16 22:42:27,972][253751] Avg episode reward: [(0, '795.263')] +[2023-07-16 22:42:27,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000005688_2912256.pth... +[2023-07-16 22:42:27,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000004944_2531328.pth +[2023-07-16 22:42:27,978][253989] Saving new best policy, reward=795.263! +[2023-07-16 22:42:30,792][254033] Updated weights for policy 0, policy_version 5760 (0.0005) +[2023-07-16 22:42:32,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12390.4). Total num frames: 2973696. Throughput: 0: 12519.6. Samples: 2969828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:42:32,972][253751] Avg episode reward: [(0, '795.137')] +[2023-07-16 22:42:34,127][254033] Updated weights for policy 0, policy_version 5840 (0.0005) +[2023-07-16 22:42:37,365][254033] Updated weights for policy 0, policy_version 5920 (0.0005) +[2023-07-16 22:42:37,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12388.3). Total num frames: 3035136. Throughput: 0: 12539.6. Samples: 3006860. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:42:37,971][253751] Avg episode reward: [(0, '788.843')] +[2023-07-16 22:42:40,627][254033] Updated weights for policy 0, policy_version 6000 (0.0005) +[2023-07-16 22:42:42,971][253751] Fps is (10 sec: 12697.5, 60 sec: 12629.3, 300 sec: 12402.7). Total num frames: 3100672. Throughput: 0: 12626.7. Samples: 3083712. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-16 22:42:42,972][253751] Avg episode reward: [(0, '793.238')] +[2023-07-16 22:42:42,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006056_3100672.pth... +[2023-07-16 22:42:42,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000005320_2723840.pth +[2023-07-16 22:42:43,861][254033] Updated weights for policy 0, policy_version 6080 (0.0005) +[2023-07-16 22:42:47,271][254033] Updated weights for policy 0, policy_version 6160 (0.0005) +[2023-07-16 22:42:47,971][253751] Fps is (10 sec: 12697.7, 60 sec: 12561.1, 300 sec: 12400.4). Total num frames: 3162112. Throughput: 0: 12535.7. Samples: 3157456. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-16 22:42:47,971][253751] Avg episode reward: [(0, '794.585')] +[2023-07-16 22:42:50,613][254033] Updated weights for policy 0, policy_version 6240 (0.0005) +[2023-07-16 22:42:52,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12382.5). Total num frames: 3219456. Throughput: 0: 12512.9. Samples: 3193912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:42:52,971][253751] Avg episode reward: [(0, '791.320')] +[2023-07-16 22:42:53,987][254033] Updated weights for policy 0, policy_version 6320 (0.0006) +[2023-07-16 22:42:57,152][254033] Updated weights for policy 0, policy_version 6400 (0.0005) +[2023-07-16 22:42:57,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12561.1, 300 sec: 12396.2). Total num frames: 3284992. Throughput: 0: 12476.7. Samples: 3268444. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:42:57,971][253751] Avg episode reward: [(0, '794.811')] +[2023-07-16 22:42:57,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006416_3284992.pth... +[2023-07-16 22:42:57,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000005688_2912256.pth +[2023-07-16 22:43:00,230][254033] Updated weights for policy 0, policy_version 6480 (0.0004) +[2023-07-16 22:43:02,971][253751] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12409.4). Total num frames: 3350528. Throughput: 0: 12579.1. Samples: 3347732. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-16 22:43:02,971][253751] Avg episode reward: [(0, '794.281')] +[2023-07-16 22:43:03,321][254033] Updated weights for policy 0, policy_version 6560 (0.0004) +[2023-07-16 22:43:06,344][254033] Updated weights for policy 0, policy_version 6640 (0.0004) +[2023-07-16 22:43:07,971][253751] Fps is (10 sec: 13516.8, 60 sec: 12697.6, 300 sec: 12436.9). Total num frames: 3420160. Throughput: 0: 12667.1. Samples: 3388132. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:43:07,972][253751] Avg episode reward: [(0, '795.459')] +[2023-07-16 22:43:07,972][253989] Saving new best policy, reward=795.459! +[2023-07-16 22:43:09,415][254033] Updated weights for policy 0, policy_version 6720 (0.0004) +[2023-07-16 22:43:12,381][254033] Updated weights for policy 0, policy_version 6800 (0.0004) +[2023-07-16 22:43:12,971][253751] Fps is (10 sec: 13516.8, 60 sec: 12697.6, 300 sec: 12448.9). Total num frames: 3485696. Throughput: 0: 12781.0. Samples: 3469384. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-16 22:43:12,971][253751] Avg episode reward: [(0, '795.547')] +[2023-07-16 22:43:12,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006808_3485696.pth... +[2023-07-16 22:43:12,976][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006056_3100672.pth +[2023-07-16 22:43:12,976][253989] Saving new best policy, reward=795.547! +[2023-07-16 22:43:15,531][254033] Updated weights for policy 0, policy_version 6880 (0.0005) +[2023-07-16 22:43:17,971][253751] Fps is (10 sec: 13107.3, 60 sec: 12765.9, 300 sec: 12460.5). Total num frames: 3551232. Throughput: 0: 12863.4. Samples: 3548680. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-16 22:43:17,971][253751] Avg episode reward: [(0, '798.018')] +[2023-07-16 22:43:17,972][253989] Saving new best policy, reward=798.018! +[2023-07-16 22:43:18,676][254033] Updated weights for policy 0, policy_version 6960 (0.0005) +[2023-07-16 22:43:21,786][254033] Updated weights for policy 0, policy_version 7040 (0.0004) +[2023-07-16 22:43:22,971][253751] Fps is (10 sec: 13107.4, 60 sec: 12834.1, 300 sec: 12471.6). Total num frames: 3616768. Throughput: 0: 12917.8. Samples: 3588160. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-16 22:43:22,971][253751] Avg episode reward: [(0, '786.229')] +[2023-07-16 22:43:24,852][254033] Updated weights for policy 0, policy_version 7120 (0.0004) +[2023-07-16 22:43:27,886][254033] Updated weights for policy 0, policy_version 7200 (0.0004) +[2023-07-16 22:43:27,971][253751] Fps is (10 sec: 13516.7, 60 sec: 12902.4, 300 sec: 12496.3). Total num frames: 3686400. Throughput: 0: 12978.3. Samples: 3667736. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-16 22:43:27,971][253751] Avg episode reward: [(0, '787.926')] +[2023-07-16 22:43:27,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007200_3686400.pth... +[2023-07-16 22:43:27,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006416_3284992.pth +[2023-07-16 22:43:31,010][254033] Updated weights for policy 0, policy_version 7280 (0.0005) +[2023-07-16 22:43:32,971][253751] Fps is (10 sec: 13107.1, 60 sec: 12902.4, 300 sec: 12649.0). Total num frames: 3747840. Throughput: 0: 13055.0. Samples: 3744932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:43:32,971][253751] Avg episode reward: [(0, '792.055')] +[2023-07-16 22:43:34,428][254033] Updated weights for policy 0, policy_version 7360 (0.0005) +[2023-07-16 22:43:37,726][254033] Updated weights for policy 0, policy_version 7440 (0.0005) +[2023-07-16 22:43:37,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12902.4, 300 sec: 12649.0). Total num frames: 3809280. Throughput: 0: 13061.7. Samples: 3781688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:43:37,972][253751] Avg episode reward: [(0, '791.125')] +[2023-07-16 22:43:41,147][254033] Updated weights for policy 0, policy_version 7520 (0.0005) +[2023-07-16 22:43:42,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12834.1, 300 sec: 12649.0). Total num frames: 3870720. Throughput: 0: 13021.2. Samples: 3854400. