[2023-07-08 12:28:30,055][958585] Saving configuration to /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/config.json... [2023-07-08 12:28:30,078][958585] Rollout worker 0 uses device cpu [2023-07-08 12:28:30,078][958585] Rollout worker 1 uses device cpu [2023-07-08 12:28:30,078][958585] Rollout worker 2 uses device cpu [2023-07-08 12:28:30,079][958585] Rollout worker 3 uses device cpu [2023-07-08 12:28:30,079][958585] Rollout worker 4 uses device cpu [2023-07-08 12:28:30,079][958585] Rollout worker 5 uses device cpu [2023-07-08 12:28:30,079][958585] Rollout worker 6 uses device cpu [2023-07-08 12:28:30,079][958585] Rollout worker 7 uses device cpu [2023-07-08 12:28:30,079][958585] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 [2023-07-08 12:28:30,095][958585] InferenceWorker_p0-w0: min num requests: 2 [2023-07-08 12:28:30,119][958585] Starting all processes... [2023-07-08 12:28:30,120][958585] Starting process learner_proc0 [2023-07-08 12:28:30,169][958585] Starting all processes... [2023-07-08 12:28:30,206][958585] Starting process inference_proc0-0 [2023-07-08 12:28:30,207][958585] Starting process rollout_proc0 [2023-07-08 12:28:30,207][958585] Starting process rollout_proc1 [2023-07-08 12:28:30,207][958585] Starting process rollout_proc2 [2023-07-08 12:28:30,207][958585] Starting process rollout_proc3 [2023-07-08 12:28:30,207][958585] Starting process rollout_proc4 [2023-07-08 12:28:30,207][958585] Starting process rollout_proc5 [2023-07-08 12:28:30,208][958585] Starting process rollout_proc6 [2023-07-08 12:28:30,208][958585] Starting process rollout_proc7 [2023-07-08 12:28:32,105][958827] Starting seed is not provided [2023-07-08 12:28:32,122][958827] Initializing actor-critic model on device cpu [2023-07-08 12:28:32,123][958827] RunningMeanStd input shape: (39,) [2023-07-08 12:28:32,123][958827] RunningMeanStd input shape: (1,) [2023-07-08 12:28:32,182][958827] Created Actor Critic model with architecture: [2023-07-08 12:28:32,182][958827] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): MultiInputEncoder( (encoders): ModuleDict( (obs): MlpEncoder( (mlp_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=Tanh) (2): RecursiveScriptModule(original_name=Linear) (3): RecursiveScriptModule(original_name=Tanh) ) ) ) ) (core): ModelCoreIdentity() (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=64, out_features=1, bias=True) (action_parameterization): ActionParameterizationContinuousNonAdaptiveStddev( (distribution_linear): Linear(in_features=64, out_features=4, bias=True) ) ) [2023-07-08 12:28:32,357][958873] Worker 1 uses CPU cores [4, 5, 6, 7] [2023-07-08 12:28:32,405][958908] Worker 5 uses CPU cores [20, 21, 22, 23] [2023-07-08 12:28:32,514][958940] Worker 6 uses CPU cores [24, 25, 26, 27] [2023-07-08 12:28:32,517][958875] Worker 3 uses CPU cores [12, 13, 14, 15] [2023-07-08 12:28:32,517][958827] Using optimizer [2023-07-08 12:28:32,518][958827] No checkpoints found [2023-07-08 12:28:32,518][958827] Did not load from checkpoint, starting from scratch! [2023-07-08 12:28:32,518][958827] Initialized policy 0 weights for model version 0 [2023-07-08 12:28:32,519][958827] LearnerWorker_p0 finished initialization! [2023-07-08 12:28:32,749][958872] RunningMeanStd input shape: (39,) [2023-07-08 12:28:32,749][958872] RunningMeanStd input shape: (1,) [2023-07-08 12:28:32,804][958871] Worker 0 uses CPU cores [0, 1, 2, 3] [2023-07-08 12:28:32,807][958585] Inference worker 0-0 is ready! [2023-07-08 12:28:32,807][958585] All inference workers are ready! Signal rollout workers to start! [2023-07-08 12:28:32,999][958876] Worker 4 uses CPU cores [16, 17, 18, 19] [2023-07-08 12:28:33,021][958874] Worker 2 uses CPU cores [8, 9, 10, 11] [2023-07-08 12:28:33,224][958986] Worker 7 uses CPU cores [28, 29, 30, 31] [2023-07-08 12:28:36,922][958940] Decorrelating experience for 0 frames... [2023-07-08 12:28:36,936][958940] Decorrelating experience for 64 frames... [2023-07-08 12:28:36,948][958875] Decorrelating experience for 0 frames... [2023-07-08 12:28:36,962][958875] Decorrelating experience for 64 frames... [2023-07-08 12:28:36,974][958940] Decorrelating experience for 128 frames... [2023-07-08 12:28:36,993][958871] Decorrelating experience for 0 frames... [2023-07-08 12:28:36,999][958875] Decorrelating experience for 128 frames... [2023-07-08 12:28:37,006][958871] Decorrelating experience for 64 frames... [2023-07-08 12:28:37,043][958871] Decorrelating experience for 128 frames... [2023-07-08 12:28:37,049][958940] Decorrelating experience for 192 frames... [2023-07-08 12:28:37,057][958908] Decorrelating experience for 0 frames... [2023-07-08 12:28:37,070][958908] Decorrelating experience for 64 frames... [2023-07-08 12:28:37,072][958875] Decorrelating experience for 192 frames... [2023-07-08 12:28:37,107][958908] Decorrelating experience for 128 frames... [2023-07-08 12:28:37,117][958871] Decorrelating experience for 192 frames... [2023-07-08 12:28:37,123][958876] Decorrelating experience for 0 frames... [2023-07-08 12:28:37,136][958876] Decorrelating experience for 64 frames... [2023-07-08 12:28:37,173][958876] Decorrelating experience for 128 frames... [2023-07-08 12:28:37,181][958908] Decorrelating experience for 192 frames... [2023-07-08 12:28:37,234][958585] 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 12:28:37,247][958876] Decorrelating experience for 192 frames... [2023-07-08 12:28:37,313][958874] Decorrelating experience for 0 frames... [2023-07-08 12:28:37,327][958874] Decorrelating experience for 64 frames... [2023-07-08 12:28:37,358][958986] Decorrelating experience for 0 frames... [2023-07-08 12:28:37,364][958874] Decorrelating experience for 128 frames... [2023-07-08 12:28:37,381][958986] Decorrelating experience for 64 frames... [2023-07-08 12:28:37,429][958986] Decorrelating experience for 128 frames... [2023-07-08 12:28:37,439][958874] Decorrelating experience for 192 frames... [2023-07-08 12:28:37,503][958986] Decorrelating experience for 192 frames... [2023-07-08 12:28:37,517][958873] Decorrelating experience for 0 frames... [2023-07-08 12:28:37,538][958873] Decorrelating experience for 64 frames... [2023-07-08 12:28:37,592][958873] Decorrelating experience for 128 frames... [2023-07-08 12:28:37,693][958873] Decorrelating experience for 192 frames... [2023-07-08 12:28:41,117][958940] Decorrelating experience for 256 frames... [2023-07-08 12:28:41,141][958875] Decorrelating experience for 256 frames... [2023-07-08 12:28:41,172][958871] Decorrelating experience for 256 frames... [2023-07-08 12:28:41,251][958940] Decorrelating experience for 320 frames... [2023-07-08 12:28:41,270][958908] Decorrelating experience for 256 frames... [2023-07-08 12:28:41,276][958875] Decorrelating experience for 320 frames... [2023-07-08 12:28:41,307][958871] Decorrelating experience for 320 frames... [2023-07-08 12:28:41,312][958876] Decorrelating experience for 256 frames... [2023-07-08 12:28:41,404][958908] Decorrelating experience for 320 frames... [2023-07-08 12:28:41,424][958940] Decorrelating experience for 384 frames... [2023-07-08 12:28:41,448][958876] Decorrelating experience for 320 frames... [2023-07-08 12:28:41,448][958875] Decorrelating experience for 384 frames... [2023-07-08 12:28:41,477][958871] Decorrelating experience for 384 frames... [2023-07-08 12:28:41,525][958874] Decorrelating experience for 256 frames... [2023-07-08 12:28:41,544][958986] Decorrelating experience for 256 frames... [2023-07-08 12:28:41,575][958908] Decorrelating experience for 384 frames... [2023-07-08 12:28:41,619][958940] Decorrelating experience for 448 frames... [2023-07-08 12:28:41,619][958876] Decorrelating experience for 384 frames... [2023-07-08 12:28:41,643][958875] Decorrelating experience for 448 frames... [2023-07-08 12:28:41,660][958874] Decorrelating experience for 320 frames... [2023-07-08 12:28:41,669][958871] Decorrelating experience for 448 frames... [2023-07-08 12:28:41,678][958986] Decorrelating experience for 320 frames... [2023-07-08 12:28:41,769][958908] Decorrelating experience for 448 frames... [2023-07-08 12:28:41,814][958876] Decorrelating experience for 448 frames... [2023-07-08 12:28:41,831][958874] Decorrelating experience for 384 frames... [2023-07-08 12:28:41,846][958986] Decorrelating experience for 384 frames... [2023-07-08 12:28:42,030][958874] Decorrelating experience for 448 frames... [2023-07-08 12:28:42,040][958986] Decorrelating experience for 448 frames... [2023-07-08 12:28:42,234][958585] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 3.2. Samples: 16. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-07-08 12:28:42,235][958585] Avg episode reward: [(0, '0.343')] [2023-07-08 12:28:42,236][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000000_0.pth... [2023-07-08 12:28:42,484][958873] Decorrelating experience for 256 frames... [2023-07-08 12:28:42,617][958873] Decorrelating experience for 320 frames... [2023-07-08 12:28:42,785][958873] Decorrelating experience for 384 frames... [2023-07-08 12:28:42,978][958873] Decorrelating experience for 448 frames... [2023-07-08 12:28:47,234][958585] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3686.4). Total num frames: 36864. Throughput: 0: 1267.6. Samples: 12676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:28:47,235][958585] Avg episode reward: [(0, '6.049')] [2023-07-08 12:28:47,553][958872] Updated weights for policy 0, policy_version 80 (0.0005) [2023-07-08 12:28:50,088][958585] Heartbeat connected on Batcher_0 [2023-07-08 12:28:50,091][958585] Heartbeat connected on LearnerWorker_p0 [2023-07-08 12:28:50,096][958585] Heartbeat connected on InferenceWorker_p0-w0 [2023-07-08 12:28:50,098][958585] Heartbeat connected on RolloutWorker_w0 [2023-07-08 12:28:50,104][958585] Heartbeat connected on RolloutWorker_w1 [2023-07-08 12:28:50,106][958585] Heartbeat connected on RolloutWorker_w2 [2023-07-08 12:28:50,109][958585] Heartbeat connected on RolloutWorker_w3 [2023-07-08 12:28:50,112][958585] Heartbeat connected on RolloutWorker_w4 [2023-07-08 12:28:50,113][958585] Heartbeat connected on RolloutWorker_w5 [2023-07-08 12:28:50,117][958585] Heartbeat connected on RolloutWorker_w6 [2023-07-08 12:28:50,121][958585] Heartbeat connected on RolloutWorker_w7 [2023-07-08 12:28:51,601][958872] Updated weights for policy 0, policy_version 160 (0.0005) [2023-07-08 12:28:52,234][958585] Fps is (10 sec: 8601.7, 60 sec: 5734.4, 300 sec: 5734.4). Total num frames: 86016. Throughput: 0: 4870.7. Samples: 73060. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:28:52,235][958585] Avg episode reward: [(0, '7.978')] [2023-07-08 12:28:55,895][958872] Updated weights for policy 0, policy_version 240 (0.0005) [2023-07-08 12:28:57,234][958585] Fps is (10 sec: 9420.8, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 131072. Throughput: 0: 6563.4. Samples: 131268. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:28:57,235][958585] Avg episode reward: [(0, '9.084')] [2023-07-08 12:28:57,254][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000264_135168.pth... [2023-07-08 12:28:57,257][958827] Saving new best policy, reward=9.084! [2023-07-08 12:29:00,439][958872] Updated weights for policy 0, policy_version 320 (0.0006) [2023-07-08 12:29:02,234][958585] Fps is (10 sec: 9011.3, 60 sec: 7045.2, 300 sec: 7045.2). Total num frames: 176128. Throughput: 0: 6388.4. Samples: 159708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:29:02,234][958585] Avg episode reward: [(0, '17.205')] [2023-07-08 12:29:02,235][958827] Saving new best policy, reward=17.205! [2023-07-08 12:29:05,038][958872] Updated weights for policy 0, policy_version 400 (0.0005) [2023-07-08 12:29:07,234][958585] Fps is (10 sec: 9420.8, 60 sec: 7509.3, 300 sec: 7509.3). Total num frames: 225280. Throughput: 0: 7096.8. Samples: 212904. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-08 12:29:07,235][958585] Avg episode reward: [(0, '44.554')] [2023-07-08 12:29:07,235][958827] Saving new best policy, reward=44.554! [2023-07-08 12:29:09,085][958872] Updated weights for policy 0, policy_version 480 (0.0005) [2023-07-08 12:29:12,234][958585] Fps is (10 sec: 9420.8, 60 sec: 7723.9, 300 sec: 7723.9). Total num frames: 270336. Throughput: 0: 7723.9. Samples: 270336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:29:12,234][958585] Avg episode reward: [(0, '75.511')] [2023-07-08 12:29:12,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000528_270336.pth... [2023-07-08 12:29:12,238][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000000_0.pth [2023-07-08 12:29:12,239][958827] Saving new best policy, reward=75.511! [2023-07-08 12:29:13,569][958872] Updated weights for policy 0, policy_version 560 (0.0005) [2023-07-08 12:29:17,234][958585] Fps is (10 sec: 9830.3, 60 sec: 8089.6, 300 sec: 8089.6). Total num frames: 323584. Throughput: 0: 7475.4. Samples: 299016. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:29:17,235][958585] Avg episode reward: [(0, '77.641')] [2023-07-08 12:29:17,236][958827] Saving new best policy, reward=77.641! [2023-07-08 12:29:17,499][958872] Updated weights for policy 0, policy_version 640 (0.0005) [2023-07-08 12:29:22,071][958872] Updated weights for policy 0, policy_version 720 (0.0005) [2023-07-08 12:29:22,234][958585] Fps is (10 sec: 9830.4, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 368640. Throughput: 0: 7956.0. Samples: 358020. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-08 12:29:22,234][958585] Avg episode reward: [(0, '95.616')] [2023-07-08 12:29:22,235][958827] Saving new best policy, reward=95.616! [2023-07-08 12:29:26,043][958872] Updated weights for policy 0, policy_version 800 (0.0005) [2023-07-08 12:29:27,234][958585] Fps is (10 sec: 9830.5, 60 sec: 8437.8, 300 sec: 8437.8). Total num frames: 421888. Throughput: 0: 9308.1. Samples: 418880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:29:27,235][958585] Avg episode reward: [(0, '108.504')] [2023-07-08 12:29:27,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000824_421888.pth... [2023-07-08 12:29:27,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000264_135168.pth [2023-07-08 12:29:27,241][958827] Saving new best policy, reward=108.504! [2023-07-08 12:29:30,005][958872] Updated weights for policy 0, policy_version 880 (0.0006) [2023-07-08 12:29:32,234][958585] Fps is (10 sec: 10239.9, 60 sec: 8564.4, 300 sec: 8564.4). Total num frames: 471040. Throughput: 0: 9703.1. Samples: 449316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:29:32,235][958585] Avg episode reward: [(0, '115.504')] [2023-07-08 12:29:32,235][958827] Saving new best policy, reward=115.504! [2023-07-08 12:29:34,342][958872] Updated weights for policy 0, policy_version 960 (0.0005) [2023-07-08 12:29:37,234][958585] Fps is (10 sec: 9420.9, 60 sec: 8601.6, 300 sec: 8601.6). Total num frames: 516096. Throughput: 0: 9604.9. Samples: 505280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:29:37,235][958585] Avg episode reward: [(0, '110.921')] [2023-07-08 12:29:38,759][958872] Updated weights for policy 0, policy_version 1040 (0.0005) [2023-07-08 12:29:42,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 8633.1). Total num frames: 561152. Throughput: 0: 9527.8. Samples: 560020. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-08 12:29:42,235][958585] Avg episode reward: [(0, '118.901')] [2023-07-08 12:29:42,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001096_561152.pth... [2023-07-08 12:29:42,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000528_270336.pth [2023-07-08 12:29:42,241][958827] Saving new best policy, reward=118.901! [2023-07-08 12:29:43,415][958872] Updated weights for policy 0, policy_version 1120 (0.0005) [2023-07-08 12:29:47,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 8718.6). Total num frames: 610304. Throughput: 0: 9482.7. Samples: 586432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:29:47,235][958585] Avg episode reward: [(0, '125.093')] [2023-07-08 12:29:47,236][958827] Saving new best policy, reward=125.093! [2023-07-08 12:29:47,563][958872] Updated weights for policy 0, policy_version 1200 (0.0006) [2023-07-08 12:29:51,676][958872] Updated weights for policy 0, policy_version 1280 (0.0006) [2023-07-08 12:29:52,234][958585] Fps is (10 sec: 9830.4, 60 sec: 9557.3, 300 sec: 8792.7). Total num frames: 659456. Throughput: 0: 9682.0. Samples: 648596. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-08 12:29:52,235][958585] Avg episode reward: [(0, '136.060')] [2023-07-08 12:29:52,236][958827] Saving new best policy, reward=136.060! [2023-07-08 12:29:55,798][958872] Updated weights for policy 0, policy_version 1360 (0.0005) [2023-07-08 12:29:57,234][958585] Fps is (10 sec: 9830.4, 60 sec: 9625.6, 300 sec: 8857.6). Total num frames: 708608. Throughput: 0: 9690.7. Samples: 706420. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:29:57,235][958585] Avg episode reward: [(0, '128.429')] [2023-07-08 12:29:57,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001384_708608.pth... [2023-07-08 12:29:57,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000000824_421888.pth [2023-07-08 12:30:00,083][958872] Updated weights for policy 0, policy_version 1440 (0.0005) [2023-07-08 12:30:02,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 8866.6). Total num frames: 753664. Throughput: 0: 9682.7. Samples: 734736. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:30:02,235][958585] Avg episode reward: [(0, '132.321')] [2023-07-08 12:30:04,424][958872] Updated weights for policy 0, policy_version 1520 (0.0006) [2023-07-08 12:30:07,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9625.6, 300 sec: 8920.2). Total num frames: 802816. Throughput: 0: 9661.4. Samples: 792784. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-08 12:30:07,235][958585] Avg episode reward: [(0, '145.851')] [2023-07-08 12:30:07,236][958827] Saving new best policy, reward=145.851! [2023-07-08 12:30:08,621][958872] Updated weights for policy 0, policy_version 1600 (0.0005) [2023-07-08 12:30:12,234][958585] Fps is (10 sec: 9830.3, 60 sec: 9693.8, 300 sec: 8968.1). Total num frames: 851968. Throughput: 0: 9555.2. Samples: 848864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:30:12,235][958585] Avg episode reward: [(0, '141.694')] [2023-07-08 12:30:12,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001664_851968.pth... [2023-07-08 12:30:12,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001096_561152.pth [2023-07-08 12:30:13,109][958872] Updated weights for policy 0, policy_version 1680 (0.0005) [2023-07-08 12:30:17,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9557.4, 300 sec: 8970.2). Total num frames: 897024. Throughput: 0: 9500.6. Samples: 876844. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:30:17,235][958585] Avg episode reward: [(0, '144.079')] [2023-07-08 12:30:17,459][958872] Updated weights for policy 0, policy_version 1760 (0.0005) [2023-07-08 12:30:22,012][958872] Updated weights for policy 0, policy_version 1840 (0.0006) [2023-07-08 12:30:22,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9557.3, 300 sec: 8972.2). Total num frames: 942080. Throughput: 0: 9495.5. Samples: 932576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:30:22,235][958585] Avg episode reward: [(0, '141.873')] [2023-07-08 12:30:26,713][958872] Updated weights for policy 0, policy_version 1920 (0.0005) [2023-07-08 12:30:27,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9420.8, 300 sec: 8974.0). Total num frames: 987136. Throughput: 0: 9426.8. Samples: 984228. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:30:27,235][958585] Avg episode reward: [(0, '147.850')] [2023-07-08 12:30:27,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001928_987136.pth... [2023-07-08 12:30:27,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001384_708608.pth [2023-07-08 12:30:27,241][958827] Saving new best policy, reward=147.850! [2023-07-08 12:30:31,119][958872] Updated weights for policy 0, policy_version 2000 (0.0005) [2023-07-08 12:30:32,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 8975.6). Total num frames: 1032192. Throughput: 0: 9452.3. Samples: 1011784. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:30:32,235][958585] Avg episode reward: [(0, '144.493')] [2023-07-08 12:30:35,719][958872] Updated weights for policy 0, policy_version 2080 (0.0006) [2023-07-08 12:30:37,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 8977.1). Total num frames: 1077248. Throughput: 0: 9272.7. Samples: 1065868. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:30:37,235][958585] Avg episode reward: [(0, '142.619')] [2023-07-08 12:30:40,161][958872] Updated weights for policy 0, policy_version 2160 (0.0005) [2023-07-08 12:30:42,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9352.5, 300 sec: 8978.4). Total num frames: 1122304. Throughput: 0: 9235.7. Samples: 1122028. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-08 12:30:42,235][958585] Avg episode reward: [(0, '142.458')] [2023-07-08 12:30:42,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002192_1122304.pth... [2023-07-08 12:30:42,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001664_851968.pth [2023-07-08 12:30:44,704][958872] Updated weights for policy 0, policy_version 2240 (0.0005) [2023-07-08 12:30:47,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 8979.7). Total num frames: 1167360. Throughput: 0: 9187.6. Samples: 1148176. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-08 12:30:47,235][958585] Avg episode reward: [(0, '147.358')] [2023-07-08 12:30:49,128][958872] Updated weights for policy 0, policy_version 2320 (0.0006) [2023-07-08 12:30:52,234][958585] Fps is (10 sec: 9420.9, 60 sec: 9284.3, 300 sec: 9011.2). Total num frames: 1216512. Throughput: 0: 9167.3. Samples: 1205312. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-08 12:30:52,235][958585] Avg episode reward: [(0, '145.494')] [2023-07-08 12:30:53,009][958872] Updated weights for policy 0, policy_version 2400 (0.0005) [2023-07-08 12:30:57,234][958585] Fps is (10 sec: 9830.2, 60 sec: 9284.2, 300 sec: 9040.5). Total num frames: 1265664. Throughput: 0: 9261.6. Samples: 1265636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:30:57,235][958585] Avg episode reward: [(0, '161.424')] [2023-07-08 12:30:57,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002472_1265664.pth... [2023-07-08 12:30:57,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000001928_987136.pth [2023-07-08 12:30:57,240][958827] Saving new best policy, reward=161.424! [2023-07-08 12:30:57,297][958872] Updated weights for policy 0, policy_version 2480 (0.0005) [2023-07-08 12:31:01,906][958872] Updated weights for policy 0, policy_version 2560 (0.0005) [2023-07-08 12:31:02,234][958585] Fps is (10 sec: 9420.9, 60 sec: 9284.3, 300 sec: 9039.5). Total num frames: 1310720. Throughput: 0: 9248.7. Samples: 1293036. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:31:02,234][958585] Avg episode reward: [(0, '174.971')] [2023-07-08 12:31:02,235][958827] Saving new best policy, reward=174.971! [2023-07-08 12:31:06,246][958872] Updated weights for policy 0, policy_version 2640 (0.0005) [2023-07-08 12:31:07,234][958585] Fps is (10 sec: 9011.4, 60 sec: 9216.0, 300 sec: 9038.5). Total num frames: 1355776. Throughput: 0: 9234.8. Samples: 1348140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:31:07,235][958585] Avg episode reward: [(0, '183.133')] [2023-07-08 12:31:07,250][958827] Saving new best policy, reward=183.133! [2023-07-08 12:31:10,747][958872] Updated weights for policy 0, policy_version 2720 (0.0005) [2023-07-08 12:31:12,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9064.1). Total num frames: 1404928. Throughput: 0: 9321.2. Samples: 1403680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:31:12,234][958585] Avg episode reward: [(0, '202.636')] [2023-07-08 12:31:12,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002744_1404928.pth... [2023-07-08 12:31:12,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002192_1122304.pth [2023-07-08 12:31:12,240][958827] Saving new best policy, reward=202.636! [2023-07-08 12:31:15,275][958872] Updated weights for policy 0, policy_version 2800 (0.0006) [2023-07-08 12:31:17,234][958585] Fps is (10 sec: 9420.7, 60 sec: 9216.0, 300 sec: 9062.4). Total num frames: 1449984. Throughput: 0: 9286.1. Samples: 1429660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:31:17,235][958585] Avg episode reward: [(0, '213.622')] [2023-07-08 12:31:17,236][958827] Saving new best policy, reward=213.622! [2023-07-08 12:31:19,739][958872] Updated weights for policy 0, policy_version 2880 (0.0005) [2023-07-08 12:31:22,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 9060.9). Total num frames: 1495040. Throughput: 0: 9305.7. Samples: 1484624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:31:22,235][958585] Avg episode reward: [(0, '227.793')] [2023-07-08 12:31:22,235][958827] Saving new best policy, reward=227.793! [2023-07-08 12:31:24,305][958872] Updated weights for policy 0, policy_version 2960 (0.0005) [2023-07-08 12:31:27,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 9059.4). Total num frames: 1540096. Throughput: 0: 9244.5. Samples: 1538032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:31:27,235][958585] Avg episode reward: [(0, '245.106')] [2023-07-08 12:31:27,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003008_1540096.pth... [2023-07-08 12:31:27,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002472_1265664.pth [2023-07-08 12:31:27,241][958827] Saving new best policy, reward=245.106! [2023-07-08 12:31:28,962][958872] Updated weights for policy 0, policy_version 3040 (0.0005) [2023-07-08 12:31:32,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9058.0). Total num frames: 1585152. Throughput: 0: 9257.1. Samples: 1564744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:31:32,235][958585] Avg episode reward: [(0, '254.667')] [2023-07-08 12:31:32,235][958827] Saving new best policy, reward=254.667! [2023-07-08 12:31:33,337][958872] Updated weights for policy 0, policy_version 3120 (0.0005) [2023-07-08 12:31:37,234][958585] Fps is (10 sec: 9421.0, 60 sec: 9284.3, 300 sec: 9079.5). Total num frames: 1634304. Throughput: 0: 9255.8. Samples: 1621824. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:31:37,234][958585] Avg episode reward: [(0, '245.629')] [2023-07-08 12:31:37,547][958872] Updated weights for policy 0, policy_version 3200 (0.0006) [2023-07-08 12:31:41,994][958872] Updated weights for policy 0, policy_version 3280 (0.0005) [2023-07-08 12:31:42,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9077.6). Total num frames: 1679360. Throughput: 0: 9174.3. Samples: 1678480. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:31:42,235][958585] Avg episode reward: [(0, '251.324')] [2023-07-08 12:31:42,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003280_1679360.pth... [2023-07-08 12:31:42,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000002744_1404928.pth [2023-07-08 12:31:46,380][958872] Updated weights for policy 0, policy_version 3360 (0.0005) [2023-07-08 12:31:47,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9284.3, 300 sec: 9075.9). Total num frames: 1724416. Throughput: 0: 9178.1. Samples: 1706052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:31:47,235][958585] Avg episode reward: [(0, '288.072')] [2023-07-08 12:31:47,276][958827] Saving new best policy, reward=288.072! [2023-07-08 12:31:50,962][958872] Updated weights for policy 0, policy_version 3440 (0.0006) [2023-07-08 12:31:52,234][958585] Fps is (10 sec: 9420.9, 60 sec: 9284.3, 300 sec: 9095.2). Total num frames: 1773568. Throughput: 0: 9173.2. Samples: 1760932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:31:52,235][958585] Avg episode reward: [(0, '330.430')] [2023-07-08 12:31:52,235][958827] Saving new best policy, reward=330.430! [2023-07-08 12:31:54,983][958872] Updated weights for policy 0, policy_version 3520 (0.0005) [2023-07-08 12:31:57,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9093.1). Total num frames: 1818624. Throughput: 0: 9221.0. Samples: 1818624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:31:57,235][958585] Avg episode reward: [(0, '319.703')] [2023-07-08 12:31:57,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003552_1818624.pth... [2023-07-08 12:31:57,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003008_1540096.pth [2023-07-08 12:31:59,515][958872] Updated weights for policy 0, policy_version 3600 (0.0005) [2023-07-08 12:32:02,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9111.1). Total num frames: 1867776. Throughput: 0: 9269.4. Samples: 1846784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:32:02,235][958585] Avg episode reward: [(0, '331.247')] [2023-07-08 12:32:02,235][958827] Saving new best policy, reward=331.247! [2023-07-08 12:32:03,993][958872] Updated weights for policy 0, policy_version 3680 (0.0005) [2023-07-08 12:32:07,234][958585] Fps is (10 sec: 9420.9, 60 sec: 9284.3, 300 sec: 9108.7). Total num frames: 1912832. Throughput: 0: 9253.1. Samples: 1901012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:32:07,235][958585] Avg episode reward: [(0, '358.442')] [2023-07-08 12:32:07,235][958827] Saving new best policy, reward=358.442! [2023-07-08 12:32:08,566][958872] Updated weights for policy 0, policy_version 3760 (0.0005) [2023-07-08 12:32:12,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9106.5). Total num frames: 1957888. Throughput: 0: 9318.0. Samples: 1957340. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:32:12,235][958585] Avg episode reward: [(0, '375.087')] [2023-07-08 12:32:12,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003824_1957888.pth... [2023-07-08 12:32:12,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003280_1679360.pth [2023-07-08 12:32:12,241][958827] Saving new best policy, reward=375.087! [2023-07-08 12:32:12,870][958872] Updated weights for policy 0, policy_version 3840 (0.0005) [2023-07-08 12:32:17,073][958872] Updated weights for policy 0, policy_version 3920 (0.0005) [2023-07-08 12:32:17,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9122.9). Total num frames: 2007040. Throughput: 0: 9328.9. Samples: 1984544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:32:17,234][958585] Avg episode reward: [(0, '373.296')] [2023-07-08 12:32:21,239][958872] Updated weights for policy 0, policy_version 4000 (0.0005) [2023-07-08 12:32:22,234][958585] Fps is (10 sec: 9830.4, 60 sec: 9352.5, 300 sec: 9138.6). Total num frames: 2056192. Throughput: 0: 9400.4. Samples: 2044844. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:32:22,235][958585] Avg episode reward: [(0, '400.939')] [2023-07-08 12:32:22,235][958827] Saving new best policy, reward=400.939! [2023-07-08 12:32:25,525][958872] Updated weights for policy 0, policy_version 4080 (0.0005) [2023-07-08 12:32:27,234][958585] Fps is (10 sec: 9420.7, 60 sec: 9352.5, 300 sec: 9135.9). Total num frames: 2101248. Throughput: 0: 9395.1. Samples: 2101260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:32:27,235][958585] Avg episode reward: [(0, '408.183')] [2023-07-08 12:32:27,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004104_2101248.pth... [2023-07-08 12:32:27,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003552_1818624.pth [2023-07-08 12:32:27,241][958827] Saving new best policy, reward=408.183! [2023-07-08 12:32:30,100][958872] Updated weights for policy 0, policy_version 4160 (0.0005) [2023-07-08 12:32:32,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9352.6, 300 sec: 9133.2). Total num frames: 2146304. Throughput: 0: 9389.6. Samples: 2128584. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:32:32,234][958585] Avg episode reward: [(0, '435.388')] [2023-07-08 12:32:32,235][958827] Saving new best policy, reward=435.388! [2023-07-08 12:32:34,852][958872] Updated weights for policy 0, policy_version 4240 (0.0006) [2023-07-08 12:32:37,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9284.2, 300 sec: 9130.7). Total num frames: 2191360. Throughput: 0: 9298.6. Samples: 2179368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:32:37,235][958585] Avg episode reward: [(0, '465.765')] [2023-07-08 12:32:37,236][958827] Saving new best policy, reward=465.765! [2023-07-08 12:32:39,301][958872] Updated weights for policy 0, policy_version 4320 (0.0005) [2023-07-08 12:32:42,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9284.3, 300 sec: 9128.2). Total num frames: 2236416. Throughput: 0: 9266.1. Samples: 2235596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:32:42,235][958585] Avg episode reward: [(0, '481.350')] [2023-07-08 12:32:42,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004368_2236416.pth... [2023-07-08 12:32:42,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000003824_1957888.pth [2023-07-08 12:32:42,241][958827] Saving new best policy, reward=481.350! [2023-07-08 12:32:43,887][958872] Updated weights for policy 0, policy_version 4400 (0.0005) [2023-07-08 12:32:47,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9284.3, 300 sec: 9125.9). Total num frames: 2281472. Throughput: 0: 9209.4. Samples: 2261204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:32:47,234][958585] Avg episode reward: [(0, '473.005')] [2023-07-08 12:32:48,591][958872] Updated weights for policy 0, policy_version 4480 (0.0006) [2023-07-08 12:32:52,234][958585] Fps is (10 sec: 8601.7, 60 sec: 9147.7, 300 sec: 9107.6). Total num frames: 2322432. Throughput: 0: 9180.1. Samples: 2314116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:32:52,235][958585] Avg episode reward: [(0, '462.749')] [2023-07-08 12:32:53,230][958872] Updated weights for policy 0, policy_version 4560 (0.0005) [2023-07-08 12:32:57,234][958585] Fps is (10 sec: 8601.6, 60 sec: 9147.8, 300 sec: 9105.7). Total num frames: 2367488. Throughput: 0: 9093.3. Samples: 2366536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:32:57,234][958585] Avg episode reward: [(0, '497.138')] [2023-07-08 12:32:57,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004624_2367488.pth... [2023-07-08 12:32:57,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004104_2101248.pth [2023-07-08 12:32:57,240][958827] Saving new best policy, reward=497.138! [2023-07-08 12:32:57,972][958872] Updated weights for policy 0, policy_version 4640 (0.0006) [2023-07-08 12:33:02,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9103.9). Total num frames: 2412544. Throughput: 0: 9062.9. Samples: 2392376. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:33:02,235][958585] Avg episode reward: [(0, '487.885')] [2023-07-08 12:33:02,669][958872] Updated weights for policy 0, policy_version 4720 (0.0005) [2023-07-08 12:33:03,118][958827] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000010 [2023-07-08 12:33:07,234][958585] Fps is (10 sec: 8601.6, 60 sec: 9011.2, 300 sec: 9087.1). Total num frames: 2453504. Throughput: 0: 8880.7. Samples: 2444476. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:33:07,235][958585] Avg episode reward: [(0, '470.053')] [2023-07-08 12:33:07,386][958872] Updated weights for policy 0, policy_version 4800 (0.0005) [2023-07-08 12:33:12,234][958585] Fps is (10 sec: 8192.1, 60 sec: 8942.9, 300 sec: 9070.8). Total num frames: 2494464. Throughput: 0: 8740.1. Samples: 2494564. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:33:12,234][958585] Avg episode reward: [(0, '483.717')] [2023-07-08 12:33:12,265][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004880_2498560.pth... [2023-07-08 12:33:12,266][958872] Updated weights for policy 0, policy_version 4880 (0.0005) [2023-07-08 12:33:12,267][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004368_2236416.pth [2023-07-08 12:33:16,984][958872] Updated weights for policy 0, policy_version 4960 (0.0005) [2023-07-08 12:33:17,234][958585] Fps is (10 sec: 8601.6, 60 sec: 8874.7, 300 sec: 9069.7). Total num frames: 2539520. Throughput: 0: 8724.5. Samples: 2521188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:33:17,235][958585] Avg episode reward: [(0, '490.403')] [2023-07-08 12:33:21,470][958872] Updated weights for policy 0, policy_version 5040 (0.0005) [2023-07-08 12:33:22,234][958585] Fps is (10 sec: 9011.1, 60 sec: 8806.4, 300 sec: 9068.7). Total num frames: 2584576. Throughput: 0: 8779.0. Samples: 2574424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:33:22,235][958585] Avg episode reward: [(0, '470.193')] [2023-07-08 12:33:25,988][958872] Updated weights for policy 0, policy_version 5120 (0.0005) [2023-07-08 12:33:27,234][958585] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 9067.7). Total num frames: 2629632. Throughput: 0: 8757.8. Samples: 2629696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:33:27,235][958585] Avg episode reward: [(0, '518.158')] [2023-07-08 12:33:27,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005136_2629632.pth... [2023-07-08 12:33:27,239][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004624_2367488.pth [2023-07-08 12:33:27,239][958827] Saving new best policy, reward=518.158! [2023-07-08 12:33:30,593][958872] Updated weights for policy 0, policy_version 5200 (0.0005) [2023-07-08 12:33:32,234][958585] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 9066.7). Total num frames: 2674688. Throughput: 0: 8772.5. Samples: 2655968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:33:32,235][958585] Avg episode reward: [(0, '521.083')] [2023-07-08 12:33:32,235][958827] Saving new best policy, reward=521.083! [2023-07-08 12:33:35,033][958872] Updated weights for policy 0, policy_version 5280 (0.0005) [2023-07-08 12:33:37,234][958585] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 9219.5). Total num frames: 2719744. Throughput: 0: 8817.1. Samples: 2710884. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-08 12:33:37,235][958585] Avg episode reward: [(0, '524.470')] [2023-07-08 12:33:37,235][958827] Saving new best policy, reward=524.470! [2023-07-08 12:33:39,842][958872] Updated weights for policy 0, policy_version 5360 (0.0005) [2023-07-08 12:33:42,234][958585] Fps is (10 sec: 8601.5, 60 sec: 8738.1, 300 sec: 9233.4). Total num frames: 2760704. Throughput: 0: 8766.6. Samples: 2761036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:33:42,235][958585] Avg episode reward: [(0, '524.912')] [2023-07-08 12:33:42,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005400_2764800.pth... [2023-07-08 12:33:42,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000004880_2498560.pth [2023-07-08 12:33:42,240][958827] Saving new best policy, reward=524.912! [2023-07-08 12:33:44,687][958872] Updated weights for policy 0, policy_version 5440 (0.0005) [2023-07-08 12:33:47,234][958585] Fps is (10 sec: 8601.5, 60 sec: 8738.1, 300 sec: 9219.5). Total num frames: 2805760. Throughput: 0: 8766.5. Samples: 2786868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:33:47,235][958585] Avg episode reward: [(0, '540.196')] [2023-07-08 12:33:47,235][958827] Saving new best policy, reward=540.196! [2023-07-08 12:33:49,169][958872] Updated weights for policy 0, policy_version 5520 (0.0005) [2023-07-08 12:33:52,234][958585] Fps is (10 sec: 9011.3, 60 sec: 8806.4, 300 sec: 9219.5). Total num frames: 2850816. Throughput: 0: 8814.3. Samples: 2841120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:33:52,235][958585] Avg episode reward: [(0, '531.464')] [2023-07-08 12:33:53,654][958872] Updated weights for policy 0, policy_version 5600 (0.0005) [2023-07-08 12:33:57,234][958585] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 9219.5). Total num frames: 2895872. Throughput: 0: 8919.4. Samples: 2895936. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:33:57,362][958585] Avg episode reward: [(0, '543.048')] [2023-07-08 12:33:57,367][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005664_2899968.pth... [2023-07-08 12:33:57,370][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005136_2629632.pth [2023-07-08 12:33:57,370][958827] Saving new best policy, reward=543.048! [2023-07-08 12:33:58,325][958872] Updated weights for policy 0, policy_version 5680 (0.0005) [2023-07-08 12:34:02,234][958585] Fps is (10 sec: 8601.6, 60 sec: 8738.2, 300 sec: 9191.7). Total num frames: 2936832. Throughput: 0: 8887.1. Samples: 2921108. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:34:02,234][958585] Avg episode reward: [(0, '547.185')] [2023-07-08 12:34:02,254][958827] Saving new best policy, reward=547.185! [2023-07-08 12:34:03,183][958872] Updated weights for policy 0, policy_version 5760 (0.0005) [2023-07-08 12:34:07,234][958585] Fps is (10 sec: 8601.7, 60 sec: 8806.4, 300 sec: 9191.7). Total num frames: 2981888. Throughput: 0: 8843.8. Samples: 2972396. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:34:07,234][958585] Avg episode reward: [(0, '524.879')] [2023-07-08 12:34:07,659][958872] Updated weights for policy 0, policy_version 5840 (0.0005) [2023-07-08 12:34:12,082][958872] Updated weights for policy 0, policy_version 5920 (0.0005) [2023-07-08 12:34:12,234][958585] Fps is (10 sec: 9420.6, 60 sec: 8942.9, 300 sec: 9177.8). Total num frames: 3031040. Throughput: 0: 8871.0. Samples: 3028892. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:34:12,235][958585] Avg episode reward: [(0, '491.275')] [2023-07-08 12:34:12,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005920_3031040.pth... [2023-07-08 12:34:12,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005400_2764800.pth [2023-07-08 12:34:16,687][958872] Updated weights for policy 0, policy_version 6000 (0.0006) [2023-07-08 12:34:17,234][958585] Fps is (10 sec: 9420.7, 60 sec: 8942.9, 300 sec: 9177.8). Total num frames: 3076096. Throughput: 0: 8872.6. Samples: 3055236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:34:17,235][958585] Avg episode reward: [(0, '500.544')] [2023-07-08 12:34:21,374][958872] Updated weights for policy 0, policy_version 6080 (0.0005) [2023-07-08 12:34:22,234][958585] Fps is (10 sec: 8601.8, 60 sec: 8874.7, 300 sec: 9136.2). Total num frames: 3117056. Throughput: 0: 8840.3. Samples: 3108696. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-08 12:34:22,234][958585] Avg episode reward: [(0, '521.972')] [2023-07-08 12:34:26,005][958872] Updated weights for policy 0, policy_version 6160 (0.0005) [2023-07-08 12:34:27,234][958585] Fps is (10 sec: 8601.6, 60 sec: 8874.7, 300 sec: 9122.3). Total num frames: 3162112. Throughput: 0: 8914.4. Samples: 3162184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:34:27,235][958585] Avg episode reward: [(0, '525.113')] [2023-07-08 12:34:27,249][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006184_3166208.pth... [2023-07-08 12:34:27,250][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005664_2899968.pth [2023-07-08 12:34:30,026][958872] Updated weights for policy 0, policy_version 6240 (0.0005) [2023-07-08 12:34:32,234][958585] Fps is (10 sec: 9420.8, 60 sec: 8942.9, 300 sec: 9136.2). Total num frames: 3211264. Throughput: 0: 9028.8. Samples: 3193164. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-08 12:34:32,235][958585] Avg episode reward: [(0, '515.631')] [2023-07-08 12:34:34,594][958872] Updated weights for policy 0, policy_version 6320 (0.0005) [2023-07-08 12:34:37,234][958585] Fps is (10 sec: 9420.9, 60 sec: 8942.9, 300 sec: 9136.2). Total num frames: 3256320. Throughput: 0: 9002.8. Samples: 3246244. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-08 12:34:37,235][958585] Avg episode reward: [(0, '531.501')] [2023-07-08 12:34:39,270][958872] Updated weights for policy 0, policy_version 6400 (0.0005) [2023-07-08 12:34:42,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9122.3). Total num frames: 3301376. Throughput: 0: 9011.2. Samples: 3301440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:34:42,234][958585] Avg episode reward: [(0, '522.697')] [2023-07-08 12:34:42,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006448_3301376.pth... [2023-07-08 12:34:42,238][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000005920_3031040.pth [2023-07-08 12:34:43,797][958872] Updated weights for policy 0, policy_version 6480 (0.0005) [2023-07-08 12:34:47,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9108.4). Total num frames: 3346432. Throughput: 0: 9012.1. Samples: 3326652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:34:47,235][958585] Avg episode reward: [(0, '539.571')] [2023-07-08 12:34:48,724][958872] Updated weights for policy 0, policy_version 6560 (0.0005) [2023-07-08 12:34:52,234][958585] Fps is (10 sec: 8601.5, 60 sec: 8942.9, 300 sec: 9080.6). Total num frames: 3387392. Throughput: 0: 8996.7. Samples: 3377248. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:34:52,235][958585] Avg episode reward: [(0, '544.857')] [2023-07-08 12:34:53,286][958872] Updated weights for policy 0, policy_version 6640 (0.0005) [2023-07-08 12:34:57,234][958585] Fps is (10 sec: 8192.0, 60 sec: 8874.7, 300 sec: 9066.7). Total num frames: 3428352. Throughput: 0: 8893.4. Samples: 3429092. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:34:57,234][958585] Avg episode reward: [(0, '559.769')] [2023-07-08 12:34:57,256][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006704_3432448.pth... [2023-07-08 12:34:57,258][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006184_3166208.pth [2023-07-08 12:34:57,258][958827] Saving new best policy, reward=559.769! [2023-07-08 12:34:58,167][958872] Updated weights for policy 0, policy_version 6720 (0.0005) [2023-07-08 12:35:02,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 9066.7). Total num frames: 3477504. Throughput: 0: 8911.6. Samples: 3456256. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-08 12:35:02,235][958585] Avg episode reward: [(0, '556.758')] [2023-07-08 12:35:02,422][958872] Updated weights for policy 0, policy_version 6800 (0.0005) [2023-07-08 12:35:06,859][958872] Updated weights for policy 0, policy_version 6880 (0.0005) [2023-07-08 12:35:07,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9011.2, 300 sec: 9052.9). Total num frames: 3522560. Throughput: 0: 9014.7. Samples: 3514356. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-08 12:35:07,235][958585] Avg episode reward: [(0, '556.570')] [2023-07-08 12:35:11,177][958872] Updated weights for policy 0, policy_version 6960 (0.0006) [2023-07-08 12:35:12,234][958585] Fps is (10 sec: 9420.7, 60 sec: 9011.2, 300 sec: 9066.7). Total num frames: 3571712. Throughput: 0: 9065.2. Samples: 3570116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:35:12,235][958585] Avg episode reward: [(0, '564.449')] [2023-07-08 12:35:12,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006976_3571712.pth... [2023-07-08 12:35:12,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006448_3301376.pth [2023-07-08 12:35:12,241][958827] Saving new best policy, reward=564.093! [2023-07-08 12:35:15,637][958872] Updated weights for policy 0, policy_version 7040 (0.0005) [2023-07-08 12:35:17,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9011.2, 300 sec: 9066.7). Total num frames: 3616768. Throughput: 0: 8971.4. Samples: 3596876. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-08 12:35:17,235][958585] Avg episode reward: [(0, '557.145')] [2023-07-08 12:35:20,447][958872] Updated weights for policy 0, policy_version 7120 (0.0005) [2023-07-08 12:35:22,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9079.4, 300 sec: 9066.7). Total num frames: 3661824. Throughput: 0: 8961.7. Samples: 3649524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:35:22,235][958585] Avg episode reward: [(0, '548.102')] [2023-07-08 12:35:24,851][958872] Updated weights for policy 0, policy_version 7200 (0.0005) [2023-07-08 12:35:27,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9066.7). Total num frames: 3706880. Throughput: 0: 8944.2. Samples: 3703932. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:35:27,235][958585] Avg episode reward: [(0, '560.545')] [2023-07-08 12:35:27,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007240_3706880.pth... [2023-07-08 12:35:27,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006704_3432448.pth [2023-07-08 12:35:29,552][958872] Updated weights for policy 0, policy_version 7280 (0.0006) [2023-07-08 12:35:32,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 9066.7). Total num frames: 3751936. Throughput: 0: 8974.8. Samples: 3730520. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:35:32,235][958585] Avg episode reward: [(0, '567.223')] [2023-07-08 12:35:32,235][958827] Saving new best policy, reward=567.223! [2023-07-08 12:35:34,014][958872] Updated weights for policy 0, policy_version 7360 (0.0005) [2023-07-08 12:35:37,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 9066.7). Total num frames: 3796992. Throughput: 0: 9116.0. Samples: 3787468. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:35:37,235][958585] Avg episode reward: [(0, '559.080')] [2023-07-08 12:35:38,268][958872] Updated weights for policy 0, policy_version 7440 (0.0005) [2023-07-08 12:35:42,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9066.7). Total num frames: 3842048. Throughput: 0: 9115.5. Samples: 3839288. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:35:42,235][958585] Avg episode reward: [(0, '569.610')] [2023-07-08 12:35:42,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007504_3842048.pth... [2023-07-08 12:35:42,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000006976_3571712.pth [2023-07-08 12:35:42,241][958827] Saving new best policy, reward=569.610! [2023-07-08 12:35:43,159][958872] Updated weights for policy 0, policy_version 7520 (0.0005) [2023-07-08 12:35:47,234][958585] Fps is (10 sec: 8601.6, 60 sec: 8942.9, 300 sec: 9039.0). Total num frames: 3883008. Throughput: 0: 9115.4. Samples: 3866448. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:35:47,235][958585] Avg episode reward: [(0, '565.602')] [2023-07-08 12:35:47,720][958872] Updated weights for policy 0, policy_version 7600 (0.0005) [2023-07-08 12:35:52,018][958872] Updated weights for policy 0, policy_version 7680 (0.0005) [2023-07-08 12:35:52,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9039.0). Total num frames: 3932160. Throughput: 0: 8988.5. Samples: 3918840. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:35:52,235][958585] Avg episode reward: [(0, '570.770')] [2023-07-08 12:35:52,235][958827] Saving new best policy, reward=570.770! [2023-07-08 12:35:56,627][958872] Updated weights for policy 0, policy_version 7760 (0.0005) [2023-07-08 12:35:57,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 9039.0). Total num frames: 3977216. Throughput: 0: 9004.6. Samples: 3975324. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:35:57,235][958585] Avg episode reward: [(0, '576.067')] [2023-07-08 12:35:57,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007768_3977216.pth... [2023-07-08 12:35:57,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007240_3706880.pth [2023-07-08 12:35:57,241][958827] Saving new best policy, reward=576.067! [2023-07-08 12:36:01,056][958872] Updated weights for policy 0, policy_version 7840 (0.0005) [2023-07-08 12:36:02,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9039.0). Total num frames: 4022272. Throughput: 0: 9027.8. Samples: 4003128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:36:02,235][958585] Avg episode reward: [(0, '577.574')] [2023-07-08 12:36:02,235][958827] Saving new best policy, reward=577.574! [2023-07-08 12:36:05,285][958872] Updated weights for policy 0, policy_version 7920 (0.0005) [2023-07-08 12:36:07,234][958585] Fps is (10 sec: 9830.5, 60 sec: 9216.0, 300 sec: 9052.9). Total num frames: 4075520. Throughput: 0: 9143.0. Samples: 4060956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:36:07,235][958585] Avg episode reward: [(0, '575.541')] [2023-07-08 12:36:09,228][958872] Updated weights for policy 0, policy_version 8000 (0.0006) [2023-07-08 12:36:12,234][958585] Fps is (10 sec: 10240.0, 60 sec: 9216.0, 300 sec: 9066.7). Total num frames: 4124672. Throughput: 0: 9272.3. Samples: 4121184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:36:12,235][958585] Avg episode reward: [(0, '565.115')] [2023-07-08 12:36:12,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008056_4124672.pth... [2023-07-08 12:36:12,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007504_3842048.pth [2023-07-08 12:36:13,287][958872] Updated weights for policy 0, policy_version 8080 (0.0005) [2023-07-08 12:36:17,234][958585] Fps is (10 sec: 9420.9, 60 sec: 9216.0, 300 sec: 9066.7). Total num frames: 4169728. Throughput: 0: 9348.3. Samples: 4151192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:36:17,234][958585] Avg episode reward: [(0, '571.662')] [2023-07-08 12:36:17,942][958872] Updated weights for policy 0, policy_version 8160 (0.0005) [2023-07-08 12:36:22,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9066.7). Total num frames: 4214784. Throughput: 0: 9252.3. Samples: 4203824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:36:22,235][958585] Avg episode reward: [(0, '577.469')] [2023-07-08 12:36:22,498][958872] Updated weights for policy 0, policy_version 8240 (0.0005) [2023-07-08 12:36:27,072][958872] Updated weights for policy 0, policy_version 8320 (0.0005) [2023-07-08 12:36:27,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 9066.7). Total num frames: 4259840. Throughput: 0: 9314.4. Samples: 4258436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:36:27,235][958585] Avg episode reward: [(0, '584.616')] [2023-07-08 12:36:27,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008320_4259840.pth... [2023-07-08 12:36:27,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000007768_3977216.pth [2023-07-08 12:36:27,240][958827] Saving new best policy, reward=584.616! [2023-07-08 12:36:31,726][958872] Updated weights for policy 0, policy_version 8400 (0.0004) [2023-07-08 12:36:32,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9216.0, 300 sec: 9052.9). Total num frames: 4304896. Throughput: 0: 9288.4. Samples: 4284424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:36:32,235][958585] Avg episode reward: [(0, '569.005')] [2023-07-08 12:36:36,348][958872] Updated weights for policy 0, policy_version 8480 (0.0005) [2023-07-08 12:36:37,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9216.0, 300 sec: 9052.9). Total num frames: 4349952. Throughput: 0: 9307.4. Samples: 4337672. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:36:37,235][958585] Avg episode reward: [(0, '575.993')] [2023-07-08 12:36:40,875][958872] Updated weights for policy 0, policy_version 8560 (0.0005) [2023-07-08 12:36:42,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 9052.9). Total num frames: 4395008. Throughput: 0: 9259.0. Samples: 4391980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:36:42,235][958585] Avg episode reward: [(0, '582.210')] [2023-07-08 12:36:42,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008584_4395008.pth... [2023-07-08 12:36:42,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008056_4124672.pth [2023-07-08 12:36:45,177][958872] Updated weights for policy 0, policy_version 8640 (0.0005) [2023-07-08 12:36:47,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9039.0). Total num frames: 4440064. Throughput: 0: 9277.3. Samples: 4420608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:36:47,235][958585] Avg episode reward: [(0, '574.294')] [2023-07-08 12:36:49,945][958872] Updated weights for policy 0, policy_version 8720 (0.0005) [2023-07-08 12:36:52,234][958585] Fps is (10 sec: 8601.7, 60 sec: 9147.7, 300 sec: 9025.1). Total num frames: 4481024. Throughput: 0: 9152.6. Samples: 4472824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:36:52,235][958585] Avg episode reward: [(0, '584.486')] [2023-07-08 12:36:54,732][958872] Updated weights for policy 0, policy_version 8800 (0.0005) [2023-07-08 12:36:57,234][958585] Fps is (10 sec: 8601.6, 60 sec: 9147.7, 300 sec: 9011.2). Total num frames: 4526080. Throughput: 0: 8949.6. Samples: 4523916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:36:57,235][958585] Avg episode reward: [(0, '573.382')] [2023-07-08 12:36:57,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008840_4526080.pth... [2023-07-08 12:36:57,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008320_4259840.pth [2023-07-08 12:36:59,305][958872] Updated weights for policy 0, policy_version 8880 (0.0005) [2023-07-08 12:37:02,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9147.7, 300 sec: 9011.2). Total num frames: 4571136. Throughput: 0: 8884.7. Samples: 4551004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:37:02,235][958585] Avg episode reward: [(0, '583.321')] [2023-07-08 12:37:03,681][958872] Updated weights for policy 0, policy_version 8960 (0.0005) [2023-07-08 12:37:07,234][958585] Fps is (10 sec: 9420.7, 60 sec: 9079.4, 300 sec: 9025.1). Total num frames: 4620288. Throughput: 0: 8984.9. Samples: 4608144. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-08 12:37:07,235][958585] Avg episode reward: [(0, '575.460')] [2023-07-08 12:37:08,098][958872] Updated weights for policy 0, policy_version 9040 (0.0005) [2023-07-08 12:37:12,234][958585] Fps is (10 sec: 9011.2, 60 sec: 8942.9, 300 sec: 8997.3). Total num frames: 4661248. Throughput: 0: 8953.0. Samples: 4661320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:37:12,239][958585] Avg episode reward: [(0, '580.702')] [2023-07-08 12:37:12,242][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009104_4661248.pth... [2023-07-08 12:37:12,244][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008584_4395008.pth [2023-07-08 12:37:12,838][958872] Updated weights for policy 0, policy_version 9120 (0.0005) [2023-07-08 12:37:17,234][958585] Fps is (10 sec: 8601.7, 60 sec: 8942.9, 300 sec: 8983.4). Total num frames: 4706304. Throughput: 0: 8938.2. Samples: 4686644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:37:17,236][958585] Avg episode reward: [(0, '580.627')] [2023-07-08 12:37:17,630][958872] Updated weights for policy 0, policy_version 9200 (0.0005) [2023-07-08 12:37:22,234][958585] Fps is (10 sec: 8601.6, 60 sec: 8874.7, 300 sec: 8969.5). Total num frames: 4747264. Throughput: 0: 8916.3. Samples: 4738908. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:37:22,235][958585] Avg episode reward: [(0, '582.632')] [2023-07-08 12:37:22,505][958872] Updated weights for policy 0, policy_version 9280 (0.0006) [2023-07-08 12:37:26,721][958872] Updated weights for policy 0, policy_version 9360 (0.0005) [2023-07-08 12:37:27,234][958585] Fps is (10 sec: 9011.1, 60 sec: 8942.9, 300 sec: 8983.4). Total num frames: 4796416. Throughput: 0: 8925.4. Samples: 4793624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:37:27,235][958585] Avg episode reward: [(0, '586.191')] [2023-07-08 12:37:27,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009368_4796416.pth... [2023-07-08 12:37:27,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000008840_4526080.pth [2023-07-08 12:37:27,240][958827] Saving new best policy, reward=586.191! [2023-07-08 12:37:31,110][958872] Updated weights for policy 0, policy_version 9440 (0.0005) [2023-07-08 12:37:32,234][958585] Fps is (10 sec: 9420.7, 60 sec: 8942.9, 300 sec: 8983.4). Total num frames: 4841472. Throughput: 0: 8934.9. Samples: 4822680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:37:32,235][958585] Avg episode reward: [(0, '595.505')] [2023-07-08 12:37:32,236][958827] Saving new best policy, reward=595.505! [2023-07-08 12:37:35,562][958872] Updated weights for policy 0, policy_version 9520 (0.0005) [2023-07-08 12:37:37,234][958585] Fps is (10 sec: 9420.9, 60 sec: 9011.2, 300 sec: 8997.3). Total num frames: 4890624. Throughput: 0: 8993.7. Samples: 4877540. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-08 12:37:37,258][958585] Avg episode reward: [(0, '580.447')] [2023-07-08 12:37:39,665][958872] Updated weights for policy 0, policy_version 9600 (0.0005) [2023-07-08 12:37:42,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9011.2, 300 sec: 8997.3). Total num frames: 4935680. Throughput: 0: 9150.3. Samples: 4935680. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-08 12:37:42,235][958585] Avg episode reward: [(0, '574.141')] [2023-07-08 12:37:42,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009640_4935680.pth... [2023-07-08 12:37:42,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009104_4661248.pth [2023-07-08 12:37:44,077][958872] Updated weights for policy 0, policy_version 9680 (0.0005) [2023-07-08 12:37:47,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 9025.1). Total num frames: 4984832. Throughput: 0: 9183.3. Samples: 4964252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:37:47,235][958585] Avg episode reward: [(0, '566.502')] [2023-07-08 12:37:48,330][958872] Updated weights for policy 0, policy_version 9760 (0.0005) [2023-07-08 12:37:52,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 9025.1). Total num frames: 5029888. Throughput: 0: 9151.7. Samples: 5019972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:37:52,235][958585] Avg episode reward: [(0, '578.827')] [2023-07-08 12:37:53,005][958872] Updated weights for policy 0, policy_version 9840 (0.0006) [2023-07-08 12:37:57,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9147.7, 300 sec: 9025.1). Total num frames: 5074944. Throughput: 0: 9164.6. Samples: 5073728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:37:57,235][958585] Avg episode reward: [(0, '580.725')] [2023-07-08 12:37:57,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009912_5074944.pth... [2023-07-08 12:37:57,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009368_4796416.pth [2023-07-08 12:37:57,514][958872] Updated weights for policy 0, policy_version 9920 (0.0005) [2023-07-08 12:38:01,698][958872] Updated weights for policy 0, policy_version 10000 (0.0005) [2023-07-08 12:38:02,234][958585] Fps is (10 sec: 9420.7, 60 sec: 9216.0, 300 sec: 9052.9). Total num frames: 5124096. Throughput: 0: 9235.6. Samples: 5102248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:38:02,235][958585] Avg episode reward: [(0, '585.904')] [2023-07-08 12:38:06,202][958872] Updated weights for policy 0, policy_version 10080 (0.0005) [2023-07-08 12:38:07,234][958585] Fps is (10 sec: 9420.9, 60 sec: 9147.8, 300 sec: 9066.7). Total num frames: 5169152. Throughput: 0: 9289.5. Samples: 5156936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:38:07,235][958585] Avg episode reward: [(0, '577.772')] [2023-07-08 12:38:10,611][958872] Updated weights for policy 0, policy_version 10160 (0.0005) [2023-07-08 12:38:12,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9216.0, 300 sec: 9066.7). Total num frames: 5214208. Throughput: 0: 9345.3. Samples: 5214164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:38:12,235][958585] Avg episode reward: [(0, '572.397')] [2023-07-08 12:38:12,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010184_5214208.pth... [2023-07-08 12:38:12,239][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009640_4935680.pth [2023-07-08 12:38:15,144][958872] Updated weights for policy 0, policy_version 10240 (0.0005) [2023-07-08 12:38:17,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9066.7). Total num frames: 5259264. Throughput: 0: 9277.2. Samples: 5240152. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:38:17,235][958585] Avg episode reward: [(0, '581.202')] [2023-07-08 12:38:19,603][958872] Updated weights for policy 0, policy_version 10320 (0.0005) [2023-07-08 12:38:22,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9284.3, 300 sec: 9066.7). Total num frames: 5304320. Throughput: 0: 9299.3. Samples: 5296008. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:38:22,235][958585] Avg episode reward: [(0, '572.054')] [2023-07-08 12:38:24,155][958872] Updated weights for policy 0, policy_version 10400 (0.0005) [2023-07-08 12:38:27,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9066.7). Total num frames: 5349376. Throughput: 0: 9193.3. Samples: 5349376. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:38:27,235][958585] Avg episode reward: [(0, '584.140')] [2023-07-08 12:38:27,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010448_5349376.pth... [2023-07-08 12:38:27,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000009912_5074944.pth [2023-07-08 12:38:28,690][958872] Updated weights for policy 0, policy_version 10480 (0.0005) [2023-07-08 12:38:32,234][958585] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9080.6). Total num frames: 5398528. Throughput: 0: 9202.0. Samples: 5378340. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:38:32,235][958585] Avg episode reward: [(0, '589.708')] [2023-07-08 12:38:33,028][958872] Updated weights for policy 0, policy_version 10560 (0.0005) [2023-07-08 12:38:37,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9094.5). Total num frames: 5443584. Throughput: 0: 9151.0. Samples: 5431768. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:38:37,235][958585] Avg episode reward: [(0, '580.360')] [2023-07-08 12:38:37,557][958872] Updated weights for policy 0, policy_version 10640 (0.0005) [2023-07-08 12:38:42,199][958872] Updated weights for policy 0, policy_version 10720 (0.0005) [2023-07-08 12:38:42,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9094.5). Total num frames: 5488640. Throughput: 0: 9162.8. Samples: 5486052. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:38:42,264][958585] Avg episode reward: [(0, '585.139')] [2023-07-08 12:38:42,267][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010720_5488640.pth... [2023-07-08 12:38:42,269][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010184_5214208.pth [2023-07-08 12:38:46,784][958872] Updated weights for policy 0, policy_version 10800 (0.0005) [2023-07-08 12:38:47,234][958585] Fps is (10 sec: 8601.6, 60 sec: 9079.5, 300 sec: 9080.6). Total num frames: 5529600. Throughput: 0: 9130.3. Samples: 5513108. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:38:47,259][958585] Avg episode reward: [(0, '586.167')] [2023-07-08 12:38:51,338][958872] Updated weights for policy 0, policy_version 10880 (0.0005) [2023-07-08 12:38:52,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9147.7, 300 sec: 9094.5). Total num frames: 5578752. Throughput: 0: 9102.0. Samples: 5566528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:38:52,235][958585] Avg episode reward: [(0, '588.986')] [2023-07-08 12:38:55,320][958872] Updated weights for policy 0, policy_version 10960 (0.0005) [2023-07-08 12:38:57,234][958585] Fps is (10 sec: 9830.3, 60 sec: 9216.0, 300 sec: 9122.3). Total num frames: 5627904. Throughput: 0: 9144.5. Samples: 5625668. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:38:57,235][958585] Avg episode reward: [(0, '587.458')] [2023-07-08 12:38:57,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010992_5627904.pth... [2023-07-08 12:38:57,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010448_5349376.pth [2023-07-08 12:38:59,830][958872] Updated weights for policy 0, policy_version 11040 (0.0006) [2023-07-08 12:39:02,234][958585] Fps is (10 sec: 9420.6, 60 sec: 9147.7, 300 sec: 9122.3). Total num frames: 5672960. Throughput: 0: 9164.2. Samples: 5652544. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:39:02,235][958585] Avg episode reward: [(0, '590.265')] [2023-07-08 12:39:04,450][958872] Updated weights for policy 0, policy_version 11120 (0.0005) [2023-07-08 12:39:07,234][958585] Fps is (10 sec: 8601.7, 60 sec: 9079.5, 300 sec: 9094.5). Total num frames: 5713920. Throughput: 0: 9105.2. Samples: 5705740. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:39:07,235][958585] Avg episode reward: [(0, '590.050')] [2023-07-08 12:39:09,004][958872] Updated weights for policy 0, policy_version 11200 (0.0006) [2023-07-08 12:39:12,234][958585] Fps is (10 sec: 9011.4, 60 sec: 9147.7, 300 sec: 9108.4). Total num frames: 5763072. Throughput: 0: 9126.2. Samples: 5760056. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:39:12,234][958585] Avg episode reward: [(0, '590.652')] [2023-07-08 12:39:12,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011256_5763072.pth... [2023-07-08 12:39:12,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010720_5488640.pth [2023-07-08 12:39:13,563][958872] Updated weights for policy 0, policy_version 11280 (0.0005) [2023-07-08 12:39:17,234][958585] Fps is (10 sec: 9420.7, 60 sec: 9147.7, 300 sec: 9122.3). Total num frames: 5808128. Throughput: 0: 9095.9. Samples: 5787656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:39:17,235][958585] Avg episode reward: [(0, '595.076')] [2023-07-08 12:39:17,880][958872] Updated weights for policy 0, policy_version 11360 (0.0005) [2023-07-08 12:39:22,149][958872] Updated weights for policy 0, policy_version 11440 (0.0005) [2023-07-08 12:39:22,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9136.2). Total num frames: 5857280. Throughput: 0: 9184.2. Samples: 5845056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:39:22,235][958585] Avg episode reward: [(0, '594.850')] [2023-07-08 12:39:26,514][958872] Updated weights for policy 0, policy_version 11520 (0.0005) [2023-07-08 12:39:27,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9122.3). Total num frames: 5902336. Throughput: 0: 9239.8. Samples: 5901844. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:39:27,235][958585] Avg episode reward: [(0, '590.328')] [2023-07-08 12:39:27,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011528_5902336.pth... [2023-07-08 12:39:27,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000010992_5627904.pth [2023-07-08 12:39:31,231][958872] Updated weights for policy 0, policy_version 11600 (0.0005) [2023-07-08 12:39:32,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9147.7, 300 sec: 9122.3). Total num frames: 5947392. Throughput: 0: 9197.1. Samples: 5926976. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:39:32,235][958585] Avg episode reward: [(0, '581.936')] [2023-07-08 12:39:35,902][958872] Updated weights for policy 0, policy_version 11680 (0.0005) [2023-07-08 12:39:37,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9147.7, 300 sec: 9122.3). Total num frames: 5992448. Throughput: 0: 9191.6. Samples: 5980148. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:39:37,234][958585] Avg episode reward: [(0, '590.307')] [2023-07-08 12:39:40,216][958872] Updated weights for policy 0, policy_version 11760 (0.0005) [2023-07-08 12:39:42,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9147.7, 300 sec: 9122.3). Total num frames: 6037504. Throughput: 0: 9114.7. Samples: 6035828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:39:42,235][958585] Avg episode reward: [(0, '590.096')] [2023-07-08 12:39:42,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011792_6037504.pth... [2023-07-08 12:39:42,239][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011256_5763072.pth [2023-07-08 12:39:44,905][958872] Updated weights for policy 0, policy_version 11840 (0.0005) [2023-07-08 12:39:47,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 9136.2). Total num frames: 6082560. Throughput: 0: 9100.8. Samples: 6062076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:39:47,235][958585] Avg episode reward: [(0, '589.227')] [2023-07-08 12:39:49,373][958872] Updated weights for policy 0, policy_version 11920 (0.0005) [2023-07-08 12:39:52,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9147.7, 300 sec: 9150.0). Total num frames: 6127616. Throughput: 0: 9190.5. Samples: 6119312. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:39:52,234][958585] Avg episode reward: [(0, '592.696')] [2023-07-08 12:39:53,547][958872] Updated weights for policy 0, policy_version 12000 (0.0005) [2023-07-08 12:39:57,234][958585] Fps is (10 sec: 9420.5, 60 sec: 9147.7, 300 sec: 9150.0). Total num frames: 6176768. Throughput: 0: 9189.9. Samples: 6173604. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:39:57,235][958585] Avg episode reward: [(0, '583.788')] [2023-07-08 12:39:57,239][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012064_6176768.pth... [2023-07-08 12:39:57,242][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011528_5902336.pth [2023-07-08 12:39:58,171][958872] Updated weights for policy 0, policy_version 12080 (0.0005) [2023-07-08 12:40:02,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9136.2). Total num frames: 6217728. Throughput: 0: 9188.2. Samples: 6201124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:40:02,235][958585] Avg episode reward: [(0, '595.644')] [2023-07-08 12:40:02,235][958827] Saving new best policy, reward=595.644! [2023-07-08 12:40:02,940][958872] Updated weights for policy 0, policy_version 12160 (0.0005) [2023-07-08 12:40:07,005][958872] Updated weights for policy 0, policy_version 12240 (0.0005) [2023-07-08 12:40:07,234][958585] Fps is (10 sec: 9011.5, 60 sec: 9216.0, 300 sec: 9136.2). Total num frames: 6266880. Throughput: 0: 9126.8. Samples: 6255764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:40:07,235][958585] Avg episode reward: [(0, '590.525')] [2023-07-08 12:40:11,170][958872] Updated weights for policy 0, policy_version 12320 (0.0005) [2023-07-08 12:40:12,234][958585] Fps is (10 sec: 9830.3, 60 sec: 9216.0, 300 sec: 9150.0). Total num frames: 6316032. Throughput: 0: 9150.2. Samples: 6313604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:40:12,235][958585] Avg episode reward: [(0, '593.636')] [2023-07-08 12:40:12,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012336_6316032.pth... [2023-07-08 12:40:12,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000011792_6037504.pth [2023-07-08 12:40:15,445][958872] Updated weights for policy 0, policy_version 12400 (0.0005) [2023-07-08 12:40:17,234][958585] Fps is (10 sec: 9830.4, 60 sec: 9284.3, 300 sec: 9163.9). Total num frames: 6365184. Throughput: 0: 9235.8. Samples: 6342588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:40:17,235][958585] Avg episode reward: [(0, '595.046')] [2023-07-08 12:40:19,910][958872] Updated weights for policy 0, policy_version 12480 (0.0005) [2023-07-08 12:40:22,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9147.7, 300 sec: 9150.1). Total num frames: 6406144. Throughput: 0: 9284.8. Samples: 6397964. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-08 12:40:22,234][958585] Avg episode reward: [(0, '601.774')] [2023-07-08 12:40:22,250][958827] Saving new best policy, reward=601.774! [2023-07-08 12:40:24,647][958872] Updated weights for policy 0, policy_version 12560 (0.0006) [2023-07-08 12:40:27,234][958585] Fps is (10 sec: 8601.6, 60 sec: 9147.7, 300 sec: 9150.0). Total num frames: 6451200. Throughput: 0: 9218.6. Samples: 6450664. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-08 12:40:27,235][958585] Avg episode reward: [(0, '600.155')] [2023-07-08 12:40:27,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012600_6451200.pth... [2023-07-08 12:40:27,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012064_6176768.pth [2023-07-08 12:40:29,323][958872] Updated weights for policy 0, policy_version 12640 (0.0005) [2023-07-08 12:40:32,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9163.9). Total num frames: 6500352. Throughput: 0: 9201.7. Samples: 6476152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:40:32,235][958585] Avg episode reward: [(0, '596.470')] [2023-07-08 12:40:33,319][958872] Updated weights for policy 0, policy_version 12720 (0.0005) [2023-07-08 12:40:37,234][958585] Fps is (10 sec: 9830.6, 60 sec: 9284.3, 300 sec: 9177.8). Total num frames: 6549504. Throughput: 0: 9305.5. Samples: 6538060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:40:37,234][958585] Avg episode reward: [(0, '591.400')] [2023-07-08 12:40:37,432][958872] Updated weights for policy 0, policy_version 12800 (0.0005) [2023-07-08 12:40:41,874][958872] Updated weights for policy 0, policy_version 12880 (0.0005) [2023-07-08 12:40:42,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9191.7). Total num frames: 6594560. Throughput: 0: 9355.0. Samples: 6594576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:40:42,235][958585] Avg episode reward: [(0, '592.257')] [2023-07-08 12:40:42,253][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012888_6598656.pth... [2023-07-08 12:40:42,254][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012336_6316032.pth [2023-07-08 12:40:46,354][958872] Updated weights for policy 0, policy_version 12960 (0.0005) [2023-07-08 12:40:47,234][958585] Fps is (10 sec: 9420.7, 60 sec: 9352.5, 300 sec: 9191.7). Total num frames: 6643712. Throughput: 0: 9380.2. Samples: 6623232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:40:47,235][958585] Avg episode reward: [(0, '592.998')] [2023-07-08 12:40:50,670][958872] Updated weights for policy 0, policy_version 13040 (0.0005) [2023-07-08 12:40:52,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9191.7). Total num frames: 6688768. Throughput: 0: 9388.7. Samples: 6678256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:40:52,235][958585] Avg episode reward: [(0, '596.897')] [2023-07-08 12:40:55,282][958872] Updated weights for policy 0, policy_version 13120 (0.0005) [2023-07-08 12:40:57,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9284.3, 300 sec: 9191.7). Total num frames: 6733824. Throughput: 0: 9288.4. Samples: 6731584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:40:57,235][958585] Avg episode reward: [(0, '601.912')] [2023-07-08 12:40:57,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013152_6733824.pth... [2023-07-08 12:40:57,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012600_6451200.pth [2023-07-08 12:40:57,242][958827] Saving new best policy, reward=601.912! [2023-07-08 12:40:59,821][958872] Updated weights for policy 0, policy_version 13200 (0.0005) [2023-07-08 12:41:02,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 9163.9). Total num frames: 6778880. Throughput: 0: 9241.9. Samples: 6758472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:41:02,235][958585] Avg episode reward: [(0, '587.646')] [2023-07-08 12:41:04,226][958872] Updated weights for policy 0, policy_version 13280 (0.0005) [2023-07-08 12:41:07,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9150.0). Total num frames: 6823936. Throughput: 0: 9242.2. Samples: 6813864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:41:07,235][958585] Avg episode reward: [(0, '602.444')] [2023-07-08 12:41:07,235][958827] Saving new best policy, reward=602.444! [2023-07-08 12:41:08,993][958872] Updated weights for policy 0, policy_version 13360 (0.0005) [2023-07-08 12:41:12,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 9150.0). Total num frames: 6868992. Throughput: 0: 9214.6. Samples: 6865320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:41:12,235][958585] Avg episode reward: [(0, '605.454')] [2023-07-08 12:41:12,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013416_6868992.pth... [2023-07-08 12:41:12,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000012888_6598656.pth [2023-07-08 12:41:12,241][958827] Saving new best policy, reward=605.454! [2023-07-08 12:41:13,739][958872] Updated weights for policy 0, policy_version 13440 (0.0005) [2023-07-08 12:41:17,234][958585] Fps is (10 sec: 8601.7, 60 sec: 9079.5, 300 sec: 9136.2). Total num frames: 6909952. Throughput: 0: 9187.9. Samples: 6889608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:41:17,235][958585] Avg episode reward: [(0, '603.476')] [2023-07-08 12:41:18,295][958872] Updated weights for policy 0, policy_version 13520 (0.0005) [2023-07-08 12:41:22,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9216.0, 300 sec: 9150.0). Total num frames: 6959104. Throughput: 0: 9083.4. Samples: 6946816. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:41:22,235][958585] Avg episode reward: [(0, '604.851')] [2023-07-08 12:41:22,619][958872] Updated weights for policy 0, policy_version 13600 (0.0005) [2023-07-08 12:41:26,856][958872] Updated weights for policy 0, policy_version 13680 (0.0005) [2023-07-08 12:41:27,234][958585] Fps is (10 sec: 9420.7, 60 sec: 9216.0, 300 sec: 9150.0). Total num frames: 7004160. Throughput: 0: 9101.8. Samples: 7004160. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:41:27,235][958585] Avg episode reward: [(0, '607.728')] [2023-07-08 12:41:27,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013680_7004160.pth... [2023-07-08 12:41:27,239][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013152_6733824.pth [2023-07-08 12:41:27,239][958827] Saving new best policy, reward=607.728! [2023-07-08 12:41:31,490][958872] Updated weights for policy 0, policy_version 13760 (0.0005) [2023-07-08 12:41:32,234][958585] Fps is (10 sec: 9420.9, 60 sec: 9216.0, 300 sec: 9163.9). Total num frames: 7053312. Throughput: 0: 9061.2. Samples: 7030984. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:41:32,235][958585] Avg episode reward: [(0, '598.265')] [2023-07-08 12:41:35,677][958872] Updated weights for policy 0, policy_version 13840 (0.0006) [2023-07-08 12:41:37,234][958585] Fps is (10 sec: 9420.9, 60 sec: 9147.7, 300 sec: 9163.9). Total num frames: 7098368. Throughput: 0: 9098.5. Samples: 7087688. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:41:37,234][958585] Avg episode reward: [(0, '602.684')] [2023-07-08 12:41:40,049][958872] Updated weights for policy 0, policy_version 13920 (0.0005) [2023-07-08 12:41:42,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9147.7, 300 sec: 9163.9). Total num frames: 7143424. Throughput: 0: 9150.8. Samples: 7143368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:41:42,234][958585] Avg episode reward: [(0, '607.202')] [2023-07-08 12:41:42,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013952_7143424.pth... [2023-07-08 12:41:42,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013416_6868992.pth [2023-07-08 12:41:44,730][958872] Updated weights for policy 0, policy_version 14000 (0.0006) [2023-07-08 12:41:47,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 7188480. Throughput: 0: 9121.1. Samples: 7168920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:41:47,235][958585] Avg episode reward: [(0, '598.709')] [2023-07-08 12:41:49,415][958872] Updated weights for policy 0, policy_version 14080 (0.0005) [2023-07-08 12:41:52,234][958585] Fps is (10 sec: 8601.5, 60 sec: 9011.2, 300 sec: 9163.9). Total num frames: 7229440. Throughput: 0: 9053.0. Samples: 7221248. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:41:52,235][958585] Avg episode reward: [(0, '604.753')] [2023-07-08 12:41:54,321][958872] Updated weights for policy 0, policy_version 14160 (0.0005) [2023-07-08 12:41:57,234][958585] Fps is (10 sec: 8601.6, 60 sec: 9011.2, 300 sec: 9163.9). Total num frames: 7274496. Throughput: 0: 9055.8. Samples: 7272828. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:41:57,235][958585] Avg episode reward: [(0, '595.626')] [2023-07-08 12:41:57,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014208_7274496.pth... [2023-07-08 12:41:57,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013680_7004160.pth [2023-07-08 12:41:58,879][958872] Updated weights for policy 0, policy_version 14240 (0.0005) [2023-07-08 12:42:02,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 9163.9). Total num frames: 7323648. Throughput: 0: 9104.4. Samples: 7299308. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-08 12:42:02,235][958585] Avg episode reward: [(0, '605.286')] [2023-07-08 12:42:03,008][958872] Updated weights for policy 0, policy_version 14320 (0.0005) [2023-07-08 12:42:07,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 7368704. Throughput: 0: 9167.7. Samples: 7359360. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-07-08 12:42:07,235][958585] Avg episode reward: [(0, '604.211')] [2023-07-08 12:42:07,488][958872] Updated weights for policy 0, policy_version 14400 (0.0005) [2023-07-08 12:42:12,113][958872] Updated weights for policy 0, policy_version 14480 (0.0005) [2023-07-08 12:42:12,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 7413760. Throughput: 0: 9049.4. Samples: 7411384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:42:12,235][958585] Avg episode reward: [(0, '598.328')] [2023-07-08 12:42:12,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014480_7413760.pth... [2023-07-08 12:42:12,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000013952_7143424.pth [2023-07-08 12:42:16,588][958872] Updated weights for policy 0, policy_version 14560 (0.0006) [2023-07-08 12:42:17,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9147.7, 300 sec: 9191.7). Total num frames: 7458816. Throughput: 0: 9045.4. Samples: 7438028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:42:17,235][958585] Avg episode reward: [(0, '598.621')] [2023-07-08 12:42:21,296][958872] Updated weights for policy 0, policy_version 14640 (0.0005) [2023-07-08 12:42:22,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 7503872. Throughput: 0: 8978.4. Samples: 7491716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:42:22,234][958585] Avg episode reward: [(0, '595.807')] [2023-07-08 12:42:25,692][958872] Updated weights for policy 0, policy_version 14720 (0.0005) [2023-07-08 12:42:27,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 7548928. Throughput: 0: 8993.6. Samples: 7548080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:42:27,235][958585] Avg episode reward: [(0, '602.441')] [2023-07-08 12:42:27,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014744_7548928.pth... [2023-07-08 12:42:27,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014208_7274496.pth [2023-07-08 12:42:29,989][958872] Updated weights for policy 0, policy_version 14800 (0.0005) [2023-07-08 12:42:32,234][958585] Fps is (10 sec: 9420.7, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 7598080. Throughput: 0: 9061.6. Samples: 7576692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:42:32,235][958585] Avg episode reward: [(0, '604.389')] [2023-07-08 12:42:34,488][958872] Updated weights for policy 0, policy_version 14880 (0.0005) [2023-07-08 12:42:37,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9163.9). Total num frames: 7639040. Throughput: 0: 9098.5. Samples: 7630680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:42:37,235][958585] Avg episode reward: [(0, '606.838')] [2023-07-08 12:42:39,096][958872] Updated weights for policy 0, policy_version 14960 (0.0004) [2023-07-08 12:42:42,234][958585] Fps is (10 sec: 8601.6, 60 sec: 9011.2, 300 sec: 9150.0). Total num frames: 7684096. Throughput: 0: 9114.5. Samples: 7682980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:42:42,235][958585] Avg episode reward: [(0, '607.748')] [2023-07-08 12:42:42,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015008_7684096.pth... [2023-07-08 12:42:42,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014480_7413760.pth [2023-07-08 12:42:42,241][958827] Saving new best policy, reward=607.748! [2023-07-08 12:42:43,795][958872] Updated weights for policy 0, policy_version 15040 (0.0005) [2023-07-08 12:42:47,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9150.0). Total num frames: 7729152. Throughput: 0: 9108.4. Samples: 7709184. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:42:47,235][958585] Avg episode reward: [(0, '607.805')] [2023-07-08 12:42:47,259][958827] Saving new best policy, reward=607.805! [2023-07-08 12:42:48,259][958872] Updated weights for policy 0, policy_version 15120 (0.0006) [2023-07-08 12:42:52,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9150.0). Total num frames: 7774208. Throughput: 0: 8975.3. Samples: 7763248. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:42:52,235][958585] Avg episode reward: [(0, '608.428')] [2023-07-08 12:42:52,235][958827] Saving new best policy, reward=608.428! [2023-07-08 12:42:53,135][958872] Updated weights for policy 0, policy_version 15200 (0.0005) [2023-07-08 12:42:57,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9136.2). Total num frames: 7819264. Throughput: 0: 9004.9. Samples: 7816604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:42:57,235][958585] Avg episode reward: [(0, '609.734')] [2023-07-08 12:42:57,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015272_7819264.pth... [2023-07-08 12:42:57,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000014744_7548928.pth [2023-07-08 12:42:57,241][958827] Saving new best policy, reward=609.734! [2023-07-08 12:42:57,614][958872] Updated weights for policy 0, policy_version 15280 (0.0005) [2023-07-08 12:43:02,234][958585] Fps is (10 sec: 8601.6, 60 sec: 8942.9, 300 sec: 9122.3). Total num frames: 7860224. Throughput: 0: 8972.2. Samples: 7841780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:43:02,235][958585] Avg episode reward: [(0, '608.598')] [2023-07-08 12:43:02,564][958872] Updated weights for policy 0, policy_version 15360 (0.0005) [2023-07-08 12:43:07,234][958585] Fps is (10 sec: 8192.1, 60 sec: 8874.7, 300 sec: 9108.4). Total num frames: 7901184. Throughput: 0: 8916.8. Samples: 7892972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:43:07,234][958585] Avg episode reward: [(0, '609.293')] [2023-07-08 12:43:07,286][958872] Updated weights for policy 0, policy_version 15440 (0.0005) [2023-07-08 12:43:12,066][958872] Updated weights for policy 0, policy_version 15520 (0.0005) [2023-07-08 12:43:12,234][958585] Fps is (10 sec: 8601.6, 60 sec: 8874.7, 300 sec: 9108.4). Total num frames: 7946240. Throughput: 0: 8827.5. Samples: 7945316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:43:12,235][958585] Avg episode reward: [(0, '606.651')] [2023-07-08 12:43:12,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015520_7946240.pth... [2023-07-08 12:43:12,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015008_7684096.pth [2023-07-08 12:43:16,807][958872] Updated weights for policy 0, policy_version 15600 (0.0005) [2023-07-08 12:43:17,234][958585] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 9094.5). Total num frames: 7987200. Throughput: 0: 8747.6. Samples: 7970332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:43:17,235][958585] Avg episode reward: [(0, '597.631')] [2023-07-08 12:43:21,373][958872] Updated weights for policy 0, policy_version 15680 (0.0005) [2023-07-08 12:43:22,234][958585] Fps is (10 sec: 8601.7, 60 sec: 8806.4, 300 sec: 9094.5). Total num frames: 8032256. Throughput: 0: 8739.1. Samples: 8023940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:43:22,235][958585] Avg episode reward: [(0, '599.488')] [2023-07-08 12:43:25,892][958872] Updated weights for policy 0, policy_version 15760 (0.0005) [2023-07-08 12:43:27,234][958585] Fps is (10 sec: 9011.2, 60 sec: 8806.4, 300 sec: 9080.6). Total num frames: 8077312. Throughput: 0: 8762.8. Samples: 8077304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:43:27,235][958585] Avg episode reward: [(0, '608.517')] [2023-07-08 12:43:27,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015776_8077312.pth... [2023-07-08 12:43:27,239][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015272_7819264.pth [2023-07-08 12:43:30,557][958872] Updated weights for policy 0, policy_version 15840 (0.0005) [2023-07-08 12:43:32,234][958585] Fps is (10 sec: 9011.1, 60 sec: 8738.1, 300 sec: 9080.6). Total num frames: 8122368. Throughput: 0: 8797.3. Samples: 8105064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:43:32,235][958585] Avg episode reward: [(0, '607.753')] [2023-07-08 12:43:35,260][958872] Updated weights for policy 0, policy_version 15920 (0.0006) [2023-07-08 12:43:37,234][958585] Fps is (10 sec: 9011.1, 60 sec: 8806.4, 300 sec: 9080.6). Total num frames: 8167424. Throughput: 0: 8730.1. Samples: 8156104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:43:37,235][958585] Avg episode reward: [(0, '607.891')] [2023-07-08 12:43:40,162][958872] Updated weights for policy 0, policy_version 16000 (0.0005) [2023-07-08 12:43:42,234][958585] Fps is (10 sec: 8601.6, 60 sec: 8738.1, 300 sec: 9080.6). Total num frames: 8208384. Throughput: 0: 8691.6. Samples: 8207724. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:43:42,235][958585] Avg episode reward: [(0, '606.151')] [2023-07-08 12:43:42,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016032_8208384.pth... [2023-07-08 12:43:42,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015520_7946240.pth [2023-07-08 12:43:44,890][958872] Updated weights for policy 0, policy_version 16080 (0.0005) [2023-07-08 12:43:47,234][958585] Fps is (10 sec: 8601.7, 60 sec: 8738.1, 300 sec: 9066.7). Total num frames: 8253440. Throughput: 0: 8688.4. Samples: 8232756. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-07-08 12:43:47,235][958585] Avg episode reward: [(0, '606.855')] [2023-07-08 12:43:49,230][958872] Updated weights for policy 0, policy_version 16160 (0.0005) [2023-07-08 12:43:52,234][958585] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 9052.9). Total num frames: 8298496. Throughput: 0: 8803.6. Samples: 8289132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:43:52,234][958585] Avg episode reward: [(0, '608.008')] [2023-07-08 12:43:53,770][958872] Updated weights for policy 0, policy_version 16240 (0.0005) [2023-07-08 12:43:57,234][958585] Fps is (10 sec: 9011.2, 60 sec: 8738.1, 300 sec: 9052.9). Total num frames: 8343552. Throughput: 0: 8824.4. Samples: 8342412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:43:57,235][958585] Avg episode reward: [(0, '610.594')] [2023-07-08 12:43:57,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016296_8343552.pth... [2023-07-08 12:43:57,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000015776_8077312.pth [2023-07-08 12:43:57,241][958827] Saving new best policy, reward=610.594! [2023-07-08 12:43:58,390][958872] Updated weights for policy 0, policy_version 16320 (0.0005) [2023-07-08 12:44:02,234][958585] Fps is (10 sec: 9011.1, 60 sec: 8806.4, 300 sec: 9066.7). Total num frames: 8388608. Throughput: 0: 8900.7. Samples: 8370864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:44:02,235][958585] Avg episode reward: [(0, '599.357')] [2023-07-08 12:44:02,789][958872] Updated weights for policy 0, policy_version 16400 (0.0005) [2023-07-08 12:44:07,234][958585] Fps is (10 sec: 9011.2, 60 sec: 8874.7, 300 sec: 9052.9). Total num frames: 8433664. Throughput: 0: 8918.9. Samples: 8425292. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:44:07,235][958585] Avg episode reward: [(0, '605.087')] [2023-07-08 12:44:07,305][958872] Updated weights for policy 0, policy_version 16480 (0.0005) [2023-07-08 12:44:11,443][958872] Updated weights for policy 0, policy_version 16560 (0.0005) [2023-07-08 12:44:12,234][958585] Fps is (10 sec: 9830.4, 60 sec: 9011.2, 300 sec: 9080.6). Total num frames: 8486912. Throughput: 0: 9012.8. Samples: 8482880. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:44:12,235][958585] Avg episode reward: [(0, '602.296')] [2023-07-08 12:44:12,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016576_8486912.pth... [2023-07-08 12:44:12,239][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016032_8208384.pth [2023-07-08 12:44:15,879][958872] Updated weights for policy 0, policy_version 16640 (0.0005) [2023-07-08 12:44:17,234][958585] Fps is (10 sec: 9830.3, 60 sec: 9079.5, 300 sec: 9066.7). Total num frames: 8531968. Throughput: 0: 9030.2. Samples: 8511424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:44:17,235][958585] Avg episode reward: [(0, '609.811')] [2023-07-08 12:44:20,322][958872] Updated weights for policy 0, policy_version 16720 (0.0005) [2023-07-08 12:44:22,234][958585] Fps is (10 sec: 8601.5, 60 sec: 9011.2, 300 sec: 9052.9). Total num frames: 8572928. Throughput: 0: 9082.1. Samples: 8564800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:44:22,235][958585] Avg episode reward: [(0, '593.769')] [2023-07-08 12:44:25,017][958872] Updated weights for policy 0, policy_version 16800 (0.0004) [2023-07-08 12:44:27,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9066.7). Total num frames: 8622080. Throughput: 0: 9141.2. Samples: 8619076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:44:27,234][958585] Avg episode reward: [(0, '598.261')] [2023-07-08 12:44:27,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016840_8622080.pth... [2023-07-08 12:44:27,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016296_8343552.pth [2023-07-08 12:44:29,392][958872] Updated weights for policy 0, policy_version 16880 (0.0005) [2023-07-08 12:44:32,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 9052.9). Total num frames: 8663040. Throughput: 0: 9198.0. Samples: 8646664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:44:32,234][958585] Avg episode reward: [(0, '612.016')] [2023-07-08 12:44:32,235][958827] Saving new best policy, reward=612.016! [2023-07-08 12:44:34,186][958872] Updated weights for policy 0, policy_version 16960 (0.0005) [2023-07-08 12:44:37,234][958585] Fps is (10 sec: 8601.6, 60 sec: 9011.2, 300 sec: 9052.9). Total num frames: 8708096. Throughput: 0: 9088.3. Samples: 8698104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:44:37,235][958585] Avg episode reward: [(0, '608.218')] [2023-07-08 12:44:38,970][958872] Updated weights for policy 0, policy_version 17040 (0.0006) [2023-07-08 12:44:42,234][958585] Fps is (10 sec: 8601.5, 60 sec: 9011.2, 300 sec: 9039.0). Total num frames: 8749056. Throughput: 0: 9038.0. Samples: 8749120. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:44:42,235][958585] Avg episode reward: [(0, '605.548')] [2023-07-08 12:44:42,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017088_8749056.pth... [2023-07-08 12:44:42,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016576_8486912.pth [2023-07-08 12:44:43,641][958872] Updated weights for policy 0, policy_version 17120 (0.0005) [2023-07-08 12:44:47,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9052.9). Total num frames: 8798208. Throughput: 0: 9040.9. Samples: 8777704. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-07-08 12:44:47,235][958585] Avg episode reward: [(0, '596.465')] [2023-07-08 12:44:48,041][958872] Updated weights for policy 0, policy_version 17200 (0.0005) [2023-07-08 12:44:52,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9079.4, 300 sec: 9039.0). Total num frames: 8843264. Throughput: 0: 9016.8. Samples: 8831048. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-08 12:44:52,235][958585] Avg episode reward: [(0, '607.702')] [2023-07-08 12:44:52,762][958872] Updated weights for policy 0, policy_version 17280 (0.0005) [2023-07-08 12:44:57,234][958585] Fps is (10 sec: 8601.6, 60 sec: 9011.2, 300 sec: 9039.0). Total num frames: 8884224. Throughput: 0: 8918.2. Samples: 8884200. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-08 12:44:57,235][958585] Avg episode reward: [(0, '600.899')] [2023-07-08 12:44:57,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017352_8884224.pth... [2023-07-08 12:44:57,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000016840_8622080.pth [2023-07-08 12:44:57,377][958872] Updated weights for policy 0, policy_version 17360 (0.0005) [2023-07-08 12:45:01,852][958872] Updated weights for policy 0, policy_version 17440 (0.0005) [2023-07-08 12:45:02,234][958585] Fps is (10 sec: 8601.6, 60 sec: 9011.2, 300 sec: 9025.1). Total num frames: 8929280. Throughput: 0: 8872.8. Samples: 8910700. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-07-08 12:45:02,235][958585] Avg episode reward: [(0, '608.594')] [2023-07-08 12:45:06,224][958872] Updated weights for policy 0, policy_version 17520 (0.0006) [2023-07-08 12:45:07,234][958585] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 9025.1). Total num frames: 8978432. Throughput: 0: 8920.2. Samples: 8966208. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-08 12:45:07,235][958585] Avg episode reward: [(0, '606.378')] [2023-07-08 12:45:10,794][958872] Updated weights for policy 0, policy_version 17600 (0.0005) [2023-07-08 12:45:12,234][958585] Fps is (10 sec: 9420.8, 60 sec: 8942.9, 300 sec: 9011.2). Total num frames: 9023488. Throughput: 0: 8929.7. Samples: 9020912. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-08 12:45:12,235][958585] Avg episode reward: [(0, '606.805')] [2023-07-08 12:45:12,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017624_9023488.pth... [2023-07-08 12:45:12,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017088_8749056.pth [2023-07-08 12:45:15,385][958872] Updated weights for policy 0, policy_version 17680 (0.0005) [2023-07-08 12:45:17,234][958585] Fps is (10 sec: 9011.2, 60 sec: 8942.9, 300 sec: 9025.1). Total num frames: 9068544. Throughput: 0: 8917.9. Samples: 9047968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:45:17,235][958585] Avg episode reward: [(0, '604.779')] [2023-07-08 12:45:19,893][958872] Updated weights for policy 0, policy_version 17760 (0.0005) [2023-07-08 12:45:22,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9025.1). Total num frames: 9113600. Throughput: 0: 8972.6. Samples: 9101872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:45:22,235][958585] Avg episode reward: [(0, '607.718')] [2023-07-08 12:45:24,275][958872] Updated weights for policy 0, policy_version 17840 (0.0005) [2023-07-08 12:45:27,234][958585] Fps is (10 sec: 9011.1, 60 sec: 8942.9, 300 sec: 9011.2). Total num frames: 9158656. Throughput: 0: 9034.7. Samples: 9155684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:45:27,235][958585] Avg episode reward: [(0, '611.200')] [2023-07-08 12:45:27,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017888_9158656.pth... [2023-07-08 12:45:27,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017352_8884224.pth [2023-07-08 12:45:29,167][958872] Updated weights for policy 0, policy_version 17920 (0.0005) [2023-07-08 12:45:32,234][958585] Fps is (10 sec: 8601.6, 60 sec: 8942.9, 300 sec: 8983.4). Total num frames: 9199616. Throughput: 0: 8951.0. Samples: 9180500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:45:32,235][958585] Avg episode reward: [(0, '608.975')] [2023-07-08 12:45:34,104][958872] Updated weights for policy 0, policy_version 18000 (0.0005) [2023-07-08 12:45:37,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 8997.3). Total num frames: 9248768. Throughput: 0: 8980.1. Samples: 9235152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:45:37,235][958585] Avg episode reward: [(0, '611.646')] [2023-07-08 12:45:37,947][958872] Updated weights for policy 0, policy_version 18080 (0.0005) [2023-07-08 12:45:41,944][958872] Updated weights for policy 0, policy_version 18160 (0.0005) [2023-07-08 12:45:42,234][958585] Fps is (10 sec: 9830.4, 60 sec: 9147.7, 300 sec: 8997.3). Total num frames: 9297920. Throughput: 0: 9192.4. Samples: 9297856. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:45:42,235][958585] Avg episode reward: [(0, '613.524')] [2023-07-08 12:45:42,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018160_9297920.pth... [2023-07-08 12:45:42,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017624_9023488.pth [2023-07-08 12:45:42,240][958827] Saving new best policy, reward=613.524! [2023-07-08 12:45:46,581][958872] Updated weights for policy 0, policy_version 18240 (0.0005) [2023-07-08 12:45:47,234][958585] Fps is (10 sec: 9420.9, 60 sec: 9079.5, 300 sec: 8997.3). Total num frames: 9342976. Throughput: 0: 9153.4. Samples: 9322604. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:45:47,235][958585] Avg episode reward: [(0, '613.511')] [2023-07-08 12:45:51,075][958872] Updated weights for policy 0, policy_version 18320 (0.0005) [2023-07-08 12:45:52,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 8997.3). Total num frames: 9388032. Throughput: 0: 9145.7. Samples: 9377764. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:45:52,235][958585] Avg episode reward: [(0, '613.881')] [2023-07-08 12:45:52,235][958827] Saving new best policy, reward=613.881! [2023-07-08 12:45:55,295][958872] Updated weights for policy 0, policy_version 18400 (0.0005) [2023-07-08 12:45:57,234][958585] Fps is (10 sec: 9420.7, 60 sec: 9216.0, 300 sec: 9011.2). Total num frames: 9437184. Throughput: 0: 9185.7. Samples: 9434268. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-08 12:45:57,235][958585] Avg episode reward: [(0, '615.805')] [2023-07-08 12:45:57,238][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018432_9437184.pth... [2023-07-08 12:45:57,241][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000017888_9158656.pth [2023-07-08 12:45:57,241][958827] Saving new best policy, reward=615.805! [2023-07-08 12:45:59,857][958872] Updated weights for policy 0, policy_version 18480 (0.0004) [2023-07-08 12:46:02,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9147.7, 300 sec: 8997.3). Total num frames: 9478144. Throughput: 0: 9195.8. Samples: 9461780. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-08 12:46:02,235][958585] Avg episode reward: [(0, '616.192')] [2023-07-08 12:46:02,235][958827] Saving new best policy, reward=616.192! [2023-07-08 12:46:04,648][958872] Updated weights for policy 0, policy_version 18560 (0.0004) [2023-07-08 12:46:07,234][958585] Fps is (10 sec: 8601.7, 60 sec: 9079.5, 300 sec: 8997.3). Total num frames: 9523200. Throughput: 0: 9180.5. Samples: 9514992. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-07-08 12:46:07,235][958585] Avg episode reward: [(0, '616.066')] [2023-07-08 12:46:09,150][958872] Updated weights for policy 0, policy_version 18640 (0.0005) [2023-07-08 12:46:12,234][958585] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9011.2). Total num frames: 9568256. Throughput: 0: 9124.4. Samples: 9566280. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:46:12,238][958585] Avg episode reward: [(0, '615.126')] [2023-07-08 12:46:12,241][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018688_9568256.pth... [2023-07-08 12:46:12,244][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018160_9297920.pth [2023-07-08 12:46:13,980][958872] Updated weights for policy 0, policy_version 18720 (0.0005) [2023-07-08 12:46:17,234][958585] Fps is (10 sec: 8601.5, 60 sec: 9011.2, 300 sec: 8983.4). Total num frames: 9609216. Throughput: 0: 9161.6. Samples: 9592772. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-07-08 12:46:17,235][958585] Avg episode reward: [(0, '616.234')] [2023-07-08 12:46:17,243][958827] Saving new best policy, reward=616.234! [2023-07-08 12:46:18,583][958872] Updated weights for policy 0, policy_version 18800 (0.0006) [2023-07-08 12:46:22,234][958585] Fps is (10 sec: 8601.6, 60 sec: 9011.2, 300 sec: 8983.4). Total num frames: 9654272. Throughput: 0: 9131.9. Samples: 9646088. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:46:22,235][958585] Avg episode reward: [(0, '612.551')] [2023-07-08 12:46:23,302][958872] Updated weights for policy 0, policy_version 18880 (0.0005) [2023-07-08 12:46:27,234][958585] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 8969.5). Total num frames: 9699328. Throughput: 0: 8903.7. Samples: 9698524. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:46:27,234][958585] Avg episode reward: [(0, '613.061')] [2023-07-08 12:46:27,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018944_9699328.pth... [2023-07-08 12:46:27,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018432_9437184.pth [2023-07-08 12:46:27,945][958872] Updated weights for policy 0, policy_version 18960 (0.0005) [2023-07-08 12:46:32,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 8969.5). Total num frames: 9744384. Throughput: 0: 8929.6. Samples: 9724436. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-07-08 12:46:32,235][958585] Avg episode reward: [(0, '611.897')] [2023-07-08 12:46:32,559][958872] Updated weights for policy 0, policy_version 19040 (0.0005) [2023-07-08 12:46:36,885][958872] Updated weights for policy 0, policy_version 19120 (0.0005) [2023-07-08 12:46:37,234][958585] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 8969.5). Total num frames: 9789440. Throughput: 0: 8964.8. Samples: 9781180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:46:37,234][958585] Avg episode reward: [(0, '610.535')] [2023-07-08 12:46:41,371][958872] Updated weights for policy 0, policy_version 19200 (0.0004) [2023-07-08 12:46:42,234][958585] Fps is (10 sec: 9011.3, 60 sec: 8942.9, 300 sec: 8969.5). Total num frames: 9834496. Throughput: 0: 8895.4. Samples: 9834560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:46:42,234][958585] Avg episode reward: [(0, '612.808')] [2023-07-08 12:46:42,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019208_9834496.pth... [2023-07-08 12:46:42,240][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018688_9568256.pth [2023-07-08 12:46:46,023][958872] Updated weights for policy 0, policy_version 19280 (0.0005) [2023-07-08 12:46:47,234][958585] Fps is (10 sec: 9011.1, 60 sec: 8942.9, 300 sec: 8983.4). Total num frames: 9879552. Throughput: 0: 8880.8. Samples: 9861416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:46:47,235][958585] Avg episode reward: [(0, '611.750')] [2023-07-08 12:46:50,540][958872] Updated weights for policy 0, policy_version 19360 (0.0005) [2023-07-08 12:46:52,234][958585] Fps is (10 sec: 9011.1, 60 sec: 8942.9, 300 sec: 8983.4). Total num frames: 9924608. Throughput: 0: 8909.6. Samples: 9915924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:46:52,235][958585] Avg episode reward: [(0, '615.237')] [2023-07-08 12:46:55,065][958872] Updated weights for policy 0, policy_version 19440 (0.0005) [2023-07-08 12:46:57,234][958585] Fps is (10 sec: 9011.2, 60 sec: 8874.7, 300 sec: 8969.5). Total num frames: 9969664. Throughput: 0: 8962.0. Samples: 9969568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-07-08 12:46:57,235][958585] Avg episode reward: [(0, '615.620')] [2023-07-08 12:46:57,237][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019472_9969664.pth... [2023-07-08 12:46:57,239][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000018944_9699328.pth [2023-07-08 12:46:59,486][958872] Updated weights for policy 0, policy_version 19520 (0.0005) [2023-07-08 12:47:00,480][958827] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000009 [2023-07-08 12:47:00,949][958827] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 [2023-07-08 12:47:00,950][958908] Stopping RolloutWorker_w5... [2023-07-08 12:47:00,950][958940] Stopping RolloutWorker_w6... [2023-07-08 12:47:00,950][958873] Stopping RolloutWorker_w1... [2023-07-08 12:47:00,950][958875] Stopping RolloutWorker_w3... [2023-07-08 12:47:00,950][958940] Loop rollout_proc6_evt_loop terminating... [2023-07-08 12:47:00,950][958876] Stopping RolloutWorker_w4... [2023-07-08 12:47:00,950][958873] Loop rollout_proc1_evt_loop terminating... [2023-07-08 12:47:00,950][958908] Loop rollout_proc5_evt_loop terminating... [2023-07-08 12:47:00,950][958986] Stopping RolloutWorker_w7... [2023-07-08 12:47:00,951][958875] Loop rollout_proc3_evt_loop terminating... [2023-07-08 12:47:00,950][958827] Stopping Batcher_0... [2023-07-08 12:47:00,950][958871] Stopping RolloutWorker_w0... [2023-07-08 12:47:00,951][958876] Loop rollout_proc4_evt_loop terminating... [2023-07-08 12:47:00,950][958585] Component RolloutWorker_w5 stopped! [2023-07-08 12:47:00,951][958874] Stopping RolloutWorker_w2... [2023-07-08 12:47:00,951][958986] Loop rollout_proc7_evt_loop terminating... [2023-07-08 12:47:00,951][958871] Loop rollout_proc0_evt_loop terminating... [2023-07-08 12:47:00,951][958874] Loop rollout_proc2_evt_loop terminating... [2023-07-08 12:47:00,951][958827] Loop batcher_evt_loop terminating... [2023-07-08 12:47:00,951][958585] Component RolloutWorker_w3 stopped! [2023-07-08 12:47:00,951][958585] Component RolloutWorker_w6 stopped! [2023-07-08 12:47:00,951][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... [2023-07-08 12:47:00,951][958585] Component RolloutWorker_w1 stopped! [2023-07-08 12:47:00,952][958585] Component RolloutWorker_w4 stopped! [2023-07-08 12:47:00,952][958585] Component RolloutWorker_w0 stopped! [2023-07-08 12:47:00,952][958585] Component RolloutWorker_w7 stopped! [2023-07-08 12:47:00,952][958585] Component Batcher_0 stopped! [2023-07-08 12:47:00,952][958585] Component RolloutWorker_w2 stopped! [2023-07-08 12:47:00,954][958827] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019208_9834496.pth [2023-07-08 12:47:00,955][958827] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/basketball-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... [2023-07-08 12:47:00,957][958827] Stopping LearnerWorker_p0... [2023-07-08 12:47:00,958][958827] Loop learner_proc0_evt_loop terminating... [2023-07-08 12:47:00,958][958585] Component LearnerWorker_p0 stopped! [2023-07-08 12:47:01,010][958872] Weights refcount: 2 0 [2023-07-08 12:47:01,011][958872] Stopping InferenceWorker_p0-w0... [2023-07-08 12:47:01,011][958872] Loop inference_proc0-0_evt_loop terminating... [2023-07-08 12:47:01,011][958585] Component InferenceWorker_p0-w0 stopped! [2023-07-08 12:47:01,012][958585] Waiting for process learner_proc0 to stop... [2023-07-08 12:47:01,706][958585] Waiting for process inference_proc0-0 to join... [2023-07-08 12:47:01,706][958585] Waiting for process rollout_proc0 to join... [2023-07-08 12:47:01,706][958585] Waiting for process rollout_proc1 to join... [2023-07-08 12:47:01,707][958585] Waiting for process rollout_proc2 to join... [2023-07-08 12:47:01,707][958585] Waiting for process rollout_proc3 to join... [2023-07-08 12:47:01,707][958585] Waiting for process rollout_proc4 to join... [2023-07-08 12:47:01,708][958585] Waiting for process rollout_proc5 to join... [2023-07-08 12:47:01,708][958585] Waiting for process rollout_proc6 to join... [2023-07-08 12:47:01,708][958585] Waiting for process rollout_proc7 to join... [2023-07-08 12:47:01,708][958585] Batcher 0 profile tree view: batching: 1.8353, releasing_batches: 1.5710 [2023-07-08 12:47:01,709][958585] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0051 wait_policy_total: 427.8681 update_model: 13.5484 weight_update: 0.0005 one_step: 0.0017 handle_policy_step: 594.4093 deserialize: 25.2894, stack: 6.3770, obs_to_device_normalize: 106.2583, forward: 294.6153, send_messages: 43.7691 prepare_outputs: 66.1047 to_cpu: 10.1845 [2023-07-08 12:47:01,709][958585] Learner 0 profile tree view: misc: 0.0094, prepare_batch: 8.3602 train: 86.5001 epoch_init: 0.0335, minibatch_init: 1.2242, losses_postprocess: 1.2731, kl_divergence: 0.4097, after_optimizer: 0.6271 calculate_losses: 36.6366 losses_init: 0.0298, forward_head: 13.9744, bptt_initial: 0.1298, bptt: 0.1218, tail: 10.6491, advantages_returns: 0.8280, losses: 9.6216 update: 44.8355 clip: 5.3973 [2023-07-08 12:47:01,709][958585] RolloutWorker_w0 profile tree view: wait_for_trajectories: 0.4626, enqueue_policy_requests: 15.0402, env_step: 694.0446, overhead: 21.6268, complete_rollouts: 0.3922 save_policy_outputs: 42.8214 split_output_tensors: 14.7116 [2023-07-08 12:47:01,709][958585] RolloutWorker_w7 profile tree view: wait_for_trajectories: 0.4235, enqueue_policy_requests: 14.7353, env_step: 687.9092, overhead: 21.2828, complete_rollouts: 0.3891 save_policy_outputs: 42.4081 split_output_tensors: 14.4833 [2023-07-08 12:47:01,710][958585] Loop Runner_EvtLoop terminating... [2023-07-08 12:47:01,710][958585] Runner profile tree view: main_loop: 1111.5915 [2023-07-08 12:47:01,710][958585] Collected {0: 10006528}, FPS: 9002.0