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-16 22:43:42,971][253751] Avg episode reward: [(0, '791.142')] +[2023-07-16 22:43:42,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007560_3870720.pth... +[2023-07-16 22:43:42,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000006808_3485696.pth +[2023-07-16 22:43:44,519][254033] Updated weights for policy 0, policy_version 7600 (0.0005) +[2023-07-16 22:43:47,829][254033] Updated weights for policy 0, policy_version 7680 (0.0005) +[2023-07-16 22:43:47,971][253751] Fps is (10 sec: 12288.1, 60 sec: 12834.1, 300 sec: 12662.9). Total num frames: 3932160. Throughput: 0: 12897.7. Samples: 3928128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:43:47,971][253751] Avg episode reward: [(0, '800.456')] +[2023-07-16 22:43:47,972][253989] Saving new best policy, reward=800.456! +[2023-07-16 22:43:51,138][254033] Updated weights for policy 0, policy_version 7760 (0.0005) +[2023-07-16 22:43:52,971][253751] Fps is (10 sec: 12288.1, 60 sec: 12902.4, 300 sec: 12676.8). Total num frames: 3993600. Throughput: 0: 12819.3. Samples: 3965000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:43:52,971][253751] Avg episode reward: [(0, '792.261')] +[2023-07-16 22:43:54,546][254033] Updated weights for policy 0, policy_version 7840 (0.0005) +[2023-07-16 22:43:57,898][254033] Updated weights for policy 0, policy_version 7920 (0.0005) +[2023-07-16 22:43:57,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12834.1, 300 sec: 12690.7). Total num frames: 4055040. Throughput: 0: 12650.5. Samples: 4038656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:43:57,971][253751] Avg episode reward: [(0, '795.238')] +[2023-07-16 22:43:57,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007920_4055040.pth... +[2023-07-16 22:43:57,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007200_3686400.pth +[2023-07-16 22:44:01,220][254033] Updated weights for policy 0, policy_version 8000 (0.0005) +[2023-07-16 22:44:02,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12765.9, 300 sec: 12718.4). Total num frames: 4116480. Throughput: 0: 12506.7. Samples: 4111480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:44:02,971][253751] Avg episode reward: [(0, '796.123')] +[2023-07-16 22:44:04,632][254033] Updated weights for policy 0, policy_version 8080 (0.0005) +[2023-07-16 22:44:07,971][253751] Fps is (10 sec: 11878.5, 60 sec: 12561.1, 300 sec: 12718.4). Total num frames: 4173824. Throughput: 0: 12442.7. Samples: 4148084. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-16 22:44:07,971][253751] Avg episode reward: [(0, '795.645')] +[2023-07-16 22:44:08,086][254033] Updated weights for policy 0, policy_version 8160 (0.0005) +[2023-07-16 22:44:11,476][254033] Updated weights for policy 0, policy_version 8240 (0.0005) +[2023-07-16 22:44:12,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12718.4). Total num frames: 4235264. Throughput: 0: 12250.7. Samples: 4219016. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-16 22:44:12,971][253751] Avg episode reward: [(0, '794.309')] +[2023-07-16 22:44:12,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000008272_4235264.pth... +[2023-07-16 22:44:12,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007560_3870720.pth +[2023-07-16 22:44:14,954][254033] Updated weights for policy 0, policy_version 8320 (0.0005) +[2023-07-16 22:44:17,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12690.7). Total num frames: 4296704. Throughput: 0: 12155.4. Samples: 4291924. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-16 22:44:17,972][253751] Avg episode reward: [(0, '793.270')] +[2023-07-16 22:44:18,238][254033] Updated weights for policy 0, policy_version 8400 (0.0005) +[2023-07-16 22:44:21,266][254033] Updated weights for policy 0, policy_version 8480 (0.0004) +[2023-07-16 22:44:22,971][253751] Fps is (10 sec: 12697.7, 60 sec: 12424.5, 300 sec: 12690.7). Total num frames: 4362240. Throughput: 0: 12217.9. Samples: 4331492. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:44:22,972][253751] Avg episode reward: [(0, '789.400')] +[2023-07-16 22:44:24,322][254033] Updated weights for policy 0, policy_version 8560 (0.0004) +[2023-07-16 22:44:27,393][254033] Updated weights for policy 0, policy_version 8640 (0.0004) +[2023-07-16 22:44:27,971][253751] Fps is (10 sec: 13107.2, 60 sec: 12356.3, 300 sec: 12676.8). Total num frames: 4427776. Throughput: 0: 12384.8. Samples: 4411716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:44:27,972][253751] Avg episode reward: [(0, '793.074')] +[2023-07-16 22:44:27,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000008648_4427776.pth... +[2023-07-16 22:44:27,976][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000007920_4055040.pth +[2023-07-16 22:44:30,514][254033] Updated weights for policy 0, policy_version 8720 (0.0004) +[2023-07-16 22:44:32,971][253751] Fps is (10 sec: 13516.8, 60 sec: 12492.8, 300 sec: 12690.7). Total num frames: 4497408. Throughput: 0: 12526.3. Samples: 4491812. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-16 22:44:32,984][253751] Avg episode reward: [(0, '791.038')] +[2023-07-16 22:44:33,554][254033] Updated weights for policy 0, policy_version 8800 (0.0004) +[2023-07-16 22:44:36,548][254033] Updated weights for policy 0, policy_version 8880 (0.0003) +[2023-07-16 22:44:37,971][253751] Fps is (10 sec: 13516.8, 60 sec: 12561.1, 300 sec: 12704.5). Total num frames: 4562944. Throughput: 0: 12600.5. Samples: 4532024. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-16 22:44:37,979][253751] Avg episode reward: [(0, '793.746')] +[2023-07-16 22:44:39,644][254033] Updated weights for policy 0, policy_version 8960 (0.0004) +[2023-07-16 22:44:42,746][254033] Updated weights for policy 0, policy_version 9040 (0.0004) +[2023-07-16 22:44:42,971][253751] Fps is (10 sec: 13107.1, 60 sec: 12629.3, 300 sec: 12704.5). Total num frames: 4628480. Throughput: 0: 12752.5. Samples: 4612516. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:44:42,972][253751] Avg episode reward: [(0, '798.915')] +[2023-07-16 22:44:42,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009040_4628480.pth... +[2023-07-16 22:44:42,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000008272_4235264.pth +[2023-07-16 22:44:46,138][254033] Updated weights for policy 0, policy_version 9120 (0.0005) +[2023-07-16 22:44:47,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12629.3, 300 sec: 12704.5). Total num frames: 4689920. Throughput: 0: 12764.6. Samples: 4685888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:44:47,972][253751] Avg episode reward: [(0, '790.288')] +[2023-07-16 22:44:49,513][254033] Updated weights for policy 0, policy_version 9200 (0.0005) +[2023-07-16 22:44:52,730][254033] Updated weights for policy 0, policy_version 9280 (0.0004) +[2023-07-16 22:44:52,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12690.7). Total num frames: 4751360. Throughput: 0: 12770.4. Samples: 4722752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:44:52,972][253751] Avg episode reward: [(0, '788.471')] +[2023-07-16 22:44:55,897][254033] Updated weights for policy 0, policy_version 9360 (0.0004) +[2023-07-16 22:44:57,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12704.5). Total num frames: 4816896. Throughput: 0: 12923.6. Samples: 4800576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:44:57,972][253751] Avg episode reward: [(0, '791.734')] +[2023-07-16 22:44:57,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009408_4816896.pth... +[2023-07-16 22:44:57,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000008648_4427776.pth +[2023-07-16 22:44:58,958][254033] Updated weights for policy 0, policy_version 9440 (0.0004) +[2023-07-16 22:45:02,029][254033] Updated weights for policy 0, policy_version 9520 (0.0004) +[2023-07-16 22:45:02,971][253751] Fps is (10 sec: 13516.8, 60 sec: 12834.1, 300 sec: 12718.4). Total num frames: 4886528. Throughput: 0: 13087.3. Samples: 4880852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:45:02,971][253751] Avg episode reward: [(0, '792.170')] +[2023-07-16 22:45:05,064][254033] Updated weights for policy 0, policy_version 9600 (0.0004) +[2023-07-16 22:45:07,971][253751] Fps is (10 sec: 13516.8, 60 sec: 12970.7, 300 sec: 12732.3). Total num frames: 4952064. Throughput: 0: 13107.7. Samples: 4921340. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:45:07,971][253751] Avg episode reward: [(0, '788.456')] +[2023-07-16 22:45:08,091][254033] Updated weights for policy 0, policy_version 9680 (0.0003) +[2023-07-16 22:45:11,213][254033] Updated weights for policy 0, policy_version 9760 (0.0004) +[2023-07-16 22:45:12,971][253751] Fps is (10 sec: 13107.2, 60 sec: 13038.9, 300 sec: 12732.3). Total num frames: 5017600. Throughput: 0: 13101.4. Samples: 5001280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:45:12,971][253751] Avg episode reward: [(0, '794.847')] +[2023-07-16 22:45:12,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009800_5017600.pth... +[2023-07-16 22:45:12,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009040_4628480.pth +[2023-07-16 22:45:14,253][254033] Updated weights for policy 0, policy_version 9840 (0.0004) +[2023-07-16 22:45:17,385][254033] Updated weights for policy 0, policy_version 9920 (0.0004) +[2023-07-16 22:45:17,971][253751] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12746.2). Total num frames: 5083136. Throughput: 0: 13084.2. Samples: 5080600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:45:17,971][253751] Avg episode reward: [(0, '796.770')] +[2023-07-16 22:45:20,412][254033] Updated weights for policy 0, policy_version 10000 (0.0004) +[2023-07-16 22:45:22,971][253751] Fps is (10 sec: 13516.8, 60 sec: 13175.5, 300 sec: 12774.0). Total num frames: 5152768. Throughput: 0: 13090.0. Samples: 5121076. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-16 22:45:22,971][253751] Avg episode reward: [(0, '793.602')] +[2023-07-16 22:45:23,437][254033] Updated weights for policy 0, policy_version 10080 (0.0003) +[2023-07-16 22:45:26,537][254033] Updated weights for policy 0, policy_version 10160 (0.0004) +[2023-07-16 22:45:27,971][253751] Fps is (10 sec: 13516.7, 60 sec: 13175.5, 300 sec: 12760.1). Total num frames: 5218304. Throughput: 0: 13098.0. Samples: 5201928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:45:27,971][253751] Avg episode reward: [(0, '800.107')] +[2023-07-16 22:45:27,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010192_5218304.pth... +[2023-07-16 22:45:27,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009408_4816896.pth +[2023-07-16 22:45:29,639][254033] Updated weights for policy 0, policy_version 10240 (0.0004) +[2023-07-16 22:45:32,749][254033] Updated weights for policy 0, policy_version 10320 (0.0004) +[2023-07-16 22:45:32,971][253751] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 5283840. Throughput: 0: 13206.6. Samples: 5280184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:45:32,971][253751] Avg episode reward: [(0, '799.986')] +[2023-07-16 22:45:35,829][254033] Updated weights for policy 0, policy_version 10400 (0.0004) +[2023-07-16 22:45:37,971][253751] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 5349376. Throughput: 0: 13289.3. Samples: 5320768. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-16 22:45:37,971][253751] Avg episode reward: [(0, '799.157')] +[2023-07-16 22:45:38,886][254033] Updated weights for policy 0, policy_version 10480 (0.0004) +[2023-07-16 22:45:42,148][254033] Updated weights for policy 0, policy_version 10560 (0.0005) +[2023-07-16 22:45:42,971][253751] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12787.9). Total num frames: 5414912. Throughput: 0: 13292.8. Samples: 5398752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:45:42,971][253751] Avg episode reward: [(0, '800.027')] +[2023-07-16 22:45:42,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010576_5414912.pth... +[2023-07-16 22:45:42,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000009800_5017600.pth +[2023-07-16 22:45:45,467][254033] Updated weights for policy 0, policy_version 10640 (0.0005) +[2023-07-16 22:45:47,971][253751] Fps is (10 sec: 12697.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 5476352. Throughput: 0: 13143.7. Samples: 5472320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:45:47,971][253751] Avg episode reward: [(0, '789.571')] +[2023-07-16 22:45:48,736][254033] Updated weights for policy 0, policy_version 10720 (0.0004) +[2023-07-16 22:45:51,860][254033] Updated weights for policy 0, policy_version 10800 (0.0004) +[2023-07-16 22:45:52,971][253751] Fps is (10 sec: 12697.6, 60 sec: 13175.5, 300 sec: 12787.9). Total num frames: 5541888. Throughput: 0: 13118.0. Samples: 5511652. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-16 22:45:52,971][253751] Avg episode reward: [(0, '782.446')] +[2023-07-16 22:45:54,876][254033] Updated weights for policy 0, policy_version 10880 (0.0003) +[2023-07-16 22:45:57,938][254033] Updated weights for policy 0, policy_version 10960 (0.0004) +[2023-07-16 22:45:57,971][253751] Fps is (10 sec: 13516.7, 60 sec: 13243.7, 300 sec: 12815.6). Total num frames: 5611520. Throughput: 0: 13142.9. Samples: 5592712. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-16 22:45:57,971][253751] Avg episode reward: [(0, '795.969')] +[2023-07-16 22:45:57,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010960_5611520.pth... +[2023-07-16 22:45:57,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010192_5218304.pth +[2023-07-16 22:46:01,173][254033] Updated weights for policy 0, policy_version 11040 (0.0005) +[2023-07-16 22:46:02,971][253751] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12801.7). Total num frames: 5672960. Throughput: 0: 13073.9. Samples: 5668928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:46:02,971][253751] Avg episode reward: [(0, '795.499')] +[2023-07-16 22:46:04,559][254033] Updated weights for policy 0, policy_version 11120 (0.0004) +[2023-07-16 22:46:07,971][253751] Fps is (10 sec: 11878.5, 60 sec: 12970.7, 300 sec: 12787.9). Total num frames: 5730304. Throughput: 0: 12982.2. Samples: 5705276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:46:07,971][253751] Avg episode reward: [(0, '797.190')] +[2023-07-16 22:46:07,989][254033] Updated weights for policy 0, policy_version 11200 (0.0005) +[2023-07-16 22:46:11,299][254033] Updated weights for policy 0, policy_version 11280 (0.0005) +[2023-07-16 22:46:12,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12902.4, 300 sec: 12787.9). Total num frames: 5791744. Throughput: 0: 12807.8. Samples: 5778280. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-16 22:46:12,971][253751] Avg episode reward: [(0, '800.288')] +[2023-07-16 22:46:12,977][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000011320_5795840.pth... +[2023-07-16 22:46:12,979][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010576_5414912.pth +[2023-07-16 22:46:14,649][254033] Updated weights for policy 0, policy_version 11360 (0.0005) +[2023-07-16 22:46:17,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12834.1, 300 sec: 12774.0). Total num frames: 5853184. Throughput: 0: 12696.7. Samples: 5851532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:46:17,971][253751] Avg episode reward: [(0, '799.380')] +[2023-07-16 22:46:18,021][254033] Updated weights for policy 0, policy_version 11440 (0.0005) +[2023-07-16 22:46:21,332][254033] Updated weights for policy 0, policy_version 11520 (0.0005) +[2023-07-16 22:46:22,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12697.6, 300 sec: 12774.0). Total num frames: 5914624. Throughput: 0: 12612.5. Samples: 5888332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:46:22,982][253751] Avg episode reward: [(0, '800.330')] +[2023-07-16 22:46:24,673][254033] Updated weights for policy 0, policy_version 11600 (0.0005) +[2023-07-16 22:46:27,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12629.3, 300 sec: 12774.0). Total num frames: 5976064. Throughput: 0: 12497.9. Samples: 5961156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:46:27,972][253751] Avg episode reward: [(0, '800.462')] +[2023-07-16 22:46:27,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000011672_5976064.pth... +[2023-07-16 22:46:27,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000010960_5611520.pth +[2023-07-16 22:46:27,978][253989] Saving new best policy, reward=800.462! +[2023-07-16 22:46:28,113][254033] Updated weights for policy 0, policy_version 11680 (0.0005) +[2023-07-16 22:46:31,589][254033] Updated weights for policy 0, policy_version 11760 (0.0005) +[2023-07-16 22:46:32,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12561.1, 300 sec: 12746.2). Total num frames: 6037504. Throughput: 0: 12459.9. Samples: 6033016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:46:32,972][253751] Avg episode reward: [(0, '799.003')] +[2023-07-16 22:46:34,961][254033] Updated weights for policy 0, policy_version 11840 (0.0005) +[2023-07-16 22:46:37,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12424.5, 300 sec: 12718.4). Total num frames: 6094848. Throughput: 0: 12395.1. Samples: 6069432. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-16 22:46:37,971][253751] Avg episode reward: [(0, '799.088')] +[2023-07-16 22:46:38,408][254033] Updated weights for policy 0, policy_version 11920 (0.0005) +[2023-07-16 22:46:41,751][254033] Updated weights for policy 0, policy_version 12000 (0.0005) +[2023-07-16 22:46:42,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12704.5). Total num frames: 6156288. Throughput: 0: 12184.1. Samples: 6140996. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-16 22:46:42,971][253751] Avg episode reward: [(0, '794.498')] +[2023-07-16 22:46:42,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012024_6156288.pth... +[2023-07-16 22:46:42,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000011320_5795840.pth +[2023-07-16 22:46:44,965][254033] Updated weights for policy 0, policy_version 12080 (0.0004) +[2023-07-16 22:46:47,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12424.5, 300 sec: 12718.4). Total num frames: 6221824. Throughput: 0: 12213.1. Samples: 6218520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:46:47,973][253751] Avg episode reward: [(0, '800.634')] +[2023-07-16 22:46:47,973][253989] Saving new best policy, reward=800.634! +[2023-07-16 22:46:48,063][254033] Updated weights for policy 0, policy_version 12160 (0.0004) +[2023-07-16 22:46:51,186][254033] Updated weights for policy 0, policy_version 12240 (0.0004) +[2023-07-16 22:46:52,971][253751] Fps is (10 sec: 13107.2, 60 sec: 12424.5, 300 sec: 12732.3). Total num frames: 6287360. Throughput: 0: 12298.2. Samples: 6258696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:46:52,972][253751] Avg episode reward: [(0, '799.082')] +[2023-07-16 22:46:54,251][254033] Updated weights for policy 0, policy_version 12320 (0.0004) +[2023-07-16 22:46:57,365][254033] Updated weights for policy 0, policy_version 12400 (0.0004) +[2023-07-16 22:46:57,971][253751] Fps is (10 sec: 13107.2, 60 sec: 12356.3, 300 sec: 12732.3). Total num frames: 6352896. Throughput: 0: 12417.5. Samples: 6337068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:46:57,972][253751] Avg episode reward: [(0, '799.098')] +[2023-07-16 22:46:58,006][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012416_6356992.pth... +[2023-07-16 22:46:58,007][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000011672_5976064.pth +[2023-07-16 22:47:00,556][254033] Updated weights for policy 0, policy_version 12480 (0.0004) +[2023-07-16 22:47:02,971][253751] Fps is (10 sec: 13107.3, 60 sec: 12424.5, 300 sec: 12746.2). Total num frames: 6418432. Throughput: 0: 12490.8. Samples: 6413620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:47:02,972][253751] Avg episode reward: [(0, '796.827')] +[2023-07-16 22:47:03,965][254033] Updated weights for policy 0, policy_version 12560 (0.0005) +[2023-07-16 22:47:07,287][254033] Updated weights for policy 0, policy_version 12640 (0.0005) +[2023-07-16 22:47:07,971][253751] Fps is (10 sec: 12697.7, 60 sec: 12492.8, 300 sec: 12732.3). Total num frames: 6479872. Throughput: 0: 12480.6. Samples: 6449960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:47:07,972][253751] Avg episode reward: [(0, '800.885')] +[2023-07-16 22:47:07,972][253989] Saving new best policy, reward=800.885! +[2023-07-16 22:47:10,639][254033] Updated weights for policy 0, policy_version 12720 (0.0005) +[2023-07-16 22:47:12,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12492.8, 300 sec: 12732.3). Total num frames: 6541312. Throughput: 0: 12506.8. Samples: 6523960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:47:12,972][253751] Avg episode reward: [(0, '795.232')] +[2023-07-16 22:47:12,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012776_6541312.pth... +[2023-07-16 22:47:12,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012024_6156288.pth +[2023-07-16 22:47:13,995][254033] Updated weights for policy 0, policy_version 12800 (0.0005) +[2023-07-16 22:47:17,374][254033] Updated weights for policy 0, policy_version 12880 (0.0005) +[2023-07-16 22:47:17,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12424.5, 300 sec: 12718.4). Total num frames: 6598656. Throughput: 0: 12515.5. Samples: 6596212. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-16 22:47:17,972][253751] Avg episode reward: [(0, '799.595')] +[2023-07-16 22:47:20,683][254033] Updated weights for policy 0, policy_version 12960 (0.0005) +[2023-07-16 22:47:22,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12424.5, 300 sec: 12704.5). Total num frames: 6660096. Throughput: 0: 12526.5. Samples: 6633124. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-16 22:47:22,972][253751] Avg episode reward: [(0, '800.015')] +[2023-07-16 22:47:24,060][254033] Updated weights for policy 0, policy_version 13040 (0.0005) +[2023-07-16 22:47:27,405][254033] Updated weights for policy 0, policy_version 13120 (0.0005) +[2023-07-16 22:47:27,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12424.5, 300 sec: 12704.5). Total num frames: 6721536. Throughput: 0: 12565.5. Samples: 6706444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:47:27,972][253751] Avg episode reward: [(0, '801.744')] +[2023-07-16 22:47:27,976][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013128_6721536.pth... +[2023-07-16 22:47:27,979][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012416_6356992.pth +[2023-07-16 22:47:27,979][253989] Saving new best policy, reward=801.744! +[2023-07-16 22:47:30,845][254033] Updated weights for policy 0, policy_version 13200 (0.0005) +[2023-07-16 22:47:32,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12704.5). Total num frames: 6782976. Throughput: 0: 12447.9. Samples: 6778676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:47:32,971][253751] Avg episode reward: [(0, '801.000')] +[2023-07-16 22:47:34,237][254033] Updated weights for policy 0, policy_version 13280 (0.0005) +[2023-07-16 22:47:37,629][254033] Updated weights for policy 0, policy_version 13360 (0.0005) +[2023-07-16 22:47:37,971][253751] Fps is (10 sec: 11878.5, 60 sec: 12424.5, 300 sec: 12676.8). Total num frames: 6840320. Throughput: 0: 12350.3. Samples: 6814460. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-16 22:47:37,972][253751] Avg episode reward: [(0, '803.578')] +[2023-07-16 22:47:37,984][253989] Saving new best policy, reward=803.578! +[2023-07-16 22:47:41,005][254033] Updated weights for policy 0, policy_version 13440 (0.0005) +[2023-07-16 22:47:42,971][253751] Fps is (10 sec: 11878.5, 60 sec: 12424.5, 300 sec: 12676.8). Total num frames: 6901760. Throughput: 0: 12225.5. Samples: 6887216. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-16 22:47:42,971][253751] Avg episode reward: [(0, '797.520')] +[2023-07-16 22:47:42,973][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013480_6901760.pth... +[2023-07-16 22:47:42,976][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000012776_6541312.pth +[2023-07-16 22:47:44,473][254033] Updated weights for policy 0, policy_version 13520 (0.0005) +[2023-07-16 22:47:47,833][254033] Updated weights for policy 0, policy_version 13600 (0.0005) +[2023-07-16 22:47:47,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12690.7). Total num frames: 6963200. Throughput: 0: 12123.3. Samples: 6959168. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-16 22:47:47,973][253751] Avg episode reward: [(0, '798.811')] +[2023-07-16 22:47:51,221][254033] Updated weights for policy 0, policy_version 13680 (0.0005) +[2023-07-16 22:47:52,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12676.8). Total num frames: 7024640. Throughput: 0: 12128.7. Samples: 6995752. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-16 22:47:52,972][253751] Avg episode reward: [(0, '802.948')] +[2023-07-16 22:47:54,629][254033] Updated weights for policy 0, policy_version 13760 (0.0005) +[2023-07-16 22:47:57,971][253751] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12649.0). Total num frames: 7081984. Throughput: 0: 12078.2. Samples: 7067480. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-16 22:47:57,994][253751] Avg episode reward: [(0, '801.382')] +[2023-07-16 22:47:57,996][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013832_7081984.pth... +[2023-07-16 22:47:57,999][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013128_6721536.pth +[2023-07-16 22:47:58,079][254033] Updated weights for policy 0, policy_version 13840 (0.0005) +[2023-07-16 22:48:01,545][254033] Updated weights for policy 0, policy_version 13920 (0.0005) +[2023-07-16 22:48:02,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12621.2). Total num frames: 7143424. Throughput: 0: 12068.8. Samples: 7139308. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-16 22:48:02,994][253751] Avg episode reward: [(0, '798.033')] +[2023-07-16 22:48:04,996][254033] Updated weights for policy 0, policy_version 14000 (0.0005) +[2023-07-16 22:48:07,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 12607.3). Total num frames: 7204864. Throughput: 0: 12029.5. Samples: 7174452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:48:07,972][253751] Avg episode reward: [(0, '802.324')] +[2023-07-16 22:48:08,310][254033] Updated weights for policy 0, policy_version 14080 (0.0005) +[2023-07-16 22:48:11,651][254033] Updated weights for policy 0, policy_version 14160 (0.0005) +[2023-07-16 22:48:12,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12593.5). Total num frames: 7266304. Throughput: 0: 12041.0. Samples: 7248288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:48:12,972][253751] Avg episode reward: [(0, '802.451')] +[2023-07-16 22:48:12,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014192_7266304.pth... +[2023-07-16 22:48:12,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013480_6901760.pth +[2023-07-16 22:48:14,977][254033] Updated weights for policy 0, policy_version 14240 (0.0005) +[2023-07-16 22:48:17,971][253751] Fps is (10 sec: 11878.6, 60 sec: 12083.2, 300 sec: 12565.7). Total num frames: 7323648. Throughput: 0: 12037.1. Samples: 7320344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:48:17,972][253751] Avg episode reward: [(0, '797.192')] +[2023-07-16 22:48:18,451][254033] Updated weights for policy 0, policy_version 14320 (0.0005) +[2023-07-16 22:48:21,804][254033] Updated weights for policy 0, policy_version 14400 (0.0005) +[2023-07-16 22:48:22,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12537.9). Total num frames: 7385088. Throughput: 0: 12055.3. Samples: 7356948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:48:22,972][253751] Avg episode reward: [(0, '803.681')] +[2023-07-16 22:48:22,972][253989] Saving new best policy, reward=803.681! +[2023-07-16 22:48:25,232][254033] Updated weights for policy 0, policy_version 14480 (0.0005) +[2023-07-16 22:48:27,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 12537.9). Total num frames: 7446528. Throughput: 0: 12062.0. Samples: 7430008. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-16 22:48:27,972][253751] Avg episode reward: [(0, '801.097')] +[2023-07-16 22:48:27,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014544_7446528.pth... +[2023-07-16 22:48:27,976][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000013832_7081984.pth +[2023-07-16 22:48:28,643][254033] Updated weights for policy 0, policy_version 14560 (0.0005) +[2023-07-16 22:48:31,986][254033] Updated weights for policy 0, policy_version 14640 (0.0005) +[2023-07-16 22:48:32,971][253751] Fps is (10 sec: 11878.5, 60 sec: 12015.0, 300 sec: 12524.0). Total num frames: 7503872. Throughput: 0: 12071.5. Samples: 7502384. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-16 22:48:32,971][253751] Avg episode reward: [(0, '799.262')] +[2023-07-16 22:48:35,379][254033] Updated weights for policy 0, policy_version 14720 (0.0005) +[2023-07-16 22:48:37,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12524.0). Total num frames: 7565312. Throughput: 0: 12055.2. Samples: 7538236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:48:37,971][253751] Avg episode reward: [(0, '804.786')] +[2023-07-16 22:48:37,972][253989] Saving new best policy, reward=804.786! +[2023-07-16 22:48:38,751][254033] Updated weights for policy 0, policy_version 14800 (0.0005) +[2023-07-16 22:48:42,263][254033] Updated weights for policy 0, policy_version 14880 (0.0005) +[2023-07-16 22:48:42,971][253751] Fps is (10 sec: 12287.8, 60 sec: 12083.2, 300 sec: 12524.0). Total num frames: 7626752. Throughput: 0: 12064.2. Samples: 7610368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:48:42,972][253751] Avg episode reward: [(0, '801.175')] +[2023-07-16 22:48:42,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014896_7626752.pth... +[2023-07-16 22:48:42,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014192_7266304.pth +[2023-07-16 22:48:45,620][254033] Updated weights for policy 0, policy_version 14960 (0.0005) +[2023-07-16 22:48:47,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12510.2). Total num frames: 7684096. Throughput: 0: 12063.9. Samples: 7682184. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-16 22:48:47,971][253751] Avg episode reward: [(0, '796.376')] +[2023-07-16 22:48:49,076][254033] Updated weights for policy 0, policy_version 15040 (0.0005) +[2023-07-16 22:48:52,469][254033] Updated weights for policy 0, policy_version 15120 (0.0005) +[2023-07-16 22:48:52,971][253751] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12510.2). Total num frames: 7745536. Throughput: 0: 12080.0. Samples: 7718048. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-16 22:48:52,971][253751] Avg episode reward: [(0, '799.948')] +[2023-07-16 22:48:55,839][254033] Updated weights for policy 0, policy_version 15200 (0.0005) +[2023-07-16 22:48:57,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12510.2). Total num frames: 7806976. Throughput: 0: 12052.6. Samples: 7790656. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:48:57,971][253751] Avg episode reward: [(0, '800.861')] +[2023-07-16 22:48:57,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015248_7806976.pth... +[2023-07-16 22:48:57,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014544_7446528.pth +[2023-07-16 22:48:59,051][254033] Updated weights for policy 0, policy_version 15280 (0.0005) +[2023-07-16 22:49:02,449][254033] Updated weights for policy 0, policy_version 15360 (0.0005) +[2023-07-16 22:49:02,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12524.0). Total num frames: 7868416. Throughput: 0: 12102.2. Samples: 7864944. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:49:02,971][253751] Avg episode reward: [(0, '794.925')] +[2023-07-16 22:49:05,734][254033] Updated weights for policy 0, policy_version 15440 (0.0005) +[2023-07-16 22:49:07,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12524.0). Total num frames: 7929856. Throughput: 0: 12129.5. Samples: 7902776. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:49:07,971][253751] Avg episode reward: [(0, '797.883')] +[2023-07-16 22:49:08,968][254033] Updated weights for policy 0, policy_version 15520 (0.0005) +[2023-07-16 22:49:12,271][254033] Updated weights for policy 0, policy_version 15600 (0.0005) +[2023-07-16 22:49:12,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 12537.9). Total num frames: 7995392. Throughput: 0: 12178.7. Samples: 7978048. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-16 22:49:12,971][253751] Avg episode reward: [(0, '793.370')] +[2023-07-16 22:49:12,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015616_7995392.pth... +[2023-07-16 22:49:12,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000014896_7626752.pth +[2023-07-16 22:49:15,564][254033] Updated weights for policy 0, policy_version 15680 (0.0005) +[2023-07-16 22:49:17,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 12524.0). Total num frames: 8056832. Throughput: 0: 12222.9. Samples: 8052416. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-16 22:49:17,971][253751] Avg episode reward: [(0, '792.588')] +[2023-07-16 22:49:18,955][254033] Updated weights for policy 0, policy_version 15760 (0.0005) +[2023-07-16 22:49:22,278][254033] Updated weights for policy 0, policy_version 15840 (0.0005) +[2023-07-16 22:49:22,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12510.2). Total num frames: 8118272. Throughput: 0: 12234.6. Samples: 8088792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:49:22,971][253751] Avg episode reward: [(0, '801.064')] +[2023-07-16 22:49:25,517][254033] Updated weights for policy 0, policy_version 15920 (0.0005) +[2023-07-16 22:49:27,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12482.4). Total num frames: 8179712. Throughput: 0: 12289.4. Samples: 8163392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:49:27,971][253751] Avg episode reward: [(0, '794.816')] +[2023-07-16 22:49:27,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015976_8179712.pth... +[2023-07-16 22:49:27,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015248_7806976.pth +[2023-07-16 22:49:28,727][254033] Updated weights for policy 0, policy_version 16000 (0.0005) +[2023-07-16 22:49:31,846][254033] Updated weights for policy 0, policy_version 16080 (0.0004) +[2023-07-16 22:49:32,971][253751] Fps is (10 sec: 12697.7, 60 sec: 12356.3, 300 sec: 12482.4). Total num frames: 8245248. Throughput: 0: 12423.1. Samples: 8241224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:49:32,971][253751] Avg episode reward: [(0, '798.685')] +[2023-07-16 22:49:35,194][254033] Updated weights for policy 0, policy_version 16160 (0.0005) +[2023-07-16 22:49:37,971][253751] Fps is (10 sec: 12697.7, 60 sec: 12356.3, 300 sec: 12468.5). Total num frames: 8306688. Throughput: 0: 12443.7. Samples: 8278016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:49:37,971][253751] Avg episode reward: [(0, '800.435')] +[2023-07-16 22:49:38,491][254033] Updated weights for policy 0, policy_version 16240 (0.0005) +[2023-07-16 22:49:41,484][254033] Updated weights for policy 0, policy_version 16320 (0.0003) +[2023-07-16 22:49:42,971][253751] Fps is (10 sec: 12697.6, 60 sec: 12424.6, 300 sec: 12482.4). Total num frames: 8372224. Throughput: 0: 12561.3. Samples: 8355912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:49:42,971][253751] Avg episode reward: [(0, '804.339')] +[2023-07-16 22:49:42,993][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000016360_8376320.pth... +[2023-07-16 22:49:42,995][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015616_7995392.pth +[2023-07-16 22:49:44,539][254033] Updated weights for policy 0, policy_version 16400 (0.0004) +[2023-07-16 22:49:47,747][254033] Updated weights for policy 0, policy_version 16480 (0.0004) +[2023-07-16 22:49:47,971][253751] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12496.3). Total num frames: 8437760. Throughput: 0: 12658.0. Samples: 8434556. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:49:47,972][253751] Avg episode reward: [(0, '798.544')] +[2023-07-16 22:49:51,162][254033] Updated weights for policy 0, policy_version 16560 (0.0005) +[2023-07-16 22:49:52,971][253751] Fps is (10 sec: 12697.5, 60 sec: 12561.1, 300 sec: 12482.4). Total num frames: 8499200. Throughput: 0: 12618.1. Samples: 8470592. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:49:52,971][253751] Avg episode reward: [(0, '799.808')] +[2023-07-16 22:49:54,612][254033] Updated weights for policy 0, policy_version 16640 (0.0005) +[2023-07-16 22:49:57,877][254033] Updated weights for policy 0, policy_version 16720 (0.0005) +[2023-07-16 22:49:57,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12454.6). Total num frames: 8560640. Throughput: 0: 12577.2. Samples: 8544020. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:49:57,971][253751] Avg episode reward: [(0, '800.818')] +[2023-07-16 22:49:57,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000016720_8560640.pth... +[2023-07-16 22:49:57,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000015976_8179712.pth +[2023-07-16 22:50:01,195][254033] Updated weights for policy 0, policy_version 16800 (0.0005) +[2023-07-16 22:50:02,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12440.7). Total num frames: 8622080. Throughput: 0: 12568.2. Samples: 8617984. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:50:02,971][253751] Avg episode reward: [(0, '788.239')] +[2023-07-16 22:50:04,542][254033] Updated weights for policy 0, policy_version 16880 (0.0005) +[2023-07-16 22:50:07,767][254033] Updated weights for policy 0, policy_version 16960 (0.0005) +[2023-07-16 22:50:07,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12426.8). Total num frames: 8683520. Throughput: 0: 12580.4. Samples: 8654912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:50:07,971][253751] Avg episode reward: [(0, '778.645')] +[2023-07-16 22:50:11,136][254033] Updated weights for policy 0, policy_version 17040 (0.0005) +[2023-07-16 22:50:12,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12492.8, 300 sec: 12413.0). Total num frames: 8744960. Throughput: 0: 12561.2. Samples: 8728648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:50:12,971][253751] Avg episode reward: [(0, '801.886')] +[2023-07-16 22:50:12,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017080_8744960.pth... +[2023-07-16 22:50:12,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000016360_8376320.pth +[2023-07-16 22:50:14,520][254033] Updated weights for policy 0, policy_version 17120 (0.0005) +[2023-07-16 22:50:17,889][254033] Updated weights for policy 0, policy_version 17200 (0.0005) +[2023-07-16 22:50:17,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12492.8, 300 sec: 12385.2). Total num frames: 8806400. Throughput: 0: 12468.7. Samples: 8802316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:50:17,971][253751] Avg episode reward: [(0, '798.604')] +[2023-07-16 22:50:21,319][254033] Updated weights for policy 0, policy_version 17280 (0.0005) +[2023-07-16 22:50:22,971][253751] Fps is (10 sec: 11878.6, 60 sec: 12424.6, 300 sec: 12357.4). Total num frames: 8863744. Throughput: 0: 12448.2. Samples: 8838184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:50:22,971][253751] Avg episode reward: [(0, '803.739')] +[2023-07-16 22:50:24,747][254033] Updated weights for policy 0, policy_version 17360 (0.0005) +[2023-07-16 22:50:27,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12424.5, 300 sec: 12343.5). Total num frames: 8925184. Throughput: 0: 12317.8. Samples: 8910216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:50:28,017][253751] Avg episode reward: [(0, '802.345')] +[2023-07-16 22:50:28,037][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017440_8929280.pth... +[2023-07-16 22:50:28,038][254033] Updated weights for policy 0, policy_version 17440 (0.0005) +[2023-07-16 22:50:28,040][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000016720_8560640.pth +[2023-07-16 22:50:31,449][254033] Updated weights for policy 0, policy_version 17520 (0.0005) +[2023-07-16 22:50:32,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12329.7). Total num frames: 8986624. Throughput: 0: 12192.7. Samples: 8983228. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:50:32,972][253751] Avg episode reward: [(0, '803.921')] +[2023-07-16 22:50:34,808][254033] Updated weights for policy 0, policy_version 17600 (0.0005) +[2023-07-16 22:50:37,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12315.8). Total num frames: 9048064. Throughput: 0: 12197.0. Samples: 9019456. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:50:37,972][253751] Avg episode reward: [(0, '800.231')] +[2023-07-16 22:50:38,199][254033] Updated weights for policy 0, policy_version 17680 (0.0005) +[2023-07-16 22:50:41,577][254033] Updated weights for policy 0, policy_version 17760 (0.0005) +[2023-07-16 22:50:42,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12315.8). Total num frames: 9109504. Throughput: 0: 12192.3. Samples: 9092676. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:50:42,972][253751] Avg episode reward: [(0, '797.174')] +[2023-07-16 22:50:42,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017792_9109504.pth... +[2023-07-16 22:50:42,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017080_8744960.pth +[2023-07-16 22:50:45,012][254033] Updated weights for policy 0, policy_version 17840 (0.0005) +[2023-07-16 22:50:47,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12288.0). Total num frames: 9166848. Throughput: 0: 12152.5. Samples: 9164848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:50:48,061][253751] Avg episode reward: [(0, '797.779')] +[2023-07-16 22:50:48,370][254033] Updated weights for policy 0, policy_version 17920 (0.0004) +[2023-07-16 22:50:51,657][254033] Updated weights for policy 0, policy_version 18000 (0.0005) +[2023-07-16 22:50:52,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12260.2). Total num frames: 9228288. Throughput: 0: 12154.8. Samples: 9201880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:50:52,972][253751] Avg episode reward: [(0, '798.552')] +[2023-07-16 22:50:55,029][254033] Updated weights for policy 0, policy_version 18080 (0.0005) +[2023-07-16 22:50:57,971][253751] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12260.2). Total num frames: 9289728. Throughput: 0: 12137.9. Samples: 9274852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:50:57,972][253751] Avg episode reward: [(0, '791.438')] +[2023-07-16 22:50:57,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018144_9289728.pth... +[2023-07-16 22:50:57,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017440_8929280.pth +[2023-07-16 22:50:58,429][254033] Updated weights for policy 0, policy_version 18160 (0.0004) +[2023-07-16 22:51:01,771][254033] Updated weights for policy 0, policy_version 18240 (0.0005) +[2023-07-16 22:51:02,971][253751] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 12274.1). Total num frames: 9351168. Throughput: 0: 12113.3. Samples: 9347412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:51:02,972][253751] Avg episode reward: [(0, '804.066')] +[2023-07-16 22:51:05,231][254033] Updated weights for policy 0, policy_version 18320 (0.0005) +[2023-07-16 22:51:07,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12260.2). Total num frames: 9408512. Throughput: 0: 12123.5. Samples: 9383740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:51:07,972][253751] Avg episode reward: [(0, '799.226')] +[2023-07-16 22:51:08,684][254033] Updated weights for policy 0, policy_version 18400 (0.0005) +[2023-07-16 22:51:11,915][254033] Updated weights for policy 0, policy_version 18480 (0.0004) +[2023-07-16 22:51:12,971][253751] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 12274.1). Total num frames: 9474048. Throughput: 0: 12153.2. Samples: 9457112. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:51:12,971][253751] Avg episode reward: [(0, '795.247')] +[2023-07-16 22:51:12,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018504_9474048.pth... +[2023-07-16 22:51:12,977][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000017792_9109504.pth +[2023-07-16 22:51:15,173][254033] Updated weights for policy 0, policy_version 18560 (0.0004) +[2023-07-16 22:51:17,971][253751] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 12274.1). Total num frames: 9535488. Throughput: 0: 12193.9. Samples: 9531956. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:51:17,975][253751] Avg episode reward: [(0, '793.018')] +[2023-07-16 22:51:18,491][254033] Updated weights for policy 0, policy_version 18640 (0.0005) +[2023-07-16 22:51:21,936][254033] Updated weights for policy 0, policy_version 18720 (0.0005) +[2023-07-16 22:51:22,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12151.4, 300 sec: 12260.2). Total num frames: 9592832. Throughput: 0: 12195.7. Samples: 9568264. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-16 22:51:22,972][253751] Avg episode reward: [(0, '798.922')] +[2023-07-16 22:51:25,295][254033] Updated weights for policy 0, policy_version 18800 (0.0005) +[2023-07-16 22:51:27,971][253751] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12260.2). Total num frames: 9654272. Throughput: 0: 12180.9. Samples: 9640816. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-16 22:51:27,971][253751] Avg episode reward: [(0, '802.975')] +[2023-07-16 22:51:27,974][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018856_9654272.pth... +[2023-07-16 22:51:27,976][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018144_9289728.pth +[2023-07-16 22:51:28,668][254033] Updated weights for policy 0, policy_version 18880 (0.0005) +[2023-07-16 22:51:31,784][254033] Updated weights for policy 0, policy_version 18960 (0.0004) +[2023-07-16 22:51:32,971][253751] Fps is (10 sec: 12697.8, 60 sec: 12219.8, 300 sec: 12288.0). Total num frames: 9719808. Throughput: 0: 12272.1. Samples: 9717092. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-16 22:51:32,983][253751] Avg episode reward: [(0, '804.718')] +[2023-07-16 22:51:34,899][254033] Updated weights for policy 0, policy_version 19040 (0.0004) +[2023-07-16 22:51:37,971][253751] Fps is (10 sec: 13107.2, 60 sec: 12288.0, 300 sec: 12301.9). Total num frames: 9785344. Throughput: 0: 12327.0. Samples: 9756596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:51:37,972][253751] Avg episode reward: [(0, '803.026')] +[2023-07-16 22:51:38,050][254033] Updated weights for policy 0, policy_version 19120 (0.0004) +[2023-07-16 22:51:41,351][254033] Updated weights for policy 0, policy_version 19200 (0.0005) +[2023-07-16 22:51:42,971][253751] Fps is (10 sec: 12697.5, 60 sec: 12288.0, 300 sec: 12288.0). Total num frames: 9846784. Throughput: 0: 12392.7. Samples: 9832524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:51:42,971][253751] Avg episode reward: [(0, '800.119')] +[2023-07-16 22:51:42,975][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000019232_9846784.pth... +[2023-07-16 22:51:42,978][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018504_9474048.pth +[2023-07-16 22:51:44,776][254033] Updated weights for policy 0, policy_version 19280 (0.0005) +[2023-07-16 22:51:47,971][253751] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12274.1). Total num frames: 9908224. Throughput: 0: 12402.9. Samples: 9905540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:51:47,972][253751] Avg episode reward: [(0, '799.294')] +[2023-07-16 22:51:47,995][254033] Updated weights for policy 0, policy_version 19360 (0.0004) +[2023-07-16 22:51:51,134][254033] Updated weights for policy 0, policy_version 19440 (0.0004) +[2023-07-16 22:51:52,971][253751] Fps is (10 sec: 12697.7, 60 sec: 12424.6, 300 sec: 12274.1). Total num frames: 9973760. Throughput: 0: 12479.5. Samples: 9945316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-16 22:51:52,972][253751] Avg episode reward: [(0, '801.007')] +[2023-07-16 22:51:54,324][254033] Updated weights for policy 0, policy_version 19520 (0.0004) +[2023-07-16 22:51:55,260][253989] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 +[2023-07-16 22:51:55,261][254037] Stopping RolloutWorker_w4... +[2023-07-16 22:51:55,261][254035] Stopping RolloutWorker_w1... +[2023-07-16 22:51:55,261][254039] Stopping RolloutWorker_w5... +[2023-07-16 22:51:55,261][254034] Stopping RolloutWorker_w0... +[2023-07-16 22:51:55,261][254036] Stopping RolloutWorker_w2... +[2023-07-16 22:51:55,261][254040] Stopping RolloutWorker_w6... +[2023-07-16 22:51:55,261][254134] Stopping RolloutWorker_w7... +[2023-07-16 22:51:55,261][254037] Loop rollout_proc4_evt_loop terminating... +[2023-07-16 22:51:55,261][254035] Loop rollout_proc1_evt_loop terminating... +[2023-07-16 22:51:55,261][254039] Loop rollout_proc5_evt_loop terminating... +[2023-07-16 22:51:55,261][254034] Loop rollout_proc0_evt_loop terminating... +[2023-07-16 22:51:55,261][254036] Loop rollout_proc2_evt_loop terminating... +[2023-07-16 22:51:55,261][254038] Stopping RolloutWorker_w3... +[2023-07-16 22:51:55,261][254040] Loop rollout_proc6_evt_loop terminating... +[2023-07-16 22:51:55,261][254134] Loop rollout_proc7_evt_loop terminating... +[2023-07-16 22:51:55,261][253751] Component RolloutWorker_w4 stopped! +[2023-07-16 22:51:55,262][254038] Loop rollout_proc3_evt_loop terminating... +[2023-07-16 22:51:55,262][253751] Component RolloutWorker_w1 stopped! +[2023-07-16 22:51:55,262][253989] Stopping Batcher_0... +[2023-07-16 22:51:55,262][253751] Component RolloutWorker_w5 stopped! +[2023-07-16 22:51:55,262][253989] Loop batcher_evt_loop terminating... +[2023-07-16 22:51:55,262][253751] Component RolloutWorker_w2 stopped! +[2023-07-16 22:51:55,262][253751] Component RolloutWorker_w6 stopped! +[2023-07-16 22:51:55,263][253751] Component RolloutWorker_w0 stopped! +[2023-07-16 22:51:55,263][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... +[2023-07-16 22:51:55,263][253751] Component RolloutWorker_w7 stopped! +[2023-07-16 22:51:55,263][253751] Component RolloutWorker_w3 stopped! +[2023-07-16 22:51:55,263][253751] Component Batcher_0 stopped! +[2023-07-16 22:51:55,265][253989] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000018856_9654272.pth +[2023-07-16 22:51:55,266][253989] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/door-unlock-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... +[2023-07-16 22:51:55,268][253989] Stopping LearnerWorker_p0... +[2023-07-16 22:51:55,268][253989] Loop learner_proc0_evt_loop terminating... +[2023-07-16 22:51:55,268][253751] Component LearnerWorker_p0 stopped! +[2023-07-16 22:51:55,328][254033] Weights refcount: 2 0 +[2023-07-16 22:51:55,329][254033] Stopping InferenceWorker_p0-w0... +[2023-07-16 22:51:55,329][254033] Loop inference_proc0-0_evt_loop terminating... +[2023-07-16 22:51:55,329][253751] Component InferenceWorker_p0-w0 stopped! +[2023-07-16 22:51:55,330][253751] Waiting for process learner_proc0 to stop... +[2023-07-16 22:51:55,842][253751] Waiting for process inference_proc0-0 to join... +[2023-07-16 22:51:55,867][253751] Waiting for process rollout_proc0 to join... +[2023-07-16 22:51:55,867][253751] Waiting for process rollout_proc1 to join... +[2023-07-16 22:51:55,868][253751] Waiting for process rollout_proc2 to join... +[2023-07-16 22:51:55,868][253751] Waiting for process rollout_proc3 to join... +[2023-07-16 22:51:55,868][253751] Waiting for process rollout_proc4 to join... +[2023-07-16 22:51:55,868][253751] Waiting for process rollout_proc5 to join... +[2023-07-16 22:51:55,868][253751] Waiting for process rollout_proc6 to join... +[2023-07-16 22:51:55,868][253751] Waiting for process rollout_proc7 to join... +[2023-07-16 22:51:55,869][253751] Batcher 0 profile tree view: +batching: 1.8568, releasing_batches: 1.6245 +[2023-07-16 22:51:55,869][253751] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0051 - wait_policy_total: 465.0201 -update_model: 13.9918 - weight_update: 0.0005 -one_step: 0.0008 - handle_policy_step: 622.6770 - deserialize: 25.8540, stack: 6.8356, obs_to_device_normalize: 111.9436, forward: 309.3683, send_messages: 44.8289 - prepare_outputs: 69.4085 - to_cpu: 10.8694 -[2023-07-08 17:45:20,060][1025936] Learner 0 profile tree view: -misc: 0.0109, prepare_batch: 8.3526 -train: 85.3222 - epoch_init: 0.0336, minibatch_init: 1.2020, losses_postprocess: 1.2394, kl_divergence: 0.4047, after_optimizer: 0.6101 - calculate_losses: 35.9799 - losses_init: 0.0328, forward_head: 13.7616, bptt_initial: 0.1242, bptt: 0.1254, tail: 10.4492, advantages_returns: 0.8146, losses: 9.4146 - update: 44.4178 - clip: 5.3235 -[2023-07-08 17:45:20,060][1025936] RolloutWorker_w0 profile tree view: -wait_for_trajectories: 0.4554, enqueue_policy_requests: 15.7278, env_step: 764.3083, overhead: 22.4302, complete_rollouts: 0.3963 -save_policy_outputs: 44.1752 - split_output_tensors: 15.1177 -[2023-07-08 17:45:20,061][1025936] RolloutWorker_w7 profile tree view: -wait_for_trajectories: 0.4288, enqueue_policy_requests: 14.7863, env_step: 741.4055, overhead: 21.6483, complete_rollouts: 0.3780 -save_policy_outputs: 41.9904 - split_output_tensors: 14.2581 -[2023-07-08 17:45:20,061][1025936] Loop Runner_EvtLoop terminating... -[2023-07-08 17:45:20,061][1025936] Runner profile tree view: -main_loop: 1182.0472 -[2023-07-08 17:45:20,061][1025936] Collected {0: 10006528}, FPS: 8465.4 + wait_policy_total: 269.2400 +update_model: 10.6669 + weight_update: 0.0004 +one_step: 0.0005 + handle_policy_step: 468.0648 + deserialize: 19.8522, stack: 4.8307, obs_to_device_normalize: 83.1915, forward: 230.3970, send_messages: 35.7453 + prepare_outputs: 53.8476 + to_cpu: 8.0845 +[2023-07-16 22:51:55,869][253751] Learner 0 profile tree view: +misc: 0.0113, prepare_batch: 10.2438 +train: 106.5894 + epoch_init: 0.0390, minibatch_init: 1.4635, losses_postprocess: 1.4114, kl_divergence: 0.4906, after_optimizer: 0.6572 + calculate_losses: 45.6649 + losses_init: 0.0394, forward_head: 17.8784, bptt_initial: 0.1581, bptt: 0.1461, tail: 12.8711, advantages_returns: 0.9809, losses: 12.0081 + update: 55.0847 + clip: 6.5240 +[2023-07-16 22:51:55,869][253751] RolloutWorker_w0 profile tree view: +wait_for_trajectories: 0.2992, enqueue_policy_requests: 12.3347, env_step: 527.4862, overhead: 20.1130, complete_rollouts: 0.3308 +save_policy_outputs: 38.9678 + split_output_tensors: 13.5177 +[2023-07-16 22:51:55,869][253751] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.2927, enqueue_policy_requests: 12.3820, env_step: 525.9642, overhead: 19.8251, complete_rollouts: 0.3172 +save_policy_outputs: 38.4461 + split_output_tensors: 13.2376 +[2023-07-16 22:51:55,870][253751] Loop Runner_EvtLoop terminating... +[2023-07-16 22:51:55,870][253751] Runner profile tree view: +main_loop: 805.8496 +[2023-07-16 22:51:55,870][253751] Collected {0: 10006528}, FPS: 12417.4