[2023-03-08 03:29:56,870][320945] Saving configuration to /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/config.json... [2023-03-08 03:29:56,885][320945] Rollout worker 0 uses device cpu [2023-03-08 03:29:56,886][320945] Rollout worker 1 uses device cpu [2023-03-08 03:29:56,886][320945] Rollout worker 2 uses device cpu [2023-03-08 03:29:56,886][320945] Rollout worker 3 uses device cpu [2023-03-08 03:29:56,886][320945] Rollout worker 4 uses device cpu [2023-03-08 03:29:56,886][320945] Rollout worker 5 uses device cpu [2023-03-08 03:29:56,886][320945] Rollout worker 6 uses device cpu [2023-03-08 03:29:56,886][320945] Rollout worker 7 uses device cpu [2023-03-08 03:29:56,887][320945] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 [2023-03-08 03:29:56,897][320945] InferenceWorker_p0-w0: min num requests: 2 [2023-03-08 03:29:56,914][320945] Starting all processes... [2023-03-08 03:29:56,914][320945] Starting process learner_proc0 [2023-03-08 03:29:56,964][320945] Starting all processes... [2023-03-08 03:29:57,009][320945] Starting process inference_proc0-0 [2023-03-08 03:29:57,009][320945] Starting process rollout_proc0 [2023-03-08 03:29:57,009][320945] Starting process rollout_proc1 [2023-03-08 03:29:57,009][320945] Starting process rollout_proc2 [2023-03-08 03:29:57,009][320945] Starting process rollout_proc3 [2023-03-08 03:29:57,010][320945] Starting process rollout_proc4 [2023-03-08 03:29:57,010][320945] Starting process rollout_proc5 [2023-03-08 03:29:57,011][320945] Starting process rollout_proc6 [2023-03-08 03:29:57,012][320945] Starting process rollout_proc7 [2023-03-08 03:29:58,479][321188] Starting seed is not provided [2023-03-08 03:29:58,479][321188] Initializing actor-critic model on device cpu [2023-03-08 03:29:58,479][321188] RunningMeanStd input shape: (39,) [2023-03-08 03:29:58,480][321188] RunningMeanStd input shape: (1,) [2023-03-08 03:29:58,509][321236] Worker 5 uses CPU cores [20, 21, 22, 23] [2023-03-08 03:29:58,536][321188] Created Actor Critic model with architecture: [2023-03-08 03:29:58,537][321188] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): MultiInputEncoder( (encoders): ModuleDict( (obs): MlpEncoder( (mlp_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=Tanh) (2): RecursiveScriptModule(original_name=Linear) (3): RecursiveScriptModule(original_name=Tanh) ) ) ) ) (core): ModelCoreIdentity() (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=64, out_features=1, bias=True) (action_parameterization): ActionParameterizationContinuousNonAdaptiveStddev( (distribution_linear): Linear(in_features=64, out_features=4, bias=True) ) ) [2023-03-08 03:29:58,607][321271] Worker 7 uses CPU cores [28, 29, 30, 31] [2023-03-08 03:29:58,695][321239] Worker 2 uses CPU cores [8, 9, 10, 11] [2023-03-08 03:29:58,743][321233] Worker 1 uses CPU cores [4, 5, 6, 7] [2023-03-08 03:29:58,827][321232] Worker 3 uses CPU cores [12, 13, 14, 15] [2023-03-08 03:29:58,848][321188] Using optimizer [2023-03-08 03:29:58,849][321188] No checkpoints found [2023-03-08 03:29:58,849][321188] Did not load from checkpoint, starting from scratch! [2023-03-08 03:29:58,849][321188] Initialized policy 0 weights for model version 0 [2023-03-08 03:29:58,850][321188] LearnerWorker_p0 finished initialization! [2023-03-08 03:29:58,911][321234] Worker 6 uses CPU cores [24, 25, 26, 27] [2023-03-08 03:29:58,992][321235] Worker 4 uses CPU cores [16, 17, 18, 19] [2023-03-08 03:29:59,033][321238] Worker 0 uses CPU cores [0, 1, 2, 3] [2023-03-08 03:29:59,171][321237] RunningMeanStd input shape: (39,) [2023-03-08 03:29:59,171][321237] RunningMeanStd input shape: (1,) [2023-03-08 03:29:59,227][320945] Inference worker 0-0 is ready! [2023-03-08 03:29:59,227][320945] All inference workers are ready! Signal rollout workers to start! [2023-03-08 03:29:59,594][320945] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-08 03:30:03,604][321238] Decorrelating experience for 0 frames... [2023-03-08 03:30:03,621][321238] Decorrelating experience for 64 frames... [2023-03-08 03:30:03,622][321239] Decorrelating experience for 0 frames... [2023-03-08 03:30:03,627][321234] Decorrelating experience for 0 frames... [2023-03-08 03:30:03,629][321236] Decorrelating experience for 0 frames... [2023-03-08 03:30:03,629][321233] Decorrelating experience for 0 frames... [2023-03-08 03:30:03,639][321239] Decorrelating experience for 64 frames... [2023-03-08 03:30:03,639][321232] Decorrelating experience for 0 frames... [2023-03-08 03:30:03,639][321235] Decorrelating experience for 0 frames... [2023-03-08 03:30:03,640][321271] Decorrelating experience for 0 frames... [2023-03-08 03:30:03,643][321234] Decorrelating experience for 64 frames... [2023-03-08 03:30:03,645][321236] Decorrelating experience for 64 frames... [2023-03-08 03:30:03,646][321233] Decorrelating experience for 64 frames... [2023-03-08 03:30:03,656][321235] Decorrelating experience for 64 frames... [2023-03-08 03:30:03,656][321232] Decorrelating experience for 64 frames... [2023-03-08 03:30:03,656][321271] Decorrelating experience for 64 frames... [2023-03-08 03:30:03,663][321238] Decorrelating experience for 128 frames... [2023-03-08 03:30:03,682][321239] Decorrelating experience for 128 frames... [2023-03-08 03:30:03,686][321233] Decorrelating experience for 128 frames... [2023-03-08 03:30:03,686][321236] Decorrelating experience for 128 frames... [2023-03-08 03:30:03,686][321234] Decorrelating experience for 128 frames... [2023-03-08 03:30:03,696][321271] Decorrelating experience for 128 frames... [2023-03-08 03:30:03,697][321232] Decorrelating experience for 128 frames... [2023-03-08 03:30:03,697][321235] Decorrelating experience for 128 frames... [2023-03-08 03:30:03,725][321238] Decorrelating experience for 192 frames... [2023-03-08 03:30:03,746][321239] Decorrelating experience for 192 frames... [2023-03-08 03:30:03,750][321236] Decorrelating experience for 192 frames... [2023-03-08 03:30:03,754][321233] Decorrelating experience for 192 frames... [2023-03-08 03:30:03,754][321234] Decorrelating experience for 192 frames... [2023-03-08 03:30:03,763][321271] Decorrelating experience for 192 frames... [2023-03-08 03:30:03,764][321235] Decorrelating experience for 192 frames... [2023-03-08 03:30:03,765][321232] Decorrelating experience for 192 frames... [2023-03-08 03:30:04,594][320945] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-08 03:30:08,082][321238] Decorrelating experience for 256 frames... [2023-03-08 03:30:08,112][321236] Decorrelating experience for 256 frames... [2023-03-08 03:30:08,121][321233] Decorrelating experience for 256 frames... [2023-03-08 03:30:08,127][321239] Decorrelating experience for 256 frames... [2023-03-08 03:30:08,131][321234] Decorrelating experience for 256 frames... [2023-03-08 03:30:08,148][321271] Decorrelating experience for 256 frames... [2023-03-08 03:30:08,152][321232] Decorrelating experience for 256 frames... [2023-03-08 03:30:08,154][321235] Decorrelating experience for 256 frames... [2023-03-08 03:30:08,206][321238] Decorrelating experience for 320 frames... [2023-03-08 03:30:08,222][321236] Decorrelating experience for 320 frames... [2023-03-08 03:30:08,232][321233] Decorrelating experience for 320 frames... [2023-03-08 03:30:08,244][321239] Decorrelating experience for 320 frames... [2023-03-08 03:30:08,256][321234] Decorrelating experience for 320 frames... [2023-03-08 03:30:08,260][321232] Decorrelating experience for 320 frames... [2023-03-08 03:30:08,262][321271] Decorrelating experience for 320 frames... [2023-03-08 03:30:08,266][321235] Decorrelating experience for 320 frames... [2023-03-08 03:30:08,332][321238] Decorrelating experience for 384 frames... [2023-03-08 03:30:08,362][321236] Decorrelating experience for 384 frames... [2023-03-08 03:30:08,362][321233] Decorrelating experience for 384 frames... [2023-03-08 03:30:08,379][321239] Decorrelating experience for 384 frames... [2023-03-08 03:30:08,391][321271] Decorrelating experience for 384 frames... [2023-03-08 03:30:08,393][321234] Decorrelating experience for 384 frames... [2023-03-08 03:30:08,397][321235] Decorrelating experience for 384 frames... [2023-03-08 03:30:08,398][321232] Decorrelating experience for 384 frames... [2023-03-08 03:30:08,514][321233] Decorrelating experience for 448 frames... [2023-03-08 03:30:08,520][321236] Decorrelating experience for 448 frames... [2023-03-08 03:30:08,524][321238] Decorrelating experience for 448 frames... [2023-03-08 03:30:08,530][321239] Decorrelating experience for 448 frames... [2023-03-08 03:30:08,552][321232] Decorrelating experience for 448 frames... [2023-03-08 03:30:08,553][321271] Decorrelating experience for 448 frames... [2023-03-08 03:30:08,555][321235] Decorrelating experience for 448 frames... [2023-03-08 03:30:08,557][321234] Decorrelating experience for 448 frames... [2023-03-08 03:30:09,594][320945] Fps is (10 sec: 409.6, 60 sec: 409.6, 300 sec: 409.6). Total num frames: 4096. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:30:09,595][320945] Avg episode reward: [(0, '69.375')] [2023-03-08 03:30:09,596][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000000008_4096.pth... [2023-03-08 03:30:12,521][321237] Updated weights for policy 0, policy_version 80 (0.0004) [2023-03-08 03:30:14,594][320945] Fps is (10 sec: 6144.0, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 61440. Throughput: 0: 4096.5. Samples: 61448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:30:14,595][320945] Avg episode reward: [(0, '1575.478')] [2023-03-08 03:30:16,163][321237] Updated weights for policy 0, policy_version 160 (0.0005) [2023-03-08 03:30:16,893][320945] Heartbeat connected on Batcher_0 [2023-03-08 03:30:16,900][320945] Heartbeat connected on RolloutWorker_w0 [2023-03-08 03:30:16,902][320945] Heartbeat connected on RolloutWorker_w1 [2023-03-08 03:30:16,904][320945] Heartbeat connected on RolloutWorker_w2 [2023-03-08 03:30:16,905][320945] Heartbeat connected on RolloutWorker_w3 [2023-03-08 03:30:16,907][320945] Heartbeat connected on RolloutWorker_w4 [2023-03-08 03:30:16,909][320945] Heartbeat connected on RolloutWorker_w5 [2023-03-08 03:30:16,911][320945] Heartbeat connected on RolloutWorker_w6 [2023-03-08 03:30:16,913][320945] Heartbeat connected on RolloutWorker_w7 [2023-03-08 03:30:16,923][320945] Heartbeat connected on LearnerWorker_p0 [2023-03-08 03:30:16,924][320945] Heartbeat connected on InferenceWorker_p0-w0 [2023-03-08 03:30:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 5734.4, 300 sec: 5734.4). Total num frames: 114688. Throughput: 0: 4699.6. Samples: 93992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:30:19,595][320945] Avg episode reward: [(0, '4064.865')] [2023-03-08 03:30:19,598][321188] Saving new best policy, reward=4064.865! [2023-03-08 03:30:19,944][321237] Updated weights for policy 0, policy_version 240 (0.0005) [2023-03-08 03:30:23,034][321237] Updated weights for policy 0, policy_version 320 (0.0004) [2023-03-08 03:30:24,594][320945] Fps is (10 sec: 12287.9, 60 sec: 7372.8, 300 sec: 7372.8). Total num frames: 184320. Throughput: 0: 6695.2. Samples: 167380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:30:24,595][320945] Avg episode reward: [(0, '4419.438')] [2023-03-08 03:30:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000000360_184320.pth... [2023-03-08 03:30:24,600][321188] Saving new best policy, reward=4419.438! [2023-03-08 03:30:25,949][321237] Updated weights for policy 0, policy_version 400 (0.0004) [2023-03-08 03:30:28,820][321237] Updated weights for policy 0, policy_version 480 (0.0004) [2023-03-08 03:30:29,594][320945] Fps is (10 sec: 13926.5, 60 sec: 8465.1, 300 sec: 8465.1). Total num frames: 253952. Throughput: 0: 8397.6. Samples: 251928. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:30:29,595][320945] Avg episode reward: [(0, '4417.974')] [2023-03-08 03:30:31,638][321237] Updated weights for policy 0, policy_version 560 (0.0004) [2023-03-08 03:30:34,511][321237] Updated weights for policy 0, policy_version 640 (0.0004) [2023-03-08 03:30:34,594][320945] Fps is (10 sec: 14336.0, 60 sec: 9362.3, 300 sec: 9362.3). Total num frames: 327680. Throughput: 0: 8441.8. Samples: 295464. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:30:34,595][320945] Avg episode reward: [(0, '4370.191')] [2023-03-08 03:30:37,477][321237] Updated weights for policy 0, policy_version 720 (0.0004) [2023-03-08 03:30:39,594][320945] Fps is (10 sec: 14335.9, 60 sec: 9932.8, 300 sec: 9932.8). Total num frames: 397312. Throughput: 0: 9498.0. Samples: 379920. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:30:39,595][320945] Avg episode reward: [(0, '4605.103')] [2023-03-08 03:30:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000000776_397312.pth... [2023-03-08 03:30:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000000008_4096.pth [2023-03-08 03:30:39,600][321188] Saving new best policy, reward=4605.103! [2023-03-08 03:30:40,347][321237] Updated weights for policy 0, policy_version 800 (0.0003) [2023-03-08 03:30:43,250][321237] Updated weights for policy 0, policy_version 880 (0.0003) [2023-03-08 03:30:44,594][320945] Fps is (10 sec: 13926.4, 60 sec: 10376.5, 300 sec: 10376.5). Total num frames: 466944. Throughput: 0: 10339.2. Samples: 465264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:30:44,595][320945] Avg episode reward: [(0, '4848.766')] [2023-03-08 03:30:44,595][321188] Saving new best policy, reward=4848.766! [2023-03-08 03:30:46,141][321237] Updated weights for policy 0, policy_version 960 (0.0004) [2023-03-08 03:30:49,082][321237] Updated weights for policy 0, policy_version 1040 (0.0004) [2023-03-08 03:30:49,594][320945] Fps is (10 sec: 13926.5, 60 sec: 10731.5, 300 sec: 10731.5). Total num frames: 536576. Throughput: 0: 11273.0. Samples: 507284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:30:49,595][320945] Avg episode reward: [(0, '4807.329')] [2023-03-08 03:30:51,974][321237] Updated weights for policy 0, policy_version 1120 (0.0003) [2023-03-08 03:30:54,594][320945] Fps is (10 sec: 13926.3, 60 sec: 11021.9, 300 sec: 11021.9). Total num frames: 606208. Throughput: 0: 13110.7. Samples: 589984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:30:54,595][320945] Avg episode reward: [(0, '4807.651')] [2023-03-08 03:30:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000001184_606208.pth... [2023-03-08 03:30:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000000360_184320.pth [2023-03-08 03:30:55,034][321237] Updated weights for policy 0, policy_version 1200 (0.0004) [2023-03-08 03:30:58,416][321237] Updated weights for policy 0, policy_version 1280 (0.0005) [2023-03-08 03:30:59,594][320945] Fps is (10 sec: 13107.3, 60 sec: 11127.5, 300 sec: 11127.5). Total num frames: 667648. Throughput: 0: 13436.3. Samples: 666080. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:30:59,595][320945] Avg episode reward: [(0, '4855.813')] [2023-03-08 03:30:59,595][321188] Saving new best policy, reward=4855.813! [2023-03-08 03:31:01,569][321237] Updated weights for policy 0, policy_version 1360 (0.0004) [2023-03-08 03:31:04,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12219.7, 300 sec: 11279.7). Total num frames: 733184. Throughput: 0: 13597.5. Samples: 705880. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:31:04,595][320945] Avg episode reward: [(0, '4773.303')] [2023-03-08 03:31:04,614][321237] Updated weights for policy 0, policy_version 1440 (0.0003) [2023-03-08 03:31:07,867][321237] Updated weights for policy 0, policy_version 1520 (0.0004) [2023-03-08 03:31:09,594][320945] Fps is (10 sec: 13107.2, 60 sec: 13243.7, 300 sec: 11410.3). Total num frames: 798720. Throughput: 0: 13675.2. Samples: 782764. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:31:09,595][320945] Avg episode reward: [(0, '4858.484')] [2023-03-08 03:31:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000001560_798720.pth... [2023-03-08 03:31:09,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000000776_397312.pth [2023-03-08 03:31:09,600][321188] Saving new best policy, reward=4858.484! [2023-03-08 03:31:11,223][321237] Updated weights for policy 0, policy_version 1600 (0.0004) [2023-03-08 03:31:14,594][320945] Fps is (10 sec: 12288.0, 60 sec: 13243.7, 300 sec: 11414.2). Total num frames: 856064. Throughput: 0: 13425.0. Samples: 856056. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:31:14,595][320945] Avg episode reward: [(0, '4817.971')] [2023-03-08 03:31:14,639][321237] Updated weights for policy 0, policy_version 1680 (0.0005) [2023-03-08 03:31:17,959][321237] Updated weights for policy 0, policy_version 1760 (0.0005) [2023-03-08 03:31:19,594][320945] Fps is (10 sec: 11878.3, 60 sec: 13380.3, 300 sec: 11468.8). Total num frames: 917504. Throughput: 0: 13273.2. Samples: 892760. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:31:19,595][320945] Avg episode reward: [(0, '4859.324')] [2023-03-08 03:31:19,602][321188] Saving new best policy, reward=4859.324! [2023-03-08 03:31:21,322][321237] Updated weights for policy 0, policy_version 1840 (0.0005) [2023-03-08 03:31:24,594][320945] Fps is (10 sec: 12288.1, 60 sec: 13243.7, 300 sec: 11517.0). Total num frames: 978944. Throughput: 0: 13038.6. Samples: 966656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:31:24,595][320945] Avg episode reward: [(0, '4809.037')] [2023-03-08 03:31:24,651][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000001920_983040.pth... [2023-03-08 03:31:24,651][321237] Updated weights for policy 0, policy_version 1920 (0.0005) [2023-03-08 03:31:24,652][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000001184_606208.pth [2023-03-08 03:31:27,969][321237] Updated weights for policy 0, policy_version 2000 (0.0005) [2023-03-08 03:31:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 13107.2, 300 sec: 11559.8). Total num frames: 1040384. Throughput: 0: 12778.2. Samples: 1040284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:31:29,595][320945] Avg episode reward: [(0, '4854.067')] [2023-03-08 03:31:31,267][321237] Updated weights for policy 0, policy_version 2080 (0.0005) [2023-03-08 03:31:34,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12902.4, 300 sec: 11598.1). Total num frames: 1101824. Throughput: 0: 12665.2. Samples: 1077216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:31:34,595][320945] Avg episode reward: [(0, '4858.446')] [2023-03-08 03:31:34,712][321237] Updated weights for policy 0, policy_version 2160 (0.0005) [2023-03-08 03:31:38,003][321237] Updated weights for policy 0, policy_version 2240 (0.0005) [2023-03-08 03:31:39,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12765.9, 300 sec: 11632.6). Total num frames: 1163264. Throughput: 0: 12459.0. Samples: 1150640. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:31:39,595][320945] Avg episode reward: [(0, '4839.458')] [2023-03-08 03:31:39,607][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000002280_1167360.pth... [2023-03-08 03:31:39,609][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000001560_798720.pth [2023-03-08 03:31:41,323][321237] Updated weights for policy 0, policy_version 2320 (0.0004) [2023-03-08 03:31:44,594][320945] Fps is (10 sec: 12288.1, 60 sec: 12629.3, 300 sec: 11663.9). Total num frames: 1224704. Throughput: 0: 12389.8. Samples: 1223620. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:31:44,595][320945] Avg episode reward: [(0, '4810.600')] [2023-03-08 03:31:44,715][321237] Updated weights for policy 0, policy_version 2400 (0.0004) [2023-03-08 03:31:48,135][321237] Updated weights for policy 0, policy_version 2480 (0.0005) [2023-03-08 03:31:49,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 11692.2). Total num frames: 1286144. Throughput: 0: 12305.7. Samples: 1259636. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:31:49,595][320945] Avg episode reward: [(0, '4857.303')] [2023-03-08 03:31:51,659][321237] Updated weights for policy 0, policy_version 2560 (0.0005) [2023-03-08 03:31:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 11682.5). Total num frames: 1343488. Throughput: 0: 12117.7. Samples: 1328060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:31:54,595][320945] Avg episode reward: [(0, '4857.178')] [2023-03-08 03:31:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000002624_1343488.pth... [2023-03-08 03:31:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000001920_983040.pth [2023-03-08 03:31:55,319][321237] Updated weights for policy 0, policy_version 2640 (0.0005) [2023-03-08 03:31:58,868][321237] Updated weights for policy 0, policy_version 2720 (0.0005) [2023-03-08 03:31:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 12151.5, 300 sec: 11639.5). Total num frames: 1396736. Throughput: 0: 12016.7. Samples: 1396808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:31:59,595][320945] Avg episode reward: [(0, '4858.588')] [2023-03-08 03:32:02,372][321237] Updated weights for policy 0, policy_version 2800 (0.0005) [2023-03-08 03:32:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 11665.4). Total num frames: 1458176. Throughput: 0: 12004.5. Samples: 1432960. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:32:04,595][320945] Avg episode reward: [(0, '4860.024')] [2023-03-08 03:32:04,595][321188] Saving new best policy, reward=4860.024! [2023-03-08 03:32:05,692][321237] Updated weights for policy 0, policy_version 2880 (0.0004) [2023-03-08 03:32:08,981][321237] Updated weights for policy 0, policy_version 2960 (0.0005) [2023-03-08 03:32:09,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11689.3). Total num frames: 1519616. Throughput: 0: 12000.6. Samples: 1506684. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:32:09,595][320945] Avg episode reward: [(0, '4859.133')] [2023-03-08 03:32:09,613][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000002976_1523712.pth... [2023-03-08 03:32:09,614][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000002280_1167360.pth [2023-03-08 03:32:12,329][321237] Updated weights for policy 0, policy_version 3040 (0.0005) [2023-03-08 03:32:14,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11711.5). Total num frames: 1581056. Throughput: 0: 11997.2. Samples: 1580156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:32:14,595][320945] Avg episode reward: [(0, '4836.043')] [2023-03-08 03:32:15,842][321237] Updated weights for policy 0, policy_version 3120 (0.0005) [2023-03-08 03:32:19,415][321237] Updated weights for policy 0, policy_version 3200 (0.0005) [2023-03-08 03:32:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 11702.9). Total num frames: 1638400. Throughput: 0: 11926.2. Samples: 1613896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:32:19,595][320945] Avg episode reward: [(0, '4856.688')] [2023-03-08 03:32:23,063][321237] Updated weights for policy 0, policy_version 3280 (0.0005) [2023-03-08 03:32:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11694.8). Total num frames: 1695744. Throughput: 0: 11802.4. Samples: 1681748. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:32:24,595][320945] Avg episode reward: [(0, '4861.230')] [2023-03-08 03:32:24,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000003312_1695744.pth... [2023-03-08 03:32:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000002624_1343488.pth [2023-03-08 03:32:24,601][321188] Saving new best policy, reward=4861.230! [2023-03-08 03:32:26,438][321237] Updated weights for policy 0, policy_version 3360 (0.0004) [2023-03-08 03:32:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11714.6). Total num frames: 1757184. Throughput: 0: 11823.4. Samples: 1755672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:32:29,595][320945] Avg episode reward: [(0, '4857.358')] [2023-03-08 03:32:29,727][321237] Updated weights for policy 0, policy_version 3440 (0.0005) [2023-03-08 03:32:33,027][321237] Updated weights for policy 0, policy_version 3520 (0.0004) [2023-03-08 03:32:34,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11733.1). Total num frames: 1818624. Throughput: 0: 11862.5. Samples: 1793448. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:32:34,595][320945] Avg episode reward: [(0, '4803.814')] [2023-03-08 03:32:36,296][321237] Updated weights for policy 0, policy_version 3600 (0.0005) [2023-03-08 03:32:39,590][321237] Updated weights for policy 0, policy_version 3680 (0.0005) [2023-03-08 03:32:39,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12014.9, 300 sec: 11776.0). Total num frames: 1884160. Throughput: 0: 11991.6. Samples: 1867684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:32:39,595][320945] Avg episode reward: [(0, '4763.292')] [2023-03-08 03:32:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000003680_1884160.pth... [2023-03-08 03:32:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000002976_1523712.pth [2023-03-08 03:32:42,827][321237] Updated weights for policy 0, policy_version 3760 (0.0004) [2023-03-08 03:32:44,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12014.9, 300 sec: 11791.5). Total num frames: 1945600. Throughput: 0: 12122.0. Samples: 1942296. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 03:32:44,594][320945] Avg episode reward: [(0, '4808.078')] [2023-03-08 03:32:46,247][321237] Updated weights for policy 0, policy_version 3840 (0.0005) [2023-03-08 03:32:49,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11782.0). Total num frames: 2002944. Throughput: 0: 12120.4. Samples: 1978376. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 03:32:49,595][320945] Avg episode reward: [(0, '4856.040')] [2023-03-08 03:32:49,656][321237] Updated weights for policy 0, policy_version 3920 (0.0005) [2023-03-08 03:32:52,910][321237] Updated weights for policy 0, policy_version 4000 (0.0005) [2023-03-08 03:32:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 11796.5). Total num frames: 2064384. Throughput: 0: 12121.9. Samples: 2052168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:32:54,595][320945] Avg episode reward: [(0, '4861.252')] [2023-03-08 03:32:54,628][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000004040_2068480.pth... [2023-03-08 03:32:54,630][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000003312_1695744.pth [2023-03-08 03:32:54,630][321188] Saving new best policy, reward=4861.252! [2023-03-08 03:32:56,351][321237] Updated weights for policy 0, policy_version 4080 (0.0005) [2023-03-08 03:32:59,594][320945] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 11810.1). Total num frames: 2125824. Throughput: 0: 12110.1. Samples: 2125108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:32:59,595][320945] Avg episode reward: [(0, '4859.157')] [2023-03-08 03:32:59,676][321237] Updated weights for policy 0, policy_version 4160 (0.0004) [2023-03-08 03:33:03,098][321237] Updated weights for policy 0, policy_version 4240 (0.0004) [2023-03-08 03:33:04,594][320945] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 11823.0). Total num frames: 2187264. Throughput: 0: 12160.9. Samples: 2161136. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:33:04,595][320945] Avg episode reward: [(0, '4858.126')] [2023-03-08 03:33:06,590][321237] Updated weights for policy 0, policy_version 4320 (0.0004) [2023-03-08 03:33:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11813.7). Total num frames: 2244608. Throughput: 0: 12235.1. Samples: 2232328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:33:09,595][320945] Avg episode reward: [(0, '4855.058')] [2023-03-08 03:33:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000004384_2244608.pth... [2023-03-08 03:33:09,598][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000003680_1884160.pth [2023-03-08 03:33:09,999][321237] Updated weights for policy 0, policy_version 4400 (0.0005) [2023-03-08 03:33:13,673][321237] Updated weights for policy 0, policy_version 4480 (0.0005) [2023-03-08 03:33:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 11804.9). Total num frames: 2301952. Throughput: 0: 12114.1. Samples: 2300808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:33:14,595][320945] Avg episode reward: [(0, '4851.523')] [2023-03-08 03:33:17,340][321237] Updated weights for policy 0, policy_version 4560 (0.0005) [2023-03-08 03:33:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11946.7, 300 sec: 11776.0). Total num frames: 2355200. Throughput: 0: 12023.4. Samples: 2334500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:33:19,594][320945] Avg episode reward: [(0, '4849.979')] [2023-03-08 03:33:21,107][321237] Updated weights for policy 0, policy_version 4640 (0.0005) [2023-03-08 03:33:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11946.7, 300 sec: 11768.5). Total num frames: 2412544. Throughput: 0: 11830.2. Samples: 2400044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:33:24,595][320945] Avg episode reward: [(0, '4847.561')] [2023-03-08 03:33:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000004712_2412544.pth... [2023-03-08 03:33:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000004040_2068480.pth [2023-03-08 03:33:24,830][321237] Updated weights for policy 0, policy_version 4720 (0.0005) [2023-03-08 03:33:28,460][321237] Updated weights for policy 0, policy_version 4800 (0.0005) [2023-03-08 03:33:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11761.4). Total num frames: 2469888. Throughput: 0: 11646.5. Samples: 2466388. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:33:29,595][320945] Avg episode reward: [(0, '4854.184')] [2023-03-08 03:33:32,019][321237] Updated weights for policy 0, policy_version 4880 (0.0005) [2023-03-08 03:33:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11754.6). Total num frames: 2527232. Throughput: 0: 11630.7. Samples: 2501756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:33:34,595][320945] Avg episode reward: [(0, '4807.053')] [2023-03-08 03:33:35,520][321237] Updated weights for policy 0, policy_version 4960 (0.0004) [2023-03-08 03:33:39,047][321237] Updated weights for policy 0, policy_version 5040 (0.0004) [2023-03-08 03:33:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11748.1). Total num frames: 2584576. Throughput: 0: 11546.9. Samples: 2571780. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:33:39,595][320945] Avg episode reward: [(0, '4853.568')] [2023-03-08 03:33:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000005048_2584576.pth... [2023-03-08 03:33:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000004384_2244608.pth [2023-03-08 03:33:42,726][321237] Updated weights for policy 0, policy_version 5120 (0.0005) [2023-03-08 03:33:44,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11537.1, 300 sec: 11723.7). Total num frames: 2637824. Throughput: 0: 11395.1. Samples: 2637888. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:33:44,594][320945] Avg episode reward: [(0, '4850.642')] [2023-03-08 03:33:46,544][321237] Updated weights for policy 0, policy_version 5200 (0.0005) [2023-03-08 03:33:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11735.9). Total num frames: 2699264. Throughput: 0: 11326.8. Samples: 2670844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:33:49,595][320945] Avg episode reward: [(0, '4860.340')] [2023-03-08 03:33:49,877][321237] Updated weights for policy 0, policy_version 5280 (0.0004) [2023-03-08 03:33:53,568][321237] Updated weights for policy 0, policy_version 5360 (0.0005) [2023-03-08 03:33:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11712.8). Total num frames: 2752512. Throughput: 0: 11295.5. Samples: 2740624. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:33:54,595][320945] Avg episode reward: [(0, '4859.269')] [2023-03-08 03:33:54,651][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000005384_2756608.pth... [2023-03-08 03:33:54,653][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000004712_2412544.pth [2023-03-08 03:33:57,284][321237] Updated weights for policy 0, policy_version 5440 (0.0005) [2023-03-08 03:33:59,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11332.3, 300 sec: 11690.7). Total num frames: 2805760. Throughput: 0: 11222.8. Samples: 2805832. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 03:33:59,594][320945] Avg episode reward: [(0, '4859.560')] [2023-03-08 03:34:01,160][321237] Updated weights for policy 0, policy_version 5520 (0.0005) [2023-03-08 03:34:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11669.4). Total num frames: 2859008. Throughput: 0: 11200.1. Samples: 2838504. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:34:04,595][320945] Avg episode reward: [(0, '4857.834')] [2023-03-08 03:34:05,007][321237] Updated weights for policy 0, policy_version 5600 (0.0005) [2023-03-08 03:34:08,522][321237] Updated weights for policy 0, policy_version 5680 (0.0005) [2023-03-08 03:34:09,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11665.4). Total num frames: 2916352. Throughput: 0: 11218.7. Samples: 2904884. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:34:09,594][320945] Avg episode reward: [(0, '4860.099')] [2023-03-08 03:34:09,600][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000005704_2920448.pth... [2023-03-08 03:34:09,602][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000005048_2584576.pth [2023-03-08 03:34:12,032][321237] Updated weights for policy 0, policy_version 5760 (0.0004) [2023-03-08 03:34:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 11677.6). Total num frames: 2977792. Throughput: 0: 11331.6. Samples: 2976308. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:34:14,595][320945] Avg episode reward: [(0, '4857.658')] [2023-03-08 03:34:15,429][321237] Updated weights for policy 0, policy_version 5840 (0.0004) [2023-03-08 03:34:18,836][321237] Updated weights for policy 0, policy_version 5920 (0.0004) [2023-03-08 03:34:19,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11400.5, 300 sec: 11689.4). Total num frames: 3039232. Throughput: 0: 11352.9. Samples: 3012636. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:34:19,595][320945] Avg episode reward: [(0, '4859.669')] [2023-03-08 03:34:22,289][321237] Updated weights for policy 0, policy_version 6000 (0.0005) [2023-03-08 03:34:24,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11400.5, 300 sec: 11685.2). Total num frames: 3096576. Throughput: 0: 11389.1. Samples: 3084288. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:34:24,595][320945] Avg episode reward: [(0, '4861.658')] [2023-03-08 03:34:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000006048_3096576.pth... [2023-03-08 03:34:24,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000005384_2756608.pth [2023-03-08 03:34:24,599][321188] Saving new best policy, reward=4861.658! [2023-03-08 03:34:25,695][321237] Updated weights for policy 0, policy_version 6080 (0.0004) [2023-03-08 03:34:29,085][321237] Updated weights for policy 0, policy_version 6160 (0.0004) [2023-03-08 03:34:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11696.4). Total num frames: 3158016. Throughput: 0: 11508.4. Samples: 3155768. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:34:29,595][320945] Avg episode reward: [(0, '4858.901')] [2023-03-08 03:34:32,741][321237] Updated weights for policy 0, policy_version 6240 (0.0005) [2023-03-08 03:34:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11677.3). Total num frames: 3211264. Throughput: 0: 11540.0. Samples: 3190144. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:34:34,595][320945] Avg episode reward: [(0, '4861.653')] [2023-03-08 03:34:36,612][321237] Updated weights for policy 0, policy_version 6320 (0.0005) [2023-03-08 03:34:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11673.6). Total num frames: 3268608. Throughput: 0: 11399.6. Samples: 3253608. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:34:39,595][320945] Avg episode reward: [(0, '4860.096')] [2023-03-08 03:34:39,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000006384_3268608.pth... [2023-03-08 03:34:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000005704_2920448.pth [2023-03-08 03:34:40,222][321237] Updated weights for policy 0, policy_version 6400 (0.0005) [2023-03-08 03:34:43,687][321237] Updated weights for policy 0, policy_version 6480 (0.0004) [2023-03-08 03:34:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11670.0). Total num frames: 3325952. Throughput: 0: 11519.4. Samples: 3324204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:34:44,595][320945] Avg episode reward: [(0, '4862.196')] [2023-03-08 03:34:44,595][321188] Saving new best policy, reward=4862.196! [2023-03-08 03:34:47,235][321237] Updated weights for policy 0, policy_version 6560 (0.0004) [2023-03-08 03:34:49,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11680.7). Total num frames: 3387392. Throughput: 0: 11561.9. Samples: 3358792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:34:49,595][320945] Avg episode reward: [(0, '4861.318')] [2023-03-08 03:34:50,700][321237] Updated weights for policy 0, policy_version 6640 (0.0004) [2023-03-08 03:34:54,091][321237] Updated weights for policy 0, policy_version 6720 (0.0004) [2023-03-08 03:34:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11537.1, 300 sec: 11677.1). Total num frames: 3444736. Throughput: 0: 11681.2. Samples: 3430540. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:34:54,595][320945] Avg episode reward: [(0, '4860.422')] [2023-03-08 03:34:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000006728_3444736.pth... [2023-03-08 03:34:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000006048_3096576.pth [2023-03-08 03:34:54,779][321188] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000009 [2023-03-08 03:34:57,492][321237] Updated weights for policy 0, policy_version 6800 (0.0004) [2023-03-08 03:34:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11885.3). Total num frames: 3506176. Throughput: 0: 11710.4. Samples: 3503276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:34:59,595][320945] Avg episode reward: [(0, '4854.877')] [2023-03-08 03:35:00,762][321237] Updated weights for policy 0, policy_version 6880 (0.0003) [2023-03-08 03:35:04,126][321237] Updated weights for policy 0, policy_version 6960 (0.0004) [2023-03-08 03:35:04,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 12079.7). Total num frames: 3567616. Throughput: 0: 11746.3. Samples: 3541220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:35:04,595][320945] Avg episode reward: [(0, '4858.994')] [2023-03-08 03:35:07,735][321237] Updated weights for policy 0, policy_version 7040 (0.0005) [2023-03-08 03:35:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12079.7). Total num frames: 3624960. Throughput: 0: 11698.9. Samples: 3610740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:35:09,594][320945] Avg episode reward: [(0, '4861.035')] [2023-03-08 03:35:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000007080_3624960.pth... [2023-03-08 03:35:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000006384_3268608.pth [2023-03-08 03:35:11,347][321237] Updated weights for policy 0, policy_version 7120 (0.0005) [2023-03-08 03:35:14,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11673.6, 300 sec: 12079.7). Total num frames: 3678208. Throughput: 0: 11603.4. Samples: 3677920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:35:14,595][320945] Avg episode reward: [(0, '4863.276')] [2023-03-08 03:35:14,595][321188] Saving new best policy, reward=4863.276! [2023-03-08 03:35:15,091][321237] Updated weights for policy 0, policy_version 7200 (0.0005) [2023-03-08 03:35:18,729][321237] Updated weights for policy 0, policy_version 7280 (0.0005) [2023-03-08 03:35:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 12038.1). Total num frames: 3735552. Throughput: 0: 11575.5. Samples: 3711040. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:35:19,595][320945] Avg episode reward: [(0, '4858.354')] [2023-03-08 03:35:22,406][321237] Updated weights for policy 0, policy_version 7360 (0.0005) [2023-03-08 03:35:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11996.4). Total num frames: 3792896. Throughput: 0: 11682.7. Samples: 3779328. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:35:24,595][320945] Avg episode reward: [(0, '4860.803')] [2023-03-08 03:35:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000007408_3792896.pth... [2023-03-08 03:35:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000006728_3444736.pth [2023-03-08 03:35:25,888][321237] Updated weights for policy 0, policy_version 7440 (0.0005) [2023-03-08 03:35:29,481][321237] Updated weights for policy 0, policy_version 7520 (0.0005) [2023-03-08 03:35:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11940.9). Total num frames: 3850240. Throughput: 0: 11628.4. Samples: 3847480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:35:29,595][320945] Avg episode reward: [(0, '4861.760')] [2023-03-08 03:35:32,914][321237] Updated weights for policy 0, policy_version 7600 (0.0004) [2023-03-08 03:35:34,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11899.2). Total num frames: 3907584. Throughput: 0: 11658.9. Samples: 3883444. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 03:35:34,595][320945] Avg episode reward: [(0, '4860.536')] [2023-03-08 03:35:36,462][321237] Updated weights for policy 0, policy_version 7680 (0.0005) [2023-03-08 03:35:39,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11605.4, 300 sec: 11857.6). Total num frames: 3964928. Throughput: 0: 11604.5. Samples: 3952740. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:35:39,605][320945] Avg episode reward: [(0, '4852.204')] [2023-03-08 03:35:39,625][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000007752_3969024.pth... [2023-03-08 03:35:39,626][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000007080_3624960.pth [2023-03-08 03:35:39,973][321237] Updated weights for policy 0, policy_version 7760 (0.0004) [2023-03-08 03:35:43,498][321237] Updated weights for policy 0, policy_version 7840 (0.0005) [2023-03-08 03:35:44,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11829.8). Total num frames: 4026368. Throughput: 0: 11542.9. Samples: 4022708. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:35:44,605][320945] Avg episode reward: [(0, '4859.882')] [2023-03-08 03:35:47,057][321237] Updated weights for policy 0, policy_version 7920 (0.0005) [2023-03-08 03:35:49,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11788.2). Total num frames: 4083712. Throughput: 0: 11476.7. Samples: 4057672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:35:49,595][320945] Avg episode reward: [(0, '4856.142')] [2023-03-08 03:35:50,518][321237] Updated weights for policy 0, policy_version 8000 (0.0005) [2023-03-08 03:35:54,076][321237] Updated weights for policy 0, policy_version 8080 (0.0005) [2023-03-08 03:35:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11774.3). Total num frames: 4141056. Throughput: 0: 11497.9. Samples: 4128144. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:35:54,595][320945] Avg episode reward: [(0, '4856.264')] [2023-03-08 03:35:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000008088_4141056.pth... [2023-03-08 03:35:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000007408_3792896.pth [2023-03-08 03:35:57,655][321237] Updated weights for policy 0, policy_version 8160 (0.0005) [2023-03-08 03:35:59,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11746.5). Total num frames: 4198400. Throughput: 0: 11534.1. Samples: 4196956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:35:59,595][320945] Avg episode reward: [(0, '4850.626')] [2023-03-08 03:36:01,187][321237] Updated weights for policy 0, policy_version 8240 (0.0005) [2023-03-08 03:36:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11718.7). Total num frames: 4255744. Throughput: 0: 11560.0. Samples: 4231240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:36:04,595][320945] Avg episode reward: [(0, '4849.651')] [2023-03-08 03:36:04,719][321237] Updated weights for policy 0, policy_version 8320 (0.0005) [2023-03-08 03:36:08,201][321237] Updated weights for policy 0, policy_version 8400 (0.0005) [2023-03-08 03:36:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11718.7). Total num frames: 4313088. Throughput: 0: 11598.7. Samples: 4301272. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:36:09,595][320945] Avg episode reward: [(0, '4857.836')] [2023-03-08 03:36:09,647][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000008432_4317184.pth... [2023-03-08 03:36:09,649][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000007752_3969024.pth [2023-03-08 03:36:11,761][321237] Updated weights for policy 0, policy_version 8480 (0.0005) [2023-03-08 03:36:14,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11537.0, 300 sec: 11704.8). Total num frames: 4370432. Throughput: 0: 11621.3. Samples: 4370440. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:36:14,595][320945] Avg episode reward: [(0, '4763.368')] [2023-03-08 03:36:15,363][321237] Updated weights for policy 0, policy_version 8560 (0.0005) [2023-03-08 03:36:18,933][321237] Updated weights for policy 0, policy_version 8640 (0.0005) [2023-03-08 03:36:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11691.0). Total num frames: 4427776. Throughput: 0: 11581.5. Samples: 4404612. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:36:19,595][320945] Avg episode reward: [(0, '4856.508')] [2023-03-08 03:36:22,500][321237] Updated weights for policy 0, policy_version 8720 (0.0005) [2023-03-08 03:36:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11677.1). Total num frames: 4485120. Throughput: 0: 11565.6. Samples: 4473192. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:36:24,595][320945] Avg episode reward: [(0, '4857.453')] [2023-03-08 03:36:24,657][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000008768_4489216.pth... [2023-03-08 03:36:24,660][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000008088_4141056.pth [2023-03-08 03:36:26,095][321237] Updated weights for policy 0, policy_version 8800 (0.0005) [2023-03-08 03:36:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11663.2). Total num frames: 4542464. Throughput: 0: 11503.0. Samples: 4540344. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:36:29,605][320945] Avg episode reward: [(0, '4811.033')] [2023-03-08 03:36:29,797][321237] Updated weights for policy 0, policy_version 8880 (0.0005) [2023-03-08 03:36:33,486][321237] Updated weights for policy 0, policy_version 8960 (0.0005) [2023-03-08 03:36:34,594][320945] Fps is (10 sec: 11468.4, 60 sec: 11537.0, 300 sec: 11649.3). Total num frames: 4599808. Throughput: 0: 11492.1. Samples: 4574820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:36:34,605][320945] Avg episode reward: [(0, '4861.631')] [2023-03-08 03:36:37,122][321237] Updated weights for policy 0, policy_version 9040 (0.0005) [2023-03-08 03:36:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11621.5). Total num frames: 4653056. Throughput: 0: 11395.5. Samples: 4640940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:36:39,595][320945] Avg episode reward: [(0, '4860.784')] [2023-03-08 03:36:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000009088_4653056.pth... [2023-03-08 03:36:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000008432_4317184.pth [2023-03-08 03:36:40,767][321237] Updated weights for policy 0, policy_version 9120 (0.0005) [2023-03-08 03:36:44,395][321237] Updated weights for policy 0, policy_version 9200 (0.0005) [2023-03-08 03:36:44,594][320945] Fps is (10 sec: 11059.7, 60 sec: 11400.5, 300 sec: 11607.6). Total num frames: 4710400. Throughput: 0: 11385.7. Samples: 4709312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:36:44,595][320945] Avg episode reward: [(0, '4863.854')] [2023-03-08 03:36:44,595][321188] Saving new best policy, reward=4863.854! [2023-03-08 03:36:47,991][321237] Updated weights for policy 0, policy_version 9280 (0.0004) [2023-03-08 03:36:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11607.7). Total num frames: 4767744. Throughput: 0: 11376.4. Samples: 4743176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:36:49,595][320945] Avg episode reward: [(0, '4861.006')] [2023-03-08 03:36:51,671][321237] Updated weights for policy 0, policy_version 9360 (0.0005) [2023-03-08 03:36:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11607.6). Total num frames: 4820992. Throughput: 0: 11310.6. Samples: 4810248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:36:54,594][320945] Avg episode reward: [(0, '4861.754')] [2023-03-08 03:36:54,631][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000009424_4825088.pth... [2023-03-08 03:36:54,633][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000008768_4489216.pth [2023-03-08 03:36:55,418][321237] Updated weights for policy 0, policy_version 9440 (0.0005) [2023-03-08 03:36:59,096][321237] Updated weights for policy 0, policy_version 9520 (0.0005) [2023-03-08 03:36:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11593.8). Total num frames: 4878336. Throughput: 0: 11237.0. Samples: 4876104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:36:59,595][320945] Avg episode reward: [(0, '4861.684')] [2023-03-08 03:37:02,777][321237] Updated weights for policy 0, policy_version 9600 (0.0005) [2023-03-08 03:37:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11566.0). Total num frames: 4931584. Throughput: 0: 11215.7. Samples: 4909320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:37:04,595][320945] Avg episode reward: [(0, '4860.471')] [2023-03-08 03:37:06,391][321237] Updated weights for policy 0, policy_version 9680 (0.0005) [2023-03-08 03:37:09,594][320945] Fps is (10 sec: 11058.9, 60 sec: 11264.0, 300 sec: 11552.1). Total num frames: 4988928. Throughput: 0: 11197.5. Samples: 4977080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:37:09,595][320945] Avg episode reward: [(0, '4862.712')] [2023-03-08 03:37:09,626][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000009752_4993024.pth... [2023-03-08 03:37:09,628][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000009088_4653056.pth [2023-03-08 03:37:09,960][321237] Updated weights for policy 0, policy_version 9760 (0.0005) [2023-03-08 03:37:13,521][321237] Updated weights for policy 0, policy_version 9840 (0.0005) [2023-03-08 03:37:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11552.1). Total num frames: 5046272. Throughput: 0: 11243.0. Samples: 5046280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:37:14,594][320945] Avg episode reward: [(0, '4863.029')] [2023-03-08 03:37:17,166][321237] Updated weights for policy 0, policy_version 9920 (0.0005) [2023-03-08 03:37:19,594][320945] Fps is (10 sec: 11469.0, 60 sec: 11264.0, 300 sec: 11552.1). Total num frames: 5103616. Throughput: 0: 11222.5. Samples: 5079828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:37:19,595][320945] Avg episode reward: [(0, '4863.199')] [2023-03-08 03:37:20,791][321237] Updated weights for policy 0, policy_version 10000 (0.0005) [2023-03-08 03:37:24,372][321237] Updated weights for policy 0, policy_version 10080 (0.0005) [2023-03-08 03:37:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11538.2). Total num frames: 5160960. Throughput: 0: 11279.3. Samples: 5148508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:37:24,595][320945] Avg episode reward: [(0, '4860.872')] [2023-03-08 03:37:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000010080_5160960.pth... [2023-03-08 03:37:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000009424_4825088.pth [2023-03-08 03:37:28,028][321237] Updated weights for policy 0, policy_version 10160 (0.0005) [2023-03-08 03:37:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 5218304. Throughput: 0: 11262.7. Samples: 5216132. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:37:29,595][320945] Avg episode reward: [(0, '4861.193')] [2023-03-08 03:37:31,643][321237] Updated weights for policy 0, policy_version 10240 (0.0005) [2023-03-08 03:37:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.1, 300 sec: 11496.6). Total num frames: 5275648. Throughput: 0: 11268.9. Samples: 5250276. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:37:34,595][320945] Avg episode reward: [(0, '4861.824')] [2023-03-08 03:37:35,234][321237] Updated weights for policy 0, policy_version 10320 (0.0005) [2023-03-08 03:37:38,938][321237] Updated weights for policy 0, policy_version 10400 (0.0005) [2023-03-08 03:37:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11468.8). Total num frames: 5328896. Throughput: 0: 11263.1. Samples: 5317088. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:37:39,595][320945] Avg episode reward: [(0, '4863.351')] [2023-03-08 03:37:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000010408_5328896.pth... [2023-03-08 03:37:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000009752_4993024.pth [2023-03-08 03:37:42,574][321237] Updated weights for policy 0, policy_version 10480 (0.0005) [2023-03-08 03:37:44,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11468.8). Total num frames: 5386240. Throughput: 0: 11323.5. Samples: 5385664. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:37:44,595][320945] Avg episode reward: [(0, '4861.948')] [2023-03-08 03:37:46,178][321237] Updated weights for policy 0, policy_version 10560 (0.0005) [2023-03-08 03:37:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11454.9). Total num frames: 5443584. Throughput: 0: 11326.4. Samples: 5419008. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:37:49,595][320945] Avg episode reward: [(0, '4863.696')] [2023-03-08 03:37:49,904][321237] Updated weights for policy 0, policy_version 10640 (0.0005) [2023-03-08 03:37:53,571][321237] Updated weights for policy 0, policy_version 10720 (0.0005) [2023-03-08 03:37:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11427.1). Total num frames: 5496832. Throughput: 0: 11287.3. Samples: 5485004. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:37:54,594][320945] Avg episode reward: [(0, '4861.493')] [2023-03-08 03:37:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000010736_5496832.pth... [2023-03-08 03:37:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000010080_5160960.pth [2023-03-08 03:37:57,233][321237] Updated weights for policy 0, policy_version 10800 (0.0005) [2023-03-08 03:37:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11413.3). Total num frames: 5554176. Throughput: 0: 11245.1. Samples: 5552308. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:37:59,595][320945] Avg episode reward: [(0, '4861.029')] [2023-03-08 03:38:00,966][321237] Updated weights for policy 0, policy_version 10880 (0.0005) [2023-03-08 03:38:04,584][321237] Updated weights for policy 0, policy_version 10960 (0.0005) [2023-03-08 03:38:04,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11332.2, 300 sec: 11413.3). Total num frames: 5611520. Throughput: 0: 11230.9. Samples: 5585220. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:38:04,595][320945] Avg episode reward: [(0, '4860.561')] [2023-03-08 03:38:08,232][321237] Updated weights for policy 0, policy_version 11040 (0.0005) [2023-03-08 03:38:09,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11399.4). Total num frames: 5664768. Throughput: 0: 11201.0. Samples: 5652552. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:38:09,595][320945] Avg episode reward: [(0, '4814.411')] [2023-03-08 03:38:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000011064_5664768.pth... [2023-03-08 03:38:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000010408_5328896.pth [2023-03-08 03:38:11,926][321237] Updated weights for policy 0, policy_version 11120 (0.0005) [2023-03-08 03:38:14,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11413.3). Total num frames: 5722112. Throughput: 0: 11189.9. Samples: 5719680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:38:14,595][320945] Avg episode reward: [(0, '4858.290')] [2023-03-08 03:38:15,564][321237] Updated weights for policy 0, policy_version 11200 (0.0005) [2023-03-08 03:38:19,154][321237] Updated weights for policy 0, policy_version 11280 (0.0005) [2023-03-08 03:38:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11413.3). Total num frames: 5779456. Throughput: 0: 11189.8. Samples: 5753816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:38:19,595][320945] Avg episode reward: [(0, '4860.313')] [2023-03-08 03:38:22,829][321237] Updated weights for policy 0, policy_version 11360 (0.0005) [2023-03-08 03:38:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11413.3). Total num frames: 5836800. Throughput: 0: 11191.5. Samples: 5820708. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:38:24,595][320945] Avg episode reward: [(0, '4857.423')] [2023-03-08 03:38:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000011400_5836800.pth... [2023-03-08 03:38:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000010736_5496832.pth [2023-03-08 03:38:26,231][321237] Updated weights for policy 0, policy_version 11440 (0.0004) [2023-03-08 03:38:29,598][320945] Fps is (10 sec: 11464.1, 60 sec: 11263.2, 300 sec: 11413.1). Total num frames: 5894144. Throughput: 0: 11213.1. Samples: 5890300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:38:29,599][320945] Avg episode reward: [(0, '4858.648')] [2023-03-08 03:38:29,944][321237] Updated weights for policy 0, policy_version 11520 (0.0005) [2023-03-08 03:38:33,494][321237] Updated weights for policy 0, policy_version 11600 (0.0005) [2023-03-08 03:38:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11413.3). Total num frames: 5951488. Throughput: 0: 11242.5. Samples: 5924920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:38:34,595][320945] Avg episode reward: [(0, '4763.736')] [2023-03-08 03:38:36,967][321237] Updated weights for policy 0, policy_version 11680 (0.0004) [2023-03-08 03:38:39,594][320945] Fps is (10 sec: 11473.5, 60 sec: 11332.3, 300 sec: 11427.1). Total num frames: 6008832. Throughput: 0: 11338.9. Samples: 5995256. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:38:39,595][320945] Avg episode reward: [(0, '4719.353')] [2023-03-08 03:38:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000011736_6008832.pth... [2023-03-08 03:38:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000011064_5664768.pth [2023-03-08 03:38:40,603][321237] Updated weights for policy 0, policy_version 11760 (0.0005) [2023-03-08 03:38:44,083][321237] Updated weights for policy 0, policy_version 11840 (0.0005) [2023-03-08 03:38:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11413.3). Total num frames: 6066176. Throughput: 0: 11377.4. Samples: 6064292. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:38:44,595][320945] Avg episode reward: [(0, '4856.939')] [2023-03-08 03:38:47,328][321237] Updated weights for policy 0, policy_version 11920 (0.0004) [2023-03-08 03:38:49,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11441.0). Total num frames: 6127616. Throughput: 0: 11497.2. Samples: 6102592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:38:49,595][320945] Avg episode reward: [(0, '4720.401')] [2023-03-08 03:38:50,802][321237] Updated weights for policy 0, policy_version 12000 (0.0004) [2023-03-08 03:38:54,347][321237] Updated weights for policy 0, policy_version 12080 (0.0005) [2023-03-08 03:38:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11468.8, 300 sec: 11454.9). Total num frames: 6184960. Throughput: 0: 11558.5. Samples: 6172684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:38:54,595][320945] Avg episode reward: [(0, '4675.801')] [2023-03-08 03:38:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000012080_6184960.pth... [2023-03-08 03:38:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000011400_5836800.pth [2023-03-08 03:38:58,030][321237] Updated weights for policy 0, policy_version 12160 (0.0005) [2023-03-08 03:38:59,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 11468.8). Total num frames: 6242304. Throughput: 0: 11539.5. Samples: 6238960. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:38:59,595][320945] Avg episode reward: [(0, '4681.076')] [2023-03-08 03:39:01,790][321237] Updated weights for policy 0, policy_version 12240 (0.0005) [2023-03-08 03:39:04,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11400.5, 300 sec: 11454.9). Total num frames: 6295552. Throughput: 0: 11519.7. Samples: 6272204. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:39:04,595][320945] Avg episode reward: [(0, '4817.365')] [2023-03-08 03:39:05,343][321237] Updated weights for policy 0, policy_version 12320 (0.0005) [2023-03-08 03:39:08,875][321237] Updated weights for policy 0, policy_version 12400 (0.0005) [2023-03-08 03:39:09,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11454.9). Total num frames: 6356992. Throughput: 0: 11570.3. Samples: 6341372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:39:09,595][320945] Avg episode reward: [(0, '4768.204')] [2023-03-08 03:39:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000012416_6356992.pth... [2023-03-08 03:39:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000011736_6008832.pth [2023-03-08 03:39:12,440][321237] Updated weights for policy 0, policy_version 12480 (0.0004) [2023-03-08 03:39:14,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11427.1). Total num frames: 6410240. Throughput: 0: 11556.7. Samples: 6410304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:39:14,594][320945] Avg episode reward: [(0, '4766.669')] [2023-03-08 03:39:16,032][321237] Updated weights for policy 0, policy_version 12560 (0.0005) [2023-03-08 03:39:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11427.1). Total num frames: 6467584. Throughput: 0: 11550.1. Samples: 6444676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:39:19,594][320945] Avg episode reward: [(0, '4814.591')] [2023-03-08 03:39:19,640][321237] Updated weights for policy 0, policy_version 12640 (0.0005) [2023-03-08 03:39:23,130][321237] Updated weights for policy 0, policy_version 12720 (0.0005) [2023-03-08 03:39:24,594][320945] Fps is (10 sec: 11878.2, 60 sec: 11537.1, 300 sec: 11427.1). Total num frames: 6529024. Throughput: 0: 11533.8. Samples: 6514276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:39:24,595][320945] Avg episode reward: [(0, '4810.204')] [2023-03-08 03:39:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000012752_6529024.pth... [2023-03-08 03:39:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000012080_6184960.pth [2023-03-08 03:39:26,783][321237] Updated weights for policy 0, policy_version 12800 (0.0005) [2023-03-08 03:39:29,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11537.9, 300 sec: 11441.0). Total num frames: 6586368. Throughput: 0: 11517.2. Samples: 6582564. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:39:29,595][320945] Avg episode reward: [(0, '4807.714')] [2023-03-08 03:39:30,272][321237] Updated weights for policy 0, policy_version 12880 (0.0005) [2023-03-08 03:39:33,898][321237] Updated weights for policy 0, policy_version 12960 (0.0005) [2023-03-08 03:39:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11427.1). Total num frames: 6639616. Throughput: 0: 11434.8. Samples: 6617156. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:39:34,595][320945] Avg episode reward: [(0, '4809.313')] [2023-03-08 03:39:37,524][321237] Updated weights for policy 0, policy_version 13040 (0.0005) [2023-03-08 03:39:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11427.1). Total num frames: 6696960. Throughput: 0: 11382.3. Samples: 6684888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:39:39,595][320945] Avg episode reward: [(0, '4859.852')] [2023-03-08 03:39:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000013080_6696960.pth... [2023-03-08 03:39:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000012416_6356992.pth [2023-03-08 03:39:41,128][321237] Updated weights for policy 0, policy_version 13120 (0.0004) [2023-03-08 03:39:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11413.3). Total num frames: 6754304. Throughput: 0: 11390.3. Samples: 6751520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:39:44,595][320945] Avg episode reward: [(0, '4767.828')] [2023-03-08 03:39:44,858][321237] Updated weights for policy 0, policy_version 13200 (0.0005) [2023-03-08 03:39:48,636][321237] Updated weights for policy 0, policy_version 13280 (0.0005) [2023-03-08 03:39:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11399.4). Total num frames: 6807552. Throughput: 0: 11383.9. Samples: 6784480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:39:49,595][320945] Avg episode reward: [(0, '4726.661')] [2023-03-08 03:39:52,296][321237] Updated weights for policy 0, policy_version 13360 (0.0005) [2023-03-08 03:39:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11385.5). Total num frames: 6864896. Throughput: 0: 11326.7. Samples: 6851072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:39:54,595][320945] Avg episode reward: [(0, '4814.825')] [2023-03-08 03:39:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000013408_6864896.pth... [2023-03-08 03:39:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000012752_6529024.pth [2023-03-08 03:39:56,011][321237] Updated weights for policy 0, policy_version 13440 (0.0005) [2023-03-08 03:39:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11357.7). Total num frames: 6918144. Throughput: 0: 11258.7. Samples: 6916948. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:39:59,595][320945] Avg episode reward: [(0, '4768.967')] [2023-03-08 03:39:59,778][321237] Updated weights for policy 0, policy_version 13520 (0.0005) [2023-03-08 03:40:03,506][321237] Updated weights for policy 0, policy_version 13600 (0.0005) [2023-03-08 03:40:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 11343.8). Total num frames: 6971392. Throughput: 0: 11223.3. Samples: 6949724. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:40:04,595][320945] Avg episode reward: [(0, '4683.334')] [2023-03-08 03:40:07,319][321237] Updated weights for policy 0, policy_version 13680 (0.0005) [2023-03-08 03:40:09,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11357.7). Total num frames: 7028736. Throughput: 0: 11129.3. Samples: 7015096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:40:09,595][320945] Avg episode reward: [(0, '4817.208')] [2023-03-08 03:40:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000013728_7028736.pth... [2023-03-08 03:40:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000013080_6696960.pth [2023-03-08 03:40:11,075][321237] Updated weights for policy 0, policy_version 13760 (0.0005) [2023-03-08 03:40:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11343.8). Total num frames: 7081984. Throughput: 0: 11042.2. Samples: 7079464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:40:14,595][320945] Avg episode reward: [(0, '4725.213')] [2023-03-08 03:40:14,867][321237] Updated weights for policy 0, policy_version 13840 (0.0005) [2023-03-08 03:40:18,487][321237] Updated weights for policy 0, policy_version 13920 (0.0005) [2023-03-08 03:40:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11330.0). Total num frames: 7135232. Throughput: 0: 11046.0. Samples: 7114228. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:40:19,595][320945] Avg episode reward: [(0, '4860.849')] [2023-03-08 03:40:22,276][321237] Updated weights for policy 0, policy_version 14000 (0.0005) [2023-03-08 03:40:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11330.0). Total num frames: 7192576. Throughput: 0: 10993.4. Samples: 7179592. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:40:24,595][320945] Avg episode reward: [(0, '4860.290')] [2023-03-08 03:40:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000014048_7192576.pth... [2023-03-08 03:40:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000013408_6864896.pth [2023-03-08 03:40:25,955][321237] Updated weights for policy 0, policy_version 14080 (0.0005) [2023-03-08 03:40:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11316.1). Total num frames: 7245824. Throughput: 0: 10984.7. Samples: 7245832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:40:29,605][320945] Avg episode reward: [(0, '4860.903')] [2023-03-08 03:40:29,648][321237] Updated weights for policy 0, policy_version 14160 (0.0005) [2023-03-08 03:40:33,277][321237] Updated weights for policy 0, policy_version 14240 (0.0005) [2023-03-08 03:40:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11059.2, 300 sec: 11316.1). Total num frames: 7303168. Throughput: 0: 10985.7. Samples: 7278836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:40:34,605][320945] Avg episode reward: [(0, '4862.891')] [2023-03-08 03:40:36,723][321237] Updated weights for policy 0, policy_version 14320 (0.0004) [2023-03-08 03:40:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11127.5, 300 sec: 11316.1). Total num frames: 7364608. Throughput: 0: 11089.4. Samples: 7350096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:40:39,605][320945] Avg episode reward: [(0, '4862.219')] [2023-03-08 03:40:39,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000014384_7364608.pth... [2023-03-08 03:40:39,612][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000013728_7028736.pth [2023-03-08 03:40:40,143][321237] Updated weights for policy 0, policy_version 14400 (0.0004) [2023-03-08 03:40:43,635][321237] Updated weights for policy 0, policy_version 14480 (0.0005) [2023-03-08 03:40:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11127.5, 300 sec: 11316.1). Total num frames: 7421952. Throughput: 0: 11210.0. Samples: 7421400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:40:44,605][320945] Avg episode reward: [(0, '4861.955')] [2023-03-08 03:40:47,127][321237] Updated weights for policy 0, policy_version 14560 (0.0004) [2023-03-08 03:40:49,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11264.0, 300 sec: 11330.0). Total num frames: 7483392. Throughput: 0: 11252.4. Samples: 7456080. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:40:49,595][320945] Avg episode reward: [(0, '4862.790')] [2023-03-08 03:40:50,599][321237] Updated weights for policy 0, policy_version 14640 (0.0004) [2023-03-08 03:40:53,846][321237] Updated weights for policy 0, policy_version 14720 (0.0004) [2023-03-08 03:40:54,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11332.3, 300 sec: 11343.8). Total num frames: 7544832. Throughput: 0: 11435.0. Samples: 7529672. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:40:54,595][320945] Avg episode reward: [(0, '4771.656')] [2023-03-08 03:40:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000014736_7544832.pth... [2023-03-08 03:40:54,602][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000014048_7192576.pth [2023-03-08 03:40:57,358][321237] Updated weights for policy 0, policy_version 14800 (0.0003) [2023-03-08 03:40:59,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11400.5, 300 sec: 11343.8). Total num frames: 7602176. Throughput: 0: 11539.7. Samples: 7598752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:40:59,595][320945] Avg episode reward: [(0, '4862.322')] [2023-03-08 03:41:00,971][321237] Updated weights for policy 0, policy_version 14880 (0.0005) [2023-03-08 03:41:04,375][321237] Updated weights for policy 0, policy_version 14960 (0.0005) [2023-03-08 03:41:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11343.8). Total num frames: 7659520. Throughput: 0: 11561.7. Samples: 7634504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:41:04,595][320945] Avg episode reward: [(0, '4860.777')] [2023-03-08 03:41:07,775][321237] Updated weights for policy 0, policy_version 15040 (0.0005) [2023-03-08 03:41:09,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11537.1, 300 sec: 11357.7). Total num frames: 7720960. Throughput: 0: 11702.0. Samples: 7706180. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:41:09,595][320945] Avg episode reward: [(0, '4859.892')] [2023-03-08 03:41:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000015080_7720960.pth... [2023-03-08 03:41:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000014384_7364608.pth [2023-03-08 03:41:11,230][321237] Updated weights for policy 0, policy_version 15120 (0.0005) [2023-03-08 03:41:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11357.7). Total num frames: 7778304. Throughput: 0: 11748.8. Samples: 7774528. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:41:14,595][320945] Avg episode reward: [(0, '4861.129')] [2023-03-08 03:41:14,967][321237] Updated weights for policy 0, policy_version 15200 (0.0005) [2023-03-08 03:41:18,842][321237] Updated weights for policy 0, policy_version 15280 (0.0005) [2023-03-08 03:41:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11343.8). Total num frames: 7831552. Throughput: 0: 11736.6. Samples: 7806984. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:41:19,595][320945] Avg episode reward: [(0, '4862.101')] [2023-03-08 03:41:22,594][321237] Updated weights for policy 0, policy_version 15360 (0.0006) [2023-03-08 03:41:24,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11537.1, 300 sec: 11330.0). Total num frames: 7884800. Throughput: 0: 11606.4. Samples: 7872384. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:41:24,595][320945] Avg episode reward: [(0, '4863.097')] [2023-03-08 03:41:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000015400_7884800.pth... [2023-03-08 03:41:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000014736_7544832.pth [2023-03-08 03:41:26,303][321237] Updated weights for policy 0, policy_version 15440 (0.0005) [2023-03-08 03:41:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11537.1, 300 sec: 11316.1). Total num frames: 7938048. Throughput: 0: 11481.4. Samples: 7938064. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:41:29,595][320945] Avg episode reward: [(0, '4863.446')] [2023-03-08 03:41:30,068][321237] Updated weights for policy 0, policy_version 15520 (0.0006) [2023-03-08 03:41:33,858][321237] Updated weights for policy 0, policy_version 15600 (0.0006) [2023-03-08 03:41:34,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11468.8, 300 sec: 11316.1). Total num frames: 7991296. Throughput: 0: 11438.8. Samples: 7970824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:41:34,595][320945] Avg episode reward: [(0, '4769.877')] [2023-03-08 03:41:37,522][321237] Updated weights for policy 0, policy_version 15680 (0.0005) [2023-03-08 03:41:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11316.1). Total num frames: 8048640. Throughput: 0: 11259.7. Samples: 8036360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:41:39,595][320945] Avg episode reward: [(0, '4783.804')] [2023-03-08 03:41:39,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000015720_8048640.pth... [2023-03-08 03:41:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000015080_7720960.pth [2023-03-08 03:41:41,255][321237] Updated weights for policy 0, policy_version 15760 (0.0006) [2023-03-08 03:41:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11302.2). Total num frames: 8101888. Throughput: 0: 11183.5. Samples: 8102008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:41:44,595][320945] Avg episode reward: [(0, '4725.671')] [2023-03-08 03:41:44,998][321237] Updated weights for policy 0, policy_version 15840 (0.0005) [2023-03-08 03:41:48,618][321237] Updated weights for policy 0, policy_version 15920 (0.0005) [2023-03-08 03:41:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11316.1). Total num frames: 8159232. Throughput: 0: 11126.9. Samples: 8135216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:41:49,595][320945] Avg episode reward: [(0, '4863.019')] [2023-03-08 03:41:52,338][321237] Updated weights for policy 0, policy_version 16000 (0.0005) [2023-03-08 03:41:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11195.7, 300 sec: 11316.1). Total num frames: 8216576. Throughput: 0: 11030.3. Samples: 8202544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:41:54,595][320945] Avg episode reward: [(0, '4862.790')] [2023-03-08 03:41:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000016048_8216576.pth... [2023-03-08 03:41:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000015400_7884800.pth [2023-03-08 03:41:56,007][321237] Updated weights for policy 0, policy_version 16080 (0.0005) [2023-03-08 03:41:59,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11127.5, 300 sec: 11316.1). Total num frames: 8269824. Throughput: 0: 11006.6. Samples: 8269824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:41:59,594][320945] Avg episode reward: [(0, '4859.409')] [2023-03-08 03:41:59,644][321237] Updated weights for policy 0, policy_version 16160 (0.0005) [2023-03-08 03:42:03,431][321237] Updated weights for policy 0, policy_version 16240 (0.0004) [2023-03-08 03:42:04,594][320945] Fps is (10 sec: 11059.4, 60 sec: 11127.5, 300 sec: 11316.1). Total num frames: 8327168. Throughput: 0: 11015.0. Samples: 8302656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:42:04,594][320945] Avg episode reward: [(0, '4862.858')] [2023-03-08 03:42:07,035][321237] Updated weights for policy 0, policy_version 16320 (0.0005) [2023-03-08 03:42:09,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11059.2, 300 sec: 11316.1). Total num frames: 8384512. Throughput: 0: 11071.4. Samples: 8370596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:42:09,595][320945] Avg episode reward: [(0, '4862.083')] [2023-03-08 03:42:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000016376_8384512.pth... [2023-03-08 03:42:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000015720_8048640.pth [2023-03-08 03:42:10,522][321237] Updated weights for policy 0, policy_version 16400 (0.0005) [2023-03-08 03:42:14,104][321237] Updated weights for policy 0, policy_version 16480 (0.0004) [2023-03-08 03:42:14,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11059.2, 300 sec: 11316.1). Total num frames: 8441856. Throughput: 0: 11148.8. Samples: 8439760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:42:14,594][320945] Avg episode reward: [(0, '4865.404')] [2023-03-08 03:42:14,595][321188] Saving new best policy, reward=4865.404! [2023-03-08 03:42:17,778][321237] Updated weights for policy 0, policy_version 16560 (0.0004) [2023-03-08 03:42:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 11316.1). Total num frames: 8499200. Throughput: 0: 11162.7. Samples: 8473144. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:42:19,595][320945] Avg episode reward: [(0, '4863.453')] [2023-03-08 03:42:21,427][321237] Updated weights for policy 0, policy_version 16640 (0.0005) [2023-03-08 03:42:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.8, 300 sec: 11316.1). Total num frames: 8556544. Throughput: 0: 11214.1. Samples: 8540992. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:42:24,594][320945] Avg episode reward: [(0, '4862.990')] [2023-03-08 03:42:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000016712_8556544.pth... [2023-03-08 03:42:24,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000016048_8216576.pth [2023-03-08 03:42:24,962][321237] Updated weights for policy 0, policy_version 16720 (0.0005) [2023-03-08 03:42:28,602][321237] Updated weights for policy 0, policy_version 16800 (0.0005) [2023-03-08 03:42:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11302.2). Total num frames: 8609792. Throughput: 0: 11276.0. Samples: 8609428. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:42:29,595][320945] Avg episode reward: [(0, '4863.988')] [2023-03-08 03:42:32,271][321237] Updated weights for policy 0, policy_version 16880 (0.0005) [2023-03-08 03:42:34,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11316.1). Total num frames: 8667136. Throughput: 0: 11275.7. Samples: 8642624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:42:34,595][320945] Avg episode reward: [(0, '4820.107')] [2023-03-08 03:42:35,906][321237] Updated weights for policy 0, policy_version 16960 (0.0005) [2023-03-08 03:42:39,428][321237] Updated weights for policy 0, policy_version 17040 (0.0005) [2023-03-08 03:42:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11316.1). Total num frames: 8724480. Throughput: 0: 11314.3. Samples: 8711688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:42:39,595][320945] Avg episode reward: [(0, '4862.460')] [2023-03-08 03:42:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000017040_8724480.pth... [2023-03-08 03:42:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000016376_8384512.pth [2023-03-08 03:42:43,146][321237] Updated weights for policy 0, policy_version 17120 (0.0005) [2023-03-08 03:42:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11302.2). Total num frames: 8777728. Throughput: 0: 11288.2. Samples: 8777792. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:42:44,595][320945] Avg episode reward: [(0, '4861.984')] [2023-03-08 03:42:46,833][321237] Updated weights for policy 0, policy_version 17200 (0.0005) [2023-03-08 03:42:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11316.1). Total num frames: 8835072. Throughput: 0: 11300.1. Samples: 8811160. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:42:49,595][320945] Avg episode reward: [(0, '4862.022')] [2023-03-08 03:42:50,455][321237] Updated weights for policy 0, policy_version 17280 (0.0004) [2023-03-08 03:42:54,110][321237] Updated weights for policy 0, policy_version 17360 (0.0005) [2023-03-08 03:42:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11316.1). Total num frames: 8892416. Throughput: 0: 11288.2. Samples: 8878564. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:42:54,595][320945] Avg episode reward: [(0, '4859.780')] [2023-03-08 03:42:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000017368_8892416.pth... [2023-03-08 03:42:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000016712_8556544.pth [2023-03-08 03:42:57,766][321237] Updated weights for policy 0, policy_version 17440 (0.0005) [2023-03-08 03:42:59,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11332.2, 300 sec: 11316.1). Total num frames: 8949760. Throughput: 0: 11279.3. Samples: 8947328. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:42:59,605][320945] Avg episode reward: [(0, '4861.648')] [2023-03-08 03:43:01,243][321237] Updated weights for policy 0, policy_version 17520 (0.0005) [2023-03-08 03:43:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11330.0). Total num frames: 9007104. Throughput: 0: 11319.7. Samples: 8982528. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:43:04,605][320945] Avg episode reward: [(0, '4860.772')] [2023-03-08 03:43:04,798][321237] Updated weights for policy 0, policy_version 17600 (0.0004) [2023-03-08 03:43:08,382][321237] Updated weights for policy 0, policy_version 17680 (0.0005) [2023-03-08 03:43:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11330.0). Total num frames: 9064448. Throughput: 0: 11337.0. Samples: 9051160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:43:09,605][320945] Avg episode reward: [(0, '4817.295')] [2023-03-08 03:43:09,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000017704_9064448.pth... [2023-03-08 03:43:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000017040_8724480.pth [2023-03-08 03:43:11,930][321237] Updated weights for policy 0, policy_version 17760 (0.0005) [2023-03-08 03:43:14,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11330.0). Total num frames: 9121792. Throughput: 0: 11343.7. Samples: 9119896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:43:14,605][320945] Avg episode reward: [(0, '4860.020')] [2023-03-08 03:43:15,503][321237] Updated weights for policy 0, policy_version 17840 (0.0004) [2023-03-08 03:43:19,126][321237] Updated weights for policy 0, policy_version 17920 (0.0005) [2023-03-08 03:43:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11330.0). Total num frames: 9179136. Throughput: 0: 11376.4. Samples: 9154560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:43:19,605][320945] Avg episode reward: [(0, '4859.860')] [2023-03-08 03:43:22,741][321237] Updated weights for policy 0, policy_version 18000 (0.0005) [2023-03-08 03:43:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11330.1). Total num frames: 9236480. Throughput: 0: 11350.3. Samples: 9222452. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:43:24,605][320945] Avg episode reward: [(0, '4855.381')] [2023-03-08 03:43:24,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000018040_9236480.pth... [2023-03-08 03:43:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000017368_8892416.pth [2023-03-08 03:43:26,259][321237] Updated weights for policy 0, policy_version 18080 (0.0005) [2023-03-08 03:43:29,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11330.0). Total num frames: 9293824. Throughput: 0: 11426.8. Samples: 9291996. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:43:29,605][320945] Avg episode reward: [(0, '4671.913')] [2023-03-08 03:43:29,782][321237] Updated weights for policy 0, policy_version 18160 (0.0005) [2023-03-08 03:43:33,447][321237] Updated weights for policy 0, policy_version 18240 (0.0006) [2023-03-08 03:43:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11330.0). Total num frames: 9351168. Throughput: 0: 11450.7. Samples: 9326440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:43:34,605][320945] Avg episode reward: [(0, '4806.903')] [2023-03-08 03:43:37,030][321237] Updated weights for policy 0, policy_version 18320 (0.0005) [2023-03-08 03:43:39,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11332.3, 300 sec: 11316.1). Total num frames: 9404416. Throughput: 0: 11430.7. Samples: 9392944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:43:39,605][320945] Avg episode reward: [(0, '4803.937')] [2023-03-08 03:43:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000018376_9408512.pth... [2023-03-08 03:43:39,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000017704_9064448.pth [2023-03-08 03:43:40,670][321237] Updated weights for policy 0, policy_version 18400 (0.0005) [2023-03-08 03:43:44,334][321237] Updated weights for policy 0, policy_version 18480 (0.0005) [2023-03-08 03:43:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11302.2). Total num frames: 9461760. Throughput: 0: 11424.3. Samples: 9461420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:43:44,605][320945] Avg episode reward: [(0, '4807.730')] [2023-03-08 03:43:47,982][321237] Updated weights for policy 0, policy_version 18560 (0.0005) [2023-03-08 03:43:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11302.2). Total num frames: 9519104. Throughput: 0: 11378.2. Samples: 9494548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:43:49,605][320945] Avg episode reward: [(0, '4672.924')] [2023-03-08 03:43:51,630][321237] Updated weights for policy 0, policy_version 18640 (0.0005) [2023-03-08 03:43:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11302.2). Total num frames: 9576448. Throughput: 0: 11359.6. Samples: 9562340. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:43:54,595][320945] Avg episode reward: [(0, '4804.541')] [2023-03-08 03:43:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000018704_9576448.pth... [2023-03-08 03:43:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000018040_9236480.pth [2023-03-08 03:43:55,262][321237] Updated weights for policy 0, policy_version 18720 (0.0005) [2023-03-08 03:43:58,862][321237] Updated weights for policy 0, policy_version 18800 (0.0005) [2023-03-08 03:43:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11302.2). Total num frames: 9629696. Throughput: 0: 11330.5. Samples: 9629768. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:43:59,595][320945] Avg episode reward: [(0, '4547.168')] [2023-03-08 03:44:02,510][321237] Updated weights for policy 0, policy_version 18880 (0.0006) [2023-03-08 03:44:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11288.3). Total num frames: 9687040. Throughput: 0: 11321.2. Samples: 9664016. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:44:04,595][320945] Avg episode reward: [(0, '4718.802')] [2023-03-08 03:44:06,190][321237] Updated weights for policy 0, policy_version 18960 (0.0005) [2023-03-08 03:44:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11302.2). Total num frames: 9744384. Throughput: 0: 11323.3. Samples: 9732000. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:44:09,595][320945] Avg episode reward: [(0, '4763.393')] [2023-03-08 03:44:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000019032_9744384.pth... [2023-03-08 03:44:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000018376_9408512.pth [2023-03-08 03:44:09,843][321237] Updated weights for policy 0, policy_version 19040 (0.0005) [2023-03-08 03:44:13,520][321237] Updated weights for policy 0, policy_version 19120 (0.0005) [2023-03-08 03:44:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11288.3). Total num frames: 9797632. Throughput: 0: 11237.8. Samples: 9797696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:44:14,595][320945] Avg episode reward: [(0, '4721.797')] [2023-03-08 03:44:17,208][321237] Updated weights for policy 0, policy_version 19200 (0.0005) [2023-03-08 03:44:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11274.4). Total num frames: 9854976. Throughput: 0: 11206.6. Samples: 9830736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:44:19,595][320945] Avg episode reward: [(0, '4728.066')] [2023-03-08 03:44:20,782][321237] Updated weights for policy 0, policy_version 19280 (0.0005) [2023-03-08 03:44:24,375][321237] Updated weights for policy 0, policy_version 19360 (0.0005) [2023-03-08 03:44:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11274.4). Total num frames: 9912320. Throughput: 0: 11268.6. Samples: 9900032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:44:24,595][320945] Avg episode reward: [(0, '4775.451')] [2023-03-08 03:44:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000019360_9912320.pth... [2023-03-08 03:44:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000018704_9576448.pth [2023-03-08 03:44:28,016][321237] Updated weights for policy 0, policy_version 19440 (0.0005) [2023-03-08 03:44:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11288.3). Total num frames: 9969664. Throughput: 0: 11258.5. Samples: 9968052. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:44:29,595][320945] Avg episode reward: [(0, '4727.922')] [2023-03-08 03:44:31,696][321237] Updated weights for policy 0, policy_version 19520 (0.0005) [2023-03-08 03:44:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11288.3). Total num frames: 10027008. Throughput: 0: 11236.0. Samples: 10000168. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:44:34,595][320945] Avg episode reward: [(0, '4810.172')] [2023-03-08 03:44:35,291][321237] Updated weights for policy 0, policy_version 19600 (0.0005) [2023-03-08 03:44:38,791][321237] Updated weights for policy 0, policy_version 19680 (0.0004) [2023-03-08 03:44:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11288.3). Total num frames: 10084352. Throughput: 0: 11291.2. Samples: 10070444. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:44:39,595][320945] Avg episode reward: [(0, '4857.187')] [2023-03-08 03:44:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000019696_10084352.pth... [2023-03-08 03:44:39,602][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000019032_9744384.pth [2023-03-08 03:44:42,479][321237] Updated weights for policy 0, policy_version 19760 (0.0003) [2023-03-08 03:44:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11288.3). Total num frames: 10137600. Throughput: 0: 11284.4. Samples: 10137564. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:44:44,595][320945] Avg episode reward: [(0, '4737.466')] [2023-03-08 03:44:46,063][321237] Updated weights for policy 0, policy_version 19840 (0.0004) [2023-03-08 03:44:49,482][321237] Updated weights for policy 0, policy_version 19920 (0.0005) [2023-03-08 03:44:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11302.2). Total num frames: 10199040. Throughput: 0: 11295.4. Samples: 10172308. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:44:49,595][320945] Avg episode reward: [(0, '4722.778')] [2023-03-08 03:44:52,838][321237] Updated weights for policy 0, policy_version 20000 (0.0005) [2023-03-08 03:44:54,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11400.5, 300 sec: 11329.9). Total num frames: 10260480. Throughput: 0: 11408.2. Samples: 10245368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:44:54,595][320945] Avg episode reward: [(0, '4810.887')] [2023-03-08 03:44:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000020040_10260480.pth... [2023-03-08 03:44:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000019360_9912320.pth [2023-03-08 03:44:56,260][321237] Updated weights for policy 0, policy_version 20080 (0.0005) [2023-03-08 03:44:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11343.8). Total num frames: 10317824. Throughput: 0: 11523.9. Samples: 10316272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:44:59,605][320945] Avg episode reward: [(0, '4769.498')] [2023-03-08 03:44:59,718][321237] Updated weights for policy 0, policy_version 20160 (0.0005) [2023-03-08 03:45:03,173][321237] Updated weights for policy 0, policy_version 20240 (0.0005) [2023-03-08 03:45:04,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11537.1, 300 sec: 11357.7). Total num frames: 10379264. Throughput: 0: 11597.5. Samples: 10352624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:45:04,595][320945] Avg episode reward: [(0, '4725.522')] [2023-03-08 03:45:06,662][321237] Updated weights for policy 0, policy_version 20320 (0.0005) [2023-03-08 03:45:09,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11605.3, 300 sec: 11385.5). Total num frames: 10440704. Throughput: 0: 11651.1. Samples: 10424332. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:45:09,605][320945] Avg episode reward: [(0, '4811.945')] [2023-03-08 03:45:09,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000020392_10440704.pth... [2023-03-08 03:45:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000019696_10084352.pth [2023-03-08 03:45:09,911][321237] Updated weights for policy 0, policy_version 20400 (0.0004) [2023-03-08 03:45:13,257][321237] Updated weights for policy 0, policy_version 20480 (0.0005) [2023-03-08 03:45:14,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11413.3). Total num frames: 10502144. Throughput: 0: 11779.1. Samples: 10498112. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:45:14,605][320945] Avg episode reward: [(0, '4854.444')] [2023-03-08 03:45:16,699][321237] Updated weights for policy 0, policy_version 20560 (0.0005) [2023-03-08 03:45:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11413.3). Total num frames: 10559488. Throughput: 0: 11848.4. Samples: 10533344. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 03:45:19,595][320945] Avg episode reward: [(0, '4854.402')] [2023-03-08 03:45:20,117][321237] Updated weights for policy 0, policy_version 20640 (0.0005) [2023-03-08 03:45:23,479][321237] Updated weights for policy 0, policy_version 20720 (0.0005) [2023-03-08 03:45:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11441.0). Total num frames: 10620928. Throughput: 0: 11901.9. Samples: 10606028. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:45:24,605][320945] Avg episode reward: [(0, '4854.115')] [2023-03-08 03:45:24,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000020744_10620928.pth... [2023-03-08 03:45:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000020040_10260480.pth [2023-03-08 03:45:26,906][321237] Updated weights for policy 0, policy_version 20800 (0.0005) [2023-03-08 03:45:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11441.0). Total num frames: 10678272. Throughput: 0: 12001.0. Samples: 10677608. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:45:29,605][320945] Avg episode reward: [(0, '4856.179')] [2023-03-08 03:45:30,379][321237] Updated weights for policy 0, policy_version 20880 (0.0005) [2023-03-08 03:45:33,894][321237] Updated weights for policy 0, policy_version 20960 (0.0005) [2023-03-08 03:45:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11441.0). Total num frames: 10739712. Throughput: 0: 12004.0. Samples: 10712488. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:45:34,605][320945] Avg episode reward: [(0, '4856.364')] [2023-03-08 03:45:37,431][321237] Updated weights for policy 0, policy_version 21040 (0.0005) [2023-03-08 03:45:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11441.0). Total num frames: 10797056. Throughput: 0: 11927.4. Samples: 10782100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:45:39,605][320945] Avg episode reward: [(0, '4856.184')] [2023-03-08 03:45:39,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000021088_10797056.pth... [2023-03-08 03:45:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000020392_10440704.pth [2023-03-08 03:45:40,957][321237] Updated weights for policy 0, policy_version 21120 (0.0005) [2023-03-08 03:45:44,378][321237] Updated weights for policy 0, policy_version 21200 (0.0005) [2023-03-08 03:45:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11427.1). Total num frames: 10854400. Throughput: 0: 11928.6. Samples: 10853060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:45:44,605][320945] Avg episode reward: [(0, '4860.609')] [2023-03-08 03:45:48,118][321237] Updated weights for policy 0, policy_version 21280 (0.0005) [2023-03-08 03:45:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11810.1, 300 sec: 11399.4). Total num frames: 10907648. Throughput: 0: 11875.4. Samples: 10887016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:45:49,594][320945] Avg episode reward: [(0, '4861.858')] [2023-03-08 03:45:52,052][321237] Updated weights for policy 0, policy_version 21360 (0.0005) [2023-03-08 03:45:54,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11673.6, 300 sec: 11385.5). Total num frames: 10960896. Throughput: 0: 11680.6. Samples: 10949956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:45:54,594][320945] Avg episode reward: [(0, '4862.690')] [2023-03-08 03:45:54,663][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000021416_10964992.pth... [2023-03-08 03:45:54,665][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000020744_10620928.pth [2023-03-08 03:45:55,786][321237] Updated weights for policy 0, policy_version 21440 (0.0005) [2023-03-08 03:45:59,499][321237] Updated weights for policy 0, policy_version 21520 (0.0005) [2023-03-08 03:45:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11385.5). Total num frames: 11018240. Throughput: 0: 11500.7. Samples: 11015644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:45:59,595][320945] Avg episode reward: [(0, '4854.734')] [2023-03-08 03:46:03,257][321237] Updated weights for policy 0, policy_version 21600 (0.0005) [2023-03-08 03:46:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11357.7). Total num frames: 11071488. Throughput: 0: 11444.5. Samples: 11048348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:46:04,595][320945] Avg episode reward: [(0, '4859.888')] [2023-03-08 03:46:07,143][321237] Updated weights for policy 0, policy_version 21680 (0.0005) [2023-03-08 03:46:09,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11400.5, 300 sec: 11343.8). Total num frames: 11124736. Throughput: 0: 11255.2. Samples: 11112512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:46:09,595][320945] Avg episode reward: [(0, '4858.888')] [2023-03-08 03:46:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000021728_11124736.pth... [2023-03-08 03:46:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000021088_10797056.pth [2023-03-08 03:46:10,934][321237] Updated weights for policy 0, policy_version 21760 (0.0005) [2023-03-08 03:46:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 11343.8). Total num frames: 11177984. Throughput: 0: 11072.5. Samples: 11175872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:46:14,595][320945] Avg episode reward: [(0, '4846.687')] [2023-03-08 03:46:14,864][321237] Updated weights for policy 0, policy_version 21840 (0.0005) [2023-03-08 03:46:18,643][321237] Updated weights for policy 0, policy_version 21920 (0.0005) [2023-03-08 03:46:19,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11195.7, 300 sec: 11343.8). Total num frames: 11231232. Throughput: 0: 11025.9. Samples: 11208652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:46:19,595][320945] Avg episode reward: [(0, '4858.763')] [2023-03-08 03:46:22,475][321237] Updated weights for policy 0, policy_version 22000 (0.0005) [2023-03-08 03:46:24,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11343.8). Total num frames: 11284480. Throughput: 0: 10891.1. Samples: 11272200. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:46:24,595][320945] Avg episode reward: [(0, '4858.900')] [2023-03-08 03:46:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000022040_11284480.pth... [2023-03-08 03:46:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000021416_10964992.pth [2023-03-08 03:46:26,408][321237] Updated weights for policy 0, policy_version 22080 (0.0005) [2023-03-08 03:46:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 11343.8). Total num frames: 11337728. Throughput: 0: 10748.0. Samples: 11336720. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:46:29,595][320945] Avg episode reward: [(0, '4859.285')] [2023-03-08 03:46:30,151][321237] Updated weights for policy 0, policy_version 22160 (0.0004) [2023-03-08 03:46:34,088][321237] Updated weights for policy 0, policy_version 22240 (0.0005) [2023-03-08 03:46:34,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11330.0). Total num frames: 11390976. Throughput: 0: 10688.0. Samples: 11367976. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:46:34,595][320945] Avg episode reward: [(0, '4858.604')] [2023-03-08 03:46:38,139][321237] Updated weights for policy 0, policy_version 22320 (0.0005) [2023-03-08 03:46:39,594][320945] Fps is (10 sec: 10240.0, 60 sec: 10717.9, 300 sec: 11316.1). Total num frames: 11440128. Throughput: 0: 10647.6. Samples: 11429100. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:46:39,595][320945] Avg episode reward: [(0, '4860.932')] [2023-03-08 03:46:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000022344_11440128.pth... [2023-03-08 03:46:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000021728_11124736.pth [2023-03-08 03:46:42,057][321237] Updated weights for policy 0, policy_version 22400 (0.0005) [2023-03-08 03:46:44,594][320945] Fps is (10 sec: 10240.0, 60 sec: 10649.6, 300 sec: 11302.2). Total num frames: 11493376. Throughput: 0: 10597.6. Samples: 11492536. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:46:44,595][320945] Avg episode reward: [(0, '4856.757')] [2023-03-08 03:46:45,831][321237] Updated weights for policy 0, policy_version 22480 (0.0005) [2023-03-08 03:46:49,399][321237] Updated weights for policy 0, policy_version 22560 (0.0005) [2023-03-08 03:46:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 11302.2). Total num frames: 11550720. Throughput: 0: 10619.3. Samples: 11526216. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:46:49,595][320945] Avg episode reward: [(0, '4861.647')] [2023-03-08 03:46:53,089][321237] Updated weights for policy 0, policy_version 22640 (0.0004) [2023-03-08 03:46:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 10786.1, 300 sec: 11316.1). Total num frames: 11608064. Throughput: 0: 10695.8. Samples: 11593824. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 03:46:54,595][320945] Avg episode reward: [(0, '4861.925')] [2023-03-08 03:46:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000022672_11608064.pth... [2023-03-08 03:46:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000022040_11284480.pth [2023-03-08 03:46:56,867][321237] Updated weights for policy 0, policy_version 22720 (0.0005) [2023-03-08 03:46:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 11288.3). Total num frames: 11657216. Throughput: 0: 10698.1. Samples: 11657288. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 03:46:59,595][320945] Avg episode reward: [(0, '4861.736')] [2023-03-08 03:47:00,771][321237] Updated weights for policy 0, policy_version 22800 (0.0005) [2023-03-08 03:47:04,594][320945] Fps is (10 sec: 10240.0, 60 sec: 10649.6, 300 sec: 11274.4). Total num frames: 11710464. Throughput: 0: 10696.3. Samples: 11689984. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 03:47:04,595][320945] Avg episode reward: [(0, '4859.351')] [2023-03-08 03:47:04,724][321237] Updated weights for policy 0, policy_version 22880 (0.0005) [2023-03-08 03:47:08,683][321237] Updated weights for policy 0, policy_version 22960 (0.0005) [2023-03-08 03:47:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 11260.5). Total num frames: 11763712. Throughput: 0: 10649.4. Samples: 11751424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:47:09,595][320945] Avg episode reward: [(0, '4861.173')] [2023-03-08 03:47:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000022976_11763712.pth... [2023-03-08 03:47:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000022344_11440128.pth [2023-03-08 03:47:12,472][321237] Updated weights for policy 0, policy_version 23040 (0.0005) [2023-03-08 03:47:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 11246.6). Total num frames: 11816960. Throughput: 0: 10644.1. Samples: 11815704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:47:14,595][320945] Avg episode reward: [(0, '4862.943')] [2023-03-08 03:47:16,365][321237] Updated weights for policy 0, policy_version 23120 (0.0004) [2023-03-08 03:47:19,594][320945] Fps is (10 sec: 10240.1, 60 sec: 10581.3, 300 sec: 11218.9). Total num frames: 11866112. Throughput: 0: 10629.1. Samples: 11846284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:47:19,594][320945] Avg episode reward: [(0, '4861.372')] [2023-03-08 03:47:20,370][321237] Updated weights for policy 0, policy_version 23200 (0.0004) [2023-03-08 03:47:24,012][321237] Updated weights for policy 0, policy_version 23280 (0.0005) [2023-03-08 03:47:24,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 11232.8). Total num frames: 11923456. Throughput: 0: 10710.3. Samples: 11911064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:47:24,595][320945] Avg episode reward: [(0, '4860.064')] [2023-03-08 03:47:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000023288_11923456.pth... [2023-03-08 03:47:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000022672_11608064.pth [2023-03-08 03:47:27,786][321237] Updated weights for policy 0, policy_version 23360 (0.0005) [2023-03-08 03:47:29,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10649.6, 300 sec: 11218.9). Total num frames: 11976704. Throughput: 0: 10759.5. Samples: 11976712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:47:29,595][320945] Avg episode reward: [(0, '4859.973')] [2023-03-08 03:47:31,555][321237] Updated weights for policy 0, policy_version 23440 (0.0005) [2023-03-08 03:47:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10717.9, 300 sec: 11218.9). Total num frames: 12034048. Throughput: 0: 10739.0. Samples: 12009472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:47:34,595][320945] Avg episode reward: [(0, '4859.542')] [2023-03-08 03:47:35,287][321237] Updated weights for policy 0, policy_version 23520 (0.0005) [2023-03-08 03:47:39,103][321237] Updated weights for policy 0, policy_version 23600 (0.0005) [2023-03-08 03:47:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 11218.9). Total num frames: 12087296. Throughput: 0: 10675.2. Samples: 12074208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:47:39,595][320945] Avg episode reward: [(0, '4860.419')] [2023-03-08 03:47:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000023608_12087296.pth... [2023-03-08 03:47:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000022976_11763712.pth [2023-03-08 03:47:42,651][321237] Updated weights for policy 0, policy_version 23680 (0.0005) [2023-03-08 03:47:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11218.9). Total num frames: 12144640. Throughput: 0: 10807.5. Samples: 12143624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:47:44,595][320945] Avg episode reward: [(0, '4859.631')] [2023-03-08 03:47:46,304][321237] Updated weights for policy 0, policy_version 23760 (0.0005) [2023-03-08 03:47:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 11205.0). Total num frames: 12197888. Throughput: 0: 10791.6. Samples: 12175604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:47:49,595][320945] Avg episode reward: [(0, '4859.255')] [2023-03-08 03:47:50,149][321237] Updated weights for policy 0, policy_version 23840 (0.0005) [2023-03-08 03:47:54,162][321237] Updated weights for policy 0, policy_version 23920 (0.0005) [2023-03-08 03:47:54,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10717.9, 300 sec: 11191.1). Total num frames: 12251136. Throughput: 0: 10831.6. Samples: 12238848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:47:54,595][320945] Avg episode reward: [(0, '4861.090')] [2023-03-08 03:47:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000023928_12251136.pth... [2023-03-08 03:47:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000023288_11923456.pth [2023-03-08 03:47:58,079][321237] Updated weights for policy 0, policy_version 24000 (0.0005) [2023-03-08 03:47:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11177.2). Total num frames: 12304384. Throughput: 0: 10783.2. Samples: 12300948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:47:59,595][320945] Avg episode reward: [(0, '4857.102')] [2023-03-08 03:48:01,919][321237] Updated weights for policy 0, policy_version 24080 (0.0004) [2023-03-08 03:48:04,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10786.1, 300 sec: 11163.3). Total num frames: 12357632. Throughput: 0: 10817.1. Samples: 12333056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:48:04,595][320945] Avg episode reward: [(0, '4858.898')] [2023-03-08 03:48:05,574][321237] Updated weights for policy 0, policy_version 24160 (0.0003) [2023-03-08 03:48:09,359][321237] Updated weights for policy 0, policy_version 24240 (0.0004) [2023-03-08 03:48:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11149.4). Total num frames: 12410880. Throughput: 0: 10853.0. Samples: 12399448. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:48:09,595][320945] Avg episode reward: [(0, '4860.934')] [2023-03-08 03:48:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000024240_12410880.pth... [2023-03-08 03:48:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000023608_12087296.pth [2023-03-08 03:48:13,277][321237] Updated weights for policy 0, policy_version 24320 (0.0003) [2023-03-08 03:48:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11135.6). Total num frames: 12464128. Throughput: 0: 10821.7. Samples: 12463688. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:48:14,595][320945] Avg episode reward: [(0, '4861.658')] [2023-03-08 03:48:16,926][321237] Updated weights for policy 0, policy_version 24400 (0.0003) [2023-03-08 03:48:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10922.7, 300 sec: 11135.6). Total num frames: 12521472. Throughput: 0: 10833.1. Samples: 12496960. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:48:19,594][320945] Avg episode reward: [(0, '4858.036')] [2023-03-08 03:48:20,787][321237] Updated weights for policy 0, policy_version 24480 (0.0005) [2023-03-08 03:48:24,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10786.1, 300 sec: 11107.8). Total num frames: 12570624. Throughput: 0: 10788.3. Samples: 12559680. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:48:24,595][320945] Avg episode reward: [(0, '4858.335')] [2023-03-08 03:48:24,659][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000024560_12574720.pth... [2023-03-08 03:48:24,660][321237] Updated weights for policy 0, policy_version 24560 (0.0005) [2023-03-08 03:48:24,661][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000023928_12251136.pth [2023-03-08 03:48:28,440][321237] Updated weights for policy 0, policy_version 24640 (0.0005) [2023-03-08 03:48:29,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 11107.8). Total num frames: 12627968. Throughput: 0: 10683.8. Samples: 12624396. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:48:29,595][320945] Avg episode reward: [(0, '4858.539')] [2023-03-08 03:48:32,125][321237] Updated weights for policy 0, policy_version 24720 (0.0005) [2023-03-08 03:48:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10786.1, 300 sec: 11107.8). Total num frames: 12681216. Throughput: 0: 10723.6. Samples: 12658168. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:48:34,595][320945] Avg episode reward: [(0, '4860.116')] [2023-03-08 03:48:35,821][321237] Updated weights for policy 0, policy_version 24800 (0.0005) [2023-03-08 03:48:39,507][321237] Updated weights for policy 0, policy_version 24880 (0.0005) [2023-03-08 03:48:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11107.8). Total num frames: 12738560. Throughput: 0: 10782.8. Samples: 12724072. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 03:48:39,595][320945] Avg episode reward: [(0, '4859.987')] [2023-03-08 03:48:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000024880_12738560.pth... [2023-03-08 03:48:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000024240_12410880.pth [2023-03-08 03:48:43,236][321237] Updated weights for policy 0, policy_version 24960 (0.0005) [2023-03-08 03:48:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 11093.9). Total num frames: 12791808. Throughput: 0: 10907.4. Samples: 12791780. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:48:44,595][320945] Avg episode reward: [(0, '4861.752')] [2023-03-08 03:48:46,856][321237] Updated weights for policy 0, policy_version 25040 (0.0005) [2023-03-08 03:48:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11093.9). Total num frames: 12849152. Throughput: 0: 10924.1. Samples: 12824640. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:48:49,595][320945] Avg episode reward: [(0, '4857.928')] [2023-03-08 03:48:50,706][321237] Updated weights for policy 0, policy_version 25120 (0.0005) [2023-03-08 03:48:54,474][321237] Updated weights for policy 0, policy_version 25200 (0.0005) [2023-03-08 03:48:54,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10854.4, 300 sec: 11093.9). Total num frames: 12902400. Throughput: 0: 10892.3. Samples: 12889604. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:48:54,595][320945] Avg episode reward: [(0, '4858.771')] [2023-03-08 03:48:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000025200_12902400.pth... [2023-03-08 03:48:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000024560_12574720.pth [2023-03-08 03:48:58,267][321237] Updated weights for policy 0, policy_version 25280 (0.0005) [2023-03-08 03:48:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11080.0). Total num frames: 12955648. Throughput: 0: 10900.4. Samples: 12954208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:48:59,595][320945] Avg episode reward: [(0, '4858.628')] [2023-03-08 03:49:02,106][321237] Updated weights for policy 0, policy_version 25360 (0.0005) [2023-03-08 03:49:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11066.1). Total num frames: 13008896. Throughput: 0: 10873.7. Samples: 12986276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:49:04,595][320945] Avg episode reward: [(0, '4859.303')] [2023-03-08 03:49:05,814][321237] Updated weights for policy 0, policy_version 25440 (0.0005) [2023-03-08 03:49:09,471][321237] Updated weights for policy 0, policy_version 25520 (0.0005) [2023-03-08 03:49:09,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11080.0). Total num frames: 13066240. Throughput: 0: 10951.2. Samples: 13052484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:49:09,595][320945] Avg episode reward: [(0, '4859.143')] [2023-03-08 03:49:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000025520_13066240.pth... [2023-03-08 03:49:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000024880_12738560.pth [2023-03-08 03:49:12,975][321237] Updated weights for policy 0, policy_version 25600 (0.0005) [2023-03-08 03:49:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 11080.0). Total num frames: 13123584. Throughput: 0: 11078.0. Samples: 13122904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:49:14,595][320945] Avg episode reward: [(0, '4857.038')] [2023-03-08 03:49:16,587][321237] Updated weights for policy 0, policy_version 25680 (0.0005) [2023-03-08 03:49:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 10990.9, 300 sec: 11080.0). Total num frames: 13180928. Throughput: 0: 11070.4. Samples: 13156336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:49:19,595][320945] Avg episode reward: [(0, '4858.870')] [2023-03-08 03:49:20,371][321237] Updated weights for policy 0, policy_version 25760 (0.0004) [2023-03-08 03:49:24,170][321237] Updated weights for policy 0, policy_version 25840 (0.0005) [2023-03-08 03:49:24,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11059.2, 300 sec: 11066.1). Total num frames: 13234176. Throughput: 0: 11031.7. Samples: 13220500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:49:24,595][320945] Avg episode reward: [(0, '4858.973')] [2023-03-08 03:49:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000025848_13234176.pth... [2023-03-08 03:49:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000025200_12902400.pth [2023-03-08 03:49:27,924][321237] Updated weights for policy 0, policy_version 25920 (0.0005) [2023-03-08 03:49:29,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10990.9, 300 sec: 11052.3). Total num frames: 13287424. Throughput: 0: 10980.3. Samples: 13285892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:49:29,605][320945] Avg episode reward: [(0, '4859.508')] [2023-03-08 03:49:31,728][321237] Updated weights for policy 0, policy_version 26000 (0.0005) [2023-03-08 03:49:34,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10990.9, 300 sec: 11038.4). Total num frames: 13340672. Throughput: 0: 10961.2. Samples: 13317896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:49:34,605][320945] Avg episode reward: [(0, '4859.103')] [2023-03-08 03:49:35,402][321237] Updated weights for policy 0, policy_version 26080 (0.0005) [2023-03-08 03:49:39,254][321237] Updated weights for policy 0, policy_version 26160 (0.0005) [2023-03-08 03:49:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11038.4). Total num frames: 13393920. Throughput: 0: 10973.1. Samples: 13383392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:49:39,605][320945] Avg episode reward: [(0, '4860.859')] [2023-03-08 03:49:39,643][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000026168_13398016.pth... [2023-03-08 03:49:39,644][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000025520_13066240.pth [2023-03-08 03:49:43,181][321237] Updated weights for policy 0, policy_version 26240 (0.0005) [2023-03-08 03:49:44,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11010.6). Total num frames: 13447168. Throughput: 0: 10954.7. Samples: 13447168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:49:44,605][320945] Avg episode reward: [(0, '4858.851')] [2023-03-08 03:49:46,924][321237] Updated weights for policy 0, policy_version 26320 (0.0006) [2023-03-08 03:49:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10996.7). Total num frames: 13504512. Throughput: 0: 10970.2. Samples: 13479936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:49:49,605][320945] Avg episode reward: [(0, '4853.846')] [2023-03-08 03:49:50,674][321237] Updated weights for policy 0, policy_version 26400 (0.0005) [2023-03-08 03:49:54,455][321237] Updated weights for policy 0, policy_version 26480 (0.0005) [2023-03-08 03:49:54,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 10982.8). Total num frames: 13557760. Throughput: 0: 10945.0. Samples: 13545008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:49:54,605][320945] Avg episode reward: [(0, '4850.781')] [2023-03-08 03:49:54,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000026480_13557760.pth... [2023-03-08 03:49:54,612][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000025848_13234176.pth [2023-03-08 03:49:58,050][321237] Updated weights for policy 0, policy_version 26560 (0.0005) [2023-03-08 03:49:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10968.9). Total num frames: 13615104. Throughput: 0: 10882.2. Samples: 13612604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:49:59,595][320945] Avg episode reward: [(0, '4854.577')] [2023-03-08 03:50:01,709][321237] Updated weights for policy 0, policy_version 26640 (0.0005) [2023-03-08 03:50:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 10955.1). Total num frames: 13672448. Throughput: 0: 10884.6. Samples: 13646144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:50:04,595][320945] Avg episode reward: [(0, '4855.406')] [2023-03-08 03:50:05,175][321237] Updated weights for policy 0, policy_version 26720 (0.0005) [2023-03-08 03:50:08,625][321237] Updated weights for policy 0, policy_version 26800 (0.0005) [2023-03-08 03:50:09,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 13729792. Throughput: 0: 11034.3. Samples: 13717044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:50:09,594][320945] Avg episode reward: [(0, '4804.868')] [2023-03-08 03:50:09,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000026824_13733888.pth... [2023-03-08 03:50:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000026168_13398016.pth [2023-03-08 03:50:11,906][321237] Updated weights for policy 0, policy_version 26880 (0.0005) [2023-03-08 03:50:14,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11127.5, 300 sec: 10955.1). Total num frames: 13791232. Throughput: 0: 11194.9. Samples: 13789660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:50:14,595][320945] Avg episode reward: [(0, '4730.456')] [2023-03-08 03:50:15,364][321237] Updated weights for policy 0, policy_version 26960 (0.0005) [2023-03-08 03:50:18,904][321237] Updated weights for policy 0, policy_version 27040 (0.0004) [2023-03-08 03:50:19,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11195.7, 300 sec: 10955.1). Total num frames: 13852672. Throughput: 0: 11287.4. Samples: 13825828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:50:19,595][320945] Avg episode reward: [(0, '4747.736')] [2023-03-08 03:50:22,487][321237] Updated weights for policy 0, policy_version 27120 (0.0003) [2023-03-08 03:50:24,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11264.0, 300 sec: 10955.1). Total num frames: 13910016. Throughput: 0: 11346.9. Samples: 13894000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:50:24,595][320945] Avg episode reward: [(0, '4784.262')] [2023-03-08 03:50:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000027168_13910016.pth... [2023-03-08 03:50:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000026480_13557760.pth [2023-03-08 03:50:25,968][321237] Updated weights for policy 0, policy_version 27200 (0.0004) [2023-03-08 03:50:29,389][321237] Updated weights for policy 0, policy_version 27280 (0.0004) [2023-03-08 03:50:29,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 10941.2). Total num frames: 13967360. Throughput: 0: 11524.1. Samples: 13965752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:50:29,595][320945] Avg episode reward: [(0, '4858.051')] [2023-03-08 03:50:32,755][321237] Updated weights for policy 0, policy_version 27360 (0.0005) [2023-03-08 03:50:34,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 10955.1). Total num frames: 14028800. Throughput: 0: 11611.5. Samples: 14002452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:50:34,595][320945] Avg episode reward: [(0, '4859.196')] [2023-03-08 03:50:36,232][321237] Updated weights for policy 0, policy_version 27440 (0.0005) [2023-03-08 03:50:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 10941.2). Total num frames: 14082048. Throughput: 0: 11692.9. Samples: 14071188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:50:39,595][320945] Avg episode reward: [(0, '4856.425')] [2023-03-08 03:50:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000027504_14082048.pth... [2023-03-08 03:50:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000026824_13733888.pth [2023-03-08 03:50:40,028][321237] Updated weights for policy 0, policy_version 27520 (0.0005) [2023-03-08 03:50:43,671][321237] Updated weights for policy 0, policy_version 27600 (0.0005) [2023-03-08 03:50:44,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11537.1, 300 sec: 10955.1). Total num frames: 14139392. Throughput: 0: 11677.2. Samples: 14138076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:50:44,595][320945] Avg episode reward: [(0, '4808.736')] [2023-03-08 03:50:47,406][321237] Updated weights for policy 0, policy_version 27680 (0.0005) [2023-03-08 03:50:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 10968.9). Total num frames: 14196736. Throughput: 0: 11668.4. Samples: 14171220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:50:49,595][320945] Avg episode reward: [(0, '4805.465')] [2023-03-08 03:50:50,960][321237] Updated weights for policy 0, policy_version 27760 (0.0005) [2023-03-08 03:50:54,530][321237] Updated weights for policy 0, policy_version 27840 (0.0005) [2023-03-08 03:50:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 10968.9). Total num frames: 14254080. Throughput: 0: 11611.0. Samples: 14239540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:50:54,595][320945] Avg episode reward: [(0, '4835.094')] [2023-03-08 03:50:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000027840_14254080.pth... [2023-03-08 03:50:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000027168_13910016.pth [2023-03-08 03:50:58,053][321237] Updated weights for policy 0, policy_version 27920 (0.0005) [2023-03-08 03:50:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 10982.8). Total num frames: 14311424. Throughput: 0: 11534.2. Samples: 14308700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:50:59,595][320945] Avg episode reward: [(0, '4798.744')] [2023-03-08 03:51:01,679][321237] Updated weights for policy 0, policy_version 28000 (0.0005) [2023-03-08 03:51:04,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11537.1, 300 sec: 10982.8). Total num frames: 14364672. Throughput: 0: 11490.3. Samples: 14342892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:51:04,595][320945] Avg episode reward: [(0, '4808.839')] [2023-03-08 03:51:05,330][321237] Updated weights for policy 0, policy_version 28080 (0.0005) [2023-03-08 03:51:08,928][321237] Updated weights for policy 0, policy_version 28160 (0.0005) [2023-03-08 03:51:09,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.0, 300 sec: 10996.7). Total num frames: 14422016. Throughput: 0: 11471.2. Samples: 14410204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:51:09,595][320945] Avg episode reward: [(0, '4807.528')] [2023-03-08 03:51:09,654][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000028176_14426112.pth... [2023-03-08 03:51:09,655][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000027504_14082048.pth [2023-03-08 03:51:12,575][321237] Updated weights for policy 0, policy_version 28240 (0.0005) [2023-03-08 03:51:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11010.6). Total num frames: 14479360. Throughput: 0: 11385.9. Samples: 14478116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:51:14,605][320945] Avg episode reward: [(0, '4852.124')] [2023-03-08 03:51:16,228][321237] Updated weights for policy 0, policy_version 28320 (0.0005) [2023-03-08 03:51:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11024.5). Total num frames: 14536704. Throughput: 0: 11323.5. Samples: 14512008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:51:19,595][320945] Avg episode reward: [(0, '4852.702')] [2023-03-08 03:51:19,947][321237] Updated weights for policy 0, policy_version 28400 (0.0005) [2023-03-08 03:51:23,666][321237] Updated weights for policy 0, policy_version 28480 (0.0005) [2023-03-08 03:51:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11024.5). Total num frames: 14589952. Throughput: 0: 11255.0. Samples: 14577664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:51:24,595][320945] Avg episode reward: [(0, '4766.173')] [2023-03-08 03:51:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000028496_14589952.pth... [2023-03-08 03:51:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000027840_14254080.pth [2023-03-08 03:51:27,326][321237] Updated weights for policy 0, policy_version 28560 (0.0005) [2023-03-08 03:51:29,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11038.4). Total num frames: 14647296. Throughput: 0: 11235.7. Samples: 14643684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:51:29,595][320945] Avg episode reward: [(0, '4810.932')] [2023-03-08 03:51:31,003][321237] Updated weights for policy 0, policy_version 28640 (0.0005) [2023-03-08 03:51:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 11052.3). Total num frames: 14700544. Throughput: 0: 11268.1. Samples: 14678284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:51:34,595][320945] Avg episode reward: [(0, '4857.675')] [2023-03-08 03:51:34,751][321237] Updated weights for policy 0, policy_version 28720 (0.0005) [2023-03-08 03:51:38,479][321237] Updated weights for policy 0, policy_version 28800 (0.0005) [2023-03-08 03:51:39,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11195.7, 300 sec: 11052.3). Total num frames: 14753792. Throughput: 0: 11193.5. Samples: 14743248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:51:39,595][320945] Avg episode reward: [(0, '4853.459')] [2023-03-08 03:51:39,612][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000028824_14757888.pth... [2023-03-08 03:51:39,613][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000028176_14426112.pth [2023-03-08 03:51:42,187][321237] Updated weights for policy 0, policy_version 28880 (0.0005) [2023-03-08 03:51:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11052.3). Total num frames: 14811136. Throughput: 0: 11140.6. Samples: 14810024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:51:44,595][320945] Avg episode reward: [(0, '4843.555')] [2023-03-08 03:51:45,876][321237] Updated weights for policy 0, policy_version 28960 (0.0005) [2023-03-08 03:51:49,567][321237] Updated weights for policy 0, policy_version 29040 (0.0005) [2023-03-08 03:51:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11195.7, 300 sec: 11052.3). Total num frames: 14868480. Throughput: 0: 11119.0. Samples: 14843248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:51:49,595][320945] Avg episode reward: [(0, '4827.030')] [2023-03-08 03:51:53,234][321237] Updated weights for policy 0, policy_version 29120 (0.0005) [2023-03-08 03:51:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11066.1). Total num frames: 14921728. Throughput: 0: 11095.8. Samples: 14909512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:51:54,594][320945] Avg episode reward: [(0, '4815.810')] [2023-03-08 03:51:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000029144_14921728.pth... [2023-03-08 03:51:54,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000028496_14589952.pth [2023-03-08 03:51:56,632][321237] Updated weights for policy 0, policy_version 29200 (0.0004) [2023-03-08 03:51:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11093.9). Total num frames: 14983168. Throughput: 0: 11209.8. Samples: 14982556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:51:59,595][320945] Avg episode reward: [(0, '4816.041')] [2023-03-08 03:51:59,994][321237] Updated weights for policy 0, policy_version 29280 (0.0005) [2023-03-08 03:52:03,535][321237] Updated weights for policy 0, policy_version 29360 (0.0005) [2023-03-08 03:52:04,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11332.3, 300 sec: 11121.7). Total num frames: 15044608. Throughput: 0: 11215.4. Samples: 15016700. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:52:04,595][320945] Avg episode reward: [(0, '4862.532')] [2023-03-08 03:52:07,043][321237] Updated weights for policy 0, policy_version 29440 (0.0005) [2023-03-08 03:52:09,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11121.7). Total num frames: 15097856. Throughput: 0: 11302.0. Samples: 15086256. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:52:09,595][320945] Avg episode reward: [(0, '4860.694')] [2023-03-08 03:52:09,616][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000029496_15101952.pth... [2023-03-08 03:52:09,617][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000028824_14757888.pth [2023-03-08 03:52:10,672][321237] Updated weights for policy 0, policy_version 29520 (0.0005) [2023-03-08 03:52:14,036][321237] Updated weights for policy 0, policy_version 29600 (0.0005) [2023-03-08 03:52:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11163.3). Total num frames: 15159296. Throughput: 0: 11431.9. Samples: 15158120. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:52:14,605][320945] Avg episode reward: [(0, '4861.253')] [2023-03-08 03:52:17,559][321237] Updated weights for policy 0, policy_version 29680 (0.0004) [2023-03-08 03:52:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11332.3, 300 sec: 11163.3). Total num frames: 15216640. Throughput: 0: 11425.6. Samples: 15192436. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:52:19,594][320945] Avg episode reward: [(0, '4816.447')] [2023-03-08 03:52:21,063][321237] Updated weights for policy 0, policy_version 29760 (0.0005) [2023-03-08 03:52:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11177.2). Total num frames: 15273984. Throughput: 0: 11521.0. Samples: 15261692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:52:24,605][320945] Avg episode reward: [(0, '4827.284')] [2023-03-08 03:52:24,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000029832_15273984.pth... [2023-03-08 03:52:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000029144_14921728.pth [2023-03-08 03:52:24,800][321237] Updated weights for policy 0, policy_version 29840 (0.0005) [2023-03-08 03:52:28,379][321237] Updated weights for policy 0, policy_version 29920 (0.0005) [2023-03-08 03:52:29,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11177.2). Total num frames: 15331328. Throughput: 0: 11545.9. Samples: 15329592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:52:29,605][320945] Avg episode reward: [(0, '4816.994')] [2023-03-08 03:52:31,735][321237] Updated weights for policy 0, policy_version 30000 (0.0005) [2023-03-08 03:52:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11537.1, 300 sec: 11205.0). Total num frames: 15392768. Throughput: 0: 11630.0. Samples: 15366596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:52:34,605][320945] Avg episode reward: [(0, '4815.475')] [2023-03-08 03:52:35,070][321237] Updated weights for policy 0, policy_version 30080 (0.0005) [2023-03-08 03:52:38,331][321237] Updated weights for policy 0, policy_version 30160 (0.0004) [2023-03-08 03:52:39,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11218.9). Total num frames: 15454208. Throughput: 0: 11821.8. Samples: 15441496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:52:39,605][320945] Avg episode reward: [(0, '4812.814')] [2023-03-08 03:52:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000030184_15454208.pth... [2023-03-08 03:52:39,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000029496_15101952.pth [2023-03-08 03:52:41,592][321237] Updated weights for policy 0, policy_version 30240 (0.0005) [2023-03-08 03:52:44,594][320945] Fps is (10 sec: 12697.5, 60 sec: 11810.1, 300 sec: 11260.5). Total num frames: 15519744. Throughput: 0: 11878.0. Samples: 15517068. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 03:52:44,605][320945] Avg episode reward: [(0, '4857.763')] [2023-03-08 03:52:44,871][321237] Updated weights for policy 0, policy_version 30320 (0.0004) [2023-03-08 03:52:48,641][321237] Updated weights for policy 0, policy_version 30400 (0.0005) [2023-03-08 03:52:49,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11260.5). Total num frames: 15572992. Throughput: 0: 11855.6. Samples: 15550200. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 03:52:49,605][320945] Avg episode reward: [(0, '4855.533')] [2023-03-08 03:52:52,287][321237] Updated weights for policy 0, policy_version 30480 (0.0005) [2023-03-08 03:52:54,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11810.1, 300 sec: 11274.4). Total num frames: 15630336. Throughput: 0: 11803.0. Samples: 15617392. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 03:52:54,605][320945] Avg episode reward: [(0, '4858.145')] [2023-03-08 03:52:54,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000030528_15630336.pth... [2023-03-08 03:52:54,612][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000029832_15273984.pth [2023-03-08 03:52:55,767][321237] Updated weights for policy 0, policy_version 30560 (0.0005) [2023-03-08 03:52:58,992][321237] Updated weights for policy 0, policy_version 30640 (0.0004) [2023-03-08 03:52:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11302.2). Total num frames: 15691776. Throughput: 0: 11854.8. Samples: 15691584. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 03:52:59,605][320945] Avg episode reward: [(0, '4858.147')] [2023-03-08 03:53:02,346][321237] Updated weights for policy 0, policy_version 30720 (0.0005) [2023-03-08 03:53:04,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11810.1, 300 sec: 11330.0). Total num frames: 15753216. Throughput: 0: 11901.4. Samples: 15728000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:53:04,605][320945] Avg episode reward: [(0, '4807.519')] [2023-03-08 03:53:05,726][321237] Updated weights for policy 0, policy_version 30800 (0.0005) [2023-03-08 03:53:09,117][321237] Updated weights for policy 0, policy_version 30880 (0.0005) [2023-03-08 03:53:09,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 11357.7). Total num frames: 15814656. Throughput: 0: 11961.7. Samples: 15799968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:53:09,595][320945] Avg episode reward: [(0, '4855.526')] [2023-03-08 03:53:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000030888_15814656.pth... [2023-03-08 03:53:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000030184_15454208.pth [2023-03-08 03:53:12,614][321237] Updated weights for policy 0, policy_version 30960 (0.0005) [2023-03-08 03:53:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11357.7). Total num frames: 15872000. Throughput: 0: 12053.5. Samples: 15872000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:53:14,595][320945] Avg episode reward: [(0, '4816.961')] [2023-03-08 03:53:15,991][321237] Updated weights for policy 0, policy_version 31040 (0.0005) [2023-03-08 03:53:19,491][321237] Updated weights for policy 0, policy_version 31120 (0.0005) [2023-03-08 03:53:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 11399.4). Total num frames: 15933440. Throughput: 0: 12019.1. Samples: 15907456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:53:19,595][320945] Avg episode reward: [(0, '4812.589')] [2023-03-08 03:53:22,999][321237] Updated weights for policy 0, policy_version 31200 (0.0005) [2023-03-08 03:53:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11399.4). Total num frames: 15990784. Throughput: 0: 11926.2. Samples: 15978176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:53:24,595][320945] Avg episode reward: [(0, '4815.159')] [2023-03-08 03:53:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000031232_15990784.pth... [2023-03-08 03:53:24,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000030528_15630336.pth [2023-03-08 03:53:26,548][321237] Updated weights for policy 0, policy_version 31280 (0.0005) [2023-03-08 03:53:29,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11946.7, 300 sec: 11413.3). Total num frames: 16048128. Throughput: 0: 11802.9. Samples: 16048200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:53:29,595][320945] Avg episode reward: [(0, '4858.922')] [2023-03-08 03:53:29,974][321237] Updated weights for policy 0, policy_version 31360 (0.0005) [2023-03-08 03:53:33,602][321237] Updated weights for policy 0, policy_version 31440 (0.0005) [2023-03-08 03:53:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11878.4, 300 sec: 11413.3). Total num frames: 16105472. Throughput: 0: 11830.0. Samples: 16082548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:53:34,594][320945] Avg episode reward: [(0, '4857.918')] [2023-03-08 03:53:37,159][321237] Updated weights for policy 0, policy_version 31520 (0.0005) [2023-03-08 03:53:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11427.1). Total num frames: 16162816. Throughput: 0: 11848.9. Samples: 16150592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:53:39,595][320945] Avg episode reward: [(0, '4860.868')] [2023-03-08 03:53:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000031568_16162816.pth... [2023-03-08 03:53:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000030888_15814656.pth [2023-03-08 03:53:40,832][321237] Updated weights for policy 0, policy_version 31600 (0.0005) [2023-03-08 03:53:44,338][321237] Updated weights for policy 0, policy_version 31680 (0.0005) [2023-03-08 03:53:44,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11427.1). Total num frames: 16220160. Throughput: 0: 11740.5. Samples: 16219904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:53:44,594][320945] Avg episode reward: [(0, '4770.446')] [2023-03-08 03:53:47,780][321237] Updated weights for policy 0, policy_version 31760 (0.0005) [2023-03-08 03:53:49,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11454.9). Total num frames: 16281600. Throughput: 0: 11710.9. Samples: 16254988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:53:49,595][320945] Avg episode reward: [(0, '4766.431')] [2023-03-08 03:53:51,191][321237] Updated weights for policy 0, policy_version 31840 (0.0003) [2023-03-08 03:53:54,564][321237] Updated weights for policy 0, policy_version 31920 (0.0003) [2023-03-08 03:53:54,594][320945] Fps is (10 sec: 12287.8, 60 sec: 11878.4, 300 sec: 11482.7). Total num frames: 16343040. Throughput: 0: 11718.2. Samples: 16327288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:53:54,595][320945] Avg episode reward: [(0, '4739.015')] [2023-03-08 03:53:54,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000031920_16343040.pth... [2023-03-08 03:53:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000031232_15990784.pth [2023-03-08 03:53:57,972][321237] Updated weights for policy 0, policy_version 32000 (0.0003) [2023-03-08 03:53:59,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11496.6). Total num frames: 16400384. Throughput: 0: 11716.4. Samples: 16399240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:53:59,595][320945] Avg episode reward: [(0, '4862.289')] [2023-03-08 03:54:01,315][321237] Updated weights for policy 0, policy_version 32080 (0.0003) [2023-03-08 03:54:04,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11510.5). Total num frames: 16461824. Throughput: 0: 11749.0. Samples: 16436160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:54:04,595][320945] Avg episode reward: [(0, '4825.425')] [2023-03-08 03:54:04,947][321237] Updated weights for policy 0, policy_version 32160 (0.0004) [2023-03-08 03:54:08,663][321237] Updated weights for policy 0, policy_version 32240 (0.0005) [2023-03-08 03:54:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11496.6). Total num frames: 16515072. Throughput: 0: 11658.1. Samples: 16502792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:54:09,595][320945] Avg episode reward: [(0, '4814.409')] [2023-03-08 03:54:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000032256_16515072.pth... [2023-03-08 03:54:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000031568_16162816.pth [2023-03-08 03:54:12,523][321237] Updated weights for policy 0, policy_version 32320 (0.0005) [2023-03-08 03:54:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11605.3, 300 sec: 11482.7). Total num frames: 16568320. Throughput: 0: 11538.7. Samples: 16567440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:54:14,595][320945] Avg episode reward: [(0, '4858.878')] [2023-03-08 03:54:16,263][321237] Updated weights for policy 0, policy_version 32400 (0.0005) [2023-03-08 03:54:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11468.8, 300 sec: 11482.7). Total num frames: 16621568. Throughput: 0: 11508.4. Samples: 16600428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:54:19,595][320945] Avg episode reward: [(0, '4760.144')] [2023-03-08 03:54:20,029][321237] Updated weights for policy 0, policy_version 32480 (0.0005) [2023-03-08 03:54:23,743][321237] Updated weights for policy 0, policy_version 32560 (0.0005) [2023-03-08 03:54:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11496.6). Total num frames: 16678912. Throughput: 0: 11451.2. Samples: 16665896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:54:24,595][320945] Avg episode reward: [(0, '4859.308')] [2023-03-08 03:54:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000032576_16678912.pth... [2023-03-08 03:54:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000031920_16343040.pth [2023-03-08 03:54:27,546][321237] Updated weights for policy 0, policy_version 32640 (0.0005) [2023-03-08 03:54:29,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11400.6, 300 sec: 11496.6). Total num frames: 16732160. Throughput: 0: 11383.6. Samples: 16732168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:54:29,594][320945] Avg episode reward: [(0, '4860.074')] [2023-03-08 03:54:31,131][321237] Updated weights for policy 0, policy_version 32720 (0.0005) [2023-03-08 03:54:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11400.5, 300 sec: 11510.5). Total num frames: 16789504. Throughput: 0: 11333.4. Samples: 16764992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:54:34,595][320945] Avg episode reward: [(0, '4796.371')] [2023-03-08 03:54:34,781][321237] Updated weights for policy 0, policy_version 32800 (0.0005) [2023-03-08 03:54:38,442][321237] Updated weights for policy 0, policy_version 32880 (0.0005) [2023-03-08 03:54:39,594][320945] Fps is (10 sec: 11468.6, 60 sec: 11400.5, 300 sec: 11524.3). Total num frames: 16846848. Throughput: 0: 11228.0. Samples: 16832548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:54:39,595][320945] Avg episode reward: [(0, '4816.094')] [2023-03-08 03:54:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000032904_16846848.pth... [2023-03-08 03:54:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000032256_16515072.pth [2023-03-08 03:54:42,122][321237] Updated weights for policy 0, policy_version 32960 (0.0005) [2023-03-08 03:54:44,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11332.2, 300 sec: 11510.5). Total num frames: 16900096. Throughput: 0: 11129.3. Samples: 16900060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:54:44,595][320945] Avg episode reward: [(0, '4816.076')] [2023-03-08 03:54:45,763][321237] Updated weights for policy 0, policy_version 33040 (0.0005) [2023-03-08 03:54:49,290][321237] Updated weights for policy 0, policy_version 33120 (0.0005) [2023-03-08 03:54:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 16957440. Throughput: 0: 11042.8. Samples: 16933084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:54:49,595][320945] Avg episode reward: [(0, '4779.790')] [2023-03-08 03:54:52,836][321237] Updated weights for policy 0, policy_version 33200 (0.0005) [2023-03-08 03:54:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11264.0, 300 sec: 11538.2). Total num frames: 17018880. Throughput: 0: 11115.5. Samples: 17002992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:54:54,595][320945] Avg episode reward: [(0, '4789.735')] [2023-03-08 03:54:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000033240_17018880.pth... [2023-03-08 03:54:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000032576_16678912.pth [2023-03-08 03:54:56,316][321237] Updated weights for policy 0, policy_version 33280 (0.0003) [2023-03-08 03:54:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 11538.2). Total num frames: 17076224. Throughput: 0: 11236.1. Samples: 17073064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:54:59,595][320945] Avg episode reward: [(0, '4819.255')] [2023-03-08 03:54:59,879][321237] Updated weights for policy 0, policy_version 33360 (0.0004) [2023-03-08 03:55:03,539][321237] Updated weights for policy 0, policy_version 33440 (0.0006) [2023-03-08 03:55:04,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11127.5, 300 sec: 11524.3). Total num frames: 17129472. Throughput: 0: 11254.8. Samples: 17106892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:55:04,595][320945] Avg episode reward: [(0, '4772.060')] [2023-03-08 03:55:07,000][321237] Updated weights for policy 0, policy_version 33520 (0.0005) [2023-03-08 03:55:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 17190912. Throughput: 0: 11371.4. Samples: 17177608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:55:09,595][320945] Avg episode reward: [(0, '4858.740')] [2023-03-08 03:55:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000033576_17190912.pth... [2023-03-08 03:55:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000032904_16846848.pth [2023-03-08 03:55:10,618][321237] Updated weights for policy 0, policy_version 33600 (0.0005) [2023-03-08 03:55:14,082][321237] Updated weights for policy 0, policy_version 33680 (0.0005) [2023-03-08 03:55:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11332.3, 300 sec: 11510.5). Total num frames: 17248256. Throughput: 0: 11431.3. Samples: 17246576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:55:14,595][320945] Avg episode reward: [(0, '4859.701')] [2023-03-08 03:55:17,692][321237] Updated weights for policy 0, policy_version 33760 (0.0005) [2023-03-08 03:55:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11510.5). Total num frames: 17305600. Throughput: 0: 11467.4. Samples: 17281024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:55:19,595][320945] Avg episode reward: [(0, '4860.754')] [2023-03-08 03:55:21,212][321237] Updated weights for policy 0, policy_version 33840 (0.0004) [2023-03-08 03:55:24,553][321237] Updated weights for policy 0, policy_version 33920 (0.0004) [2023-03-08 03:55:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11524.3). Total num frames: 17367040. Throughput: 0: 11515.1. Samples: 17350728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:55:24,595][320945] Avg episode reward: [(0, '4857.153')] [2023-03-08 03:55:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000033920_17367040.pth... [2023-03-08 03:55:24,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000033240_17018880.pth [2023-03-08 03:55:27,922][321237] Updated weights for policy 0, policy_version 34000 (0.0003) [2023-03-08 03:55:29,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11537.0, 300 sec: 11510.5). Total num frames: 17424384. Throughput: 0: 11651.8. Samples: 17424392. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:55:29,595][320945] Avg episode reward: [(0, '4859.020')] [2023-03-08 03:55:31,215][321237] Updated weights for policy 0, policy_version 34080 (0.0003) [2023-03-08 03:55:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11538.2). Total num frames: 17485824. Throughput: 0: 11737.2. Samples: 17461256. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:55:34,594][320945] Avg episode reward: [(0, '4860.064')] [2023-03-08 03:55:34,639][321237] Updated weights for policy 0, policy_version 34160 (0.0003) [2023-03-08 03:55:37,868][321237] Updated weights for policy 0, policy_version 34240 (0.0003) [2023-03-08 03:55:39,594][320945] Fps is (10 sec: 12697.6, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 17551360. Throughput: 0: 11827.5. Samples: 17535228. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:55:39,595][320945] Avg episode reward: [(0, '4861.323')] [2023-03-08 03:55:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000034280_17551360.pth... [2023-03-08 03:55:39,602][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000033576_17190912.pth [2023-03-08 03:55:41,367][321237] Updated weights for policy 0, policy_version 34320 (0.0003) [2023-03-08 03:55:44,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 11566.0). Total num frames: 17608704. Throughput: 0: 11864.5. Samples: 17606968. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:55:44,595][320945] Avg episode reward: [(0, '4862.176')] [2023-03-08 03:55:44,774][321237] Updated weights for policy 0, policy_version 34400 (0.0004) [2023-03-08 03:55:48,400][321237] Updated weights for policy 0, policy_version 34480 (0.0005) [2023-03-08 03:55:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11566.0). Total num frames: 17666048. Throughput: 0: 11879.7. Samples: 17641480. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:55:49,595][320945] Avg episode reward: [(0, '4824.054')] [2023-03-08 03:55:51,896][321237] Updated weights for policy 0, policy_version 34560 (0.0005) [2023-03-08 03:55:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 17723392. Throughput: 0: 11855.5. Samples: 17711104. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:55:54,595][320945] Avg episode reward: [(0, '4815.622')] [2023-03-08 03:55:54,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000034616_17723392.pth... [2023-03-08 03:55:54,602][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000033920_17367040.pth [2023-03-08 03:55:55,518][321237] Updated weights for policy 0, policy_version 34640 (0.0005) [2023-03-08 03:55:59,081][321237] Updated weights for policy 0, policy_version 34720 (0.0006) [2023-03-08 03:55:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11579.9). Total num frames: 17780736. Throughput: 0: 11832.7. Samples: 17779048. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:55:59,595][320945] Avg episode reward: [(0, '4718.469')] [2023-03-08 03:56:02,657][321237] Updated weights for policy 0, policy_version 34800 (0.0004) [2023-03-08 03:56:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11579.9). Total num frames: 17838080. Throughput: 0: 11824.3. Samples: 17813120. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:56:04,595][320945] Avg episode reward: [(0, '4861.838')] [2023-03-08 03:56:06,104][321237] Updated weights for policy 0, policy_version 34880 (0.0003) [2023-03-08 03:56:09,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 11579.9). Total num frames: 17895424. Throughput: 0: 11832.9. Samples: 17883208. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 03:56:09,594][320945] Avg episode reward: [(0, '4770.205')] [2023-03-08 03:56:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000034952_17895424.pth... [2023-03-08 03:56:09,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000034280_17551360.pth [2023-03-08 03:56:09,723][321237] Updated weights for policy 0, policy_version 34960 (0.0003) [2023-03-08 03:56:13,098][321237] Updated weights for policy 0, policy_version 35040 (0.0003) [2023-03-08 03:56:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11593.8). Total num frames: 17956864. Throughput: 0: 11778.9. Samples: 17954444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:56:14,605][320945] Avg episode reward: [(0, '4624.821')] [2023-03-08 03:56:16,518][321237] Updated weights for policy 0, policy_version 35120 (0.0003) [2023-03-08 03:56:19,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11878.4, 300 sec: 11621.5). Total num frames: 18018304. Throughput: 0: 11743.1. Samples: 17989696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:56:19,605][320945] Avg episode reward: [(0, '4812.171')] [2023-03-08 03:56:19,901][321237] Updated weights for policy 0, policy_version 35200 (0.0004) [2023-03-08 03:56:23,493][321237] Updated weights for policy 0, policy_version 35280 (0.0004) [2023-03-08 03:56:24,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 11607.6). Total num frames: 18071552. Throughput: 0: 11673.4. Samples: 18060528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:56:24,594][320945] Avg episode reward: [(0, '4860.176')] [2023-03-08 03:56:24,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000035304_18075648.pth... [2023-03-08 03:56:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000034616_17723392.pth [2023-03-08 03:56:27,124][321237] Updated weights for policy 0, policy_version 35360 (0.0005) [2023-03-08 03:56:29,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11635.4). Total num frames: 18132992. Throughput: 0: 11612.8. Samples: 18129544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:56:29,595][320945] Avg episode reward: [(0, '4860.781')] [2023-03-08 03:56:30,650][321237] Updated weights for policy 0, policy_version 35440 (0.0004) [2023-03-08 03:56:33,863][321237] Updated weights for policy 0, policy_version 35520 (0.0003) [2023-03-08 03:56:34,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11663.2). Total num frames: 18194432. Throughput: 0: 11652.1. Samples: 18165824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:56:34,605][320945] Avg episode reward: [(0, '4861.396')] [2023-03-08 03:56:37,147][321237] Updated weights for policy 0, policy_version 35600 (0.0003) [2023-03-08 03:56:39,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 18251776. Throughput: 0: 11745.1. Samples: 18239632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:56:39,605][320945] Avg episode reward: [(0, '4862.556')] [2023-03-08 03:56:39,668][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000035656_18255872.pth... [2023-03-08 03:56:39,669][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000034952_17895424.pth [2023-03-08 03:56:40,700][321237] Updated weights for policy 0, policy_version 35680 (0.0005) [2023-03-08 03:56:44,103][321237] Updated weights for policy 0, policy_version 35760 (0.0004) [2023-03-08 03:56:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 18313216. Throughput: 0: 11825.6. Samples: 18311200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:56:44,605][320945] Avg episode reward: [(0, '4859.830')] [2023-03-08 03:56:47,655][321237] Updated weights for policy 0, policy_version 35840 (0.0005) [2023-03-08 03:56:49,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11691.0). Total num frames: 18370560. Throughput: 0: 11841.8. Samples: 18346000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:56:49,605][320945] Avg episode reward: [(0, '4859.841')] [2023-03-08 03:56:51,214][321237] Updated weights for policy 0, policy_version 35920 (0.0005) [2023-03-08 03:56:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 18427904. Throughput: 0: 11795.4. Samples: 18414004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:56:54,605][320945] Avg episode reward: [(0, '4864.196')] [2023-03-08 03:56:54,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000035992_18427904.pth... [2023-03-08 03:56:54,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000035304_18075648.pth [2023-03-08 03:56:54,819][321237] Updated weights for policy 0, policy_version 36000 (0.0006) [2023-03-08 03:56:58,470][321237] Updated weights for policy 0, policy_version 36080 (0.0006) [2023-03-08 03:56:59,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11741.8, 300 sec: 11663.2). Total num frames: 18485248. Throughput: 0: 11706.2. Samples: 18481224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:56:59,605][320945] Avg episode reward: [(0, '4860.163')] [2023-03-08 03:57:02,014][321237] Updated weights for policy 0, policy_version 36160 (0.0006) [2023-03-08 03:57:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 18542592. Throughput: 0: 11722.0. Samples: 18517188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:57:04,605][320945] Avg episode reward: [(0, '4860.858')] [2023-03-08 03:57:05,411][321237] Updated weights for policy 0, policy_version 36240 (0.0004) [2023-03-08 03:57:09,084][321237] Updated weights for policy 0, policy_version 36320 (0.0005) [2023-03-08 03:57:09,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11741.8, 300 sec: 11663.2). Total num frames: 18599936. Throughput: 0: 11703.3. Samples: 18587180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:57:09,605][320945] Avg episode reward: [(0, '4862.644')] [2023-03-08 03:57:09,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000036328_18599936.pth... [2023-03-08 03:57:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000035656_18255872.pth [2023-03-08 03:57:12,686][321237] Updated weights for policy 0, policy_version 36400 (0.0005) [2023-03-08 03:57:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 18657280. Throughput: 0: 11661.2. Samples: 18654300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:57:14,605][320945] Avg episode reward: [(0, '4862.532')] [2023-03-08 03:57:16,252][321237] Updated weights for policy 0, policy_version 36480 (0.0005) [2023-03-08 03:57:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11663.2). Total num frames: 18714624. Throughput: 0: 11646.8. Samples: 18689932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:57:19,605][320945] Avg episode reward: [(0, '4860.348')] [2023-03-08 03:57:19,855][321237] Updated weights for policy 0, policy_version 36560 (0.0006) [2023-03-08 03:57:23,206][321237] Updated weights for policy 0, policy_version 36640 (0.0005) [2023-03-08 03:57:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.8, 300 sec: 11677.1). Total num frames: 18776064. Throughput: 0: 11564.6. Samples: 18760040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:57:24,605][320945] Avg episode reward: [(0, '4863.516')] [2023-03-08 03:57:24,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000036672_18776064.pth... [2023-03-08 03:57:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000035992_18427904.pth [2023-03-08 03:57:26,683][321237] Updated weights for policy 0, policy_version 36720 (0.0004) [2023-03-08 03:57:29,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 18833408. Throughput: 0: 11559.4. Samples: 18831372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:57:29,595][320945] Avg episode reward: [(0, '4863.676')] [2023-03-08 03:57:30,081][321237] Updated weights for policy 0, policy_version 36800 (0.0004) [2023-03-08 03:57:33,515][321237] Updated weights for policy 0, policy_version 36880 (0.0005) [2023-03-08 03:57:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 18894848. Throughput: 0: 11575.2. Samples: 18866884. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:57:34,595][320945] Avg episode reward: [(0, '4859.916')] [2023-03-08 03:57:36,811][321237] Updated weights for policy 0, policy_version 36960 (0.0005) [2023-03-08 03:57:39,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 11635.4). Total num frames: 18952192. Throughput: 0: 11704.6. Samples: 18940712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:57:39,595][320945] Avg episode reward: [(0, '4860.861')] [2023-03-08 03:57:39,659][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000037024_18956288.pth... [2023-03-08 03:57:39,661][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000036328_18599936.pth [2023-03-08 03:57:40,399][321237] Updated weights for policy 0, policy_version 37040 (0.0005) [2023-03-08 03:57:43,621][321237] Updated weights for policy 0, policy_version 37120 (0.0004) [2023-03-08 03:57:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 19013632. Throughput: 0: 11825.7. Samples: 19013380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:57:44,595][320945] Avg episode reward: [(0, '4859.913')] [2023-03-08 03:57:47,228][321237] Updated weights for policy 0, policy_version 37200 (0.0003) [2023-03-08 03:57:49,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 19070976. Throughput: 0: 11761.9. Samples: 19046472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:57:49,594][320945] Avg episode reward: [(0, '4864.021')] [2023-03-08 03:57:50,724][321237] Updated weights for policy 0, policy_version 37280 (0.0005) [2023-03-08 03:57:54,463][321237] Updated weights for policy 0, policy_version 37360 (0.0006) [2023-03-08 03:57:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11649.3). Total num frames: 19128320. Throughput: 0: 11752.3. Samples: 19116032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:57:54,595][320945] Avg episode reward: [(0, '4859.655')] [2023-03-08 03:57:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000037360_19128320.pth... [2023-03-08 03:57:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000036672_18776064.pth [2023-03-08 03:57:58,086][321237] Updated weights for policy 0, policy_version 37440 (0.0005) [2023-03-08 03:57:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11635.4). Total num frames: 19185664. Throughput: 0: 11749.3. Samples: 19183020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:57:59,595][320945] Avg episode reward: [(0, '4860.130')] [2023-03-08 03:58:01,692][321237] Updated weights for policy 0, policy_version 37520 (0.0005) [2023-03-08 03:58:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11621.5). Total num frames: 19243008. Throughput: 0: 11704.0. Samples: 19216612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:58:04,595][320945] Avg episode reward: [(0, '4815.237')] [2023-03-08 03:58:05,233][321237] Updated weights for policy 0, policy_version 37600 (0.0005) [2023-03-08 03:58:08,723][321237] Updated weights for policy 0, policy_version 37680 (0.0003) [2023-03-08 03:58:09,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11621.5). Total num frames: 19300352. Throughput: 0: 11722.4. Samples: 19287548. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:58:09,595][320945] Avg episode reward: [(0, '4771.940')] [2023-03-08 03:58:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000037696_19300352.pth... [2023-03-08 03:58:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000037024_18956288.pth [2023-03-08 03:58:12,244][321237] Updated weights for policy 0, policy_version 37760 (0.0003) [2023-03-08 03:58:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11621.5). Total num frames: 19361792. Throughput: 0: 11726.2. Samples: 19359052. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:58:14,595][320945] Avg episode reward: [(0, '4863.623')] [2023-03-08 03:58:15,575][321237] Updated weights for policy 0, policy_version 37840 (0.0004) [2023-03-08 03:58:19,089][321237] Updated weights for policy 0, policy_version 37920 (0.0005) [2023-03-08 03:58:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11621.5). Total num frames: 19419136. Throughput: 0: 11712.5. Samples: 19393948. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:58:19,595][320945] Avg episode reward: [(0, '4861.958')] [2023-03-08 03:58:22,648][321237] Updated weights for policy 0, policy_version 38000 (0.0005) [2023-03-08 03:58:24,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11621.5). Total num frames: 19476480. Throughput: 0: 11620.7. Samples: 19463644. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:58:24,595][320945] Avg episode reward: [(0, '4863.758')] [2023-03-08 03:58:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000038040_19476480.pth... [2023-03-08 03:58:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000037360_19128320.pth [2023-03-08 03:58:26,117][321237] Updated weights for policy 0, policy_version 38080 (0.0005) [2023-03-08 03:58:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11621.5). Total num frames: 19533824. Throughput: 0: 11553.5. Samples: 19533288. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 03:58:29,595][320945] Avg episode reward: [(0, '4861.488')] [2023-03-08 03:58:29,743][321237] Updated weights for policy 0, policy_version 38160 (0.0005) [2023-03-08 03:58:33,396][321237] Updated weights for policy 0, policy_version 38240 (0.0005) [2023-03-08 03:58:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11621.5). Total num frames: 19591168. Throughput: 0: 11556.1. Samples: 19566496. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:58:34,595][320945] Avg episode reward: [(0, '4862.615')] [2023-03-08 03:58:37,041][321237] Updated weights for policy 0, policy_version 38320 (0.0005) [2023-03-08 03:58:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11621.5). Total num frames: 19648512. Throughput: 0: 11518.9. Samples: 19634384. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:58:39,595][320945] Avg episode reward: [(0, '4819.087')] [2023-03-08 03:58:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000038376_19648512.pth... [2023-03-08 03:58:39,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000037696_19300352.pth [2023-03-08 03:58:40,637][321237] Updated weights for policy 0, policy_version 38400 (0.0005) [2023-03-08 03:58:44,195][321237] Updated weights for policy 0, policy_version 38480 (0.0005) [2023-03-08 03:58:44,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11607.6). Total num frames: 19705856. Throughput: 0: 11538.8. Samples: 19702264. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:58:44,595][320945] Avg episode reward: [(0, '4861.926')] [2023-03-08 03:58:47,755][321237] Updated weights for policy 0, policy_version 38560 (0.0005) [2023-03-08 03:58:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.0, 300 sec: 11593.8). Total num frames: 19763200. Throughput: 0: 11552.3. Samples: 19736464. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:58:49,595][320945] Avg episode reward: [(0, '4818.497')] [2023-03-08 03:58:51,266][321237] Updated weights for policy 0, policy_version 38640 (0.0004) [2023-03-08 03:58:54,594][320945] Fps is (10 sec: 11059.0, 60 sec: 11468.8, 300 sec: 11579.9). Total num frames: 19816448. Throughput: 0: 11519.0. Samples: 19805904. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 03:58:54,595][320945] Avg episode reward: [(0, '4727.981')] [2023-03-08 03:58:54,639][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000038712_19820544.pth... [2023-03-08 03:58:54,640][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000038040_19476480.pth [2023-03-08 03:58:55,028][321237] Updated weights for policy 0, policy_version 38720 (0.0005) [2023-03-08 03:58:58,567][321237] Updated weights for policy 0, policy_version 38800 (0.0003) [2023-03-08 03:58:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11566.0). Total num frames: 19873792. Throughput: 0: 11433.1. Samples: 19873544. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:58:59,595][320945] Avg episode reward: [(0, '4814.583')] [2023-03-08 03:59:02,176][321237] Updated weights for policy 0, policy_version 38880 (0.0005) [2023-03-08 03:59:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11579.9). Total num frames: 19931136. Throughput: 0: 11409.2. Samples: 19907364. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:59:04,595][320945] Avg episode reward: [(0, '4818.859')] [2023-03-08 03:59:05,814][321237] Updated weights for policy 0, policy_version 38960 (0.0005) [2023-03-08 03:59:09,378][321237] Updated weights for policy 0, policy_version 39040 (0.0005) [2023-03-08 03:59:09,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11593.8). Total num frames: 19988480. Throughput: 0: 11382.4. Samples: 19975852. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:59:09,595][320945] Avg episode reward: [(0, '4730.729')] [2023-03-08 03:59:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000039040_19988480.pth... [2023-03-08 03:59:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000038376_19648512.pth [2023-03-08 03:59:13,103][321237] Updated weights for policy 0, policy_version 39120 (0.0006) [2023-03-08 03:59:14,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11607.6). Total num frames: 20045824. Throughput: 0: 11304.7. Samples: 20042000. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:59:14,595][320945] Avg episode reward: [(0, '4691.183')] [2023-03-08 03:59:16,662][321237] Updated weights for policy 0, policy_version 39200 (0.0005) [2023-03-08 03:59:19,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11607.6). Total num frames: 20103168. Throughput: 0: 11373.4. Samples: 20078300. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 03:59:19,595][320945] Avg episode reward: [(0, '4776.726')] [2023-03-08 03:59:20,029][321237] Updated weights for policy 0, policy_version 39280 (0.0005) [2023-03-08 03:59:23,429][321237] Updated weights for policy 0, policy_version 39360 (0.0005) [2023-03-08 03:59:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11635.4). Total num frames: 20164608. Throughput: 0: 11465.0. Samples: 20150308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:59:24,595][320945] Avg episode reward: [(0, '4816.753')] [2023-03-08 03:59:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000039384_20164608.pth... [2023-03-08 03:59:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000038712_19820544.pth [2023-03-08 03:59:26,707][321237] Updated weights for policy 0, policy_version 39440 (0.0005) [2023-03-08 03:59:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11649.3). Total num frames: 20226048. Throughput: 0: 11611.0. Samples: 20224760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:59:29,595][320945] Avg episode reward: [(0, '4818.635')] [2023-03-08 03:59:30,018][321237] Updated weights for policy 0, policy_version 39520 (0.0004) [2023-03-08 03:59:33,534][321237] Updated weights for policy 0, policy_version 39600 (0.0005) [2023-03-08 03:59:34,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11663.2). Total num frames: 20287488. Throughput: 0: 11646.0. Samples: 20260536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:59:34,595][320945] Avg episode reward: [(0, '4777.137')] [2023-03-08 03:59:36,903][321237] Updated weights for policy 0, policy_version 39680 (0.0005) [2023-03-08 03:59:39,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11673.6, 300 sec: 11691.0). Total num frames: 20348928. Throughput: 0: 11704.7. Samples: 20332616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:59:39,595][320945] Avg episode reward: [(0, '4859.893')] [2023-03-08 03:59:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000039744_20348928.pth... [2023-03-08 03:59:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000039040_19988480.pth [2023-03-08 03:59:40,125][321237] Updated weights for policy 0, policy_version 39760 (0.0004) [2023-03-08 03:59:43,395][321237] Updated weights for policy 0, policy_version 39840 (0.0004) [2023-03-08 03:59:44,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11704.8). Total num frames: 20410368. Throughput: 0: 11897.3. Samples: 20408924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:59:44,595][320945] Avg episode reward: [(0, '4773.843')] [2023-03-08 03:59:46,661][321237] Updated weights for policy 0, policy_version 39920 (0.0004) [2023-03-08 03:59:49,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11704.8). Total num frames: 20471808. Throughput: 0: 11970.2. Samples: 20446024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:59:49,595][320945] Avg episode reward: [(0, '4860.526')] [2023-03-08 03:59:50,263][321237] Updated weights for policy 0, policy_version 40000 (0.0005) [2023-03-08 03:59:53,959][321237] Updated weights for policy 0, policy_version 40080 (0.0005) [2023-03-08 03:59:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11810.1, 300 sec: 11691.0). Total num frames: 20525056. Throughput: 0: 11933.0. Samples: 20512840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:59:54,595][320945] Avg episode reward: [(0, '4860.215')] [2023-03-08 03:59:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000040088_20525056.pth... [2023-03-08 03:59:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000039384_20164608.pth [2023-03-08 03:59:57,520][321237] Updated weights for policy 0, policy_version 40160 (0.0005) [2023-03-08 03:59:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11704.8). Total num frames: 20582400. Throughput: 0: 11999.7. Samples: 20581984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 03:59:59,595][320945] Avg episode reward: [(0, '4818.984')] [2023-03-08 04:00:01,164][321237] Updated weights for policy 0, policy_version 40240 (0.0005) [2023-03-08 04:00:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11691.0). Total num frames: 20639744. Throughput: 0: 11932.0. Samples: 20615240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:00:04,595][320945] Avg episode reward: [(0, '4777.378')] [2023-03-08 04:00:04,746][321237] Updated weights for policy 0, policy_version 40320 (0.0005) [2023-03-08 04:00:08,507][321237] Updated weights for policy 0, policy_version 40400 (0.0005) [2023-03-08 04:00:09,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11741.8, 300 sec: 11677.1). Total num frames: 20692992. Throughput: 0: 11821.7. Samples: 20682284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:00:09,595][320945] Avg episode reward: [(0, '4748.959')] [2023-03-08 04:00:09,617][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000040424_20697088.pth... [2023-03-08 04:00:09,619][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000039744_20348928.pth [2023-03-08 04:00:12,231][321237] Updated weights for policy 0, policy_version 40480 (0.0005) [2023-03-08 04:00:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 20750336. Throughput: 0: 11598.6. Samples: 20746696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:00:14,605][320945] Avg episode reward: [(0, '4771.210')] [2023-03-08 04:00:15,983][321237] Updated weights for policy 0, policy_version 40560 (0.0005) [2023-03-08 04:00:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11673.6, 300 sec: 11649.3). Total num frames: 20803584. Throughput: 0: 11567.5. Samples: 20781072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:00:19,605][320945] Avg episode reward: [(0, '4773.031')] [2023-03-08 04:00:19,642][321237] Updated weights for policy 0, policy_version 40640 (0.0005) [2023-03-08 04:00:22,888][321237] Updated weights for policy 0, policy_version 40720 (0.0003) [2023-03-08 04:00:24,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 20865024. Throughput: 0: 11561.8. Samples: 20852896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:00:24,605][320945] Avg episode reward: [(0, '4696.258')] [2023-03-08 04:00:24,621][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000040760_20869120.pth... [2023-03-08 04:00:24,622][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000040088_20525056.pth [2023-03-08 04:00:26,390][321237] Updated weights for policy 0, policy_version 40800 (0.0004) [2023-03-08 04:00:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 20926464. Throughput: 0: 11446.0. Samples: 20923996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:00:29,605][320945] Avg episode reward: [(0, '4729.573')] [2023-03-08 04:00:29,790][321237] Updated weights for policy 0, policy_version 40880 (0.0003) [2023-03-08 04:00:33,379][321237] Updated weights for policy 0, policy_version 40960 (0.0004) [2023-03-08 04:00:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11635.4). Total num frames: 20983808. Throughput: 0: 11399.2. Samples: 20958988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:00:34,605][320945] Avg episode reward: [(0, '4776.160')] [2023-03-08 04:00:36,921][321237] Updated weights for policy 0, policy_version 41040 (0.0004) [2023-03-08 04:00:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11635.4). Total num frames: 21041152. Throughput: 0: 11443.7. Samples: 21027808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:00:39,605][320945] Avg episode reward: [(0, '4734.490')] [2023-03-08 04:00:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000041096_21041152.pth... [2023-03-08 04:00:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000040424_20697088.pth [2023-03-08 04:00:40,417][321237] Updated weights for policy 0, policy_version 41120 (0.0004) [2023-03-08 04:00:43,942][321237] Updated weights for policy 0, policy_version 41200 (0.0004) [2023-03-08 04:00:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11635.4). Total num frames: 21098496. Throughput: 0: 11478.2. Samples: 21098504. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:00:44,605][320945] Avg episode reward: [(0, '4818.819')] [2023-03-08 04:00:47,546][321237] Updated weights for policy 0, policy_version 41280 (0.0004) [2023-03-08 04:00:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11635.4). Total num frames: 21155840. Throughput: 0: 11476.3. Samples: 21131672. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:00:49,595][320945] Avg episode reward: [(0, '4817.428')] [2023-03-08 04:00:51,071][321237] Updated weights for policy 0, policy_version 41360 (0.0005) [2023-03-08 04:00:54,545][321237] Updated weights for policy 0, policy_version 41440 (0.0005) [2023-03-08 04:00:54,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11649.3). Total num frames: 21217280. Throughput: 0: 11535.9. Samples: 21201400. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:00:54,595][320945] Avg episode reward: [(0, '4818.710')] [2023-03-08 04:00:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000041440_21217280.pth... [2023-03-08 04:00:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000040760_20869120.pth [2023-03-08 04:00:57,777][321237] Updated weights for policy 0, policy_version 41520 (0.0004) [2023-03-08 04:00:59,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11663.2). Total num frames: 21278720. Throughput: 0: 11792.0. Samples: 21277336. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:00:59,605][320945] Avg episode reward: [(0, '4774.830')] [2023-03-08 04:01:00,935][321237] Updated weights for policy 0, policy_version 41600 (0.0004) [2023-03-08 04:01:04,194][321237] Updated weights for policy 0, policy_version 41680 (0.0004) [2023-03-08 04:01:04,594][320945] Fps is (10 sec: 12697.6, 60 sec: 11741.9, 300 sec: 11691.0). Total num frames: 21344256. Throughput: 0: 11879.5. Samples: 21315648. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:01:04,605][320945] Avg episode reward: [(0, '4860.654')] [2023-03-08 04:01:07,587][321237] Updated weights for policy 0, policy_version 41760 (0.0003) [2023-03-08 04:01:09,594][320945] Fps is (10 sec: 12697.6, 60 sec: 11878.4, 300 sec: 11691.0). Total num frames: 21405696. Throughput: 0: 11929.7. Samples: 21389732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:01:09,605][320945] Avg episode reward: [(0, '4860.161')] [2023-03-08 04:01:09,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000041808_21405696.pth... [2023-03-08 04:01:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000041096_21041152.pth [2023-03-08 04:01:10,723][321237] Updated weights for policy 0, policy_version 41840 (0.0003) [2023-03-08 04:01:13,927][321237] Updated weights for policy 0, policy_version 41920 (0.0003) [2023-03-08 04:01:14,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12014.9, 300 sec: 11704.8). Total num frames: 21471232. Throughput: 0: 12071.4. Samples: 21467208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:01:14,605][320945] Avg episode reward: [(0, '4814.912')] [2023-03-08 04:01:17,274][321237] Updated weights for policy 0, policy_version 42000 (0.0004) [2023-03-08 04:01:19,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11718.7). Total num frames: 21528576. Throughput: 0: 12111.6. Samples: 21504008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:01:19,605][320945] Avg episode reward: [(0, '4774.551')] [2023-03-08 04:01:20,753][321237] Updated weights for policy 0, policy_version 42080 (0.0005) [2023-03-08 04:01:24,410][321237] Updated weights for policy 0, policy_version 42160 (0.0005) [2023-03-08 04:01:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 11704.8). Total num frames: 21585920. Throughput: 0: 12123.6. Samples: 21573372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:01:24,602][320945] Avg episode reward: [(0, '4817.063')] [2023-03-08 04:01:24,606][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000042160_21585920.pth... [2023-03-08 04:01:24,608][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000041440_21217280.pth [2023-03-08 04:01:27,850][321237] Updated weights for policy 0, policy_version 42240 (0.0005) [2023-03-08 04:01:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11704.8). Total num frames: 21647360. Throughput: 0: 12127.6. Samples: 21644248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:01:29,605][320945] Avg episode reward: [(0, '4861.758')] [2023-03-08 04:01:31,049][321237] Updated weights for policy 0, policy_version 42320 (0.0004) [2023-03-08 04:01:34,244][321237] Updated weights for policy 0, policy_version 42400 (0.0005) [2023-03-08 04:01:34,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12151.5, 300 sec: 11732.6). Total num frames: 21712896. Throughput: 0: 12269.2. Samples: 21683784. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:01:34,605][320945] Avg episode reward: [(0, '4860.375')] [2023-03-08 04:01:37,455][321237] Updated weights for policy 0, policy_version 42480 (0.0005) [2023-03-08 04:01:39,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 11732.6). Total num frames: 21774336. Throughput: 0: 12415.7. Samples: 21760108. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:01:39,605][320945] Avg episode reward: [(0, '4862.463')] [2023-03-08 04:01:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000042528_21774336.pth... [2023-03-08 04:01:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000041808_21405696.pth [2023-03-08 04:01:40,643][321237] Updated weights for policy 0, policy_version 42560 (0.0005) [2023-03-08 04:01:44,203][321237] Updated weights for policy 0, policy_version 42640 (0.0005) [2023-03-08 04:01:44,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11746.5). Total num frames: 21835776. Throughput: 0: 12327.7. Samples: 21832084. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:01:44,605][320945] Avg episode reward: [(0, '4861.932')] [2023-03-08 04:01:47,758][321237] Updated weights for policy 0, policy_version 42720 (0.0005) [2023-03-08 04:01:49,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 11746.5). Total num frames: 21893120. Throughput: 0: 12271.6. Samples: 21867872. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:01:49,605][320945] Avg episode reward: [(0, '4862.433')] [2023-03-08 04:01:51,267][321237] Updated weights for policy 0, policy_version 42800 (0.0005) [2023-03-08 04:01:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 12219.7, 300 sec: 11746.5). Total num frames: 21950464. Throughput: 0: 12163.6. Samples: 21937096. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:01:54,603][320945] Avg episode reward: [(0, '4815.074')] [2023-03-08 04:01:54,607][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000042872_21950464.pth... [2023-03-08 04:01:54,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000042160_21585920.pth [2023-03-08 04:01:54,874][321237] Updated weights for policy 0, policy_version 42880 (0.0005) [2023-03-08 04:01:58,531][321237] Updated weights for policy 0, policy_version 42960 (0.0005) [2023-03-08 04:01:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 12083.2, 300 sec: 11732.6). Total num frames: 22003712. Throughput: 0: 11922.6. Samples: 22003724. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:01:59,595][320945] Avg episode reward: [(0, '4859.071')] [2023-03-08 04:02:02,115][321237] Updated weights for policy 0, policy_version 43040 (0.0005) [2023-03-08 04:02:04,594][320945] Fps is (10 sec: 11059.4, 60 sec: 11946.7, 300 sec: 11732.6). Total num frames: 22061056. Throughput: 0: 11875.4. Samples: 22038400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:02:04,594][320945] Avg episode reward: [(0, '4768.240')] [2023-03-08 04:02:05,699][321237] Updated weights for policy 0, policy_version 43120 (0.0005) [2023-03-08 04:02:09,292][321237] Updated weights for policy 0, policy_version 43200 (0.0005) [2023-03-08 04:02:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11732.6). Total num frames: 22118400. Throughput: 0: 11854.3. Samples: 22106816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:02:09,594][320945] Avg episode reward: [(0, '4861.852')] [2023-03-08 04:02:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000043200_22118400.pth... [2023-03-08 04:02:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000042528_21774336.pth [2023-03-08 04:02:12,639][321237] Updated weights for policy 0, policy_version 43280 (0.0004) [2023-03-08 04:02:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11746.5). Total num frames: 22179840. Throughput: 0: 11902.3. Samples: 22179852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:02:14,594][320945] Avg episode reward: [(0, '4813.155')] [2023-03-08 04:02:15,941][321237] Updated weights for policy 0, policy_version 43360 (0.0004) [2023-03-08 04:02:19,250][321237] Updated weights for policy 0, policy_version 43440 (0.0004) [2023-03-08 04:02:19,594][320945] Fps is (10 sec: 12697.7, 60 sec: 11946.7, 300 sec: 11760.4). Total num frames: 22245376. Throughput: 0: 11838.0. Samples: 22216492. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:02:19,594][320945] Avg episode reward: [(0, '4818.665')] [2023-03-08 04:02:22,540][321237] Updated weights for policy 0, policy_version 43520 (0.0004) [2023-03-08 04:02:24,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12014.9, 300 sec: 11774.3). Total num frames: 22306816. Throughput: 0: 11797.8. Samples: 22291008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:02:24,595][320945] Avg episode reward: [(0, '4816.014')] [2023-03-08 04:02:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000043568_22306816.pth... [2023-03-08 04:02:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000042872_21950464.pth [2023-03-08 04:02:25,853][321237] Updated weights for policy 0, policy_version 43600 (0.0004) [2023-03-08 04:02:29,144][321237] Updated weights for policy 0, policy_version 43680 (0.0005) [2023-03-08 04:02:29,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 11774.3). Total num frames: 22368256. Throughput: 0: 11854.9. Samples: 22365556. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:02:29,595][320945] Avg episode reward: [(0, '4814.595')] [2023-03-08 04:02:32,474][321237] Updated weights for policy 0, policy_version 43760 (0.0004) [2023-03-08 04:02:34,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11946.7, 300 sec: 11788.2). Total num frames: 22429696. Throughput: 0: 11875.6. Samples: 22402272. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:02:34,595][320945] Avg episode reward: [(0, '4864.210')] [2023-03-08 04:02:35,846][321237] Updated weights for policy 0, policy_version 43840 (0.0005) [2023-03-08 04:02:39,143][321237] Updated weights for policy 0, policy_version 43920 (0.0004) [2023-03-08 04:02:39,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11788.2). Total num frames: 22491136. Throughput: 0: 11971.9. Samples: 22475828. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:02:39,595][320945] Avg episode reward: [(0, '4864.734')] [2023-03-08 04:02:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000043928_22491136.pth... [2023-03-08 04:02:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000043200_22118400.pth [2023-03-08 04:02:42,474][321237] Updated weights for policy 0, policy_version 44000 (0.0005) [2023-03-08 04:02:44,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 11802.0). Total num frames: 22552576. Throughput: 0: 12135.6. Samples: 22549828. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:02:44,595][320945] Avg episode reward: [(0, '4859.769')] [2023-03-08 04:02:45,737][321237] Updated weights for policy 0, policy_version 44080 (0.0004) [2023-03-08 04:02:49,111][321237] Updated weights for policy 0, policy_version 44160 (0.0004) [2023-03-08 04:02:49,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11815.9). Total num frames: 22614016. Throughput: 0: 12210.6. Samples: 22587876. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:02:49,595][320945] Avg episode reward: [(0, '4820.386')] [2023-03-08 04:02:52,524][321237] Updated weights for policy 0, policy_version 44240 (0.0004) [2023-03-08 04:02:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 11815.9). Total num frames: 22671360. Throughput: 0: 12273.9. Samples: 22659144. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:02:54,595][320945] Avg episode reward: [(0, '4773.288')] [2023-03-08 04:02:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000044280_22671360.pth... [2023-03-08 04:02:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000043568_22306816.pth [2023-03-08 04:02:56,176][321237] Updated weights for policy 0, policy_version 44320 (0.0005) [2023-03-08 04:02:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 11815.9). Total num frames: 22728704. Throughput: 0: 12188.0. Samples: 22728312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:02:59,595][320945] Avg episode reward: [(0, '4821.362')] [2023-03-08 04:02:59,674][321237] Updated weights for policy 0, policy_version 44400 (0.0005) [2023-03-08 04:03:03,382][321237] Updated weights for policy 0, policy_version 44480 (0.0005) [2023-03-08 04:03:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 12083.2, 300 sec: 11815.9). Total num frames: 22786048. Throughput: 0: 12112.1. Samples: 22761536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:03:04,595][320945] Avg episode reward: [(0, '4818.191')] [2023-03-08 04:03:06,992][321237] Updated weights for policy 0, policy_version 44560 (0.0005) [2023-03-08 04:03:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 11802.0). Total num frames: 22843392. Throughput: 0: 11995.6. Samples: 22830812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:03:09,595][320945] Avg episode reward: [(0, '4819.957')] [2023-03-08 04:03:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000044616_22843392.pth... [2023-03-08 04:03:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000043928_22491136.pth [2023-03-08 04:03:10,401][321237] Updated weights for policy 0, policy_version 44640 (0.0005) [2023-03-08 04:03:13,571][321237] Updated weights for policy 0, policy_version 44720 (0.0004) [2023-03-08 04:03:14,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12151.4, 300 sec: 11829.8). Total num frames: 22908928. Throughput: 0: 11991.1. Samples: 22905156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:03:14,595][320945] Avg episode reward: [(0, '4687.007')] [2023-03-08 04:03:16,589][321237] Updated weights for policy 0, policy_version 44800 (0.0004) [2023-03-08 04:03:19,594][320945] Fps is (10 sec: 13107.2, 60 sec: 12151.4, 300 sec: 11857.6). Total num frames: 22974464. Throughput: 0: 12087.5. Samples: 22946208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:03:19,595][320945] Avg episode reward: [(0, '4737.400')] [2023-03-08 04:03:19,699][321237] Updated weights for policy 0, policy_version 44880 (0.0004) [2023-03-08 04:03:22,958][321237] Updated weights for policy 0, policy_version 44960 (0.0005) [2023-03-08 04:03:24,594][320945] Fps is (10 sec: 13107.2, 60 sec: 12219.7, 300 sec: 11885.3). Total num frames: 23040000. Throughput: 0: 12173.3. Samples: 23023628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:03:24,595][320945] Avg episode reward: [(0, '4788.163')] [2023-03-08 04:03:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000045000_23040000.pth... [2023-03-08 04:03:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000044280_22671360.pth [2023-03-08 04:03:26,091][321237] Updated weights for policy 0, policy_version 45040 (0.0004) [2023-03-08 04:03:29,222][321237] Updated weights for policy 0, policy_version 45120 (0.0004) [2023-03-08 04:03:29,594][320945] Fps is (10 sec: 13107.2, 60 sec: 12288.0, 300 sec: 11913.1). Total num frames: 23105536. Throughput: 0: 12261.2. Samples: 23101580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:03:29,595][320945] Avg episode reward: [(0, '4730.411')] [2023-03-08 04:03:32,433][321237] Updated weights for policy 0, policy_version 45200 (0.0005) [2023-03-08 04:03:34,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 11927.0). Total num frames: 23166976. Throughput: 0: 12263.6. Samples: 23139736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:03:34,595][320945] Avg episode reward: [(0, '4727.336')] [2023-03-08 04:03:35,621][321237] Updated weights for policy 0, policy_version 45280 (0.0004) [2023-03-08 04:03:38,775][321237] Updated weights for policy 0, policy_version 45360 (0.0004) [2023-03-08 04:03:39,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 11954.8). Total num frames: 23232512. Throughput: 0: 12405.6. Samples: 23217396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:03:39,595][320945] Avg episode reward: [(0, '4813.852')] [2023-03-08 04:03:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000045376_23232512.pth... [2023-03-08 04:03:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000044616_22843392.pth [2023-03-08 04:03:42,012][321237] Updated weights for policy 0, policy_version 45440 (0.0005) [2023-03-08 04:03:44,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12356.3, 300 sec: 11968.7). Total num frames: 23293952. Throughput: 0: 12571.2. Samples: 23294016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:03:44,594][320945] Avg episode reward: [(0, '4862.585')] [2023-03-08 04:03:45,229][321237] Updated weights for policy 0, policy_version 45520 (0.0004) [2023-03-08 04:03:48,458][321237] Updated weights for policy 0, policy_version 45600 (0.0005) [2023-03-08 04:03:49,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12424.5, 300 sec: 12010.3). Total num frames: 23359488. Throughput: 0: 12679.9. Samples: 23332132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:03:49,595][320945] Avg episode reward: [(0, '4860.003')] [2023-03-08 04:03:51,633][321237] Updated weights for policy 0, policy_version 45680 (0.0005) [2023-03-08 04:03:54,594][320945] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12038.1). Total num frames: 23425024. Throughput: 0: 12851.8. Samples: 23409144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:03:54,595][320945] Avg episode reward: [(0, '4751.764')] [2023-03-08 04:03:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000045752_23425024.pth... [2023-03-08 04:03:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000045000_23040000.pth [2023-03-08 04:03:54,744][321237] Updated weights for policy 0, policy_version 45760 (0.0004) [2023-03-08 04:03:57,935][321237] Updated weights for policy 0, policy_version 45840 (0.0005) [2023-03-08 04:03:59,594][320945] Fps is (10 sec: 13107.2, 60 sec: 12697.6, 300 sec: 12065.8). Total num frames: 23490560. Throughput: 0: 12925.5. Samples: 23486804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:03:59,595][320945] Avg episode reward: [(0, '4836.358')] [2023-03-08 04:04:01,086][321237] Updated weights for policy 0, policy_version 45920 (0.0005) [2023-03-08 04:04:04,249][321237] Updated weights for policy 0, policy_version 46000 (0.0005) [2023-03-08 04:04:04,594][320945] Fps is (10 sec: 13107.1, 60 sec: 12834.1, 300 sec: 12093.6). Total num frames: 23556096. Throughput: 0: 12881.6. Samples: 23525880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:04:04,595][320945] Avg episode reward: [(0, '4850.501')] [2023-03-08 04:04:07,199][321237] Updated weights for policy 0, policy_version 46080 (0.0004) [2023-03-08 04:04:09,594][320945] Fps is (10 sec: 13107.1, 60 sec: 12970.7, 300 sec: 12121.4). Total num frames: 23621632. Throughput: 0: 12978.3. Samples: 23607652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:04:09,595][320945] Avg episode reward: [(0, '4862.344')] [2023-03-08 04:04:09,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000046136_23621632.pth... [2023-03-08 04:04:09,602][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000045376_23232512.pth [2023-03-08 04:04:10,422][321237] Updated weights for policy 0, policy_version 46160 (0.0005) [2023-03-08 04:04:13,317][321237] Updated weights for policy 0, policy_version 46240 (0.0004) [2023-03-08 04:04:14,594][320945] Fps is (10 sec: 13516.8, 60 sec: 13038.9, 300 sec: 12163.0). Total num frames: 23691264. Throughput: 0: 13020.9. Samples: 23687520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:04:14,595][320945] Avg episode reward: [(0, '4861.849')] [2023-03-08 04:04:16,392][321237] Updated weights for policy 0, policy_version 46320 (0.0004) [2023-03-08 04:04:19,594][320945] Fps is (10 sec: 13107.3, 60 sec: 12970.7, 300 sec: 12163.0). Total num frames: 23752704. Throughput: 0: 13054.3. Samples: 23727180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:04:19,595][320945] Avg episode reward: [(0, '4862.301')] [2023-03-08 04:04:19,726][321237] Updated weights for policy 0, policy_version 46400 (0.0005) [2023-03-08 04:04:22,970][321237] Updated weights for policy 0, policy_version 46480 (0.0005) [2023-03-08 04:04:24,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12902.4, 300 sec: 12163.0). Total num frames: 23814144. Throughput: 0: 12988.2. Samples: 23801864. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:04:24,595][320945] Avg episode reward: [(0, '4859.073')] [2023-03-08 04:04:24,601][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000046520_23818240.pth... [2023-03-08 04:04:24,602][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000045752_23425024.pth [2023-03-08 04:04:26,220][321237] Updated weights for policy 0, policy_version 46560 (0.0005) [2023-03-08 04:04:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12834.1, 300 sec: 12163.0). Total num frames: 23875584. Throughput: 0: 12923.9. Samples: 23875592. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:04:29,595][320945] Avg episode reward: [(0, '4857.235')] [2023-03-08 04:04:29,608][321237] Updated weights for policy 0, policy_version 46640 (0.0005) [2023-03-08 04:04:32,874][321237] Updated weights for policy 0, policy_version 46720 (0.0005) [2023-03-08 04:04:34,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12176.9). Total num frames: 23941120. Throughput: 0: 12897.3. Samples: 23912512. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:04:34,595][320945] Avg episode reward: [(0, '4862.509')] [2023-03-08 04:04:36,030][321237] Updated weights for policy 0, policy_version 46800 (0.0004) [2023-03-08 04:04:39,458][321237] Updated weights for policy 0, policy_version 46880 (0.0005) [2023-03-08 04:04:39,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12834.1, 300 sec: 12176.9). Total num frames: 24002560. Throughput: 0: 12871.2. Samples: 23988348. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:04:39,595][320945] Avg episode reward: [(0, '4862.713')] [2023-03-08 04:04:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000046880_24002560.pth... [2023-03-08 04:04:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000046136_23621632.pth [2023-03-08 04:04:42,845][321237] Updated weights for policy 0, policy_version 46960 (0.0005) [2023-03-08 04:04:44,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12834.1, 300 sec: 12176.9). Total num frames: 24064000. Throughput: 0: 12778.1. Samples: 24061820. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:04:44,595][320945] Avg episode reward: [(0, '4864.351')] [2023-03-08 04:04:46,058][321237] Updated weights for policy 0, policy_version 47040 (0.0005) [2023-03-08 04:04:49,336][321237] Updated weights for policy 0, policy_version 47120 (0.0005) [2023-03-08 04:04:49,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12765.9, 300 sec: 12204.7). Total num frames: 24125440. Throughput: 0: 12768.4. Samples: 24100460. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:04:49,595][320945] Avg episode reward: [(0, '4858.450')] [2023-03-08 04:04:52,722][321237] Updated weights for policy 0, policy_version 47200 (0.0005) [2023-03-08 04:04:54,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12697.6, 300 sec: 12218.6). Total num frames: 24186880. Throughput: 0: 12559.2. Samples: 24172816. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:04:54,595][320945] Avg episode reward: [(0, '4838.764')] [2023-03-08 04:04:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000047240_24186880.pth... [2023-03-08 04:04:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000046520_23818240.pth [2023-03-08 04:04:56,174][321237] Updated weights for policy 0, policy_version 47280 (0.0005) [2023-03-08 04:04:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12561.1, 300 sec: 12218.6). Total num frames: 24244224. Throughput: 0: 12362.1. Samples: 24243816. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:04:59,595][320945] Avg episode reward: [(0, '4863.061')] [2023-03-08 04:04:59,699][321237] Updated weights for policy 0, policy_version 47360 (0.0004) [2023-03-08 04:05:03,101][321237] Updated weights for policy 0, policy_version 47440 (0.0005) [2023-03-08 04:05:04,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12246.3). Total num frames: 24305664. Throughput: 0: 12270.3. Samples: 24279344. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:05:04,595][320945] Avg episode reward: [(0, '4851.894')] [2023-03-08 04:05:06,486][321237] Updated weights for policy 0, policy_version 47520 (0.0005) [2023-03-08 04:05:09,594][320945] Fps is (10 sec: 11878.3, 60 sec: 12356.3, 300 sec: 12246.3). Total num frames: 24363008. Throughput: 0: 12197.0. Samples: 24350728. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:05:09,595][320945] Avg episode reward: [(0, '4854.748')] [2023-03-08 04:05:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000047584_24363008.pth... [2023-03-08 04:05:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000046880_24002560.pth [2023-03-08 04:05:10,015][321237] Updated weights for policy 0, policy_version 47600 (0.0005) [2023-03-08 04:05:13,555][321237] Updated weights for policy 0, policy_version 47680 (0.0005) [2023-03-08 04:05:14,594][320945] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12274.1). Total num frames: 24424448. Throughput: 0: 12107.2. Samples: 24420416. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:05:14,595][320945] Avg episode reward: [(0, '4854.978')] [2023-03-08 04:05:17,118][321237] Updated weights for policy 0, policy_version 47760 (0.0005) [2023-03-08 04:05:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 12246.3). Total num frames: 24477696. Throughput: 0: 12056.0. Samples: 24455032. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:05:19,595][320945] Avg episode reward: [(0, '4858.583')] [2023-03-08 04:05:20,742][321237] Updated weights for policy 0, policy_version 47840 (0.0005) [2023-03-08 04:05:24,313][321237] Updated weights for policy 0, policy_version 47920 (0.0005) [2023-03-08 04:05:24,594][320945] Fps is (10 sec: 11059.1, 60 sec: 12014.9, 300 sec: 12232.5). Total num frames: 24535040. Throughput: 0: 11877.1. Samples: 24522816. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:05:24,595][320945] Avg episode reward: [(0, '4862.618')] [2023-03-08 04:05:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000047920_24535040.pth... [2023-03-08 04:05:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000047240_24186880.pth [2023-03-08 04:05:27,491][321237] Updated weights for policy 0, policy_version 48000 (0.0005) [2023-03-08 04:05:29,594][320945] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 12260.2). Total num frames: 24600576. Throughput: 0: 11914.1. Samples: 24597952. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:05:29,595][320945] Avg episode reward: [(0, '4863.370')] [2023-03-08 04:05:30,792][321237] Updated weights for policy 0, policy_version 48080 (0.0004) [2023-03-08 04:05:34,014][321237] Updated weights for policy 0, policy_version 48160 (0.0004) [2023-03-08 04:05:34,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12014.9, 300 sec: 12274.1). Total num frames: 24662016. Throughput: 0: 11897.0. Samples: 24635824. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:05:34,595][320945] Avg episode reward: [(0, '4863.336')] [2023-03-08 04:05:37,374][321237] Updated weights for policy 0, policy_version 48240 (0.0004) [2023-03-08 04:05:39,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 12288.0). Total num frames: 24723456. Throughput: 0: 11958.4. Samples: 24710944. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:05:39,595][320945] Avg episode reward: [(0, '4863.093')] [2023-03-08 04:05:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000048288_24723456.pth... [2023-03-08 04:05:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000047584_24363008.pth [2023-03-08 04:05:40,647][321237] Updated weights for policy 0, policy_version 48320 (0.0004) [2023-03-08 04:05:44,025][321237] Updated weights for policy 0, policy_version 48400 (0.0004) [2023-03-08 04:05:44,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12301.9). Total num frames: 24784896. Throughput: 0: 12001.0. Samples: 24783860. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:05:44,595][320945] Avg episode reward: [(0, '4862.298')] [2023-03-08 04:05:47,374][321237] Updated weights for policy 0, policy_version 48480 (0.0004) [2023-03-08 04:05:49,594][320945] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 12301.9). Total num frames: 24846336. Throughput: 0: 12035.6. Samples: 24820948. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:05:49,595][320945] Avg episode reward: [(0, '4861.910')] [2023-03-08 04:05:51,015][321237] Updated weights for policy 0, policy_version 48560 (0.0005) [2023-03-08 04:05:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11878.4, 300 sec: 12274.1). Total num frames: 24899584. Throughput: 0: 11925.2. Samples: 24887360. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:05:54,595][320945] Avg episode reward: [(0, '4863.622')] [2023-03-08 04:05:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000048632_24899584.pth... [2023-03-08 04:05:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000047920_24535040.pth [2023-03-08 04:05:54,660][321237] Updated weights for policy 0, policy_version 48640 (0.0005) [2023-03-08 04:05:58,163][321237] Updated weights for policy 0, policy_version 48720 (0.0005) [2023-03-08 04:05:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11878.4, 300 sec: 12246.3). Total num frames: 24956928. Throughput: 0: 11922.6. Samples: 24956936. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:05:59,595][320945] Avg episode reward: [(0, '4862.009')] [2023-03-08 04:06:01,799][321237] Updated weights for policy 0, policy_version 48800 (0.0005) [2023-03-08 04:06:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 12232.5). Total num frames: 25014272. Throughput: 0: 11912.4. Samples: 24991088. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:06:04,595][320945] Avg episode reward: [(0, '4861.931')] [2023-03-08 04:06:05,323][321237] Updated weights for policy 0, policy_version 48880 (0.0005) [2023-03-08 04:06:08,857][321237] Updated weights for policy 0, policy_version 48960 (0.0005) [2023-03-08 04:06:09,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 12218.6). Total num frames: 25075712. Throughput: 0: 11953.1. Samples: 25060704. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:06:09,595][320945] Avg episode reward: [(0, '4861.929')] [2023-03-08 04:06:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000048976_25075712.pth... [2023-03-08 04:06:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000048288_24723456.pth [2023-03-08 04:06:12,346][321237] Updated weights for policy 0, policy_version 49040 (0.0005) [2023-03-08 04:06:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12218.6). Total num frames: 25133056. Throughput: 0: 11842.1. Samples: 25130848. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:06:14,595][320945] Avg episode reward: [(0, '4859.375')] [2023-03-08 04:06:15,902][321237] Updated weights for policy 0, policy_version 49120 (0.0005) [2023-03-08 04:06:19,490][321237] Updated weights for policy 0, policy_version 49200 (0.0005) [2023-03-08 04:06:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 12218.6). Total num frames: 25190400. Throughput: 0: 11772.0. Samples: 25165564. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:06:19,595][320945] Avg episode reward: [(0, '4861.545')] [2023-03-08 04:06:23,005][321237] Updated weights for policy 0, policy_version 49280 (0.0005) [2023-03-08 04:06:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 12204.7). Total num frames: 25247744. Throughput: 0: 11646.8. Samples: 25235052. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:06:24,595][320945] Avg episode reward: [(0, '4857.170')] [2023-03-08 04:06:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000049312_25247744.pth... [2023-03-08 04:06:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000048632_24899584.pth [2023-03-08 04:06:26,507][321237] Updated weights for policy 0, policy_version 49360 (0.0005) [2023-03-08 04:06:29,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 12176.9). Total num frames: 25305088. Throughput: 0: 11582.9. Samples: 25305088. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:06:29,594][320945] Avg episode reward: [(0, '4860.353')] [2023-03-08 04:06:30,038][321237] Updated weights for policy 0, policy_version 49440 (0.0005) [2023-03-08 04:06:33,567][321237] Updated weights for policy 0, policy_version 49520 (0.0005) [2023-03-08 04:06:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 12163.0). Total num frames: 25362432. Throughput: 0: 11530.0. Samples: 25339796. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:06:34,594][320945] Avg episode reward: [(0, '4860.511')] [2023-03-08 04:06:37,117][321237] Updated weights for policy 0, policy_version 49600 (0.0005) [2023-03-08 04:06:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.4, 300 sec: 12149.2). Total num frames: 25419776. Throughput: 0: 11575.2. Samples: 25408244. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:06:39,594][320945] Avg episode reward: [(0, '4862.893')] [2023-03-08 04:06:39,658][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000049656_25423872.pth... [2023-03-08 04:06:39,659][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000048976_25075712.pth [2023-03-08 04:06:40,728][321237] Updated weights for policy 0, policy_version 49680 (0.0005) [2023-03-08 04:06:44,243][321237] Updated weights for policy 0, policy_version 49760 (0.0005) [2023-03-08 04:06:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 12149.2). Total num frames: 25477120. Throughput: 0: 11561.3. Samples: 25477192. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:06:44,594][320945] Avg episode reward: [(0, '4860.822')] [2023-03-08 04:06:47,815][321237] Updated weights for policy 0, policy_version 49840 (0.0005) [2023-03-08 04:06:49,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11537.1, 300 sec: 12163.0). Total num frames: 25538560. Throughput: 0: 11574.7. Samples: 25511948. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:06:49,595][320945] Avg episode reward: [(0, '4861.648')] [2023-03-08 04:06:51,367][321237] Updated weights for policy 0, policy_version 49920 (0.0005) [2023-03-08 04:06:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 12163.0). Total num frames: 25591808. Throughput: 0: 11530.9. Samples: 25579592. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:06:54,594][320945] Avg episode reward: [(0, '4865.083')] [2023-03-08 04:06:54,632][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000049992_25595904.pth... [2023-03-08 04:06:54,634][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000049312_25247744.pth [2023-03-08 04:06:54,983][321237] Updated weights for policy 0, policy_version 50000 (0.0005) [2023-03-08 04:06:58,509][321237] Updated weights for policy 0, policy_version 50080 (0.0005) [2023-03-08 04:06:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 12176.9). Total num frames: 25653248. Throughput: 0: 11519.7. Samples: 25649232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:06:59,595][320945] Avg episode reward: [(0, '4862.342')] [2023-03-08 04:07:02,024][321237] Updated weights for policy 0, policy_version 50160 (0.0005) [2023-03-08 04:07:04,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 12176.9). Total num frames: 25710592. Throughput: 0: 11547.1. Samples: 25685184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:07:04,595][320945] Avg episode reward: [(0, '4860.582')] [2023-03-08 04:07:05,406][321237] Updated weights for policy 0, policy_version 50240 (0.0005) [2023-03-08 04:07:08,859][321237] Updated weights for policy 0, policy_version 50320 (0.0005) [2023-03-08 04:07:09,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 12176.9). Total num frames: 25772032. Throughput: 0: 11601.6. Samples: 25757124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:07:09,595][320945] Avg episode reward: [(0, '4818.670')] [2023-03-08 04:07:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000050336_25772032.pth... [2023-03-08 04:07:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000049656_25423872.pth [2023-03-08 04:07:12,135][321237] Updated weights for policy 0, policy_version 50400 (0.0005) [2023-03-08 04:07:14,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11673.6, 300 sec: 12163.0). Total num frames: 25833472. Throughput: 0: 11652.4. Samples: 25829448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:07:14,595][320945] Avg episode reward: [(0, '4859.842')] [2023-03-08 04:07:15,623][321237] Updated weights for policy 0, policy_version 50480 (0.0005) [2023-03-08 04:07:19,096][321237] Updated weights for policy 0, policy_version 50560 (0.0005) [2023-03-08 04:07:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 12149.2). Total num frames: 25890816. Throughput: 0: 11692.3. Samples: 25865952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:07:19,595][320945] Avg episode reward: [(0, '4860.934')] [2023-03-08 04:07:22,579][321237] Updated weights for policy 0, policy_version 50640 (0.0005) [2023-03-08 04:07:24,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 12135.3). Total num frames: 25948160. Throughput: 0: 11726.5. Samples: 25935936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:07:24,594][320945] Avg episode reward: [(0, '4819.983')] [2023-03-08 04:07:24,658][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000050688_25952256.pth... [2023-03-08 04:07:24,659][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000049992_25595904.pth [2023-03-08 04:07:26,079][321237] Updated weights for policy 0, policy_version 50720 (0.0005) [2023-03-08 04:07:29,592][321237] Updated weights for policy 0, policy_version 50800 (0.0004) [2023-03-08 04:07:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 12135.3). Total num frames: 26009600. Throughput: 0: 11741.9. Samples: 26005576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:07:29,595][320945] Avg episode reward: [(0, '4686.187')] [2023-03-08 04:07:33,172][321237] Updated weights for policy 0, policy_version 50880 (0.0005) [2023-03-08 04:07:34,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 12121.4). Total num frames: 26066944. Throughput: 0: 11732.2. Samples: 26039896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:07:34,595][320945] Avg episode reward: [(0, '4692.303')] [2023-03-08 04:07:36,709][321237] Updated weights for policy 0, policy_version 50960 (0.0004) [2023-03-08 04:07:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11741.8, 300 sec: 12107.5). Total num frames: 26124288. Throughput: 0: 11793.5. Samples: 26110300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:07:39,595][320945] Avg episode reward: [(0, '4819.152')] [2023-03-08 04:07:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000051024_26124288.pth... [2023-03-08 04:07:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000050336_25772032.pth [2023-03-08 04:07:40,199][321237] Updated weights for policy 0, policy_version 51040 (0.0005) [2023-03-08 04:07:43,970][321237] Updated weights for policy 0, policy_version 51120 (0.0005) [2023-03-08 04:07:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 12079.7). Total num frames: 26177536. Throughput: 0: 11739.5. Samples: 26177508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:07:44,595][320945] Avg episode reward: [(0, '4861.084')] [2023-03-08 04:07:47,503][321237] Updated weights for policy 0, policy_version 51200 (0.0005) [2023-03-08 04:07:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 12079.7). Total num frames: 26234880. Throughput: 0: 11693.3. Samples: 26211384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:07:49,595][320945] Avg episode reward: [(0, '4770.427')] [2023-03-08 04:07:51,170][321237] Updated weights for policy 0, policy_version 51280 (0.0005) [2023-03-08 04:07:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 12079.7). Total num frames: 26292224. Throughput: 0: 11603.4. Samples: 26279276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:07:54,595][320945] Avg episode reward: [(0, '4819.366')] [2023-03-08 04:07:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000051352_26292224.pth... [2023-03-08 04:07:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000050688_25952256.pth [2023-03-08 04:07:54,749][321237] Updated weights for policy 0, policy_version 51360 (0.0005) [2023-03-08 04:07:58,319][321237] Updated weights for policy 0, policy_version 51440 (0.0005) [2023-03-08 04:07:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 12079.7). Total num frames: 26349568. Throughput: 0: 11515.7. Samples: 26347656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:07:59,595][320945] Avg episode reward: [(0, '4859.062')] [2023-03-08 04:08:01,875][321237] Updated weights for policy 0, policy_version 51520 (0.0005) [2023-03-08 04:08:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 12079.7). Total num frames: 26406912. Throughput: 0: 11476.8. Samples: 26382408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:08:04,595][320945] Avg episode reward: [(0, '4820.874')] [2023-03-08 04:08:05,394][321237] Updated weights for policy 0, policy_version 51600 (0.0005) [2023-03-08 04:08:08,899][321237] Updated weights for policy 0, policy_version 51680 (0.0005) [2023-03-08 04:08:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 12052.0). Total num frames: 26464256. Throughput: 0: 11477.4. Samples: 26452420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:08:09,594][320945] Avg episode reward: [(0, '4863.972')] [2023-03-08 04:08:09,606][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000051696_26468352.pth... [2023-03-08 04:08:09,608][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000051024_26124288.pth [2023-03-08 04:08:12,478][321237] Updated weights for policy 0, policy_version 51760 (0.0005) [2023-03-08 04:08:14,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 12024.2). Total num frames: 26521600. Throughput: 0: 11467.2. Samples: 26521600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:08:14,594][320945] Avg episode reward: [(0, '4863.674')] [2023-03-08 04:08:16,113][321237] Updated weights for policy 0, policy_version 51840 (0.0005) [2023-03-08 04:08:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11996.4). Total num frames: 26578944. Throughput: 0: 11444.3. Samples: 26554888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:08:19,595][320945] Avg episode reward: [(0, '4818.651')] [2023-03-08 04:08:19,660][321237] Updated weights for policy 0, policy_version 51920 (0.0004) [2023-03-08 04:08:23,130][321237] Updated weights for policy 0, policy_version 52000 (0.0004) [2023-03-08 04:08:24,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11537.1, 300 sec: 11982.5). Total num frames: 26640384. Throughput: 0: 11451.0. Samples: 26625596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:08:24,595][320945] Avg episode reward: [(0, '4860.514')] [2023-03-08 04:08:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000052032_26640384.pth... [2023-03-08 04:08:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000051352_26292224.pth [2023-03-08 04:08:26,608][321237] Updated weights for policy 0, policy_version 52080 (0.0005) [2023-03-08 04:08:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11968.7). Total num frames: 26697728. Throughput: 0: 11506.7. Samples: 26695308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:08:29,595][320945] Avg episode reward: [(0, '4821.485')] [2023-03-08 04:08:30,208][321237] Updated weights for policy 0, policy_version 52160 (0.0005) [2023-03-08 04:08:33,724][321237] Updated weights for policy 0, policy_version 52240 (0.0005) [2023-03-08 04:08:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11940.9). Total num frames: 26755072. Throughput: 0: 11534.9. Samples: 26730452. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:08:34,595][320945] Avg episode reward: [(0, '4863.122')] [2023-03-08 04:08:37,359][321237] Updated weights for policy 0, policy_version 52320 (0.0004) [2023-03-08 04:08:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11927.0). Total num frames: 26812416. Throughput: 0: 11535.9. Samples: 26798392. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:08:39,595][320945] Avg episode reward: [(0, '4864.268')] [2023-03-08 04:08:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000052368_26812416.pth... [2023-03-08 04:08:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000051696_26468352.pth [2023-03-08 04:08:40,947][321237] Updated weights for policy 0, policy_version 52400 (0.0005) [2023-03-08 04:08:44,363][321237] Updated weights for policy 0, policy_version 52480 (0.0005) [2023-03-08 04:08:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11899.2). Total num frames: 26869760. Throughput: 0: 11591.1. Samples: 26869256. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:08:44,595][320945] Avg episode reward: [(0, '4862.352')] [2023-03-08 04:08:47,912][321237] Updated weights for policy 0, policy_version 52560 (0.0005) [2023-03-08 04:08:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11871.5). Total num frames: 26927104. Throughput: 0: 11564.5. Samples: 26902812. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:08:49,595][320945] Avg episode reward: [(0, '4863.404')] [2023-03-08 04:08:51,468][321237] Updated weights for policy 0, policy_version 52640 (0.0005) [2023-03-08 04:08:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11857.6). Total num frames: 26988544. Throughput: 0: 11558.6. Samples: 26972560. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:08:54,595][320945] Avg episode reward: [(0, '4865.100')] [2023-03-08 04:08:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000052712_26988544.pth... [2023-03-08 04:08:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000052032_26640384.pth [2023-03-08 04:08:54,896][321237] Updated weights for policy 0, policy_version 52720 (0.0005) [2023-03-08 04:08:58,404][321237] Updated weights for policy 0, policy_version 52800 (0.0005) [2023-03-08 04:08:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11829.8). Total num frames: 27045888. Throughput: 0: 11594.0. Samples: 27043332. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:08:59,605][320945] Avg episode reward: [(0, '4861.938')] [2023-03-08 04:09:01,983][321237] Updated weights for policy 0, policy_version 52880 (0.0005) [2023-03-08 04:09:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11802.0). Total num frames: 27103232. Throughput: 0: 11636.4. Samples: 27078524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:09:04,595][320945] Avg episode reward: [(0, '4860.152')] [2023-03-08 04:09:05,563][321237] Updated weights for policy 0, policy_version 52960 (0.0005) [2023-03-08 04:09:09,039][321237] Updated weights for policy 0, policy_version 53040 (0.0005) [2023-03-08 04:09:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11760.4). Total num frames: 27160576. Throughput: 0: 11611.8. Samples: 27148128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:09:09,595][320945] Avg episode reward: [(0, '4820.090')] [2023-03-08 04:09:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000053048_27160576.pth... [2023-03-08 04:09:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000052368_26812416.pth [2023-03-08 04:09:12,635][321237] Updated weights for policy 0, policy_version 53120 (0.0005) [2023-03-08 04:09:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11746.5). Total num frames: 27217920. Throughput: 0: 11582.2. Samples: 27216508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:09:14,595][320945] Avg episode reward: [(0, '4863.522')] [2023-03-08 04:09:16,159][321237] Updated weights for policy 0, policy_version 53200 (0.0005) [2023-03-08 04:09:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11732.6). Total num frames: 27275264. Throughput: 0: 11562.4. Samples: 27250760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:09:19,594][320945] Avg episode reward: [(0, '4862.829')] [2023-03-08 04:09:19,655][321237] Updated weights for policy 0, policy_version 53280 (0.0005) [2023-03-08 04:09:23,190][321237] Updated weights for policy 0, policy_version 53360 (0.0004) [2023-03-08 04:09:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11732.6). Total num frames: 27336704. Throughput: 0: 11613.2. Samples: 27320988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:09:24,595][320945] Avg episode reward: [(0, '4861.001')] [2023-03-08 04:09:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000053392_27336704.pth... [2023-03-08 04:09:24,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000052712_26988544.pth [2023-03-08 04:09:26,667][321237] Updated weights for policy 0, policy_version 53440 (0.0005) [2023-03-08 04:09:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11704.8). Total num frames: 27394048. Throughput: 0: 11618.2. Samples: 27392076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:09:29,595][320945] Avg episode reward: [(0, '4864.785')] [2023-03-08 04:09:30,131][321237] Updated weights for policy 0, policy_version 53520 (0.0004) [2023-03-08 04:09:33,627][321237] Updated weights for policy 0, policy_version 53600 (0.0005) [2023-03-08 04:09:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11691.0). Total num frames: 27451392. Throughput: 0: 11646.1. Samples: 27426888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:09:34,595][320945] Avg episode reward: [(0, '4860.499')] [2023-03-08 04:09:37,103][321237] Updated weights for policy 0, policy_version 53680 (0.0005) [2023-03-08 04:09:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11691.0). Total num frames: 27512832. Throughput: 0: 11669.3. Samples: 27497680. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:09:39,595][320945] Avg episode reward: [(0, '4862.691')] [2023-03-08 04:09:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000053736_27512832.pth... [2023-03-08 04:09:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000053048_27160576.pth [2023-03-08 04:09:40,655][321237] Updated weights for policy 0, policy_version 53760 (0.0005) [2023-03-08 04:09:44,238][321237] Updated weights for policy 0, policy_version 53840 (0.0005) [2023-03-08 04:09:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11677.1). Total num frames: 27570176. Throughput: 0: 11618.2. Samples: 27566152. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:09:44,595][320945] Avg episode reward: [(0, '4859.440')] [2023-03-08 04:09:47,719][321237] Updated weights for policy 0, policy_version 53920 (0.0005) [2023-03-08 04:09:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 27627520. Throughput: 0: 11627.6. Samples: 27601764. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:09:49,595][320945] Avg episode reward: [(0, '4858.502')] [2023-03-08 04:09:51,298][321237] Updated weights for policy 0, policy_version 54000 (0.0005) [2023-03-08 04:09:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11663.2). Total num frames: 27684864. Throughput: 0: 11609.7. Samples: 27670564. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:09:54,595][320945] Avg episode reward: [(0, '4863.240')] [2023-03-08 04:09:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000054072_27684864.pth... [2023-03-08 04:09:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000053392_27336704.pth [2023-03-08 04:09:54,887][321237] Updated weights for policy 0, policy_version 54080 (0.0005) [2023-03-08 04:09:58,409][321237] Updated weights for policy 0, policy_version 54160 (0.0005) [2023-03-08 04:09:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11649.3). Total num frames: 27742208. Throughput: 0: 11645.8. Samples: 27740568. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:09:59,595][320945] Avg episode reward: [(0, '4860.389')] [2023-03-08 04:10:01,644][321237] Updated weights for policy 0, policy_version 54240 (0.0004) [2023-03-08 04:10:04,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 27803648. Throughput: 0: 11741.7. Samples: 27779136. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:10:04,594][320945] Avg episode reward: [(0, '4863.366')] [2023-03-08 04:10:05,005][321237] Updated weights for policy 0, policy_version 54320 (0.0004) [2023-03-08 04:10:08,593][321237] Updated weights for policy 0, policy_version 54400 (0.0005) [2023-03-08 04:10:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11649.3). Total num frames: 27860992. Throughput: 0: 11727.3. Samples: 27848716. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:10:09,595][320945] Avg episode reward: [(0, '4864.054')] [2023-03-08 04:10:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000054416_27860992.pth... [2023-03-08 04:10:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000053736_27512832.pth [2023-03-08 04:10:12,151][321237] Updated weights for policy 0, policy_version 54480 (0.0005) [2023-03-08 04:10:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 27922432. Throughput: 0: 11699.5. Samples: 27918552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:10:14,595][320945] Avg episode reward: [(0, '4862.898')] [2023-03-08 04:10:15,608][321237] Updated weights for policy 0, policy_version 54560 (0.0005) [2023-03-08 04:10:19,111][321237] Updated weights for policy 0, policy_version 54640 (0.0004) [2023-03-08 04:10:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 27979776. Throughput: 0: 11733.2. Samples: 27954884. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:10:19,595][320945] Avg episode reward: [(0, '4862.576')] [2023-03-08 04:10:22,567][321237] Updated weights for policy 0, policy_version 54720 (0.0003) [2023-03-08 04:10:24,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11649.3). Total num frames: 28037120. Throughput: 0: 11714.7. Samples: 28024840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:10:24,595][320945] Avg episode reward: [(0, '4818.118')] [2023-03-08 04:10:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000054760_28037120.pth... [2023-03-08 04:10:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000054072_27684864.pth [2023-03-08 04:10:26,224][321237] Updated weights for policy 0, policy_version 54800 (0.0004) [2023-03-08 04:10:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11635.4). Total num frames: 28094464. Throughput: 0: 11703.7. Samples: 28092820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:10:29,595][320945] Avg episode reward: [(0, '4862.456')] [2023-03-08 04:10:29,778][321237] Updated weights for policy 0, policy_version 54880 (0.0005) [2023-03-08 04:10:33,304][321237] Updated weights for policy 0, policy_version 54960 (0.0005) [2023-03-08 04:10:34,594][320945] Fps is (10 sec: 11469.0, 60 sec: 11673.6, 300 sec: 11621.5). Total num frames: 28151808. Throughput: 0: 11681.7. Samples: 28127440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:10:34,594][320945] Avg episode reward: [(0, '4774.796')] [2023-03-08 04:10:36,819][321237] Updated weights for policy 0, policy_version 55040 (0.0005) [2023-03-08 04:10:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11607.6). Total num frames: 28209152. Throughput: 0: 11695.7. Samples: 28196872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:10:39,595][320945] Avg episode reward: [(0, '4863.932')] [2023-03-08 04:10:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000055096_28209152.pth... [2023-03-08 04:10:39,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000054416_27860992.pth [2023-03-08 04:10:40,417][321237] Updated weights for policy 0, policy_version 55120 (0.0004) [2023-03-08 04:10:44,046][321237] Updated weights for policy 0, policy_version 55200 (0.0005) [2023-03-08 04:10:44,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11593.8). Total num frames: 28266496. Throughput: 0: 11656.4. Samples: 28265104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:10:44,595][320945] Avg episode reward: [(0, '4862.376')] [2023-03-08 04:10:47,706][321237] Updated weights for policy 0, policy_version 55280 (0.0005) [2023-03-08 04:10:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11607.6). Total num frames: 28323840. Throughput: 0: 11552.1. Samples: 28298980. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:10:49,595][320945] Avg episode reward: [(0, '4862.670')] [2023-03-08 04:10:51,256][321237] Updated weights for policy 0, policy_version 55360 (0.0005) [2023-03-08 04:10:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11607.6). Total num frames: 28381184. Throughput: 0: 11532.7. Samples: 28367688. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:10:54,595][320945] Avg episode reward: [(0, '4859.884')] [2023-03-08 04:10:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000055432_28381184.pth... [2023-03-08 04:10:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000054760_28037120.pth [2023-03-08 04:10:54,862][321237] Updated weights for policy 0, policy_version 55440 (0.0005) [2023-03-08 04:10:58,486][321237] Updated weights for policy 0, policy_version 55520 (0.0005) [2023-03-08 04:10:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11607.6). Total num frames: 28438528. Throughput: 0: 11469.4. Samples: 28434676. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:10:59,595][320945] Avg episode reward: [(0, '4860.864')] [2023-03-08 04:11:02,135][321237] Updated weights for policy 0, policy_version 55600 (0.0005) [2023-03-08 04:11:04,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11579.9). Total num frames: 28491776. Throughput: 0: 11412.0. Samples: 28468424. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:11:04,595][320945] Avg episode reward: [(0, '4864.400')] [2023-03-08 04:11:05,879][321237] Updated weights for policy 0, policy_version 55680 (0.0005) [2023-03-08 04:11:09,436][321237] Updated weights for policy 0, policy_version 55760 (0.0005) [2023-03-08 04:11:09,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11579.9). Total num frames: 28549120. Throughput: 0: 11368.4. Samples: 28536416. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:11:09,595][320945] Avg episode reward: [(0, '4863.049')] [2023-03-08 04:11:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000055760_28549120.pth... [2023-03-08 04:11:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000055096_28209152.pth [2023-03-08 04:11:13,023][321237] Updated weights for policy 0, policy_version 55840 (0.0005) [2023-03-08 04:11:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11579.9). Total num frames: 28606464. Throughput: 0: 11365.3. Samples: 28604256. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:11:14,595][320945] Avg episode reward: [(0, '4862.682')] [2023-03-08 04:11:16,568][321237] Updated weights for policy 0, policy_version 55920 (0.0005) [2023-03-08 04:11:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11579.9). Total num frames: 28663808. Throughput: 0: 11373.1. Samples: 28639232. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:11:19,595][320945] Avg episode reward: [(0, '4862.326')] [2023-03-08 04:11:20,174][321237] Updated weights for policy 0, policy_version 56000 (0.0005) [2023-03-08 04:11:23,920][321237] Updated weights for policy 0, policy_version 56080 (0.0005) [2023-03-08 04:11:24,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11332.3, 300 sec: 11566.0). Total num frames: 28717056. Throughput: 0: 11292.8. Samples: 28705048. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:11:24,595][320945] Avg episode reward: [(0, '4861.503')] [2023-03-08 04:11:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000056088_28717056.pth... [2023-03-08 04:11:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000055432_28381184.pth [2023-03-08 04:11:27,604][321237] Updated weights for policy 0, policy_version 56160 (0.0005) [2023-03-08 04:11:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11566.0). Total num frames: 28774400. Throughput: 0: 11277.2. Samples: 28772576. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:11:29,595][320945] Avg episode reward: [(0, '4865.283')] [2023-03-08 04:11:31,281][321237] Updated weights for policy 0, policy_version 56240 (0.0005) [2023-03-08 04:11:34,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11552.1). Total num frames: 28827648. Throughput: 0: 11260.4. Samples: 28805700. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:11:34,595][320945] Avg episode reward: [(0, '4863.640')] [2023-03-08 04:11:35,038][321237] Updated weights for policy 0, policy_version 56320 (0.0005) [2023-03-08 04:11:38,728][321237] Updated weights for policy 0, policy_version 56400 (0.0005) [2023-03-08 04:11:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11552.1). Total num frames: 28884992. Throughput: 0: 11218.0. Samples: 28872496. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:11:39,595][320945] Avg episode reward: [(0, '4860.946')] [2023-03-08 04:11:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000056416_28884992.pth... [2023-03-08 04:11:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000055760_28549120.pth [2023-03-08 04:11:42,389][321237] Updated weights for policy 0, policy_version 56480 (0.0005) [2023-03-08 04:11:44,594][320945] Fps is (10 sec: 11469.0, 60 sec: 11264.0, 300 sec: 11538.2). Total num frames: 28942336. Throughput: 0: 11191.8. Samples: 28938304. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:11:44,594][320945] Avg episode reward: [(0, '4860.057')] [2023-03-08 04:11:46,072][321237] Updated weights for policy 0, policy_version 56560 (0.0005) [2023-03-08 04:11:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11538.2). Total num frames: 28995584. Throughput: 0: 11182.8. Samples: 28971652. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:11:49,595][320945] Avg episode reward: [(0, '4864.847')] [2023-03-08 04:11:49,713][321237] Updated weights for policy 0, policy_version 56640 (0.0005) [2023-03-08 04:11:53,386][321237] Updated weights for policy 0, policy_version 56720 (0.0005) [2023-03-08 04:11:54,594][320945] Fps is (10 sec: 11059.0, 60 sec: 11195.7, 300 sec: 11524.3). Total num frames: 29052928. Throughput: 0: 11182.7. Samples: 29039640. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:11:54,595][320945] Avg episode reward: [(0, '4864.734')] [2023-03-08 04:11:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000056744_29052928.pth... [2023-03-08 04:11:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000056088_28717056.pth [2023-03-08 04:11:56,980][321237] Updated weights for policy 0, policy_version 56800 (0.0005) [2023-03-08 04:11:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11524.3). Total num frames: 29110272. Throughput: 0: 11190.9. Samples: 29107848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:11:59,595][320945] Avg episode reward: [(0, '4859.297')] [2023-03-08 04:12:00,483][321237] Updated weights for policy 0, policy_version 56880 (0.0005) [2023-03-08 04:12:04,104][321237] Updated weights for policy 0, policy_version 56960 (0.0005) [2023-03-08 04:12:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11264.0, 300 sec: 11510.5). Total num frames: 29167616. Throughput: 0: 11197.2. Samples: 29143104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:12:04,595][320945] Avg episode reward: [(0, '4863.671')] [2023-03-08 04:12:07,766][321237] Updated weights for policy 0, policy_version 57040 (0.0005) [2023-03-08 04:12:09,594][320945] Fps is (10 sec: 11059.0, 60 sec: 11195.7, 300 sec: 11482.7). Total num frames: 29220864. Throughput: 0: 11210.3. Samples: 29209512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:12:09,595][320945] Avg episode reward: [(0, '4862.596')] [2023-03-08 04:12:09,631][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000057080_29224960.pth... [2023-03-08 04:12:09,633][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000056416_28884992.pth [2023-03-08 04:12:11,423][321237] Updated weights for policy 0, policy_version 57120 (0.0005) [2023-03-08 04:12:14,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11195.7, 300 sec: 11482.7). Total num frames: 29278208. Throughput: 0: 11237.7. Samples: 29278272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:12:14,595][320945] Avg episode reward: [(0, '4861.647')] [2023-03-08 04:12:14,987][321237] Updated weights for policy 0, policy_version 57200 (0.0005) [2023-03-08 04:12:18,673][321237] Updated weights for policy 0, policy_version 57280 (0.0005) [2023-03-08 04:12:19,594][320945] Fps is (10 sec: 11469.0, 60 sec: 11195.7, 300 sec: 11482.7). Total num frames: 29335552. Throughput: 0: 11234.7. Samples: 29311260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:12:19,595][320945] Avg episode reward: [(0, '4863.289')] [2023-03-08 04:12:22,408][321237] Updated weights for policy 0, policy_version 57360 (0.0005) [2023-03-08 04:12:24,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11195.7, 300 sec: 11454.9). Total num frames: 29388800. Throughput: 0: 11228.0. Samples: 29377760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:12:24,595][320945] Avg episode reward: [(0, '4861.416')] [2023-03-08 04:12:24,656][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000057408_29392896.pth... [2023-03-08 04:12:24,658][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000056744_29052928.pth [2023-03-08 04:12:26,096][321237] Updated weights for policy 0, policy_version 57440 (0.0005) [2023-03-08 04:12:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11454.9). Total num frames: 29446144. Throughput: 0: 11252.3. Samples: 29444660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:12:29,595][320945] Avg episode reward: [(0, '4861.696')] [2023-03-08 04:12:29,729][321237] Updated weights for policy 0, policy_version 57520 (0.0005) [2023-03-08 04:12:32,979][321237] Updated weights for policy 0, policy_version 57600 (0.0004) [2023-03-08 04:12:34,594][320945] Fps is (10 sec: 11878.6, 60 sec: 11332.3, 300 sec: 11468.8). Total num frames: 29507584. Throughput: 0: 11334.1. Samples: 29481688. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:12:34,595][320945] Avg episode reward: [(0, '4864.167')] [2023-03-08 04:12:36,279][321237] Updated weights for policy 0, policy_version 57680 (0.0004) [2023-03-08 04:12:39,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11400.5, 300 sec: 11496.6). Total num frames: 29569024. Throughput: 0: 11444.2. Samples: 29554628. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:12:39,595][320945] Avg episode reward: [(0, '4862.987')] [2023-03-08 04:12:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000057752_29569024.pth... [2023-03-08 04:12:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000057080_29224960.pth [2023-03-08 04:12:39,890][321237] Updated weights for policy 0, policy_version 57760 (0.0005) [2023-03-08 04:12:43,521][321237] Updated weights for policy 0, policy_version 57840 (0.0005) [2023-03-08 04:12:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.2, 300 sec: 11482.7). Total num frames: 29622272. Throughput: 0: 11433.2. Samples: 29622344. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:12:44,595][320945] Avg episode reward: [(0, '4858.378')] [2023-03-08 04:12:47,134][321237] Updated weights for policy 0, policy_version 57920 (0.0005) [2023-03-08 04:12:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11400.5, 300 sec: 11482.7). Total num frames: 29679616. Throughput: 0: 11403.4. Samples: 29656256. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:12:49,595][320945] Avg episode reward: [(0, '4817.199')] [2023-03-08 04:12:50,739][321237] Updated weights for policy 0, policy_version 58000 (0.0005) [2023-03-08 04:12:54,459][321237] Updated weights for policy 0, policy_version 58080 (0.0005) [2023-03-08 04:12:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11482.7). Total num frames: 29736960. Throughput: 0: 11440.0. Samples: 29724312. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:12:54,595][320945] Avg episode reward: [(0, '4861.747')] [2023-03-08 04:12:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000058080_29736960.pth... [2023-03-08 04:12:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000057408_29392896.pth [2023-03-08 04:12:58,120][321237] Updated weights for policy 0, policy_version 58160 (0.0005) [2023-03-08 04:12:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11482.7). Total num frames: 29794304. Throughput: 0: 11378.0. Samples: 29790280. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:12:59,595][320945] Avg episode reward: [(0, '4864.318')] [2023-03-08 04:13:01,647][321237] Updated weights for policy 0, policy_version 58240 (0.0005) [2023-03-08 04:13:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11482.7). Total num frames: 29851648. Throughput: 0: 11436.5. Samples: 29825904. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:13:04,595][320945] Avg episode reward: [(0, '4862.431')] [2023-03-08 04:13:05,266][321237] Updated weights for policy 0, policy_version 58320 (0.0005) [2023-03-08 04:13:08,852][321237] Updated weights for policy 0, policy_version 58400 (0.0005) [2023-03-08 04:13:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11482.7). Total num frames: 29908992. Throughput: 0: 11489.0. Samples: 29894764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:13:09,595][320945] Avg episode reward: [(0, '4818.223')] [2023-03-08 04:13:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000058416_29908992.pth... [2023-03-08 04:13:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000057752_29569024.pth [2023-03-08 04:13:12,228][321237] Updated weights for policy 0, policy_version 58480 (0.0004) [2023-03-08 04:13:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11496.6). Total num frames: 29970432. Throughput: 0: 11623.1. Samples: 29967700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:13:14,595][320945] Avg episode reward: [(0, '4861.029')] [2023-03-08 04:13:15,435][321237] Updated weights for policy 0, policy_version 58560 (0.0004) [2023-03-08 04:13:18,777][321237] Updated weights for policy 0, policy_version 58640 (0.0004) [2023-03-08 04:13:19,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11496.6). Total num frames: 30031872. Throughput: 0: 11628.7. Samples: 30004980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:13:19,595][320945] Avg episode reward: [(0, '4862.570')] [2023-03-08 04:13:21,963][321237] Updated weights for policy 0, policy_version 58720 (0.0004) [2023-03-08 04:13:24,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11510.5). Total num frames: 30093312. Throughput: 0: 11687.4. Samples: 30080560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:13:24,595][320945] Avg episode reward: [(0, '4860.929')] [2023-03-08 04:13:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000058776_30093312.pth... [2023-03-08 04:13:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000058080_29736960.pth [2023-03-08 04:13:25,390][321237] Updated weights for policy 0, policy_version 58800 (0.0005) [2023-03-08 04:13:28,846][321237] Updated weights for policy 0, policy_version 58880 (0.0004) [2023-03-08 04:13:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11524.3). Total num frames: 30154752. Throughput: 0: 11751.0. Samples: 30151140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:13:29,595][320945] Avg episode reward: [(0, '4826.637')] [2023-03-08 04:13:32,319][321237] Updated weights for policy 0, policy_version 58960 (0.0005) [2023-03-08 04:13:34,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11524.3). Total num frames: 30212096. Throughput: 0: 11805.9. Samples: 30187520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:13:34,595][320945] Avg episode reward: [(0, '4863.294')] [2023-03-08 04:13:35,875][321237] Updated weights for policy 0, policy_version 59040 (0.0005) [2023-03-08 04:13:39,446][321237] Updated weights for policy 0, policy_version 59120 (0.0005) [2023-03-08 04:13:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11524.3). Total num frames: 30269440. Throughput: 0: 11817.2. Samples: 30256084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:13:39,595][320945] Avg episode reward: [(0, '4818.161')] [2023-03-08 04:13:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000059120_30269440.pth... [2023-03-08 04:13:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000058416_29908992.pth [2023-03-08 04:13:43,059][321237] Updated weights for policy 0, policy_version 59200 (0.0005) [2023-03-08 04:13:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11524.3). Total num frames: 30326784. Throughput: 0: 11851.7. Samples: 30323608. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:13:44,595][320945] Avg episode reward: [(0, '4818.604')] [2023-03-08 04:13:46,752][321237] Updated weights for policy 0, policy_version 59280 (0.0005) [2023-03-08 04:13:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11673.6, 300 sec: 11496.6). Total num frames: 30380032. Throughput: 0: 11798.2. Samples: 30356820. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:13:49,594][320945] Avg episode reward: [(0, '4861.534')] [2023-03-08 04:13:50,373][321237] Updated weights for policy 0, policy_version 59360 (0.0005) [2023-03-08 04:13:54,054][321237] Updated weights for policy 0, policy_version 59440 (0.0005) [2023-03-08 04:13:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11496.6). Total num frames: 30437376. Throughput: 0: 11785.0. Samples: 30425088. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:13:54,595][320945] Avg episode reward: [(0, '4861.229')] [2023-03-08 04:13:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000059448_30437376.pth... [2023-03-08 04:13:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000058776_30093312.pth [2023-03-08 04:13:57,772][321237] Updated weights for policy 0, policy_version 59520 (0.0005) [2023-03-08 04:13:59,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11496.6). Total num frames: 30494720. Throughput: 0: 11628.4. Samples: 30490980. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:13:59,595][320945] Avg episode reward: [(0, '4818.316')] [2023-03-08 04:14:01,415][321237] Updated weights for policy 0, policy_version 59600 (0.0005) [2023-03-08 04:14:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11496.6). Total num frames: 30552064. Throughput: 0: 11546.4. Samples: 30524568. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:14:04,595][320945] Avg episode reward: [(0, '4861.665')] [2023-03-08 04:14:04,849][321237] Updated weights for policy 0, policy_version 59680 (0.0005) [2023-03-08 04:14:08,121][321237] Updated weights for policy 0, policy_version 59760 (0.0004) [2023-03-08 04:14:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11510.5). Total num frames: 30613504. Throughput: 0: 11519.2. Samples: 30598924. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:14:09,595][320945] Avg episode reward: [(0, '4860.931')] [2023-03-08 04:14:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000059792_30613504.pth... [2023-03-08 04:14:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000059120_30269440.pth [2023-03-08 04:14:11,420][321237] Updated weights for policy 0, policy_version 59840 (0.0004) [2023-03-08 04:14:14,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11524.3). Total num frames: 30674944. Throughput: 0: 11588.6. Samples: 30672628. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:14:14,595][320945] Avg episode reward: [(0, '4862.241')] [2023-03-08 04:14:14,768][321237] Updated weights for policy 0, policy_version 59920 (0.0003) [2023-03-08 04:14:18,242][321237] Updated weights for policy 0, policy_version 60000 (0.0005) [2023-03-08 04:14:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11510.5). Total num frames: 30732288. Throughput: 0: 11566.3. Samples: 30708004. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:14:19,594][320945] Avg episode reward: [(0, '4862.477')] [2023-03-08 04:14:21,859][321237] Updated weights for policy 0, policy_version 60080 (0.0005) [2023-03-08 04:14:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11510.5). Total num frames: 30789632. Throughput: 0: 11583.8. Samples: 30777356. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:14:24,595][320945] Avg episode reward: [(0, '4820.176')] [2023-03-08 04:14:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000060136_30789632.pth... [2023-03-08 04:14:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000059448_30437376.pth [2023-03-08 04:14:25,369][321237] Updated weights for policy 0, policy_version 60160 (0.0005) [2023-03-08 04:14:28,800][321237] Updated weights for policy 0, policy_version 60240 (0.0005) [2023-03-08 04:14:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11524.3). Total num frames: 30851072. Throughput: 0: 11653.3. Samples: 30848008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:14:29,595][320945] Avg episode reward: [(0, '4862.185')] [2023-03-08 04:14:32,391][321237] Updated weights for policy 0, policy_version 60320 (0.0005) [2023-03-08 04:14:34,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11510.5). Total num frames: 30908416. Throughput: 0: 11696.2. Samples: 30883152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:14:34,595][320945] Avg episode reward: [(0, '4863.309')] [2023-03-08 04:14:35,991][321237] Updated weights for policy 0, policy_version 60400 (0.0004) [2023-03-08 04:14:39,470][321237] Updated weights for policy 0, policy_version 60480 (0.0005) [2023-03-08 04:14:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11510.5). Total num frames: 30965760. Throughput: 0: 11725.0. Samples: 30952712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:14:39,595][320945] Avg episode reward: [(0, '4863.449')] [2023-03-08 04:14:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000060480_30965760.pth... [2023-03-08 04:14:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000059792_30613504.pth [2023-03-08 04:14:43,068][321237] Updated weights for policy 0, policy_version 60560 (0.0005) [2023-03-08 04:14:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11510.5). Total num frames: 31023104. Throughput: 0: 11765.8. Samples: 31020440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:14:44,595][320945] Avg episode reward: [(0, '4863.075')] [2023-03-08 04:14:46,627][321237] Updated weights for policy 0, policy_version 60640 (0.0005) [2023-03-08 04:14:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11510.5). Total num frames: 31080448. Throughput: 0: 11805.0. Samples: 31055792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:14:49,595][320945] Avg episode reward: [(0, '4862.519')] [2023-03-08 04:14:50,211][321237] Updated weights for policy 0, policy_version 60720 (0.0005) [2023-03-08 04:14:53,787][321237] Updated weights for policy 0, policy_version 60800 (0.0005) [2023-03-08 04:14:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11510.5). Total num frames: 31137792. Throughput: 0: 11661.9. Samples: 31123712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:14:54,595][320945] Avg episode reward: [(0, '4862.132')] [2023-03-08 04:14:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000060816_31137792.pth... [2023-03-08 04:14:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000060136_30789632.pth [2023-03-08 04:14:57,491][321237] Updated weights for policy 0, policy_version 60880 (0.0005) [2023-03-08 04:14:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11482.7). Total num frames: 31191040. Throughput: 0: 11516.9. Samples: 31190888. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:14:59,595][320945] Avg episode reward: [(0, '4863.007')] [2023-03-08 04:15:01,192][321237] Updated weights for policy 0, policy_version 60960 (0.0005) [2023-03-08 04:15:04,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11605.3, 300 sec: 11482.7). Total num frames: 31248384. Throughput: 0: 11462.6. Samples: 31223820. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:15:04,595][320945] Avg episode reward: [(0, '4862.955')] [2023-03-08 04:15:04,785][321237] Updated weights for policy 0, policy_version 61040 (0.0005) [2023-03-08 04:15:08,387][321237] Updated weights for policy 0, policy_version 61120 (0.0005) [2023-03-08 04:15:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11468.8). Total num frames: 31305728. Throughput: 0: 11440.8. Samples: 31292192. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:15:09,595][320945] Avg episode reward: [(0, '4862.053')] [2023-03-08 04:15:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000061144_31305728.pth... [2023-03-08 04:15:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000060480_30965760.pth [2023-03-08 04:15:12,092][321237] Updated weights for policy 0, policy_version 61200 (0.0005) [2023-03-08 04:15:14,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11400.5, 300 sec: 11454.9). Total num frames: 31358976. Throughput: 0: 11356.5. Samples: 31359048. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:15:14,594][320945] Avg episode reward: [(0, '4862.893')] [2023-03-08 04:15:15,627][321237] Updated weights for policy 0, policy_version 61280 (0.0005) [2023-03-08 04:15:19,166][321237] Updated weights for policy 0, policy_version 61360 (0.0005) [2023-03-08 04:15:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11468.8). Total num frames: 31420416. Throughput: 0: 11374.8. Samples: 31395016. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:15:19,595][320945] Avg episode reward: [(0, '4864.926')] [2023-03-08 04:15:22,771][321237] Updated weights for policy 0, policy_version 61440 (0.0005) [2023-03-08 04:15:24,594][320945] Fps is (10 sec: 11468.6, 60 sec: 11400.5, 300 sec: 11454.9). Total num frames: 31473664. Throughput: 0: 11334.5. Samples: 31462764. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:15:24,595][320945] Avg episode reward: [(0, '4862.155')] [2023-03-08 04:15:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000061480_31477760.pth... [2023-03-08 04:15:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000060816_31137792.pth [2023-03-08 04:15:26,424][321237] Updated weights for policy 0, policy_version 61520 (0.0005) [2023-03-08 04:15:29,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11468.8). Total num frames: 31535104. Throughput: 0: 11348.7. Samples: 31531132. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:15:29,595][320945] Avg episode reward: [(0, '4820.469')] [2023-03-08 04:15:29,973][321237] Updated weights for policy 0, policy_version 61600 (0.0005) [2023-03-08 04:15:33,590][321237] Updated weights for policy 0, policy_version 61680 (0.0005) [2023-03-08 04:15:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11454.9). Total num frames: 31588352. Throughput: 0: 11328.9. Samples: 31565592. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:15:34,595][320945] Avg episode reward: [(0, '4863.764')] [2023-03-08 04:15:37,266][321237] Updated weights for policy 0, policy_version 61760 (0.0005) [2023-03-08 04:15:39,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11332.3, 300 sec: 11454.9). Total num frames: 31645696. Throughput: 0: 11319.0. Samples: 31633068. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:15:39,595][320945] Avg episode reward: [(0, '4862.133')] [2023-03-08 04:15:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000061808_31645696.pth... [2023-03-08 04:15:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000061144_31305728.pth [2023-03-08 04:15:40,865][321237] Updated weights for policy 0, policy_version 61840 (0.0005) [2023-03-08 04:15:44,431][321237] Updated weights for policy 0, policy_version 61920 (0.0005) [2023-03-08 04:15:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11454.9). Total num frames: 31703040. Throughput: 0: 11335.1. Samples: 31700968. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:15:44,595][320945] Avg episode reward: [(0, '4861.638')] [2023-03-08 04:15:47,900][321237] Updated weights for policy 0, policy_version 62000 (0.0005) [2023-03-08 04:15:49,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11468.8). Total num frames: 31764480. Throughput: 0: 11378.9. Samples: 31735872. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:15:49,595][320945] Avg episode reward: [(0, '4860.722')] [2023-03-08 04:15:51,130][321237] Updated weights for policy 0, policy_version 62080 (0.0004) [2023-03-08 04:15:54,547][321237] Updated weights for policy 0, policy_version 62160 (0.0004) [2023-03-08 04:15:54,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11468.8, 300 sec: 11482.7). Total num frames: 31825920. Throughput: 0: 11538.5. Samples: 31811424. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:15:54,595][320945] Avg episode reward: [(0, '4864.234')] [2023-03-08 04:15:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000062160_31825920.pth... [2023-03-08 04:15:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000061480_31477760.pth [2023-03-08 04:15:57,951][321237] Updated weights for policy 0, policy_version 62240 (0.0005) [2023-03-08 04:15:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11496.6). Total num frames: 31883264. Throughput: 0: 11649.5. Samples: 31883276. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:15:59,595][320945] Avg episode reward: [(0, '4861.848')] [2023-03-08 04:16:01,363][321237] Updated weights for policy 0, policy_version 62320 (0.0004) [2023-03-08 04:16:04,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11510.5). Total num frames: 31944704. Throughput: 0: 11644.2. Samples: 31919004. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:16:04,595][320945] Avg episode reward: [(0, '4818.305')] [2023-03-08 04:16:04,797][321237] Updated weights for policy 0, policy_version 62400 (0.0005) [2023-03-08 04:16:08,175][321237] Updated weights for policy 0, policy_version 62480 (0.0004) [2023-03-08 04:16:09,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11524.3). Total num frames: 32006144. Throughput: 0: 11729.8. Samples: 31990604. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:16:09,595][320945] Avg episode reward: [(0, '4820.063')] [2023-03-08 04:16:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000062512_32006144.pth... [2023-03-08 04:16:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000061808_31645696.pth [2023-03-08 04:16:11,561][321237] Updated weights for policy 0, policy_version 62560 (0.0004) [2023-03-08 04:16:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.8, 300 sec: 11524.3). Total num frames: 32063488. Throughput: 0: 11813.8. Samples: 32062752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:16:14,595][320945] Avg episode reward: [(0, '4864.378')] [2023-03-08 04:16:15,096][321237] Updated weights for policy 0, policy_version 62640 (0.0004) [2023-03-08 04:16:18,657][321237] Updated weights for policy 0, policy_version 62720 (0.0005) [2023-03-08 04:16:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11538.2). Total num frames: 32120832. Throughput: 0: 11794.1. Samples: 32096328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:16:19,595][320945] Avg episode reward: [(0, '4772.332')] [2023-03-08 04:16:22,171][321237] Updated weights for policy 0, policy_version 62800 (0.0005) [2023-03-08 04:16:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11538.2). Total num frames: 32178176. Throughput: 0: 11841.9. Samples: 32165952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:16:24,605][320945] Avg episode reward: [(0, '4771.811')] [2023-03-08 04:16:24,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000062848_32178176.pth... [2023-03-08 04:16:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000062160_31825920.pth [2023-03-08 04:16:25,770][321237] Updated weights for policy 0, policy_version 62880 (0.0005) [2023-03-08 04:16:29,395][321237] Updated weights for policy 0, policy_version 62960 (0.0005) [2023-03-08 04:16:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11552.1). Total num frames: 32235520. Throughput: 0: 11855.8. Samples: 32234480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:16:29,605][320945] Avg episode reward: [(0, '4818.062')] [2023-03-08 04:16:32,661][321237] Updated weights for policy 0, policy_version 63040 (0.0004) [2023-03-08 04:16:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11566.0). Total num frames: 32296960. Throughput: 0: 11902.9. Samples: 32271500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:16:34,595][320945] Avg episode reward: [(0, '4815.883')] [2023-03-08 04:16:36,107][321237] Updated weights for policy 0, policy_version 63120 (0.0004) [2023-03-08 04:16:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11566.0). Total num frames: 32354304. Throughput: 0: 11791.1. Samples: 32342024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:16:39,605][320945] Avg episode reward: [(0, '4820.515')] [2023-03-08 04:16:39,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000063192_32354304.pth... [2023-03-08 04:16:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000062512_32006144.pth [2023-03-08 04:16:39,756][321237] Updated weights for policy 0, policy_version 63200 (0.0005) [2023-03-08 04:16:43,256][321237] Updated weights for policy 0, policy_version 63280 (0.0005) [2023-03-08 04:16:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11579.9). Total num frames: 32411648. Throughput: 0: 11741.6. Samples: 32411648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:16:44,605][320945] Avg episode reward: [(0, '4861.032')] [2023-03-08 04:16:46,810][321237] Updated weights for policy 0, policy_version 63360 (0.0005) [2023-03-08 04:16:49,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11810.2, 300 sec: 11593.8). Total num frames: 32473088. Throughput: 0: 11715.9. Samples: 32446220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:16:49,605][320945] Avg episode reward: [(0, '4862.363')] [2023-03-08 04:16:50,012][321237] Updated weights for policy 0, policy_version 63440 (0.0004) [2023-03-08 04:16:53,272][321237] Updated weights for policy 0, policy_version 63520 (0.0004) [2023-03-08 04:16:54,594][320945] Fps is (10 sec: 12697.6, 60 sec: 11878.4, 300 sec: 11621.5). Total num frames: 32538624. Throughput: 0: 11814.3. Samples: 32522248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:16:54,605][320945] Avg episode reward: [(0, '4862.923')] [2023-03-08 04:16:54,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000063552_32538624.pth... [2023-03-08 04:16:54,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000062848_32178176.pth [2023-03-08 04:16:56,678][321237] Updated weights for policy 0, policy_version 63600 (0.0003) [2023-03-08 04:16:59,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11878.4, 300 sec: 11621.5). Total num frames: 32595968. Throughput: 0: 11808.2. Samples: 32594120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:16:59,595][320945] Avg episode reward: [(0, '4862.790')] [2023-03-08 04:17:00,194][321237] Updated weights for policy 0, policy_version 63680 (0.0004) [2023-03-08 04:17:03,887][321237] Updated weights for policy 0, policy_version 63760 (0.0005) [2023-03-08 04:17:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11635.4). Total num frames: 32653312. Throughput: 0: 11808.9. Samples: 32627728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:17:04,595][320945] Avg episode reward: [(0, '4861.525')] [2023-03-08 04:17:07,249][321237] Updated weights for policy 0, policy_version 63840 (0.0004) [2023-03-08 04:17:09,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11649.3). Total num frames: 32714752. Throughput: 0: 11832.9. Samples: 32698432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:17:09,595][320945] Avg episode reward: [(0, '4863.434')] [2023-03-08 04:17:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000063896_32714752.pth... [2023-03-08 04:17:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000063192_32354304.pth [2023-03-08 04:17:10,604][321237] Updated weights for policy 0, policy_version 63920 (0.0004) [2023-03-08 04:17:14,266][321237] Updated weights for policy 0, policy_version 64000 (0.0005) [2023-03-08 04:17:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11635.4). Total num frames: 32768000. Throughput: 0: 11856.4. Samples: 32768016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:17:14,594][320945] Avg episode reward: [(0, '4861.677')] [2023-03-08 04:17:17,883][321237] Updated weights for policy 0, policy_version 64080 (0.0005) [2023-03-08 04:17:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11663.2). Total num frames: 32829440. Throughput: 0: 11771.3. Samples: 32801208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:17:19,595][320945] Avg episode reward: [(0, '4864.008')] [2023-03-08 04:17:21,147][321237] Updated weights for policy 0, policy_version 64160 (0.0004) [2023-03-08 04:17:24,498][321237] Updated weights for policy 0, policy_version 64240 (0.0004) [2023-03-08 04:17:24,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11878.4, 300 sec: 11677.1). Total num frames: 32890880. Throughput: 0: 11844.5. Samples: 32875024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:17:24,595][320945] Avg episode reward: [(0, '4864.813')] [2023-03-08 04:17:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000064240_32890880.pth... [2023-03-08 04:17:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000063552_32538624.pth [2023-03-08 04:17:28,138][321237] Updated weights for policy 0, policy_version 64320 (0.0005) [2023-03-08 04:17:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11649.3). Total num frames: 32944128. Throughput: 0: 11834.3. Samples: 32944192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:17:29,594][320945] Avg episode reward: [(0, '4862.935')] [2023-03-08 04:17:31,695][321237] Updated weights for policy 0, policy_version 64400 (0.0004) [2023-03-08 04:17:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11649.3). Total num frames: 33005568. Throughput: 0: 11856.3. Samples: 32979752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:17:34,595][320945] Avg episode reward: [(0, '4860.636')] [2023-03-08 04:17:35,175][321237] Updated weights for policy 0, policy_version 64480 (0.0004) [2023-03-08 04:17:38,955][321237] Updated weights for policy 0, policy_version 64560 (0.0005) [2023-03-08 04:17:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11649.3). Total num frames: 33058816. Throughput: 0: 11659.2. Samples: 33046912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:17:39,595][320945] Avg episode reward: [(0, '4823.443')] [2023-03-08 04:17:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000064568_33058816.pth... [2023-03-08 04:17:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000063896_32714752.pth [2023-03-08 04:17:42,607][321237] Updated weights for policy 0, policy_version 64640 (0.0005) [2023-03-08 04:17:44,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11810.2, 300 sec: 11663.2). Total num frames: 33120256. Throughput: 0: 11602.3. Samples: 33116224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:17:44,594][320945] Avg episode reward: [(0, '4817.775')] [2023-03-08 04:17:45,911][321237] Updated weights for policy 0, policy_version 64720 (0.0004) [2023-03-08 04:17:49,130][321237] Updated weights for policy 0, policy_version 64800 (0.0004) [2023-03-08 04:17:49,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11677.1). Total num frames: 33181696. Throughput: 0: 11681.3. Samples: 33153388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:17:49,595][320945] Avg episode reward: [(0, '4863.319')] [2023-03-08 04:17:52,477][321237] Updated weights for policy 0, policy_version 64880 (0.0005) [2023-03-08 04:17:54,594][320945] Fps is (10 sec: 12287.8, 60 sec: 11741.9, 300 sec: 11691.0). Total num frames: 33243136. Throughput: 0: 11758.8. Samples: 33227576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:17:54,595][320945] Avg episode reward: [(0, '4863.355')] [2023-03-08 04:17:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000064928_33243136.pth... [2023-03-08 04:17:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000064240_32890880.pth [2023-03-08 04:17:56,021][321237] Updated weights for policy 0, policy_version 64960 (0.0005) [2023-03-08 04:17:59,306][321237] Updated weights for policy 0, policy_version 65040 (0.0005) [2023-03-08 04:17:59,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11691.0). Total num frames: 33300480. Throughput: 0: 11830.9. Samples: 33300404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:17:59,594][320945] Avg episode reward: [(0, '4858.936')] [2023-03-08 04:18:02,534][321237] Updated weights for policy 0, policy_version 65120 (0.0004) [2023-03-08 04:18:04,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11718.7). Total num frames: 33366016. Throughput: 0: 11927.0. Samples: 33337924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:18:04,595][320945] Avg episode reward: [(0, '4862.781')] [2023-03-08 04:18:05,802][321237] Updated weights for policy 0, policy_version 65200 (0.0004) [2023-03-08 04:18:09,034][321237] Updated weights for policy 0, policy_version 65280 (0.0004) [2023-03-08 04:18:09,594][320945] Fps is (10 sec: 12697.4, 60 sec: 11878.4, 300 sec: 11718.7). Total num frames: 33427456. Throughput: 0: 11972.1. Samples: 33413768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:18:09,595][320945] Avg episode reward: [(0, '4864.685')] [2023-03-08 04:18:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000065288_33427456.pth... [2023-03-08 04:18:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000064568_33058816.pth [2023-03-08 04:18:12,283][321237] Updated weights for policy 0, policy_version 65360 (0.0004) [2023-03-08 04:18:14,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12083.2, 300 sec: 11732.6). Total num frames: 33492992. Throughput: 0: 12106.0. Samples: 33488960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:18:14,595][320945] Avg episode reward: [(0, '4864.329')] [2023-03-08 04:18:15,567][321237] Updated weights for policy 0, policy_version 65440 (0.0004) [2023-03-08 04:18:18,827][321237] Updated weights for policy 0, policy_version 65520 (0.0004) [2023-03-08 04:18:19,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12083.2, 300 sec: 11732.6). Total num frames: 33554432. Throughput: 0: 12147.5. Samples: 33526388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:18:19,595][320945] Avg episode reward: [(0, '4863.186')] [2023-03-08 04:18:22,103][321237] Updated weights for policy 0, policy_version 65600 (0.0004) [2023-03-08 04:18:24,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 11732.6). Total num frames: 33615872. Throughput: 0: 12321.2. Samples: 33601364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:18:24,595][320945] Avg episode reward: [(0, '4818.467')] [2023-03-08 04:18:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000065656_33615872.pth... [2023-03-08 04:18:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000064928_33243136.pth [2023-03-08 04:18:25,424][321237] Updated weights for policy 0, policy_version 65680 (0.0004) [2023-03-08 04:18:28,702][321237] Updated weights for policy 0, policy_version 65760 (0.0004) [2023-03-08 04:18:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 11746.5). Total num frames: 33677312. Throughput: 0: 12448.4. Samples: 33676404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:18:29,595][320945] Avg episode reward: [(0, '4863.962')] [2023-03-08 04:18:31,986][321237] Updated weights for policy 0, policy_version 65840 (0.0004) [2023-03-08 04:18:34,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 11760.4). Total num frames: 33738752. Throughput: 0: 12456.1. Samples: 33713912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:18:34,595][320945] Avg episode reward: [(0, '4863.723')] [2023-03-08 04:18:35,348][321237] Updated weights for policy 0, policy_version 65920 (0.0004) [2023-03-08 04:18:38,895][321237] Updated weights for policy 0, policy_version 66000 (0.0005) [2023-03-08 04:18:39,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 11774.3). Total num frames: 33800192. Throughput: 0: 12368.5. Samples: 33784156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:18:39,595][320945] Avg episode reward: [(0, '4864.003')] [2023-03-08 04:18:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000066016_33800192.pth... [2023-03-08 04:18:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000065288_33427456.pth [2023-03-08 04:18:42,336][321237] Updated weights for policy 0, policy_version 66080 (0.0004) [2023-03-08 04:18:44,594][320945] Fps is (10 sec: 11878.5, 60 sec: 12288.0, 300 sec: 11788.1). Total num frames: 33857536. Throughput: 0: 12361.3. Samples: 33856664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:18:44,595][320945] Avg episode reward: [(0, '4863.405')] [2023-03-08 04:18:45,671][321237] Updated weights for policy 0, policy_version 66160 (0.0004) [2023-03-08 04:18:48,821][321237] Updated weights for policy 0, policy_version 66240 (0.0003) [2023-03-08 04:18:49,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11815.9). Total num frames: 33923072. Throughput: 0: 12367.6. Samples: 33894464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:18:49,595][320945] Avg episode reward: [(0, '4862.413')] [2023-03-08 04:18:52,071][321237] Updated weights for policy 0, policy_version 66320 (0.0004) [2023-03-08 04:18:54,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12356.3, 300 sec: 11829.8). Total num frames: 33984512. Throughput: 0: 12383.1. Samples: 33971008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:18:54,595][320945] Avg episode reward: [(0, '4815.539')] [2023-03-08 04:18:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000066376_33984512.pth... [2023-03-08 04:18:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000065656_33615872.pth [2023-03-08 04:18:55,462][321237] Updated weights for policy 0, policy_version 66400 (0.0004) [2023-03-08 04:18:58,764][321237] Updated weights for policy 0, policy_version 66480 (0.0004) [2023-03-08 04:18:59,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 11843.7). Total num frames: 34045952. Throughput: 0: 12333.0. Samples: 34043944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:18:59,595][320945] Avg episode reward: [(0, '4858.502')] [2023-03-08 04:19:02,046][321237] Updated weights for policy 0, policy_version 66560 (0.0004) [2023-03-08 04:19:04,594][320945] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 11843.7). Total num frames: 34107392. Throughput: 0: 12335.7. Samples: 34081496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:19:04,595][320945] Avg episode reward: [(0, '4816.213')] [2023-03-08 04:19:05,466][321237] Updated weights for policy 0, policy_version 66640 (0.0005) [2023-03-08 04:19:09,123][321237] Updated weights for policy 0, policy_version 66720 (0.0005) [2023-03-08 04:19:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 11829.8). Total num frames: 34164736. Throughput: 0: 12222.7. Samples: 34151388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:19:09,595][320945] Avg episode reward: [(0, '4862.948')] [2023-03-08 04:19:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000066728_34164736.pth... [2023-03-08 04:19:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000066016_33800192.pth [2023-03-08 04:19:12,766][321237] Updated weights for policy 0, policy_version 66800 (0.0005) [2023-03-08 04:19:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12151.5, 300 sec: 11829.8). Total num frames: 34222080. Throughput: 0: 12071.4. Samples: 34219616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:19:14,595][320945] Avg episode reward: [(0, '4864.394')] [2023-03-08 04:19:16,125][321237] Updated weights for policy 0, policy_version 66880 (0.0004) [2023-03-08 04:19:19,435][321237] Updated weights for policy 0, policy_version 66960 (0.0004) [2023-03-08 04:19:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 11843.7). Total num frames: 34283520. Throughput: 0: 12042.8. Samples: 34255836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:19:19,595][320945] Avg episode reward: [(0, '4863.853')] [2023-03-08 04:19:22,756][321237] Updated weights for policy 0, policy_version 67040 (0.0005) [2023-03-08 04:19:24,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 11843.7). Total num frames: 34344960. Throughput: 0: 12142.6. Samples: 34330572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:19:24,595][320945] Avg episode reward: [(0, '4862.098')] [2023-03-08 04:19:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000067080_34344960.pth... [2023-03-08 04:19:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000066376_33984512.pth [2023-03-08 04:19:26,154][321237] Updated weights for policy 0, policy_version 67120 (0.0005) [2023-03-08 04:19:29,442][321237] Updated weights for policy 0, policy_version 67200 (0.0004) [2023-03-08 04:19:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11857.6). Total num frames: 34406400. Throughput: 0: 12155.4. Samples: 34403656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:19:29,605][320945] Avg episode reward: [(0, '4858.435')] [2023-03-08 04:19:32,552][321237] Updated weights for policy 0, policy_version 67280 (0.0003) [2023-03-08 04:19:34,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12219.7, 300 sec: 11885.3). Total num frames: 34471936. Throughput: 0: 12197.0. Samples: 34443328. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:19:34,605][320945] Avg episode reward: [(0, '4817.160')] [2023-03-08 04:19:35,920][321237] Updated weights for policy 0, policy_version 67360 (0.0005) [2023-03-08 04:19:39,466][321237] Updated weights for policy 0, policy_version 67440 (0.0005) [2023-03-08 04:19:39,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 11885.3). Total num frames: 34529280. Throughput: 0: 12104.9. Samples: 34515728. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:19:39,605][320945] Avg episode reward: [(0, '4863.789')] [2023-03-08 04:19:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000067440_34529280.pth... [2023-03-08 04:19:39,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000066728_34164736.pth [2023-03-08 04:19:43,184][321237] Updated weights for policy 0, policy_version 67520 (0.0005) [2023-03-08 04:19:44,594][320945] Fps is (10 sec: 11059.3, 60 sec: 12083.2, 300 sec: 11871.5). Total num frames: 34582528. Throughput: 0: 11970.0. Samples: 34582592. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:19:44,605][320945] Avg episode reward: [(0, '4820.343')] [2023-03-08 04:19:46,836][321237] Updated weights for policy 0, policy_version 67600 (0.0005) [2023-03-08 04:19:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11946.7, 300 sec: 11871.5). Total num frames: 34639872. Throughput: 0: 11869.0. Samples: 34615600. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:19:49,595][320945] Avg episode reward: [(0, '4863.693')] [2023-03-08 04:19:50,476][321237] Updated weights for policy 0, policy_version 67680 (0.0005) [2023-03-08 04:19:53,967][321237] Updated weights for policy 0, policy_version 67760 (0.0005) [2023-03-08 04:19:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11878.4, 300 sec: 11885.3). Total num frames: 34697216. Throughput: 0: 11856.9. Samples: 34684948. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:19:54,605][320945] Avg episode reward: [(0, '4859.408')] [2023-03-08 04:19:54,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000067768_34697216.pth... [2023-03-08 04:19:54,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000067080_34344960.pth [2023-03-08 04:19:57,635][321237] Updated weights for policy 0, policy_version 67840 (0.0005) [2023-03-08 04:19:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11871.5). Total num frames: 34750464. Throughput: 0: 11802.6. Samples: 34750732. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:19:59,605][320945] Avg episode reward: [(0, '4864.425')] [2023-03-08 04:20:01,439][321237] Updated weights for policy 0, policy_version 67920 (0.0005) [2023-03-08 04:20:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11871.5). Total num frames: 34807808. Throughput: 0: 11751.9. Samples: 34784672. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:20:04,595][320945] Avg episode reward: [(0, '4862.597')] [2023-03-08 04:20:05,035][321237] Updated weights for policy 0, policy_version 68000 (0.0005) [2023-03-08 04:20:08,365][321237] Updated weights for policy 0, policy_version 68080 (0.0004) [2023-03-08 04:20:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11899.2). Total num frames: 34869248. Throughput: 0: 11671.6. Samples: 34855792. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:20:09,605][320945] Avg episode reward: [(0, '4862.053')] [2023-03-08 04:20:09,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000068104_34869248.pth... [2023-03-08 04:20:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000067440_34529280.pth [2023-03-08 04:20:11,612][321237] Updated weights for policy 0, policy_version 68160 (0.0004) [2023-03-08 04:20:14,594][320945] Fps is (10 sec: 12697.6, 60 sec: 11878.4, 300 sec: 11913.1). Total num frames: 34934784. Throughput: 0: 11713.2. Samples: 34930752. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:20:14,605][320945] Avg episode reward: [(0, '4862.967')] [2023-03-08 04:20:14,903][321237] Updated weights for policy 0, policy_version 68240 (0.0005) [2023-03-08 04:20:18,261][321237] Updated weights for policy 0, policy_version 68320 (0.0004) [2023-03-08 04:20:19,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11810.1, 300 sec: 11927.0). Total num frames: 34992128. Throughput: 0: 11650.9. Samples: 34967616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:20:19,605][320945] Avg episode reward: [(0, '4859.746')] [2023-03-08 04:20:21,811][321237] Updated weights for policy 0, policy_version 68400 (0.0004) [2023-03-08 04:20:24,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 11913.1). Total num frames: 35049472. Throughput: 0: 11591.7. Samples: 35037352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:20:24,605][320945] Avg episode reward: [(0, '4860.307')] [2023-03-08 04:20:24,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000068456_35049472.pth... [2023-03-08 04:20:24,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000067768_34697216.pth [2023-03-08 04:20:25,431][321237] Updated weights for policy 0, policy_version 68480 (0.0003) [2023-03-08 04:20:29,116][321237] Updated weights for policy 0, policy_version 68560 (0.0003) [2023-03-08 04:20:29,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11927.0). Total num frames: 35106816. Throughput: 0: 11592.0. Samples: 35104232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:20:29,595][320945] Avg episode reward: [(0, '4862.235')] [2023-03-08 04:20:32,748][321237] Updated weights for policy 0, policy_version 68640 (0.0005) [2023-03-08 04:20:34,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11927.0). Total num frames: 35164160. Throughput: 0: 11623.5. Samples: 35138656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:20:34,595][320945] Avg episode reward: [(0, '4861.195')] [2023-03-08 04:20:36,354][321237] Updated weights for policy 0, policy_version 68720 (0.0005) [2023-03-08 04:20:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11913.1). Total num frames: 35217408. Throughput: 0: 11588.0. Samples: 35206408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:20:39,595][320945] Avg episode reward: [(0, '4860.831')] [2023-03-08 04:20:39,619][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000068792_35221504.pth... [2023-03-08 04:20:39,621][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000068104_34869248.pth [2023-03-08 04:20:39,977][321237] Updated weights for policy 0, policy_version 68800 (0.0005) [2023-03-08 04:20:43,496][321237] Updated weights for policy 0, policy_version 68880 (0.0004) [2023-03-08 04:20:44,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11537.1, 300 sec: 11899.2). Total num frames: 35274752. Throughput: 0: 11646.3. Samples: 35274816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:20:44,594][320945] Avg episode reward: [(0, '4860.911')] [2023-03-08 04:20:47,235][321237] Updated weights for policy 0, policy_version 68960 (0.0005) [2023-03-08 04:20:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11885.3). Total num frames: 35332096. Throughput: 0: 11620.5. Samples: 35307592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:20:49,595][320945] Avg episode reward: [(0, '4862.342')] [2023-03-08 04:20:50,788][321237] Updated weights for policy 0, policy_version 69040 (0.0005) [2023-03-08 04:20:54,415][321237] Updated weights for policy 0, policy_version 69120 (0.0005) [2023-03-08 04:20:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11885.3). Total num frames: 35389440. Throughput: 0: 11567.8. Samples: 35376344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:20:54,595][320945] Avg episode reward: [(0, '4862.631')] [2023-03-08 04:20:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000069120_35389440.pth... [2023-03-08 04:20:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000068456_35049472.pth [2023-03-08 04:20:57,785][321237] Updated weights for policy 0, policy_version 69200 (0.0004) [2023-03-08 04:20:59,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 11885.3). Total num frames: 35450880. Throughput: 0: 11515.7. Samples: 35448960. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:20:59,595][320945] Avg episode reward: [(0, '4864.324')] [2023-03-08 04:21:01,058][321237] Updated weights for policy 0, policy_version 69280 (0.0004) [2023-03-08 04:21:04,540][321237] Updated weights for policy 0, policy_version 69360 (0.0004) [2023-03-08 04:21:04,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11885.3). Total num frames: 35512320. Throughput: 0: 11498.6. Samples: 35485056. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:21:04,595][320945] Avg episode reward: [(0, '4862.076')] [2023-03-08 04:21:08,030][321237] Updated weights for policy 0, policy_version 69440 (0.0005) [2023-03-08 04:21:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11885.3). Total num frames: 35569664. Throughput: 0: 11532.7. Samples: 35556324. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:21:09,595][320945] Avg episode reward: [(0, '4861.546')] [2023-03-08 04:21:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000069472_35569664.pth... [2023-03-08 04:21:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000068792_35221504.pth [2023-03-08 04:21:11,556][321237] Updated weights for policy 0, policy_version 69520 (0.0005) [2023-03-08 04:21:14,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11885.3). Total num frames: 35627008. Throughput: 0: 11565.7. Samples: 35624688. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:21:14,595][320945] Avg episode reward: [(0, '4812.926')] [2023-03-08 04:21:15,165][321237] Updated weights for policy 0, policy_version 69600 (0.0005) [2023-03-08 04:21:18,735][321237] Updated weights for policy 0, policy_version 69680 (0.0005) [2023-03-08 04:21:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11885.3). Total num frames: 35684352. Throughput: 0: 11580.5. Samples: 35659776. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:21:19,595][320945] Avg episode reward: [(0, '4860.640')] [2023-03-08 04:21:22,306][321237] Updated weights for policy 0, policy_version 69760 (0.0005) [2023-03-08 04:21:24,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11537.0, 300 sec: 11885.3). Total num frames: 35741696. Throughput: 0: 11583.7. Samples: 35727676. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:21:24,595][320945] Avg episode reward: [(0, '4862.888')] [2023-03-08 04:21:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000069808_35741696.pth... [2023-03-08 04:21:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000069120_35389440.pth [2023-03-08 04:21:25,919][321237] Updated weights for policy 0, policy_version 69840 (0.0005) [2023-03-08 04:21:29,111][321237] Updated weights for policy 0, policy_version 69920 (0.0004) [2023-03-08 04:21:29,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11885.3). Total num frames: 35803136. Throughput: 0: 11687.6. Samples: 35800760. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:21:29,595][320945] Avg episode reward: [(0, '4860.286')] [2023-03-08 04:21:32,458][321237] Updated weights for policy 0, policy_version 70000 (0.0004) [2023-03-08 04:21:34,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11899.2). Total num frames: 35864576. Throughput: 0: 11779.4. Samples: 35837664. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:21:34,595][320945] Avg episode reward: [(0, '4861.702')] [2023-03-08 04:21:35,850][321237] Updated weights for policy 0, policy_version 70080 (0.0005) [2023-03-08 04:21:39,136][321237] Updated weights for policy 0, policy_version 70160 (0.0004) [2023-03-08 04:21:39,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11913.1). Total num frames: 35926016. Throughput: 0: 11891.5. Samples: 35911460. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:21:39,595][320945] Avg episode reward: [(0, '4857.130')] [2023-03-08 04:21:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000070168_35926016.pth... [2023-03-08 04:21:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000069472_35569664.pth [2023-03-08 04:21:42,496][321237] Updated weights for policy 0, policy_version 70240 (0.0005) [2023-03-08 04:21:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11899.2). Total num frames: 35983360. Throughput: 0: 11877.0. Samples: 35983424. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:21:44,595][320945] Avg episode reward: [(0, '4859.640')] [2023-03-08 04:21:46,030][321237] Updated weights for policy 0, policy_version 70320 (0.0005) [2023-03-08 04:21:49,511][321237] Updated weights for policy 0, policy_version 70400 (0.0005) [2023-03-08 04:21:49,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11885.3). Total num frames: 36044800. Throughput: 0: 11864.3. Samples: 36018948. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:21:49,595][320945] Avg episode reward: [(0, '4859.576')] [2023-03-08 04:21:52,952][321237] Updated weights for policy 0, policy_version 70480 (0.0005) [2023-03-08 04:21:54,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11885.3). Total num frames: 36102144. Throughput: 0: 11856.3. Samples: 36089856. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:21:54,595][320945] Avg episode reward: [(0, '4860.502')] [2023-03-08 04:21:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000070512_36102144.pth... [2023-03-08 04:21:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000069808_35741696.pth [2023-03-08 04:21:56,416][321237] Updated weights for policy 0, policy_version 70560 (0.0005) [2023-03-08 04:21:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11899.2). Total num frames: 36163584. Throughput: 0: 11901.8. Samples: 36160268. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:21:59,595][320945] Avg episode reward: [(0, '4861.954')] [2023-03-08 04:21:59,848][321237] Updated weights for policy 0, policy_version 70640 (0.0005) [2023-03-08 04:22:03,338][321237] Updated weights for policy 0, policy_version 70720 (0.0005) [2023-03-08 04:22:04,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11885.3). Total num frames: 36220928. Throughput: 0: 11925.5. Samples: 36196424. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:22:04,595][320945] Avg episode reward: [(0, '4862.901')] [2023-03-08 04:22:06,872][321237] Updated weights for policy 0, policy_version 70800 (0.0005) [2023-03-08 04:22:09,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11810.1, 300 sec: 11899.2). Total num frames: 36278272. Throughput: 0: 11962.4. Samples: 36265984. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:22:09,595][320945] Avg episode reward: [(0, '4859.877')] [2023-03-08 04:22:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000070856_36278272.pth... [2023-03-08 04:22:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000070168_35926016.pth [2023-03-08 04:22:10,378][321237] Updated weights for policy 0, policy_version 70880 (0.0005) [2023-03-08 04:22:13,931][321237] Updated weights for policy 0, policy_version 70960 (0.0005) [2023-03-08 04:22:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11885.3). Total num frames: 36335616. Throughput: 0: 11885.7. Samples: 36335616. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:22:14,594][320945] Avg episode reward: [(0, '4862.330')] [2023-03-08 04:22:17,498][321237] Updated weights for policy 0, policy_version 71040 (0.0005) [2023-03-08 04:22:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11871.5). Total num frames: 36392960. Throughput: 0: 11829.1. Samples: 36369972. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:22:19,595][320945] Avg episode reward: [(0, '4862.224')] [2023-03-08 04:22:21,184][321237] Updated weights for policy 0, policy_version 71120 (0.0005) [2023-03-08 04:22:24,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11810.1, 300 sec: 11885.3). Total num frames: 36450304. Throughput: 0: 11685.7. Samples: 36437316. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:22:24,595][320945] Avg episode reward: [(0, '4862.686')] [2023-03-08 04:22:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000071192_36450304.pth... [2023-03-08 04:22:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000070512_36102144.pth [2023-03-08 04:22:24,842][321237] Updated weights for policy 0, policy_version 71200 (0.0005) [2023-03-08 04:22:28,362][321237] Updated weights for policy 0, policy_version 71280 (0.0005) [2023-03-08 04:22:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11871.5). Total num frames: 36507648. Throughput: 0: 11624.5. Samples: 36506528. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:22:29,595][320945] Avg episode reward: [(0, '4859.521')] [2023-03-08 04:22:31,850][321237] Updated weights for policy 0, policy_version 71360 (0.0005) [2023-03-08 04:22:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11885.3). Total num frames: 36564992. Throughput: 0: 11591.5. Samples: 36540568. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:22:34,595][320945] Avg episode reward: [(0, '4859.912')] [2023-03-08 04:22:35,456][321237] Updated weights for policy 0, policy_version 71440 (0.0005) [2023-03-08 04:22:39,169][321237] Updated weights for policy 0, policy_version 71520 (0.0005) [2023-03-08 04:22:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11871.5). Total num frames: 36622336. Throughput: 0: 11514.5. Samples: 36608008. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:22:39,595][320945] Avg episode reward: [(0, '4861.960')] [2023-03-08 04:22:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000071528_36622336.pth... [2023-03-08 04:22:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000070856_36278272.pth [2023-03-08 04:22:42,748][321237] Updated weights for policy 0, policy_version 71600 (0.0005) [2023-03-08 04:22:44,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11537.0, 300 sec: 11843.7). Total num frames: 36675584. Throughput: 0: 11451.6. Samples: 36675592. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:22:44,595][320945] Avg episode reward: [(0, '4860.489')] [2023-03-08 04:22:46,455][321237] Updated weights for policy 0, policy_version 71680 (0.0004) [2023-03-08 04:22:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11829.8). Total num frames: 36732928. Throughput: 0: 11393.9. Samples: 36709152. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:22:49,595][320945] Avg episode reward: [(0, '4863.303')] [2023-03-08 04:22:50,051][321237] Updated weights for policy 0, policy_version 71760 (0.0005) [2023-03-08 04:22:53,639][321237] Updated weights for policy 0, policy_version 71840 (0.0004) [2023-03-08 04:22:54,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11829.8). Total num frames: 36790272. Throughput: 0: 11379.2. Samples: 36778048. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:22:54,595][320945] Avg episode reward: [(0, '4862.030')] [2023-03-08 04:22:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000071856_36790272.pth... [2023-03-08 04:22:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000071192_36450304.pth [2023-03-08 04:22:56,949][321237] Updated weights for policy 0, policy_version 71920 (0.0004) [2023-03-08 04:22:59,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11829.8). Total num frames: 36855808. Throughput: 0: 11489.8. Samples: 36852656. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:22:59,595][320945] Avg episode reward: [(0, '4861.719')] [2023-03-08 04:23:00,138][321237] Updated weights for policy 0, policy_version 72000 (0.0004) [2023-03-08 04:23:03,573][321237] Updated weights for policy 0, policy_version 72080 (0.0005) [2023-03-08 04:23:04,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11815.9). Total num frames: 36913152. Throughput: 0: 11563.4. Samples: 36890324. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:23:04,595][320945] Avg episode reward: [(0, '4860.943')] [2023-03-08 04:23:07,113][321237] Updated weights for policy 0, policy_version 72160 (0.0005) [2023-03-08 04:23:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11802.0). Total num frames: 36974592. Throughput: 0: 11590.0. Samples: 36958868. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:23:09,595][320945] Avg episode reward: [(0, '4861.814')] [2023-03-08 04:23:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000072216_36974592.pth... [2023-03-08 04:23:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000071528_36622336.pth [2023-03-08 04:23:10,640][321237] Updated weights for policy 0, policy_version 72240 (0.0005) [2023-03-08 04:23:14,295][321237] Updated weights for policy 0, policy_version 72320 (0.0005) [2023-03-08 04:23:14,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11537.0, 300 sec: 11774.3). Total num frames: 37027840. Throughput: 0: 11585.0. Samples: 37027852. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:23:14,595][320945] Avg episode reward: [(0, '4815.399')] [2023-03-08 04:23:17,923][321237] Updated weights for policy 0, policy_version 72400 (0.0005) [2023-03-08 04:23:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11537.1, 300 sec: 11760.4). Total num frames: 37085184. Throughput: 0: 11566.0. Samples: 37061036. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:23:19,595][320945] Avg episode reward: [(0, '4864.009')] [2023-03-08 04:23:21,404][321237] Updated weights for policy 0, policy_version 72480 (0.0005) [2023-03-08 04:23:24,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11760.4). Total num frames: 37146624. Throughput: 0: 11618.1. Samples: 37130820. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:23:24,595][320945] Avg episode reward: [(0, '4862.918')] [2023-03-08 04:23:24,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000072552_37146624.pth... [2023-03-08 04:23:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000071856_36790272.pth [2023-03-08 04:23:24,923][321237] Updated weights for policy 0, policy_version 72560 (0.0005) [2023-03-08 04:23:28,436][321237] Updated weights for policy 0, policy_version 72640 (0.0005) [2023-03-08 04:23:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11746.5). Total num frames: 37203968. Throughput: 0: 11704.5. Samples: 37202292. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:23:29,595][320945] Avg episode reward: [(0, '4862.229')] [2023-03-08 04:23:31,650][321237] Updated weights for policy 0, policy_version 72720 (0.0004) [2023-03-08 04:23:34,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11746.5). Total num frames: 37265408. Throughput: 0: 11800.2. Samples: 37240160. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:23:34,595][320945] Avg episode reward: [(0, '4863.063')] [2023-03-08 04:23:34,989][321237] Updated weights for policy 0, policy_version 72800 (0.0004) [2023-03-08 04:23:38,337][321237] Updated weights for policy 0, policy_version 72880 (0.0004) [2023-03-08 04:23:39,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11741.9, 300 sec: 11760.4). Total num frames: 37326848. Throughput: 0: 11915.6. Samples: 37314252. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:23:39,595][320945] Avg episode reward: [(0, '4861.056')] [2023-03-08 04:23:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000072904_37326848.pth... [2023-03-08 04:23:39,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000072216_36974592.pth [2023-03-08 04:23:41,584][321237] Updated weights for policy 0, policy_version 72960 (0.0004) [2023-03-08 04:23:44,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11746.5). Total num frames: 37388288. Throughput: 0: 11895.6. Samples: 37387960. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:23:44,595][320945] Avg episode reward: [(0, '4862.806')] [2023-03-08 04:23:45,014][321237] Updated weights for policy 0, policy_version 73040 (0.0005) [2023-03-08 04:23:48,328][321237] Updated weights for policy 0, policy_version 73120 (0.0005) [2023-03-08 04:23:49,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12014.9, 300 sec: 11760.4). Total num frames: 37453824. Throughput: 0: 11875.3. Samples: 37424712. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:23:49,595][320945] Avg episode reward: [(0, '4860.802')] [2023-03-08 04:23:51,458][321237] Updated weights for policy 0, policy_version 73200 (0.0004) [2023-03-08 04:23:54,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12083.2, 300 sec: 11760.4). Total num frames: 37515264. Throughput: 0: 12023.6. Samples: 37499928. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:23:54,595][320945] Avg episode reward: [(0, '4861.792')] [2023-03-08 04:23:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000073272_37515264.pth... [2023-03-08 04:23:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000072552_37146624.pth [2023-03-08 04:23:54,761][321237] Updated weights for policy 0, policy_version 73280 (0.0004) [2023-03-08 04:23:57,898][321237] Updated weights for policy 0, policy_version 73360 (0.0004) [2023-03-08 04:23:59,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11760.4). Total num frames: 37576704. Throughput: 0: 12198.1. Samples: 37576768. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:23:59,595][320945] Avg episode reward: [(0, '4859.738')] [2023-03-08 04:24:01,247][321237] Updated weights for policy 0, policy_version 73440 (0.0005) [2023-03-08 04:24:04,410][321237] Updated weights for policy 0, policy_version 73520 (0.0004) [2023-03-08 04:24:04,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12151.5, 300 sec: 11788.1). Total num frames: 37642240. Throughput: 0: 12296.6. Samples: 37614384. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:24:04,595][320945] Avg episode reward: [(0, '4860.302')] [2023-03-08 04:24:07,684][321237] Updated weights for policy 0, policy_version 73600 (0.0004) [2023-03-08 04:24:09,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 11802.0). Total num frames: 37703680. Throughput: 0: 12440.2. Samples: 37690628. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:24:09,595][320945] Avg episode reward: [(0, '4861.293')] [2023-03-08 04:24:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000073640_37703680.pth... [2023-03-08 04:24:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000072904_37326848.pth [2023-03-08 04:24:11,001][321237] Updated weights for policy 0, policy_version 73680 (0.0004) [2023-03-08 04:24:14,131][321237] Updated weights for policy 0, policy_version 73760 (0.0003) [2023-03-08 04:24:14,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 11815.9). Total num frames: 37769216. Throughput: 0: 12542.6. Samples: 37766708. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:24:14,595][320945] Avg episode reward: [(0, '4861.056')] [2023-03-08 04:24:17,430][321237] Updated weights for policy 0, policy_version 73840 (0.0004) [2023-03-08 04:24:19,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12424.5, 300 sec: 11815.9). Total num frames: 37830656. Throughput: 0: 12530.5. Samples: 37804032. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:24:19,595][320945] Avg episode reward: [(0, '4861.429')] [2023-03-08 04:24:20,959][321237] Updated weights for policy 0, policy_version 73920 (0.0005) [2023-03-08 04:24:24,232][321237] Updated weights for policy 0, policy_version 74000 (0.0005) [2023-03-08 04:24:24,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 11815.9). Total num frames: 37892096. Throughput: 0: 12477.2. Samples: 37875724. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:24:24,595][320945] Avg episode reward: [(0, '4861.823')] [2023-03-08 04:24:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000074008_37892096.pth... [2023-03-08 04:24:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000073272_37515264.pth [2023-03-08 04:24:27,440][321237] Updated weights for policy 0, policy_version 74080 (0.0004) [2023-03-08 04:24:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 11802.0). Total num frames: 37953536. Throughput: 0: 12554.7. Samples: 37952920. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:24:29,595][320945] Avg episode reward: [(0, '4861.545')] [2023-03-08 04:24:30,635][321237] Updated weights for policy 0, policy_version 74160 (0.0004) [2023-03-08 04:24:33,892][321237] Updated weights for policy 0, policy_version 74240 (0.0004) [2023-03-08 04:24:34,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12561.1, 300 sec: 11829.8). Total num frames: 38019072. Throughput: 0: 12586.2. Samples: 37991092. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:24:34,595][320945] Avg episode reward: [(0, '4860.477')] [2023-03-08 04:24:37,087][321237] Updated weights for policy 0, policy_version 74320 (0.0003) [2023-03-08 04:24:39,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 11857.6). Total num frames: 38080512. Throughput: 0: 12578.0. Samples: 38065936. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:24:39,595][320945] Avg episode reward: [(0, '4860.689')] [2023-03-08 04:24:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000074376_38080512.pth... [2023-03-08 04:24:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000073640_37703680.pth [2023-03-08 04:24:40,437][321237] Updated weights for policy 0, policy_version 74400 (0.0004) [2023-03-08 04:24:43,668][321237] Updated weights for policy 0, policy_version 74480 (0.0004) [2023-03-08 04:24:44,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 11871.5). Total num frames: 38141952. Throughput: 0: 12559.7. Samples: 38141952. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:24:44,595][320945] Avg episode reward: [(0, '4860.833')] [2023-03-08 04:24:46,803][321237] Updated weights for policy 0, policy_version 74560 (0.0004) [2023-03-08 04:24:49,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 11899.2). Total num frames: 38207488. Throughput: 0: 12584.2. Samples: 38180672. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:24:49,595][320945] Avg episode reward: [(0, '4863.055')] [2023-03-08 04:24:50,134][321237] Updated weights for policy 0, policy_version 74640 (0.0004) [2023-03-08 04:24:53,556][321237] Updated weights for policy 0, policy_version 74720 (0.0005) [2023-03-08 04:24:54,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12492.8, 300 sec: 11913.1). Total num frames: 38264832. Throughput: 0: 12503.0. Samples: 38253264. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:24:54,595][320945] Avg episode reward: [(0, '4860.574')] [2023-03-08 04:24:54,646][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000074744_38268928.pth... [2023-03-08 04:24:54,648][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000074008_37892096.pth [2023-03-08 04:24:57,162][321237] Updated weights for policy 0, policy_version 74800 (0.0005) [2023-03-08 04:24:59,594][320945] Fps is (10 sec: 11468.9, 60 sec: 12424.6, 300 sec: 11913.1). Total num frames: 38322176. Throughput: 0: 12343.8. Samples: 38322176. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:24:59,594][320945] Avg episode reward: [(0, '4862.729')] [2023-03-08 04:25:00,708][321237] Updated weights for policy 0, policy_version 74880 (0.0005) [2023-03-08 04:25:04,374][321237] Updated weights for policy 0, policy_version 74960 (0.0005) [2023-03-08 04:25:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 12288.0, 300 sec: 11899.2). Total num frames: 38379520. Throughput: 0: 12260.1. Samples: 38355736. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:25:04,595][320945] Avg episode reward: [(0, '4862.830')] [2023-03-08 04:25:07,988][321237] Updated weights for policy 0, policy_version 75040 (0.0005) [2023-03-08 04:25:09,594][320945] Fps is (10 sec: 11468.6, 60 sec: 12219.7, 300 sec: 11871.5). Total num frames: 38436864. Throughput: 0: 12186.7. Samples: 38424124. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:25:09,595][320945] Avg episode reward: [(0, '4861.950')] [2023-03-08 04:25:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000075072_38436864.pth... [2023-03-08 04:25:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000074376_38080512.pth [2023-03-08 04:25:11,512][321237] Updated weights for policy 0, policy_version 75120 (0.0004) [2023-03-08 04:25:14,594][320945] Fps is (10 sec: 11468.9, 60 sec: 12083.2, 300 sec: 11871.5). Total num frames: 38494208. Throughput: 0: 12030.1. Samples: 38494272. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:25:14,594][320945] Avg episode reward: [(0, '4863.766')] [2023-03-08 04:25:14,944][321237] Updated weights for policy 0, policy_version 75200 (0.0005) [2023-03-08 04:25:18,157][321237] Updated weights for policy 0, policy_version 75280 (0.0003) [2023-03-08 04:25:19,594][320945] Fps is (10 sec: 12288.2, 60 sec: 12151.5, 300 sec: 11899.2). Total num frames: 38559744. Throughput: 0: 12002.3. Samples: 38531196. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:25:19,595][320945] Avg episode reward: [(0, '4862.036')] [2023-03-08 04:25:21,465][321237] Updated weights for policy 0, policy_version 75360 (0.0005) [2023-03-08 04:25:24,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 11913.1). Total num frames: 38621184. Throughput: 0: 11979.6. Samples: 38605016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:25:24,595][320945] Avg episode reward: [(0, '4861.515')] [2023-03-08 04:25:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000075432_38621184.pth... [2023-03-08 04:25:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000074744_38268928.pth [2023-03-08 04:25:24,889][321237] Updated weights for policy 0, policy_version 75440 (0.0005) [2023-03-08 04:25:28,487][321237] Updated weights for policy 0, policy_version 75520 (0.0005) [2023-03-08 04:25:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11913.1). Total num frames: 38678528. Throughput: 0: 11845.6. Samples: 38675004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:25:29,595][320945] Avg episode reward: [(0, '4818.519')] [2023-03-08 04:25:32,018][321237] Updated weights for policy 0, policy_version 75600 (0.0005) [2023-03-08 04:25:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11927.0). Total num frames: 38735872. Throughput: 0: 11772.5. Samples: 38710436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:25:34,595][320945] Avg episode reward: [(0, '4863.969')] [2023-03-08 04:25:35,539][321237] Updated weights for policy 0, policy_version 75680 (0.0005) [2023-03-08 04:25:39,203][321237] Updated weights for policy 0, policy_version 75760 (0.0005) [2023-03-08 04:25:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11878.4, 300 sec: 11927.0). Total num frames: 38793216. Throughput: 0: 11684.4. Samples: 38779064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:25:39,595][320945] Avg episode reward: [(0, '4862.192')] [2023-03-08 04:25:39,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000075768_38793216.pth... [2023-03-08 04:25:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000075072_38436864.pth [2023-03-08 04:25:42,804][321237] Updated weights for policy 0, policy_version 75840 (0.0005) [2023-03-08 04:25:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11913.1). Total num frames: 38846464. Throughput: 0: 11652.2. Samples: 38846528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:25:44,595][320945] Avg episode reward: [(0, '4863.119')] [2023-03-08 04:25:46,380][321237] Updated weights for policy 0, policy_version 75920 (0.0005) [2023-03-08 04:25:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11927.0). Total num frames: 38907904. Throughput: 0: 11679.6. Samples: 38881316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:25:49,595][320945] Avg episode reward: [(0, '4861.682')] [2023-03-08 04:25:49,855][321237] Updated weights for policy 0, policy_version 76000 (0.0005) [2023-03-08 04:25:53,358][321237] Updated weights for policy 0, policy_version 76080 (0.0005) [2023-03-08 04:25:54,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11913.1). Total num frames: 38965248. Throughput: 0: 11744.9. Samples: 38952644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:25:54,595][320945] Avg episode reward: [(0, '4861.512')] [2023-03-08 04:25:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000076104_38965248.pth... [2023-03-08 04:25:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000075432_38621184.pth [2023-03-08 04:25:56,831][321237] Updated weights for policy 0, policy_version 76160 (0.0005) [2023-03-08 04:25:59,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11741.9, 300 sec: 11913.1). Total num frames: 39026688. Throughput: 0: 11783.8. Samples: 39024544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:25:59,595][320945] Avg episode reward: [(0, '4860.755')] [2023-03-08 04:26:00,032][321237] Updated weights for policy 0, policy_version 76240 (0.0004) [2023-03-08 04:26:03,309][321237] Updated weights for policy 0, policy_version 76320 (0.0004) [2023-03-08 04:26:04,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11927.0). Total num frames: 39088128. Throughput: 0: 11819.9. Samples: 39063092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:26:04,594][320945] Avg episode reward: [(0, '4861.246')] [2023-03-08 04:26:06,571][321237] Updated weights for policy 0, policy_version 76400 (0.0004) [2023-03-08 04:26:09,594][320945] Fps is (10 sec: 12697.6, 60 sec: 11946.7, 300 sec: 11954.8). Total num frames: 39153664. Throughput: 0: 11829.5. Samples: 39137344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:26:09,595][320945] Avg episode reward: [(0, '4863.256')] [2023-03-08 04:26:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000076472_39153664.pth... [2023-03-08 04:26:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000075768_38793216.pth [2023-03-08 04:26:09,853][321237] Updated weights for policy 0, policy_version 76480 (0.0004) [2023-03-08 04:26:13,047][321237] Updated weights for policy 0, policy_version 76560 (0.0004) [2023-03-08 04:26:14,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12014.9, 300 sec: 11968.6). Total num frames: 39215104. Throughput: 0: 11988.7. Samples: 39214496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:26:14,595][320945] Avg episode reward: [(0, '4860.863')] [2023-03-08 04:26:16,396][321237] Updated weights for policy 0, policy_version 76640 (0.0004) [2023-03-08 04:26:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11968.7). Total num frames: 39272448. Throughput: 0: 11967.2. Samples: 39248960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:26:19,595][320945] Avg episode reward: [(0, '4863.265')] [2023-03-08 04:26:20,021][321237] Updated weights for policy 0, policy_version 76720 (0.0005) [2023-03-08 04:26:23,530][321237] Updated weights for policy 0, policy_version 76800 (0.0005) [2023-03-08 04:26:24,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11954.8). Total num frames: 39329792. Throughput: 0: 11986.7. Samples: 39318464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:26:24,594][320945] Avg episode reward: [(0, '4865.317')] [2023-03-08 04:26:24,615][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000076824_39333888.pth... [2023-03-08 04:26:24,616][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000076104_38965248.pth [2023-03-08 04:26:27,091][321237] Updated weights for policy 0, policy_version 76880 (0.0005) [2023-03-08 04:26:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11954.8). Total num frames: 39391232. Throughput: 0: 12014.9. Samples: 39387200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:26:29,595][320945] Avg episode reward: [(0, '4863.159')] [2023-03-08 04:26:30,683][321237] Updated weights for policy 0, policy_version 76960 (0.0005) [2023-03-08 04:26:34,130][321237] Updated weights for policy 0, policy_version 77040 (0.0005) [2023-03-08 04:26:34,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11940.9). Total num frames: 39448576. Throughput: 0: 12025.8. Samples: 39422476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:26:34,595][320945] Avg episode reward: [(0, '4859.507')] [2023-03-08 04:26:37,329][321237] Updated weights for policy 0, policy_version 77120 (0.0004) [2023-03-08 04:26:39,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 11968.6). Total num frames: 39514112. Throughput: 0: 12114.4. Samples: 39497792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:26:39,595][320945] Avg episode reward: [(0, '4862.796')] [2023-03-08 04:26:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000077176_39514112.pth... [2023-03-08 04:26:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000076472_39153664.pth [2023-03-08 04:26:40,506][321237] Updated weights for policy 0, policy_version 77200 (0.0004) [2023-03-08 04:26:43,815][321237] Updated weights for policy 0, policy_version 77280 (0.0005) [2023-03-08 04:26:44,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 11968.6). Total num frames: 39575552. Throughput: 0: 12179.9. Samples: 39572640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:26:44,595][320945] Avg episode reward: [(0, '4818.442')] [2023-03-08 04:26:47,025][321237] Updated weights for policy 0, policy_version 77360 (0.0004) [2023-03-08 04:26:49,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 11996.4). Total num frames: 39641088. Throughput: 0: 12193.0. Samples: 39611776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:26:49,595][320945] Avg episode reward: [(0, '4862.396')] [2023-03-08 04:26:50,144][321237] Updated weights for policy 0, policy_version 77440 (0.0004) [2023-03-08 04:26:53,534][321237] Updated weights for policy 0, policy_version 77520 (0.0005) [2023-03-08 04:26:54,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12288.0, 300 sec: 11996.4). Total num frames: 39702528. Throughput: 0: 12212.9. Samples: 39686924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:26:54,595][320945] Avg episode reward: [(0, '4819.046')] [2023-03-08 04:26:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000077544_39702528.pth... [2023-03-08 04:26:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000076824_39333888.pth [2023-03-08 04:26:56,908][321237] Updated weights for policy 0, policy_version 77600 (0.0005) [2023-03-08 04:26:59,594][320945] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 11996.4). Total num frames: 39759872. Throughput: 0: 12117.3. Samples: 39759776. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:26:59,594][320945] Avg episode reward: [(0, '4860.375')] [2023-03-08 04:27:00,330][321237] Updated weights for policy 0, policy_version 77680 (0.0005) [2023-03-08 04:27:03,807][321237] Updated weights for policy 0, policy_version 77760 (0.0005) [2023-03-08 04:27:04,594][320945] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12010.3). Total num frames: 39821312. Throughput: 0: 12140.9. Samples: 39795300. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:27:04,595][320945] Avg episode reward: [(0, '4860.221')] [2023-03-08 04:27:07,225][321237] Updated weights for policy 0, policy_version 77840 (0.0005) [2023-03-08 04:27:09,594][320945] Fps is (10 sec: 11878.3, 60 sec: 12083.2, 300 sec: 12010.3). Total num frames: 39878656. Throughput: 0: 12175.6. Samples: 39866368. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:27:09,595][320945] Avg episode reward: [(0, '4818.826')] [2023-03-08 04:27:09,611][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000077896_39882752.pth... [2023-03-08 04:27:09,613][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000077176_39514112.pth [2023-03-08 04:27:10,684][321237] Updated weights for policy 0, policy_version 77920 (0.0005) [2023-03-08 04:27:14,140][321237] Updated weights for policy 0, policy_version 78000 (0.0005) [2023-03-08 04:27:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12024.2). Total num frames: 39940096. Throughput: 0: 12229.1. Samples: 39937512. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:27:14,595][320945] Avg episode reward: [(0, '4865.271')] [2023-03-08 04:27:17,464][321237] Updated weights for policy 0, policy_version 78080 (0.0003) [2023-03-08 04:27:19,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12038.1). Total num frames: 40001536. Throughput: 0: 12258.7. Samples: 39974116. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:27:19,595][320945] Avg episode reward: [(0, '4862.902')] [2023-03-08 04:27:20,713][321237] Updated weights for policy 0, policy_version 78160 (0.0003) [2023-03-08 04:27:24,051][321237] Updated weights for policy 0, policy_version 78240 (0.0003) [2023-03-08 04:27:24,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12052.0). Total num frames: 40062976. Throughput: 0: 12247.0. Samples: 40048908. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:27:24,595][320945] Avg episode reward: [(0, '4859.916')] [2023-03-08 04:27:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000078248_40062976.pth... [2023-03-08 04:27:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000077544_39702528.pth [2023-03-08 04:27:27,340][321237] Updated weights for policy 0, policy_version 78320 (0.0003) [2023-03-08 04:27:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12065.8). Total num frames: 40124416. Throughput: 0: 12258.2. Samples: 40124260. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:27:29,595][320945] Avg episode reward: [(0, '4861.259')] [2023-03-08 04:27:30,673][321237] Updated weights for policy 0, policy_version 78400 (0.0003) [2023-03-08 04:27:34,011][321237] Updated weights for policy 0, policy_version 78480 (0.0003) [2023-03-08 04:27:34,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12079.7). Total num frames: 40185856. Throughput: 0: 12211.4. Samples: 40161288. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:27:34,595][320945] Avg episode reward: [(0, '4818.366')] [2023-03-08 04:27:37,310][321237] Updated weights for policy 0, policy_version 78560 (0.0003) [2023-03-08 04:27:39,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12219.7, 300 sec: 12107.5). Total num frames: 40247296. Throughput: 0: 12158.1. Samples: 40234040. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:27:39,595][320945] Avg episode reward: [(0, '4863.094')] [2023-03-08 04:27:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000078608_40247296.pth... [2023-03-08 04:27:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000077896_39882752.pth [2023-03-08 04:27:40,716][321237] Updated weights for policy 0, policy_version 78640 (0.0003) [2023-03-08 04:27:44,076][321237] Updated weights for policy 0, policy_version 78720 (0.0003) [2023-03-08 04:27:44,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12121.4). Total num frames: 40308736. Throughput: 0: 12166.4. Samples: 40307264. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:27:44,595][320945] Avg episode reward: [(0, '4857.133')] [2023-03-08 04:27:47,518][321237] Updated weights for policy 0, policy_version 78800 (0.0003) [2023-03-08 04:27:49,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12135.3). Total num frames: 40370176. Throughput: 0: 12147.1. Samples: 40341920. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:27:49,595][320945] Avg episode reward: [(0, '4859.899')] [2023-03-08 04:27:50,931][321237] Updated weights for policy 0, policy_version 78880 (0.0003) [2023-03-08 04:27:54,205][321237] Updated weights for policy 0, policy_version 78960 (0.0003) [2023-03-08 04:27:54,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12121.4). Total num frames: 40431616. Throughput: 0: 12198.8. Samples: 40415312. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:27:54,595][320945] Avg episode reward: [(0, '4864.378')] [2023-03-08 04:27:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000078968_40431616.pth... [2023-03-08 04:27:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000078248_40062976.pth [2023-03-08 04:27:57,476][321237] Updated weights for policy 0, policy_version 79040 (0.0003) [2023-03-08 04:27:59,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12135.3). Total num frames: 40493056. Throughput: 0: 12293.7. Samples: 40490728. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:27:59,595][320945] Avg episode reward: [(0, '4864.169')] [2023-03-08 04:28:00,940][321237] Updated weights for policy 0, policy_version 79120 (0.0004) [2023-03-08 04:28:04,456][321237] Updated weights for policy 0, policy_version 79200 (0.0003) [2023-03-08 04:28:04,594][320945] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 12121.4). Total num frames: 40550400. Throughput: 0: 12221.3. Samples: 40524076. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:28:04,595][320945] Avg episode reward: [(0, '4864.152')] [2023-03-08 04:28:07,939][321237] Updated weights for policy 0, policy_version 79280 (0.0005) [2023-03-08 04:28:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12151.5, 300 sec: 12135.3). Total num frames: 40607744. Throughput: 0: 12145.5. Samples: 40595456. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:28:09,595][320945] Avg episode reward: [(0, '4863.636')] [2023-03-08 04:28:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000079312_40607744.pth... [2023-03-08 04:28:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000078608_40247296.pth [2023-03-08 04:28:11,588][321237] Updated weights for policy 0, policy_version 79360 (0.0005) [2023-03-08 04:28:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 12135.3). Total num frames: 40665088. Throughput: 0: 11970.8. Samples: 40662944. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:28:14,595][320945] Avg episode reward: [(0, '4863.499')] [2023-03-08 04:28:15,216][321237] Updated weights for policy 0, policy_version 79440 (0.0005) [2023-03-08 04:28:18,866][321237] Updated weights for policy 0, policy_version 79520 (0.0004) [2023-03-08 04:28:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 12014.9, 300 sec: 12121.4). Total num frames: 40722432. Throughput: 0: 11904.6. Samples: 40696996. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:28:19,595][320945] Avg episode reward: [(0, '4862.691')] [2023-03-08 04:28:22,426][321237] Updated weights for policy 0, policy_version 79600 (0.0004) [2023-03-08 04:28:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 12121.4). Total num frames: 40779776. Throughput: 0: 11780.7. Samples: 40764172. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:28:24,595][320945] Avg episode reward: [(0, '4863.505')] [2023-03-08 04:28:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000079648_40779776.pth... [2023-03-08 04:28:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000078968_40431616.pth [2023-03-08 04:28:25,972][321237] Updated weights for policy 0, policy_version 79680 (0.0004) [2023-03-08 04:28:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 12093.6). Total num frames: 40833024. Throughput: 0: 11685.2. Samples: 40833096. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:28:29,594][320945] Avg episode reward: [(0, '4863.310')] [2023-03-08 04:28:29,606][321237] Updated weights for policy 0, policy_version 79760 (0.0005) [2023-03-08 04:28:33,127][321237] Updated weights for policy 0, policy_version 79840 (0.0005) [2023-03-08 04:28:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 12093.6). Total num frames: 40894464. Throughput: 0: 11699.8. Samples: 40868408. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:28:34,594][320945] Avg episode reward: [(0, '4863.122')] [2023-03-08 04:28:36,580][321237] Updated weights for policy 0, policy_version 79920 (0.0005) [2023-03-08 04:28:39,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 12093.6). Total num frames: 40955904. Throughput: 0: 11656.4. Samples: 40939848. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:28:39,595][320945] Avg episode reward: [(0, '4861.233')] [2023-03-08 04:28:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000079992_40955904.pth... [2023-03-08 04:28:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000079312_40607744.pth [2023-03-08 04:28:39,818][321237] Updated weights for policy 0, policy_version 80000 (0.0005) [2023-03-08 04:28:43,123][321237] Updated weights for policy 0, policy_version 80080 (0.0004) [2023-03-08 04:28:44,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 12079.7). Total num frames: 41017344. Throughput: 0: 11632.9. Samples: 41014208. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:28:44,595][320945] Avg episode reward: [(0, '4859.095')] [2023-03-08 04:28:46,628][321237] Updated weights for policy 0, policy_version 80160 (0.0005) [2023-03-08 04:28:49,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 12065.8). Total num frames: 41074688. Throughput: 0: 11682.7. Samples: 41049796. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:28:49,595][320945] Avg episode reward: [(0, '4859.088')] [2023-03-08 04:28:50,134][321237] Updated weights for policy 0, policy_version 80240 (0.0005) [2023-03-08 04:28:53,811][321237] Updated weights for policy 0, policy_version 80320 (0.0005) [2023-03-08 04:28:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 12052.0). Total num frames: 41132032. Throughput: 0: 11603.1. Samples: 41117596. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:28:54,595][320945] Avg episode reward: [(0, '4858.786')] [2023-03-08 04:28:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000080336_41132032.pth... [2023-03-08 04:28:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000079648_40779776.pth [2023-03-08 04:28:57,148][321237] Updated weights for policy 0, policy_version 80400 (0.0005) [2023-03-08 04:28:59,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 12038.1). Total num frames: 41193472. Throughput: 0: 11766.0. Samples: 41192416. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:28:59,595][320945] Avg episode reward: [(0, '4776.837')] [2023-03-08 04:29:00,343][321237] Updated weights for policy 0, policy_version 80480 (0.0004) [2023-03-08 04:29:03,726][321237] Updated weights for policy 0, policy_version 80560 (0.0005) [2023-03-08 04:29:04,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11741.9, 300 sec: 12038.1). Total num frames: 41254912. Throughput: 0: 11837.1. Samples: 41229668. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:29:04,595][320945] Avg episode reward: [(0, '4861.024')] [2023-03-08 04:29:06,978][321237] Updated weights for policy 0, policy_version 80640 (0.0004) [2023-03-08 04:29:09,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 12024.2). Total num frames: 41316352. Throughput: 0: 11986.7. Samples: 41303576. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:29:09,595][320945] Avg episode reward: [(0, '4863.278')] [2023-03-08 04:29:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000080696_41316352.pth... [2023-03-08 04:29:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000079992_40955904.pth [2023-03-08 04:29:10,480][321237] Updated weights for policy 0, policy_version 80720 (0.0004) [2023-03-08 04:29:14,031][321237] Updated weights for policy 0, policy_version 80800 (0.0005) [2023-03-08 04:29:14,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 12010.3). Total num frames: 41373696. Throughput: 0: 11986.7. Samples: 41372500. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:29:14,595][320945] Avg episode reward: [(0, '4864.512')] [2023-03-08 04:29:17,571][321237] Updated weights for policy 0, policy_version 80880 (0.0005) [2023-03-08 04:29:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11996.4). Total num frames: 41431040. Throughput: 0: 11964.6. Samples: 41406816. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:29:19,595][320945] Avg episode reward: [(0, '4861.271')] [2023-03-08 04:29:21,165][321237] Updated weights for policy 0, policy_version 80960 (0.0005) [2023-03-08 04:29:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11996.4). Total num frames: 41492480. Throughput: 0: 11920.2. Samples: 41476256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:29:24,595][320945] Avg episode reward: [(0, '4820.721')] [2023-03-08 04:29:24,595][321237] Updated weights for policy 0, policy_version 81040 (0.0005) [2023-03-08 04:29:24,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000081040_41492480.pth... [2023-03-08 04:29:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000080336_41132032.pth [2023-03-08 04:29:28,084][321237] Updated weights for policy 0, policy_version 81120 (0.0005) [2023-03-08 04:29:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11968.6). Total num frames: 41549824. Throughput: 0: 11825.0. Samples: 41546332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:29:29,595][320945] Avg episode reward: [(0, '4863.768')] [2023-03-08 04:29:31,585][321237] Updated weights for policy 0, policy_version 81200 (0.0005) [2023-03-08 04:29:34,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11968.7). Total num frames: 41611264. Throughput: 0: 11841.3. Samples: 41582656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:29:34,595][320945] Avg episode reward: [(0, '4862.136')] [2023-03-08 04:29:34,807][321237] Updated weights for policy 0, policy_version 81280 (0.0004) [2023-03-08 04:29:38,187][321237] Updated weights for policy 0, policy_version 81360 (0.0004) [2023-03-08 04:29:39,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11954.8). Total num frames: 41668608. Throughput: 0: 11987.0. Samples: 41657012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:29:39,594][320945] Avg episode reward: [(0, '4860.159')] [2023-03-08 04:29:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000081392_41672704.pth... [2023-03-08 04:29:39,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000080696_41316352.pth [2023-03-08 04:29:41,732][321237] Updated weights for policy 0, policy_version 81440 (0.0005) [2023-03-08 04:29:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11927.0). Total num frames: 41725952. Throughput: 0: 11850.8. Samples: 41725700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:29:44,595][320945] Avg episode reward: [(0, '4860.915')] [2023-03-08 04:29:45,376][321237] Updated weights for policy 0, policy_version 81520 (0.0005) [2023-03-08 04:29:49,011][321237] Updated weights for policy 0, policy_version 81600 (0.0005) [2023-03-08 04:29:49,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11810.1, 300 sec: 11927.0). Total num frames: 41783296. Throughput: 0: 11781.1. Samples: 41759816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:29:49,595][320945] Avg episode reward: [(0, '4860.955')] [2023-03-08 04:29:52,614][321237] Updated weights for policy 0, policy_version 81680 (0.0005) [2023-03-08 04:29:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11810.1, 300 sec: 11927.0). Total num frames: 41840640. Throughput: 0: 11655.1. Samples: 41828056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:29:54,595][320945] Avg episode reward: [(0, '4862.821')] [2023-03-08 04:29:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000081720_41840640.pth... [2023-03-08 04:29:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000081040_41492480.pth [2023-03-08 04:29:56,243][321237] Updated weights for policy 0, policy_version 81760 (0.0005) [2023-03-08 04:29:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11927.0). Total num frames: 41897984. Throughput: 0: 11677.2. Samples: 41897976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:29:59,595][320945] Avg episode reward: [(0, '4863.868')] [2023-03-08 04:29:59,607][321237] Updated weights for policy 0, policy_version 81840 (0.0004) [2023-03-08 04:30:02,860][321237] Updated weights for policy 0, policy_version 81920 (0.0003) [2023-03-08 04:30:04,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11810.1, 300 sec: 11954.8). Total num frames: 41963520. Throughput: 0: 11749.8. Samples: 41935556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:30:04,595][320945] Avg episode reward: [(0, '4861.180')] [2023-03-08 04:30:06,208][321237] Updated weights for policy 0, policy_version 82000 (0.0005) [2023-03-08 04:30:09,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11954.8). Total num frames: 42020864. Throughput: 0: 11810.7. Samples: 42007736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:30:09,595][320945] Avg episode reward: [(0, '4863.175')] [2023-03-08 04:30:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000082072_42020864.pth... [2023-03-08 04:30:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000081392_41672704.pth [2023-03-08 04:30:09,728][321237] Updated weights for policy 0, policy_version 82080 (0.0004) [2023-03-08 04:30:12,960][321237] Updated weights for policy 0, policy_version 82160 (0.0004) [2023-03-08 04:30:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11940.9). Total num frames: 42082304. Throughput: 0: 11906.9. Samples: 42082144. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:30:14,595][320945] Avg episode reward: [(0, '4863.091')] [2023-03-08 04:30:16,391][321237] Updated weights for policy 0, policy_version 82240 (0.0005) [2023-03-08 04:30:19,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11940.9). Total num frames: 42143744. Throughput: 0: 11881.0. Samples: 42117300. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:30:19,595][320945] Avg episode reward: [(0, '4819.764')] [2023-03-08 04:30:19,918][321237] Updated weights for policy 0, policy_version 82320 (0.0005) [2023-03-08 04:30:23,576][321237] Updated weights for policy 0, policy_version 82400 (0.0005) [2023-03-08 04:30:24,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11940.9). Total num frames: 42201088. Throughput: 0: 11728.2. Samples: 42184784. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:30:24,595][320945] Avg episode reward: [(0, '4859.601')] [2023-03-08 04:30:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000082424_42201088.pth... [2023-03-08 04:30:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000081720_41840640.pth [2023-03-08 04:30:26,830][321237] Updated weights for policy 0, policy_version 82480 (0.0004) [2023-03-08 04:30:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11940.9). Total num frames: 42258432. Throughput: 0: 11838.0. Samples: 42258412. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:30:29,595][320945] Avg episode reward: [(0, '4858.001')] [2023-03-08 04:30:30,446][321237] Updated weights for policy 0, policy_version 82560 (0.0005) [2023-03-08 04:30:34,012][321237] Updated weights for policy 0, policy_version 82640 (0.0005) [2023-03-08 04:30:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 11940.9). Total num frames: 42315776. Throughput: 0: 11810.0. Samples: 42291264. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:30:34,594][320945] Avg episode reward: [(0, '4863.714')] [2023-03-08 04:30:37,459][321237] Updated weights for policy 0, policy_version 82720 (0.0005) [2023-03-08 04:30:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11968.6). Total num frames: 42377216. Throughput: 0: 11875.5. Samples: 42362452. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:30:39,595][320945] Avg episode reward: [(0, '4864.426')] [2023-03-08 04:30:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000082768_42377216.pth... [2023-03-08 04:30:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000082072_42020864.pth [2023-03-08 04:30:40,786][321237] Updated weights for policy 0, policy_version 82800 (0.0004) [2023-03-08 04:30:44,077][321237] Updated weights for policy 0, policy_version 82880 (0.0004) [2023-03-08 04:30:44,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11878.4, 300 sec: 11968.6). Total num frames: 42438656. Throughput: 0: 11973.6. Samples: 42436788. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:30:44,595][320945] Avg episode reward: [(0, '4863.173')] [2023-03-08 04:30:47,488][321237] Updated weights for policy 0, policy_version 82960 (0.0004) [2023-03-08 04:30:49,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11946.7, 300 sec: 11982.5). Total num frames: 42500096. Throughput: 0: 11929.7. Samples: 42472392. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:30:49,595][320945] Avg episode reward: [(0, '4865.624')] [2023-03-08 04:30:49,595][321188] Saving new best policy, reward=4865.624! [2023-03-08 04:30:50,739][321237] Updated weights for policy 0, policy_version 83040 (0.0004) [2023-03-08 04:30:53,930][321237] Updated weights for policy 0, policy_version 83120 (0.0003) [2023-03-08 04:30:54,594][320945] Fps is (10 sec: 12288.1, 60 sec: 12015.0, 300 sec: 11982.5). Total num frames: 42561536. Throughput: 0: 12031.0. Samples: 42549132. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:30:54,594][320945] Avg episode reward: [(0, '4863.381')] [2023-03-08 04:30:54,606][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000083136_42565632.pth... [2023-03-08 04:30:54,607][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000082424_42201088.pth [2023-03-08 04:30:57,268][321237] Updated weights for policy 0, policy_version 83200 (0.0004) [2023-03-08 04:30:59,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11982.5). Total num frames: 42622976. Throughput: 0: 11986.4. Samples: 42621532. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:30:59,595][320945] Avg episode reward: [(0, '4861.332')] [2023-03-08 04:31:00,756][321237] Updated weights for policy 0, policy_version 83280 (0.0004) [2023-03-08 04:31:04,004][321237] Updated weights for policy 0, policy_version 83360 (0.0004) [2023-03-08 04:31:04,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11968.7). Total num frames: 42684416. Throughput: 0: 12034.2. Samples: 42658840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:31:04,595][320945] Avg episode reward: [(0, '4865.162')] [2023-03-08 04:31:07,339][321237] Updated weights for policy 0, policy_version 83440 (0.0004) [2023-03-08 04:31:09,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 11968.6). Total num frames: 42745856. Throughput: 0: 12160.5. Samples: 42732008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:31:09,595][320945] Avg episode reward: [(0, '4864.566')] [2023-03-08 04:31:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000083488_42745856.pth... [2023-03-08 04:31:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000082768_42377216.pth [2023-03-08 04:31:10,890][321237] Updated weights for policy 0, policy_version 83520 (0.0005) [2023-03-08 04:31:14,522][321237] Updated weights for policy 0, policy_version 83600 (0.0005) [2023-03-08 04:31:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11968.7). Total num frames: 42803200. Throughput: 0: 12028.5. Samples: 42799692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:31:14,595][320945] Avg episode reward: [(0, '4862.930')] [2023-03-08 04:31:18,083][321237] Updated weights for policy 0, policy_version 83680 (0.0005) [2023-03-08 04:31:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11946.7, 300 sec: 11968.6). Total num frames: 42860544. Throughput: 0: 12079.2. Samples: 42834828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:31:19,595][320945] Avg episode reward: [(0, '4862.858')] [2023-03-08 04:31:21,684][321237] Updated weights for policy 0, policy_version 83760 (0.0005) [2023-03-08 04:31:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11954.8). Total num frames: 42917888. Throughput: 0: 12030.1. Samples: 42903808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:31:24,595][320945] Avg episode reward: [(0, '4864.510')] [2023-03-08 04:31:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000083824_42917888.pth... [2023-03-08 04:31:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000083136_42565632.pth [2023-03-08 04:31:25,168][321237] Updated weights for policy 0, policy_version 83840 (0.0005) [2023-03-08 04:31:28,795][321237] Updated weights for policy 0, policy_version 83920 (0.0005) [2023-03-08 04:31:29,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11946.7, 300 sec: 11954.8). Total num frames: 42975232. Throughput: 0: 11895.2. Samples: 42972072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:31:29,595][320945] Avg episode reward: [(0, '4865.087')] [2023-03-08 04:31:32,342][321237] Updated weights for policy 0, policy_version 84000 (0.0005) [2023-03-08 04:31:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11927.0). Total num frames: 43032576. Throughput: 0: 11899.0. Samples: 43007848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:31:34,595][320945] Avg episode reward: [(0, '4864.107')] [2023-03-08 04:31:35,923][321237] Updated weights for policy 0, policy_version 84080 (0.0005) [2023-03-08 04:31:39,385][321237] Updated weights for policy 0, policy_version 84160 (0.0005) [2023-03-08 04:31:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11878.4, 300 sec: 11913.1). Total num frames: 43089920. Throughput: 0: 11739.9. Samples: 43077428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:31:39,595][320945] Avg episode reward: [(0, '4863.553')] [2023-03-08 04:31:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000084160_43089920.pth... [2023-03-08 04:31:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000083488_42745856.pth [2023-03-08 04:31:42,983][321237] Updated weights for policy 0, policy_version 84240 (0.0005) [2023-03-08 04:31:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11885.3). Total num frames: 43147264. Throughput: 0: 11643.7. Samples: 43145500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:31:44,595][320945] Avg episode reward: [(0, '4864.649')] [2023-03-08 04:31:46,654][321237] Updated weights for policy 0, policy_version 84320 (0.0005) [2023-03-08 04:31:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11673.6, 300 sec: 11857.6). Total num frames: 43200512. Throughput: 0: 11564.7. Samples: 43179252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:31:49,595][320945] Avg episode reward: [(0, '4863.363')] [2023-03-08 04:31:50,322][321237] Updated weights for policy 0, policy_version 84400 (0.0005) [2023-03-08 04:31:53,827][321237] Updated weights for policy 0, policy_version 84480 (0.0005) [2023-03-08 04:31:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11871.5). Total num frames: 43261952. Throughput: 0: 11451.1. Samples: 43247308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:31:54,595][320945] Avg episode reward: [(0, '4861.740')] [2023-03-08 04:31:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000084496_43261952.pth... [2023-03-08 04:31:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000083824_42917888.pth [2023-03-08 04:31:57,423][321237] Updated weights for policy 0, policy_version 84560 (0.0005) [2023-03-08 04:31:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11857.6). Total num frames: 43319296. Throughput: 0: 11487.4. Samples: 43316624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:31:59,595][320945] Avg episode reward: [(0, '4865.543')] [2023-03-08 04:32:00,984][321237] Updated weights for policy 0, policy_version 84640 (0.0005) [2023-03-08 04:32:04,591][321237] Updated weights for policy 0, policy_version 84720 (0.0005) [2023-03-08 04:32:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11857.6). Total num frames: 43376640. Throughput: 0: 11466.3. Samples: 43350812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:32:04,595][320945] Avg episode reward: [(0, '4862.164')] [2023-03-08 04:32:08,157][321237] Updated weights for policy 0, policy_version 84800 (0.0005) [2023-03-08 04:32:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11843.7). Total num frames: 43433984. Throughput: 0: 11443.7. Samples: 43418772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:32:09,595][320945] Avg episode reward: [(0, '4862.410')] [2023-03-08 04:32:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000084832_43433984.pth... [2023-03-08 04:32:09,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000084160_43089920.pth [2023-03-08 04:32:11,746][321237] Updated weights for policy 0, policy_version 84880 (0.0005) [2023-03-08 04:32:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11815.9). Total num frames: 43487232. Throughput: 0: 11449.4. Samples: 43487296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:32:14,595][320945] Avg episode reward: [(0, '4864.344')] [2023-03-08 04:32:15,330][321237] Updated weights for policy 0, policy_version 84960 (0.0005) [2023-03-08 04:32:18,866][321237] Updated weights for policy 0, policy_version 85040 (0.0005) [2023-03-08 04:32:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11802.0). Total num frames: 43544576. Throughput: 0: 11450.9. Samples: 43523140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:32:19,595][320945] Avg episode reward: [(0, '4862.383')] [2023-03-08 04:32:22,550][321237] Updated weights for policy 0, policy_version 85120 (0.0005) [2023-03-08 04:32:24,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11788.1). Total num frames: 43601920. Throughput: 0: 11383.9. Samples: 43589704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:32:24,595][320945] Avg episode reward: [(0, '4861.775')] [2023-03-08 04:32:24,620][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000085168_43606016.pth... [2023-03-08 04:32:24,621][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000084496_43261952.pth [2023-03-08 04:32:26,064][321237] Updated weights for policy 0, policy_version 85200 (0.0005) [2023-03-08 04:32:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11774.3). Total num frames: 43659264. Throughput: 0: 11417.2. Samples: 43659272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:32:29,595][320945] Avg episode reward: [(0, '4863.788')] [2023-03-08 04:32:29,615][321237] Updated weights for policy 0, policy_version 85280 (0.0005) [2023-03-08 04:32:33,157][321237] Updated weights for policy 0, policy_version 85360 (0.0005) [2023-03-08 04:32:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11760.4). Total num frames: 43716608. Throughput: 0: 11447.7. Samples: 43694400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:32:34,595][320945] Avg episode reward: [(0, '4861.418')] [2023-03-08 04:32:36,756][321237] Updated weights for policy 0, policy_version 85440 (0.0005) [2023-03-08 04:32:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11746.5). Total num frames: 43773952. Throughput: 0: 11452.6. Samples: 43762676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:32:39,595][320945] Avg episode reward: [(0, '4863.303')] [2023-03-08 04:32:39,634][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000085504_43778048.pth... [2023-03-08 04:32:39,636][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000084832_43433984.pth [2023-03-08 04:32:40,351][321237] Updated weights for policy 0, policy_version 85520 (0.0005) [2023-03-08 04:32:43,935][321237] Updated weights for policy 0, policy_version 85600 (0.0005) [2023-03-08 04:32:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11732.6). Total num frames: 43831296. Throughput: 0: 11437.3. Samples: 43831304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:32:44,595][320945] Avg episode reward: [(0, '4864.742')] [2023-03-08 04:32:47,539][321237] Updated weights for policy 0, policy_version 85680 (0.0005) [2023-03-08 04:32:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11718.7). Total num frames: 43888640. Throughput: 0: 11427.7. Samples: 43865060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:32:49,595][320945] Avg episode reward: [(0, '4860.962')] [2023-03-08 04:32:51,129][321237] Updated weights for policy 0, policy_version 85760 (0.0005) [2023-03-08 04:32:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11704.8). Total num frames: 43945984. Throughput: 0: 11444.2. Samples: 43933760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:32:54,595][320945] Avg episode reward: [(0, '4863.448')] [2023-03-08 04:32:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000085832_43945984.pth... [2023-03-08 04:32:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000085168_43606016.pth [2023-03-08 04:32:54,667][321237] Updated weights for policy 0, policy_version 85840 (0.0005) [2023-03-08 04:32:57,885][321237] Updated weights for policy 0, policy_version 85920 (0.0004) [2023-03-08 04:32:59,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11732.6). Total num frames: 44011520. Throughput: 0: 11567.6. Samples: 44007840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:32:59,595][320945] Avg episode reward: [(0, '4862.662')] [2023-03-08 04:33:01,069][321237] Updated weights for policy 0, policy_version 86000 (0.0004) [2023-03-08 04:33:04,264][321237] Updated weights for policy 0, policy_version 86080 (0.0004) [2023-03-08 04:33:04,594][320945] Fps is (10 sec: 13107.3, 60 sec: 11673.6, 300 sec: 11760.4). Total num frames: 44077056. Throughput: 0: 11656.2. Samples: 44047668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:33:04,595][320945] Avg episode reward: [(0, '4863.005')] [2023-03-08 04:33:07,469][321237] Updated weights for policy 0, policy_version 86160 (0.0004) [2023-03-08 04:33:09,594][320945] Fps is (10 sec: 12697.5, 60 sec: 11741.9, 300 sec: 11774.3). Total num frames: 44138496. Throughput: 0: 11884.1. Samples: 44124488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:33:09,595][320945] Avg episode reward: [(0, '4862.327')] [2023-03-08 04:33:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000086208_44138496.pth... [2023-03-08 04:33:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000085504_43778048.pth [2023-03-08 04:33:10,666][321237] Updated weights for policy 0, policy_version 86240 (0.0004) [2023-03-08 04:33:13,931][321237] Updated weights for policy 0, policy_version 86320 (0.0004) [2023-03-08 04:33:14,594][320945] Fps is (10 sec: 12697.7, 60 sec: 11946.7, 300 sec: 11802.0). Total num frames: 44204032. Throughput: 0: 12016.2. Samples: 44200000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:33:14,595][320945] Avg episode reward: [(0, '4863.469')] [2023-03-08 04:33:17,118][321237] Updated weights for policy 0, policy_version 86400 (0.0004) [2023-03-08 04:33:19,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12014.9, 300 sec: 11815.9). Total num frames: 44265472. Throughput: 0: 12094.7. Samples: 44238660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:33:19,595][320945] Avg episode reward: [(0, '4864.978')] [2023-03-08 04:33:20,311][321237] Updated weights for policy 0, policy_version 86480 (0.0004) [2023-03-08 04:33:23,485][321237] Updated weights for policy 0, policy_version 86560 (0.0004) [2023-03-08 04:33:24,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 11857.6). Total num frames: 44331008. Throughput: 0: 12289.3. Samples: 44315696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:33:24,595][320945] Avg episode reward: [(0, '4862.035')] [2023-03-08 04:33:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000086584_44331008.pth... [2023-03-08 04:33:24,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000085832_43945984.pth [2023-03-08 04:33:26,918][321237] Updated weights for policy 0, policy_version 86640 (0.0004) [2023-03-08 04:33:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11843.7). Total num frames: 44388352. Throughput: 0: 12346.3. Samples: 44386888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:33:29,595][320945] Avg episode reward: [(0, '4863.873')] [2023-03-08 04:33:30,480][321237] Updated weights for policy 0, policy_version 86720 (0.0003) [2023-03-08 04:33:33,991][321237] Updated weights for policy 0, policy_version 86800 (0.0004) [2023-03-08 04:33:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 12151.5, 300 sec: 11829.8). Total num frames: 44445696. Throughput: 0: 12356.9. Samples: 44421120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:33:34,594][320945] Avg episode reward: [(0, '4863.364')] [2023-03-08 04:33:37,452][321237] Updated weights for policy 0, policy_version 86880 (0.0005) [2023-03-08 04:33:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12151.5, 300 sec: 11815.9). Total num frames: 44503040. Throughput: 0: 12389.1. Samples: 44491268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:33:39,594][320945] Avg episode reward: [(0, '4861.626')] [2023-03-08 04:33:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000086928_44507136.pth... [2023-03-08 04:33:39,598][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000086208_44138496.pth [2023-03-08 04:33:41,000][321237] Updated weights for policy 0, policy_version 86960 (0.0005) [2023-03-08 04:33:44,340][321237] Updated weights for policy 0, policy_version 87040 (0.0004) [2023-03-08 04:33:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 11829.8). Total num frames: 44564480. Throughput: 0: 12352.0. Samples: 44563680. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:33:44,595][320945] Avg episode reward: [(0, '4861.839')] [2023-03-08 04:33:47,694][321237] Updated weights for policy 0, policy_version 87120 (0.0004) [2023-03-08 04:33:49,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11843.7). Total num frames: 44625920. Throughput: 0: 12297.6. Samples: 44601060. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:33:49,595][320945] Avg episode reward: [(0, '4864.713')] [2023-03-08 04:33:51,128][321237] Updated weights for policy 0, policy_version 87200 (0.0005) [2023-03-08 04:33:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 11829.8). Total num frames: 44683264. Throughput: 0: 12145.6. Samples: 44671040. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:33:54,595][320945] Avg episode reward: [(0, '4860.363')] [2023-03-08 04:33:54,634][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000087280_44687360.pth... [2023-03-08 04:33:54,634][321237] Updated weights for policy 0, policy_version 87280 (0.0005) [2023-03-08 04:33:54,636][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000086584_44331008.pth [2023-03-08 04:33:58,080][321237] Updated weights for policy 0, policy_version 87360 (0.0005) [2023-03-08 04:33:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 11829.8). Total num frames: 44744704. Throughput: 0: 12052.2. Samples: 44742348. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:33:59,595][320945] Avg episode reward: [(0, '4860.674')] [2023-03-08 04:34:01,572][321237] Updated weights for policy 0, policy_version 87440 (0.0005) [2023-03-08 04:34:04,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11815.9). Total num frames: 44802048. Throughput: 0: 11973.9. Samples: 44777484. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:34:04,595][320945] Avg episode reward: [(0, '4861.450')] [2023-03-08 04:34:04,947][321237] Updated weights for policy 0, policy_version 87520 (0.0005) [2023-03-08 04:34:08,547][321237] Updated weights for policy 0, policy_version 87600 (0.0005) [2023-03-08 04:34:09,594][320945] Fps is (10 sec: 11878.2, 60 sec: 12083.2, 300 sec: 11829.8). Total num frames: 44863488. Throughput: 0: 11820.3. Samples: 44847612. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:34:09,595][320945] Avg episode reward: [(0, '4864.723')] [2023-03-08 04:34:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000087624_44863488.pth... [2023-03-08 04:34:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000086928_44507136.pth [2023-03-08 04:34:12,005][321237] Updated weights for policy 0, policy_version 87680 (0.0005) [2023-03-08 04:34:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11829.8). Total num frames: 44920832. Throughput: 0: 11814.3. Samples: 44918532. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:34:14,595][320945] Avg episode reward: [(0, '4862.985')] [2023-03-08 04:34:15,515][321237] Updated weights for policy 0, policy_version 87760 (0.0005) [2023-03-08 04:34:18,991][321237] Updated weights for policy 0, policy_version 87840 (0.0005) [2023-03-08 04:34:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11878.4, 300 sec: 11815.9). Total num frames: 44978176. Throughput: 0: 11832.9. Samples: 44953600. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:34:19,595][320945] Avg episode reward: [(0, '4864.238')] [2023-03-08 04:34:22,554][321237] Updated weights for policy 0, policy_version 87920 (0.0004) [2023-03-08 04:34:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11815.9). Total num frames: 45035520. Throughput: 0: 11821.7. Samples: 45023248. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:34:24,595][320945] Avg episode reward: [(0, '4862.682')] [2023-03-08 04:34:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000087968_45039616.pth... [2023-03-08 04:34:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000087280_44687360.pth [2023-03-08 04:34:25,849][321237] Updated weights for policy 0, policy_version 88000 (0.0005) [2023-03-08 04:34:29,018][321237] Updated weights for policy 0, policy_version 88080 (0.0004) [2023-03-08 04:34:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11829.8). Total num frames: 45101056. Throughput: 0: 11925.0. Samples: 45100304. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:34:29,595][320945] Avg episode reward: [(0, '4862.835')] [2023-03-08 04:34:32,245][321237] Updated weights for policy 0, policy_version 88160 (0.0004) [2023-03-08 04:34:34,594][320945] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 11857.6). Total num frames: 45166592. Throughput: 0: 11931.6. Samples: 45137984. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:34:34,595][320945] Avg episode reward: [(0, '4863.295')] [2023-03-08 04:34:35,487][321237] Updated weights for policy 0, policy_version 88240 (0.0004) [2023-03-08 04:34:38,814][321237] Updated weights for policy 0, policy_version 88320 (0.0005) [2023-03-08 04:34:39,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12083.2, 300 sec: 11871.5). Total num frames: 45228032. Throughput: 0: 12048.2. Samples: 45213208. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:34:39,595][320945] Avg episode reward: [(0, '4861.643')] [2023-03-08 04:34:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000088336_45228032.pth... [2023-03-08 04:34:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000087624_44863488.pth [2023-03-08 04:34:42,003][321237] Updated weights for policy 0, policy_version 88400 (0.0004) [2023-03-08 04:34:44,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 11899.2). Total num frames: 45293568. Throughput: 0: 12176.8. Samples: 45290304. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:34:44,595][320945] Avg episode reward: [(0, '4861.818')] [2023-03-08 04:34:45,149][321237] Updated weights for policy 0, policy_version 88480 (0.0004) [2023-03-08 04:34:48,393][321237] Updated weights for policy 0, policy_version 88560 (0.0003) [2023-03-08 04:34:49,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 11913.1). Total num frames: 45355008. Throughput: 0: 12249.9. Samples: 45328728. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:34:49,595][320945] Avg episode reward: [(0, '4861.496')] [2023-03-08 04:34:51,583][321237] Updated weights for policy 0, policy_version 88640 (0.0003) [2023-03-08 04:34:54,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12288.0, 300 sec: 11940.9). Total num frames: 45420544. Throughput: 0: 12389.4. Samples: 45405136. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:34:54,595][320945] Avg episode reward: [(0, '4862.285')] [2023-03-08 04:34:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000088712_45420544.pth... [2023-03-08 04:34:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000087968_45039616.pth [2023-03-08 04:34:54,801][321237] Updated weights for policy 0, policy_version 88720 (0.0004) [2023-03-08 04:34:58,012][321237] Updated weights for policy 0, policy_version 88800 (0.0004) [2023-03-08 04:34:59,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 11927.0). Total num frames: 45481984. Throughput: 0: 12515.2. Samples: 45481716. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:34:59,595][320945] Avg episode reward: [(0, '4862.567')] [2023-03-08 04:35:01,447][321237] Updated weights for policy 0, policy_version 88880 (0.0004) [2023-03-08 04:35:04,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11940.9). Total num frames: 45543424. Throughput: 0: 12489.0. Samples: 45515604. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:35:04,595][320945] Avg episode reward: [(0, '4861.443')] [2023-03-08 04:35:04,921][321237] Updated weights for policy 0, policy_version 88960 (0.0005) [2023-03-08 04:35:08,360][321237] Updated weights for policy 0, policy_version 89040 (0.0005) [2023-03-08 04:35:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 11927.0). Total num frames: 45600768. Throughput: 0: 12547.0. Samples: 45587864. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:35:09,595][320945] Avg episode reward: [(0, '4863.320')] [2023-03-08 04:35:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000089064_45600768.pth... [2023-03-08 04:35:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000088336_45228032.pth [2023-03-08 04:35:11,880][321237] Updated weights for policy 0, policy_version 89120 (0.0005) [2023-03-08 04:35:14,594][320945] Fps is (10 sec: 11469.0, 60 sec: 12288.0, 300 sec: 11913.1). Total num frames: 45658112. Throughput: 0: 12395.8. Samples: 45658112. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:35:14,594][320945] Avg episode reward: [(0, '4863.258')] [2023-03-08 04:35:15,322][321237] Updated weights for policy 0, policy_version 89200 (0.0005) [2023-03-08 04:35:18,803][321237] Updated weights for policy 0, policy_version 89280 (0.0005) [2023-03-08 04:35:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 11927.0). Total num frames: 45719552. Throughput: 0: 12342.7. Samples: 45693404. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:35:19,595][320945] Avg episode reward: [(0, '4864.316')] [2023-03-08 04:35:22,357][321237] Updated weights for policy 0, policy_version 89360 (0.0005) [2023-03-08 04:35:24,594][320945] Fps is (10 sec: 11878.3, 60 sec: 12356.3, 300 sec: 11927.0). Total num frames: 45776896. Throughput: 0: 12227.8. Samples: 45763460. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 04:35:24,595][320945] Avg episode reward: [(0, '4864.439')] [2023-03-08 04:35:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000089408_45776896.pth... [2023-03-08 04:35:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000088712_45420544.pth [2023-03-08 04:35:25,875][321237] Updated weights for policy 0, policy_version 89440 (0.0005) [2023-03-08 04:35:29,114][321237] Updated weights for policy 0, policy_version 89520 (0.0004) [2023-03-08 04:35:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 11940.9). Total num frames: 45838336. Throughput: 0: 12125.3. Samples: 45835944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:35:29,595][320945] Avg episode reward: [(0, '4863.707')] [2023-03-08 04:35:32,321][321237] Updated weights for policy 0, policy_version 89600 (0.0004) [2023-03-08 04:35:34,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12288.0, 300 sec: 11954.8). Total num frames: 45903872. Throughput: 0: 12127.9. Samples: 45874484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:35:34,595][320945] Avg episode reward: [(0, '4863.725')] [2023-03-08 04:35:35,526][321237] Updated weights for policy 0, policy_version 89680 (0.0004) [2023-03-08 04:35:38,980][321237] Updated weights for policy 0, policy_version 89760 (0.0005) [2023-03-08 04:35:39,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12219.7, 300 sec: 11940.9). Total num frames: 45961216. Throughput: 0: 12084.5. Samples: 45948936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:35:39,595][320945] Avg episode reward: [(0, '4863.519')] [2023-03-08 04:35:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000089768_45961216.pth... [2023-03-08 04:35:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000089064_45600768.pth [2023-03-08 04:35:42,607][321237] Updated weights for policy 0, policy_version 89840 (0.0005) [2023-03-08 04:35:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 11927.0). Total num frames: 46018560. Throughput: 0: 11904.8. Samples: 46017432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:35:44,595][320945] Avg episode reward: [(0, '4864.298')] [2023-03-08 04:35:46,052][321237] Updated weights for policy 0, policy_version 89920 (0.0005) [2023-03-08 04:35:49,245][321237] Updated weights for policy 0, policy_version 90000 (0.0004) [2023-03-08 04:35:49,594][320945] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 11940.9). Total num frames: 46084096. Throughput: 0: 11985.7. Samples: 46054960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:35:49,595][320945] Avg episode reward: [(0, '4864.155')] [2023-03-08 04:35:52,430][321237] Updated weights for policy 0, policy_version 90080 (0.0004) [2023-03-08 04:35:54,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12083.2, 300 sec: 11940.9). Total num frames: 46145536. Throughput: 0: 12091.5. Samples: 46131984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:35:54,595][320945] Avg episode reward: [(0, '4863.994')] [2023-03-08 04:35:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000090128_46145536.pth... [2023-03-08 04:35:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000089408_45776896.pth [2023-03-08 04:35:55,756][321237] Updated weights for policy 0, policy_version 90160 (0.0004) [2023-03-08 04:35:59,362][321237] Updated weights for policy 0, policy_version 90240 (0.0005) [2023-03-08 04:35:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11927.0). Total num frames: 46202880. Throughput: 0: 12096.7. Samples: 46202464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:35:59,595][320945] Avg episode reward: [(0, '4863.639')] [2023-03-08 04:36:03,074][321237] Updated weights for policy 0, policy_version 90320 (0.0005) [2023-03-08 04:36:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11946.7, 300 sec: 11913.1). Total num frames: 46260224. Throughput: 0: 12050.0. Samples: 46235656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:36:04,605][320945] Avg episode reward: [(0, '4861.885')] [2023-03-08 04:36:06,688][321237] Updated weights for policy 0, policy_version 90400 (0.0005) [2023-03-08 04:36:09,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11946.7, 300 sec: 11913.1). Total num frames: 46317568. Throughput: 0: 12008.6. Samples: 46303844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:36:09,595][320945] Avg episode reward: [(0, '4862.190')] [2023-03-08 04:36:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000090464_46317568.pth... [2023-03-08 04:36:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000089768_45961216.pth [2023-03-08 04:36:10,171][321237] Updated weights for policy 0, policy_version 90480 (0.0005) [2023-03-08 04:36:13,748][321237] Updated weights for policy 0, policy_version 90560 (0.0004) [2023-03-08 04:36:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11913.1). Total num frames: 46374912. Throughput: 0: 11934.5. Samples: 46372996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:36:14,595][320945] Avg episode reward: [(0, '4865.596')] [2023-03-08 04:36:17,314][321237] Updated weights for policy 0, policy_version 90640 (0.0005) [2023-03-08 04:36:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11913.1). Total num frames: 46432256. Throughput: 0: 11848.8. Samples: 46407680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:36:19,595][320945] Avg episode reward: [(0, '4864.352')] [2023-03-08 04:36:20,907][321237] Updated weights for policy 0, policy_version 90720 (0.0005) [2023-03-08 04:36:24,438][321237] Updated weights for policy 0, policy_version 90800 (0.0005) [2023-03-08 04:36:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11913.1). Total num frames: 46489600. Throughput: 0: 11719.4. Samples: 46476308. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:36:24,595][320945] Avg episode reward: [(0, '4863.974')] [2023-03-08 04:36:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000090800_46489600.pth... [2023-03-08 04:36:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000090128_46145536.pth [2023-03-08 04:36:27,991][321237] Updated weights for policy 0, policy_version 90880 (0.0005) [2023-03-08 04:36:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11913.1). Total num frames: 46546944. Throughput: 0: 11728.5. Samples: 46545216. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:36:29,595][320945] Avg episode reward: [(0, '4867.024')] [2023-03-08 04:36:29,595][321188] Saving new best policy, reward=4867.024! [2023-03-08 04:36:31,510][321237] Updated weights for policy 0, policy_version 90960 (0.0005) [2023-03-08 04:36:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11913.1). Total num frames: 46604288. Throughput: 0: 11664.2. Samples: 46579848. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:36:34,595][320945] Avg episode reward: [(0, '4864.895')] [2023-03-08 04:36:35,042][321237] Updated weights for policy 0, policy_version 91040 (0.0005) [2023-03-08 04:36:38,575][321237] Updated weights for policy 0, policy_version 91120 (0.0004) [2023-03-08 04:36:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11927.0). Total num frames: 46665728. Throughput: 0: 11498.3. Samples: 46649408. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:36:39,595][320945] Avg episode reward: [(0, '4857.505')] [2023-03-08 04:36:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000091144_46665728.pth... [2023-03-08 04:36:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000090464_46317568.pth [2023-03-08 04:36:42,030][321237] Updated weights for policy 0, policy_version 91200 (0.0005) [2023-03-08 04:36:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11940.9). Total num frames: 46723072. Throughput: 0: 11515.4. Samples: 46720656. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:36:44,595][320945] Avg episode reward: [(0, '4858.957')] [2023-03-08 04:36:45,462][321237] Updated weights for policy 0, policy_version 91280 (0.0005) [2023-03-08 04:36:48,921][321237] Updated weights for policy 0, policy_version 91360 (0.0005) [2023-03-08 04:36:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11927.0). Total num frames: 46780416. Throughput: 0: 11561.0. Samples: 46755904. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:36:49,595][320945] Avg episode reward: [(0, '4812.691')] [2023-03-08 04:36:52,346][321237] Updated weights for policy 0, policy_version 91440 (0.0005) [2023-03-08 04:36:54,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11940.9). Total num frames: 46841856. Throughput: 0: 11657.0. Samples: 46828412. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:36:54,595][320945] Avg episode reward: [(0, '4818.684')] [2023-03-08 04:36:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000091488_46841856.pth... [2023-03-08 04:36:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000090800_46489600.pth [2023-03-08 04:36:55,614][321237] Updated weights for policy 0, policy_version 91520 (0.0005) [2023-03-08 04:36:58,986][321237] Updated weights for policy 0, policy_version 91600 (0.0004) [2023-03-08 04:36:59,594][320945] Fps is (10 sec: 12697.9, 60 sec: 11741.9, 300 sec: 11968.7). Total num frames: 46907392. Throughput: 0: 11779.7. Samples: 46903080. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:36:59,594][320945] Avg episode reward: [(0, '4860.199')] [2023-03-08 04:37:02,208][321237] Updated weights for policy 0, policy_version 91680 (0.0004) [2023-03-08 04:37:04,594][320945] Fps is (10 sec: 12697.7, 60 sec: 11810.1, 300 sec: 11982.5). Total num frames: 46968832. Throughput: 0: 11840.3. Samples: 46940492. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:37:04,595][320945] Avg episode reward: [(0, '4862.205')] [2023-03-08 04:37:05,595][321237] Updated weights for policy 0, policy_version 91760 (0.0005) [2023-03-08 04:37:09,073][321237] Updated weights for policy 0, policy_version 91840 (0.0005) [2023-03-08 04:37:09,594][320945] Fps is (10 sec: 11878.2, 60 sec: 11810.1, 300 sec: 11996.4). Total num frames: 47026176. Throughput: 0: 11909.3. Samples: 47012228. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:37:09,595][320945] Avg episode reward: [(0, '4859.395')] [2023-03-08 04:37:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000091848_47026176.pth... [2023-03-08 04:37:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000091144_46665728.pth [2023-03-08 04:37:12,358][321237] Updated weights for policy 0, policy_version 91920 (0.0004) [2023-03-08 04:37:14,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12024.2). Total num frames: 47091712. Throughput: 0: 12054.8. Samples: 47087680. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:37:14,595][320945] Avg episode reward: [(0, '4865.480')] [2023-03-08 04:37:15,475][321237] Updated weights for policy 0, policy_version 92000 (0.0005) [2023-03-08 04:37:18,653][321237] Updated weights for policy 0, policy_version 92080 (0.0005) [2023-03-08 04:37:19,594][320945] Fps is (10 sec: 13107.3, 60 sec: 12083.2, 300 sec: 12052.0). Total num frames: 47157248. Throughput: 0: 12181.5. Samples: 47128016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:37:19,595][320945] Avg episode reward: [(0, '4863.667')] [2023-03-08 04:37:21,885][321237] Updated weights for policy 0, policy_version 92160 (0.0005) [2023-03-08 04:37:24,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 12065.8). Total num frames: 47218688. Throughput: 0: 12319.1. Samples: 47203768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:37:24,595][320945] Avg episode reward: [(0, '4865.008')] [2023-03-08 04:37:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000092224_47218688.pth... [2023-03-08 04:37:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000091488_46841856.pth [2023-03-08 04:37:25,049][321237] Updated weights for policy 0, policy_version 92240 (0.0004) [2023-03-08 04:37:28,291][321237] Updated weights for policy 0, policy_version 92320 (0.0005) [2023-03-08 04:37:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12079.7). Total num frames: 47280128. Throughput: 0: 12432.7. Samples: 47280128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:37:29,594][320945] Avg episode reward: [(0, '4861.796')] [2023-03-08 04:37:31,705][321237] Updated weights for policy 0, policy_version 92400 (0.0005) [2023-03-08 04:37:34,594][320945] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12093.6). Total num frames: 47341568. Throughput: 0: 12440.6. Samples: 47315728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:37:34,595][320945] Avg episode reward: [(0, '4863.554')] [2023-03-08 04:37:35,090][321237] Updated weights for policy 0, policy_version 92480 (0.0005) [2023-03-08 04:37:38,555][321237] Updated weights for policy 0, policy_version 92560 (0.0005) [2023-03-08 04:37:39,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12107.5). Total num frames: 47403008. Throughput: 0: 12407.6. Samples: 47386752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:37:39,595][320945] Avg episode reward: [(0, '4863.785')] [2023-03-08 04:37:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000092584_47403008.pth... [2023-03-08 04:37:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000091848_47026176.pth [2023-03-08 04:37:41,953][321237] Updated weights for policy 0, policy_version 92640 (0.0005) [2023-03-08 04:37:44,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12121.4). Total num frames: 47464448. Throughput: 0: 12385.4. Samples: 47460424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:37:44,595][320945] Avg episode reward: [(0, '4863.796')] [2023-03-08 04:37:45,173][321237] Updated weights for policy 0, policy_version 92720 (0.0005) [2023-03-08 04:37:48,276][321237] Updated weights for policy 0, policy_version 92800 (0.0004) [2023-03-08 04:37:49,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12149.2). Total num frames: 47529984. Throughput: 0: 12432.3. Samples: 47499944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:37:49,595][320945] Avg episode reward: [(0, '4860.626')] [2023-03-08 04:37:51,400][321237] Updated weights for policy 0, policy_version 92880 (0.0004) [2023-03-08 04:37:54,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12492.8, 300 sec: 12135.3). Total num frames: 47591424. Throughput: 0: 12589.9. Samples: 47578772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:37:54,594][320945] Avg episode reward: [(0, '4862.562')] [2023-03-08 04:37:54,631][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000092960_47595520.pth... [2023-03-08 04:37:54,631][321237] Updated weights for policy 0, policy_version 92960 (0.0005) [2023-03-08 04:37:54,633][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000092224_47218688.pth [2023-03-08 04:37:57,790][321237] Updated weights for policy 0, policy_version 93040 (0.0005) [2023-03-08 04:37:59,594][320945] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12135.3). Total num frames: 47656960. Throughput: 0: 12633.0. Samples: 47656164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:37:59,595][320945] Avg episode reward: [(0, '4861.101')] [2023-03-08 04:38:00,879][321237] Updated weights for policy 0, policy_version 93120 (0.0004) [2023-03-08 04:38:03,954][321237] Updated weights for policy 0, policy_version 93200 (0.0004) [2023-03-08 04:38:04,594][320945] Fps is (10 sec: 13516.7, 60 sec: 12629.3, 300 sec: 12163.0). Total num frames: 47726592. Throughput: 0: 12618.5. Samples: 47695848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:38:04,595][320945] Avg episode reward: [(0, '4865.045')] [2023-03-08 04:38:07,125][321237] Updated weights for policy 0, policy_version 93280 (0.0004) [2023-03-08 04:38:09,594][320945] Fps is (10 sec: 13107.2, 60 sec: 12697.6, 300 sec: 12149.1). Total num frames: 47788032. Throughput: 0: 12682.6. Samples: 47774484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:38:09,595][320945] Avg episode reward: [(0, '4816.124')] [2023-03-08 04:38:09,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000093336_47788032.pth... [2023-03-08 04:38:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000092584_47403008.pth [2023-03-08 04:38:10,371][321237] Updated weights for policy 0, policy_version 93360 (0.0004) [2023-03-08 04:38:13,877][321237] Updated weights for policy 0, policy_version 93440 (0.0003) [2023-03-08 04:38:14,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12629.3, 300 sec: 12149.1). Total num frames: 47849472. Throughput: 0: 12575.3. Samples: 47846016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:38:14,595][320945] Avg episode reward: [(0, '4861.898')] [2023-03-08 04:38:17,177][321237] Updated weights for policy 0, policy_version 93520 (0.0004) [2023-03-08 04:38:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12121.4). Total num frames: 47906816. Throughput: 0: 12608.4. Samples: 47883104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:38:19,595][320945] Avg episode reward: [(0, '4861.850')] [2023-03-08 04:38:20,624][321237] Updated weights for policy 0, policy_version 93600 (0.0005) [2023-03-08 04:38:24,240][321237] Updated weights for policy 0, policy_version 93680 (0.0005) [2023-03-08 04:38:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12135.3). Total num frames: 47968256. Throughput: 0: 12590.5. Samples: 47953324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:38:24,595][320945] Avg episode reward: [(0, '4817.425')] [2023-03-08 04:38:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000093688_47968256.pth... [2023-03-08 04:38:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000092960_47595520.pth [2023-03-08 04:38:27,636][321237] Updated weights for policy 0, policy_version 93760 (0.0004) [2023-03-08 04:38:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12424.5, 300 sec: 12135.3). Total num frames: 48025600. Throughput: 0: 12513.1. Samples: 48023512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:38:29,595][320945] Avg episode reward: [(0, '4860.729')] [2023-03-08 04:38:31,171][321237] Updated weights for policy 0, policy_version 93840 (0.0004) [2023-03-08 04:38:34,586][321237] Updated weights for policy 0, policy_version 93920 (0.0003) [2023-03-08 04:38:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 12424.5, 300 sec: 12149.2). Total num frames: 48087040. Throughput: 0: 12410.8. Samples: 48058432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:38:34,595][320945] Avg episode reward: [(0, '4819.630')] [2023-03-08 04:38:37,964][321237] Updated weights for policy 0, policy_version 94000 (0.0003) [2023-03-08 04:38:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12135.3). Total num frames: 48144384. Throughput: 0: 12295.3. Samples: 48132064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:38:39,595][320945] Avg episode reward: [(0, '4819.358')] [2023-03-08 04:38:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000094032_48144384.pth... [2023-03-08 04:38:39,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000093336_47788032.pth [2023-03-08 04:38:41,311][321237] Updated weights for policy 0, policy_version 94080 (0.0003) [2023-03-08 04:38:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12135.3). Total num frames: 48205824. Throughput: 0: 12150.8. Samples: 48202948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:38:44,595][320945] Avg episode reward: [(0, '4861.057')] [2023-03-08 04:38:44,862][321237] Updated weights for policy 0, policy_version 94160 (0.0005) [2023-03-08 04:38:48,450][321237] Updated weights for policy 0, policy_version 94240 (0.0005) [2023-03-08 04:38:49,594][320945] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12135.3). Total num frames: 48263168. Throughput: 0: 12057.3. Samples: 48238428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:38:49,595][320945] Avg episode reward: [(0, '4860.985')] [2023-03-08 04:38:51,920][321237] Updated weights for policy 0, policy_version 94320 (0.0004) [2023-03-08 04:38:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12135.3). Total num frames: 48324608. Throughput: 0: 11880.4. Samples: 48309104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:38:54,595][320945] Avg episode reward: [(0, '4861.085')] [2023-03-08 04:38:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000094384_48324608.pth... [2023-03-08 04:38:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000093688_47968256.pth [2023-03-08 04:38:55,099][321237] Updated weights for policy 0, policy_version 94400 (0.0003) [2023-03-08 04:38:58,408][321237] Updated weights for policy 0, policy_version 94480 (0.0004) [2023-03-08 04:38:59,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12149.2). Total num frames: 48386048. Throughput: 0: 11983.5. Samples: 48385272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:38:59,595][320945] Avg episode reward: [(0, '4861.493')] [2023-03-08 04:39:01,597][321237] Updated weights for policy 0, policy_version 94560 (0.0003) [2023-03-08 04:39:04,594][320945] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 12149.2). Total num frames: 48447488. Throughput: 0: 11995.7. Samples: 48422912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:39:04,595][320945] Avg episode reward: [(0, '4863.716')] [2023-03-08 04:39:05,005][321237] Updated weights for policy 0, policy_version 94640 (0.0003) [2023-03-08 04:39:08,377][321237] Updated weights for policy 0, policy_version 94720 (0.0005) [2023-03-08 04:39:09,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 12163.0). Total num frames: 48508928. Throughput: 0: 12051.6. Samples: 48495644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:39:09,595][320945] Avg episode reward: [(0, '4861.395')] [2023-03-08 04:39:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000094744_48508928.pth... [2023-03-08 04:39:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000094032_48144384.pth [2023-03-08 04:39:11,824][321237] Updated weights for policy 0, policy_version 94800 (0.0005) [2023-03-08 04:39:14,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12176.9). Total num frames: 48570368. Throughput: 0: 12068.1. Samples: 48566576. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:39:14,595][320945] Avg episode reward: [(0, '4861.353')] [2023-03-08 04:39:15,314][321237] Updated weights for policy 0, policy_version 94880 (0.0005) [2023-03-08 04:39:18,703][321237] Updated weights for policy 0, policy_version 94960 (0.0005) [2023-03-08 04:39:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12176.9). Total num frames: 48627712. Throughput: 0: 12073.8. Samples: 48601752. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:39:19,595][320945] Avg episode reward: [(0, '4862.386')] [2023-03-08 04:39:22,006][321237] Updated weights for policy 0, policy_version 95040 (0.0005) [2023-03-08 04:39:24,594][320945] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12163.0). Total num frames: 48689152. Throughput: 0: 12102.5. Samples: 48676676. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:39:24,595][320945] Avg episode reward: [(0, '4857.961')] [2023-03-08 04:39:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000095096_48689152.pth... [2023-03-08 04:39:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000094384_48324608.pth [2023-03-08 04:39:25,360][321237] Updated weights for policy 0, policy_version 95120 (0.0005) [2023-03-08 04:39:28,824][321237] Updated weights for policy 0, policy_version 95200 (0.0005) [2023-03-08 04:39:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12149.2). Total num frames: 48750592. Throughput: 0: 12101.1. Samples: 48747496. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:39:29,595][320945] Avg episode reward: [(0, '4862.680')] [2023-03-08 04:39:32,297][321237] Updated weights for policy 0, policy_version 95280 (0.0005) [2023-03-08 04:39:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12135.3). Total num frames: 48807936. Throughput: 0: 12109.6. Samples: 48783360. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:39:34,595][320945] Avg episode reward: [(0, '4861.572')] [2023-03-08 04:39:35,854][321237] Updated weights for policy 0, policy_version 95360 (0.0005) [2023-03-08 04:39:39,376][321237] Updated weights for policy 0, policy_version 95440 (0.0005) [2023-03-08 04:39:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 12014.9, 300 sec: 12107.5). Total num frames: 48865280. Throughput: 0: 12078.5. Samples: 48852636. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:39:39,595][320945] Avg episode reward: [(0, '4860.736')] [2023-03-08 04:39:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000095440_48865280.pth... [2023-03-08 04:39:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000094744_48508928.pth [2023-03-08 04:39:42,887][321237] Updated weights for policy 0, policy_version 95520 (0.0003) [2023-03-08 04:39:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 12093.6). Total num frames: 48922624. Throughput: 0: 11942.7. Samples: 48922696. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:39:44,598][320945] Avg episode reward: [(0, '4863.841')] [2023-03-08 04:39:46,308][321237] Updated weights for policy 0, policy_version 95600 (0.0003) [2023-03-08 04:39:49,594][320945] Fps is (10 sec: 11878.6, 60 sec: 12014.9, 300 sec: 12079.7). Total num frames: 48984064. Throughput: 0: 11924.1. Samples: 48959496. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:39:49,605][320945] Avg episode reward: [(0, '4857.927')] [2023-03-08 04:39:49,695][321237] Updated weights for policy 0, policy_version 95680 (0.0004) [2023-03-08 04:39:53,244][321237] Updated weights for policy 0, policy_version 95760 (0.0005) [2023-03-08 04:39:54,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12065.8). Total num frames: 49041408. Throughput: 0: 11856.6. Samples: 49029192. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:39:54,605][320945] Avg episode reward: [(0, '4859.153')] [2023-03-08 04:39:54,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000095784_49041408.pth... [2023-03-08 04:39:54,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000095096_48689152.pth [2023-03-08 04:39:56,807][321237] Updated weights for policy 0, policy_version 95840 (0.0005) [2023-03-08 04:39:59,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 12065.8). Total num frames: 49102848. Throughput: 0: 11828.4. Samples: 49098856. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:39:59,605][320945] Avg episode reward: [(0, '4859.385')] [2023-03-08 04:40:00,186][321237] Updated weights for policy 0, policy_version 95920 (0.0005) [2023-03-08 04:40:03,340][321237] Updated weights for policy 0, policy_version 96000 (0.0005) [2023-03-08 04:40:04,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11946.7, 300 sec: 12079.7). Total num frames: 49164288. Throughput: 0: 11912.7. Samples: 49137824. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:40:04,605][320945] Avg episode reward: [(0, '4863.566')] [2023-03-08 04:40:06,654][321237] Updated weights for policy 0, policy_version 96080 (0.0004) [2023-03-08 04:40:09,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 12093.6). Total num frames: 49225728. Throughput: 0: 11911.5. Samples: 49212692. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 04:40:09,605][320945] Avg episode reward: [(0, '4861.714')] [2023-03-08 04:40:09,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000096144_49225728.pth... [2023-03-08 04:40:09,612][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000095440_48865280.pth [2023-03-08 04:40:10,064][321237] Updated weights for policy 0, policy_version 96160 (0.0005) [2023-03-08 04:40:13,590][321237] Updated weights for policy 0, policy_version 96240 (0.0005) [2023-03-08 04:40:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12079.7). Total num frames: 49283072. Throughput: 0: 11901.9. Samples: 49283080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:40:14,605][320945] Avg episode reward: [(0, '4863.176')] [2023-03-08 04:40:17,211][321237] Updated weights for policy 0, policy_version 96320 (0.0005) [2023-03-08 04:40:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 12079.7). Total num frames: 49340416. Throughput: 0: 11839.6. Samples: 49316144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:40:19,605][320945] Avg episode reward: [(0, '4861.526')] [2023-03-08 04:40:20,865][321237] Updated weights for policy 0, policy_version 96400 (0.0005) [2023-03-08 04:40:24,562][321237] Updated weights for policy 0, policy_version 96480 (0.0005) [2023-03-08 04:40:24,594][320945] Fps is (10 sec: 11468.5, 60 sec: 11810.1, 300 sec: 12065.8). Total num frames: 49397760. Throughput: 0: 11796.5. Samples: 49383480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:40:24,605][320945] Avg episode reward: [(0, '4863.126')] [2023-03-08 04:40:24,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000096480_49397760.pth... [2023-03-08 04:40:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000095784_49041408.pth [2023-03-08 04:40:28,134][321237] Updated weights for policy 0, policy_version 96560 (0.0005) [2023-03-08 04:40:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 12024.2). Total num frames: 49451008. Throughput: 0: 11741.7. Samples: 49451072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:40:29,605][320945] Avg episode reward: [(0, '4862.636')] [2023-03-08 04:40:31,837][321237] Updated weights for policy 0, policy_version 96640 (0.0004) [2023-03-08 04:40:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11673.6, 300 sec: 12024.2). Total num frames: 49508352. Throughput: 0: 11664.4. Samples: 49484396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:40:34,605][320945] Avg episode reward: [(0, '4814.209')] [2023-03-08 04:40:35,462][321237] Updated weights for policy 0, policy_version 96720 (0.0005) [2023-03-08 04:40:39,064][321237] Updated weights for policy 0, policy_version 96800 (0.0005) [2023-03-08 04:40:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 12024.2). Total num frames: 49565696. Throughput: 0: 11634.0. Samples: 49552720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:40:39,605][320945] Avg episode reward: [(0, '4865.683')] [2023-03-08 04:40:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000096808_49565696.pth... [2023-03-08 04:40:39,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000096144_49225728.pth [2023-03-08 04:40:42,680][321237] Updated weights for policy 0, policy_version 96880 (0.0005) [2023-03-08 04:40:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11996.4). Total num frames: 49623040. Throughput: 0: 11590.2. Samples: 49620416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:40:44,605][320945] Avg episode reward: [(0, '4863.687')] [2023-03-08 04:40:46,353][321237] Updated weights for policy 0, policy_version 96960 (0.0005) [2023-03-08 04:40:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11982.5). Total num frames: 49680384. Throughput: 0: 11480.6. Samples: 49654452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:40:49,595][320945] Avg episode reward: [(0, '4855.711')] [2023-03-08 04:40:49,946][321237] Updated weights for policy 0, policy_version 97040 (0.0005) [2023-03-08 04:40:53,587][321237] Updated weights for policy 0, policy_version 97120 (0.0005) [2023-03-08 04:40:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11968.7). Total num frames: 49733632. Throughput: 0: 11306.1. Samples: 49721468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:40:54,595][320945] Avg episode reward: [(0, '4864.450')] [2023-03-08 04:40:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000097136_49733632.pth... [2023-03-08 04:40:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000096480_49397760.pth [2023-03-08 04:40:57,347][321237] Updated weights for policy 0, policy_version 97200 (0.0005) [2023-03-08 04:40:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11968.7). Total num frames: 49790976. Throughput: 0: 11221.2. Samples: 49788032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:40:59,595][320945] Avg episode reward: [(0, '4817.487')] [2023-03-08 04:41:00,938][321237] Updated weights for policy 0, policy_version 97280 (0.0004) [2023-03-08 04:41:04,364][321237] Updated weights for policy 0, policy_version 97360 (0.0005) [2023-03-08 04:41:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11968.7). Total num frames: 49848320. Throughput: 0: 11278.8. Samples: 49823692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:41:04,595][320945] Avg episode reward: [(0, '4865.110')] [2023-03-08 04:41:07,620][321237] Updated weights for policy 0, policy_version 97440 (0.0004) [2023-03-08 04:41:09,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11400.5, 300 sec: 11982.5). Total num frames: 49909760. Throughput: 0: 11422.1. Samples: 49897472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:41:09,595][320945] Avg episode reward: [(0, '4862.870')] [2023-03-08 04:41:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000097480_49909760.pth... [2023-03-08 04:41:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000096808_49565696.pth [2023-03-08 04:41:11,033][321237] Updated weights for policy 0, policy_version 97520 (0.0004) [2023-03-08 04:41:14,327][321237] Updated weights for policy 0, policy_version 97600 (0.0004) [2023-03-08 04:41:14,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11468.8, 300 sec: 11996.4). Total num frames: 49971200. Throughput: 0: 11548.3. Samples: 49970744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:41:14,595][320945] Avg episode reward: [(0, '4820.986')] [2023-03-08 04:41:17,724][321237] Updated weights for policy 0, policy_version 97680 (0.0005) [2023-03-08 04:41:19,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11537.1, 300 sec: 12010.3). Total num frames: 50032640. Throughput: 0: 11603.6. Samples: 50006556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:41:19,595][320945] Avg episode reward: [(0, '4862.899')] [2023-03-08 04:41:20,948][321237] Updated weights for policy 0, policy_version 97760 (0.0004) [2023-03-08 04:41:24,264][321237] Updated weights for policy 0, policy_version 97840 (0.0004) [2023-03-08 04:41:24,594][320945] Fps is (10 sec: 12697.7, 60 sec: 11673.6, 300 sec: 12038.1). Total num frames: 50098176. Throughput: 0: 11757.2. Samples: 50081792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:41:24,595][320945] Avg episode reward: [(0, '4861.331')] [2023-03-08 04:41:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000097848_50098176.pth... [2023-03-08 04:41:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000097136_49733632.pth [2023-03-08 04:41:27,621][321237] Updated weights for policy 0, policy_version 97920 (0.0004) [2023-03-08 04:41:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 12038.1). Total num frames: 50155520. Throughput: 0: 11891.4. Samples: 50155528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:41:29,595][320945] Avg episode reward: [(0, '4861.638')] [2023-03-08 04:41:30,993][321237] Updated weights for policy 0, policy_version 98000 (0.0005) [2023-03-08 04:41:34,276][321237] Updated weights for policy 0, policy_version 98080 (0.0004) [2023-03-08 04:41:34,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 12052.0). Total num frames: 50221056. Throughput: 0: 11942.2. Samples: 50191852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:41:34,595][320945] Avg episode reward: [(0, '4862.534')] [2023-03-08 04:41:37,543][321237] Updated weights for policy 0, policy_version 98160 (0.0004) [2023-03-08 04:41:39,594][320945] Fps is (10 sec: 12697.5, 60 sec: 11946.7, 300 sec: 12065.8). Total num frames: 50282496. Throughput: 0: 12105.0. Samples: 50266192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:41:39,595][320945] Avg episode reward: [(0, '4862.946')] [2023-03-08 04:41:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000098208_50282496.pth... [2023-03-08 04:41:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000097480_49909760.pth [2023-03-08 04:41:40,841][321237] Updated weights for policy 0, policy_version 98240 (0.0004) [2023-03-08 04:41:44,108][321237] Updated weights for policy 0, policy_version 98320 (0.0004) [2023-03-08 04:41:44,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12079.7). Total num frames: 50343936. Throughput: 0: 12306.8. Samples: 50341840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:41:44,595][320945] Avg episode reward: [(0, '4862.037')] [2023-03-08 04:41:47,714][321237] Updated weights for policy 0, policy_version 98400 (0.0005) [2023-03-08 04:41:49,594][320945] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12065.8). Total num frames: 50401280. Throughput: 0: 12282.3. Samples: 50376396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:41:49,595][320945] Avg episode reward: [(0, '4863.811')] [2023-03-08 04:41:51,361][321237] Updated weights for policy 0, policy_version 98480 (0.0005) [2023-03-08 04:41:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 12014.9, 300 sec: 12024.2). Total num frames: 50454528. Throughput: 0: 12118.0. Samples: 50442784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:41:54,595][320945] Avg episode reward: [(0, '4862.737')] [2023-03-08 04:41:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000098544_50454528.pth... [2023-03-08 04:41:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000097848_50098176.pth [2023-03-08 04:41:55,079][321237] Updated weights for policy 0, policy_version 98560 (0.0005) [2023-03-08 04:41:58,715][321237] Updated weights for policy 0, policy_version 98640 (0.0005) [2023-03-08 04:41:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 12014.9, 300 sec: 12010.3). Total num frames: 50511872. Throughput: 0: 11990.8. Samples: 50510328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:41:59,595][320945] Avg episode reward: [(0, '4863.715')] [2023-03-08 04:42:02,279][321237] Updated weights for policy 0, policy_version 98720 (0.0005) [2023-03-08 04:42:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 12014.9, 300 sec: 12010.3). Total num frames: 50569216. Throughput: 0: 11957.6. Samples: 50544648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:42:04,595][320945] Avg episode reward: [(0, '4863.398')] [2023-03-08 04:42:05,800][321237] Updated weights for policy 0, policy_version 98800 (0.0005) [2023-03-08 04:42:09,422][321237] Updated weights for policy 0, policy_version 98880 (0.0005) [2023-03-08 04:42:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11982.5). Total num frames: 50626560. Throughput: 0: 11832.9. Samples: 50614272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:42:09,595][320945] Avg episode reward: [(0, '4858.075')] [2023-03-08 04:42:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000098880_50626560.pth... [2023-03-08 04:42:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000098208_50282496.pth [2023-03-08 04:42:13,083][321237] Updated weights for policy 0, policy_version 98960 (0.0005) [2023-03-08 04:42:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11954.8). Total num frames: 50683904. Throughput: 0: 11683.6. Samples: 50681292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:42:14,595][320945] Avg episode reward: [(0, '4863.106')] [2023-03-08 04:42:16,578][321237] Updated weights for policy 0, policy_version 99040 (0.0005) [2023-03-08 04:42:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11954.8). Total num frames: 50745344. Throughput: 0: 11664.3. Samples: 50716744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:42:19,595][320945] Avg episode reward: [(0, '4862.726')] [2023-03-08 04:42:19,854][321237] Updated weights for policy 0, policy_version 99120 (0.0004) [2023-03-08 04:42:23,193][321237] Updated weights for policy 0, policy_version 99200 (0.0004) [2023-03-08 04:42:24,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11954.8). Total num frames: 50806784. Throughput: 0: 11661.7. Samples: 50790968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:42:24,595][320945] Avg episode reward: [(0, '4861.166')] [2023-03-08 04:42:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000099232_50806784.pth... [2023-03-08 04:42:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000098544_50454528.pth [2023-03-08 04:42:26,498][321237] Updated weights for policy 0, policy_version 99280 (0.0004) [2023-03-08 04:42:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11954.8). Total num frames: 50868224. Throughput: 0: 11643.7. Samples: 50865808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:42:29,595][320945] Avg episode reward: [(0, '4862.053')] [2023-03-08 04:42:29,792][321237] Updated weights for policy 0, policy_version 99360 (0.0004) [2023-03-08 04:42:33,073][321237] Updated weights for policy 0, policy_version 99440 (0.0004) [2023-03-08 04:42:34,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11954.8). Total num frames: 50929664. Throughput: 0: 11721.0. Samples: 50903840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:42:34,595][320945] Avg episode reward: [(0, '4861.791')] [2023-03-08 04:42:36,501][321237] Updated weights for policy 0, policy_version 99520 (0.0004) [2023-03-08 04:42:39,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11954.8). Total num frames: 50991104. Throughput: 0: 11849.1. Samples: 50975992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:42:39,595][320945] Avg episode reward: [(0, '4861.698')] [2023-03-08 04:42:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000099592_50991104.pth... [2023-03-08 04:42:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000098880_50626560.pth [2023-03-08 04:42:39,752][321237] Updated weights for policy 0, policy_version 99600 (0.0004) [2023-03-08 04:42:43,042][321237] Updated weights for policy 0, policy_version 99680 (0.0005) [2023-03-08 04:42:44,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11810.1, 300 sec: 11940.9). Total num frames: 51052544. Throughput: 0: 12020.5. Samples: 51051252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:42:44,595][320945] Avg episode reward: [(0, '4861.824')] [2023-03-08 04:42:45,030][321188] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000004 [2023-03-08 04:42:46,379][321237] Updated weights for policy 0, policy_version 99760 (0.0004) [2023-03-08 04:42:49,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11878.4, 300 sec: 11940.9). Total num frames: 51113984. Throughput: 0: 12075.8. Samples: 51088060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:42:49,595][320945] Avg episode reward: [(0, '4861.464')] [2023-03-08 04:42:49,821][321237] Updated weights for policy 0, policy_version 99840 (0.0004) [2023-03-08 04:42:53,116][321237] Updated weights for policy 0, policy_version 99920 (0.0004) [2023-03-08 04:42:54,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 11927.0). Total num frames: 51175424. Throughput: 0: 12143.1. Samples: 51160712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:42:54,595][320945] Avg episode reward: [(0, '4817.304')] [2023-03-08 04:42:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000099952_51175424.pth... [2023-03-08 04:42:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000099232_50806784.pth [2023-03-08 04:42:56,318][321237] Updated weights for policy 0, policy_version 100000 (0.0005) [2023-03-08 04:42:59,472][321237] Updated weights for policy 0, policy_version 100080 (0.0004) [2023-03-08 04:42:59,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 11913.1). Total num frames: 51240960. Throughput: 0: 12371.8. Samples: 51238024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:42:59,595][320945] Avg episode reward: [(0, '4863.448')] [2023-03-08 04:43:02,826][321237] Updated weights for policy 0, policy_version 100160 (0.0004) [2023-03-08 04:43:04,594][320945] Fps is (10 sec: 12697.7, 60 sec: 12219.7, 300 sec: 11913.1). Total num frames: 51302400. Throughput: 0: 12409.5. Samples: 51275172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:43:04,595][320945] Avg episode reward: [(0, '4863.209')] [2023-03-08 04:43:06,173][321237] Updated weights for policy 0, policy_version 100240 (0.0004) [2023-03-08 04:43:09,594][320945] Fps is (10 sec: 11878.5, 60 sec: 12219.8, 300 sec: 11899.2). Total num frames: 51359744. Throughput: 0: 12375.2. Samples: 51347852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:43:09,594][320945] Avg episode reward: [(0, '4867.016')] [2023-03-08 04:43:09,601][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000100320_51363840.pth... [2023-03-08 04:43:09,601][321237] Updated weights for policy 0, policy_version 100320 (0.0004) [2023-03-08 04:43:09,602][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000099592_50991104.pth [2023-03-08 04:43:13,016][321237] Updated weights for policy 0, policy_version 100400 (0.0004) [2023-03-08 04:43:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 11913.1). Total num frames: 51421184. Throughput: 0: 12307.2. Samples: 51419632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:43:14,595][320945] Avg episode reward: [(0, '4865.833')] [2023-03-08 04:43:16,471][321237] Updated weights for policy 0, policy_version 100480 (0.0004) [2023-03-08 04:43:19,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 11913.1). Total num frames: 51482624. Throughput: 0: 12244.1. Samples: 51454824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:43:19,595][320945] Avg episode reward: [(0, '4865.253')] [2023-03-08 04:43:19,762][321237] Updated weights for policy 0, policy_version 100560 (0.0004) [2023-03-08 04:43:23,058][321237] Updated weights for policy 0, policy_version 100640 (0.0004) [2023-03-08 04:43:24,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 11927.0). Total num frames: 51544064. Throughput: 0: 12323.5. Samples: 51530548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:43:24,595][320945] Avg episode reward: [(0, '4863.166')] [2023-03-08 04:43:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000100672_51544064.pth... [2023-03-08 04:43:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000099952_51175424.pth [2023-03-08 04:43:26,360][321237] Updated weights for policy 0, policy_version 100720 (0.0004) [2023-03-08 04:43:29,594][320945] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 11927.0). Total num frames: 51605504. Throughput: 0: 12239.6. Samples: 51602032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:43:29,595][320945] Avg episode reward: [(0, '4862.576')] [2023-03-08 04:43:29,870][321237] Updated weights for policy 0, policy_version 100800 (0.0004) [2023-03-08 04:43:33,168][321237] Updated weights for policy 0, policy_version 100880 (0.0004) [2023-03-08 04:43:34,594][320945] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 11940.9). Total num frames: 51666944. Throughput: 0: 12228.5. Samples: 51638344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:43:34,595][320945] Avg episode reward: [(0, '4861.062')] [2023-03-08 04:43:36,676][321237] Updated weights for policy 0, policy_version 100960 (0.0004) [2023-03-08 04:43:39,594][320945] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 11927.0). Total num frames: 51724288. Throughput: 0: 12195.8. Samples: 51709524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:43:39,595][320945] Avg episode reward: [(0, '4863.275')] [2023-03-08 04:43:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000101024_51724288.pth... [2023-03-08 04:43:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000100320_51363840.pth [2023-03-08 04:43:40,245][321237] Updated weights for policy 0, policy_version 101040 (0.0005) [2023-03-08 04:43:43,886][321237] Updated weights for policy 0, policy_version 101120 (0.0005) [2023-03-08 04:43:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12151.5, 300 sec: 11927.0). Total num frames: 51781632. Throughput: 0: 11990.8. Samples: 51777608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:43:44,595][320945] Avg episode reward: [(0, '4862.795')] [2023-03-08 04:43:47,429][321237] Updated weights for policy 0, policy_version 101200 (0.0005) [2023-03-08 04:43:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 12083.2, 300 sec: 11913.1). Total num frames: 51838976. Throughput: 0: 11939.7. Samples: 51812460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:43:49,595][320945] Avg episode reward: [(0, '4863.706')] [2023-03-08 04:43:51,052][321237] Updated weights for policy 0, policy_version 101280 (0.0005) [2023-03-08 04:43:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11946.7, 300 sec: 11885.3). Total num frames: 51892224. Throughput: 0: 11832.5. Samples: 51880316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:43:54,594][320945] Avg episode reward: [(0, '4862.455')] [2023-03-08 04:43:54,647][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000101360_51896320.pth... [2023-03-08 04:43:54,648][321237] Updated weights for policy 0, policy_version 101360 (0.0005) [2023-03-08 04:43:54,648][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000100672_51544064.pth [2023-03-08 04:43:58,253][321237] Updated weights for policy 0, policy_version 101440 (0.0005) [2023-03-08 04:43:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11871.5). Total num frames: 51949568. Throughput: 0: 11771.7. Samples: 51949360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:43:59,595][320945] Avg episode reward: [(0, '4863.173')] [2023-03-08 04:44:01,903][321237] Updated weights for policy 0, policy_version 101520 (0.0005) [2023-03-08 04:44:04,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11857.6). Total num frames: 52006912. Throughput: 0: 11723.9. Samples: 51982400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:44:04,595][320945] Avg episode reward: [(0, '4863.626')] [2023-03-08 04:44:05,431][321237] Updated weights for policy 0, policy_version 101600 (0.0005) [2023-03-08 04:44:09,064][321237] Updated weights for policy 0, policy_version 101680 (0.0005) [2023-03-08 04:44:09,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11741.8, 300 sec: 11843.7). Total num frames: 52064256. Throughput: 0: 11587.1. Samples: 52051968. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:44:09,595][320945] Avg episode reward: [(0, '4862.506')] [2023-03-08 04:44:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000101688_52064256.pth... [2023-03-08 04:44:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000101024_51724288.pth [2023-03-08 04:44:12,751][321237] Updated weights for policy 0, policy_version 101760 (0.0005) [2023-03-08 04:44:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11843.7). Total num frames: 52121600. Throughput: 0: 11465.6. Samples: 52117984. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:44:14,595][320945] Avg episode reward: [(0, '4863.640')] [2023-03-08 04:44:16,400][321237] Updated weights for policy 0, policy_version 101840 (0.0005) [2023-03-08 04:44:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11537.1, 300 sec: 11815.9). Total num frames: 52174848. Throughput: 0: 11402.5. Samples: 52151456. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:44:19,595][320945] Avg episode reward: [(0, '4859.730')] [2023-03-08 04:44:20,142][321237] Updated weights for policy 0, policy_version 101920 (0.0005) [2023-03-08 04:44:23,771][321237] Updated weights for policy 0, policy_version 102000 (0.0005) [2023-03-08 04:44:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11802.0). Total num frames: 52232192. Throughput: 0: 11313.4. Samples: 52218628. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:44:24,595][320945] Avg episode reward: [(0, '4863.663')] [2023-03-08 04:44:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000102016_52232192.pth... [2023-03-08 04:44:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000101360_51896320.pth [2023-03-08 04:44:27,409][321237] Updated weights for policy 0, policy_version 102080 (0.0005) [2023-03-08 04:44:29,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11802.0). Total num frames: 52289536. Throughput: 0: 11286.7. Samples: 52285512. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:44:29,595][320945] Avg episode reward: [(0, '4864.465')] [2023-03-08 04:44:30,993][321237] Updated weights for policy 0, policy_version 102160 (0.0005) [2023-03-08 04:44:34,500][321237] Updated weights for policy 0, policy_version 102240 (0.0005) [2023-03-08 04:44:34,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11802.0). Total num frames: 52346880. Throughput: 0: 11312.3. Samples: 52321512. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:44:34,595][320945] Avg episode reward: [(0, '4861.594')] [2023-03-08 04:44:38,130][321237] Updated weights for policy 0, policy_version 102320 (0.0005) [2023-03-08 04:44:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11802.0). Total num frames: 52404224. Throughput: 0: 11314.4. Samples: 52389464. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:44:39,595][320945] Avg episode reward: [(0, '4864.183')] [2023-03-08 04:44:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000102352_52404224.pth... [2023-03-08 04:44:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000101688_52064256.pth [2023-03-08 04:44:41,764][321237] Updated weights for policy 0, policy_version 102400 (0.0005) [2023-03-08 04:44:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11774.3). Total num frames: 52457472. Throughput: 0: 11291.7. Samples: 52457488. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:44:44,605][320945] Avg episode reward: [(0, '4861.487')] [2023-03-08 04:44:45,291][321237] Updated weights for policy 0, policy_version 102480 (0.0005) [2023-03-08 04:44:48,956][321237] Updated weights for policy 0, policy_version 102560 (0.0005) [2023-03-08 04:44:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11774.3). Total num frames: 52514816. Throughput: 0: 11316.0. Samples: 52491620. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:44:49,605][320945] Avg episode reward: [(0, '4864.640')] [2023-03-08 04:44:52,484][321237] Updated weights for policy 0, policy_version 102640 (0.0005) [2023-03-08 04:44:54,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11774.3). Total num frames: 52576256. Throughput: 0: 11300.4. Samples: 52560484. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:44:54,605][320945] Avg episode reward: [(0, '4860.490')] [2023-03-08 04:44:54,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000102688_52576256.pth... [2023-03-08 04:44:54,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000102016_52232192.pth [2023-03-08 04:44:55,931][321237] Updated weights for policy 0, policy_version 102720 (0.0005) [2023-03-08 04:44:59,250][321237] Updated weights for policy 0, policy_version 102800 (0.0004) [2023-03-08 04:44:59,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11468.8, 300 sec: 11774.3). Total num frames: 52637696. Throughput: 0: 11459.5. Samples: 52633664. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:44:59,605][320945] Avg episode reward: [(0, '4863.512')] [2023-03-08 04:45:02,442][321237] Updated weights for policy 0, policy_version 102880 (0.0004) [2023-03-08 04:45:04,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11537.1, 300 sec: 11774.3). Total num frames: 52699136. Throughput: 0: 11575.6. Samples: 52672360. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:45:04,605][320945] Avg episode reward: [(0, '4863.009')] [2023-03-08 04:45:05,797][321237] Updated weights for policy 0, policy_version 102960 (0.0004) [2023-03-08 04:45:09,081][321237] Updated weights for policy 0, policy_version 103040 (0.0005) [2023-03-08 04:45:09,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11788.1). Total num frames: 52760576. Throughput: 0: 11741.3. Samples: 52746988. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:45:09,605][320945] Avg episode reward: [(0, '4860.496')] [2023-03-08 04:45:09,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000103048_52760576.pth... [2023-03-08 04:45:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000102352_52404224.pth [2023-03-08 04:45:12,307][321237] Updated weights for policy 0, policy_version 103120 (0.0004) [2023-03-08 04:45:14,594][320945] Fps is (10 sec: 12697.6, 60 sec: 11741.9, 300 sec: 11815.9). Total num frames: 52826112. Throughput: 0: 11923.7. Samples: 52822080. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:45:14,605][320945] Avg episode reward: [(0, '4864.864')] [2023-03-08 04:45:15,591][321237] Updated weights for policy 0, policy_version 103200 (0.0005) [2023-03-08 04:45:18,910][321237] Updated weights for policy 0, policy_version 103280 (0.0005) [2023-03-08 04:45:19,594][320945] Fps is (10 sec: 12697.6, 60 sec: 11878.4, 300 sec: 11829.8). Total num frames: 52887552. Throughput: 0: 11928.0. Samples: 52858272. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:45:19,605][320945] Avg episode reward: [(0, '4863.524')] [2023-03-08 04:45:22,175][321237] Updated weights for policy 0, policy_version 103360 (0.0004) [2023-03-08 04:45:24,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11946.6, 300 sec: 11857.6). Total num frames: 52948992. Throughput: 0: 12098.6. Samples: 52933900. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:45:24,605][320945] Avg episode reward: [(0, '4863.800')] [2023-03-08 04:45:24,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000103416_52948992.pth... [2023-03-08 04:45:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000102688_52576256.pth [2023-03-08 04:45:25,575][321237] Updated weights for policy 0, policy_version 103440 (0.0005) [2023-03-08 04:45:28,949][321237] Updated weights for policy 0, policy_version 103520 (0.0005) [2023-03-08 04:45:29,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 11857.6). Total num frames: 53006336. Throughput: 0: 12197.1. Samples: 53006356. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:45:29,605][320945] Avg episode reward: [(0, '4865.182')] [2023-03-08 04:45:32,249][321237] Updated weights for policy 0, policy_version 103600 (0.0004) [2023-03-08 04:45:34,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11885.3). Total num frames: 53071872. Throughput: 0: 12258.7. Samples: 53043264. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:45:34,605][320945] Avg episode reward: [(0, '4861.311')] [2023-03-08 04:45:35,476][321237] Updated weights for policy 0, policy_version 103680 (0.0004) [2023-03-08 04:45:38,882][321237] Updated weights for policy 0, policy_version 103760 (0.0005) [2023-03-08 04:45:39,594][320945] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 11899.2). Total num frames: 53133312. Throughput: 0: 12378.2. Samples: 53117504. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:45:39,605][320945] Avg episode reward: [(0, '4864.544')] [2023-03-08 04:45:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000103776_53133312.pth... [2023-03-08 04:45:39,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000103048_52760576.pth [2023-03-08 04:45:42,411][321237] Updated weights for policy 0, policy_version 103840 (0.0004) [2023-03-08 04:45:44,594][320945] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 11899.2). Total num frames: 53190656. Throughput: 0: 12304.2. Samples: 53187352. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:45:44,605][320945] Avg episode reward: [(0, '4864.497')] [2023-03-08 04:45:45,928][321237] Updated weights for policy 0, policy_version 103920 (0.0004) [2023-03-08 04:45:49,498][321237] Updated weights for policy 0, policy_version 104000 (0.0005) [2023-03-08 04:45:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 12219.7, 300 sec: 11913.1). Total num frames: 53248000. Throughput: 0: 12231.7. Samples: 53222784. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:45:49,595][320945] Avg episode reward: [(0, '4863.234')] [2023-03-08 04:45:53,000][321237] Updated weights for policy 0, policy_version 104080 (0.0005) [2023-03-08 04:45:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 12151.5, 300 sec: 11913.1). Total num frames: 53305344. Throughput: 0: 12123.5. Samples: 53292544. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:45:54,595][320945] Avg episode reward: [(0, '4863.345')] [2023-03-08 04:45:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000104112_53305344.pth... [2023-03-08 04:45:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000103416_52948992.pth [2023-03-08 04:45:56,529][321237] Updated weights for policy 0, policy_version 104160 (0.0004) [2023-03-08 04:45:59,594][320945] Fps is (10 sec: 11468.7, 60 sec: 12083.2, 300 sec: 11913.1). Total num frames: 53362688. Throughput: 0: 12012.9. Samples: 53362660. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:45:59,595][320945] Avg episode reward: [(0, '4864.569')] [2023-03-08 04:46:00,012][321237] Updated weights for policy 0, policy_version 104240 (0.0004) [2023-03-08 04:46:03,561][321237] Updated weights for policy 0, policy_version 104320 (0.0004) [2023-03-08 04:46:04,594][320945] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11913.1). Total num frames: 53424128. Throughput: 0: 11956.9. Samples: 53396332. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 04:46:04,595][320945] Avg episode reward: [(0, '4858.985')] [2023-03-08 04:46:07,079][321237] Updated weights for policy 0, policy_version 104400 (0.0005) [2023-03-08 04:46:09,594][320945] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 11899.2). Total num frames: 53481472. Throughput: 0: 11855.8. Samples: 53467412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:46:09,595][320945] Avg episode reward: [(0, '4859.987')] [2023-03-08 04:46:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000104456_53481472.pth... [2023-03-08 04:46:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000103776_53133312.pth [2023-03-08 04:46:10,490][321237] Updated weights for policy 0, policy_version 104480 (0.0005) [2023-03-08 04:46:13,934][321237] Updated weights for policy 0, policy_version 104560 (0.0005) [2023-03-08 04:46:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11885.3). Total num frames: 53538816. Throughput: 0: 11832.7. Samples: 53538828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:46:14,595][320945] Avg episode reward: [(0, '4859.974')] [2023-03-08 04:46:17,492][321237] Updated weights for policy 0, policy_version 104640 (0.0005) [2023-03-08 04:46:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11871.5). Total num frames: 53600256. Throughput: 0: 11774.0. Samples: 53573092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:46:19,595][320945] Avg episode reward: [(0, '4863.951')] [2023-03-08 04:46:20,947][321237] Updated weights for policy 0, policy_version 104720 (0.0005) [2023-03-08 04:46:24,399][321237] Updated weights for policy 0, policy_version 104800 (0.0005) [2023-03-08 04:46:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11871.5). Total num frames: 53657600. Throughput: 0: 11701.0. Samples: 53644048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:46:24,595][320945] Avg episode reward: [(0, '4860.754')] [2023-03-08 04:46:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000104800_53657600.pth... [2023-03-08 04:46:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000104112_53305344.pth [2023-03-08 04:46:27,794][321237] Updated weights for policy 0, policy_version 104880 (0.0005) [2023-03-08 04:46:29,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11857.6). Total num frames: 53719040. Throughput: 0: 11741.6. Samples: 53715724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:46:29,595][320945] Avg episode reward: [(0, '4862.984')] [2023-03-08 04:46:31,231][321237] Updated weights for policy 0, policy_version 104960 (0.0004) [2023-03-08 04:46:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11843.7). Total num frames: 53776384. Throughput: 0: 11756.4. Samples: 53751820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:46:34,595][320945] Avg episode reward: [(0, '4856.984')] [2023-03-08 04:46:34,718][321237] Updated weights for policy 0, policy_version 105040 (0.0005) [2023-03-08 04:46:38,276][321237] Updated weights for policy 0, policy_version 105120 (0.0005) [2023-03-08 04:46:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11829.8). Total num frames: 53833728. Throughput: 0: 11753.5. Samples: 53821452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:46:39,594][320945] Avg episode reward: [(0, '4862.986')] [2023-03-08 04:46:39,654][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000105152_53837824.pth... [2023-03-08 04:46:39,656][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000104456_53481472.pth [2023-03-08 04:46:41,757][321237] Updated weights for policy 0, policy_version 105200 (0.0005) [2023-03-08 04:46:44,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11829.8). Total num frames: 53891072. Throughput: 0: 11743.9. Samples: 53891136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:46:44,594][320945] Avg episode reward: [(0, '4861.973')] [2023-03-08 04:46:45,395][321237] Updated weights for policy 0, policy_version 105280 (0.0005) [2023-03-08 04:46:48,944][321237] Updated weights for policy 0, policy_version 105360 (0.0005) [2023-03-08 04:46:49,594][320945] Fps is (10 sec: 11468.6, 60 sec: 11673.6, 300 sec: 11843.7). Total num frames: 53948416. Throughput: 0: 11723.8. Samples: 53923904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:46:49,595][320945] Avg episode reward: [(0, '4861.566')] [2023-03-08 04:46:52,523][321237] Updated weights for policy 0, policy_version 105440 (0.0005) [2023-03-08 04:46:54,594][320945] Fps is (10 sec: 11468.6, 60 sec: 11673.6, 300 sec: 11843.7). Total num frames: 54005760. Throughput: 0: 11691.7. Samples: 53993536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:46:54,595][320945] Avg episode reward: [(0, '4862.535')] [2023-03-08 04:46:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000105480_54005760.pth... [2023-03-08 04:46:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000104800_53657600.pth [2023-03-08 04:46:56,134][321237] Updated weights for policy 0, policy_version 105520 (0.0005) [2023-03-08 04:46:59,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11843.7). Total num frames: 54063104. Throughput: 0: 11650.4. Samples: 54063096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:46:59,595][320945] Avg episode reward: [(0, '4863.684')] [2023-03-08 04:46:59,644][321237] Updated weights for policy 0, policy_version 105600 (0.0004) [2023-03-08 04:47:03,072][321237] Updated weights for policy 0, policy_version 105680 (0.0005) [2023-03-08 04:47:04,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11857.6). Total num frames: 54124544. Throughput: 0: 11702.0. Samples: 54099684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:47:04,595][320945] Avg episode reward: [(0, '4861.971')] [2023-03-08 04:47:06,626][321237] Updated weights for policy 0, policy_version 105760 (0.0004) [2023-03-08 04:47:09,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 11857.6). Total num frames: 54181888. Throughput: 0: 11628.8. Samples: 54167344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:47:09,595][320945] Avg episode reward: [(0, '4861.748')] [2023-03-08 04:47:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000105824_54181888.pth... [2023-03-08 04:47:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000105152_53837824.pth [2023-03-08 04:47:10,317][321237] Updated weights for policy 0, policy_version 105840 (0.0004) [2023-03-08 04:47:13,807][321237] Updated weights for policy 0, policy_version 105920 (0.0003) [2023-03-08 04:47:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11843.7). Total num frames: 54239232. Throughput: 0: 11560.0. Samples: 54235924. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:47:14,604][320945] Avg episode reward: [(0, '4861.717')] [2023-03-08 04:47:17,398][321237] Updated weights for policy 0, policy_version 106000 (0.0004) [2023-03-08 04:47:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11829.8). Total num frames: 54296576. Throughput: 0: 11534.0. Samples: 54270852. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:47:19,605][320945] Avg episode reward: [(0, '4862.366')] [2023-03-08 04:47:21,006][321237] Updated weights for policy 0, policy_version 106080 (0.0005) [2023-03-08 04:47:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11802.0). Total num frames: 54349824. Throughput: 0: 11470.1. Samples: 54337608. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:47:24,605][320945] Avg episode reward: [(0, '4863.216')] [2023-03-08 04:47:24,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000106152_54349824.pth... [2023-03-08 04:47:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000105480_54005760.pth [2023-03-08 04:47:24,704][321237] Updated weights for policy 0, policy_version 106160 (0.0005) [2023-03-08 04:47:28,382][321237] Updated weights for policy 0, policy_version 106240 (0.0005) [2023-03-08 04:47:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11788.1). Total num frames: 54407168. Throughput: 0: 11411.0. Samples: 54404632. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:47:29,605][320945] Avg episode reward: [(0, '4861.944')] [2023-03-08 04:47:32,075][321237] Updated weights for policy 0, policy_version 106320 (0.0005) [2023-03-08 04:47:34,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11760.4). Total num frames: 54460416. Throughput: 0: 11431.8. Samples: 54438336. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:47:34,605][320945] Avg episode reward: [(0, '4863.389')] [2023-03-08 04:47:35,784][321237] Updated weights for policy 0, policy_version 106400 (0.0005) [2023-03-08 04:47:39,523][321237] Updated weights for policy 0, policy_version 106480 (0.0005) [2023-03-08 04:47:39,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11400.5, 300 sec: 11746.5). Total num frames: 54517760. Throughput: 0: 11355.5. Samples: 54504532. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:47:39,605][320945] Avg episode reward: [(0, '4861.063')] [2023-03-08 04:47:39,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000106480_54517760.pth... [2023-03-08 04:47:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000105824_54181888.pth [2023-03-08 04:47:43,234][321237] Updated weights for policy 0, policy_version 106560 (0.0005) [2023-03-08 04:47:44,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11332.2, 300 sec: 11718.7). Total num frames: 54571008. Throughput: 0: 11270.8. Samples: 54570284. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:47:44,605][320945] Avg episode reward: [(0, '4860.703')] [2023-03-08 04:47:47,100][321237] Updated weights for policy 0, policy_version 106640 (0.0005) [2023-03-08 04:47:49,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11264.0, 300 sec: 11691.0). Total num frames: 54624256. Throughput: 0: 11154.1. Samples: 54601620. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:47:49,595][320945] Avg episode reward: [(0, '4861.824')] [2023-03-08 04:47:50,791][321237] Updated weights for policy 0, policy_version 106720 (0.0005) [2023-03-08 04:47:54,163][321237] Updated weights for policy 0, policy_version 106800 (0.0004) [2023-03-08 04:47:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11677.1). Total num frames: 54685696. Throughput: 0: 11184.9. Samples: 54670664. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:47:54,605][320945] Avg episode reward: [(0, '4799.595')] [2023-03-08 04:47:54,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000106808_54685696.pth... [2023-03-08 04:47:54,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000106152_54349824.pth [2023-03-08 04:47:57,585][321237] Updated weights for policy 0, policy_version 106880 (0.0004) [2023-03-08 04:47:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11332.3, 300 sec: 11663.2). Total num frames: 54743040. Throughput: 0: 11262.3. Samples: 54742728. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:47:59,605][320945] Avg episode reward: [(0, '4861.804')] [2023-03-08 04:48:01,056][321237] Updated weights for policy 0, policy_version 106960 (0.0004) [2023-03-08 04:48:04,391][321237] Updated weights for policy 0, policy_version 107040 (0.0004) [2023-03-08 04:48:04,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11332.3, 300 sec: 11677.1). Total num frames: 54804480. Throughput: 0: 11276.5. Samples: 54778296. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:48:04,595][320945] Avg episode reward: [(0, '4861.323')] [2023-03-08 04:48:07,876][321237] Updated weights for policy 0, policy_version 107120 (0.0005) [2023-03-08 04:48:09,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11332.3, 300 sec: 11663.2). Total num frames: 54861824. Throughput: 0: 11377.6. Samples: 54849600. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:48:09,605][320945] Avg episode reward: [(0, '4860.173')] [2023-03-08 04:48:09,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000107152_54861824.pth... [2023-03-08 04:48:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000106480_54517760.pth [2023-03-08 04:48:11,564][321237] Updated weights for policy 0, policy_version 107200 (0.0005) [2023-03-08 04:48:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11663.2). Total num frames: 54923264. Throughput: 0: 11435.7. Samples: 54919240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:48:14,595][320945] Avg episode reward: [(0, '4862.277')] [2023-03-08 04:48:14,889][321237] Updated weights for policy 0, policy_version 107280 (0.0003) [2023-03-08 04:48:18,255][321237] Updated weights for policy 0, policy_version 107360 (0.0004) [2023-03-08 04:48:19,594][320945] Fps is (10 sec: 12288.2, 60 sec: 11468.8, 300 sec: 11663.2). Total num frames: 54984704. Throughput: 0: 11505.8. Samples: 54956096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:48:19,595][320945] Avg episode reward: [(0, '4860.398')] [2023-03-08 04:48:21,610][321237] Updated weights for policy 0, policy_version 107440 (0.0004) [2023-03-08 04:48:24,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11537.1, 300 sec: 11649.3). Total num frames: 55042048. Throughput: 0: 11672.0. Samples: 55029772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:48:24,595][320945] Avg episode reward: [(0, '4859.838')] [2023-03-08 04:48:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000107504_55042048.pth... [2023-03-08 04:48:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000106808_54685696.pth [2023-03-08 04:48:25,009][321237] Updated weights for policy 0, policy_version 107520 (0.0004) [2023-03-08 04:48:28,329][321237] Updated weights for policy 0, policy_version 107600 (0.0004) [2023-03-08 04:48:29,342][321188] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000005 [2023-03-08 04:48:29,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11649.3). Total num frames: 55103488. Throughput: 0: 11825.8. Samples: 55102444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:48:29,595][320945] Avg episode reward: [(0, '4861.392')] [2023-03-08 04:48:31,731][321237] Updated weights for policy 0, policy_version 107680 (0.0005) [2023-03-08 04:48:34,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11741.9, 300 sec: 11663.2). Total num frames: 55164928. Throughput: 0: 11938.7. Samples: 55138860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:48:34,595][320945] Avg episode reward: [(0, '4862.623')] [2023-03-08 04:48:35,070][321237] Updated weights for policy 0, policy_version 107760 (0.0005) [2023-03-08 04:48:38,552][321237] Updated weights for policy 0, policy_version 107840 (0.0005) [2023-03-08 04:48:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11663.2). Total num frames: 55222272. Throughput: 0: 11992.3. Samples: 55210320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:48:39,595][320945] Avg episode reward: [(0, '4858.968')] [2023-03-08 04:48:39,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000107864_55226368.pth... [2023-03-08 04:48:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000107152_54861824.pth [2023-03-08 04:48:42,112][321237] Updated weights for policy 0, policy_version 107920 (0.0005) [2023-03-08 04:48:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11663.2). Total num frames: 55279616. Throughput: 0: 11930.9. Samples: 55279616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:48:44,595][320945] Avg episode reward: [(0, '4859.395')] [2023-03-08 04:48:45,712][321237] Updated weights for policy 0, policy_version 108000 (0.0005) [2023-03-08 04:48:49,320][321237] Updated weights for policy 0, policy_version 108080 (0.0005) [2023-03-08 04:48:49,594][320945] Fps is (10 sec: 11469.0, 60 sec: 11878.4, 300 sec: 11677.1). Total num frames: 55336960. Throughput: 0: 11883.6. Samples: 55313056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:48:49,594][320945] Avg episode reward: [(0, '4860.506')] [2023-03-08 04:48:52,716][321237] Updated weights for policy 0, policy_version 108160 (0.0005) [2023-03-08 04:48:54,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11691.0). Total num frames: 55398400. Throughput: 0: 11885.2. Samples: 55384432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:48:54,595][320945] Avg episode reward: [(0, '4862.679')] [2023-03-08 04:48:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000108200_55398400.pth... [2023-03-08 04:48:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000107504_55042048.pth [2023-03-08 04:48:56,126][321237] Updated weights for policy 0, policy_version 108240 (0.0005) [2023-03-08 04:48:59,425][321237] Updated weights for policy 0, policy_version 108320 (0.0004) [2023-03-08 04:48:59,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11704.8). Total num frames: 55459840. Throughput: 0: 11977.2. Samples: 55458212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:48:59,595][320945] Avg episode reward: [(0, '4863.734')] [2023-03-08 04:49:02,766][321237] Updated weights for policy 0, policy_version 108400 (0.0005) [2023-03-08 04:49:04,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11718.7). Total num frames: 55521280. Throughput: 0: 11969.1. Samples: 55494704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:49:04,595][320945] Avg episode reward: [(0, '4857.411')] [2023-03-08 04:49:06,253][321237] Updated weights for policy 0, policy_version 108480 (0.0005) [2023-03-08 04:49:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11704.8). Total num frames: 55574528. Throughput: 0: 11851.5. Samples: 55563088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:49:09,594][320945] Avg episode reward: [(0, '4858.227')] [2023-03-08 04:49:09,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000108552_55578624.pth... [2023-03-08 04:49:09,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000107864_55226368.pth [2023-03-08 04:49:09,935][321237] Updated weights for policy 0, policy_version 108560 (0.0005) [2023-03-08 04:49:13,450][321237] Updated weights for policy 0, policy_version 108640 (0.0004) [2023-03-08 04:49:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11732.6). Total num frames: 55635968. Throughput: 0: 11771.5. Samples: 55632160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:49:14,595][320945] Avg episode reward: [(0, '4861.859')] [2023-03-08 04:49:17,079][321237] Updated weights for policy 0, policy_version 108720 (0.0005) [2023-03-08 04:49:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11732.6). Total num frames: 55693312. Throughput: 0: 11737.6. Samples: 55667052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:49:19,595][320945] Avg episode reward: [(0, '4855.467')] [2023-03-08 04:49:20,452][321237] Updated weights for policy 0, policy_version 108800 (0.0004) [2023-03-08 04:49:23,856][321237] Updated weights for policy 0, policy_version 108880 (0.0003) [2023-03-08 04:49:24,594][320945] Fps is (10 sec: 11878.2, 60 sec: 11878.4, 300 sec: 11746.5). Total num frames: 55754752. Throughput: 0: 11757.2. Samples: 55739392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:49:24,595][320945] Avg episode reward: [(0, '4859.227')] [2023-03-08 04:49:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000108896_55754752.pth... [2023-03-08 04:49:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000108200_55398400.pth [2023-03-08 04:49:27,276][321237] Updated weights for policy 0, policy_version 108960 (0.0004) [2023-03-08 04:49:29,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11746.5). Total num frames: 55812096. Throughput: 0: 11832.4. Samples: 55812076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:49:29,595][320945] Avg episode reward: [(0, '4862.485')] [2023-03-08 04:49:30,714][321237] Updated weights for policy 0, policy_version 109040 (0.0005) [2023-03-08 04:49:34,113][321237] Updated weights for policy 0, policy_version 109120 (0.0003) [2023-03-08 04:49:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11760.4). Total num frames: 55873536. Throughput: 0: 11872.3. Samples: 55847312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:49:34,595][320945] Avg episode reward: [(0, '4863.143')] [2023-03-08 04:49:37,589][321237] Updated weights for policy 0, policy_version 109200 (0.0004) [2023-03-08 04:49:39,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11788.1). Total num frames: 55934976. Throughput: 0: 11871.6. Samples: 55918656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:49:39,595][320945] Avg episode reward: [(0, '4861.861')] [2023-03-08 04:49:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000109248_55934976.pth... [2023-03-08 04:49:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000108552_55578624.pth [2023-03-08 04:49:40,987][321237] Updated weights for policy 0, policy_version 109280 (0.0003) [2023-03-08 04:49:44,441][321237] Updated weights for policy 0, policy_version 109360 (0.0004) [2023-03-08 04:49:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11788.1). Total num frames: 55992320. Throughput: 0: 11819.9. Samples: 55990108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:49:44,595][320945] Avg episode reward: [(0, '4862.711')] [2023-03-08 04:49:47,756][321237] Updated weights for policy 0, policy_version 109440 (0.0004) [2023-03-08 04:49:49,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11946.6, 300 sec: 11788.2). Total num frames: 56053760. Throughput: 0: 11840.0. Samples: 56027504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:49:49,595][320945] Avg episode reward: [(0, '4861.571')] [2023-03-08 04:49:51,127][321237] Updated weights for policy 0, policy_version 109520 (0.0004) [2023-03-08 04:49:54,529][321237] Updated weights for policy 0, policy_version 109600 (0.0004) [2023-03-08 04:49:54,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11788.1). Total num frames: 56115200. Throughput: 0: 11917.4. Samples: 56099372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:49:54,595][320945] Avg episode reward: [(0, '4862.229')] [2023-03-08 04:49:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000109600_56115200.pth... [2023-03-08 04:49:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000108896_55754752.pth [2023-03-08 04:49:57,932][321237] Updated weights for policy 0, policy_version 109680 (0.0005) [2023-03-08 04:49:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11774.3). Total num frames: 56172544. Throughput: 0: 12008.7. Samples: 56172552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:49:59,595][320945] Avg episode reward: [(0, '4854.207')] [2023-03-08 04:50:01,367][321237] Updated weights for policy 0, policy_version 109760 (0.0004) [2023-03-08 04:50:04,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11774.3). Total num frames: 56233984. Throughput: 0: 12024.2. Samples: 56208140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:50:04,595][320945] Avg episode reward: [(0, '4860.566')] [2023-03-08 04:50:04,819][321237] Updated weights for policy 0, policy_version 109840 (0.0004) [2023-03-08 04:50:08,271][321237] Updated weights for policy 0, policy_version 109920 (0.0004) [2023-03-08 04:50:09,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 11760.4). Total num frames: 56295424. Throughput: 0: 11992.6. Samples: 56279060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:50:09,595][320945] Avg episode reward: [(0, '4862.566')] [2023-03-08 04:50:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000109952_56295424.pth... [2023-03-08 04:50:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000109248_55934976.pth [2023-03-08 04:50:11,621][321237] Updated weights for policy 0, policy_version 110000 (0.0005) [2023-03-08 04:50:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11746.5). Total num frames: 56352768. Throughput: 0: 11984.8. Samples: 56351392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:50:14,595][320945] Avg episode reward: [(0, '4857.285')] [2023-03-08 04:50:15,050][321237] Updated weights for policy 0, policy_version 110080 (0.0004) [2023-03-08 04:50:18,533][321237] Updated weights for policy 0, policy_version 110160 (0.0004) [2023-03-08 04:50:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11946.7, 300 sec: 11732.6). Total num frames: 56410112. Throughput: 0: 12007.6. Samples: 56387652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:50:19,595][320945] Avg episode reward: [(0, '4863.522')] [2023-03-08 04:50:21,954][321237] Updated weights for policy 0, policy_version 110240 (0.0004) [2023-03-08 04:50:24,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11760.4). Total num frames: 56475648. Throughput: 0: 12013.3. Samples: 56459256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:50:24,595][320945] Avg episode reward: [(0, '4863.943')] [2023-03-08 04:50:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000110304_56475648.pth... [2023-03-08 04:50:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000109600_56115200.pth [2023-03-08 04:50:25,319][321237] Updated weights for policy 0, policy_version 110320 (0.0004) [2023-03-08 04:50:28,812][321237] Updated weights for policy 0, policy_version 110400 (0.0005) [2023-03-08 04:50:29,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 11732.6). Total num frames: 56532992. Throughput: 0: 11995.0. Samples: 56529884. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:50:29,595][320945] Avg episode reward: [(0, '4863.665')] [2023-03-08 04:50:32,177][321237] Updated weights for policy 0, policy_version 110480 (0.0003) [2023-03-08 04:50:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11718.7). Total num frames: 56590336. Throughput: 0: 11979.6. Samples: 56566588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:50:34,595][320945] Avg episode reward: [(0, '4863.059')] [2023-03-08 04:50:35,680][321237] Updated weights for policy 0, policy_version 110560 (0.0004) [2023-03-08 04:50:39,091][321237] Updated weights for policy 0, policy_version 110640 (0.0004) [2023-03-08 04:50:39,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 11732.6). Total num frames: 56651776. Throughput: 0: 11965.7. Samples: 56637828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:50:39,595][320945] Avg episode reward: [(0, '4862.081')] [2023-03-08 04:50:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000110648_56651776.pth... [2023-03-08 04:50:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000109952_56295424.pth [2023-03-08 04:50:42,438][321237] Updated weights for policy 0, policy_version 110720 (0.0004) [2023-03-08 04:50:44,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11746.5). Total num frames: 56713216. Throughput: 0: 11929.1. Samples: 56709360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:50:44,595][320945] Avg episode reward: [(0, '4862.918')] [2023-03-08 04:50:45,989][321237] Updated weights for policy 0, policy_version 110800 (0.0004) [2023-03-08 04:50:49,415][321237] Updated weights for policy 0, policy_version 110880 (0.0004) [2023-03-08 04:50:49,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 11746.5). Total num frames: 56770560. Throughput: 0: 11935.2. Samples: 56745224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:50:49,595][320945] Avg episode reward: [(0, '4863.003')] [2023-03-08 04:50:52,796][321237] Updated weights for policy 0, policy_version 110960 (0.0004) [2023-03-08 04:50:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 11760.4). Total num frames: 56832000. Throughput: 0: 11960.5. Samples: 56817284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:50:54,595][320945] Avg episode reward: [(0, '4863.562')] [2023-03-08 04:50:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000111000_56832000.pth... [2023-03-08 04:50:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000110304_56475648.pth [2023-03-08 04:50:56,272][321237] Updated weights for policy 0, policy_version 111040 (0.0005) [2023-03-08 04:50:59,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11946.6, 300 sec: 11746.5). Total num frames: 56889344. Throughput: 0: 11896.7. Samples: 56886744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:50:59,595][320945] Avg episode reward: [(0, '4859.516')] [2023-03-08 04:50:59,834][321237] Updated weights for policy 0, policy_version 111120 (0.0004) [2023-03-08 04:51:03,626][321237] Updated weights for policy 0, policy_version 111200 (0.0005) [2023-03-08 04:51:04,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11810.1, 300 sec: 11732.6). Total num frames: 56942592. Throughput: 0: 11815.4. Samples: 56919344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:51:04,595][320945] Avg episode reward: [(0, '4862.148')] [2023-03-08 04:51:07,306][321237] Updated weights for policy 0, policy_version 111280 (0.0005) [2023-03-08 04:51:09,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11732.6). Total num frames: 56999936. Throughput: 0: 11701.7. Samples: 56985832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:51:09,595][320945] Avg episode reward: [(0, '4861.161')] [2023-03-08 04:51:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000111328_56999936.pth... [2023-03-08 04:51:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000110648_56651776.pth [2023-03-08 04:51:11,037][321237] Updated weights for policy 0, policy_version 111360 (0.0004) [2023-03-08 04:51:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11704.8). Total num frames: 57053184. Throughput: 0: 11603.2. Samples: 57052028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:51:14,595][320945] Avg episode reward: [(0, '4859.125')] [2023-03-08 04:51:14,759][321237] Updated weights for policy 0, policy_version 111440 (0.0004) [2023-03-08 04:51:18,542][321237] Updated weights for policy 0, policy_version 111520 (0.0005) [2023-03-08 04:51:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11605.3, 300 sec: 11691.0). Total num frames: 57106432. Throughput: 0: 11504.4. Samples: 57084284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:51:19,595][320945] Avg episode reward: [(0, '4863.225')] [2023-03-08 04:51:22,350][321237] Updated weights for policy 0, policy_version 111600 (0.0005) [2023-03-08 04:51:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11677.1). Total num frames: 57163776. Throughput: 0: 11373.2. Samples: 57149620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:51:24,595][320945] Avg episode reward: [(0, '4861.802')] [2023-03-08 04:51:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000111648_57163776.pth... [2023-03-08 04:51:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000111000_56832000.pth [2023-03-08 04:51:26,118][321237] Updated weights for policy 0, policy_version 111680 (0.0004) [2023-03-08 04:51:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11663.2). Total num frames: 57217024. Throughput: 0: 11251.4. Samples: 57215672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:51:29,595][320945] Avg episode reward: [(0, '4859.061')] [2023-03-08 04:51:29,799][321237] Updated weights for policy 0, policy_version 111760 (0.0005) [2023-03-08 04:51:33,427][321237] Updated weights for policy 0, policy_version 111840 (0.0004) [2023-03-08 04:51:34,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11663.2). Total num frames: 57274368. Throughput: 0: 11207.6. Samples: 57249568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:51:34,595][320945] Avg episode reward: [(0, '4859.241')] [2023-03-08 04:51:37,206][321237] Updated weights for policy 0, policy_version 111920 (0.0004) [2023-03-08 04:51:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11649.3). Total num frames: 57327616. Throughput: 0: 11067.6. Samples: 57315328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:51:39,595][320945] Avg episode reward: [(0, '4861.558')] [2023-03-08 04:51:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000111968_57327616.pth... [2023-03-08 04:51:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000111328_56999936.pth [2023-03-08 04:51:40,953][321237] Updated weights for policy 0, policy_version 112000 (0.0004) [2023-03-08 04:51:44,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11635.4). Total num frames: 57380864. Throughput: 0: 10962.4. Samples: 57380052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:51:44,595][320945] Avg episode reward: [(0, '4861.582')] [2023-03-08 04:51:44,728][321237] Updated weights for policy 0, policy_version 112080 (0.0005) [2023-03-08 04:51:48,492][321237] Updated weights for policy 0, policy_version 112160 (0.0004) [2023-03-08 04:51:49,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11059.2, 300 sec: 11621.5). Total num frames: 57434112. Throughput: 0: 10958.3. Samples: 57412468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:51:49,595][320945] Avg episode reward: [(0, '4819.884')] [2023-03-08 04:51:52,230][321237] Updated weights for policy 0, policy_version 112240 (0.0005) [2023-03-08 04:51:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11621.5). Total num frames: 57491456. Throughput: 0: 10948.6. Samples: 57478520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:51:54,595][320945] Avg episode reward: [(0, '4815.323')] [2023-03-08 04:51:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000112288_57491456.pth... [2023-03-08 04:51:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000111648_57163776.pth [2023-03-08 04:51:56,003][321237] Updated weights for policy 0, policy_version 112320 (0.0005) [2023-03-08 04:51:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11593.8). Total num frames: 57544704. Throughput: 0: 10920.7. Samples: 57543460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:51:59,595][320945] Avg episode reward: [(0, '4816.774')] [2023-03-08 04:51:59,774][321237] Updated weights for policy 0, policy_version 112400 (0.0005) [2023-03-08 04:52:03,511][321237] Updated weights for policy 0, policy_version 112480 (0.0005) [2023-03-08 04:52:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11579.9). Total num frames: 57597952. Throughput: 0: 10918.8. Samples: 57575628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:52:04,595][320945] Avg episode reward: [(0, '4864.375')] [2023-03-08 04:52:07,259][321237] Updated weights for policy 0, policy_version 112560 (0.0004) [2023-03-08 04:52:09,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 11579.9). Total num frames: 57655296. Throughput: 0: 10945.9. Samples: 57642188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:52:09,595][320945] Avg episode reward: [(0, '4817.435')] [2023-03-08 04:52:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000112608_57655296.pth... [2023-03-08 04:52:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000111968_57327616.pth [2023-03-08 04:52:11,111][321237] Updated weights for policy 0, policy_version 112640 (0.0005) [2023-03-08 04:52:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11566.0). Total num frames: 57708544. Throughput: 0: 10905.2. Samples: 57706404. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:52:14,595][320945] Avg episode reward: [(0, '4816.024')] [2023-03-08 04:52:14,851][321237] Updated weights for policy 0, policy_version 112720 (0.0004) [2023-03-08 04:52:18,614][321237] Updated weights for policy 0, policy_version 112800 (0.0005) [2023-03-08 04:52:19,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10922.7, 300 sec: 11566.0). Total num frames: 57761792. Throughput: 0: 10882.0. Samples: 57739260. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:52:19,595][320945] Avg episode reward: [(0, '4862.380')] [2023-03-08 04:52:22,402][321237] Updated weights for policy 0, policy_version 112880 (0.0005) [2023-03-08 04:52:24,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 11552.1). Total num frames: 57815040. Throughput: 0: 10851.3. Samples: 57803636. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:52:24,595][320945] Avg episode reward: [(0, '4860.934')] [2023-03-08 04:52:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000112920_57815040.pth... [2023-03-08 04:52:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000112288_57491456.pth [2023-03-08 04:52:26,146][321237] Updated weights for policy 0, policy_version 112960 (0.0005) [2023-03-08 04:52:29,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10922.7, 300 sec: 11566.0). Total num frames: 57872384. Throughput: 0: 10925.7. Samples: 57871708. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:52:29,595][320945] Avg episode reward: [(0, '4860.849')] [2023-03-08 04:52:29,704][321237] Updated weights for policy 0, policy_version 113040 (0.0005) [2023-03-08 04:52:33,208][321237] Updated weights for policy 0, policy_version 113120 (0.0004) [2023-03-08 04:52:34,594][320945] Fps is (10 sec: 11469.0, 60 sec: 10922.7, 300 sec: 11566.0). Total num frames: 57929728. Throughput: 0: 10964.7. Samples: 57905880. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:52:34,594][320945] Avg episode reward: [(0, '4864.491')] [2023-03-08 04:52:36,850][321237] Updated weights for policy 0, policy_version 113200 (0.0005) [2023-03-08 04:52:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 10990.9, 300 sec: 11579.9). Total num frames: 57987072. Throughput: 0: 11016.9. Samples: 57974280. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:52:39,595][320945] Avg episode reward: [(0, '4861.063')] [2023-03-08 04:52:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000113256_57987072.pth... [2023-03-08 04:52:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000112608_57655296.pth [2023-03-08 04:52:40,628][321237] Updated weights for policy 0, policy_version 113280 (0.0005) [2023-03-08 04:52:44,452][321237] Updated weights for policy 0, policy_version 113360 (0.0004) [2023-03-08 04:52:44,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 11579.9). Total num frames: 58040320. Throughput: 0: 11006.0. Samples: 58038732. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:52:44,595][320945] Avg episode reward: [(0, '4863.139')] [2023-03-08 04:52:48,260][321237] Updated weights for policy 0, policy_version 113440 (0.0005) [2023-03-08 04:52:49,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 11552.1). Total num frames: 58093568. Throughput: 0: 11013.2. Samples: 58071224. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:52:49,595][320945] Avg episode reward: [(0, '4860.734')] [2023-03-08 04:52:52,064][321237] Updated weights for policy 0, policy_version 113520 (0.0005) [2023-03-08 04:52:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11538.2). Total num frames: 58146816. Throughput: 0: 10950.2. Samples: 58134948. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:52:54,595][320945] Avg episode reward: [(0, '4863.449')] [2023-03-08 04:52:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000113568_58146816.pth... [2023-03-08 04:52:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000112920_57815040.pth [2023-03-08 04:52:55,847][321237] Updated weights for policy 0, policy_version 113600 (0.0005) [2023-03-08 04:52:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11510.5). Total num frames: 58200064. Throughput: 0: 10970.2. Samples: 58200064. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:52:59,595][320945] Avg episode reward: [(0, '4863.007')] [2023-03-08 04:52:59,670][321237] Updated weights for policy 0, policy_version 113680 (0.0005) [2023-03-08 04:53:03,352][321237] Updated weights for policy 0, policy_version 113760 (0.0005) [2023-03-08 04:53:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11510.5). Total num frames: 58257408. Throughput: 0: 10969.7. Samples: 58232896. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:53:04,595][320945] Avg episode reward: [(0, '4863.938')] [2023-03-08 04:53:07,010][321237] Updated weights for policy 0, policy_version 113840 (0.0005) [2023-03-08 04:53:09,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 11482.7). Total num frames: 58310656. Throughput: 0: 11022.8. Samples: 58299664. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:53:09,595][320945] Avg episode reward: [(0, '4864.500')] [2023-03-08 04:53:09,647][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000113896_58314752.pth... [2023-03-08 04:53:09,649][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000113256_57987072.pth [2023-03-08 04:53:10,764][321237] Updated weights for policy 0, policy_version 113920 (0.0005) [2023-03-08 04:53:14,244][321237] Updated weights for policy 0, policy_version 114000 (0.0005) [2023-03-08 04:53:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 11482.7). Total num frames: 58372096. Throughput: 0: 11030.1. Samples: 58368064. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 04:53:14,595][320945] Avg episode reward: [(0, '4863.966')] [2023-03-08 04:53:17,753][321237] Updated weights for policy 0, policy_version 114080 (0.0004) [2023-03-08 04:53:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11127.5, 300 sec: 11482.7). Total num frames: 58429440. Throughput: 0: 11055.4. Samples: 58403372. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:53:19,595][320945] Avg episode reward: [(0, '4864.133')] [2023-03-08 04:53:21,259][321237] Updated weights for policy 0, policy_version 114160 (0.0004) [2023-03-08 04:53:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11468.8). Total num frames: 58486784. Throughput: 0: 11117.3. Samples: 58474560. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:53:24,595][320945] Avg episode reward: [(0, '4863.046')] [2023-03-08 04:53:24,600][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000114240_58490880.pth... [2023-03-08 04:53:24,600][321237] Updated weights for policy 0, policy_version 114240 (0.0004) [2023-03-08 04:53:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000113568_58146816.pth [2023-03-08 04:53:28,189][321237] Updated weights for policy 0, policy_version 114320 (0.0004) [2023-03-08 04:53:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 11468.8). Total num frames: 58548224. Throughput: 0: 11238.2. Samples: 58544452. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:53:29,595][320945] Avg episode reward: [(0, '4863.183')] [2023-03-08 04:53:31,644][321237] Updated weights for policy 0, policy_version 114400 (0.0004) [2023-03-08 04:53:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11264.0, 300 sec: 11468.8). Total num frames: 58605568. Throughput: 0: 11314.7. Samples: 58580384. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:53:34,595][320945] Avg episode reward: [(0, '4862.826')] [2023-03-08 04:53:35,073][321237] Updated weights for policy 0, policy_version 114480 (0.0005) [2023-03-08 04:53:38,573][321237] Updated weights for policy 0, policy_version 114560 (0.0004) [2023-03-08 04:53:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11468.8). Total num frames: 58662912. Throughput: 0: 11461.0. Samples: 58650696. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:53:39,595][320945] Avg episode reward: [(0, '4865.450')] [2023-03-08 04:53:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000114584_58667008.pth... [2023-03-08 04:53:39,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000113896_58314752.pth [2023-03-08 04:53:42,064][321237] Updated weights for policy 0, policy_version 114640 (0.0004) [2023-03-08 04:53:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11482.7). Total num frames: 58724352. Throughput: 0: 11614.2. Samples: 58722704. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:53:44,595][320945] Avg episode reward: [(0, '4861.712')] [2023-03-08 04:53:45,515][321237] Updated weights for policy 0, policy_version 114720 (0.0003) [2023-03-08 04:53:48,980][321237] Updated weights for policy 0, policy_version 114800 (0.0004) [2023-03-08 04:53:49,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11468.8, 300 sec: 11468.8). Total num frames: 58781696. Throughput: 0: 11649.2. Samples: 58757112. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:53:49,605][320945] Avg episode reward: [(0, '4864.361')] [2023-03-08 04:53:52,486][321237] Updated weights for policy 0, policy_version 114880 (0.0004) [2023-03-08 04:53:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11468.8). Total num frames: 58843136. Throughput: 0: 11731.6. Samples: 58827588. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:53:54,605][320945] Avg episode reward: [(0, '4861.538')] [2023-03-08 04:53:54,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000114928_58843136.pth... [2023-03-08 04:53:54,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000114240_58490880.pth [2023-03-08 04:53:55,991][321237] Updated weights for policy 0, policy_version 114960 (0.0004) [2023-03-08 04:53:59,468][321237] Updated weights for policy 0, policy_version 115040 (0.0004) [2023-03-08 04:53:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11454.9). Total num frames: 58900480. Throughput: 0: 11782.2. Samples: 58898264. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:53:59,605][320945] Avg episode reward: [(0, '4862.002')] [2023-03-08 04:54:02,974][321237] Updated weights for policy 0, policy_version 115120 (0.0004) [2023-03-08 04:54:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11468.8). Total num frames: 58957824. Throughput: 0: 11768.3. Samples: 58932944. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:54:04,605][320945] Avg episode reward: [(0, '4863.484')] [2023-03-08 04:54:06,423][321237] Updated weights for policy 0, policy_version 115200 (0.0004) [2023-03-08 04:54:09,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11810.2, 300 sec: 11468.8). Total num frames: 59019264. Throughput: 0: 11779.4. Samples: 59004632. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:54:09,605][320945] Avg episode reward: [(0, '4861.547')] [2023-03-08 04:54:09,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000115272_59019264.pth... [2023-03-08 04:54:09,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000114584_58667008.pth [2023-03-08 04:54:09,812][321237] Updated weights for policy 0, policy_version 115280 (0.0004) [2023-03-08 04:54:13,274][321237] Updated weights for policy 0, policy_version 115360 (0.0004) [2023-03-08 04:54:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11468.8). Total num frames: 59076608. Throughput: 0: 11818.2. Samples: 59076272. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 04:54:14,605][320945] Avg episode reward: [(0, '4863.985')] [2023-03-08 04:54:16,767][321237] Updated weights for policy 0, policy_version 115440 (0.0004) [2023-03-08 04:54:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11468.8). Total num frames: 59138048. Throughput: 0: 11791.4. Samples: 59110996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:54:19,595][320945] Avg episode reward: [(0, '4862.999')] [2023-03-08 04:54:20,213][321237] Updated weights for policy 0, policy_version 115520 (0.0004) [2023-03-08 04:54:23,791][321237] Updated weights for policy 0, policy_version 115600 (0.0004) [2023-03-08 04:54:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11468.8). Total num frames: 59195392. Throughput: 0: 11796.5. Samples: 59181540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:54:24,595][320945] Avg episode reward: [(0, '4862.873')] [2023-03-08 04:54:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000115616_59195392.pth... [2023-03-08 04:54:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000114928_58843136.pth [2023-03-08 04:54:27,522][321237] Updated weights for policy 0, policy_version 115680 (0.0005) [2023-03-08 04:54:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11441.0). Total num frames: 59248640. Throughput: 0: 11676.2. Samples: 59248132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:54:29,605][320945] Avg episode reward: [(0, '4865.173')] [2023-03-08 04:54:31,171][321237] Updated weights for policy 0, policy_version 115760 (0.0005) [2023-03-08 04:54:34,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11427.1). Total num frames: 59305984. Throughput: 0: 11652.6. Samples: 59281480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:54:34,605][320945] Avg episode reward: [(0, '4861.218')] [2023-03-08 04:54:34,822][321237] Updated weights for policy 0, policy_version 115840 (0.0005) [2023-03-08 04:54:38,552][321237] Updated weights for policy 0, policy_version 115920 (0.0005) [2023-03-08 04:54:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11413.3). Total num frames: 59359232. Throughput: 0: 11558.9. Samples: 59347736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:54:39,605][320945] Avg episode reward: [(0, '4771.921')] [2023-03-08 04:54:39,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000115936_59359232.pth... [2023-03-08 04:54:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000115272_59019264.pth [2023-03-08 04:54:42,278][321237] Updated weights for policy 0, policy_version 116000 (0.0005) [2023-03-08 04:54:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11399.4). Total num frames: 59416576. Throughput: 0: 11467.1. Samples: 59414284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:54:44,605][320945] Avg episode reward: [(0, '4815.022')] [2023-03-08 04:54:46,028][321237] Updated weights for policy 0, policy_version 116080 (0.0005) [2023-03-08 04:54:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11371.6). Total num frames: 59469824. Throughput: 0: 11407.8. Samples: 59446296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:54:49,605][320945] Avg episode reward: [(0, '4818.892')] [2023-03-08 04:54:49,768][321237] Updated weights for policy 0, policy_version 116160 (0.0005) [2023-03-08 04:54:53,471][321237] Updated weights for policy 0, policy_version 116240 (0.0005) [2023-03-08 04:54:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.6, 300 sec: 11371.6). Total num frames: 59527168. Throughput: 0: 11291.6. Samples: 59512752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:54:54,605][320945] Avg episode reward: [(0, '4817.292')] [2023-03-08 04:54:54,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000116264_59527168.pth... [2023-03-08 04:54:54,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000115616_59195392.pth [2023-03-08 04:54:57,267][321188] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000004 [2023-03-08 04:54:57,269][321237] Updated weights for policy 0, policy_version 116320 (0.0005) [2023-03-08 04:54:59,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11332.3, 300 sec: 11343.8). Total num frames: 59580416. Throughput: 0: 11127.3. Samples: 59577000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:54:59,605][320945] Avg episode reward: [(0, '4864.673')] [2023-03-08 04:55:01,031][321237] Updated weights for policy 0, policy_version 116400 (0.0005) [2023-03-08 04:55:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 11316.1). Total num frames: 59633664. Throughput: 0: 11083.2. Samples: 59609740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:55:04,605][320945] Avg episode reward: [(0, '4864.242')] [2023-03-08 04:55:04,866][321237] Updated weights for policy 0, policy_version 116480 (0.0005) [2023-03-08 04:55:08,660][321237] Updated weights for policy 0, policy_version 116560 (0.0005) [2023-03-08 04:55:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11302.2). Total num frames: 59686912. Throughput: 0: 10958.8. Samples: 59674688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:55:09,605][320945] Avg episode reward: [(0, '4865.102')] [2023-03-08 04:55:09,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000116576_59686912.pth... [2023-03-08 04:55:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000115936_59359232.pth [2023-03-08 04:55:12,474][321237] Updated weights for policy 0, policy_version 116640 (0.0005) [2023-03-08 04:55:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11288.3). Total num frames: 59740160. Throughput: 0: 10910.6. Samples: 59739108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:55:14,605][320945] Avg episode reward: [(0, '4865.064')] [2023-03-08 04:55:16,268][321237] Updated weights for policy 0, policy_version 116720 (0.0004) [2023-03-08 04:55:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11246.6). Total num frames: 59793408. Throughput: 0: 10898.9. Samples: 59771932. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:55:19,605][320945] Avg episode reward: [(0, '4863.935')] [2023-03-08 04:55:20,035][321237] Updated weights for policy 0, policy_version 116800 (0.0005) [2023-03-08 04:55:23,627][321237] Updated weights for policy 0, policy_version 116880 (0.0005) [2023-03-08 04:55:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11246.6). Total num frames: 59850752. Throughput: 0: 10906.5. Samples: 59838528. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:55:24,605][320945] Avg episode reward: [(0, '4860.246')] [2023-03-08 04:55:24,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000116896_59850752.pth... [2023-03-08 04:55:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000116264_59527168.pth [2023-03-08 04:55:27,260][321237] Updated weights for policy 0, policy_version 116960 (0.0005) [2023-03-08 04:55:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 11246.6). Total num frames: 59908096. Throughput: 0: 10938.2. Samples: 59906504. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:55:29,605][320945] Avg episode reward: [(0, '4861.943')] [2023-03-08 04:55:30,906][321237] Updated weights for policy 0, policy_version 117040 (0.0005) [2023-03-08 04:55:34,432][321237] Updated weights for policy 0, policy_version 117120 (0.0005) [2023-03-08 04:55:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 11232.8). Total num frames: 59965440. Throughput: 0: 10990.4. Samples: 59940864. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:55:34,595][320945] Avg episode reward: [(0, '4861.331')] [2023-03-08 04:55:38,104][321237] Updated weights for policy 0, policy_version 117200 (0.0005) [2023-03-08 04:55:39,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 11205.0). Total num frames: 60018688. Throughput: 0: 11007.5. Samples: 60008092. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:55:39,595][320945] Avg episode reward: [(0, '4861.874')] [2023-03-08 04:55:39,612][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000117232_60022784.pth... [2023-03-08 04:55:39,613][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000116576_59686912.pth [2023-03-08 04:55:41,850][321237] Updated weights for policy 0, policy_version 117280 (0.0005) [2023-03-08 04:55:44,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 11205.0). Total num frames: 60076032. Throughput: 0: 11066.8. Samples: 60075004. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:55:44,595][320945] Avg episode reward: [(0, '4865.527')] [2023-03-08 04:55:45,548][321237] Updated weights for policy 0, policy_version 117360 (0.0005) [2023-03-08 04:55:49,298][321237] Updated weights for policy 0, policy_version 117440 (0.0005) [2023-03-08 04:55:49,594][320945] Fps is (10 sec: 11059.4, 60 sec: 10990.9, 300 sec: 11177.2). Total num frames: 60129280. Throughput: 0: 11066.6. Samples: 60107736. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:55:49,594][320945] Avg episode reward: [(0, '4862.734')] [2023-03-08 04:55:52,975][321237] Updated weights for policy 0, policy_version 117520 (0.0005) [2023-03-08 04:55:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11177.2). Total num frames: 60186624. Throughput: 0: 11095.1. Samples: 60173968. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:55:54,595][320945] Avg episode reward: [(0, '4862.085')] [2023-03-08 04:55:54,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000117552_60186624.pth... [2023-03-08 04:55:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000116896_59850752.pth [2023-03-08 04:55:56,462][321237] Updated weights for policy 0, policy_version 117600 (0.0004) [2023-03-08 04:55:59,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11127.5, 300 sec: 11205.0). Total num frames: 60248064. Throughput: 0: 11228.4. Samples: 60244388. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:55:59,595][320945] Avg episode reward: [(0, '4862.822')] [2023-03-08 04:55:59,880][321237] Updated weights for policy 0, policy_version 117680 (0.0004) [2023-03-08 04:56:03,227][321237] Updated weights for policy 0, policy_version 117760 (0.0003) [2023-03-08 04:56:04,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11195.7, 300 sec: 11205.0). Total num frames: 60305408. Throughput: 0: 11310.5. Samples: 60280904. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:56:04,595][320945] Avg episode reward: [(0, '4860.790')] [2023-03-08 04:56:06,660][321237] Updated weights for policy 0, policy_version 117840 (0.0004) [2023-03-08 04:56:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11218.9). Total num frames: 60362752. Throughput: 0: 11429.0. Samples: 60352832. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:56:09,595][320945] Avg episode reward: [(0, '4863.608')] [2023-03-08 04:56:09,603][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000117904_60366848.pth... [2023-03-08 04:56:09,605][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000117232_60022784.pth [2023-03-08 04:56:10,386][321237] Updated weights for policy 0, policy_version 117920 (0.0005) [2023-03-08 04:56:13,882][321237] Updated weights for policy 0, policy_version 118000 (0.0005) [2023-03-08 04:56:14,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11400.5, 300 sec: 11246.6). Total num frames: 60424192. Throughput: 0: 11414.8. Samples: 60420168. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:56:14,605][320945] Avg episode reward: [(0, '4859.244')] [2023-03-08 04:56:17,353][321237] Updated weights for policy 0, policy_version 118080 (0.0005) [2023-03-08 04:56:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11468.8, 300 sec: 11246.6). Total num frames: 60481536. Throughput: 0: 11445.4. Samples: 60455908. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:56:19,595][320945] Avg episode reward: [(0, '4861.934')] [2023-03-08 04:56:20,851][321237] Updated weights for policy 0, policy_version 118160 (0.0005) [2023-03-08 04:56:24,337][321237] Updated weights for policy 0, policy_version 118240 (0.0005) [2023-03-08 04:56:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11260.5). Total num frames: 60538880. Throughput: 0: 11522.5. Samples: 60526604. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:56:24,605][320945] Avg episode reward: [(0, '4861.016')] [2023-03-08 04:56:24,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000118240_60538880.pth... [2023-03-08 04:56:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000117552_60186624.pth [2023-03-08 04:56:27,813][321237] Updated weights for policy 0, policy_version 118320 (0.0004) [2023-03-08 04:56:29,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11537.1, 300 sec: 11274.4). Total num frames: 60600320. Throughput: 0: 11603.3. Samples: 60597152. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:56:29,605][320945] Avg episode reward: [(0, '4863.065')] [2023-03-08 04:56:31,213][321237] Updated weights for policy 0, policy_version 118400 (0.0005) [2023-03-08 04:56:34,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11288.3). Total num frames: 60657664. Throughput: 0: 11676.1. Samples: 60633160. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:56:34,605][320945] Avg episode reward: [(0, '4863.153')] [2023-03-08 04:56:34,681][321237] Updated weights for policy 0, policy_version 118480 (0.0005) [2023-03-08 04:56:38,201][321237] Updated weights for policy 0, policy_version 118560 (0.0005) [2023-03-08 04:56:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11316.1). Total num frames: 60719104. Throughput: 0: 11759.3. Samples: 60703136. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:56:39,605][320945] Avg episode reward: [(0, '4864.191')] [2023-03-08 04:56:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000118592_60719104.pth... [2023-03-08 04:56:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000117904_60366848.pth [2023-03-08 04:56:41,717][321237] Updated weights for policy 0, policy_version 118640 (0.0004) [2023-03-08 04:56:44,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11330.0). Total num frames: 60776448. Throughput: 0: 11764.1. Samples: 60773772. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:56:44,605][320945] Avg episode reward: [(0, '4863.317')] [2023-03-08 04:56:45,203][321237] Updated weights for policy 0, policy_version 118720 (0.0005) [2023-03-08 04:56:48,690][321237] Updated weights for policy 0, policy_version 118800 (0.0005) [2023-03-08 04:56:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 11330.0). Total num frames: 60833792. Throughput: 0: 11730.2. Samples: 60808760. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:56:49,595][320945] Avg episode reward: [(0, '4862.495')] [2023-03-08 04:56:52,197][321237] Updated weights for policy 0, policy_version 118880 (0.0005) [2023-03-08 04:56:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11343.8). Total num frames: 60891136. Throughput: 0: 11690.9. Samples: 60878920. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:56:54,595][320945] Avg episode reward: [(0, '4862.490')] [2023-03-08 04:56:54,600][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000118936_60895232.pth... [2023-03-08 04:56:54,602][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000118240_60538880.pth [2023-03-08 04:56:55,638][321237] Updated weights for policy 0, policy_version 118960 (0.0004) [2023-03-08 04:56:59,067][321237] Updated weights for policy 0, policy_version 119040 (0.0005) [2023-03-08 04:56:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11371.6). Total num frames: 60952576. Throughput: 0: 11796.0. Samples: 60950988. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:56:59,595][320945] Avg episode reward: [(0, '4861.135')] [2023-03-08 04:57:02,836][321237] Updated weights for policy 0, policy_version 119120 (0.0005) [2023-03-08 04:57:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11357.7). Total num frames: 61005824. Throughput: 0: 11730.7. Samples: 60983788. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:57:04,595][320945] Avg episode reward: [(0, '4864.335')] [2023-03-08 04:57:06,350][321237] Updated weights for policy 0, policy_version 119200 (0.0005) [2023-03-08 04:57:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11385.5). Total num frames: 61067264. Throughput: 0: 11698.2. Samples: 61053024. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:57:09,595][320945] Avg episode reward: [(0, '4862.875')] [2023-03-08 04:57:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000119272_61067264.pth... [2023-03-08 04:57:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000118592_60719104.pth [2023-03-08 04:57:09,771][321237] Updated weights for policy 0, policy_version 119280 (0.0005) [2023-03-08 04:57:13,314][321237] Updated weights for policy 0, policy_version 119360 (0.0005) [2023-03-08 04:57:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11399.4). Total num frames: 61124608. Throughput: 0: 11705.3. Samples: 61123888. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:57:14,594][320945] Avg episode reward: [(0, '4863.519')] [2023-03-08 04:57:16,641][321237] Updated weights for policy 0, policy_version 119440 (0.0004) [2023-03-08 04:57:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11427.1). Total num frames: 61186048. Throughput: 0: 11737.1. Samples: 61161328. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 04:57:19,605][320945] Avg episode reward: [(0, '4864.300')] [2023-03-08 04:57:20,019][321237] Updated weights for policy 0, policy_version 119520 (0.0005) [2023-03-08 04:57:23,398][321237] Updated weights for policy 0, policy_version 119600 (0.0005) [2023-03-08 04:57:24,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 11441.0). Total num frames: 61247488. Throughput: 0: 11789.6. Samples: 61233668. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:57:24,605][320945] Avg episode reward: [(0, '4862.951')] [2023-03-08 04:57:24,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000119624_61247488.pth... [2023-03-08 04:57:24,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000118936_60895232.pth [2023-03-08 04:57:26,776][321237] Updated weights for policy 0, policy_version 119680 (0.0005) [2023-03-08 04:57:29,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11454.9). Total num frames: 61308928. Throughput: 0: 11859.2. Samples: 61307436. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:57:29,605][320945] Avg episode reward: [(0, '4861.109')] [2023-03-08 04:57:30,049][321237] Updated weights for policy 0, policy_version 119760 (0.0004) [2023-03-08 04:57:33,413][321237] Updated weights for policy 0, policy_version 119840 (0.0004) [2023-03-08 04:57:34,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11468.8). Total num frames: 61370368. Throughput: 0: 11895.6. Samples: 61344060. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:57:34,605][320945] Avg episode reward: [(0, '4859.427')] [2023-03-08 04:57:36,879][321237] Updated weights for policy 0, policy_version 119920 (0.0005) [2023-03-08 04:57:39,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11482.7). Total num frames: 61427712. Throughput: 0: 11919.4. Samples: 61415292. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:57:39,605][320945] Avg episode reward: [(0, '4821.144')] [2023-03-08 04:57:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000119976_61427712.pth... [2023-03-08 04:57:39,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000119272_61067264.pth [2023-03-08 04:57:40,361][321237] Updated weights for policy 0, policy_version 120000 (0.0005) [2023-03-08 04:57:43,698][321237] Updated weights for policy 0, policy_version 120080 (0.0005) [2023-03-08 04:57:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11510.5). Total num frames: 61489152. Throughput: 0: 11934.7. Samples: 61488048. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:57:44,605][320945] Avg episode reward: [(0, '4858.590')] [2023-03-08 04:57:47,051][321237] Updated weights for policy 0, policy_version 120160 (0.0004) [2023-03-08 04:57:49,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11946.7, 300 sec: 11538.2). Total num frames: 61550592. Throughput: 0: 12016.6. Samples: 61524536. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:57:49,605][320945] Avg episode reward: [(0, '4862.558')] [2023-03-08 04:57:50,364][321237] Updated weights for policy 0, policy_version 120240 (0.0004) [2023-03-08 04:57:53,775][321237] Updated weights for policy 0, policy_version 120320 (0.0005) [2023-03-08 04:57:54,594][320945] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 11566.0). Total num frames: 61612032. Throughput: 0: 12101.9. Samples: 61597608. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:57:54,605][320945] Avg episode reward: [(0, '4861.988')] [2023-03-08 04:57:54,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000120336_61612032.pth... [2023-03-08 04:57:54,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000119624_61247488.pth [2023-03-08 04:57:57,177][321237] Updated weights for policy 0, policy_version 120400 (0.0004) [2023-03-08 04:57:59,594][320945] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11579.9). Total num frames: 61673472. Throughput: 0: 12127.3. Samples: 61669616. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:57:59,605][320945] Avg episode reward: [(0, '4863.618')] [2023-03-08 04:58:00,582][321237] Updated weights for policy 0, policy_version 120480 (0.0005) [2023-03-08 04:58:04,226][321237] Updated weights for policy 0, policy_version 120560 (0.0005) [2023-03-08 04:58:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 12014.9, 300 sec: 11579.9). Total num frames: 61726720. Throughput: 0: 12074.6. Samples: 61704684. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:58:04,594][320945] Avg episode reward: [(0, '4818.394')] [2023-03-08 04:58:07,955][321237] Updated weights for policy 0, policy_version 120640 (0.0005) [2023-03-08 04:58:09,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11946.7, 300 sec: 11566.0). Total num frames: 61784064. Throughput: 0: 11957.7. Samples: 61771764. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:58:09,595][320945] Avg episode reward: [(0, '4819.398')] [2023-03-08 04:58:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000120672_61784064.pth... [2023-03-08 04:58:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000119976_61427712.pth [2023-03-08 04:58:11,509][321237] Updated weights for policy 0, policy_version 120720 (0.0005) [2023-03-08 04:58:14,594][320945] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 11579.9). Total num frames: 61845504. Throughput: 0: 11877.6. Samples: 61841928. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:58:14,595][320945] Avg episode reward: [(0, '4860.191')] [2023-03-08 04:58:14,916][321237] Updated weights for policy 0, policy_version 120800 (0.0005) [2023-03-08 04:58:18,627][321237] Updated weights for policy 0, policy_version 120880 (0.0005) [2023-03-08 04:58:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11566.0). Total num frames: 61898752. Throughput: 0: 11813.5. Samples: 61875668. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 04:58:19,595][320945] Avg episode reward: [(0, '4859.848')] [2023-03-08 04:58:22,282][321237] Updated weights for policy 0, policy_version 120960 (0.0005) [2023-03-08 04:58:24,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11810.1, 300 sec: 11552.1). Total num frames: 61956096. Throughput: 0: 11737.4. Samples: 61943476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:58:24,595][320945] Avg episode reward: [(0, '4863.160')] [2023-03-08 04:58:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000121008_61956096.pth... [2023-03-08 04:58:24,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000120336_61612032.pth [2023-03-08 04:58:25,685][321237] Updated weights for policy 0, policy_version 121040 (0.0005) [2023-03-08 04:58:29,161][321237] Updated weights for policy 0, policy_version 121120 (0.0005) [2023-03-08 04:58:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11566.0). Total num frames: 62017536. Throughput: 0: 11699.0. Samples: 62014504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:58:29,595][320945] Avg episode reward: [(0, '4864.406')] [2023-03-08 04:58:32,662][321237] Updated weights for policy 0, policy_version 121200 (0.0005) [2023-03-08 04:58:34,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 62074880. Throughput: 0: 11675.5. Samples: 62049932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:58:34,595][320945] Avg episode reward: [(0, '4863.812')] [2023-03-08 04:58:36,085][321237] Updated weights for policy 0, policy_version 121280 (0.0004) [2023-03-08 04:58:39,445][321237] Updated weights for policy 0, policy_version 121360 (0.0004) [2023-03-08 04:58:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11566.0). Total num frames: 62136320. Throughput: 0: 11647.2. Samples: 62121732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:58:39,595][320945] Avg episode reward: [(0, '4863.072')] [2023-03-08 04:58:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000121360_62136320.pth... [2023-03-08 04:58:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000120672_61784064.pth [2023-03-08 04:58:42,944][321237] Updated weights for policy 0, policy_version 121440 (0.0005) [2023-03-08 04:58:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 62193664. Throughput: 0: 11637.5. Samples: 62193304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:58:44,595][320945] Avg episode reward: [(0, '4863.796')] [2023-03-08 04:58:46,350][321237] Updated weights for policy 0, policy_version 121520 (0.0004) [2023-03-08 04:58:49,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 62255104. Throughput: 0: 11658.6. Samples: 62229324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:58:49,595][320945] Avg episode reward: [(0, '4861.337')] [2023-03-08 04:58:49,767][321237] Updated weights for policy 0, policy_version 121600 (0.0004) [2023-03-08 04:58:53,229][321237] Updated weights for policy 0, policy_version 121680 (0.0005) [2023-03-08 04:58:54,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11579.9). Total num frames: 62316544. Throughput: 0: 11743.7. Samples: 62300232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:58:54,595][320945] Avg episode reward: [(0, '4862.034')] [2023-03-08 04:58:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000121712_62316544.pth... [2023-03-08 04:58:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000121008_61956096.pth [2023-03-08 04:58:56,607][321237] Updated weights for policy 0, policy_version 121760 (0.0004) [2023-03-08 04:58:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11579.9). Total num frames: 62373888. Throughput: 0: 11783.0. Samples: 62372164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:58:59,605][320945] Avg episode reward: [(0, '4814.015')] [2023-03-08 04:59:00,082][321237] Updated weights for policy 0, policy_version 121840 (0.0004) [2023-03-08 04:59:03,573][321237] Updated weights for policy 0, policy_version 121920 (0.0005) [2023-03-08 04:59:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 62431232. Throughput: 0: 11817.0. Samples: 62407432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:59:04,605][320945] Avg episode reward: [(0, '4862.147')] [2023-03-08 04:59:07,124][321237] Updated weights for policy 0, policy_version 122000 (0.0005) [2023-03-08 04:59:09,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11579.9). Total num frames: 62492672. Throughput: 0: 11847.8. Samples: 62476628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:59:09,605][320945] Avg episode reward: [(0, '4862.943')] [2023-03-08 04:59:09,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000122056_62492672.pth... [2023-03-08 04:59:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000121360_62136320.pth [2023-03-08 04:59:10,590][321237] Updated weights for policy 0, policy_version 122080 (0.0005) [2023-03-08 04:59:14,130][321237] Updated weights for policy 0, policy_version 122160 (0.0005) [2023-03-08 04:59:14,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 62550016. Throughput: 0: 11843.4. Samples: 62547456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:59:14,605][320945] Avg episode reward: [(0, '4862.693')] [2023-03-08 04:59:17,595][321237] Updated weights for policy 0, policy_version 122240 (0.0004) [2023-03-08 04:59:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11566.0). Total num frames: 62607360. Throughput: 0: 11842.8. Samples: 62582856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:59:19,595][320945] Avg episode reward: [(0, '4863.648')] [2023-03-08 04:59:21,314][321237] Updated weights for policy 0, policy_version 122320 (0.0005) [2023-03-08 04:59:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 62660608. Throughput: 0: 11725.3. Samples: 62649372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:59:24,595][320945] Avg episode reward: [(0, '4863.190')] [2023-03-08 04:59:24,603][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000122392_62664704.pth... [2023-03-08 04:59:24,605][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000121712_62316544.pth [2023-03-08 04:59:24,937][321237] Updated weights for policy 0, policy_version 122400 (0.0005) [2023-03-08 04:59:28,720][321237] Updated weights for policy 0, policy_version 122480 (0.0005) [2023-03-08 04:59:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11566.0). Total num frames: 62717952. Throughput: 0: 11614.1. Samples: 62715940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:59:29,605][320945] Avg episode reward: [(0, '4863.826')] [2023-03-08 04:59:32,212][321237] Updated weights for policy 0, policy_version 122560 (0.0005) [2023-03-08 04:59:34,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11741.8, 300 sec: 11593.8). Total num frames: 62779392. Throughput: 0: 11592.6. Samples: 62750992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:59:34,605][320945] Avg episode reward: [(0, '4862.353')] [2023-03-08 04:59:35,710][321237] Updated weights for policy 0, policy_version 122640 (0.0005) [2023-03-08 04:59:39,129][321237] Updated weights for policy 0, policy_version 122720 (0.0004) [2023-03-08 04:59:39,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 11593.8). Total num frames: 62836736. Throughput: 0: 11598.8. Samples: 62822180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:59:39,605][320945] Avg episode reward: [(0, '4863.472')] [2023-03-08 04:59:39,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000122728_62836736.pth... [2023-03-08 04:59:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000122056_62492672.pth [2023-03-08 04:59:42,434][321237] Updated weights for policy 0, policy_version 122800 (0.0004) [2023-03-08 04:59:44,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11621.5). Total num frames: 62898176. Throughput: 0: 11622.8. Samples: 62895188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:59:44,605][320945] Avg episode reward: [(0, '4864.340')] [2023-03-08 04:59:45,821][321237] Updated weights for policy 0, policy_version 122880 (0.0005) [2023-03-08 04:59:49,194][321237] Updated weights for policy 0, policy_version 122960 (0.0005) [2023-03-08 04:59:49,594][320945] Fps is (10 sec: 12288.1, 60 sec: 11741.9, 300 sec: 11635.4). Total num frames: 62959616. Throughput: 0: 11655.8. Samples: 62931944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:59:49,605][320945] Avg episode reward: [(0, '4863.093')] [2023-03-08 04:59:52,516][321237] Updated weights for policy 0, policy_version 123040 (0.0005) [2023-03-08 04:59:54,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11741.9, 300 sec: 11663.2). Total num frames: 63021056. Throughput: 0: 11756.2. Samples: 63005656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:59:54,605][320945] Avg episode reward: [(0, '4862.400')] [2023-03-08 04:59:54,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000123088_63021056.pth... [2023-03-08 04:59:54,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000122392_62664704.pth [2023-03-08 04:59:56,011][321237] Updated weights for policy 0, policy_version 123120 (0.0005) [2023-03-08 04:59:59,322][321237] Updated weights for policy 0, policy_version 123200 (0.0004) [2023-03-08 04:59:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 63078400. Throughput: 0: 11782.5. Samples: 63077668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 04:59:59,605][320945] Avg episode reward: [(0, '4861.089')] [2023-03-08 05:00:02,812][321237] Updated weights for policy 0, policy_version 123280 (0.0005) [2023-03-08 05:00:04,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11704.8). Total num frames: 63139840. Throughput: 0: 11780.1. Samples: 63112960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:00:04,605][320945] Avg episode reward: [(0, '4863.388')] [2023-03-08 05:00:06,157][321237] Updated weights for policy 0, policy_version 123360 (0.0004) [2023-03-08 05:00:09,550][321237] Updated weights for policy 0, policy_version 123440 (0.0005) [2023-03-08 05:00:09,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11732.6). Total num frames: 63201280. Throughput: 0: 11915.3. Samples: 63185560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:00:09,605][320945] Avg episode reward: [(0, '4863.714')] [2023-03-08 05:00:09,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000123440_63201280.pth... [2023-03-08 05:00:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000122728_62836736.pth [2023-03-08 05:00:13,019][321237] Updated weights for policy 0, policy_version 123520 (0.0005) [2023-03-08 05:00:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11746.5). Total num frames: 63258624. Throughput: 0: 12018.9. Samples: 63256792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:00:14,605][320945] Avg episode reward: [(0, '4860.148')] [2023-03-08 05:00:16,704][321237] Updated weights for policy 0, policy_version 123600 (0.0005) [2023-03-08 05:00:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11732.6). Total num frames: 63311872. Throughput: 0: 11959.6. Samples: 63289172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:00:19,605][320945] Avg episode reward: [(0, '4863.762')] [2023-03-08 05:00:20,532][321237] Updated weights for policy 0, policy_version 123680 (0.0005) [2023-03-08 05:00:24,309][321237] Updated weights for policy 0, policy_version 123760 (0.0005) [2023-03-08 05:00:24,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11741.9, 300 sec: 11718.7). Total num frames: 63365120. Throughput: 0: 11800.4. Samples: 63353196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:00:24,605][320945] Avg episode reward: [(0, '4863.460')] [2023-03-08 05:00:24,607][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000123760_63365120.pth... [2023-03-08 05:00:24,609][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000123088_63021056.pth [2023-03-08 05:00:27,854][321237] Updated weights for policy 0, policy_version 123840 (0.0005) [2023-03-08 05:00:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11718.7). Total num frames: 63422464. Throughput: 0: 11718.8. Samples: 63422536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:00:29,595][320945] Avg episode reward: [(0, '4864.103')] [2023-03-08 05:00:31,460][321237] Updated weights for policy 0, policy_version 123920 (0.0005) [2023-03-08 05:00:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11732.6). Total num frames: 63479808. Throughput: 0: 11647.0. Samples: 63456056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:00:34,594][320945] Avg episode reward: [(0, '4816.964')] [2023-03-08 05:00:34,981][321237] Updated weights for policy 0, policy_version 124000 (0.0005) [2023-03-08 05:00:38,512][321237] Updated weights for policy 0, policy_version 124080 (0.0005) [2023-03-08 05:00:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11746.5). Total num frames: 63541248. Throughput: 0: 11558.8. Samples: 63525800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:00:39,595][320945] Avg episode reward: [(0, '4864.293')] [2023-03-08 05:00:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000124104_63541248.pth... [2023-03-08 05:00:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000123440_63201280.pth [2023-03-08 05:00:41,989][321237] Updated weights for policy 0, policy_version 124160 (0.0004) [2023-03-08 05:00:44,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 11760.4). Total num frames: 63598592. Throughput: 0: 11520.7. Samples: 63596100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:00:44,595][320945] Avg episode reward: [(0, '4863.519')] [2023-03-08 05:00:45,510][321237] Updated weights for policy 0, policy_version 124240 (0.0004) [2023-03-08 05:00:49,005][321237] Updated weights for policy 0, policy_version 124320 (0.0004) [2023-03-08 05:00:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11760.4). Total num frames: 63655936. Throughput: 0: 11523.0. Samples: 63631496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:00:49,595][320945] Avg episode reward: [(0, '4861.446')] [2023-03-08 05:00:52,616][321237] Updated weights for policy 0, policy_version 124400 (0.0005) [2023-03-08 05:00:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11746.5). Total num frames: 63713280. Throughput: 0: 11438.9. Samples: 63700312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:00:54,595][320945] Avg episode reward: [(0, '4863.892')] [2023-03-08 05:00:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000124440_63713280.pth... [2023-03-08 05:00:54,598][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000123760_63365120.pth [2023-03-08 05:00:56,306][321237] Updated weights for policy 0, policy_version 124480 (0.0005) [2023-03-08 05:00:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11746.5). Total num frames: 63770624. Throughput: 0: 11368.3. Samples: 63768364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:00:59,595][320945] Avg episode reward: [(0, '4863.134')] [2023-03-08 05:00:59,786][321237] Updated weights for policy 0, policy_version 124560 (0.0005) [2023-03-08 05:01:03,420][321237] Updated weights for policy 0, policy_version 124640 (0.0005) [2023-03-08 05:01:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11746.5). Total num frames: 63827968. Throughput: 0: 11427.3. Samples: 63803400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:01:04,595][320945] Avg episode reward: [(0, '4863.603')] [2023-03-08 05:01:06,992][321237] Updated weights for policy 0, policy_version 124720 (0.0005) [2023-03-08 05:01:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11732.6). Total num frames: 63885312. Throughput: 0: 11529.7. Samples: 63872032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:01:09,595][320945] Avg episode reward: [(0, '4861.776')] [2023-03-08 05:01:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000124776_63885312.pth... [2023-03-08 05:01:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000124104_63541248.pth [2023-03-08 05:01:10,350][321237] Updated weights for policy 0, policy_version 124800 (0.0004) [2023-03-08 05:01:13,756][321237] Updated weights for policy 0, policy_version 124880 (0.0004) [2023-03-08 05:01:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11746.5). Total num frames: 63946752. Throughput: 0: 11590.4. Samples: 63944104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:01:14,595][320945] Avg episode reward: [(0, '4858.617')] [2023-03-08 05:01:17,297][321237] Updated weights for policy 0, policy_version 124960 (0.0005) [2023-03-08 05:01:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11746.5). Total num frames: 64004096. Throughput: 0: 11630.7. Samples: 63979440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:01:19,595][320945] Avg episode reward: [(0, '4863.615')] [2023-03-08 05:01:20,799][321237] Updated weights for policy 0, policy_version 125040 (0.0005) [2023-03-08 05:01:24,334][321237] Updated weights for policy 0, policy_version 125120 (0.0005) [2023-03-08 05:01:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11732.6). Total num frames: 64061440. Throughput: 0: 11628.1. Samples: 64049064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:01:24,595][320945] Avg episode reward: [(0, '4864.920')] [2023-03-08 05:01:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000125120_64061440.pth... [2023-03-08 05:01:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000124440_63713280.pth [2023-03-08 05:01:27,792][321237] Updated weights for policy 0, policy_version 125200 (0.0005) [2023-03-08 05:01:29,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11746.5). Total num frames: 64122880. Throughput: 0: 11638.5. Samples: 64119832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:01:29,595][320945] Avg episode reward: [(0, '4862.887')] [2023-03-08 05:01:31,182][321237] Updated weights for policy 0, policy_version 125280 (0.0004) [2023-03-08 05:01:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11732.6). Total num frames: 64180224. Throughput: 0: 11649.4. Samples: 64155720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:01:34,594][320945] Avg episode reward: [(0, '4860.970')] [2023-03-08 05:01:34,630][321237] Updated weights for policy 0, policy_version 125360 (0.0005) [2023-03-08 05:01:38,099][321237] Updated weights for policy 0, policy_version 125440 (0.0005) [2023-03-08 05:01:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11746.5). Total num frames: 64241664. Throughput: 0: 11710.1. Samples: 64227268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:01:39,595][320945] Avg episode reward: [(0, '4861.943')] [2023-03-08 05:01:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000125472_64241664.pth... [2023-03-08 05:01:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000124776_63885312.pth [2023-03-08 05:01:41,827][321237] Updated weights for policy 0, policy_version 125520 (0.0005) [2023-03-08 05:01:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11732.6). Total num frames: 64294912. Throughput: 0: 11697.2. Samples: 64294736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:01:44,594][320945] Avg episode reward: [(0, '4861.765')] [2023-03-08 05:01:45,333][321237] Updated weights for policy 0, policy_version 125600 (0.0005) [2023-03-08 05:01:48,741][321237] Updated weights for policy 0, policy_version 125680 (0.0004) [2023-03-08 05:01:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11746.5). Total num frames: 64356352. Throughput: 0: 11726.9. Samples: 64331112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:01:49,595][320945] Avg episode reward: [(0, '4862.725')] [2023-03-08 05:01:52,240][321237] Updated weights for policy 0, policy_version 125760 (0.0005) [2023-03-08 05:01:54,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11732.6). Total num frames: 64413696. Throughput: 0: 11763.9. Samples: 64401408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:01:54,594][320945] Avg episode reward: [(0, '4863.259')] [2023-03-08 05:01:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000125808_64413696.pth... [2023-03-08 05:01:54,598][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000125120_64061440.pth [2023-03-08 05:01:55,695][321237] Updated weights for policy 0, policy_version 125840 (0.0005) [2023-03-08 05:01:59,306][321237] Updated weights for policy 0, policy_version 125920 (0.0005) [2023-03-08 05:01:59,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11746.5). Total num frames: 64471040. Throughput: 0: 11709.7. Samples: 64471040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:01:59,595][320945] Avg episode reward: [(0, '4861.028')] [2023-03-08 05:02:02,946][321237] Updated weights for policy 0, policy_version 126000 (0.0004) [2023-03-08 05:02:04,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11732.6). Total num frames: 64528384. Throughput: 0: 11654.1. Samples: 64503872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:02:04,595][320945] Avg episode reward: [(0, '4862.834')] [2023-03-08 05:02:06,434][321237] Updated weights for policy 0, policy_version 126080 (0.0004) [2023-03-08 05:02:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11746.5). Total num frames: 64589824. Throughput: 0: 11689.4. Samples: 64575088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:02:09,595][320945] Avg episode reward: [(0, '4863.431')] [2023-03-08 05:02:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000126152_64589824.pth... [2023-03-08 05:02:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000125472_64241664.pth [2023-03-08 05:02:09,849][321237] Updated weights for policy 0, policy_version 126160 (0.0004) [2023-03-08 05:02:13,307][321237] Updated weights for policy 0, policy_version 126240 (0.0005) [2023-03-08 05:02:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11732.6). Total num frames: 64647168. Throughput: 0: 11697.2. Samples: 64646208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:02:14,595][320945] Avg episode reward: [(0, '4862.253')] [2023-03-08 05:02:16,798][321237] Updated weights for policy 0, policy_version 126320 (0.0005) [2023-03-08 05:02:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11732.6). Total num frames: 64708608. Throughput: 0: 11686.7. Samples: 64681624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:02:19,595][320945] Avg episode reward: [(0, '4863.403')] [2023-03-08 05:02:20,194][321237] Updated weights for policy 0, policy_version 126400 (0.0004) [2023-03-08 05:02:23,740][321237] Updated weights for policy 0, policy_version 126480 (0.0004) [2023-03-08 05:02:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11718.7). Total num frames: 64765952. Throughput: 0: 11654.1. Samples: 64751704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:02:24,595][320945] Avg episode reward: [(0, '4861.916')] [2023-03-08 05:02:24,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000126496_64765952.pth... [2023-03-08 05:02:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000125808_64413696.pth [2023-03-08 05:02:27,188][321237] Updated weights for policy 0, policy_version 126560 (0.0005) [2023-03-08 05:02:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11704.8). Total num frames: 64823296. Throughput: 0: 11741.1. Samples: 64823088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:02:29,595][320945] Avg episode reward: [(0, '4863.467')] [2023-03-08 05:02:30,891][321237] Updated weights for policy 0, policy_version 126640 (0.0005) [2023-03-08 05:02:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11605.3, 300 sec: 11691.0). Total num frames: 64876544. Throughput: 0: 11659.7. Samples: 64855800. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:02:34,595][320945] Avg episode reward: [(0, '4861.577')] [2023-03-08 05:02:34,636][321237] Updated weights for policy 0, policy_version 126720 (0.0005) [2023-03-08 05:02:38,363][321237] Updated weights for policy 0, policy_version 126800 (0.0005) [2023-03-08 05:02:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11677.1). Total num frames: 64933888. Throughput: 0: 11551.5. Samples: 64921224. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:02:39,595][320945] Avg episode reward: [(0, '4863.044')] [2023-03-08 05:02:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000126824_64933888.pth... [2023-03-08 05:02:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000126152_64589824.pth [2023-03-08 05:02:42,142][321237] Updated weights for policy 0, policy_version 126880 (0.0005) [2023-03-08 05:02:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11649.3). Total num frames: 64987136. Throughput: 0: 11467.5. Samples: 64987076. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:02:44,595][320945] Avg episode reward: [(0, '4861.809')] [2023-03-08 05:02:45,849][321237] Updated weights for policy 0, policy_version 126960 (0.0005) [2023-03-08 05:02:49,409][321237] Updated weights for policy 0, policy_version 127040 (0.0005) [2023-03-08 05:02:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11635.4). Total num frames: 65044480. Throughput: 0: 11467.6. Samples: 65019912. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:02:49,595][320945] Avg episode reward: [(0, '4862.399')] [2023-03-08 05:02:53,090][321237] Updated weights for policy 0, policy_version 127120 (0.0005) [2023-03-08 05:02:54,594][320945] Fps is (10 sec: 11468.5, 60 sec: 11468.7, 300 sec: 11621.5). Total num frames: 65101824. Throughput: 0: 11389.9. Samples: 65087636. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:02:54,595][320945] Avg episode reward: [(0, '4862.870')] [2023-03-08 05:02:54,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000127152_65101824.pth... [2023-03-08 05:02:54,602][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000126496_64765952.pth [2023-03-08 05:02:56,752][321237] Updated weights for policy 0, policy_version 127200 (0.0005) [2023-03-08 05:02:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11621.5). Total num frames: 65155072. Throughput: 0: 11284.2. Samples: 65153996. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:02:59,595][320945] Avg episode reward: [(0, '4863.534')] [2023-03-08 05:03:00,470][321237] Updated weights for policy 0, policy_version 127280 (0.0005) [2023-03-08 05:03:03,981][321237] Updated weights for policy 0, policy_version 127360 (0.0004) [2023-03-08 05:03:04,594][320945] Fps is (10 sec: 11059.4, 60 sec: 11400.5, 300 sec: 11621.5). Total num frames: 65212416. Throughput: 0: 11246.9. Samples: 65187736. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:03:04,595][320945] Avg episode reward: [(0, '4863.581')] [2023-03-08 05:03:07,694][321237] Updated weights for policy 0, policy_version 127440 (0.0005) [2023-03-08 05:03:09,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11593.8). Total num frames: 65265664. Throughput: 0: 11197.1. Samples: 65255572. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:03:09,595][320945] Avg episode reward: [(0, '4862.594')] [2023-03-08 05:03:09,627][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000127480_65269760.pth... [2023-03-08 05:03:09,629][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000126824_64933888.pth [2023-03-08 05:03:11,563][321237] Updated weights for policy 0, policy_version 127520 (0.0005) [2023-03-08 05:03:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11607.6). Total num frames: 65323008. Throughput: 0: 11046.9. Samples: 65320200. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:03:14,595][320945] Avg episode reward: [(0, '4863.567')] [2023-03-08 05:03:15,164][321237] Updated weights for policy 0, policy_version 127600 (0.0005) [2023-03-08 05:03:18,633][321237] Updated weights for policy 0, policy_version 127680 (0.0004) [2023-03-08 05:03:19,594][320945] Fps is (10 sec: 11469.0, 60 sec: 11195.7, 300 sec: 11607.7). Total num frames: 65380352. Throughput: 0: 11112.2. Samples: 65355848. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:03:19,595][320945] Avg episode reward: [(0, '4864.578')] [2023-03-08 05:03:22,161][321237] Updated weights for policy 0, policy_version 127760 (0.0005) [2023-03-08 05:03:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11593.8). Total num frames: 65437696. Throughput: 0: 11205.7. Samples: 65425480. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:03:24,595][320945] Avg episode reward: [(0, '4823.944')] [2023-03-08 05:03:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000127808_65437696.pth... [2023-03-08 05:03:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000127152_65101824.pth [2023-03-08 05:03:25,709][321237] Updated weights for policy 0, policy_version 127840 (0.0004) [2023-03-08 05:03:29,257][321237] Updated weights for policy 0, policy_version 127920 (0.0004) [2023-03-08 05:03:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11593.8). Total num frames: 65495040. Throughput: 0: 11289.5. Samples: 65495104. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:03:29,594][320945] Avg episode reward: [(0, '4861.357')] [2023-03-08 05:03:32,745][321237] Updated weights for policy 0, policy_version 128000 (0.0005) [2023-03-08 05:03:34,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11332.3, 300 sec: 11593.8). Total num frames: 65556480. Throughput: 0: 11339.4. Samples: 65530184. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:03:34,595][320945] Avg episode reward: [(0, '4863.122')] [2023-03-08 05:03:36,278][321237] Updated weights for policy 0, policy_version 128080 (0.0004) [2023-03-08 05:03:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11332.3, 300 sec: 11593.8). Total num frames: 65613824. Throughput: 0: 11376.7. Samples: 65599584. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:03:39,595][320945] Avg episode reward: [(0, '4863.000')] [2023-03-08 05:03:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000128152_65613824.pth... [2023-03-08 05:03:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000127480_65269760.pth [2023-03-08 05:03:39,938][321237] Updated weights for policy 0, policy_version 128160 (0.0004) [2023-03-08 05:03:43,581][321237] Updated weights for policy 0, policy_version 128240 (0.0005) [2023-03-08 05:03:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11566.0). Total num frames: 65667072. Throughput: 0: 11402.0. Samples: 65667084. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:03:44,595][320945] Avg episode reward: [(0, '4864.346')] [2023-03-08 05:03:47,117][321237] Updated weights for policy 0, policy_version 128320 (0.0004) [2023-03-08 05:03:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11552.1). Total num frames: 65724416. Throughput: 0: 11417.2. Samples: 65701512. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:03:49,595][320945] Avg episode reward: [(0, '4861.728')] [2023-03-08 05:03:50,618][321237] Updated weights for policy 0, policy_version 128400 (0.0004) [2023-03-08 05:03:54,176][321237] Updated weights for policy 0, policy_version 128480 (0.0004) [2023-03-08 05:03:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11400.6, 300 sec: 11566.0). Total num frames: 65785856. Throughput: 0: 11455.6. Samples: 65771072. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:03:54,595][320945] Avg episode reward: [(0, '4863.223')] [2023-03-08 05:03:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000128488_65785856.pth... [2023-03-08 05:03:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000127808_65437696.pth [2023-03-08 05:03:57,755][321237] Updated weights for policy 0, policy_version 128560 (0.0004) [2023-03-08 05:03:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11566.0). Total num frames: 65843200. Throughput: 0: 11544.1. Samples: 65839684. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:03:59,595][320945] Avg episode reward: [(0, '4861.940')] [2023-03-08 05:04:01,303][321237] Updated weights for policy 0, policy_version 128640 (0.0004) [2023-03-08 05:04:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11552.1). Total num frames: 65900544. Throughput: 0: 11537.2. Samples: 65875024. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:04:04,595][320945] Avg episode reward: [(0, '4863.827')] [2023-03-08 05:04:04,918][321237] Updated weights for policy 0, policy_version 128720 (0.0005) [2023-03-08 05:04:08,466][321237] Updated weights for policy 0, policy_version 128800 (0.0004) [2023-03-08 05:04:09,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11552.1). Total num frames: 65957888. Throughput: 0: 11505.9. Samples: 65943244. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:04:09,595][320945] Avg episode reward: [(0, '4862.654')] [2023-03-08 05:04:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000128824_65957888.pth... [2023-03-08 05:04:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000128152_65613824.pth [2023-03-08 05:04:12,115][321237] Updated weights for policy 0, policy_version 128880 (0.0005) [2023-03-08 05:04:14,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11538.2). Total num frames: 66011136. Throughput: 0: 11438.6. Samples: 66009840. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:04:14,595][320945] Avg episode reward: [(0, '4861.504')] [2023-03-08 05:04:15,939][321237] Updated weights for policy 0, policy_version 128960 (0.0005) [2023-03-08 05:04:19,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11400.5, 300 sec: 11538.2). Total num frames: 66064384. Throughput: 0: 11385.0. Samples: 66042508. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:04:19,595][320945] Avg episode reward: [(0, '4863.226')] [2023-03-08 05:04:19,662][321237] Updated weights for policy 0, policy_version 129040 (0.0005) [2023-03-08 05:04:23,467][321237] Updated weights for policy 0, policy_version 129120 (0.0005) [2023-03-08 05:04:24,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11400.5, 300 sec: 11538.2). Total num frames: 66121728. Throughput: 0: 11274.4. Samples: 66106932. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:04:24,595][320945] Avg episode reward: [(0, '4862.321')] [2023-03-08 05:04:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000129144_66121728.pth... [2023-03-08 05:04:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000128488_65785856.pth [2023-03-08 05:04:27,114][321237] Updated weights for policy 0, policy_version 129200 (0.0005) [2023-03-08 05:04:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11510.5). Total num frames: 66174976. Throughput: 0: 11265.9. Samples: 66174052. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:04:29,595][320945] Avg episode reward: [(0, '4865.721')] [2023-03-08 05:04:30,942][321237] Updated weights for policy 0, policy_version 129280 (0.0005) [2023-03-08 05:04:34,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11496.6). Total num frames: 66228224. Throughput: 0: 11194.3. Samples: 66205256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:04:34,595][320945] Avg episode reward: [(0, '4864.702')] [2023-03-08 05:04:34,838][321237] Updated weights for policy 0, policy_version 129360 (0.0005) [2023-03-08 05:04:38,501][321237] Updated weights for policy 0, policy_version 129440 (0.0005) [2023-03-08 05:04:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11482.7). Total num frames: 66285568. Throughput: 0: 11090.2. Samples: 66270132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:04:39,595][320945] Avg episode reward: [(0, '4862.565')] [2023-03-08 05:04:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000129464_66285568.pth... [2023-03-08 05:04:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000128824_65957888.pth [2023-03-08 05:04:42,072][321237] Updated weights for policy 0, policy_version 129520 (0.0003) [2023-03-08 05:04:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11468.8). Total num frames: 66342912. Throughput: 0: 11093.2. Samples: 66338880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:04:44,595][320945] Avg episode reward: [(0, '4859.478')] [2023-03-08 05:04:45,598][321237] Updated weights for policy 0, policy_version 129600 (0.0003) [2023-03-08 05:04:49,191][321237] Updated weights for policy 0, policy_version 129680 (0.0003) [2023-03-08 05:04:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11454.9). Total num frames: 66400256. Throughput: 0: 11093.9. Samples: 66374248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:04:49,595][320945] Avg episode reward: [(0, '4769.586')] [2023-03-08 05:04:52,916][321237] Updated weights for policy 0, policy_version 129760 (0.0004) [2023-03-08 05:04:54,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11127.5, 300 sec: 11441.0). Total num frames: 66453504. Throughput: 0: 11066.4. Samples: 66441232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:04:54,595][320945] Avg episode reward: [(0, '4860.994')] [2023-03-08 05:04:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000129792_66453504.pth... [2023-03-08 05:04:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000129144_66121728.pth [2023-03-08 05:04:56,686][321237] Updated weights for policy 0, policy_version 129840 (0.0004) [2023-03-08 05:04:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11427.1). Total num frames: 66510848. Throughput: 0: 11055.8. Samples: 66507352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:04:59,595][320945] Avg episode reward: [(0, '4862.454')] [2023-03-08 05:05:00,221][321237] Updated weights for policy 0, policy_version 129920 (0.0003) [2023-03-08 05:05:03,816][321237] Updated weights for policy 0, policy_version 130000 (0.0003) [2023-03-08 05:05:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11127.5, 300 sec: 11413.3). Total num frames: 66568192. Throughput: 0: 11101.8. Samples: 66542088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:05:04,595][320945] Avg episode reward: [(0, '4862.139')] [2023-03-08 05:05:07,392][321237] Updated weights for policy 0, policy_version 130080 (0.0003) [2023-03-08 05:05:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 11413.3). Total num frames: 66625536. Throughput: 0: 11191.5. Samples: 66610548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:05:09,595][320945] Avg episode reward: [(0, '4865.009')] [2023-03-08 05:05:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000130128_66625536.pth... [2023-03-08 05:05:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000129464_66285568.pth [2023-03-08 05:05:11,002][321237] Updated weights for policy 0, policy_version 130160 (0.0003) [2023-03-08 05:05:14,519][321237] Updated weights for policy 0, policy_version 130240 (0.0004) [2023-03-08 05:05:14,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11195.7, 300 sec: 11427.1). Total num frames: 66682880. Throughput: 0: 11229.2. Samples: 66679368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:05:14,595][320945] Avg episode reward: [(0, '4865.179')] [2023-03-08 05:05:18,056][321237] Updated weights for policy 0, policy_version 130320 (0.0003) [2023-03-08 05:05:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11441.0). Total num frames: 66740224. Throughput: 0: 11329.8. Samples: 66715096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:05:19,595][320945] Avg episode reward: [(0, '4863.375')] [2023-03-08 05:05:21,697][321237] Updated weights for policy 0, policy_version 130400 (0.0003) [2023-03-08 05:05:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11441.0). Total num frames: 66797568. Throughput: 0: 11409.6. Samples: 66783564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:05:24,595][320945] Avg episode reward: [(0, '4863.963')] [2023-03-08 05:05:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000130464_66797568.pth... [2023-03-08 05:05:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000129792_66453504.pth [2023-03-08 05:05:25,130][321237] Updated weights for policy 0, policy_version 130480 (0.0003) [2023-03-08 05:05:28,708][321237] Updated weights for policy 0, policy_version 130560 (0.0003) [2023-03-08 05:05:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11441.0). Total num frames: 66854912. Throughput: 0: 11439.2. Samples: 66853644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:05:29,595][320945] Avg episode reward: [(0, '4862.897')] [2023-03-08 05:05:32,308][321237] Updated weights for policy 0, policy_version 130640 (0.0003) [2023-03-08 05:05:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11427.1). Total num frames: 66912256. Throughput: 0: 11404.9. Samples: 66887468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:05:34,595][320945] Avg episode reward: [(0, '4859.964')] [2023-03-08 05:05:35,927][321237] Updated weights for policy 0, policy_version 130720 (0.0003) [2023-03-08 05:05:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11413.3). Total num frames: 66965504. Throughput: 0: 11423.7. Samples: 66955296. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:05:39,595][320945] Avg episode reward: [(0, '4862.150')] [2023-03-08 05:05:39,625][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000130800_66969600.pth... [2023-03-08 05:05:39,625][321237] Updated weights for policy 0, policy_version 130800 (0.0005) [2023-03-08 05:05:39,626][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000130128_66625536.pth [2023-03-08 05:05:43,343][321237] Updated weights for policy 0, policy_version 130880 (0.0005) [2023-03-08 05:05:44,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11413.3). Total num frames: 67022848. Throughput: 0: 11395.7. Samples: 67020156. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:05:44,595][320945] Avg episode reward: [(0, '4862.379')] [2023-03-08 05:05:47,164][321237] Updated weights for policy 0, policy_version 130960 (0.0005) [2023-03-08 05:05:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11399.4). Total num frames: 67076096. Throughput: 0: 11343.5. Samples: 67052548. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:05:49,595][320945] Avg episode reward: [(0, '4864.968')] [2023-03-08 05:05:50,708][321237] Updated weights for policy 0, policy_version 131040 (0.0004) [2023-03-08 05:05:54,254][321237] Updated weights for policy 0, policy_version 131120 (0.0003) [2023-03-08 05:05:54,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11332.3, 300 sec: 11399.4). Total num frames: 67133440. Throughput: 0: 11350.7. Samples: 67121332. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:05:54,595][320945] Avg episode reward: [(0, '4864.413')] [2023-03-08 05:05:54,624][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000131128_67137536.pth... [2023-03-08 05:05:54,627][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000130464_66797568.pth [2023-03-08 05:05:57,905][321237] Updated weights for policy 0, policy_version 131200 (0.0004) [2023-03-08 05:05:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11399.4). Total num frames: 67190784. Throughput: 0: 11333.3. Samples: 67189368. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:05:59,595][320945] Avg episode reward: [(0, '4862.030')] [2023-03-08 05:06:01,714][321237] Updated weights for policy 0, policy_version 131280 (0.0005) [2023-03-08 05:06:04,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11385.5). Total num frames: 67244032. Throughput: 0: 11244.8. Samples: 67221112. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:06:04,595][320945] Avg episode reward: [(0, '4861.535')] [2023-03-08 05:06:05,500][321237] Updated weights for policy 0, policy_version 131360 (0.0005) [2023-03-08 05:06:09,239][321237] Updated weights for policy 0, policy_version 131440 (0.0005) [2023-03-08 05:06:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11357.7). Total num frames: 67297280. Throughput: 0: 11176.6. Samples: 67286512. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:06:09,595][320945] Avg episode reward: [(0, '4861.933')] [2023-03-08 05:06:09,642][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000131448_67301376.pth... [2023-03-08 05:06:09,643][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000130800_66969600.pth [2023-03-08 05:06:13,059][321237] Updated weights for policy 0, policy_version 131520 (0.0005) [2023-03-08 05:06:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11357.7). Total num frames: 67354624. Throughput: 0: 11050.5. Samples: 67350916. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:06:14,595][320945] Avg episode reward: [(0, '4863.479')] [2023-03-08 05:06:16,840][321237] Updated weights for policy 0, policy_version 131600 (0.0005) [2023-03-08 05:06:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11127.5, 300 sec: 11343.8). Total num frames: 67407872. Throughput: 0: 11020.2. Samples: 67383376. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:06:19,595][320945] Avg episode reward: [(0, '4862.771')] [2023-03-08 05:06:20,632][321237] Updated weights for policy 0, policy_version 131680 (0.0005) [2023-03-08 05:06:24,504][321237] Updated weights for policy 0, policy_version 131760 (0.0005) [2023-03-08 05:06:24,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11316.1). Total num frames: 67461120. Throughput: 0: 10965.6. Samples: 67448748. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:06:24,595][320945] Avg episode reward: [(0, '4859.022')] [2023-03-08 05:06:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000131760_67461120.pth... [2023-03-08 05:06:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000131128_67137536.pth [2023-03-08 05:06:27,982][321237] Updated weights for policy 0, policy_version 131840 (0.0004) [2023-03-08 05:06:29,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11059.2, 300 sec: 11316.1). Total num frames: 67518464. Throughput: 0: 11040.8. Samples: 67516992. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:06:29,605][320945] Avg episode reward: [(0, '4861.718')] [2023-03-08 05:06:31,612][321237] Updated weights for policy 0, policy_version 131920 (0.0004) [2023-03-08 05:06:34,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11288.3). Total num frames: 67571712. Throughput: 0: 11067.8. Samples: 67550600. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:06:34,605][320945] Avg episode reward: [(0, '4862.200')] [2023-03-08 05:06:35,481][321237] Updated weights for policy 0, policy_version 132000 (0.0005) [2023-03-08 05:06:39,286][321237] Updated weights for policy 0, policy_version 132080 (0.0005) [2023-03-08 05:06:39,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10991.0, 300 sec: 11288.3). Total num frames: 67624960. Throughput: 0: 10941.1. Samples: 67613680. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:06:39,594][320945] Avg episode reward: [(0, '4859.302')] [2023-03-08 05:06:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000132080_67624960.pth... [2023-03-08 05:06:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000131448_67301376.pth [2023-03-08 05:06:43,078][321237] Updated weights for policy 0, policy_version 132160 (0.0005) [2023-03-08 05:06:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11274.4). Total num frames: 67682304. Throughput: 0: 10870.8. Samples: 67678556. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:06:44,595][320945] Avg episode reward: [(0, '4859.057')] [2023-03-08 05:06:46,887][321237] Updated weights for policy 0, policy_version 132240 (0.0005) [2023-03-08 05:06:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11260.5). Total num frames: 67735552. Throughput: 0: 10886.1. Samples: 67710988. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:06:49,594][320945] Avg episode reward: [(0, '4863.599')] [2023-03-08 05:06:50,698][321237] Updated weights for policy 0, policy_version 132320 (0.0005) [2023-03-08 05:06:54,355][321237] Updated weights for policy 0, policy_version 132400 (0.0005) [2023-03-08 05:06:54,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10922.7, 300 sec: 11246.6). Total num frames: 67788800. Throughput: 0: 10888.9. Samples: 67776512. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:06:54,595][320945] Avg episode reward: [(0, '4862.138')] [2023-03-08 05:06:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000132400_67788800.pth... [2023-03-08 05:06:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000131760_67461120.pth [2023-03-08 05:06:57,863][321237] Updated weights for policy 0, policy_version 132480 (0.0004) [2023-03-08 05:06:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11246.6). Total num frames: 67846144. Throughput: 0: 11005.3. Samples: 67846152. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:06:59,594][320945] Avg episode reward: [(0, '4862.247')] [2023-03-08 05:07:01,336][321237] Updated weights for policy 0, policy_version 132560 (0.0004) [2023-03-08 05:07:04,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11059.2, 300 sec: 11246.6). Total num frames: 67907584. Throughput: 0: 11082.0. Samples: 67882068. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:07:04,595][320945] Avg episode reward: [(0, '4861.373')] [2023-03-08 05:07:04,751][321237] Updated weights for policy 0, policy_version 132640 (0.0004) [2023-03-08 05:07:08,296][321237] Updated weights for policy 0, policy_version 132720 (0.0005) [2023-03-08 05:07:09,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11127.5, 300 sec: 11246.6). Total num frames: 67964928. Throughput: 0: 11195.8. Samples: 67952560. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:07:09,595][320945] Avg episode reward: [(0, '4865.611')] [2023-03-08 05:07:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000132744_67964928.pth... [2023-03-08 05:07:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000132080_67624960.pth [2023-03-08 05:07:11,677][321237] Updated weights for policy 0, policy_version 132800 (0.0004) [2023-03-08 05:07:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11195.7, 300 sec: 11246.6). Total num frames: 68026368. Throughput: 0: 11268.4. Samples: 68024072. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:07:14,595][320945] Avg episode reward: [(0, '4861.572')] [2023-03-08 05:07:15,177][321237] Updated weights for policy 0, policy_version 132880 (0.0004) [2023-03-08 05:07:18,529][321237] Updated weights for policy 0, policy_version 132960 (0.0004) [2023-03-08 05:07:19,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11332.3, 300 sec: 11260.5). Total num frames: 68087808. Throughput: 0: 11310.1. Samples: 68059556. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:07:19,595][320945] Avg episode reward: [(0, '4862.897')] [2023-03-08 05:07:21,980][321237] Updated weights for policy 0, policy_version 133040 (0.0005) [2023-03-08 05:07:24,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11400.5, 300 sec: 11260.5). Total num frames: 68145152. Throughput: 0: 11496.6. Samples: 68131028. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:07:24,595][320945] Avg episode reward: [(0, '4863.861')] [2023-03-08 05:07:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000133096_68145152.pth... [2023-03-08 05:07:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000132400_67788800.pth [2023-03-08 05:07:25,577][321237] Updated weights for policy 0, policy_version 133120 (0.0004) [2023-03-08 05:07:29,020][321237] Updated weights for policy 0, policy_version 133200 (0.0003) [2023-03-08 05:07:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11274.4). Total num frames: 68202496. Throughput: 0: 11618.7. Samples: 68201396. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:07:29,595][320945] Avg episode reward: [(0, '4865.263')] [2023-03-08 05:07:32,541][321237] Updated weights for policy 0, policy_version 133280 (0.0004) [2023-03-08 05:07:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11274.4). Total num frames: 68259840. Throughput: 0: 11664.8. Samples: 68235904. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:07:34,595][320945] Avg episode reward: [(0, '4865.029')] [2023-03-08 05:07:36,000][321237] Updated weights for policy 0, policy_version 133360 (0.0004) [2023-03-08 05:07:39,403][321237] Updated weights for policy 0, policy_version 133440 (0.0004) [2023-03-08 05:07:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11302.2). Total num frames: 68321280. Throughput: 0: 11812.9. Samples: 68308092. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:07:39,595][320945] Avg episode reward: [(0, '4862.786')] [2023-03-08 05:07:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000133440_68321280.pth... [2023-03-08 05:07:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000132744_67964928.pth [2023-03-08 05:07:42,778][321237] Updated weights for policy 0, policy_version 133520 (0.0004) [2023-03-08 05:07:44,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11316.1). Total num frames: 68382720. Throughput: 0: 11872.1. Samples: 68380396. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:07:44,595][320945] Avg episode reward: [(0, '4862.379')] [2023-03-08 05:07:46,172][321237] Updated weights for policy 0, policy_version 133600 (0.0004) [2023-03-08 05:07:49,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11316.1). Total num frames: 68440064. Throughput: 0: 11855.4. Samples: 68415560. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:07:49,595][320945] Avg episode reward: [(0, '4863.474')] [2023-03-08 05:07:49,680][321237] Updated weights for policy 0, policy_version 133680 (0.0004) [2023-03-08 05:07:53,191][321237] Updated weights for policy 0, policy_version 133760 (0.0004) [2023-03-08 05:07:54,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11343.8). Total num frames: 68501504. Throughput: 0: 11847.5. Samples: 68485700. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:07:54,595][320945] Avg episode reward: [(0, '4862.936')] [2023-03-08 05:07:54,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000133792_68501504.pth... [2023-03-08 05:07:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000133096_68145152.pth [2023-03-08 05:07:56,725][321237] Updated weights for policy 0, policy_version 133840 (0.0004) [2023-03-08 05:07:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11343.8). Total num frames: 68558848. Throughput: 0: 11798.2. Samples: 68554992. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:07:59,605][320945] Avg episode reward: [(0, '4861.555')] [2023-03-08 05:08:00,313][321237] Updated weights for policy 0, policy_version 133920 (0.0005) [2023-03-08 05:08:03,685][321237] Updated weights for policy 0, policy_version 134000 (0.0005) [2023-03-08 05:08:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11357.7). Total num frames: 68616192. Throughput: 0: 11809.0. Samples: 68590960. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:08:04,605][320945] Avg episode reward: [(0, '4860.896')] [2023-03-08 05:08:07,098][321237] Updated weights for policy 0, policy_version 134080 (0.0004) [2023-03-08 05:08:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11371.6). Total num frames: 68677632. Throughput: 0: 11819.2. Samples: 68662892. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:08:09,605][320945] Avg episode reward: [(0, '4861.981')] [2023-03-08 05:08:09,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000134136_68677632.pth... [2023-03-08 05:08:09,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000133440_68321280.pth [2023-03-08 05:08:10,530][321237] Updated weights for policy 0, policy_version 134160 (0.0004) [2023-03-08 05:08:14,020][321237] Updated weights for policy 0, policy_version 134240 (0.0004) [2023-03-08 05:08:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11371.6). Total num frames: 68734976. Throughput: 0: 11832.3. Samples: 68733848. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:08:14,605][320945] Avg episode reward: [(0, '4864.860')] [2023-03-08 05:08:17,399][321237] Updated weights for policy 0, policy_version 134320 (0.0003) [2023-03-08 05:08:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11385.5). Total num frames: 68796416. Throughput: 0: 11875.2. Samples: 68770288. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:08:19,605][320945] Avg episode reward: [(0, '4862.753')] [2023-03-08 05:08:20,841][321237] Updated weights for policy 0, policy_version 134400 (0.0004) [2023-03-08 05:08:24,346][321237] Updated weights for policy 0, policy_version 134480 (0.0004) [2023-03-08 05:08:24,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11385.5). Total num frames: 68853760. Throughput: 0: 11853.1. Samples: 68841480. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:08:24,605][320945] Avg episode reward: [(0, '4865.133')] [2023-03-08 05:08:24,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000134480_68853760.pth... [2023-03-08 05:08:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000133792_68501504.pth [2023-03-08 05:08:27,897][321237] Updated weights for policy 0, policy_version 134560 (0.0004) [2023-03-08 05:08:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11371.6). Total num frames: 68911104. Throughput: 0: 11792.2. Samples: 68911044. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:08:29,605][320945] Avg episode reward: [(0, '4863.667')] [2023-03-08 05:08:31,415][321237] Updated weights for policy 0, policy_version 134640 (0.0004) [2023-03-08 05:08:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11385.5). Total num frames: 68972544. Throughput: 0: 11779.6. Samples: 68945644. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:08:34,605][320945] Avg episode reward: [(0, '4863.346')] [2023-03-08 05:08:34,913][321237] Updated weights for policy 0, policy_version 134720 (0.0004) [2023-03-08 05:08:38,476][321237] Updated weights for policy 0, policy_version 134800 (0.0005) [2023-03-08 05:08:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11399.4). Total num frames: 69029888. Throughput: 0: 11760.8. Samples: 69014936. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:08:39,605][320945] Avg episode reward: [(0, '4863.339')] [2023-03-08 05:08:39,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000134824_69029888.pth... [2023-03-08 05:08:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000134136_68677632.pth [2023-03-08 05:08:42,046][321237] Updated weights for policy 0, policy_version 134880 (0.0004) [2023-03-08 05:08:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11399.4). Total num frames: 69087232. Throughput: 0: 11743.4. Samples: 69083444. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:08:44,605][320945] Avg episode reward: [(0, '4864.508')] [2023-03-08 05:08:45,579][321237] Updated weights for policy 0, policy_version 134960 (0.0004) [2023-03-08 05:08:49,060][321237] Updated weights for policy 0, policy_version 135040 (0.0005) [2023-03-08 05:08:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11385.5). Total num frames: 69144576. Throughput: 0: 11756.4. Samples: 69120000. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:08:49,605][320945] Avg episode reward: [(0, '4861.574')] [2023-03-08 05:08:52,563][321237] Updated weights for policy 0, policy_version 135120 (0.0004) [2023-03-08 05:08:54,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11385.5). Total num frames: 69201920. Throughput: 0: 11706.8. Samples: 69189696. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:08:54,605][320945] Avg episode reward: [(0, '4862.546')] [2023-03-08 05:08:54,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000135160_69201920.pth... [2023-03-08 05:08:54,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000134480_68853760.pth [2023-03-08 05:08:56,090][321237] Updated weights for policy 0, policy_version 135200 (0.0004) [2023-03-08 05:08:59,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11385.5). Total num frames: 69259264. Throughput: 0: 11667.2. Samples: 69258872. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:08:59,605][320945] Avg episode reward: [(0, '4865.485')] [2023-03-08 05:08:59,692][321237] Updated weights for policy 0, policy_version 135280 (0.0004) [2023-03-08 05:09:03,218][321237] Updated weights for policy 0, policy_version 135360 (0.0004) [2023-03-08 05:09:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11385.5). Total num frames: 69316608. Throughput: 0: 11617.3. Samples: 69293068. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:09:04,595][320945] Avg episode reward: [(0, '4865.239')] [2023-03-08 05:09:06,775][321237] Updated weights for policy 0, policy_version 135440 (0.0004) [2023-03-08 05:09:09,594][320945] Fps is (10 sec: 11878.2, 60 sec: 11673.6, 300 sec: 11413.3). Total num frames: 69378048. Throughput: 0: 11592.4. Samples: 69363140. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:09:09,595][320945] Avg episode reward: [(0, '4864.257')] [2023-03-08 05:09:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000135504_69378048.pth... [2023-03-08 05:09:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000134824_69029888.pth [2023-03-08 05:09:10,317][321237] Updated weights for policy 0, policy_version 135520 (0.0004) [2023-03-08 05:09:14,059][321237] Updated weights for policy 0, policy_version 135600 (0.0005) [2023-03-08 05:09:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11413.3). Total num frames: 69431296. Throughput: 0: 11522.3. Samples: 69429548. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:09:14,595][320945] Avg episode reward: [(0, '4863.109')] [2023-03-08 05:09:17,811][321237] Updated weights for policy 0, policy_version 135680 (0.0005) [2023-03-08 05:09:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11537.1, 300 sec: 11413.3). Total num frames: 69488640. Throughput: 0: 11489.4. Samples: 69462668. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:09:19,595][320945] Avg episode reward: [(0, '4863.899')] [2023-03-08 05:09:21,316][321237] Updated weights for policy 0, policy_version 135760 (0.0005) [2023-03-08 05:09:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11413.3). Total num frames: 69541888. Throughput: 0: 11453.2. Samples: 69530328. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:09:24,595][320945] Avg episode reward: [(0, '4863.083')] [2023-03-08 05:09:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000135824_69541888.pth... [2023-03-08 05:09:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000135160_69201920.pth [2023-03-08 05:09:25,113][321237] Updated weights for policy 0, policy_version 135840 (0.0005) [2023-03-08 05:09:28,963][321237] Updated weights for policy 0, policy_version 135920 (0.0006) [2023-03-08 05:09:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11400.5, 300 sec: 11413.3). Total num frames: 69595136. Throughput: 0: 11362.5. Samples: 69594756. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:09:29,595][320945] Avg episode reward: [(0, '4865.603')] [2023-03-08 05:09:32,883][321237] Updated weights for policy 0, policy_version 136000 (0.0005) [2023-03-08 05:09:34,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 11399.4). Total num frames: 69648384. Throughput: 0: 11234.5. Samples: 69625552. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:09:34,595][320945] Avg episode reward: [(0, '4865.349')] [2023-03-08 05:09:36,770][321237] Updated weights for policy 0, policy_version 136080 (0.0005) [2023-03-08 05:09:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11385.5). Total num frames: 69701632. Throughput: 0: 11104.9. Samples: 69689416. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:09:39,595][320945] Avg episode reward: [(0, '4863.272')] [2023-03-08 05:09:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000136136_69701632.pth... [2023-03-08 05:09:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000135504_69378048.pth [2023-03-08 05:09:40,447][321237] Updated weights for policy 0, policy_version 136160 (0.0005) [2023-03-08 05:09:44,224][321237] Updated weights for policy 0, policy_version 136240 (0.0006) [2023-03-08 05:09:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11385.5). Total num frames: 69758976. Throughput: 0: 11024.2. Samples: 69754960. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:09:44,595][320945] Avg episode reward: [(0, '4862.560')] [2023-03-08 05:09:48,018][321237] Updated weights for policy 0, policy_version 136320 (0.0006) [2023-03-08 05:09:49,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11059.2, 300 sec: 11371.6). Total num frames: 69808128. Throughput: 0: 10992.5. Samples: 69787728. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:09:49,594][320945] Avg episode reward: [(0, '4861.541')] [2023-03-08 05:09:51,810][321237] Updated weights for policy 0, policy_version 136400 (0.0005) [2023-03-08 05:09:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11371.6). Total num frames: 69865472. Throughput: 0: 10891.5. Samples: 69853256. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:09:54,595][320945] Avg episode reward: [(0, '4862.338')] [2023-03-08 05:09:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000136456_69865472.pth... [2023-03-08 05:09:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000135824_69541888.pth [2023-03-08 05:09:55,593][321237] Updated weights for policy 0, policy_version 136480 (0.0004) [2023-03-08 05:09:59,339][321237] Updated weights for policy 0, policy_version 136560 (0.0005) [2023-03-08 05:09:59,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 11357.7). Total num frames: 69918720. Throughput: 0: 10861.6. Samples: 69918320. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:09:59,595][320945] Avg episode reward: [(0, '4864.017')] [2023-03-08 05:10:02,928][321237] Updated weights for policy 0, policy_version 136640 (0.0005) [2023-03-08 05:10:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11357.7). Total num frames: 69976064. Throughput: 0: 10876.2. Samples: 69952096. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:10:04,595][320945] Avg episode reward: [(0, '4865.529')] [2023-03-08 05:10:06,493][321237] Updated weights for policy 0, policy_version 136720 (0.0005) [2023-03-08 05:10:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10922.7, 300 sec: 11357.7). Total num frames: 70033408. Throughput: 0: 10907.9. Samples: 70021184. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:10:09,595][320945] Avg episode reward: [(0, '4860.665')] [2023-03-08 05:10:09,631][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000136792_70037504.pth... [2023-03-08 05:10:09,633][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000136136_69701632.pth [2023-03-08 05:10:09,965][321237] Updated weights for policy 0, policy_version 136800 (0.0005) [2023-03-08 05:10:13,482][321237] Updated weights for policy 0, policy_version 136880 (0.0005) [2023-03-08 05:10:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11059.2, 300 sec: 11371.6). Total num frames: 70094848. Throughput: 0: 11040.6. Samples: 70091584. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:10:14,595][320945] Avg episode reward: [(0, '4861.516')] [2023-03-08 05:10:17,076][321237] Updated weights for policy 0, policy_version 136960 (0.0005) [2023-03-08 05:10:19,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11059.2, 300 sec: 11371.6). Total num frames: 70152192. Throughput: 0: 11117.1. Samples: 70125820. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:10:19,595][320945] Avg episode reward: [(0, '4863.820')] [2023-03-08 05:10:20,590][321237] Updated weights for policy 0, policy_version 137040 (0.0005) [2023-03-08 05:10:24,068][321237] Updated weights for policy 0, policy_version 137120 (0.0004) [2023-03-08 05:10:24,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11127.5, 300 sec: 11371.6). Total num frames: 70209536. Throughput: 0: 11262.2. Samples: 70196216. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:10:24,595][320945] Avg episode reward: [(0, '4863.609')] [2023-03-08 05:10:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000137128_70209536.pth... [2023-03-08 05:10:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000136456_69865472.pth [2023-03-08 05:10:27,572][321237] Updated weights for policy 0, policy_version 137200 (0.0004) [2023-03-08 05:10:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11371.6). Total num frames: 70266880. Throughput: 0: 11372.5. Samples: 70266724. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:10:29,595][320945] Avg episode reward: [(0, '4864.779')] [2023-03-08 05:10:31,048][321237] Updated weights for policy 0, policy_version 137280 (0.0004) [2023-03-08 05:10:34,536][321237] Updated weights for policy 0, policy_version 137360 (0.0004) [2023-03-08 05:10:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11332.3, 300 sec: 11399.4). Total num frames: 70328320. Throughput: 0: 11415.8. Samples: 70301440. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:10:34,605][320945] Avg episode reward: [(0, '4862.063')] [2023-03-08 05:10:38,316][321237] Updated weights for policy 0, policy_version 137440 (0.0005) [2023-03-08 05:10:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11385.5). Total num frames: 70381568. Throughput: 0: 11465.8. Samples: 70369216. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:10:39,605][320945] Avg episode reward: [(0, '4864.140')] [2023-03-08 05:10:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000137464_70381568.pth... [2023-03-08 05:10:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000136792_70037504.pth [2023-03-08 05:10:42,069][321237] Updated weights for policy 0, policy_version 137520 (0.0005) [2023-03-08 05:10:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11399.4). Total num frames: 70438912. Throughput: 0: 11506.4. Samples: 70436108. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 05:10:44,605][320945] Avg episode reward: [(0, '4865.555')] [2023-03-08 05:10:45,566][321237] Updated weights for policy 0, policy_version 137600 (0.0005) [2023-03-08 05:10:49,020][321237] Updated weights for policy 0, policy_version 137680 (0.0005) [2023-03-08 05:10:49,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11399.4). Total num frames: 70496256. Throughput: 0: 11546.5. Samples: 70471688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:10:49,595][320945] Avg episode reward: [(0, '4861.864')] [2023-03-08 05:10:52,469][321237] Updated weights for policy 0, policy_version 137760 (0.0004) [2023-03-08 05:10:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 11399.4). Total num frames: 70553600. Throughput: 0: 11560.7. Samples: 70541416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:10:54,595][320945] Avg episode reward: [(0, '4864.300')] [2023-03-08 05:10:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000137800_70553600.pth... [2023-03-08 05:10:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000137128_70209536.pth [2023-03-08 05:10:56,075][321237] Updated weights for policy 0, policy_version 137840 (0.0005) [2023-03-08 05:10:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11413.3). Total num frames: 70610944. Throughput: 0: 11497.4. Samples: 70608968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:10:59,595][320945] Avg episode reward: [(0, '4861.861')] [2023-03-08 05:10:59,770][321237] Updated weights for policy 0, policy_version 137920 (0.0003) [2023-03-08 05:11:03,129][321237] Updated weights for policy 0, policy_version 138000 (0.0005) [2023-03-08 05:11:04,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11441.0). Total num frames: 70672384. Throughput: 0: 11545.3. Samples: 70645360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:11:04,595][320945] Avg episode reward: [(0, '4862.235')] [2023-03-08 05:11:06,565][321237] Updated weights for policy 0, policy_version 138080 (0.0005) [2023-03-08 05:11:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11441.0). Total num frames: 70729728. Throughput: 0: 11584.2. Samples: 70717504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:11:09,594][320945] Avg episode reward: [(0, '4861.826')] [2023-03-08 05:11:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000138152_70733824.pth... [2023-03-08 05:11:09,598][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000137464_70381568.pth [2023-03-08 05:11:09,936][321237] Updated weights for policy 0, policy_version 138160 (0.0004) [2023-03-08 05:11:13,409][321237] Updated weights for policy 0, policy_version 138240 (0.0005) [2023-03-08 05:11:14,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11468.8). Total num frames: 70791168. Throughput: 0: 11598.1. Samples: 70788640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:11:14,595][320945] Avg episode reward: [(0, '4864.160')] [2023-03-08 05:11:16,909][321237] Updated weights for policy 0, policy_version 138320 (0.0004) [2023-03-08 05:11:19,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11482.7). Total num frames: 70848512. Throughput: 0: 11612.4. Samples: 70824000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:11:19,595][320945] Avg episode reward: [(0, '4862.251')] [2023-03-08 05:11:20,617][321237] Updated weights for policy 0, policy_version 138400 (0.0004) [2023-03-08 05:11:24,091][321237] Updated weights for policy 0, policy_version 138480 (0.0003) [2023-03-08 05:11:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11482.7). Total num frames: 70905856. Throughput: 0: 11621.5. Samples: 70892184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:11:24,595][320945] Avg episode reward: [(0, '4863.647')] [2023-03-08 05:11:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000138488_70905856.pth... [2023-03-08 05:11:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000137800_70553600.pth [2023-03-08 05:11:27,622][321237] Updated weights for policy 0, policy_version 138560 (0.0003) [2023-03-08 05:11:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11496.6). Total num frames: 70963200. Throughput: 0: 11664.8. Samples: 70961024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:11:29,595][320945] Avg episode reward: [(0, '4861.648')] [2023-03-08 05:11:31,272][321237] Updated weights for policy 0, policy_version 138640 (0.0003) [2023-03-08 05:11:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11510.5). Total num frames: 71020544. Throughput: 0: 11638.8. Samples: 70995436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:11:34,595][320945] Avg episode reward: [(0, '4864.086')] [2023-03-08 05:11:34,853][321237] Updated weights for policy 0, policy_version 138720 (0.0004) [2023-03-08 05:11:38,440][321237] Updated weights for policy 0, policy_version 138800 (0.0003) [2023-03-08 05:11:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11510.5). Total num frames: 71077888. Throughput: 0: 11609.3. Samples: 71063836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:11:39,595][320945] Avg episode reward: [(0, '4862.069')] [2023-03-08 05:11:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000138824_71077888.pth... [2023-03-08 05:11:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000138152_70733824.pth [2023-03-08 05:11:42,207][321237] Updated weights for policy 0, policy_version 138880 (0.0003) [2023-03-08 05:11:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11510.5). Total num frames: 71131136. Throughput: 0: 11542.8. Samples: 71128396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:11:44,595][320945] Avg episode reward: [(0, '4863.664')] [2023-03-08 05:11:46,050][321237] Updated weights for policy 0, policy_version 138960 (0.0003) [2023-03-08 05:11:49,591][321237] Updated weights for policy 0, policy_version 139040 (0.0004) [2023-03-08 05:11:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11524.3). Total num frames: 71188480. Throughput: 0: 11479.9. Samples: 71161956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:11:49,595][320945] Avg episode reward: [(0, '4859.801')] [2023-03-08 05:11:53,072][321237] Updated weights for policy 0, policy_version 139120 (0.0003) [2023-03-08 05:11:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11524.3). Total num frames: 71245824. Throughput: 0: 11432.0. Samples: 71231944. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:11:54,595][320945] Avg episode reward: [(0, '4861.293')] [2023-03-08 05:11:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000139152_71245824.pth... [2023-03-08 05:11:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000138488_70905856.pth [2023-03-08 05:11:56,556][321237] Updated weights for policy 0, policy_version 139200 (0.0004) [2023-03-08 05:11:59,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11510.5). Total num frames: 71303168. Throughput: 0: 11384.0. Samples: 71300920. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:11:59,595][320945] Avg episode reward: [(0, '4862.425')] [2023-03-08 05:12:00,170][321237] Updated weights for policy 0, policy_version 139280 (0.0003) [2023-03-08 05:12:03,854][321237] Updated weights for policy 0, policy_version 139360 (0.0004) [2023-03-08 05:12:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11510.5). Total num frames: 71360512. Throughput: 0: 11361.3. Samples: 71335260. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:12:04,595][320945] Avg episode reward: [(0, '4863.401')] [2023-03-08 05:12:07,383][321237] Updated weights for policy 0, policy_version 139440 (0.0003) [2023-03-08 05:12:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11496.6). Total num frames: 71417856. Throughput: 0: 11356.6. Samples: 71403232. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:12:09,595][320945] Avg episode reward: [(0, '4862.826')] [2023-03-08 05:12:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000139488_71417856.pth... [2023-03-08 05:12:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000138824_71077888.pth [2023-03-08 05:12:11,058][321237] Updated weights for policy 0, policy_version 139520 (0.0003) [2023-03-08 05:12:14,536][321237] Updated weights for policy 0, policy_version 139600 (0.0003) [2023-03-08 05:12:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11482.7). Total num frames: 71475200. Throughput: 0: 11343.5. Samples: 71471480. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:12:14,595][320945] Avg episode reward: [(0, '4860.909')] [2023-03-08 05:12:18,215][321237] Updated weights for policy 0, policy_version 139680 (0.0004) [2023-03-08 05:12:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11468.8). Total num frames: 71528448. Throughput: 0: 11329.5. Samples: 71505264. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:12:19,595][320945] Avg episode reward: [(0, '4861.167')] [2023-03-08 05:12:21,874][321237] Updated weights for policy 0, policy_version 139760 (0.0003) [2023-03-08 05:12:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11468.8). Total num frames: 71585792. Throughput: 0: 11311.6. Samples: 71572856. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:12:24,595][320945] Avg episode reward: [(0, '4864.389')] [2023-03-08 05:12:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000139816_71585792.pth... [2023-03-08 05:12:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000139152_71245824.pth [2023-03-08 05:12:25,431][321237] Updated weights for policy 0, policy_version 139840 (0.0003) [2023-03-08 05:12:28,940][321237] Updated weights for policy 0, policy_version 139920 (0.0003) [2023-03-08 05:12:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11468.8). Total num frames: 71643136. Throughput: 0: 11438.7. Samples: 71643136. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:12:29,595][320945] Avg episode reward: [(0, '4863.769')] [2023-03-08 05:12:32,724][321237] Updated weights for policy 0, policy_version 140000 (0.0003) [2023-03-08 05:12:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11454.9). Total num frames: 71700480. Throughput: 0: 11412.6. Samples: 71675524. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:12:34,595][320945] Avg episode reward: [(0, '4865.670')] [2023-03-08 05:12:36,452][321237] Updated weights for policy 0, policy_version 140080 (0.0004) [2023-03-08 05:12:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11427.1). Total num frames: 71753728. Throughput: 0: 11304.8. Samples: 71740660. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:12:39,595][320945] Avg episode reward: [(0, '4861.400')] [2023-03-08 05:12:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000140144_71753728.pth... [2023-03-08 05:12:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000139488_71417856.pth [2023-03-08 05:12:40,298][321237] Updated weights for policy 0, policy_version 140160 (0.0005) [2023-03-08 05:12:43,795][321237] Updated weights for policy 0, policy_version 140240 (0.0003) [2023-03-08 05:12:44,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11427.2). Total num frames: 71811072. Throughput: 0: 11258.7. Samples: 71807560. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:12:44,594][320945] Avg episode reward: [(0, '4861.891')] [2023-03-08 05:12:47,525][321237] Updated weights for policy 0, policy_version 140320 (0.0003) [2023-03-08 05:12:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11399.4). Total num frames: 71864320. Throughput: 0: 11222.7. Samples: 71840280. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:12:49,595][320945] Avg episode reward: [(0, '4862.130')] [2023-03-08 05:12:51,146][321237] Updated weights for policy 0, policy_version 140400 (0.0003) [2023-03-08 05:12:54,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11399.4). Total num frames: 71921664. Throughput: 0: 11247.7. Samples: 71909380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:12:54,595][320945] Avg episode reward: [(0, '4864.181')] [2023-03-08 05:12:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000140472_71921664.pth... [2023-03-08 05:12:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000139816_71585792.pth [2023-03-08 05:12:54,737][321237] Updated weights for policy 0, policy_version 140480 (0.0004) [2023-03-08 05:12:58,400][321237] Updated weights for policy 0, policy_version 140560 (0.0003) [2023-03-08 05:12:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11399.4). Total num frames: 71979008. Throughput: 0: 11229.2. Samples: 71976796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:12:59,595][320945] Avg episode reward: [(0, '4864.452')] [2023-03-08 05:13:02,027][321237] Updated weights for policy 0, policy_version 140640 (0.0003) [2023-03-08 05:13:04,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11195.7, 300 sec: 11371.6). Total num frames: 72032256. Throughput: 0: 11232.3. Samples: 72010716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:13:04,595][320945] Avg episode reward: [(0, '4820.388')] [2023-03-08 05:13:05,817][321237] Updated weights for policy 0, policy_version 140720 (0.0005) [2023-03-08 05:13:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11357.7). Total num frames: 72085504. Throughput: 0: 11141.2. Samples: 72074212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:13:09,595][320945] Avg episode reward: [(0, '4862.315')] [2023-03-08 05:13:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000140792_72085504.pth... [2023-03-08 05:13:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000140144_71753728.pth [2023-03-08 05:13:09,707][321237] Updated weights for policy 0, policy_version 140800 (0.0005) [2023-03-08 05:13:13,531][321237] Updated weights for policy 0, policy_version 140880 (0.0005) [2023-03-08 05:13:14,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11059.2, 300 sec: 11330.0). Total num frames: 72138752. Throughput: 0: 11013.9. Samples: 72138760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:13:14,594][320945] Avg episode reward: [(0, '4863.746')] [2023-03-08 05:13:17,169][321237] Updated weights for policy 0, policy_version 140960 (0.0004) [2023-03-08 05:13:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11127.5, 300 sec: 11330.0). Total num frames: 72196096. Throughput: 0: 11042.8. Samples: 72172448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:13:19,594][320945] Avg episode reward: [(0, '4817.940')] [2023-03-08 05:13:20,697][321237] Updated weights for policy 0, policy_version 141040 (0.0005) [2023-03-08 05:13:24,225][321237] Updated weights for policy 0, policy_version 141120 (0.0004) [2023-03-08 05:13:24,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11195.7, 300 sec: 11343.8). Total num frames: 72257536. Throughput: 0: 11156.0. Samples: 72242680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:13:24,595][320945] Avg episode reward: [(0, '4863.903')] [2023-03-08 05:13:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000141128_72257536.pth... [2023-03-08 05:13:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000140472_71921664.pth [2023-03-08 05:13:27,715][321237] Updated weights for policy 0, policy_version 141200 (0.0004) [2023-03-08 05:13:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11195.7, 300 sec: 11330.0). Total num frames: 72314880. Throughput: 0: 11219.4. Samples: 72312436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:13:29,595][320945] Avg episode reward: [(0, '4860.297')] [2023-03-08 05:13:31,252][321237] Updated weights for policy 0, policy_version 141280 (0.0004) [2023-03-08 05:13:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11195.7, 300 sec: 11330.0). Total num frames: 72372224. Throughput: 0: 11259.7. Samples: 72346968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:13:34,595][320945] Avg episode reward: [(0, '4863.149')] [2023-03-08 05:13:34,817][321237] Updated weights for policy 0, policy_version 141360 (0.0005) [2023-03-08 05:13:38,274][321237] Updated weights for policy 0, policy_version 141440 (0.0005) [2023-03-08 05:13:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11330.0). Total num frames: 72429568. Throughput: 0: 11286.7. Samples: 72417280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:13:39,595][320945] Avg episode reward: [(0, '4861.489')] [2023-03-08 05:13:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000141464_72429568.pth... [2023-03-08 05:13:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000140792_72085504.pth [2023-03-08 05:13:41,902][321237] Updated weights for policy 0, policy_version 141520 (0.0004) [2023-03-08 05:13:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11330.0). Total num frames: 72486912. Throughput: 0: 11292.0. Samples: 72484936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:13:44,595][320945] Avg episode reward: [(0, '4864.314')] [2023-03-08 05:13:45,610][321237] Updated weights for policy 0, policy_version 141600 (0.0005) [2023-03-08 05:13:49,550][321237] Updated weights for policy 0, policy_version 141680 (0.0005) [2023-03-08 05:13:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11316.1). Total num frames: 72540160. Throughput: 0: 11239.4. Samples: 72516488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:13:49,595][320945] Avg episode reward: [(0, '4821.737')] [2023-03-08 05:13:53,428][321237] Updated weights for policy 0, policy_version 141760 (0.0005) [2023-03-08 05:13:54,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11195.7, 300 sec: 11302.2). Total num frames: 72593408. Throughput: 0: 11231.9. Samples: 72579648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:13:54,595][320945] Avg episode reward: [(0, '4864.935')] [2023-03-08 05:13:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000141784_72593408.pth... [2023-03-08 05:13:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000141128_72257536.pth [2023-03-08 05:13:57,248][321237] Updated weights for policy 0, policy_version 141840 (0.0005) [2023-03-08 05:13:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11288.3). Total num frames: 72646656. Throughput: 0: 11213.5. Samples: 72643368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:13:59,595][320945] Avg episode reward: [(0, '4864.724')] [2023-03-08 05:14:01,023][321237] Updated weights for policy 0, policy_version 141920 (0.0005) [2023-03-08 05:14:04,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11127.5, 300 sec: 11260.5). Total num frames: 72699904. Throughput: 0: 11181.0. Samples: 72675592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:14:04,595][320945] Avg episode reward: [(0, '4863.626')] [2023-03-08 05:14:04,723][321237] Updated weights for policy 0, policy_version 142000 (0.0003) [2023-03-08 05:14:08,479][321237] Updated weights for policy 0, policy_version 142080 (0.0003) [2023-03-08 05:14:09,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11127.5, 300 sec: 11260.5). Total num frames: 72753152. Throughput: 0: 11104.6. Samples: 72742388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:14:09,594][320945] Avg episode reward: [(0, '4818.111')] [2023-03-08 05:14:09,603][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000142104_72757248.pth... [2023-03-08 05:14:09,606][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000141464_72429568.pth [2023-03-08 05:14:12,271][321237] Updated weights for policy 0, policy_version 142160 (0.0004) [2023-03-08 05:14:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11260.5). Total num frames: 72810496. Throughput: 0: 11021.0. Samples: 72808380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:14:14,595][320945] Avg episode reward: [(0, '4863.262')] [2023-03-08 05:14:15,884][321237] Updated weights for policy 0, policy_version 142240 (0.0003) [2023-03-08 05:14:19,463][321237] Updated weights for policy 0, policy_version 142320 (0.0003) [2023-03-08 05:14:19,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11195.7, 300 sec: 11274.4). Total num frames: 72867840. Throughput: 0: 11030.2. Samples: 72843328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:14:19,595][320945] Avg episode reward: [(0, '4861.889')] [2023-03-08 05:14:23,239][321237] Updated weights for policy 0, policy_version 142400 (0.0003) [2023-03-08 05:14:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11274.4). Total num frames: 72921088. Throughput: 0: 10924.3. Samples: 72908872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:14:24,595][320945] Avg episode reward: [(0, '4864.756')] [2023-03-08 05:14:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000142424_72921088.pth... [2023-03-08 05:14:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000141784_72593408.pth [2023-03-08 05:14:27,011][321237] Updated weights for policy 0, policy_version 142480 (0.0004) [2023-03-08 05:14:29,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10990.9, 300 sec: 11274.4). Total num frames: 72974336. Throughput: 0: 10877.2. Samples: 72974408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:14:29,594][320945] Avg episode reward: [(0, '4863.487')] [2023-03-08 05:14:30,752][321237] Updated weights for policy 0, policy_version 142560 (0.0005) [2023-03-08 05:14:34,523][321237] Updated weights for policy 0, policy_version 142640 (0.0004) [2023-03-08 05:14:34,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11288.3). Total num frames: 73031680. Throughput: 0: 10902.6. Samples: 73007104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:14:34,595][320945] Avg episode reward: [(0, '4866.547')] [2023-03-08 05:14:38,249][321237] Updated weights for policy 0, policy_version 142720 (0.0003) [2023-03-08 05:14:39,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 11274.4). Total num frames: 73084928. Throughput: 0: 10956.8. Samples: 73072704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:14:39,595][320945] Avg episode reward: [(0, '4865.765')] [2023-03-08 05:14:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000142744_73084928.pth... [2023-03-08 05:14:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000142104_72757248.pth [2023-03-08 05:14:41,970][321237] Updated weights for policy 0, policy_version 142800 (0.0005) [2023-03-08 05:14:44,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 11288.3). Total num frames: 73138176. Throughput: 0: 10995.7. Samples: 73138176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:14:44,595][320945] Avg episode reward: [(0, '4818.727')] [2023-03-08 05:14:45,694][321237] Updated weights for policy 0, policy_version 142880 (0.0004) [2023-03-08 05:14:49,287][321237] Updated weights for policy 0, policy_version 142960 (0.0003) [2023-03-08 05:14:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10922.7, 300 sec: 11288.3). Total num frames: 73195520. Throughput: 0: 11053.5. Samples: 73173000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:14:49,594][320945] Avg episode reward: [(0, '4864.338')] [2023-03-08 05:14:52,904][321237] Updated weights for policy 0, policy_version 143040 (0.0003) [2023-03-08 05:14:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 10990.9, 300 sec: 11302.2). Total num frames: 73252864. Throughput: 0: 11071.1. Samples: 73240588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:14:54,595][320945] Avg episode reward: [(0, '4865.213')] [2023-03-08 05:14:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000143072_73252864.pth... [2023-03-08 05:14:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000142424_72921088.pth [2023-03-08 05:14:56,675][321237] Updated weights for policy 0, policy_version 143120 (0.0004) [2023-03-08 05:14:59,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 11288.3). Total num frames: 73306112. Throughput: 0: 11060.7. Samples: 73306112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:14:59,595][320945] Avg episode reward: [(0, '4864.742')] [2023-03-08 05:15:00,467][321237] Updated weights for policy 0, policy_version 143200 (0.0005) [2023-03-08 05:15:04,084][321237] Updated weights for policy 0, policy_version 143280 (0.0005) [2023-03-08 05:15:04,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11059.2, 300 sec: 11288.3). Total num frames: 73363456. Throughput: 0: 11007.4. Samples: 73338660. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:15:04,595][320945] Avg episode reward: [(0, '4864.867')] [2023-03-08 05:15:07,562][321237] Updated weights for policy 0, policy_version 143360 (0.0005) [2023-03-08 05:15:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 11274.4). Total num frames: 73420800. Throughput: 0: 11103.3. Samples: 73408520. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:15:09,595][320945] Avg episode reward: [(0, '4863.713')] [2023-03-08 05:15:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000143400_73420800.pth... [2023-03-08 05:15:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000142744_73084928.pth [2023-03-08 05:15:11,170][321237] Updated weights for policy 0, policy_version 143440 (0.0004) [2023-03-08 05:15:14,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11059.2, 300 sec: 11260.5). Total num frames: 73474048. Throughput: 0: 11110.9. Samples: 73474400. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:15:14,595][320945] Avg episode reward: [(0, '4863.021')] [2023-03-08 05:15:14,995][321237] Updated weights for policy 0, policy_version 143520 (0.0005) [2023-03-08 05:15:18,727][321237] Updated weights for policy 0, policy_version 143600 (0.0005) [2023-03-08 05:15:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11260.5). Total num frames: 73531392. Throughput: 0: 11115.4. Samples: 73507296. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:15:19,595][320945] Avg episode reward: [(0, '4865.936')] [2023-03-08 05:15:22,511][321237] Updated weights for policy 0, policy_version 143680 (0.0005) [2023-03-08 05:15:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 11260.5). Total num frames: 73588736. Throughput: 0: 11121.2. Samples: 73573160. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:15:24,595][320945] Avg episode reward: [(0, '4862.633')] [2023-03-08 05:15:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000143728_73588736.pth... [2023-03-08 05:15:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000143072_73252864.pth [2023-03-08 05:15:25,945][321237] Updated weights for policy 0, policy_version 143760 (0.0004) [2023-03-08 05:15:29,523][321237] Updated weights for policy 0, policy_version 143840 (0.0005) [2023-03-08 05:15:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11246.6). Total num frames: 73646080. Throughput: 0: 11220.4. Samples: 73643092. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:15:29,595][320945] Avg episode reward: [(0, '4864.457')] [2023-03-08 05:15:33,094][321237] Updated weights for policy 0, policy_version 143920 (0.0004) [2023-03-08 05:15:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11260.5). Total num frames: 73703424. Throughput: 0: 11222.0. Samples: 73677992. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:15:34,595][320945] Avg episode reward: [(0, '4864.248')] [2023-03-08 05:15:36,574][321237] Updated weights for policy 0, policy_version 144000 (0.0005) [2023-03-08 05:15:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11260.5). Total num frames: 73760768. Throughput: 0: 11272.4. Samples: 73747844. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:15:39,595][320945] Avg episode reward: [(0, '4862.231')] [2023-03-08 05:15:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000144064_73760768.pth... [2023-03-08 05:15:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000143400_73420800.pth [2023-03-08 05:15:40,121][321237] Updated weights for policy 0, policy_version 144080 (0.0004) [2023-03-08 05:15:43,659][321237] Updated weights for policy 0, policy_version 144160 (0.0004) [2023-03-08 05:15:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11260.5). Total num frames: 73818112. Throughput: 0: 11338.6. Samples: 73816348. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:15:44,595][320945] Avg episode reward: [(0, '4818.068')] [2023-03-08 05:15:47,264][321237] Updated weights for policy 0, policy_version 144240 (0.0004) [2023-03-08 05:15:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.2, 300 sec: 11260.5). Total num frames: 73875456. Throughput: 0: 11382.8. Samples: 73850888. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:15:49,595][320945] Avg episode reward: [(0, '4866.038')] [2023-03-08 05:15:50,779][321237] Updated weights for policy 0, policy_version 144320 (0.0004) [2023-03-08 05:15:54,214][321237] Updated weights for policy 0, policy_version 144400 (0.0004) [2023-03-08 05:15:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11400.5, 300 sec: 11274.4). Total num frames: 73936896. Throughput: 0: 11391.5. Samples: 73921136. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:15:54,595][320945] Avg episode reward: [(0, '4861.397')] [2023-03-08 05:15:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000144408_73936896.pth... [2023-03-08 05:15:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000143728_73588736.pth [2023-03-08 05:15:57,784][321237] Updated weights for policy 0, policy_version 144480 (0.0005) [2023-03-08 05:15:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11260.5). Total num frames: 73994240. Throughput: 0: 11466.3. Samples: 73990384. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:15:59,595][320945] Avg episode reward: [(0, '4863.249')] [2023-03-08 05:16:01,311][321237] Updated weights for policy 0, policy_version 144560 (0.0005) [2023-03-08 05:16:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11260.5). Total num frames: 74051584. Throughput: 0: 11523.4. Samples: 74025848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:16:04,595][320945] Avg episode reward: [(0, '4860.531')] [2023-03-08 05:16:04,778][321237] Updated weights for policy 0, policy_version 144640 (0.0004) [2023-03-08 05:16:08,198][321237] Updated weights for policy 0, policy_version 144720 (0.0003) [2023-03-08 05:16:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11260.5). Total num frames: 74113024. Throughput: 0: 11643.8. Samples: 74097132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:16:09,595][320945] Avg episode reward: [(0, '4861.475')] [2023-03-08 05:16:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000144752_74113024.pth... [2023-03-08 05:16:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000144064_73760768.pth [2023-03-08 05:16:11,571][321237] Updated weights for policy 0, policy_version 144800 (0.0004) [2023-03-08 05:16:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11260.5). Total num frames: 74170368. Throughput: 0: 11716.4. Samples: 74170332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:16:14,595][320945] Avg episode reward: [(0, '4863.930')] [2023-03-08 05:16:15,016][321237] Updated weights for policy 0, policy_version 144880 (0.0004) [2023-03-08 05:16:18,601][321237] Updated weights for policy 0, policy_version 144960 (0.0005) [2023-03-08 05:16:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11260.5). Total num frames: 74227712. Throughput: 0: 11693.8. Samples: 74204212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:16:19,595][320945] Avg episode reward: [(0, '4860.920')] [2023-03-08 05:16:22,080][321237] Updated weights for policy 0, policy_version 145040 (0.0005) [2023-03-08 05:16:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11274.4). Total num frames: 74289152. Throughput: 0: 11693.1. Samples: 74274032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:16:24,595][320945] Avg episode reward: [(0, '4862.084')] [2023-03-08 05:16:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000145096_74289152.pth... [2023-03-08 05:16:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000144408_73936896.pth [2023-03-08 05:16:25,554][321237] Updated weights for policy 0, policy_version 145120 (0.0004) [2023-03-08 05:16:29,104][321237] Updated weights for policy 0, policy_version 145200 (0.0004) [2023-03-08 05:16:29,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 11274.4). Total num frames: 74346496. Throughput: 0: 11727.1. Samples: 74344068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:16:29,595][320945] Avg episode reward: [(0, '4861.945')] [2023-03-08 05:16:32,634][321237] Updated weights for policy 0, policy_version 145280 (0.0004) [2023-03-08 05:16:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11274.4). Total num frames: 74403840. Throughput: 0: 11741.1. Samples: 74379236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:16:34,595][320945] Avg episode reward: [(0, '4863.790')] [2023-03-08 05:16:36,127][321237] Updated weights for policy 0, policy_version 145360 (0.0004) [2023-03-08 05:16:39,526][321237] Updated weights for policy 0, policy_version 145440 (0.0004) [2023-03-08 05:16:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11302.2). Total num frames: 74465280. Throughput: 0: 11762.6. Samples: 74450452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:16:39,595][320945] Avg episode reward: [(0, '4862.043')] [2023-03-08 05:16:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000145440_74465280.pth... [2023-03-08 05:16:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000144752_74113024.pth [2023-03-08 05:16:43,089][321237] Updated weights for policy 0, policy_version 145520 (0.0004) [2023-03-08 05:16:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11302.2). Total num frames: 74522624. Throughput: 0: 11773.4. Samples: 74520188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:16:44,595][320945] Avg episode reward: [(0, '4863.853')] [2023-03-08 05:16:46,602][321237] Updated weights for policy 0, policy_version 145600 (0.0005) [2023-03-08 05:16:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11302.2). Total num frames: 74579968. Throughput: 0: 11764.4. Samples: 74555244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:16:49,595][320945] Avg episode reward: [(0, '4865.311')] [2023-03-08 05:16:50,053][321237] Updated weights for policy 0, policy_version 145680 (0.0004) [2023-03-08 05:16:53,483][321237] Updated weights for policy 0, policy_version 145760 (0.0004) [2023-03-08 05:16:54,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11316.1). Total num frames: 74641408. Throughput: 0: 11768.3. Samples: 74626704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:16:54,595][320945] Avg episode reward: [(0, '4864.584')] [2023-03-08 05:16:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000145784_74641408.pth... [2023-03-08 05:16:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000145096_74289152.pth [2023-03-08 05:16:56,884][321237] Updated weights for policy 0, policy_version 145840 (0.0004) [2023-03-08 05:16:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11316.1). Total num frames: 74698752. Throughput: 0: 11732.9. Samples: 74698312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:16:59,595][320945] Avg episode reward: [(0, '4863.587')] [2023-03-08 05:17:00,333][321237] Updated weights for policy 0, policy_version 145920 (0.0004) [2023-03-08 05:17:03,778][321237] Updated weights for policy 0, policy_version 146000 (0.0004) [2023-03-08 05:17:04,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11330.0). Total num frames: 74760192. Throughput: 0: 11779.0. Samples: 74734268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:17:04,595][320945] Avg episode reward: [(0, '4864.450')] [2023-03-08 05:17:07,295][321237] Updated weights for policy 0, policy_version 146080 (0.0005) [2023-03-08 05:17:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11329.9). Total num frames: 74817536. Throughput: 0: 11775.6. Samples: 74803936. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:17:09,595][320945] Avg episode reward: [(0, '4865.028')] [2023-03-08 05:17:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000146128_74817536.pth... [2023-03-08 05:17:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000145440_74465280.pth [2023-03-08 05:17:10,760][321237] Updated weights for policy 0, policy_version 146160 (0.0004) [2023-03-08 05:17:14,194][321237] Updated weights for policy 0, policy_version 146240 (0.0004) [2023-03-08 05:17:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11357.7). Total num frames: 74878976. Throughput: 0: 11807.5. Samples: 74875404. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:17:14,595][320945] Avg episode reward: [(0, '4863.538')] [2023-03-08 05:17:17,768][321237] Updated weights for policy 0, policy_version 146320 (0.0004) [2023-03-08 05:17:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11357.7). Total num frames: 74936320. Throughput: 0: 11805.3. Samples: 74910476. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:17:19,595][320945] Avg episode reward: [(0, '4865.831')] [2023-03-08 05:17:21,295][321237] Updated weights for policy 0, policy_version 146400 (0.0005) [2023-03-08 05:17:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11357.7). Total num frames: 74993664. Throughput: 0: 11752.3. Samples: 74979304. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:17:24,595][320945] Avg episode reward: [(0, '4863.629')] [2023-03-08 05:17:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000146472_74993664.pth... [2023-03-08 05:17:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000145784_74641408.pth [2023-03-08 05:17:24,840][321237] Updated weights for policy 0, policy_version 146480 (0.0004) [2023-03-08 05:17:28,312][321237] Updated weights for policy 0, policy_version 146560 (0.0004) [2023-03-08 05:17:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11357.7). Total num frames: 75051008. Throughput: 0: 11752.0. Samples: 75049028. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:17:29,595][320945] Avg episode reward: [(0, '4863.832')] [2023-03-08 05:17:31,887][321237] Updated weights for policy 0, policy_version 146640 (0.0004) [2023-03-08 05:17:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 11371.6). Total num frames: 75108352. Throughput: 0: 11746.8. Samples: 75083848. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:17:34,595][320945] Avg episode reward: [(0, '4862.006')] [2023-03-08 05:17:35,360][321237] Updated weights for policy 0, policy_version 146720 (0.0005) [2023-03-08 05:17:38,869][321237] Updated weights for policy 0, policy_version 146800 (0.0004) [2023-03-08 05:17:39,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11741.9, 300 sec: 11385.5). Total num frames: 75169792. Throughput: 0: 11721.1. Samples: 75154152. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:17:39,595][320945] Avg episode reward: [(0, '4861.939')] [2023-03-08 05:17:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000146816_75169792.pth... [2023-03-08 05:17:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000146128_74817536.pth [2023-03-08 05:17:42,375][321237] Updated weights for policy 0, policy_version 146880 (0.0004) [2023-03-08 05:17:44,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11399.4). Total num frames: 75227136. Throughput: 0: 11692.0. Samples: 75224452. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:17:44,595][320945] Avg episode reward: [(0, '4859.190')] [2023-03-08 05:17:45,880][321237] Updated weights for policy 0, policy_version 146960 (0.0004) [2023-03-08 05:17:49,214][321237] Updated weights for policy 0, policy_version 147040 (0.0004) [2023-03-08 05:17:49,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11413.3). Total num frames: 75288576. Throughput: 0: 11682.9. Samples: 75260000. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:17:49,595][320945] Avg episode reward: [(0, '4862.133')] [2023-03-08 05:17:52,705][321237] Updated weights for policy 0, policy_version 147120 (0.0004) [2023-03-08 05:17:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11741.9, 300 sec: 11413.3). Total num frames: 75345920. Throughput: 0: 11733.9. Samples: 75331960. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:17:54,595][320945] Avg episode reward: [(0, '4861.071')] [2023-03-08 05:17:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000147160_75345920.pth... [2023-03-08 05:17:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000146472_74993664.pth [2023-03-08 05:17:56,153][321237] Updated weights for policy 0, policy_version 147200 (0.0004) [2023-03-08 05:17:59,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11427.1). Total num frames: 75403264. Throughput: 0: 11692.4. Samples: 75401560. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:17:59,595][320945] Avg episode reward: [(0, '4818.461')] [2023-03-08 05:17:59,767][321237] Updated weights for policy 0, policy_version 147280 (0.0005) [2023-03-08 05:18:03,350][321237] Updated weights for policy 0, policy_version 147360 (0.0005) [2023-03-08 05:18:04,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11441.0). Total num frames: 75460608. Throughput: 0: 11671.3. Samples: 75435684. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:18:04,595][320945] Avg episode reward: [(0, '4860.291')] [2023-03-08 05:18:06,885][321237] Updated weights for policy 0, policy_version 147440 (0.0004) [2023-03-08 05:18:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11454.9). Total num frames: 75517952. Throughput: 0: 11666.8. Samples: 75504308. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:18:09,595][320945] Avg episode reward: [(0, '4861.179')] [2023-03-08 05:18:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000147496_75517952.pth... [2023-03-08 05:18:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000146816_75169792.pth [2023-03-08 05:18:10,761][321237] Updated weights for policy 0, policy_version 147520 (0.0005) [2023-03-08 05:18:14,499][321237] Updated weights for policy 0, policy_version 147600 (0.0005) [2023-03-08 05:18:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11441.0). Total num frames: 75571200. Throughput: 0: 11535.2. Samples: 75568112. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:18:14,595][320945] Avg episode reward: [(0, '4863.674')] [2023-03-08 05:18:17,988][321237] Updated weights for policy 0, policy_version 147680 (0.0005) [2023-03-08 05:18:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11427.1). Total num frames: 75628544. Throughput: 0: 11557.9. Samples: 75603952. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:18:19,595][320945] Avg episode reward: [(0, '4857.420')] [2023-03-08 05:18:21,454][321237] Updated weights for policy 0, policy_version 147760 (0.0004) [2023-03-08 05:18:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11427.1). Total num frames: 75685888. Throughput: 0: 11544.7. Samples: 75673664. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:18:24,595][320945] Avg episode reward: [(0, '4863.882')] [2023-03-08 05:18:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000147824_75685888.pth... [2023-03-08 05:18:24,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000147160_75345920.pth [2023-03-08 05:18:25,035][321237] Updated weights for policy 0, policy_version 147840 (0.0004) [2023-03-08 05:18:28,629][321237] Updated weights for policy 0, policy_version 147920 (0.0004) [2023-03-08 05:18:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11427.1). Total num frames: 75743232. Throughput: 0: 11516.3. Samples: 75742688. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:18:29,595][320945] Avg episode reward: [(0, '4865.838')] [2023-03-08 05:18:32,129][321237] Updated weights for policy 0, policy_version 148000 (0.0005) [2023-03-08 05:18:34,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11441.0). Total num frames: 75804672. Throughput: 0: 11501.3. Samples: 75777560. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:18:34,595][320945] Avg episode reward: [(0, '4864.052')] [2023-03-08 05:18:35,571][321237] Updated weights for policy 0, policy_version 148080 (0.0004) [2023-03-08 05:18:39,093][321237] Updated weights for policy 0, policy_version 148160 (0.0004) [2023-03-08 05:18:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11441.0). Total num frames: 75862016. Throughput: 0: 11474.7. Samples: 75848320. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:18:39,595][320945] Avg episode reward: [(0, '4861.242')] [2023-03-08 05:18:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000148168_75862016.pth... [2023-03-08 05:18:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000147496_75517952.pth [2023-03-08 05:18:42,669][321237] Updated weights for policy 0, policy_version 148240 (0.0005) [2023-03-08 05:18:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11454.9). Total num frames: 75919360. Throughput: 0: 11458.0. Samples: 75917168. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:18:44,595][320945] Avg episode reward: [(0, '4774.786')] [2023-03-08 05:18:46,285][321237] Updated weights for policy 0, policy_version 148320 (0.0005) [2023-03-08 05:18:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11468.8). Total num frames: 75976704. Throughput: 0: 11478.0. Samples: 75952192. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:18:49,605][320945] Avg episode reward: [(0, '4863.976')] [2023-03-08 05:18:49,700][321237] Updated weights for policy 0, policy_version 148400 (0.0004) [2023-03-08 05:18:53,214][321237] Updated weights for policy 0, policy_version 148480 (0.0004) [2023-03-08 05:18:54,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11496.6). Total num frames: 76038144. Throughput: 0: 11504.1. Samples: 76021992. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:18:54,605][320945] Avg episode reward: [(0, '4866.329')] [2023-03-08 05:18:54,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000148512_76038144.pth... [2023-03-08 05:18:54,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000147824_75685888.pth [2023-03-08 05:18:56,653][321237] Updated weights for policy 0, policy_version 148560 (0.0004) [2023-03-08 05:18:59,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11510.5). Total num frames: 76095488. Throughput: 0: 11667.2. Samples: 76093136. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:18:59,595][320945] Avg episode reward: [(0, '4861.870')] [2023-03-08 05:19:00,158][321237] Updated weights for policy 0, policy_version 148640 (0.0004) [2023-03-08 05:19:03,616][321237] Updated weights for policy 0, policy_version 148720 (0.0004) [2023-03-08 05:19:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11524.3). Total num frames: 76152832. Throughput: 0: 11651.4. Samples: 76128264. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:19:04,595][320945] Avg episode reward: [(0, '4865.879')] [2023-03-08 05:19:07,062][321237] Updated weights for policy 0, policy_version 148800 (0.0004) [2023-03-08 05:19:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11538.2). Total num frames: 76214272. Throughput: 0: 11689.6. Samples: 76199696. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 05:19:09,595][320945] Avg episode reward: [(0, '4817.337')] [2023-03-08 05:19:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000148856_76214272.pth... [2023-03-08 05:19:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000148168_75862016.pth [2023-03-08 05:19:10,441][321237] Updated weights for policy 0, policy_version 148880 (0.0004) [2023-03-08 05:19:13,832][321237] Updated weights for policy 0, policy_version 148960 (0.0004) [2023-03-08 05:19:14,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11552.1). Total num frames: 76275712. Throughput: 0: 11763.7. Samples: 76272056. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:19:14,595][320945] Avg episode reward: [(0, '4817.225')] [2023-03-08 05:19:17,229][321237] Updated weights for policy 0, policy_version 149040 (0.0004) [2023-03-08 05:19:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 76333056. Throughput: 0: 11799.8. Samples: 76308552. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:19:19,595][320945] Avg episode reward: [(0, '4862.065')] [2023-03-08 05:19:20,817][321237] Updated weights for policy 0, policy_version 149120 (0.0004) [2023-03-08 05:19:24,349][321237] Updated weights for policy 0, policy_version 149200 (0.0004) [2023-03-08 05:19:24,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11579.9). Total num frames: 76390400. Throughput: 0: 11763.8. Samples: 76377692. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:19:24,595][320945] Avg episode reward: [(0, '4818.692')] [2023-03-08 05:19:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000149200_76390400.pth... [2023-03-08 05:19:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000148512_76038144.pth [2023-03-08 05:19:27,839][321237] Updated weights for policy 0, policy_version 149280 (0.0004) [2023-03-08 05:19:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11593.8). Total num frames: 76451840. Throughput: 0: 11806.0. Samples: 76448440. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:19:29,595][320945] Avg episode reward: [(0, '4863.983')] [2023-03-08 05:19:31,298][321237] Updated weights for policy 0, policy_version 149360 (0.0004) [2023-03-08 05:19:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11607.6). Total num frames: 76509184. Throughput: 0: 11812.0. Samples: 76483732. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:19:34,595][320945] Avg episode reward: [(0, '4818.525')] [2023-03-08 05:19:34,730][321237] Updated weights for policy 0, policy_version 149440 (0.0004) [2023-03-08 05:19:38,173][321237] Updated weights for policy 0, policy_version 149520 (0.0004) [2023-03-08 05:19:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11621.5). Total num frames: 76566528. Throughput: 0: 11847.3. Samples: 76555120. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:19:39,595][320945] Avg episode reward: [(0, '4773.880')] [2023-03-08 05:19:39,610][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000149552_76570624.pth... [2023-03-08 05:19:39,612][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000148856_76214272.pth [2023-03-08 05:19:41,876][321237] Updated weights for policy 0, policy_version 149600 (0.0005) [2023-03-08 05:19:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11621.5). Total num frames: 76623872. Throughput: 0: 11717.6. Samples: 76620428. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:19:44,595][320945] Avg episode reward: [(0, '4774.941')] [2023-03-08 05:19:45,758][321237] Updated weights for policy 0, policy_version 149680 (0.0005) [2023-03-08 05:19:49,554][321237] Updated weights for policy 0, policy_version 149760 (0.0005) [2023-03-08 05:19:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11673.6, 300 sec: 11607.6). Total num frames: 76677120. Throughput: 0: 11650.7. Samples: 76652544. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:19:49,595][320945] Avg episode reward: [(0, '4819.747')] [2023-03-08 05:19:53,425][321237] Updated weights for policy 0, policy_version 149840 (0.0005) [2023-03-08 05:19:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11537.1, 300 sec: 11607.6). Total num frames: 76730368. Throughput: 0: 11481.0. Samples: 76716340. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:19:54,595][320945] Avg episode reward: [(0, '4863.774')] [2023-03-08 05:19:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000149864_76730368.pth... [2023-03-08 05:19:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000149200_76390400.pth [2023-03-08 05:19:56,855][321237] Updated weights for policy 0, policy_version 149920 (0.0004) [2023-03-08 05:19:59,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11537.1, 300 sec: 11607.6). Total num frames: 76787712. Throughput: 0: 11432.6. Samples: 76786524. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:19:59,595][320945] Avg episode reward: [(0, '4820.385')] [2023-03-08 05:20:00,588][321237] Updated weights for policy 0, policy_version 150000 (0.0005) [2023-03-08 05:20:04,520][321237] Updated weights for policy 0, policy_version 150080 (0.0005) [2023-03-08 05:20:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11593.8). Total num frames: 76840960. Throughput: 0: 11289.4. Samples: 76816576. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:20:04,595][320945] Avg episode reward: [(0, '4818.918')] [2023-03-08 05:20:08,387][321237] Updated weights for policy 0, policy_version 150160 (0.0005) [2023-03-08 05:20:09,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11332.3, 300 sec: 11593.8). Total num frames: 76894208. Throughput: 0: 11178.7. Samples: 76880732. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:20:09,595][320945] Avg episode reward: [(0, '4864.198')] [2023-03-08 05:20:09,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000150184_76894208.pth... [2023-03-08 05:20:09,602][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000149552_76570624.pth [2023-03-08 05:20:12,243][321237] Updated weights for policy 0, policy_version 150240 (0.0005) [2023-03-08 05:20:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11579.9). Total num frames: 76947456. Throughput: 0: 11045.4. Samples: 76945484. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:20:14,595][320945] Avg episode reward: [(0, '4862.815')] [2023-03-08 05:20:16,038][321237] Updated weights for policy 0, policy_version 150320 (0.0005) [2023-03-08 05:20:19,594][320945] Fps is (10 sec: 10649.8, 60 sec: 11127.5, 300 sec: 11566.0). Total num frames: 77000704. Throughput: 0: 10981.0. Samples: 76977876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:20:19,594][320945] Avg episode reward: [(0, '4860.957')] [2023-03-08 05:20:19,649][321237] Updated weights for policy 0, policy_version 150400 (0.0005) [2023-03-08 05:20:23,189][321237] Updated weights for policy 0, policy_version 150480 (0.0005) [2023-03-08 05:20:24,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11195.7, 300 sec: 11579.9). Total num frames: 77062144. Throughput: 0: 10916.9. Samples: 77046380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:20:24,595][320945] Avg episode reward: [(0, '4822.137')] [2023-03-08 05:20:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000150512_77062144.pth... [2023-03-08 05:20:24,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000149864_76730368.pth [2023-03-08 05:20:26,751][321237] Updated weights for policy 0, policy_version 150560 (0.0005) [2023-03-08 05:20:29,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11059.2, 300 sec: 11566.0). Total num frames: 77115392. Throughput: 0: 10983.4. Samples: 77114680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:20:29,595][320945] Avg episode reward: [(0, '4863.958')] [2023-03-08 05:20:30,443][321237] Updated weights for policy 0, policy_version 150640 (0.0005) [2023-03-08 05:20:34,008][321237] Updated weights for policy 0, policy_version 150720 (0.0005) [2023-03-08 05:20:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11059.2, 300 sec: 11566.0). Total num frames: 77172736. Throughput: 0: 11034.6. Samples: 77149100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:20:34,595][320945] Avg episode reward: [(0, '4769.312')] [2023-03-08 05:20:37,530][321237] Updated weights for policy 0, policy_version 150800 (0.0004) [2023-03-08 05:20:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 11566.0). Total num frames: 77230080. Throughput: 0: 11144.8. Samples: 77217856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:20:39,595][320945] Avg episode reward: [(0, '4778.348')] [2023-03-08 05:20:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000150840_77230080.pth... [2023-03-08 05:20:39,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000150184_76894208.pth [2023-03-08 05:20:41,048][321237] Updated weights for policy 0, policy_version 150880 (0.0004) [2023-03-08 05:20:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 11566.0). Total num frames: 77287424. Throughput: 0: 11131.3. Samples: 77287432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:20:44,595][320945] Avg episode reward: [(0, '4864.530')] [2023-03-08 05:20:44,598][321237] Updated weights for policy 0, policy_version 150960 (0.0004) [2023-03-08 05:20:48,114][321237] Updated weights for policy 0, policy_version 151040 (0.0005) [2023-03-08 05:20:49,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11195.7, 300 sec: 11566.0). Total num frames: 77348864. Throughput: 0: 11248.0. Samples: 77322736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:20:49,595][320945] Avg episode reward: [(0, '4865.105')] [2023-03-08 05:20:51,590][321237] Updated weights for policy 0, policy_version 151120 (0.0004) [2023-03-08 05:20:54,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11264.0, 300 sec: 11566.0). Total num frames: 77406208. Throughput: 0: 11390.3. Samples: 77393296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:20:54,595][320945] Avg episode reward: [(0, '4865.774')] [2023-03-08 05:20:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000151184_77406208.pth... [2023-03-08 05:20:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000150512_77062144.pth [2023-03-08 05:20:55,097][321237] Updated weights for policy 0, policy_version 151200 (0.0004) [2023-03-08 05:20:58,616][321237] Updated weights for policy 0, policy_version 151280 (0.0005) [2023-03-08 05:20:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11566.0). Total num frames: 77463552. Throughput: 0: 11503.1. Samples: 77463124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:20:59,595][320945] Avg episode reward: [(0, '4864.922')] [2023-03-08 05:21:02,136][321237] Updated weights for policy 0, policy_version 151360 (0.0005) [2023-03-08 05:21:04,594][320945] Fps is (10 sec: 11469.0, 60 sec: 11332.3, 300 sec: 11552.1). Total num frames: 77520896. Throughput: 0: 11553.3. Samples: 77497776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:21:04,594][320945] Avg episode reward: [(0, '4862.577')] [2023-03-08 05:21:05,663][321237] Updated weights for policy 0, policy_version 151440 (0.0004) [2023-03-08 05:21:09,132][321237] Updated weights for policy 0, policy_version 151520 (0.0004) [2023-03-08 05:21:09,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11468.8, 300 sec: 11566.0). Total num frames: 77582336. Throughput: 0: 11588.6. Samples: 77567864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:21:09,594][320945] Avg episode reward: [(0, '4863.350')] [2023-03-08 05:21:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000151528_77582336.pth... [2023-03-08 05:21:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000150840_77230080.pth [2023-03-08 05:21:12,532][321237] Updated weights for policy 0, policy_version 151600 (0.0004) [2023-03-08 05:21:14,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11537.1, 300 sec: 11566.0). Total num frames: 77639680. Throughput: 0: 11666.9. Samples: 77639688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:21:14,595][320945] Avg episode reward: [(0, '4863.658')] [2023-03-08 05:21:16,002][321237] Updated weights for policy 0, policy_version 151680 (0.0004) [2023-03-08 05:21:19,391][321237] Updated weights for policy 0, policy_version 151760 (0.0004) [2023-03-08 05:21:19,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 11566.0). Total num frames: 77701120. Throughput: 0: 11704.3. Samples: 77675792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:21:19,595][320945] Avg episode reward: [(0, '4861.908')] [2023-03-08 05:21:22,930][321237] Updated weights for policy 0, policy_version 151840 (0.0004) [2023-03-08 05:21:24,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11566.0). Total num frames: 77758464. Throughput: 0: 11739.9. Samples: 77746152. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:21:24,595][320945] Avg episode reward: [(0, '4861.090')] [2023-03-08 05:21:24,617][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000151880_77762560.pth... [2023-03-08 05:21:24,618][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000151184_77406208.pth [2023-03-08 05:21:26,565][321237] Updated weights for policy 0, policy_version 151920 (0.0004) [2023-03-08 05:21:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11552.1). Total num frames: 77811712. Throughput: 0: 11650.7. Samples: 77811712. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:21:29,595][320945] Avg episode reward: [(0, '4864.424')] [2023-03-08 05:21:30,408][321237] Updated weights for policy 0, policy_version 152000 (0.0005) [2023-03-08 05:21:34,026][321237] Updated weights for policy 0, policy_version 152080 (0.0005) [2023-03-08 05:21:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11605.3, 300 sec: 11538.2). Total num frames: 77869056. Throughput: 0: 11605.2. Samples: 77844968. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:21:34,595][320945] Avg episode reward: [(0, '4821.187')] [2023-03-08 05:21:37,855][321237] Updated weights for policy 0, policy_version 152160 (0.0004) [2023-03-08 05:21:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11524.3). Total num frames: 77922304. Throughput: 0: 11484.3. Samples: 77910088. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:21:39,595][320945] Avg episode reward: [(0, '4821.713')] [2023-03-08 05:21:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000152192_77922304.pth... [2023-03-08 05:21:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000151528_77582336.pth [2023-03-08 05:21:41,573][321237] Updated weights for policy 0, policy_version 152240 (0.0005) [2023-03-08 05:21:44,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11468.8, 300 sec: 11510.5). Total num frames: 77975552. Throughput: 0: 11388.7. Samples: 77975616. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:21:44,595][320945] Avg episode reward: [(0, '4775.030')] [2023-03-08 05:21:45,398][321237] Updated weights for policy 0, policy_version 152320 (0.0005) [2023-03-08 05:21:48,956][321237] Updated weights for policy 0, policy_version 152400 (0.0005) [2023-03-08 05:21:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11496.6). Total num frames: 78032896. Throughput: 0: 11392.2. Samples: 78010424. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:21:49,595][320945] Avg episode reward: [(0, '4817.959')] [2023-03-08 05:21:52,695][321237] Updated weights for policy 0, policy_version 152480 (0.0005) [2023-03-08 05:21:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11496.6). Total num frames: 78090240. Throughput: 0: 11303.3. Samples: 78076516. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:21:54,595][320945] Avg episode reward: [(0, '4729.458')] [2023-03-08 05:21:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000152520_78090240.pth... [2023-03-08 05:21:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000151880_77762560.pth [2023-03-08 05:21:56,537][321237] Updated weights for policy 0, policy_version 152560 (0.0005) [2023-03-08 05:21:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 11454.9). Total num frames: 78139392. Throughput: 0: 11111.2. Samples: 78139692. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:21:59,595][320945] Avg episode reward: [(0, '4862.958')] [2023-03-08 05:22:00,412][321237] Updated weights for policy 0, policy_version 152640 (0.0005) [2023-03-08 05:22:04,210][321237] Updated weights for policy 0, policy_version 152720 (0.0005) [2023-03-08 05:22:04,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11264.0, 300 sec: 11454.9). Total num frames: 78196736. Throughput: 0: 11031.8. Samples: 78172224. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:22:04,594][320945] Avg episode reward: [(0, '4863.521')] [2023-03-08 05:22:07,991][321237] Updated weights for policy 0, policy_version 152800 (0.0005) [2023-03-08 05:22:09,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11127.4, 300 sec: 11427.1). Total num frames: 78249984. Throughput: 0: 10908.1. Samples: 78237016. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:22:09,595][320945] Avg episode reward: [(0, '4820.839')] [2023-03-08 05:22:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000152832_78249984.pth... [2023-03-08 05:22:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000152192_77922304.pth [2023-03-08 05:22:11,748][321237] Updated weights for policy 0, policy_version 152880 (0.0004) [2023-03-08 05:22:14,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11059.2, 300 sec: 11413.3). Total num frames: 78303232. Throughput: 0: 10892.6. Samples: 78301880. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:22:14,595][320945] Avg episode reward: [(0, '4860.480')] [2023-03-08 05:22:15,638][321237] Updated weights for policy 0, policy_version 152960 (0.0003) [2023-03-08 05:22:19,437][321237] Updated weights for policy 0, policy_version 153040 (0.0005) [2023-03-08 05:22:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11399.4). Total num frames: 78356480. Throughput: 0: 10848.3. Samples: 78333144. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:22:19,595][320945] Avg episode reward: [(0, '4819.114')] [2023-03-08 05:22:23,250][321237] Updated weights for policy 0, policy_version 153120 (0.0005) [2023-03-08 05:22:24,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11385.5). Total num frames: 78409728. Throughput: 0: 10831.5. Samples: 78397504. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 05:22:24,595][320945] Avg episode reward: [(0, '4861.984')] [2023-03-08 05:22:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000153144_78409728.pth... [2023-03-08 05:22:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000152520_78090240.pth [2023-03-08 05:22:27,059][321237] Updated weights for policy 0, policy_version 153200 (0.0005) [2023-03-08 05:22:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11371.6). Total num frames: 78462976. Throughput: 0: 10830.2. Samples: 78462976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:22:29,595][320945] Avg episode reward: [(0, '4816.482')] [2023-03-08 05:22:30,803][321237] Updated weights for policy 0, policy_version 153280 (0.0005) [2023-03-08 05:22:34,566][321237] Updated weights for policy 0, policy_version 153360 (0.0005) [2023-03-08 05:22:34,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11357.7). Total num frames: 78520320. Throughput: 0: 10779.8. Samples: 78495516. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:22:34,595][320945] Avg episode reward: [(0, '4772.610')] [2023-03-08 05:22:38,438][321237] Updated weights for policy 0, policy_version 153440 (0.0005) [2023-03-08 05:22:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11329.9). Total num frames: 78569472. Throughput: 0: 10744.3. Samples: 78560008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:22:39,595][320945] Avg episode reward: [(0, '4774.475')] [2023-03-08 05:22:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000153464_78573568.pth... [2023-03-08 05:22:39,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000152832_78249984.pth [2023-03-08 05:22:42,226][321237] Updated weights for policy 0, policy_version 153520 (0.0005) [2023-03-08 05:22:44,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11316.1). Total num frames: 78626816. Throughput: 0: 10754.0. Samples: 78623624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:22:44,595][320945] Avg episode reward: [(0, '4823.031')] [2023-03-08 05:22:46,143][321237] Updated weights for policy 0, policy_version 153600 (0.0005) [2023-03-08 05:22:49,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 11288.3). Total num frames: 78675968. Throughput: 0: 10739.4. Samples: 78655496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:22:49,595][320945] Avg episode reward: [(0, '4821.244')] [2023-03-08 05:22:50,079][321237] Updated weights for policy 0, policy_version 153680 (0.0005) [2023-03-08 05:22:53,927][321237] Updated weights for policy 0, policy_version 153760 (0.0005) [2023-03-08 05:22:54,594][320945] Fps is (10 sec: 10240.0, 60 sec: 10649.6, 300 sec: 11274.4). Total num frames: 78729216. Throughput: 0: 10688.5. Samples: 78718000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:22:54,595][320945] Avg episode reward: [(0, '4865.095')] [2023-03-08 05:22:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000153768_78729216.pth... [2023-03-08 05:22:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000153144_78409728.pth [2023-03-08 05:22:57,686][321237] Updated weights for policy 0, policy_version 153840 (0.0005) [2023-03-08 05:22:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 11274.4). Total num frames: 78786560. Throughput: 0: 10691.0. Samples: 78782976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:22:59,595][320945] Avg episode reward: [(0, '4863.069')] [2023-03-08 05:23:01,446][321237] Updated weights for policy 0, policy_version 153920 (0.0004) [2023-03-08 05:23:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 11260.5). Total num frames: 78839808. Throughput: 0: 10726.4. Samples: 78815832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:23:04,595][320945] Avg episode reward: [(0, '4862.904')] [2023-03-08 05:23:05,267][321237] Updated weights for policy 0, policy_version 154000 (0.0005) [2023-03-08 05:23:09,098][321237] Updated weights for policy 0, policy_version 154080 (0.0005) [2023-03-08 05:23:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 11260.5). Total num frames: 78893056. Throughput: 0: 10739.5. Samples: 78880780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:23:09,595][320945] Avg episode reward: [(0, '4815.476')] [2023-03-08 05:23:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000154088_78893056.pth... [2023-03-08 05:23:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000153464_78573568.pth [2023-03-08 05:23:12,943][321237] Updated weights for policy 0, policy_version 154160 (0.0005) [2023-03-08 05:23:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 11246.6). Total num frames: 78946304. Throughput: 0: 10699.3. Samples: 78944444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:23:14,595][320945] Avg episode reward: [(0, '4863.227')] [2023-03-08 05:23:16,658][321237] Updated weights for policy 0, policy_version 154240 (0.0005) [2023-03-08 05:23:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10786.1, 300 sec: 11246.6). Total num frames: 79003648. Throughput: 0: 10735.3. Samples: 78978604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:23:19,595][320945] Avg episode reward: [(0, '4863.591')] [2023-03-08 05:23:20,155][321237] Updated weights for policy 0, policy_version 154320 (0.0004) [2023-03-08 05:23:23,681][321237] Updated weights for policy 0, policy_version 154400 (0.0005) [2023-03-08 05:23:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10854.4, 300 sec: 11246.6). Total num frames: 79060992. Throughput: 0: 10849.0. Samples: 79048212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:23:24,595][320945] Avg episode reward: [(0, '4865.134')] [2023-03-08 05:23:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000154416_79060992.pth... [2023-03-08 05:23:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000153768_78729216.pth [2023-03-08 05:23:27,150][321237] Updated weights for policy 0, policy_version 154480 (0.0004) [2023-03-08 05:23:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10922.7, 300 sec: 11232.8). Total num frames: 79118336. Throughput: 0: 10995.0. Samples: 79118400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:23:29,595][320945] Avg episode reward: [(0, '4862.972')] [2023-03-08 05:23:30,593][321237] Updated weights for policy 0, policy_version 154560 (0.0004) [2023-03-08 05:23:34,089][321237] Updated weights for policy 0, policy_version 154640 (0.0004) [2023-03-08 05:23:34,594][320945] Fps is (10 sec: 11878.4, 60 sec: 10990.9, 300 sec: 11246.6). Total num frames: 79179776. Throughput: 0: 11094.5. Samples: 79154748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:23:34,595][320945] Avg episode reward: [(0, '4863.060')] [2023-03-08 05:23:37,623][321237] Updated weights for policy 0, policy_version 154720 (0.0005) [2023-03-08 05:23:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11127.5, 300 sec: 11246.6). Total num frames: 79237120. Throughput: 0: 11260.0. Samples: 79224700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:23:39,595][320945] Avg episode reward: [(0, '4863.209')] [2023-03-08 05:23:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000154760_79237120.pth... [2023-03-08 05:23:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000154088_78893056.pth [2023-03-08 05:23:41,097][321237] Updated weights for policy 0, policy_version 154800 (0.0004) [2023-03-08 05:23:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 11246.6). Total num frames: 79294464. Throughput: 0: 11366.6. Samples: 79294472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:23:44,595][320945] Avg episode reward: [(0, '4864.818')] [2023-03-08 05:23:44,665][321237] Updated weights for policy 0, policy_version 154880 (0.0004) [2023-03-08 05:23:48,438][321237] Updated weights for policy 0, policy_version 154960 (0.0005) [2023-03-08 05:23:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11232.8). Total num frames: 79351808. Throughput: 0: 11365.9. Samples: 79327296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:23:49,595][320945] Avg episode reward: [(0, '4861.262')] [2023-03-08 05:23:52,250][321237] Updated weights for policy 0, policy_version 155040 (0.0004) [2023-03-08 05:23:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11218.9). Total num frames: 79405056. Throughput: 0: 11348.9. Samples: 79391480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:23:54,595][320945] Avg episode reward: [(0, '4823.220')] [2023-03-08 05:23:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000155088_79405056.pth... [2023-03-08 05:23:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000154416_79060992.pth [2023-03-08 05:23:55,839][321237] Updated weights for policy 0, policy_version 155120 (0.0004) [2023-03-08 05:23:59,327][321237] Updated weights for policy 0, policy_version 155200 (0.0004) [2023-03-08 05:23:59,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11218.9). Total num frames: 79462400. Throughput: 0: 11505.1. Samples: 79462172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:23:59,595][320945] Avg episode reward: [(0, '4862.882')] [2023-03-08 05:24:03,162][321237] Updated weights for policy 0, policy_version 155280 (0.0005) [2023-03-08 05:24:04,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11191.1). Total num frames: 79515648. Throughput: 0: 11439.8. Samples: 79493396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:24:04,594][320945] Avg episode reward: [(0, '4863.889')] [2023-03-08 05:24:07,037][321237] Updated weights for policy 0, policy_version 155360 (0.0005) [2023-03-08 05:24:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 11163.3). Total num frames: 79568896. Throughput: 0: 11303.0. Samples: 79556848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:24:09,595][320945] Avg episode reward: [(0, '4862.124')] [2023-03-08 05:24:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000155408_79568896.pth... [2023-03-08 05:24:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000154760_79237120.pth [2023-03-08 05:24:10,860][321237] Updated weights for policy 0, policy_version 155440 (0.0004) [2023-03-08 05:24:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 11149.5). Total num frames: 79622144. Throughput: 0: 11194.5. Samples: 79622152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:24:14,594][320945] Avg episode reward: [(0, '4864.806')] [2023-03-08 05:24:14,671][321237] Updated weights for policy 0, policy_version 155520 (0.0005) [2023-03-08 05:24:18,581][321237] Updated weights for policy 0, policy_version 155600 (0.0005) [2023-03-08 05:24:19,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11195.7, 300 sec: 11135.6). Total num frames: 79675392. Throughput: 0: 11090.6. Samples: 79653824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:24:19,595][320945] Avg episode reward: [(0, '4867.256')] [2023-03-08 05:24:19,595][321188] Saving new best policy, reward=4867.256! [2023-03-08 05:24:22,424][321237] Updated weights for policy 0, policy_version 155680 (0.0005) [2023-03-08 05:24:24,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11127.5, 300 sec: 11107.8). Total num frames: 79728640. Throughput: 0: 10936.7. Samples: 79716852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:24:24,595][320945] Avg episode reward: [(0, '4776.670')] [2023-03-08 05:24:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000155720_79728640.pth... [2023-03-08 05:24:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000155088_79405056.pth [2023-03-08 05:24:26,279][321237] Updated weights for policy 0, policy_version 155760 (0.0005) [2023-03-08 05:24:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11093.9). Total num frames: 79781888. Throughput: 0: 10806.2. Samples: 79780752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:24:29,595][320945] Avg episode reward: [(0, '4866.409')] [2023-03-08 05:24:30,142][321237] Updated weights for policy 0, policy_version 155840 (0.0005) [2023-03-08 05:24:33,974][321237] Updated weights for policy 0, policy_version 155920 (0.0005) [2023-03-08 05:24:34,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10922.7, 300 sec: 11080.0). Total num frames: 79835136. Throughput: 0: 10773.2. Samples: 79812088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:24:34,595][320945] Avg episode reward: [(0, '4820.694')] [2023-03-08 05:24:37,613][321237] Updated weights for policy 0, policy_version 156000 (0.0003) [2023-03-08 05:24:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11080.0). Total num frames: 79892480. Throughput: 0: 10856.2. Samples: 79880008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:24:39,595][320945] Avg episode reward: [(0, '4777.770')] [2023-03-08 05:24:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000156040_79892480.pth... [2023-03-08 05:24:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000155408_79568896.pth [2023-03-08 05:24:41,120][321237] Updated weights for policy 0, policy_version 156080 (0.0004) [2023-03-08 05:24:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10922.7, 300 sec: 11093.9). Total num frames: 79949824. Throughput: 0: 10811.9. Samples: 79948708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:24:44,595][320945] Avg episode reward: [(0, '4814.405')] [2023-03-08 05:24:44,787][321237] Updated weights for policy 0, policy_version 156160 (0.0005) [2023-03-08 05:24:48,561][321237] Updated weights for policy 0, policy_version 156240 (0.0005) [2023-03-08 05:24:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11093.9). Total num frames: 80003072. Throughput: 0: 10826.8. Samples: 79980604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:24:49,595][320945] Avg episode reward: [(0, '4861.598')] [2023-03-08 05:24:52,322][321237] Updated weights for policy 0, policy_version 156320 (0.0005) [2023-03-08 05:24:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11093.9). Total num frames: 80060416. Throughput: 0: 10875.3. Samples: 80046236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:24:54,595][320945] Avg episode reward: [(0, '4817.951')] [2023-03-08 05:24:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000156368_80060416.pth... [2023-03-08 05:24:54,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000155720_79728640.pth [2023-03-08 05:24:56,062][321237] Updated weights for policy 0, policy_version 156400 (0.0005) [2023-03-08 05:24:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11093.9). Total num frames: 80113664. Throughput: 0: 10858.2. Samples: 80110772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:24:59,595][320945] Avg episode reward: [(0, '4862.574')] [2023-03-08 05:24:59,888][321237] Updated weights for policy 0, policy_version 156480 (0.0005) [2023-03-08 05:25:03,705][321237] Updated weights for policy 0, policy_version 156560 (0.0005) [2023-03-08 05:25:04,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10854.4, 300 sec: 11093.9). Total num frames: 80166912. Throughput: 0: 10880.8. Samples: 80143460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:25:04,595][320945] Avg episode reward: [(0, '4863.602')] [2023-03-08 05:25:07,535][321237] Updated weights for policy 0, policy_version 156640 (0.0005) [2023-03-08 05:25:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11093.9). Total num frames: 80220160. Throughput: 0: 10911.8. Samples: 80207884. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:25:09,595][320945] Avg episode reward: [(0, '4820.086')] [2023-03-08 05:25:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000156680_80220160.pth... [2023-03-08 05:25:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000156040_79892480.pth [2023-03-08 05:25:11,315][321237] Updated weights for policy 0, policy_version 156720 (0.0005) [2023-03-08 05:25:14,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 11093.9). Total num frames: 80273408. Throughput: 0: 10941.1. Samples: 80273100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:25:14,595][320945] Avg episode reward: [(0, '4864.876')] [2023-03-08 05:25:15,148][321237] Updated weights for policy 0, policy_version 156800 (0.0005) [2023-03-08 05:25:18,984][321237] Updated weights for policy 0, policy_version 156880 (0.0005) [2023-03-08 05:25:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11066.1). Total num frames: 80326656. Throughput: 0: 10921.3. Samples: 80303548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:25:19,595][320945] Avg episode reward: [(0, '4863.992')] [2023-03-08 05:25:22,838][321237] Updated weights for policy 0, policy_version 156960 (0.0005) [2023-03-08 05:25:24,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 11066.1). Total num frames: 80379904. Throughput: 0: 10837.3. Samples: 80367688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:25:24,595][320945] Avg episode reward: [(0, '4824.930')] [2023-03-08 05:25:24,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000156992_80379904.pth... [2023-03-08 05:25:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000156368_80060416.pth [2023-03-08 05:25:26,671][321237] Updated weights for policy 0, policy_version 157040 (0.0005) [2023-03-08 05:25:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11052.3). Total num frames: 80433152. Throughput: 0: 10765.4. Samples: 80433152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:25:29,595][320945] Avg episode reward: [(0, '4821.099')] [2023-03-08 05:25:30,501][321237] Updated weights for policy 0, policy_version 157120 (0.0005) [2023-03-08 05:25:34,268][321237] Updated weights for policy 0, policy_version 157200 (0.0005) [2023-03-08 05:25:34,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10854.4, 300 sec: 11038.4). Total num frames: 80486400. Throughput: 0: 10760.6. Samples: 80464828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:25:34,594][320945] Avg episode reward: [(0, '4815.701')] [2023-03-08 05:25:38,161][321237] Updated weights for policy 0, policy_version 157280 (0.0005) [2023-03-08 05:25:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11024.5). Total num frames: 80539648. Throughput: 0: 10708.5. Samples: 80528120. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:25:39,595][320945] Avg episode reward: [(0, '4864.153')] [2023-03-08 05:25:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000157304_80539648.pth... [2023-03-08 05:25:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000156680_80220160.pth [2023-03-08 05:25:42,127][321237] Updated weights for policy 0, policy_version 157360 (0.0005) [2023-03-08 05:25:44,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10717.9, 300 sec: 10996.7). Total num frames: 80592896. Throughput: 0: 10686.2. Samples: 80591652. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:25:44,595][320945] Avg episode reward: [(0, '4776.846')] [2023-03-08 05:25:45,834][321237] Updated weights for policy 0, policy_version 157440 (0.0005) [2023-03-08 05:25:49,587][321237] Updated weights for policy 0, policy_version 157520 (0.0005) [2023-03-08 05:25:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 10996.7). Total num frames: 80650240. Throughput: 0: 10703.7. Samples: 80625128. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:25:49,595][320945] Avg episode reward: [(0, '4819.830')] [2023-03-08 05:25:53,358][321237] Updated weights for policy 0, policy_version 157600 (0.0005) [2023-03-08 05:25:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 10982.8). Total num frames: 80703488. Throughput: 0: 10734.0. Samples: 80690916. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:25:54,595][320945] Avg episode reward: [(0, '4863.778')] [2023-03-08 05:25:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000157624_80703488.pth... [2023-03-08 05:25:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000156992_80379904.pth [2023-03-08 05:25:57,231][321237] Updated weights for policy 0, policy_version 157680 (0.0005) [2023-03-08 05:25:59,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10717.9, 300 sec: 10968.9). Total num frames: 80756736. Throughput: 0: 10687.4. Samples: 80754032. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:25:59,595][320945] Avg episode reward: [(0, '4864.390')] [2023-03-08 05:26:01,066][321237] Updated weights for policy 0, policy_version 157760 (0.0005) [2023-03-08 05:26:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10941.2). Total num frames: 80809984. Throughput: 0: 10721.1. Samples: 80785996. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:26:04,595][320945] Avg episode reward: [(0, '4864.662')] [2023-03-08 05:26:04,908][321237] Updated weights for policy 0, policy_version 157840 (0.0005) [2023-03-08 05:26:08,677][321237] Updated weights for policy 0, policy_version 157920 (0.0005) [2023-03-08 05:26:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10927.3). Total num frames: 80863232. Throughput: 0: 10735.4. Samples: 80850780. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:26:09,595][320945] Avg episode reward: [(0, '4862.380')] [2023-03-08 05:26:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000157936_80863232.pth... [2023-03-08 05:26:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000157304_80539648.pth [2023-03-08 05:26:12,117][321237] Updated weights for policy 0, policy_version 158000 (0.0005) [2023-03-08 05:26:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 10913.4). Total num frames: 80920576. Throughput: 0: 10833.2. Samples: 80920648. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:26:14,595][320945] Avg episode reward: [(0, '4862.805')] [2023-03-08 05:26:15,841][321237] Updated weights for policy 0, policy_version 158080 (0.0005) [2023-03-08 05:26:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10786.1, 300 sec: 10899.5). Total num frames: 80973824. Throughput: 0: 10824.5. Samples: 80951932. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:26:19,595][320945] Avg episode reward: [(0, '4865.012')] [2023-03-08 05:26:19,744][321237] Updated weights for policy 0, policy_version 158160 (0.0005) [2023-03-08 05:26:23,539][321237] Updated weights for policy 0, policy_version 158240 (0.0005) [2023-03-08 05:26:24,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10854.4, 300 sec: 10913.4). Total num frames: 81031168. Throughput: 0: 10825.5. Samples: 81015268. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:26:24,595][320945] Avg episode reward: [(0, '4862.781')] [2023-03-08 05:26:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000158264_81031168.pth... [2023-03-08 05:26:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000157624_80703488.pth [2023-03-08 05:26:27,101][321237] Updated weights for policy 0, policy_version 158320 (0.0005) [2023-03-08 05:26:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10922.7, 300 sec: 10913.4). Total num frames: 81088512. Throughput: 0: 10979.9. Samples: 81085748. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:26:29,595][320945] Avg episode reward: [(0, '4863.992')] [2023-03-08 05:26:30,575][321237] Updated weights for policy 0, policy_version 158400 (0.0005) [2023-03-08 05:26:34,158][321237] Updated weights for policy 0, policy_version 158480 (0.0005) [2023-03-08 05:26:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 10990.9, 300 sec: 10927.3). Total num frames: 81145856. Throughput: 0: 11010.1. Samples: 81120584. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:26:34,595][320945] Avg episode reward: [(0, '4863.925')] [2023-03-08 05:26:37,679][321237] Updated weights for policy 0, policy_version 158560 (0.0004) [2023-03-08 05:26:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 81203200. Throughput: 0: 11087.7. Samples: 81189864. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:26:39,595][320945] Avg episode reward: [(0, '4863.098')] [2023-03-08 05:26:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000158600_81203200.pth... [2023-03-08 05:26:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000157936_80863232.pth [2023-03-08 05:26:41,299][321237] Updated weights for policy 0, policy_version 158640 (0.0005) [2023-03-08 05:26:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 10941.2). Total num frames: 81260544. Throughput: 0: 11224.7. Samples: 81259144. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:26:44,595][320945] Avg episode reward: [(0, '4864.597')] [2023-03-08 05:26:44,803][321237] Updated weights for policy 0, policy_version 158720 (0.0005) [2023-03-08 05:26:48,550][321237] Updated weights for policy 0, policy_version 158800 (0.0005) [2023-03-08 05:26:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11059.2, 300 sec: 10927.3). Total num frames: 81313792. Throughput: 0: 11234.5. Samples: 81291548. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:26:49,594][320945] Avg episode reward: [(0, '4861.004')] [2023-03-08 05:26:52,376][321237] Updated weights for policy 0, policy_version 158880 (0.0005) [2023-03-08 05:26:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 81367040. Throughput: 0: 11225.3. Samples: 81355916. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:26:54,595][320945] Avg episode reward: [(0, '4818.701')] [2023-03-08 05:26:54,631][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000158928_81371136.pth... [2023-03-08 05:26:54,633][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000158264_81031168.pth [2023-03-08 05:26:56,187][321237] Updated weights for policy 0, policy_version 158960 (0.0005) [2023-03-08 05:26:59,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11059.2, 300 sec: 10927.3). Total num frames: 81420288. Throughput: 0: 11104.7. Samples: 81420360. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:26:59,595][320945] Avg episode reward: [(0, '4864.367')] [2023-03-08 05:27:00,001][321237] Updated weights for policy 0, policy_version 159040 (0.0005) [2023-03-08 05:27:03,728][321237] Updated weights for policy 0, policy_version 159120 (0.0005) [2023-03-08 05:27:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 10941.2). Total num frames: 81477632. Throughput: 0: 11137.7. Samples: 81453128. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:27:04,595][320945] Avg episode reward: [(0, '4863.985')] [2023-03-08 05:27:07,392][321237] Updated weights for policy 0, policy_version 159200 (0.0005) [2023-03-08 05:27:09,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 10955.1). Total num frames: 81534976. Throughput: 0: 11221.0. Samples: 81520212. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:27:09,595][320945] Avg episode reward: [(0, '4863.926')] [2023-03-08 05:27:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000159248_81534976.pth... [2023-03-08 05:27:09,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000158600_81203200.pth [2023-03-08 05:27:11,120][321237] Updated weights for policy 0, policy_version 159280 (0.0005) [2023-03-08 05:27:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 81584128. Throughput: 0: 11076.7. Samples: 81584200. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:27:14,595][320945] Avg episode reward: [(0, '4863.243')] [2023-03-08 05:27:15,003][321237] Updated weights for policy 0, policy_version 159360 (0.0005) [2023-03-08 05:27:18,838][321237] Updated weights for policy 0, policy_version 159440 (0.0005) [2023-03-08 05:27:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 10955.1). Total num frames: 81641472. Throughput: 0: 11029.2. Samples: 81616896. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:27:19,594][320945] Avg episode reward: [(0, '4859.874')] [2023-03-08 05:27:22,324][321237] Updated weights for policy 0, policy_version 159520 (0.0005) [2023-03-08 05:27:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 10968.9). Total num frames: 81698816. Throughput: 0: 11027.0. Samples: 81686080. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:27:24,605][320945] Avg episode reward: [(0, '4824.780')] [2023-03-08 05:27:24,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000159568_81698816.pth... [2023-03-08 05:27:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000158928_81371136.pth [2023-03-08 05:27:25,773][321237] Updated weights for policy 0, policy_version 159600 (0.0005) [2023-03-08 05:27:29,300][321237] Updated weights for policy 0, policy_version 159680 (0.0005) [2023-03-08 05:27:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 10968.9). Total num frames: 81756160. Throughput: 0: 11043.0. Samples: 81756080. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:27:29,595][320945] Avg episode reward: [(0, '4785.066')] [2023-03-08 05:27:33,047][321237] Updated weights for policy 0, policy_version 159760 (0.0005) [2023-03-08 05:27:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11127.5, 300 sec: 10996.7). Total num frames: 81813504. Throughput: 0: 11053.3. Samples: 81788948. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:27:34,595][320945] Avg episode reward: [(0, '4720.286')] [2023-03-08 05:27:36,909][321237] Updated weights for policy 0, policy_version 159840 (0.0005) [2023-03-08 05:27:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10968.9). Total num frames: 81862656. Throughput: 0: 11027.7. Samples: 81852164. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:27:39,595][320945] Avg episode reward: [(0, '4863.562')] [2023-03-08 05:27:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000159888_81862656.pth... [2023-03-08 05:27:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000159248_81534976.pth [2023-03-08 05:27:40,827][321237] Updated weights for policy 0, policy_version 159920 (0.0005) [2023-03-08 05:27:44,594][320945] Fps is (10 sec: 10239.9, 60 sec: 10922.7, 300 sec: 10982.8). Total num frames: 81915904. Throughput: 0: 11013.5. Samples: 81915968. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:27:44,595][320945] Avg episode reward: [(0, '4862.255')] [2023-03-08 05:27:44,618][321237] Updated weights for policy 0, policy_version 160000 (0.0005) [2023-03-08 05:27:48,500][321237] Updated weights for policy 0, policy_version 160080 (0.0005) [2023-03-08 05:27:49,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10982.8). Total num frames: 81969152. Throughput: 0: 11012.1. Samples: 81948672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:27:49,595][320945] Avg episode reward: [(0, '4861.949')] [2023-03-08 05:27:52,319][321237] Updated weights for policy 0, policy_version 160160 (0.0005) [2023-03-08 05:27:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10982.8). Total num frames: 82026496. Throughput: 0: 10927.0. Samples: 82011928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:27:54,595][320945] Avg episode reward: [(0, '4827.594')] [2023-03-08 05:27:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000160208_82026496.pth... [2023-03-08 05:27:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000159568_81698816.pth [2023-03-08 05:27:56,038][321237] Updated weights for policy 0, policy_version 160240 (0.0005) [2023-03-08 05:27:59,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 10982.8). Total num frames: 82079744. Throughput: 0: 10949.5. Samples: 82076928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:27:59,605][320945] Avg episode reward: [(0, '4863.639')] [2023-03-08 05:27:59,892][321237] Updated weights for policy 0, policy_version 160320 (0.0005) [2023-03-08 05:28:03,787][321237] Updated weights for policy 0, policy_version 160400 (0.0005) [2023-03-08 05:28:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10982.8). Total num frames: 82132992. Throughput: 0: 10924.1. Samples: 82108480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:28:04,605][320945] Avg episode reward: [(0, '4855.324')] [2023-03-08 05:28:07,521][321237] Updated weights for policy 0, policy_version 160480 (0.0005) [2023-03-08 05:28:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10982.8). Total num frames: 82186240. Throughput: 0: 10843.0. Samples: 82174016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:28:09,605][320945] Avg episode reward: [(0, '4818.004')] [2023-03-08 05:28:09,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000160520_82186240.pth... [2023-03-08 05:28:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000159888_81862656.pth [2023-03-08 05:28:11,288][321237] Updated weights for policy 0, policy_version 160560 (0.0005) [2023-03-08 05:28:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10968.9). Total num frames: 82239488. Throughput: 0: 10712.7. Samples: 82238152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:28:14,605][320945] Avg episode reward: [(0, '4867.603')] [2023-03-08 05:28:14,606][321188] Saving new best policy, reward=4867.603! [2023-03-08 05:28:15,267][321237] Updated weights for policy 0, policy_version 160640 (0.0005) [2023-03-08 05:28:19,106][321237] Updated weights for policy 0, policy_version 160720 (0.0005) [2023-03-08 05:28:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10955.1). Total num frames: 82292736. Throughput: 0: 10657.6. Samples: 82268540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:28:19,605][320945] Avg episode reward: [(0, '4834.881')] [2023-03-08 05:28:22,862][321237] Updated weights for policy 0, policy_version 160800 (0.0005) [2023-03-08 05:28:24,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10941.2). Total num frames: 82345984. Throughput: 0: 10702.3. Samples: 82333768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:28:24,605][320945] Avg episode reward: [(0, '4862.533')] [2023-03-08 05:28:24,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000160832_82345984.pth... [2023-03-08 05:28:24,612][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000160208_82026496.pth [2023-03-08 05:28:26,611][321237] Updated weights for policy 0, policy_version 160880 (0.0005) [2023-03-08 05:28:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10913.4). Total num frames: 82399232. Throughput: 0: 10740.6. Samples: 82399296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:28:29,605][320945] Avg episode reward: [(0, '4863.486')] [2023-03-08 05:28:30,420][321237] Updated weights for policy 0, policy_version 160960 (0.0005) [2023-03-08 05:28:34,071][321237] Updated weights for policy 0, policy_version 161040 (0.0005) [2023-03-08 05:28:34,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 10913.4). Total num frames: 82456576. Throughput: 0: 10742.0. Samples: 82432064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:28:34,605][320945] Avg episode reward: [(0, '4822.584')] [2023-03-08 05:28:38,002][321237] Updated weights for policy 0, policy_version 161120 (0.0005) [2023-03-08 05:28:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 10899.5). Total num frames: 82509824. Throughput: 0: 10772.3. Samples: 82496680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:28:39,605][320945] Avg episode reward: [(0, '4819.847')] [2023-03-08 05:28:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000161152_82509824.pth... [2023-03-08 05:28:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000160520_82186240.pth [2023-03-08 05:28:41,671][321237] Updated weights for policy 0, policy_version 161200 (0.0004) [2023-03-08 05:28:44,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10854.4, 300 sec: 10899.5). Total num frames: 82567168. Throughput: 0: 10810.1. Samples: 82563380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:28:44,605][320945] Avg episode reward: [(0, '4834.919')] [2023-03-08 05:28:45,311][321237] Updated weights for policy 0, policy_version 161280 (0.0003) [2023-03-08 05:28:48,916][321237] Updated weights for policy 0, policy_version 161360 (0.0003) [2023-03-08 05:28:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10899.5). Total num frames: 82620416. Throughput: 0: 10884.0. Samples: 82598260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:28:49,595][320945] Avg episode reward: [(0, '4820.134')] [2023-03-08 05:28:52,712][321237] Updated weights for policy 0, policy_version 161440 (0.0004) [2023-03-08 05:28:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10885.6). Total num frames: 82673664. Throughput: 0: 10870.9. Samples: 82663204. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:28:54,595][320945] Avg episode reward: [(0, '4862.594')] [2023-03-08 05:28:54,622][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000161480_82677760.pth... [2023-03-08 05:28:54,624][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000160832_82345984.pth [2023-03-08 05:28:56,481][321237] Updated weights for policy 0, policy_version 161520 (0.0005) [2023-03-08 05:28:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10899.5). Total num frames: 82731008. Throughput: 0: 10898.0. Samples: 82728560. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:28:59,595][320945] Avg episode reward: [(0, '4864.222')] [2023-03-08 05:29:00,219][321237] Updated weights for policy 0, policy_version 161600 (0.0005) [2023-03-08 05:29:04,108][321237] Updated weights for policy 0, policy_version 161680 (0.0005) [2023-03-08 05:29:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10899.5). Total num frames: 82784256. Throughput: 0: 10915.8. Samples: 82759752. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:29:04,595][320945] Avg episode reward: [(0, '4784.929')] [2023-03-08 05:29:07,624][321237] Updated weights for policy 0, policy_version 161760 (0.0005) [2023-03-08 05:29:09,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10913.4). Total num frames: 82841600. Throughput: 0: 11002.2. Samples: 82828868. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:29:09,595][320945] Avg episode reward: [(0, '4765.435')] [2023-03-08 05:29:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000161800_82841600.pth... [2023-03-08 05:29:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000161152_82509824.pth [2023-03-08 05:29:11,192][321237] Updated weights for policy 0, policy_version 161840 (0.0005) [2023-03-08 05:29:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 10927.3). Total num frames: 82898944. Throughput: 0: 11079.9. Samples: 82897892. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:29:14,595][320945] Avg episode reward: [(0, '4863.757')] [2023-03-08 05:29:14,740][321237] Updated weights for policy 0, policy_version 161920 (0.0004) [2023-03-08 05:29:18,302][321237] Updated weights for policy 0, policy_version 162000 (0.0005) [2023-03-08 05:29:19,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 82956288. Throughput: 0: 11100.0. Samples: 82931564. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:29:19,595][320945] Avg episode reward: [(0, '4822.779')] [2023-03-08 05:29:21,795][321237] Updated weights for policy 0, policy_version 162080 (0.0005) [2023-03-08 05:29:24,594][320945] Fps is (10 sec: 11878.3, 60 sec: 11195.7, 300 sec: 10968.9). Total num frames: 83017728. Throughput: 0: 11231.8. Samples: 83002112. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:29:24,595][320945] Avg episode reward: [(0, '4861.975')] [2023-03-08 05:29:24,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000162144_83017728.pth... [2023-03-08 05:29:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000161480_82677760.pth [2023-03-08 05:29:25,315][321237] Updated weights for policy 0, policy_version 162160 (0.0005) [2023-03-08 05:29:28,855][321237] Updated weights for policy 0, policy_version 162240 (0.0005) [2023-03-08 05:29:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 10982.8). Total num frames: 83075072. Throughput: 0: 11285.3. Samples: 83071216. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:29:29,595][320945] Avg episode reward: [(0, '4858.798')] [2023-03-08 05:29:32,409][321237] Updated weights for policy 0, policy_version 162320 (0.0005) [2023-03-08 05:29:34,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11264.0, 300 sec: 10982.8). Total num frames: 83132416. Throughput: 0: 11291.8. Samples: 83106392. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:29:34,595][320945] Avg episode reward: [(0, '4786.093')] [2023-03-08 05:29:35,943][321237] Updated weights for policy 0, policy_version 162400 (0.0004) [2023-03-08 05:29:39,388][321237] Updated weights for policy 0, policy_version 162480 (0.0004) [2023-03-08 05:29:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 10982.8). Total num frames: 83189760. Throughput: 0: 11415.1. Samples: 83176884. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:29:39,595][320945] Avg episode reward: [(0, '4825.294')] [2023-03-08 05:29:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000162480_83189760.pth... [2023-03-08 05:29:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000161800_82841600.pth [2023-03-08 05:29:42,935][321237] Updated weights for policy 0, policy_version 162560 (0.0004) [2023-03-08 05:29:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 10996.7). Total num frames: 83247104. Throughput: 0: 11492.6. Samples: 83245728. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:29:44,595][320945] Avg episode reward: [(0, '4825.546')] [2023-03-08 05:29:46,631][321237] Updated weights for policy 0, policy_version 162640 (0.0005) [2023-03-08 05:29:49,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 10996.7). Total num frames: 83304448. Throughput: 0: 11553.0. Samples: 83279636. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:29:49,595][320945] Avg episode reward: [(0, '4863.139')] [2023-03-08 05:29:50,149][321237] Updated weights for policy 0, policy_version 162720 (0.0004) [2023-03-08 05:29:53,719][321237] Updated weights for policy 0, policy_version 162800 (0.0004) [2023-03-08 05:29:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 11010.6). Total num frames: 83361792. Throughput: 0: 11545.0. Samples: 83348392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:29:54,595][320945] Avg episode reward: [(0, '4865.155')] [2023-03-08 05:29:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000162816_83361792.pth... [2023-03-08 05:29:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000162144_83017728.pth [2023-03-08 05:29:57,255][321237] Updated weights for policy 0, policy_version 162880 (0.0004) [2023-03-08 05:29:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11024.5). Total num frames: 83419136. Throughput: 0: 11527.6. Samples: 83416636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:29:59,595][320945] Avg episode reward: [(0, '4863.530')] [2023-03-08 05:30:01,034][321237] Updated weights for policy 0, policy_version 162960 (0.0005) [2023-03-08 05:30:04,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11024.5). Total num frames: 83472384. Throughput: 0: 11499.0. Samples: 83449020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:30:04,595][320945] Avg episode reward: [(0, '4862.545')] [2023-03-08 05:30:04,782][321237] Updated weights for policy 0, policy_version 163040 (0.0005) [2023-03-08 05:30:08,395][321237] Updated weights for policy 0, policy_version 163120 (0.0005) [2023-03-08 05:30:09,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11468.8, 300 sec: 11038.4). Total num frames: 83529728. Throughput: 0: 11425.8. Samples: 83516272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:30:09,595][320945] Avg episode reward: [(0, '4864.410')] [2023-03-08 05:30:09,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000163144_83529728.pth... [2023-03-08 05:30:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000162480_83189760.pth [2023-03-08 05:30:12,151][321237] Updated weights for policy 0, policy_version 163200 (0.0005) [2023-03-08 05:30:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11038.4). Total num frames: 83582976. Throughput: 0: 11333.8. Samples: 83581236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:30:14,595][320945] Avg episode reward: [(0, '4865.403')] [2023-03-08 05:30:15,914][321237] Updated weights for policy 0, policy_version 163280 (0.0004) [2023-03-08 05:30:19,445][321237] Updated weights for policy 0, policy_version 163360 (0.0005) [2023-03-08 05:30:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11052.3). Total num frames: 83640320. Throughput: 0: 11305.8. Samples: 83615152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:30:19,595][320945] Avg episode reward: [(0, '4863.244')] [2023-03-08 05:30:22,959][321237] Updated weights for policy 0, policy_version 163440 (0.0004) [2023-03-08 05:30:24,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11066.1). Total num frames: 83697664. Throughput: 0: 11296.7. Samples: 83685236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:30:24,595][320945] Avg episode reward: [(0, '4826.801')] [2023-03-08 05:30:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000163472_83697664.pth... [2023-03-08 05:30:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000162816_83361792.pth [2023-03-08 05:30:26,404][321237] Updated weights for policy 0, policy_version 163520 (0.0004) [2023-03-08 05:30:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11093.9). Total num frames: 83759104. Throughput: 0: 11341.8. Samples: 83756108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:30:29,595][320945] Avg episode reward: [(0, '4781.649')] [2023-03-08 05:30:29,849][321237] Updated weights for policy 0, policy_version 163600 (0.0004) [2023-03-08 05:30:33,354][321237] Updated weights for policy 0, policy_version 163680 (0.0005) [2023-03-08 05:30:34,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11400.5, 300 sec: 11107.8). Total num frames: 83816448. Throughput: 0: 11379.6. Samples: 83791720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:30:34,595][320945] Avg episode reward: [(0, '4863.212')] [2023-03-08 05:30:36,862][321237] Updated weights for policy 0, policy_version 163760 (0.0004) [2023-03-08 05:30:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11121.7). Total num frames: 83873792. Throughput: 0: 11372.5. Samples: 83860152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:30:39,595][320945] Avg episode reward: [(0, '4863.661')] [2023-03-08 05:30:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000163816_83873792.pth... [2023-03-08 05:30:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000163144_83529728.pth [2023-03-08 05:30:40,738][321237] Updated weights for policy 0, policy_version 163840 (0.0005) [2023-03-08 05:30:44,566][321237] Updated weights for policy 0, policy_version 163920 (0.0005) [2023-03-08 05:30:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11107.8). Total num frames: 83927040. Throughput: 0: 11261.7. Samples: 83923412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:30:44,595][320945] Avg episode reward: [(0, '4756.403')] [2023-03-08 05:30:48,303][321237] Updated weights for policy 0, policy_version 164000 (0.0005) [2023-03-08 05:30:49,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 11107.8). Total num frames: 83980288. Throughput: 0: 11268.5. Samples: 83956104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:30:49,595][320945] Avg episode reward: [(0, '4862.686')] [2023-03-08 05:30:52,030][321237] Updated weights for policy 0, policy_version 164080 (0.0005) [2023-03-08 05:30:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11107.8). Total num frames: 84033536. Throughput: 0: 11237.2. Samples: 84021944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:30:54,595][320945] Avg episode reward: [(0, '4864.409')] [2023-03-08 05:30:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000164128_84033536.pth... [2023-03-08 05:30:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000163472_83697664.pth [2023-03-08 05:30:55,799][321237] Updated weights for policy 0, policy_version 164160 (0.0005) [2023-03-08 05:30:59,464][321237] Updated weights for policy 0, policy_version 164240 (0.0004) [2023-03-08 05:30:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11121.7). Total num frames: 84090880. Throughput: 0: 11281.3. Samples: 84088896. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:30:59,595][320945] Avg episode reward: [(0, '4863.934')] [2023-03-08 05:31:03,291][321237] Updated weights for policy 0, policy_version 164320 (0.0005) [2023-03-08 05:31:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11121.7). Total num frames: 84144128. Throughput: 0: 11237.9. Samples: 84120856. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:31:04,595][320945] Avg episode reward: [(0, '4865.236')] [2023-03-08 05:31:07,068][321237] Updated weights for policy 0, policy_version 164400 (0.0005) [2023-03-08 05:31:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11107.8). Total num frames: 84197376. Throughput: 0: 11131.6. Samples: 84186156. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:31:09,605][320945] Avg episode reward: [(0, '4864.445')] [2023-03-08 05:31:09,634][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000164456_84201472.pth... [2023-03-08 05:31:09,636][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000163816_83873792.pth [2023-03-08 05:31:10,766][321237] Updated weights for policy 0, policy_version 164480 (0.0005) [2023-03-08 05:31:14,430][321237] Updated weights for policy 0, policy_version 164560 (0.0004) [2023-03-08 05:31:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11121.7). Total num frames: 84254720. Throughput: 0: 11041.2. Samples: 84252960. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:31:14,595][320945] Avg episode reward: [(0, '4862.715')] [2023-03-08 05:31:18,296][321237] Updated weights for policy 0, policy_version 164640 (0.0005) [2023-03-08 05:31:19,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11127.5, 300 sec: 11107.8). Total num frames: 84307968. Throughput: 0: 10960.6. Samples: 84284948. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:31:19,595][320945] Avg episode reward: [(0, '4864.444')] [2023-03-08 05:31:22,196][321237] Updated weights for policy 0, policy_version 164720 (0.0005) [2023-03-08 05:31:24,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11059.2, 300 sec: 11093.9). Total num frames: 84361216. Throughput: 0: 10861.7. Samples: 84348928. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:31:24,595][320945] Avg episode reward: [(0, '4859.032')] [2023-03-08 05:31:24,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000164768_84361216.pth... [2023-03-08 05:31:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000164128_84033536.pth [2023-03-08 05:31:26,038][321237] Updated weights for policy 0, policy_version 164800 (0.0005) [2023-03-08 05:31:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11080.0). Total num frames: 84414464. Throughput: 0: 10889.2. Samples: 84413428. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:31:29,595][320945] Avg episode reward: [(0, '4864.261')] [2023-03-08 05:31:29,769][321237] Updated weights for policy 0, policy_version 164880 (0.0005) [2023-03-08 05:31:33,532][321237] Updated weights for policy 0, policy_version 164960 (0.0005) [2023-03-08 05:31:34,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10854.4, 300 sec: 11066.1). Total num frames: 84467712. Throughput: 0: 10881.0. Samples: 84445748. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:31:34,594][320945] Avg episode reward: [(0, '4863.759')] [2023-03-08 05:31:37,287][321237] Updated weights for policy 0, policy_version 165040 (0.0005) [2023-03-08 05:31:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11052.3). Total num frames: 84520960. Throughput: 0: 10868.3. Samples: 84511020. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:31:39,595][320945] Avg episode reward: [(0, '4864.128')] [2023-03-08 05:31:39,606][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000165088_84525056.pth... [2023-03-08 05:31:39,607][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000164456_84201472.pth [2023-03-08 05:31:41,158][321237] Updated weights for policy 0, policy_version 165120 (0.0005) [2023-03-08 05:31:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11066.1). Total num frames: 84578304. Throughput: 0: 10814.3. Samples: 84575540. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:31:44,595][320945] Avg episode reward: [(0, '4862.665')] [2023-03-08 05:31:44,868][321237] Updated weights for policy 0, policy_version 165200 (0.0005) [2023-03-08 05:31:48,626][321237] Updated weights for policy 0, policy_version 165280 (0.0005) [2023-03-08 05:31:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11066.1). Total num frames: 84631552. Throughput: 0: 10825.3. Samples: 84607996. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:31:49,595][320945] Avg episode reward: [(0, '4826.748')] [2023-03-08 05:31:52,284][321237] Updated weights for policy 0, policy_version 165360 (0.0005) [2023-03-08 05:31:54,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10922.6, 300 sec: 11080.0). Total num frames: 84688896. Throughput: 0: 10878.1. Samples: 84675672. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:31:54,595][320945] Avg episode reward: [(0, '4863.289')] [2023-03-08 05:31:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000165408_84688896.pth... [2023-03-08 05:31:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000164768_84361216.pth [2023-03-08 05:31:55,984][321237] Updated weights for policy 0, policy_version 165440 (0.0005) [2023-03-08 05:31:59,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10854.4, 300 sec: 11066.1). Total num frames: 84742144. Throughput: 0: 10861.2. Samples: 84741716. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:31:59,595][320945] Avg episode reward: [(0, '4862.809')] [2023-03-08 05:31:59,756][321237] Updated weights for policy 0, policy_version 165520 (0.0005) [2023-03-08 05:32:03,626][321237] Updated weights for policy 0, policy_version 165600 (0.0005) [2023-03-08 05:32:04,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10854.4, 300 sec: 11052.3). Total num frames: 84795392. Throughput: 0: 10819.8. Samples: 84771840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:32:04,595][320945] Avg episode reward: [(0, '4862.657')] [2023-03-08 05:32:07,400][321237] Updated weights for policy 0, policy_version 165680 (0.0005) [2023-03-08 05:32:09,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10854.4, 300 sec: 11066.1). Total num frames: 84848640. Throughput: 0: 10861.9. Samples: 84837712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:32:09,594][320945] Avg episode reward: [(0, '4865.543')] [2023-03-08 05:32:09,602][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000165728_84852736.pth... [2023-03-08 05:32:09,603][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000165088_84525056.pth [2023-03-08 05:32:10,952][321237] Updated weights for policy 0, policy_version 165760 (0.0004) [2023-03-08 05:32:14,491][321237] Updated weights for policy 0, policy_version 165840 (0.0004) [2023-03-08 05:32:14,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10922.7, 300 sec: 11080.0). Total num frames: 84910080. Throughput: 0: 10979.6. Samples: 84907512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:32:14,595][320945] Avg episode reward: [(0, '4866.241')] [2023-03-08 05:32:17,995][321237] Updated weights for policy 0, policy_version 165920 (0.0004) [2023-03-08 05:32:19,594][320945] Fps is (10 sec: 11878.3, 60 sec: 10990.9, 300 sec: 11080.0). Total num frames: 84967424. Throughput: 0: 11048.1. Samples: 84942912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:32:19,595][320945] Avg episode reward: [(0, '4863.312')] [2023-03-08 05:32:21,744][321237] Updated weights for policy 0, policy_version 166000 (0.0005) [2023-03-08 05:32:24,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 11066.1). Total num frames: 85020672. Throughput: 0: 11052.1. Samples: 85008364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:32:24,595][320945] Avg episode reward: [(0, '4863.442')] [2023-03-08 05:32:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000166056_85020672.pth... [2023-03-08 05:32:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000165408_84688896.pth [2023-03-08 05:32:25,634][321237] Updated weights for policy 0, policy_version 166080 (0.0005) [2023-03-08 05:32:29,455][321237] Updated weights for policy 0, policy_version 166160 (0.0005) [2023-03-08 05:32:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 11052.3). Total num frames: 85073920. Throughput: 0: 11034.8. Samples: 85072108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:32:29,595][320945] Avg episode reward: [(0, '4865.382')] [2023-03-08 05:32:33,247][321237] Updated weights for policy 0, policy_version 166240 (0.0005) [2023-03-08 05:32:34,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 11066.1). Total num frames: 85127168. Throughput: 0: 11039.6. Samples: 85104780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:32:34,595][320945] Avg episode reward: [(0, '4852.035')] [2023-03-08 05:32:36,967][321237] Updated weights for policy 0, policy_version 166320 (0.0005) [2023-03-08 05:32:39,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11059.2, 300 sec: 11080.0). Total num frames: 85184512. Throughput: 0: 10995.0. Samples: 85170448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:32:39,595][320945] Avg episode reward: [(0, '4862.277')] [2023-03-08 05:32:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000166376_85184512.pth... [2023-03-08 05:32:39,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000165728_84852736.pth [2023-03-08 05:32:40,678][321237] Updated weights for policy 0, policy_version 166400 (0.0005) [2023-03-08 05:32:44,319][321237] Updated weights for policy 0, policy_version 166480 (0.0005) [2023-03-08 05:32:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11080.0). Total num frames: 85237760. Throughput: 0: 11021.1. Samples: 85237664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:32:44,595][320945] Avg episode reward: [(0, '4862.796')] [2023-03-08 05:32:48,023][321237] Updated weights for policy 0, policy_version 166560 (0.0005) [2023-03-08 05:32:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11059.2, 300 sec: 11080.0). Total num frames: 85295104. Throughput: 0: 11082.1. Samples: 85270536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:32:49,595][320945] Avg episode reward: [(0, '4864.323')] [2023-03-08 05:32:51,494][321237] Updated weights for policy 0, policy_version 166640 (0.0004) [2023-03-08 05:32:54,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 11080.0). Total num frames: 85348352. Throughput: 0: 11126.3. Samples: 85338396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:32:54,595][320945] Avg episode reward: [(0, '4864.569')] [2023-03-08 05:32:54,607][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000166704_85352448.pth... [2023-03-08 05:32:54,609][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000166056_85020672.pth [2023-03-08 05:32:55,315][321237] Updated weights for policy 0, policy_version 166720 (0.0005) [2023-03-08 05:32:59,114][321237] Updated weights for policy 0, policy_version 166800 (0.0005) [2023-03-08 05:32:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11093.9). Total num frames: 85405696. Throughput: 0: 11018.8. Samples: 85403356. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:32:59,595][320945] Avg episode reward: [(0, '4861.350')] [2023-03-08 05:33:02,915][321237] Updated weights for policy 0, policy_version 166880 (0.0004) [2023-03-08 05:33:04,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11059.2, 300 sec: 11093.9). Total num frames: 85458944. Throughput: 0: 10945.5. Samples: 85435460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:33:04,595][320945] Avg episode reward: [(0, '4864.635')] [2023-03-08 05:33:06,691][321237] Updated weights for policy 0, policy_version 166960 (0.0005) [2023-03-08 05:33:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11093.9). Total num frames: 85512192. Throughput: 0: 10943.5. Samples: 85500820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:33:09,595][320945] Avg episode reward: [(0, '4864.746')] [2023-03-08 05:33:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000167016_85512192.pth... [2023-03-08 05:33:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000166376_85184512.pth [2023-03-08 05:33:10,468][321237] Updated weights for policy 0, policy_version 167040 (0.0005) [2023-03-08 05:33:14,368][321237] Updated weights for policy 0, policy_version 167120 (0.0005) [2023-03-08 05:33:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11093.9). Total num frames: 85565440. Throughput: 0: 10951.7. Samples: 85564936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:33:14,595][320945] Avg episode reward: [(0, '4865.841')] [2023-03-08 05:33:18,119][321237] Updated weights for policy 0, policy_version 167200 (0.0005) [2023-03-08 05:33:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10922.7, 300 sec: 11107.8). Total num frames: 85622784. Throughput: 0: 10952.9. Samples: 85597660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:33:19,595][320945] Avg episode reward: [(0, '4863.967')] [2023-03-08 05:33:21,791][321237] Updated weights for policy 0, policy_version 167280 (0.0005) [2023-03-08 05:33:24,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 11107.8). Total num frames: 85676032. Throughput: 0: 10962.1. Samples: 85663744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:33:24,595][320945] Avg episode reward: [(0, '4865.101')] [2023-03-08 05:33:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000167336_85676032.pth... [2023-03-08 05:33:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000166704_85352448.pth [2023-03-08 05:33:25,568][321237] Updated weights for policy 0, policy_version 167360 (0.0005) [2023-03-08 05:33:29,396][321237] Updated weights for policy 0, policy_version 167440 (0.0005) [2023-03-08 05:33:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11093.9). Total num frames: 85729280. Throughput: 0: 10898.7. Samples: 85728104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:33:29,595][320945] Avg episode reward: [(0, '4865.257')] [2023-03-08 05:33:33,302][321237] Updated weights for policy 0, policy_version 167520 (0.0005) [2023-03-08 05:33:34,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11093.9). Total num frames: 85782528. Throughput: 0: 10859.7. Samples: 85759224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:33:34,595][320945] Avg episode reward: [(0, '4864.264')] [2023-03-08 05:33:37,127][321237] Updated weights for policy 0, policy_version 167600 (0.0005) [2023-03-08 05:33:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11080.0). Total num frames: 85835776. Throughput: 0: 10781.3. Samples: 85823552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:33:39,595][320945] Avg episode reward: [(0, '4817.788')] [2023-03-08 05:33:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000167648_85835776.pth... [2023-03-08 05:33:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000167016_85512192.pth [2023-03-08 05:33:40,823][321237] Updated weights for policy 0, policy_version 167680 (0.0005) [2023-03-08 05:33:44,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11080.0). Total num frames: 85889024. Throughput: 0: 10797.6. Samples: 85889248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:33:44,595][320945] Avg episode reward: [(0, '4864.367')] [2023-03-08 05:33:44,598][321237] Updated weights for policy 0, policy_version 167760 (0.0005) [2023-03-08 05:33:48,318][321237] Updated weights for policy 0, policy_version 167840 (0.0005) [2023-03-08 05:33:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11093.9). Total num frames: 85946368. Throughput: 0: 10809.0. Samples: 85921864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:33:49,595][320945] Avg episode reward: [(0, '4862.879')] [2023-03-08 05:33:52,088][321237] Updated weights for policy 0, policy_version 167920 (0.0005) [2023-03-08 05:33:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11080.0). Total num frames: 85999616. Throughput: 0: 10820.6. Samples: 85987748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:33:54,595][320945] Avg episode reward: [(0, '4864.712')] [2023-03-08 05:33:54,646][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000167976_86003712.pth... [2023-03-08 05:33:54,648][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000167336_85676032.pth [2023-03-08 05:33:55,728][321237] Updated weights for policy 0, policy_version 168000 (0.0005) [2023-03-08 05:33:59,522][321237] Updated weights for policy 0, policy_version 168080 (0.0005) [2023-03-08 05:33:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11093.9). Total num frames: 86056960. Throughput: 0: 10879.7. Samples: 86054524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:33:59,595][320945] Avg episode reward: [(0, '4861.916')] [2023-03-08 05:34:03,403][321237] Updated weights for policy 0, policy_version 168160 (0.0005) [2023-03-08 05:34:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11080.0). Total num frames: 86110208. Throughput: 0: 10845.2. Samples: 86085696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:34:04,595][320945] Avg episode reward: [(0, '4862.125')] [2023-03-08 05:34:07,250][321237] Updated weights for policy 0, policy_version 168240 (0.0005) [2023-03-08 05:34:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11066.1). Total num frames: 86163456. Throughput: 0: 10796.7. Samples: 86149596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:34:09,595][320945] Avg episode reward: [(0, '4863.275')] [2023-03-08 05:34:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000168288_86163456.pth... [2023-03-08 05:34:09,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000167648_85835776.pth [2023-03-08 05:34:11,127][321237] Updated weights for policy 0, policy_version 168320 (0.0005) [2023-03-08 05:34:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11052.3). Total num frames: 86216704. Throughput: 0: 10808.5. Samples: 86214488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:34:14,595][320945] Avg episode reward: [(0, '4864.929')] [2023-03-08 05:34:14,866][321237] Updated weights for policy 0, policy_version 168400 (0.0005) [2023-03-08 05:34:18,615][321237] Updated weights for policy 0, policy_version 168480 (0.0005) [2023-03-08 05:34:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11024.5). Total num frames: 86269952. Throughput: 0: 10856.9. Samples: 86247784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:34:19,595][320945] Avg episode reward: [(0, '4865.146')] [2023-03-08 05:34:22,287][321237] Updated weights for policy 0, policy_version 168560 (0.0005) [2023-03-08 05:34:24,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10786.1, 300 sec: 11010.6). Total num frames: 86323200. Throughput: 0: 10880.8. Samples: 86313188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:34:24,595][320945] Avg episode reward: [(0, '4864.168')] [2023-03-08 05:34:24,640][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000168608_86327296.pth... [2023-03-08 05:34:24,642][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000167976_86003712.pth [2023-03-08 05:34:26,202][321237] Updated weights for policy 0, policy_version 168640 (0.0005) [2023-03-08 05:34:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10996.7). Total num frames: 86376448. Throughput: 0: 10828.1. Samples: 86376512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:34:29,595][320945] Avg episode reward: [(0, '4866.541')] [2023-03-08 05:34:29,987][321237] Updated weights for policy 0, policy_version 168720 (0.0005) [2023-03-08 05:34:33,774][321237] Updated weights for policy 0, policy_version 168800 (0.0005) [2023-03-08 05:34:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10854.4, 300 sec: 10996.7). Total num frames: 86433792. Throughput: 0: 10831.6. Samples: 86409288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:34:34,595][320945] Avg episode reward: [(0, '4865.578')] [2023-03-08 05:34:37,555][321237] Updated weights for policy 0, policy_version 168880 (0.0005) [2023-03-08 05:34:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10982.8). Total num frames: 86487040. Throughput: 0: 10822.3. Samples: 86474752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:34:39,595][320945] Avg episode reward: [(0, '4866.922')] [2023-03-08 05:34:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000168920_86487040.pth... [2023-03-08 05:34:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000168288_86163456.pth [2023-03-08 05:34:41,128][321237] Updated weights for policy 0, policy_version 168960 (0.0005) [2023-03-08 05:34:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10982.8). Total num frames: 86544384. Throughput: 0: 10885.8. Samples: 86544384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:34:44,595][320945] Avg episode reward: [(0, '4864.029')] [2023-03-08 05:34:44,701][321237] Updated weights for policy 0, policy_version 169040 (0.0005) [2023-03-08 05:34:48,484][321237] Updated weights for policy 0, policy_version 169120 (0.0005) [2023-03-08 05:34:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10854.4, 300 sec: 10969.0). Total num frames: 86597632. Throughput: 0: 10904.1. Samples: 86576380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:34:49,594][320945] Avg episode reward: [(0, '4864.161')] [2023-03-08 05:34:52,288][321237] Updated weights for policy 0, policy_version 169200 (0.0005) [2023-03-08 05:34:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10968.9). Total num frames: 86654976. Throughput: 0: 10928.2. Samples: 86641364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:34:54,595][320945] Avg episode reward: [(0, '4865.285')] [2023-03-08 05:34:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000169248_86654976.pth... [2023-03-08 05:34:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000168608_86327296.pth [2023-03-08 05:34:56,123][321237] Updated weights for policy 0, policy_version 169280 (0.0005) [2023-03-08 05:34:59,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10854.4, 300 sec: 10968.9). Total num frames: 86708224. Throughput: 0: 10904.1. Samples: 86705172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:34:59,595][320945] Avg episode reward: [(0, '4865.195')] [2023-03-08 05:34:59,917][321237] Updated weights for policy 0, policy_version 169360 (0.0005) [2023-03-08 05:35:03,727][321237] Updated weights for policy 0, policy_version 169440 (0.0005) [2023-03-08 05:35:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10955.1). Total num frames: 86761472. Throughput: 0: 10878.4. Samples: 86737312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:35:04,595][320945] Avg episode reward: [(0, '4865.513')] [2023-03-08 05:35:07,557][321237] Updated weights for policy 0, policy_version 169520 (0.0005) [2023-03-08 05:35:09,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 10955.1). Total num frames: 86814720. Throughput: 0: 10871.2. Samples: 86802392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:35:09,595][320945] Avg episode reward: [(0, '4865.672')] [2023-03-08 05:35:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000169560_86814720.pth... [2023-03-08 05:35:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000168920_86487040.pth [2023-03-08 05:35:11,239][321237] Updated weights for policy 0, policy_version 169600 (0.0005) [2023-03-08 05:35:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10955.1). Total num frames: 86872064. Throughput: 0: 10941.2. Samples: 86868868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:35:14,595][320945] Avg episode reward: [(0, '4862.175')] [2023-03-08 05:35:14,897][321237] Updated weights for policy 0, policy_version 169680 (0.0005) [2023-03-08 05:35:18,611][321237] Updated weights for policy 0, policy_version 169760 (0.0005) [2023-03-08 05:35:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10941.2). Total num frames: 86925312. Throughput: 0: 10935.6. Samples: 86901388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:35:19,595][320945] Avg episode reward: [(0, '4865.110')] [2023-03-08 05:35:22,193][321237] Updated weights for policy 0, policy_version 169840 (0.0005) [2023-03-08 05:35:24,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10927.3). Total num frames: 86982656. Throughput: 0: 11015.1. Samples: 86970432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:35:24,595][320945] Avg episode reward: [(0, '4863.477')] [2023-03-08 05:35:24,622][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000169896_86986752.pth... [2023-03-08 05:35:24,623][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000169248_86654976.pth [2023-03-08 05:35:25,650][321237] Updated weights for policy 0, policy_version 169920 (0.0004) [2023-03-08 05:35:29,275][321237] Updated weights for policy 0, policy_version 170000 (0.0005) [2023-03-08 05:35:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 10927.3). Total num frames: 87040000. Throughput: 0: 11014.0. Samples: 87040012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:35:29,595][320945] Avg episode reward: [(0, '4861.081')] [2023-03-08 05:35:32,890][321237] Updated weights for policy 0, policy_version 170080 (0.0005) [2023-03-08 05:35:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 10927.3). Total num frames: 87097344. Throughput: 0: 11049.4. Samples: 87073604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:35:34,595][320945] Avg episode reward: [(0, '4863.233')] [2023-03-08 05:35:36,352][321237] Updated weights for policy 0, policy_version 170160 (0.0004) [2023-03-08 05:35:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 10941.2). Total num frames: 87154688. Throughput: 0: 11149.9. Samples: 87143108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:35:39,595][320945] Avg episode reward: [(0, '4862.876')] [2023-03-08 05:35:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000170224_87154688.pth... [2023-03-08 05:35:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000169560_86814720.pth [2023-03-08 05:35:40,119][321237] Updated weights for policy 0, policy_version 170240 (0.0004) [2023-03-08 05:35:43,942][321237] Updated weights for policy 0, policy_version 170320 (0.0005) [2023-03-08 05:35:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 87207936. Throughput: 0: 11171.8. Samples: 87207904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:35:44,595][320945] Avg episode reward: [(0, '4861.393')] [2023-03-08 05:35:47,726][321237] Updated weights for policy 0, policy_version 170400 (0.0005) [2023-03-08 05:35:49,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 87261184. Throughput: 0: 11175.5. Samples: 87240208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:35:49,595][320945] Avg episode reward: [(0, '4866.154')] [2023-03-08 05:35:51,565][321237] Updated weights for policy 0, policy_version 170480 (0.0005) [2023-03-08 05:35:54,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 87318528. Throughput: 0: 11152.7. Samples: 87304264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:35:54,595][320945] Avg episode reward: [(0, '4863.582')] [2023-03-08 05:35:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000170544_87318528.pth... [2023-03-08 05:35:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000169896_86986752.pth [2023-03-08 05:35:55,277][321237] Updated weights for policy 0, policy_version 170560 (0.0005) [2023-03-08 05:35:59,164][321237] Updated weights for policy 0, policy_version 170640 (0.0004) [2023-03-08 05:35:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 87371776. Throughput: 0: 11107.2. Samples: 87368692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:35:59,595][320945] Avg episode reward: [(0, '4864.519')] [2023-03-08 05:36:02,831][321237] Updated weights for policy 0, policy_version 170720 (0.0003) [2023-03-08 05:36:04,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11127.5, 300 sec: 10955.1). Total num frames: 87429120. Throughput: 0: 11140.2. Samples: 87402696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:36:04,595][320945] Avg episode reward: [(0, '4863.615')] [2023-03-08 05:36:06,480][321237] Updated weights for policy 0, policy_version 170800 (0.0004) [2023-03-08 05:36:09,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11127.5, 300 sec: 10941.2). Total num frames: 87482368. Throughput: 0: 11094.4. Samples: 87469680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:36:09,595][320945] Avg episode reward: [(0, '4864.454')] [2023-03-08 05:36:09,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000170864_87482368.pth... [2023-03-08 05:36:09,602][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000170224_87154688.pth [2023-03-08 05:36:10,235][321237] Updated weights for policy 0, policy_version 170880 (0.0005) [2023-03-08 05:36:14,091][321237] Updated weights for policy 0, policy_version 170960 (0.0005) [2023-03-08 05:36:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 87535616. Throughput: 0: 10970.0. Samples: 87533664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:36:14,595][320945] Avg episode reward: [(0, '4865.501')] [2023-03-08 05:36:17,866][321237] Updated weights for policy 0, policy_version 171040 (0.0005) [2023-03-08 05:36:19,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 87588864. Throughput: 0: 10952.3. Samples: 87566456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:36:19,595][320945] Avg episode reward: [(0, '4864.110')] [2023-03-08 05:36:21,615][321237] Updated weights for policy 0, policy_version 171120 (0.0005) [2023-03-08 05:36:24,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10941.2). Total num frames: 87642112. Throughput: 0: 10848.0. Samples: 87631268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:36:24,595][320945] Avg episode reward: [(0, '4862.272')] [2023-03-08 05:36:24,646][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000171184_87646208.pth... [2023-03-08 05:36:24,649][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000170544_87318528.pth [2023-03-08 05:36:25,400][321237] Updated weights for policy 0, policy_version 171200 (0.0005) [2023-03-08 05:36:29,029][321237] Updated weights for policy 0, policy_version 171280 (0.0005) [2023-03-08 05:36:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10955.1). Total num frames: 87699456. Throughput: 0: 10895.5. Samples: 87698200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:36:29,595][320945] Avg episode reward: [(0, '4864.604')] [2023-03-08 05:36:32,545][321237] Updated weights for policy 0, policy_version 171360 (0.0005) [2023-03-08 05:36:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 10968.9). Total num frames: 87756800. Throughput: 0: 10938.7. Samples: 87732448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:36:34,595][320945] Avg episode reward: [(0, '4863.493')] [2023-03-08 05:36:35,972][321237] Updated weights for policy 0, policy_version 171440 (0.0005) [2023-03-08 05:36:39,391][321237] Updated weights for policy 0, policy_version 171520 (0.0004) [2023-03-08 05:36:39,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11059.2, 300 sec: 10982.8). Total num frames: 87818240. Throughput: 0: 11114.5. Samples: 87804416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:36:39,595][320945] Avg episode reward: [(0, '4862.256')] [2023-03-08 05:36:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000171520_87818240.pth... [2023-03-08 05:36:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000170864_87482368.pth [2023-03-08 05:36:42,879][321237] Updated weights for policy 0, policy_version 171600 (0.0004) [2023-03-08 05:36:44,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11127.5, 300 sec: 10996.7). Total num frames: 87875584. Throughput: 0: 11252.2. Samples: 87875040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:36:44,595][320945] Avg episode reward: [(0, '4864.102')] [2023-03-08 05:36:46,675][321237] Updated weights for policy 0, policy_version 171680 (0.0005) [2023-03-08 05:36:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 10982.8). Total num frames: 87928832. Throughput: 0: 11194.2. Samples: 87906436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:36:49,595][320945] Avg episode reward: [(0, '4867.256')] [2023-03-08 05:36:50,564][321237] Updated weights for policy 0, policy_version 171760 (0.0005) [2023-03-08 05:36:54,326][321237] Updated weights for policy 0, policy_version 171840 (0.0005) [2023-03-08 05:36:54,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11059.2, 300 sec: 10982.8). Total num frames: 87982080. Throughput: 0: 11120.9. Samples: 87970120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:36:54,595][320945] Avg episode reward: [(0, '4865.616')] [2023-03-08 05:36:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000171840_87982080.pth... [2023-03-08 05:36:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000171184_87646208.pth [2023-03-08 05:36:58,128][321237] Updated weights for policy 0, policy_version 171920 (0.0005) [2023-03-08 05:36:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 10982.8). Total num frames: 88035328. Throughput: 0: 11148.5. Samples: 88035348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:36:59,595][320945] Avg episode reward: [(0, '4864.334')] [2023-03-08 05:37:01,923][321237] Updated weights for policy 0, policy_version 172000 (0.0005) [2023-03-08 05:37:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 10996.7). Total num frames: 88092672. Throughput: 0: 11147.9. Samples: 88068112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:37:04,595][320945] Avg episode reward: [(0, '4864.926')] [2023-03-08 05:37:05,654][321237] Updated weights for policy 0, policy_version 172080 (0.0005) [2023-03-08 05:37:09,481][321237] Updated weights for policy 0, policy_version 172160 (0.0005) [2023-03-08 05:37:09,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 10969.0). Total num frames: 88145920. Throughput: 0: 11154.3. Samples: 88133212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:37:09,595][320945] Avg episode reward: [(0, '4861.776')] [2023-03-08 05:37:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000172160_88145920.pth... [2023-03-08 05:37:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000171520_87818240.pth [2023-03-08 05:37:13,192][321237] Updated weights for policy 0, policy_version 172240 (0.0005) [2023-03-08 05:37:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 10955.1). Total num frames: 88199168. Throughput: 0: 11126.6. Samples: 88198896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:37:14,595][320945] Avg episode reward: [(0, '4865.205')] [2023-03-08 05:37:17,005][321237] Updated weights for policy 0, policy_version 172320 (0.0005) [2023-03-08 05:37:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 10955.1). Total num frames: 88252416. Throughput: 0: 11082.6. Samples: 88231164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:37:19,595][320945] Avg episode reward: [(0, '4864.862')] [2023-03-08 05:37:20,858][321237] Updated weights for policy 0, policy_version 172400 (0.0005) [2023-03-08 05:37:24,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11059.2, 300 sec: 10955.1). Total num frames: 88305664. Throughput: 0: 10901.4. Samples: 88294980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:37:24,595][320945] Avg episode reward: [(0, '4862.973')] [2023-03-08 05:37:24,622][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000172480_88309760.pth... [2023-03-08 05:37:24,623][321237] Updated weights for policy 0, policy_version 172480 (0.0005) [2023-03-08 05:37:24,624][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000171840_87982080.pth [2023-03-08 05:37:28,436][321237] Updated weights for policy 0, policy_version 172560 (0.0005) [2023-03-08 05:37:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 10969.0). Total num frames: 88363008. Throughput: 0: 10765.4. Samples: 88359484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:37:29,594][320945] Avg episode reward: [(0, '4863.427')] [2023-03-08 05:37:32,200][321237] Updated weights for policy 0, policy_version 172640 (0.0005) [2023-03-08 05:37:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 10955.1). Total num frames: 88416256. Throughput: 0: 10793.5. Samples: 88392144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:37:34,595][320945] Avg episode reward: [(0, '4820.522')] [2023-03-08 05:37:35,902][321237] Updated weights for policy 0, policy_version 172720 (0.0005) [2023-03-08 05:37:39,594][320945] Fps is (10 sec: 10649.4, 60 sec: 10854.4, 300 sec: 10955.1). Total num frames: 88469504. Throughput: 0: 10869.1. Samples: 88459232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:37:39,595][320945] Avg episode reward: [(0, '4861.629')] [2023-03-08 05:37:39,600][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000172800_88473600.pth... [2023-03-08 05:37:39,600][321237] Updated weights for policy 0, policy_version 172800 (0.0005) [2023-03-08 05:37:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000172160_88145920.pth [2023-03-08 05:37:43,384][321237] Updated weights for policy 0, policy_version 172880 (0.0005) [2023-03-08 05:37:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10955.1). Total num frames: 88526848. Throughput: 0: 10854.9. Samples: 88523820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:37:44,595][320945] Avg episode reward: [(0, '4864.842')] [2023-03-08 05:37:47,225][321237] Updated weights for policy 0, policy_version 172960 (0.0005) [2023-03-08 05:37:49,594][320945] Fps is (10 sec: 11059.4, 60 sec: 10854.4, 300 sec: 10955.1). Total num frames: 88580096. Throughput: 0: 10832.9. Samples: 88555592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:37:49,595][320945] Avg episode reward: [(0, '4865.881')] [2023-03-08 05:37:50,991][321237] Updated weights for policy 0, policy_version 173040 (0.0005) [2023-03-08 05:37:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10941.2). Total num frames: 88633344. Throughput: 0: 10841.0. Samples: 88621056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:37:54,595][320945] Avg episode reward: [(0, '4817.622')] [2023-03-08 05:37:54,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000173112_88633344.pth... [2023-03-08 05:37:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000172480_88309760.pth [2023-03-08 05:37:54,826][321237] Updated weights for policy 0, policy_version 173120 (0.0005) [2023-03-08 05:37:58,634][321237] Updated weights for policy 0, policy_version 173200 (0.0005) [2023-03-08 05:37:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10941.2). Total num frames: 88686592. Throughput: 0: 10826.7. Samples: 88686096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:37:59,595][320945] Avg episode reward: [(0, '4863.876')] [2023-03-08 05:38:02,173][321237] Updated weights for policy 0, policy_version 173280 (0.0004) [2023-03-08 05:38:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10955.1). Total num frames: 88743936. Throughput: 0: 10861.9. Samples: 88719948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:38:04,595][320945] Avg episode reward: [(0, '4865.067')] [2023-03-08 05:38:05,648][321237] Updated weights for policy 0, policy_version 173360 (0.0004) [2023-03-08 05:38:09,137][321237] Updated weights for policy 0, policy_version 173440 (0.0004) [2023-03-08 05:38:09,594][320945] Fps is (10 sec: 11878.4, 60 sec: 10990.9, 300 sec: 10982.8). Total num frames: 88805376. Throughput: 0: 11024.8. Samples: 88791096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:38:09,595][320945] Avg episode reward: [(0, '4863.170')] [2023-03-08 05:38:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000173448_88805376.pth... [2023-03-08 05:38:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000172800_88473600.pth [2023-03-08 05:38:12,651][321237] Updated weights for policy 0, policy_version 173520 (0.0004) [2023-03-08 05:38:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11059.2, 300 sec: 10982.8). Total num frames: 88862720. Throughput: 0: 11149.9. Samples: 88861232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:38:14,595][320945] Avg episode reward: [(0, '4865.825')] [2023-03-08 05:38:16,154][321237] Updated weights for policy 0, policy_version 173600 (0.0004) [2023-03-08 05:38:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11127.5, 300 sec: 10996.7). Total num frames: 88920064. Throughput: 0: 11187.2. Samples: 88895568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:38:19,595][320945] Avg episode reward: [(0, '4863.917')] [2023-03-08 05:38:19,654][321237] Updated weights for policy 0, policy_version 173680 (0.0004) [2023-03-08 05:38:23,149][321237] Updated weights for policy 0, policy_version 173760 (0.0004) [2023-03-08 05:38:24,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 11024.5). Total num frames: 88981504. Throughput: 0: 11269.2. Samples: 88966344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:38:24,595][320945] Avg episode reward: [(0, '4866.002')] [2023-03-08 05:38:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000173792_88981504.pth... [2023-03-08 05:38:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000173112_88633344.pth [2023-03-08 05:38:26,740][321237] Updated weights for policy 0, policy_version 173840 (0.0004) [2023-03-08 05:38:29,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 11038.4). Total num frames: 89038848. Throughput: 0: 11361.1. Samples: 89035072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:38:29,595][320945] Avg episode reward: [(0, '4863.423')] [2023-03-08 05:38:30,233][321237] Updated weights for policy 0, policy_version 173920 (0.0004) [2023-03-08 05:38:33,689][321237] Updated weights for policy 0, policy_version 174000 (0.0005) [2023-03-08 05:38:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11052.3). Total num frames: 89096192. Throughput: 0: 11460.0. Samples: 89071292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:38:34,595][320945] Avg episode reward: [(0, '4862.786')] [2023-03-08 05:38:37,196][321237] Updated weights for policy 0, policy_version 174080 (0.0004) [2023-03-08 05:38:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.6, 300 sec: 11066.1). Total num frames: 89153536. Throughput: 0: 11561.4. Samples: 89141320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:38:39,595][320945] Avg episode reward: [(0, '4865.181')] [2023-03-08 05:38:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000174128_89153536.pth... [2023-03-08 05:38:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000173448_88805376.pth [2023-03-08 05:38:40,854][321237] Updated weights for policy 0, policy_version 174160 (0.0004) [2023-03-08 05:38:44,528][321237] Updated weights for policy 0, policy_version 174240 (0.0004) [2023-03-08 05:38:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11066.1). Total num frames: 89210880. Throughput: 0: 11596.4. Samples: 89207936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:38:44,595][320945] Avg episode reward: [(0, '4863.902')] [2023-03-08 05:38:48,243][321237] Updated weights for policy 0, policy_version 174320 (0.0004) [2023-03-08 05:38:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11400.5, 300 sec: 11066.1). Total num frames: 89264128. Throughput: 0: 11560.9. Samples: 89240188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:38:49,594][320945] Avg episode reward: [(0, '4863.825')] [2023-03-08 05:38:51,950][321237] Updated weights for policy 0, policy_version 174400 (0.0004) [2023-03-08 05:38:54,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11400.5, 300 sec: 11052.3). Total num frames: 89317376. Throughput: 0: 11459.7. Samples: 89306780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:38:54,594][320945] Avg episode reward: [(0, '4865.062')] [2023-03-08 05:38:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000174448_89317376.pth... [2023-03-08 05:38:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000173792_88981504.pth [2023-03-08 05:38:55,831][321237] Updated weights for policy 0, policy_version 174480 (0.0005) [2023-03-08 05:38:59,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11400.5, 300 sec: 11052.3). Total num frames: 89370624. Throughput: 0: 11320.0. Samples: 89370632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:38:59,595][320945] Avg episode reward: [(0, '4864.800')] [2023-03-08 05:38:59,656][321237] Updated weights for policy 0, policy_version 174560 (0.0005) [2023-03-08 05:39:03,567][321237] Updated weights for policy 0, policy_version 174640 (0.0005) [2023-03-08 05:39:04,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11332.3, 300 sec: 11052.3). Total num frames: 89423872. Throughput: 0: 11280.8. Samples: 89403204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:39:04,595][320945] Avg episode reward: [(0, '4863.798')] [2023-03-08 05:39:07,411][321237] Updated weights for policy 0, policy_version 174720 (0.0005) [2023-03-08 05:39:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11052.3). Total num frames: 89477120. Throughput: 0: 11097.1. Samples: 89465712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:39:09,595][320945] Avg episode reward: [(0, '4863.347')] [2023-03-08 05:39:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000174760_89477120.pth... [2023-03-08 05:39:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000174128_89153536.pth [2023-03-08 05:39:11,300][321237] Updated weights for policy 0, policy_version 174800 (0.0005) [2023-03-08 05:39:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11052.3). Total num frames: 89530368. Throughput: 0: 11004.0. Samples: 89530252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:39:14,595][320945] Avg episode reward: [(0, '4863.651')] [2023-03-08 05:39:15,098][321237] Updated weights for policy 0, policy_version 174880 (0.0004) [2023-03-08 05:39:18,964][321237] Updated weights for policy 0, policy_version 174960 (0.0005) [2023-03-08 05:39:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11052.3). Total num frames: 89583616. Throughput: 0: 10895.6. Samples: 89561592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:39:19,595][320945] Avg episode reward: [(0, '4864.639')] [2023-03-08 05:39:22,699][321237] Updated weights for policy 0, policy_version 175040 (0.0004) [2023-03-08 05:39:24,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10922.7, 300 sec: 11052.3). Total num frames: 89636864. Throughput: 0: 10793.5. Samples: 89627028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:39:24,595][320945] Avg episode reward: [(0, '4863.036')] [2023-03-08 05:39:24,646][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000175080_89640960.pth... [2023-03-08 05:39:24,647][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000174448_89317376.pth [2023-03-08 05:39:26,619][321237] Updated weights for policy 0, policy_version 175120 (0.0005) [2023-03-08 05:39:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11038.4). Total num frames: 89690112. Throughput: 0: 10715.3. Samples: 89690124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:39:29,603][320945] Avg episode reward: [(0, '4866.221')] [2023-03-08 05:39:30,442][321237] Updated weights for policy 0, policy_version 175200 (0.0005) [2023-03-08 05:39:34,219][321237] Updated weights for policy 0, policy_version 175280 (0.0005) [2023-03-08 05:39:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10854.4, 300 sec: 11052.3). Total num frames: 89747456. Throughput: 0: 10726.5. Samples: 89722880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:39:34,602][320945] Avg episode reward: [(0, '4864.950')] [2023-03-08 05:39:38,107][321237] Updated weights for policy 0, policy_version 175360 (0.0005) [2023-03-08 05:39:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 11024.5). Total num frames: 89796608. Throughput: 0: 10653.4. Samples: 89786184. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:39:39,605][320945] Avg episode reward: [(0, '4862.377')] [2023-03-08 05:39:39,636][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000175392_89800704.pth... [2023-03-08 05:39:39,637][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000174760_89477120.pth [2023-03-08 05:39:41,962][321237] Updated weights for policy 0, policy_version 175440 (0.0005) [2023-03-08 05:39:44,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 11038.4). Total num frames: 89853952. Throughput: 0: 10675.1. Samples: 89851012. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:39:44,605][320945] Avg episode reward: [(0, '4865.010')] [2023-03-08 05:39:45,638][321237] Updated weights for policy 0, policy_version 175520 (0.0005) [2023-03-08 05:39:49,495][321237] Updated weights for policy 0, policy_version 175600 (0.0005) [2023-03-08 05:39:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 11024.5). Total num frames: 89907200. Throughput: 0: 10675.9. Samples: 89883620. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:39:49,605][320945] Avg episode reward: [(0, '4862.130')] [2023-03-08 05:39:53,318][321237] Updated weights for policy 0, policy_version 175680 (0.0005) [2023-03-08 05:39:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 11024.5). Total num frames: 89960448. Throughput: 0: 10717.7. Samples: 89948008. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:39:54,595][320945] Avg episode reward: [(0, '4863.908')] [2023-03-08 05:39:54,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000175704_89960448.pth... [2023-03-08 05:39:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000175080_89640960.pth [2023-03-08 05:39:57,119][321237] Updated weights for policy 0, policy_version 175760 (0.0005) [2023-03-08 05:39:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 11024.5). Total num frames: 90013696. Throughput: 0: 10707.9. Samples: 90012108. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:39:59,595][320945] Avg episode reward: [(0, '4864.143')] [2023-03-08 05:40:00,944][321237] Updated weights for policy 0, policy_version 175840 (0.0005) [2023-03-08 05:40:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 11024.5). Total num frames: 90066944. Throughput: 0: 10733.6. Samples: 90044604. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:40:04,595][320945] Avg episode reward: [(0, '4866.029')] [2023-03-08 05:40:04,671][321237] Updated weights for policy 0, policy_version 175920 (0.0005) [2023-03-08 05:40:08,448][321237] Updated weights for policy 0, policy_version 176000 (0.0005) [2023-03-08 05:40:09,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 11024.5). Total num frames: 90124288. Throughput: 0: 10737.4. Samples: 90110212. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:40:09,595][320945] Avg episode reward: [(0, '4865.014')] [2023-03-08 05:40:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000176024_90124288.pth... [2023-03-08 05:40:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000175392_89800704.pth [2023-03-08 05:40:12,234][321237] Updated weights for policy 0, policy_version 176080 (0.0005) [2023-03-08 05:40:14,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10786.1, 300 sec: 11024.5). Total num frames: 90177536. Throughput: 0: 10746.7. Samples: 90173724. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:40:14,595][320945] Avg episode reward: [(0, '4863.469')] [2023-03-08 05:40:16,136][321237] Updated weights for policy 0, policy_version 176160 (0.0005) [2023-03-08 05:40:19,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10786.1, 300 sec: 11010.6). Total num frames: 90230784. Throughput: 0: 10740.8. Samples: 90206216. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:40:19,595][320945] Avg episode reward: [(0, '4866.753')] [2023-03-08 05:40:19,908][321237] Updated weights for policy 0, policy_version 176240 (0.0005) [2023-03-08 05:40:23,718][321237] Updated weights for policy 0, policy_version 176320 (0.0005) [2023-03-08 05:40:24,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10786.1, 300 sec: 10996.7). Total num frames: 90284032. Throughput: 0: 10787.6. Samples: 90271624. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:40:24,595][320945] Avg episode reward: [(0, '4863.185')] [2023-03-08 05:40:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000176336_90284032.pth... [2023-03-08 05:40:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000175704_89960448.pth [2023-03-08 05:40:27,384][321237] Updated weights for policy 0, policy_version 176400 (0.0005) [2023-03-08 05:40:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.2, 300 sec: 10982.8). Total num frames: 90337280. Throughput: 0: 10806.0. Samples: 90337280. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:40:29,594][320945] Avg episode reward: [(0, '4865.029')] [2023-03-08 05:40:31,150][321237] Updated weights for policy 0, policy_version 176480 (0.0005) [2023-03-08 05:40:34,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 10982.8). Total num frames: 90394624. Throughput: 0: 10809.7. Samples: 90370056. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:40:34,595][320945] Avg episode reward: [(0, '4864.798')] [2023-03-08 05:40:34,862][321237] Updated weights for policy 0, policy_version 176560 (0.0004) [2023-03-08 05:40:38,640][321237] Updated weights for policy 0, policy_version 176640 (0.0005) [2023-03-08 05:40:39,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10854.4, 300 sec: 10982.8). Total num frames: 90447872. Throughput: 0: 10835.2. Samples: 90435592. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:40:39,595][320945] Avg episode reward: [(0, '4864.719')] [2023-03-08 05:40:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000176656_90447872.pth... [2023-03-08 05:40:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000176024_90124288.pth [2023-03-08 05:40:42,371][321237] Updated weights for policy 0, policy_version 176720 (0.0005) [2023-03-08 05:40:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10996.7). Total num frames: 90505216. Throughput: 0: 10907.9. Samples: 90502964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:40:44,595][320945] Avg episode reward: [(0, '4863.874')] [2023-03-08 05:40:45,952][321237] Updated weights for policy 0, policy_version 176800 (0.0003) [2023-03-08 05:40:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10854.4, 300 sec: 10982.8). Total num frames: 90558464. Throughput: 0: 10918.5. Samples: 90535936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:40:49,595][320945] Avg episode reward: [(0, '4863.176')] [2023-03-08 05:40:49,684][321237] Updated weights for policy 0, policy_version 176880 (0.0004) [2023-03-08 05:40:53,461][321237] Updated weights for policy 0, policy_version 176960 (0.0005) [2023-03-08 05:40:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10996.7). Total num frames: 90615808. Throughput: 0: 10924.0. Samples: 90601792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:40:54,595][320945] Avg episode reward: [(0, '4863.876')] [2023-03-08 05:40:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000176984_90615808.pth... [2023-03-08 05:40:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000176336_90284032.pth [2023-03-08 05:40:57,111][321237] Updated weights for policy 0, policy_version 177040 (0.0004) [2023-03-08 05:40:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10982.8). Total num frames: 90669056. Throughput: 0: 11009.0. Samples: 90669128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:40:59,594][320945] Avg episode reward: [(0, '4864.965')] [2023-03-08 05:41:00,752][321237] Updated weights for policy 0, policy_version 177120 (0.0003) [2023-03-08 05:41:04,535][321237] Updated weights for policy 0, policy_version 177200 (0.0005) [2023-03-08 05:41:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10996.7). Total num frames: 90726400. Throughput: 0: 11013.5. Samples: 90701824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:41:04,595][320945] Avg episode reward: [(0, '4866.262')] [2023-03-08 05:41:08,172][321237] Updated weights for policy 0, policy_version 177280 (0.0004) [2023-03-08 05:41:09,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 10996.7). Total num frames: 90779648. Throughput: 0: 11030.1. Samples: 90767980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:41:09,605][320945] Avg episode reward: [(0, '4863.824')] [2023-03-08 05:41:09,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000177304_90779648.pth... [2023-03-08 05:41:09,612][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000176656_90447872.pth [2023-03-08 05:41:11,994][321237] Updated weights for policy 0, policy_version 177360 (0.0005) [2023-03-08 05:41:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10996.7). Total num frames: 90832896. Throughput: 0: 11015.3. Samples: 90832968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:41:14,605][320945] Avg episode reward: [(0, '4863.497')] [2023-03-08 05:41:15,767][321237] Updated weights for policy 0, policy_version 177440 (0.0005) [2023-03-08 05:41:19,396][321237] Updated weights for policy 0, policy_version 177520 (0.0003) [2023-03-08 05:41:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11010.6). Total num frames: 90890240. Throughput: 0: 11014.9. Samples: 90865728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:41:19,605][320945] Avg episode reward: [(0, '4866.399')] [2023-03-08 05:41:23,044][321237] Updated weights for policy 0, policy_version 177600 (0.0003) [2023-03-08 05:41:24,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 10996.7). Total num frames: 90943488. Throughput: 0: 11071.2. Samples: 90933796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:41:24,605][320945] Avg episode reward: [(0, '4863.466')] [2023-03-08 05:41:24,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000177632_90947584.pth... [2023-03-08 05:41:24,612][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000176984_90615808.pth [2023-03-08 05:41:26,790][321237] Updated weights for policy 0, policy_version 177680 (0.0004) [2023-03-08 05:41:29,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11059.2, 300 sec: 10996.7). Total num frames: 91000832. Throughput: 0: 11016.2. Samples: 90998692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:41:29,605][320945] Avg episode reward: [(0, '4865.476')] [2023-03-08 05:41:30,595][321237] Updated weights for policy 0, policy_version 177760 (0.0005) [2023-03-08 05:41:34,447][321237] Updated weights for policy 0, policy_version 177840 (0.0005) [2023-03-08 05:41:34,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10969.0). Total num frames: 91054080. Throughput: 0: 10999.1. Samples: 91030896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:41:34,605][320945] Avg episode reward: [(0, '4864.441')] [2023-03-08 05:41:38,202][321237] Updated weights for policy 0, policy_version 177920 (0.0005) [2023-03-08 05:41:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10955.1). Total num frames: 91107328. Throughput: 0: 10970.1. Samples: 91095448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:41:39,605][320945] Avg episode reward: [(0, '4862.578')] [2023-03-08 05:41:39,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000177944_91107328.pth... [2023-03-08 05:41:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000177304_90779648.pth [2023-03-08 05:41:42,076][321237] Updated weights for policy 0, policy_version 178000 (0.0005) [2023-03-08 05:41:44,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.6, 300 sec: 10955.1). Total num frames: 91160576. Throughput: 0: 10911.4. Samples: 91160144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:41:44,605][320945] Avg episode reward: [(0, '4866.875')] [2023-03-08 05:41:45,823][321237] Updated weights for policy 0, policy_version 178080 (0.0005) [2023-03-08 05:41:49,549][321237] Updated weights for policy 0, policy_version 178160 (0.0005) [2023-03-08 05:41:49,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 10968.9). Total num frames: 91217920. Throughput: 0: 10922.6. Samples: 91193344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:41:49,605][320945] Avg episode reward: [(0, '4863.937')] [2023-03-08 05:41:53,319][321237] Updated weights for policy 0, policy_version 178240 (0.0003) [2023-03-08 05:41:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10968.9). Total num frames: 91271168. Throughput: 0: 10908.9. Samples: 91258880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:41:54,605][320945] Avg episode reward: [(0, '4865.540')] [2023-03-08 05:41:54,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000178264_91271168.pth... [2023-03-08 05:41:54,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000177632_90947584.pth [2023-03-08 05:41:57,123][321237] Updated weights for policy 0, policy_version 178320 (0.0003) [2023-03-08 05:41:59,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10922.7, 300 sec: 10955.1). Total num frames: 91324416. Throughput: 0: 10902.6. Samples: 91323584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:41:59,605][320945] Avg episode reward: [(0, '4865.184')] [2023-03-08 05:42:00,930][321237] Updated weights for policy 0, policy_version 178400 (0.0004) [2023-03-08 05:42:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10955.1). Total num frames: 91377664. Throughput: 0: 10890.4. Samples: 91355796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:42:04,605][320945] Avg episode reward: [(0, '4862.352')] [2023-03-08 05:42:04,623][321237] Updated weights for policy 0, policy_version 178480 (0.0005) [2023-03-08 05:42:08,166][321237] Updated weights for policy 0, policy_version 178560 (0.0004) [2023-03-08 05:42:09,594][320945] Fps is (10 sec: 11468.7, 60 sec: 10990.9, 300 sec: 10982.8). Total num frames: 91439104. Throughput: 0: 10887.1. Samples: 91423716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:42:09,605][320945] Avg episode reward: [(0, '4865.140')] [2023-03-08 05:42:09,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000178592_91439104.pth... [2023-03-08 05:42:09,612][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000177944_91107328.pth [2023-03-08 05:42:11,689][321237] Updated weights for policy 0, policy_version 178640 (0.0004) [2023-03-08 05:42:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11059.2, 300 sec: 10996.7). Total num frames: 91496448. Throughput: 0: 11003.6. Samples: 91493856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:42:14,605][320945] Avg episode reward: [(0, '4865.596')] [2023-03-08 05:42:15,226][321237] Updated weights for policy 0, policy_version 178720 (0.0005) [2023-03-08 05:42:18,697][321237] Updated weights for policy 0, policy_version 178800 (0.0004) [2023-03-08 05:42:19,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11059.2, 300 sec: 11010.6). Total num frames: 91553792. Throughput: 0: 11072.4. Samples: 91529156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:42:19,605][320945] Avg episode reward: [(0, '4861.392')] [2023-03-08 05:42:22,106][321237] Updated weights for policy 0, policy_version 178880 (0.0004) [2023-03-08 05:42:24,594][320945] Fps is (10 sec: 11468.9, 60 sec: 11127.5, 300 sec: 11010.6). Total num frames: 91611136. Throughput: 0: 11214.5. Samples: 91600100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:42:24,594][320945] Avg episode reward: [(0, '4862.829')] [2023-03-08 05:42:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000178928_91611136.pth... [2023-03-08 05:42:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000178264_91271168.pth [2023-03-08 05:42:25,850][321237] Updated weights for policy 0, policy_version 178960 (0.0005) [2023-03-08 05:42:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11010.6). Total num frames: 91664384. Throughput: 0: 11206.9. Samples: 91664456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:42:29,595][320945] Avg episode reward: [(0, '4865.652')] [2023-03-08 05:42:29,638][321237] Updated weights for policy 0, policy_version 179040 (0.0005) [2023-03-08 05:42:33,438][321237] Updated weights for policy 0, policy_version 179120 (0.0005) [2023-03-08 05:42:34,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11024.5). Total num frames: 91721728. Throughput: 0: 11196.1. Samples: 91697168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:42:34,595][320945] Avg episode reward: [(0, '4866.793')] [2023-03-08 05:42:37,204][321237] Updated weights for policy 0, policy_version 179200 (0.0005) [2023-03-08 05:42:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11010.6). Total num frames: 91774976. Throughput: 0: 11195.7. Samples: 91762688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:42:39,595][320945] Avg episode reward: [(0, '4864.619')] [2023-03-08 05:42:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000179248_91774976.pth... [2023-03-08 05:42:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000178592_91439104.pth [2023-03-08 05:42:40,975][321237] Updated weights for policy 0, policy_version 179280 (0.0005) [2023-03-08 05:42:44,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11010.6). Total num frames: 91828224. Throughput: 0: 11183.8. Samples: 91826856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:42:44,595][320945] Avg episode reward: [(0, '4866.124')] [2023-03-08 05:42:44,832][321237] Updated weights for policy 0, policy_version 179360 (0.0005) [2023-03-08 05:42:48,555][321237] Updated weights for policy 0, policy_version 179440 (0.0005) [2023-03-08 05:42:49,594][320945] Fps is (10 sec: 10649.7, 60 sec: 11059.2, 300 sec: 11010.6). Total num frames: 91881472. Throughput: 0: 11167.2. Samples: 91858320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:42:49,594][320945] Avg episode reward: [(0, '4820.178')] [2023-03-08 05:42:52,290][321237] Updated weights for policy 0, policy_version 179520 (0.0005) [2023-03-08 05:42:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11024.5). Total num frames: 91938816. Throughput: 0: 11159.7. Samples: 91925900. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:42:54,595][320945] Avg episode reward: [(0, '4864.455')] [2023-03-08 05:42:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000179568_91938816.pth... [2023-03-08 05:42:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000178928_91611136.pth [2023-03-08 05:42:55,964][321237] Updated weights for policy 0, policy_version 179600 (0.0005) [2023-03-08 05:42:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11010.6). Total num frames: 91992064. Throughput: 0: 11071.7. Samples: 91992080. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:42:59,594][320945] Avg episode reward: [(0, '4864.227')] [2023-03-08 05:42:59,667][321237] Updated weights for policy 0, policy_version 179680 (0.0005) [2023-03-08 05:43:03,470][321237] Updated weights for policy 0, policy_version 179760 (0.0005) [2023-03-08 05:43:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 10982.8). Total num frames: 92045312. Throughput: 0: 11011.8. Samples: 92024688. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:43:04,595][320945] Avg episode reward: [(0, '4864.429')] [2023-03-08 05:43:07,280][321237] Updated weights for policy 0, policy_version 179840 (0.0005) [2023-03-08 05:43:09,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11059.2, 300 sec: 10982.8). Total num frames: 92102656. Throughput: 0: 10862.0. Samples: 92088892. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:43:09,595][320945] Avg episode reward: [(0, '4864.002')] [2023-03-08 05:43:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000179888_92102656.pth... [2023-03-08 05:43:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000179248_91774976.pth [2023-03-08 05:43:10,975][321237] Updated weights for policy 0, policy_version 179920 (0.0005) [2023-03-08 05:43:14,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10991.0, 300 sec: 10969.0). Total num frames: 92155904. Throughput: 0: 10921.1. Samples: 92155904. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:43:14,594][320945] Avg episode reward: [(0, '4864.074')] [2023-03-08 05:43:14,674][321237] Updated weights for policy 0, policy_version 180000 (0.0005) [2023-03-08 05:43:18,316][321237] Updated weights for policy 0, policy_version 180080 (0.0005) [2023-03-08 05:43:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10955.1). Total num frames: 92213248. Throughput: 0: 10923.9. Samples: 92188744. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:43:19,595][320945] Avg episode reward: [(0, '4865.401')] [2023-03-08 05:43:21,996][321237] Updated weights for policy 0, policy_version 180160 (0.0005) [2023-03-08 05:43:24,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 10941.2). Total num frames: 92266496. Throughput: 0: 10955.8. Samples: 92255700. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:43:24,595][320945] Avg episode reward: [(0, '4862.893')] [2023-03-08 05:43:24,600][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000180216_92270592.pth... [2023-03-08 05:43:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000179568_91938816.pth [2023-03-08 05:43:25,743][321237] Updated weights for policy 0, policy_version 180240 (0.0005) [2023-03-08 05:43:29,467][321237] Updated weights for policy 0, policy_version 180320 (0.0005) [2023-03-08 05:43:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10941.2). Total num frames: 92323840. Throughput: 0: 11004.2. Samples: 92322044. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:43:29,595][320945] Avg episode reward: [(0, '4865.049')] [2023-03-08 05:43:33,116][321237] Updated weights for policy 0, policy_version 180400 (0.0005) [2023-03-08 05:43:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 10941.2). Total num frames: 92381184. Throughput: 0: 11045.9. Samples: 92355384. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:43:34,595][320945] Avg episode reward: [(0, '4865.136')] [2023-03-08 05:43:36,769][321237] Updated weights for policy 0, policy_version 180480 (0.0005) [2023-03-08 05:43:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10927.3). Total num frames: 92434432. Throughput: 0: 11029.1. Samples: 92422208. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:43:39,595][320945] Avg episode reward: [(0, '4864.754')] [2023-03-08 05:43:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000180536_92434432.pth... [2023-03-08 05:43:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000179888_92102656.pth [2023-03-08 05:43:40,450][321237] Updated weights for policy 0, policy_version 180560 (0.0005) [2023-03-08 05:43:44,164][321237] Updated weights for policy 0, policy_version 180640 (0.0005) [2023-03-08 05:43:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 92491776. Throughput: 0: 11034.1. Samples: 92488616. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:43:44,595][320945] Avg episode reward: [(0, '4864.477')] [2023-03-08 05:43:47,868][321237] Updated weights for policy 0, policy_version 180720 (0.0005) [2023-03-08 05:43:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 92545024. Throughput: 0: 11054.1. Samples: 92522124. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:43:49,595][320945] Avg episode reward: [(0, '4864.228')] [2023-03-08 05:43:51,634][321237] Updated weights for policy 0, policy_version 180800 (0.0005) [2023-03-08 05:43:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10941.2). Total num frames: 92598272. Throughput: 0: 11074.0. Samples: 92587220. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 05:43:54,595][320945] Avg episode reward: [(0, '4863.857')] [2023-03-08 05:43:54,630][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000180864_92602368.pth... [2023-03-08 05:43:54,632][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000180216_92270592.pth [2023-03-08 05:43:55,396][321237] Updated weights for policy 0, policy_version 180880 (0.0005) [2023-03-08 05:43:59,171][321237] Updated weights for policy 0, policy_version 180960 (0.0005) [2023-03-08 05:43:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 10955.1). Total num frames: 92655616. Throughput: 0: 11031.5. Samples: 92652324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:43:59,595][320945] Avg episode reward: [(0, '4863.729')] [2023-03-08 05:44:02,542][321237] Updated weights for policy 0, policy_version 181040 (0.0005) [2023-03-08 05:44:04,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11195.7, 300 sec: 10982.8). Total num frames: 92717056. Throughput: 0: 11115.7. Samples: 92688952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:44:04,595][320945] Avg episode reward: [(0, '4863.598')] [2023-03-08 05:44:05,932][321237] Updated weights for policy 0, policy_version 181120 (0.0004) [2023-03-08 05:44:09,252][321237] Updated weights for policy 0, policy_version 181200 (0.0004) [2023-03-08 05:44:09,594][320945] Fps is (10 sec: 12287.9, 60 sec: 11264.0, 300 sec: 11010.6). Total num frames: 92778496. Throughput: 0: 11253.8. Samples: 92762120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:44:09,595][320945] Avg episode reward: [(0, '4864.827')] [2023-03-08 05:44:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000181208_92778496.pth... [2023-03-08 05:44:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000180536_92434432.pth [2023-03-08 05:44:12,634][321237] Updated weights for policy 0, policy_version 181280 (0.0004) [2023-03-08 05:44:14,594][320945] Fps is (10 sec: 11878.4, 60 sec: 11332.2, 300 sec: 11024.5). Total num frames: 92835840. Throughput: 0: 11416.8. Samples: 92835800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:44:14,595][320945] Avg episode reward: [(0, '4863.036')] [2023-03-08 05:44:15,994][321237] Updated weights for policy 0, policy_version 181360 (0.0004) [2023-03-08 05:44:19,317][321237] Updated weights for policy 0, policy_version 181440 (0.0004) [2023-03-08 05:44:19,594][320945] Fps is (10 sec: 11878.5, 60 sec: 11400.5, 300 sec: 11052.3). Total num frames: 92897280. Throughput: 0: 11467.6. Samples: 92871428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:44:19,595][320945] Avg episode reward: [(0, '4862.758')] [2023-03-08 05:44:22,760][321237] Updated weights for policy 0, policy_version 181520 (0.0004) [2023-03-08 05:44:24,594][320945] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11080.0). Total num frames: 92958720. Throughput: 0: 11598.5. Samples: 92944140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:44:24,595][320945] Avg episode reward: [(0, '4864.357')] [2023-03-08 05:44:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000181560_92958720.pth... [2023-03-08 05:44:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000180864_92602368.pth [2023-03-08 05:44:26,440][321237] Updated weights for policy 0, policy_version 181600 (0.0004) [2023-03-08 05:44:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11066.1). Total num frames: 93011968. Throughput: 0: 11630.2. Samples: 93011976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:44:29,594][320945] Avg episode reward: [(0, '4863.834')] [2023-03-08 05:44:30,060][321237] Updated weights for policy 0, policy_version 181680 (0.0005) [2023-03-08 05:44:33,775][321237] Updated weights for policy 0, policy_version 181760 (0.0005) [2023-03-08 05:44:34,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11093.9). Total num frames: 93069312. Throughput: 0: 11613.6. Samples: 93044736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:44:34,595][320945] Avg episode reward: [(0, '4862.886')] [2023-03-08 05:44:37,448][321237] Updated weights for policy 0, policy_version 181840 (0.0005) [2023-03-08 05:44:39,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11468.8, 300 sec: 11080.0). Total num frames: 93122560. Throughput: 0: 11636.0. Samples: 93110840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:44:39,595][320945] Avg episode reward: [(0, '4864.531')] [2023-03-08 05:44:39,625][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000181888_93126656.pth... [2023-03-08 05:44:39,627][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000181208_92778496.pth [2023-03-08 05:44:41,102][321237] Updated weights for policy 0, policy_version 181920 (0.0005) [2023-03-08 05:44:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11093.9). Total num frames: 93179904. Throughput: 0: 11690.1. Samples: 93178380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:44:44,595][320945] Avg episode reward: [(0, '4866.305')] [2023-03-08 05:44:44,773][321237] Updated weights for policy 0, policy_version 182000 (0.0004) [2023-03-08 05:44:48,459][321237] Updated weights for policy 0, policy_version 182080 (0.0005) [2023-03-08 05:44:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11093.9). Total num frames: 93233152. Throughput: 0: 11627.7. Samples: 93212196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:44:49,594][320945] Avg episode reward: [(0, '4863.474')] [2023-03-08 05:44:52,199][321237] Updated weights for policy 0, policy_version 182160 (0.0005) [2023-03-08 05:44:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11107.8). Total num frames: 93290496. Throughput: 0: 11468.8. Samples: 93278216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:44:54,595][320945] Avg episode reward: [(0, '4861.966')] [2023-03-08 05:44:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000182208_93290496.pth... [2023-03-08 05:44:54,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000181560_92958720.pth [2023-03-08 05:44:55,914][321237] Updated weights for policy 0, policy_version 182240 (0.0004) [2023-03-08 05:44:59,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11107.8). Total num frames: 93343744. Throughput: 0: 11287.9. Samples: 93343756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:44:59,594][320945] Avg episode reward: [(0, '4864.030')] [2023-03-08 05:44:59,695][321237] Updated weights for policy 0, policy_version 182320 (0.0004) [2023-03-08 05:45:03,339][321237] Updated weights for policy 0, policy_version 182400 (0.0004) [2023-03-08 05:45:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11107.8). Total num frames: 93401088. Throughput: 0: 11225.5. Samples: 93376576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:45:04,595][320945] Avg episode reward: [(0, '4862.498')] [2023-03-08 05:45:06,967][321237] Updated weights for policy 0, policy_version 182480 (0.0004) [2023-03-08 05:45:09,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11121.7). Total num frames: 93458432. Throughput: 0: 11111.7. Samples: 93444168. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:45:09,595][320945] Avg episode reward: [(0, '4865.090')] [2023-03-08 05:45:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000182536_93458432.pth... [2023-03-08 05:45:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000181888_93126656.pth [2023-03-08 05:45:10,686][321237] Updated weights for policy 0, policy_version 182560 (0.0005) [2023-03-08 05:45:14,414][321237] Updated weights for policy 0, policy_version 182640 (0.0005) [2023-03-08 05:45:14,594][320945] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11121.7). Total num frames: 93511680. Throughput: 0: 11075.7. Samples: 93510384. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:45:14,595][320945] Avg episode reward: [(0, '4864.448')] [2023-03-08 05:45:18,048][321237] Updated weights for policy 0, policy_version 182720 (0.0005) [2023-03-08 05:45:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11135.6). Total num frames: 93569024. Throughput: 0: 11085.9. Samples: 93543604. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:45:19,595][320945] Avg episode reward: [(0, '4866.135')] [2023-03-08 05:45:21,549][321237] Updated weights for policy 0, policy_version 182800 (0.0004) [2023-03-08 05:45:24,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 11149.4). Total num frames: 93626368. Throughput: 0: 11180.4. Samples: 93613960. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:45:24,595][320945] Avg episode reward: [(0, '4866.321')] [2023-03-08 05:45:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000182864_93626368.pth... [2023-03-08 05:45:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000182208_93290496.pth [2023-03-08 05:45:25,048][321237] Updated weights for policy 0, policy_version 182880 (0.0004) [2023-03-08 05:45:28,574][321237] Updated weights for policy 0, policy_version 182960 (0.0004) [2023-03-08 05:45:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11149.4). Total num frames: 93683712. Throughput: 0: 11231.0. Samples: 93683776. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:45:29,595][320945] Avg episode reward: [(0, '4861.509')] [2023-03-08 05:45:32,119][321237] Updated weights for policy 0, policy_version 183040 (0.0005) [2023-03-08 05:45:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11163.3). Total num frames: 93741056. Throughput: 0: 11243.5. Samples: 93718156. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:45:34,595][320945] Avg episode reward: [(0, '4863.276')] [2023-03-08 05:45:35,658][321237] Updated weights for policy 0, policy_version 183120 (0.0004) [2023-03-08 05:45:39,359][321237] Updated weights for policy 0, policy_version 183200 (0.0003) [2023-03-08 05:45:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11163.3). Total num frames: 93798400. Throughput: 0: 11295.9. Samples: 93786532. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:45:39,595][320945] Avg episode reward: [(0, '4864.768')] [2023-03-08 05:45:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000183200_93798400.pth... [2023-03-08 05:45:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000182536_93458432.pth [2023-03-08 05:45:43,191][321237] Updated weights for policy 0, policy_version 183280 (0.0005) [2023-03-08 05:45:44,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 11163.3). Total num frames: 93851648. Throughput: 0: 11283.8. Samples: 93851528. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:45:44,595][320945] Avg episode reward: [(0, '4863.464')] [2023-03-08 05:45:47,014][321237] Updated weights for policy 0, policy_version 183360 (0.0005) [2023-03-08 05:45:49,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11149.5). Total num frames: 93904896. Throughput: 0: 11267.8. Samples: 93883628. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:45:49,595][320945] Avg episode reward: [(0, '4863.054')] [2023-03-08 05:45:50,826][321237] Updated weights for policy 0, policy_version 183440 (0.0005) [2023-03-08 05:45:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11149.4). Total num frames: 93958144. Throughput: 0: 11186.1. Samples: 93947540. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:45:54,595][320945] Avg episode reward: [(0, '4863.196')] [2023-03-08 05:45:54,650][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000183520_93962240.pth... [2023-03-08 05:45:54,650][321237] Updated weights for policy 0, policy_version 183520 (0.0005) [2023-03-08 05:45:54,652][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000182864_93626368.pth [2023-03-08 05:45:58,543][321237] Updated weights for policy 0, policy_version 183600 (0.0005) [2023-03-08 05:45:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11135.6). Total num frames: 94011392. Throughput: 0: 11133.3. Samples: 94011384. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:45:59,595][320945] Avg episode reward: [(0, '4861.852')] [2023-03-08 05:46:02,408][321237] Updated weights for policy 0, policy_version 183680 (0.0005) [2023-03-08 05:46:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11135.6). Total num frames: 94064640. Throughput: 0: 11097.3. Samples: 94042980. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:46:04,594][320945] Avg episode reward: [(0, '4865.635')] [2023-03-08 05:46:06,250][321237] Updated weights for policy 0, policy_version 183760 (0.0005) [2023-03-08 05:46:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 11135.6). Total num frames: 94117888. Throughput: 0: 10934.3. Samples: 94106004. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:46:09,595][320945] Avg episode reward: [(0, '4863.110')] [2023-03-08 05:46:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000183824_94117888.pth... [2023-03-08 05:46:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000183200_93798400.pth [2023-03-08 05:46:10,147][321237] Updated weights for policy 0, policy_version 183840 (0.0005) [2023-03-08 05:46:13,978][321237] Updated weights for policy 0, policy_version 183920 (0.0005) [2023-03-08 05:46:14,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10990.9, 300 sec: 11121.7). Total num frames: 94171136. Throughput: 0: 10817.5. Samples: 94170564. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:46:14,595][320945] Avg episode reward: [(0, '4865.890')] [2023-03-08 05:46:17,868][321237] Updated weights for policy 0, policy_version 184000 (0.0005) [2023-03-08 05:46:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11121.7). Total num frames: 94224384. Throughput: 0: 10743.1. Samples: 94201596. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:46:19,595][320945] Avg episode reward: [(0, '4864.902')] [2023-03-08 05:46:21,795][321237] Updated weights for policy 0, policy_version 184080 (0.0005) [2023-03-08 05:46:24,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 11107.8). Total num frames: 94277632. Throughput: 0: 10640.4. Samples: 94265352. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:46:24,595][320945] Avg episode reward: [(0, '4864.587')] [2023-03-08 05:46:24,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000184136_94277632.pth... [2023-03-08 05:46:24,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000183520_93962240.pth [2023-03-08 05:46:25,639][321237] Updated weights for policy 0, policy_version 184160 (0.0005) [2023-03-08 05:46:29,535][321237] Updated weights for policy 0, policy_version 184240 (0.0005) [2023-03-08 05:46:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11107.8). Total num frames: 94330880. Throughput: 0: 10580.8. Samples: 94327664. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:46:29,595][320945] Avg episode reward: [(0, '4865.597')] [2023-03-08 05:46:33,331][321237] Updated weights for policy 0, policy_version 184320 (0.0005) [2023-03-08 05:46:34,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10717.9, 300 sec: 11107.8). Total num frames: 94384128. Throughput: 0: 10592.9. Samples: 94360308. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:46:34,595][320945] Avg episode reward: [(0, '4864.097')] [2023-03-08 05:46:37,000][321237] Updated weights for policy 0, policy_version 184400 (0.0004) [2023-03-08 05:46:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 11107.8). Total num frames: 94437376. Throughput: 0: 10643.3. Samples: 94426488. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:46:39,595][320945] Avg episode reward: [(0, '4863.988')] [2023-03-08 05:46:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000184448_94437376.pth... [2023-03-08 05:46:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000183824_94117888.pth [2023-03-08 05:46:40,875][321237] Updated weights for policy 0, policy_version 184480 (0.0005) [2023-03-08 05:46:44,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 11093.9). Total num frames: 94490624. Throughput: 0: 10641.3. Samples: 94490244. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:46:44,595][320945] Avg episode reward: [(0, '4865.896')] [2023-03-08 05:46:44,711][321237] Updated weights for policy 0, policy_version 184560 (0.0005) [2023-03-08 05:46:48,451][321237] Updated weights for policy 0, policy_version 184640 (0.0005) [2023-03-08 05:46:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 11107.8). Total num frames: 94547968. Throughput: 0: 10672.7. Samples: 94523252. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:46:49,594][320945] Avg episode reward: [(0, '4861.572')] [2023-03-08 05:46:52,284][321237] Updated weights for policy 0, policy_version 184720 (0.0005) [2023-03-08 05:46:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 11093.9). Total num frames: 94597120. Throughput: 0: 10689.0. Samples: 94587008. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:46:54,595][320945] Avg episode reward: [(0, '4865.454')] [2023-03-08 05:46:54,616][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000184768_94601216.pth... [2023-03-08 05:46:54,618][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000184136_94277632.pth [2023-03-08 05:46:56,195][321237] Updated weights for policy 0, policy_version 184800 (0.0005) [2023-03-08 05:46:59,594][320945] Fps is (10 sec: 10240.0, 60 sec: 10649.6, 300 sec: 11093.9). Total num frames: 94650368. Throughput: 0: 10663.7. Samples: 94650432. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:46:59,594][320945] Avg episode reward: [(0, '4863.389')] [2023-03-08 05:47:00,015][321237] Updated weights for policy 0, policy_version 184880 (0.0005) [2023-03-08 05:47:03,803][321237] Updated weights for policy 0, policy_version 184960 (0.0005) [2023-03-08 05:47:04,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 11080.0). Total num frames: 94707712. Throughput: 0: 10702.3. Samples: 94683200. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:47:04,595][320945] Avg episode reward: [(0, '4863.226')] [2023-03-08 05:47:07,555][321237] Updated weights for policy 0, policy_version 185040 (0.0005) [2023-03-08 05:47:09,594][320945] Fps is (10 sec: 11468.7, 60 sec: 10786.1, 300 sec: 11080.0). Total num frames: 94765056. Throughput: 0: 10744.1. Samples: 94748836. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:47:09,595][320945] Avg episode reward: [(0, '4863.133')] [2023-03-08 05:47:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000185088_94765056.pth... [2023-03-08 05:47:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000184448_94437376.pth [2023-03-08 05:47:11,111][321237] Updated weights for policy 0, policy_version 185120 (0.0004) [2023-03-08 05:47:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 11066.1). Total num frames: 94818304. Throughput: 0: 10822.5. Samples: 94814676. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 05:47:14,595][320945] Avg episode reward: [(0, '4864.810')] [2023-03-08 05:47:14,922][321237] Updated weights for policy 0, policy_version 185200 (0.0005) [2023-03-08 05:47:18,799][321237] Updated weights for policy 0, policy_version 185280 (0.0005) [2023-03-08 05:47:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11052.3). Total num frames: 94871552. Throughput: 0: 10825.3. Samples: 94847448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:47:19,595][320945] Avg episode reward: [(0, '4866.093')] [2023-03-08 05:47:22,618][321237] Updated weights for policy 0, policy_version 185360 (0.0005) [2023-03-08 05:47:24,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11052.3). Total num frames: 94924800. Throughput: 0: 10787.2. Samples: 94911912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:47:24,595][320945] Avg episode reward: [(0, '4865.601')] [2023-03-08 05:47:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000185400_94924800.pth... [2023-03-08 05:47:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000184768_94601216.pth [2023-03-08 05:47:26,399][321237] Updated weights for policy 0, policy_version 185440 (0.0005) [2023-03-08 05:47:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11038.4). Total num frames: 94978048. Throughput: 0: 10809.4. Samples: 94976668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:47:29,605][320945] Avg episode reward: [(0, '4864.421')] [2023-03-08 05:47:30,200][321237] Updated weights for policy 0, policy_version 185520 (0.0005) [2023-03-08 05:47:34,074][321237] Updated weights for policy 0, policy_version 185600 (0.0005) [2023-03-08 05:47:34,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11038.4). Total num frames: 95031296. Throughput: 0: 10772.8. Samples: 95008028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:47:34,605][320945] Avg episode reward: [(0, '4864.792')] [2023-03-08 05:47:37,900][321237] Updated weights for policy 0, policy_version 185680 (0.0005) [2023-03-08 05:47:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11038.4). Total num frames: 95084544. Throughput: 0: 10784.7. Samples: 95072320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:47:39,605][320945] Avg episode reward: [(0, '4864.626')] [2023-03-08 05:47:39,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000185712_95084544.pth... [2023-03-08 05:47:39,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000185088_94765056.pth [2023-03-08 05:47:41,779][321237] Updated weights for policy 0, policy_version 185760 (0.0004) [2023-03-08 05:47:44,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11038.4). Total num frames: 95137792. Throughput: 0: 10770.3. Samples: 95135096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:47:44,605][320945] Avg episode reward: [(0, '4864.513')] [2023-03-08 05:47:45,676][321237] Updated weights for policy 0, policy_version 185840 (0.0005) [2023-03-08 05:47:49,515][321237] Updated weights for policy 0, policy_version 185920 (0.0005) [2023-03-08 05:47:49,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 11024.5). Total num frames: 95191040. Throughput: 0: 10749.1. Samples: 95166912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:47:49,595][320945] Avg episode reward: [(0, '4863.919')] [2023-03-08 05:47:53,307][321237] Updated weights for policy 0, policy_version 186000 (0.0005) [2023-03-08 05:47:54,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10786.1, 300 sec: 11024.5). Total num frames: 95244288. Throughput: 0: 10737.0. Samples: 95232000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:47:54,605][320945] Avg episode reward: [(0, '4864.887')] [2023-03-08 05:47:54,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000186024_95244288.pth... [2023-03-08 05:47:54,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000185400_94924800.pth [2023-03-08 05:47:57,195][321237] Updated weights for policy 0, policy_version 186080 (0.0005) [2023-03-08 05:47:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11024.5). Total num frames: 95297536. Throughput: 0: 10682.7. Samples: 95295396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:47:59,605][320945] Avg episode reward: [(0, '4864.048')] [2023-03-08 05:48:01,023][321237] Updated weights for policy 0, policy_version 186160 (0.0005) [2023-03-08 05:48:04,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10717.9, 300 sec: 11010.6). Total num frames: 95350784. Throughput: 0: 10647.8. Samples: 95326600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:48:04,595][320945] Avg episode reward: [(0, '4862.839')] [2023-03-08 05:48:04,880][321237] Updated weights for policy 0, policy_version 186240 (0.0005) [2023-03-08 05:48:08,660][321237] Updated weights for policy 0, policy_version 186320 (0.0005) [2023-03-08 05:48:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 11010.6). Total num frames: 95404032. Throughput: 0: 10664.4. Samples: 95391808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:48:09,605][320945] Avg episode reward: [(0, '4817.663')] [2023-03-08 05:48:09,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000186336_95404032.pth... [2023-03-08 05:48:09,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000185712_95084544.pth [2023-03-08 05:48:12,445][321237] Updated weights for policy 0, policy_version 186400 (0.0005) [2023-03-08 05:48:14,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10649.6, 300 sec: 10996.7). Total num frames: 95457280. Throughput: 0: 10673.9. Samples: 95456992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:48:14,605][320945] Avg episode reward: [(0, '4863.654')] [2023-03-08 05:48:16,280][321237] Updated weights for policy 0, policy_version 186480 (0.0005) [2023-03-08 05:48:19,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10996.7). Total num frames: 95510528. Throughput: 0: 10678.8. Samples: 95488572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:48:19,605][320945] Avg episode reward: [(0, '4821.176')] [2023-03-08 05:48:20,112][321237] Updated weights for policy 0, policy_version 186560 (0.0005) [2023-03-08 05:48:24,041][321237] Updated weights for policy 0, policy_version 186640 (0.0005) [2023-03-08 05:48:24,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10982.8). Total num frames: 95563776. Throughput: 0: 10649.8. Samples: 95551560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:48:24,605][320945] Avg episode reward: [(0, '4863.086')] [2023-03-08 05:48:24,608][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000186648_95563776.pth... [2023-03-08 05:48:24,611][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000186024_95244288.pth [2023-03-08 05:48:27,772][321237] Updated weights for policy 0, policy_version 186720 (0.0003) [2023-03-08 05:48:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10968.9). Total num frames: 95617024. Throughput: 0: 10709.5. Samples: 95617024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:48:29,605][320945] Avg episode reward: [(0, '4864.217')] [2023-03-08 05:48:31,611][321237] Updated weights for policy 0, policy_version 186800 (0.0005) [2023-03-08 05:48:34,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10969.0). Total num frames: 95670272. Throughput: 0: 10707.0. Samples: 95648728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:48:34,595][320945] Avg episode reward: [(0, '4866.257')] [2023-03-08 05:48:35,475][321237] Updated weights for policy 0, policy_version 186880 (0.0005) [2023-03-08 05:48:39,300][321237] Updated weights for policy 0, policy_version 186960 (0.0005) [2023-03-08 05:48:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10955.1). Total num frames: 95723520. Throughput: 0: 10681.4. Samples: 95712660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:48:39,595][320945] Avg episode reward: [(0, '4864.440')] [2023-03-08 05:48:39,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000186960_95723520.pth... [2023-03-08 05:48:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000186336_95404032.pth [2023-03-08 05:48:43,158][321237] Updated weights for policy 0, policy_version 187040 (0.0005) [2023-03-08 05:48:44,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10955.1). Total num frames: 95776768. Throughput: 0: 10697.2. Samples: 95776768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:48:44,594][320945] Avg episode reward: [(0, '4866.063')] [2023-03-08 05:48:46,892][321237] Updated weights for policy 0, policy_version 187120 (0.0004) [2023-03-08 05:48:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 10968.9). Total num frames: 95834112. Throughput: 0: 10733.5. Samples: 95809608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:48:49,595][320945] Avg episode reward: [(0, '4821.552')] [2023-03-08 05:48:50,424][321237] Updated weights for policy 0, policy_version 187200 (0.0004) [2023-03-08 05:48:53,932][321237] Updated weights for policy 0, policy_version 187280 (0.0004) [2023-03-08 05:48:54,594][320945] Fps is (10 sec: 11468.7, 60 sec: 10786.1, 300 sec: 10968.9). Total num frames: 95891456. Throughput: 0: 10831.8. Samples: 95879240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:48:54,595][320945] Avg episode reward: [(0, '4814.031')] [2023-03-08 05:48:54,632][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000187296_95895552.pth... [2023-03-08 05:48:54,634][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000186648_95563776.pth [2023-03-08 05:48:57,507][321237] Updated weights for policy 0, policy_version 187360 (0.0004) [2023-03-08 05:48:59,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10854.4, 300 sec: 10955.1). Total num frames: 95948800. Throughput: 0: 10918.1. Samples: 95948308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:48:59,595][320945] Avg episode reward: [(0, '4771.194')] [2023-03-08 05:49:01,106][321237] Updated weights for policy 0, policy_version 187440 (0.0004) [2023-03-08 05:49:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10922.7, 300 sec: 10941.2). Total num frames: 96006144. Throughput: 0: 10967.5. Samples: 95982112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:49:04,595][320945] Avg episode reward: [(0, '4864.823')] [2023-03-08 05:49:04,882][321237] Updated weights for policy 0, policy_version 187520 (0.0004) [2023-03-08 05:49:08,719][321237] Updated weights for policy 0, policy_version 187600 (0.0005) [2023-03-08 05:49:09,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 10927.3). Total num frames: 96059392. Throughput: 0: 11012.1. Samples: 96047104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:49:09,595][320945] Avg episode reward: [(0, '4848.708')] [2023-03-08 05:49:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000187616_96059392.pth... [2023-03-08 05:49:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000186960_95723520.pth [2023-03-08 05:49:12,473][321237] Updated weights for policy 0, policy_version 187680 (0.0005) [2023-03-08 05:49:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10899.5). Total num frames: 96112640. Throughput: 0: 10991.3. Samples: 96111632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:49:14,595][320945] Avg episode reward: [(0, '4864.995')] [2023-03-08 05:49:16,153][321237] Updated weights for policy 0, policy_version 187760 (0.0004) [2023-03-08 05:49:19,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 10885.6). Total num frames: 96169984. Throughput: 0: 11040.4. Samples: 96145544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:49:19,595][320945] Avg episode reward: [(0, '4863.873')] [2023-03-08 05:49:19,723][321237] Updated weights for policy 0, policy_version 187840 (0.0004) [2023-03-08 05:49:23,654][321237] Updated weights for policy 0, policy_version 187920 (0.0005) [2023-03-08 05:49:24,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 10885.6). Total num frames: 96223232. Throughput: 0: 11073.2. Samples: 96210956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:49:24,595][320945] Avg episode reward: [(0, '4821.192')] [2023-03-08 05:49:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000187936_96223232.pth... [2023-03-08 05:49:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000187296_95895552.pth [2023-03-08 05:49:27,610][321237] Updated weights for policy 0, policy_version 188000 (0.0005) [2023-03-08 05:49:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10871.8). Total num frames: 96276480. Throughput: 0: 11033.1. Samples: 96273260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:49:29,595][320945] Avg episode reward: [(0, '4799.578')] [2023-03-08 05:49:31,478][321237] Updated weights for policy 0, policy_version 188080 (0.0005) [2023-03-08 05:49:34,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10871.8). Total num frames: 96329728. Throughput: 0: 11013.7. Samples: 96305224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:49:34,595][320945] Avg episode reward: [(0, '4819.713')] [2023-03-08 05:49:35,256][321237] Updated weights for policy 0, policy_version 188160 (0.0005) [2023-03-08 05:49:38,734][321237] Updated weights for policy 0, policy_version 188240 (0.0004) [2023-03-08 05:49:39,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 10871.8). Total num frames: 96387072. Throughput: 0: 10979.2. Samples: 96373304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:49:39,595][320945] Avg episode reward: [(0, '4865.132')] [2023-03-08 05:49:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000188256_96387072.pth... [2023-03-08 05:49:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000187616_96059392.pth [2023-03-08 05:49:42,220][321237] Updated weights for policy 0, policy_version 188320 (0.0003) [2023-03-08 05:49:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 10885.6). Total num frames: 96444416. Throughput: 0: 10978.8. Samples: 96442356. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:49:44,595][320945] Avg episode reward: [(0, '4863.042')] [2023-03-08 05:49:45,954][321237] Updated weights for policy 0, policy_version 188400 (0.0005) [2023-03-08 05:49:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11059.2, 300 sec: 10871.8). Total num frames: 96497664. Throughput: 0: 10953.7. Samples: 96475028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:49:49,595][320945] Avg episode reward: [(0, '4863.767')] [2023-03-08 05:49:49,776][321237] Updated weights for policy 0, policy_version 188480 (0.0005) [2023-03-08 05:49:53,650][321237] Updated weights for policy 0, policy_version 188560 (0.0005) [2023-03-08 05:49:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10871.8). Total num frames: 96550912. Throughput: 0: 10924.1. Samples: 96538688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:49:54,595][320945] Avg episode reward: [(0, '4864.581')] [2023-03-08 05:49:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000188576_96550912.pth... [2023-03-08 05:49:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000187936_96223232.pth [2023-03-08 05:49:57,470][321237] Updated weights for policy 0, policy_version 188640 (0.0005) [2023-03-08 05:49:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10857.9). Total num frames: 96604160. Throughput: 0: 10931.0. Samples: 96603528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:49:59,594][320945] Avg episode reward: [(0, '4819.180')] [2023-03-08 05:50:01,251][321237] Updated weights for policy 0, policy_version 188720 (0.0005) [2023-03-08 05:50:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10844.0). Total num frames: 96657408. Throughput: 0: 10917.8. Samples: 96636844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:50:04,595][320945] Avg episode reward: [(0, '4864.019')] [2023-03-08 05:50:05,010][321237] Updated weights for policy 0, policy_version 188800 (0.0005) [2023-03-08 05:50:08,834][321237] Updated weights for policy 0, policy_version 188880 (0.0005) [2023-03-08 05:50:09,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10857.9). Total num frames: 96714752. Throughput: 0: 10876.2. Samples: 96700384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:50:09,595][320945] Avg episode reward: [(0, '4864.469')] [2023-03-08 05:50:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000188896_96714752.pth... [2023-03-08 05:50:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000188256_96387072.pth [2023-03-08 05:50:12,691][321237] Updated weights for policy 0, policy_version 188960 (0.0005) [2023-03-08 05:50:14,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10844.0). Total num frames: 96768000. Throughput: 0: 10911.0. Samples: 96764256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:50:14,595][320945] Avg episode reward: [(0, '4866.392')] [2023-03-08 05:50:16,480][321237] Updated weights for policy 0, policy_version 189040 (0.0005) [2023-03-08 05:50:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10830.1). Total num frames: 96821248. Throughput: 0: 10926.5. Samples: 96796916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:50:19,595][320945] Avg episode reward: [(0, '4864.526')] [2023-03-08 05:50:20,357][321237] Updated weights for policy 0, policy_version 189120 (0.0005) [2023-03-08 05:50:24,087][321237] Updated weights for policy 0, policy_version 189200 (0.0005) [2023-03-08 05:50:24,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 10816.2). Total num frames: 96874496. Throughput: 0: 10855.4. Samples: 96861796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:50:24,595][320945] Avg episode reward: [(0, '4862.176')] [2023-03-08 05:50:24,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000189208_96874496.pth... [2023-03-08 05:50:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000188576_96550912.pth [2023-03-08 05:50:27,939][321237] Updated weights for policy 0, policy_version 189280 (0.0005) [2023-03-08 05:50:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10802.3). Total num frames: 96927744. Throughput: 0: 10730.1. Samples: 96925212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:50:29,595][320945] Avg episode reward: [(0, '4864.262')] [2023-03-08 05:50:31,779][321237] Updated weights for policy 0, policy_version 189360 (0.0005) [2023-03-08 05:50:34,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10788.4). Total num frames: 96980992. Throughput: 0: 10725.6. Samples: 96957680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:50:34,595][320945] Avg episode reward: [(0, '4862.299')] [2023-03-08 05:50:35,557][321237] Updated weights for policy 0, policy_version 189440 (0.0005) [2023-03-08 05:50:39,031][321237] Updated weights for policy 0, policy_version 189520 (0.0004) [2023-03-08 05:50:39,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10854.4, 300 sec: 10802.3). Total num frames: 97038336. Throughput: 0: 10814.4. Samples: 97025336. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:50:39,595][320945] Avg episode reward: [(0, '4862.173')] [2023-03-08 05:50:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000189528_97038336.pth... [2023-03-08 05:50:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000188896_96714752.pth [2023-03-08 05:50:42,472][321237] Updated weights for policy 0, policy_version 189600 (0.0004) [2023-03-08 05:50:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10854.4, 300 sec: 10816.2). Total num frames: 97095680. Throughput: 0: 10930.7. Samples: 97095408. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:50:44,595][320945] Avg episode reward: [(0, '4863.748')] [2023-03-08 05:50:46,219][321237] Updated weights for policy 0, policy_version 189680 (0.0005) [2023-03-08 05:50:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 10854.4, 300 sec: 10816.2). Total num frames: 97148928. Throughput: 0: 10913.9. Samples: 97127968. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:50:49,595][320945] Avg episode reward: [(0, '4866.096')] [2023-03-08 05:50:50,079][321237] Updated weights for policy 0, policy_version 189760 (0.0005) [2023-03-08 05:50:53,929][321237] Updated weights for policy 0, policy_version 189840 (0.0005) [2023-03-08 05:50:54,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 10816.2). Total num frames: 97202176. Throughput: 0: 10891.6. Samples: 97190508. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:50:54,595][320945] Avg episode reward: [(0, '4863.946')] [2023-03-08 05:50:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000189848_97202176.pth... [2023-03-08 05:50:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000189208_96874496.pth [2023-03-08 05:50:57,779][321237] Updated weights for policy 0, policy_version 189920 (0.0005) [2023-03-08 05:50:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10816.2). Total num frames: 97255424. Throughput: 0: 10909.9. Samples: 97255204. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:50:59,595][320945] Avg episode reward: [(0, '4866.092')] [2023-03-08 05:51:01,600][321237] Updated weights for policy 0, policy_version 190000 (0.0004) [2023-03-08 05:51:04,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10854.4, 300 sec: 10816.2). Total num frames: 97308672. Throughput: 0: 10901.8. Samples: 97287496. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:51:04,595][320945] Avg episode reward: [(0, '4862.936')] [2023-03-08 05:51:05,471][321237] Updated weights for policy 0, policy_version 190080 (0.0005) [2023-03-08 05:51:09,391][321237] Updated weights for policy 0, policy_version 190160 (0.0005) [2023-03-08 05:51:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10816.2). Total num frames: 97361920. Throughput: 0: 10842.4. Samples: 97349704. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:51:09,595][320945] Avg episode reward: [(0, '4817.839')] [2023-03-08 05:51:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000190160_97361920.pth... [2023-03-08 05:51:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000189528_97038336.pth [2023-03-08 05:51:13,242][321237] Updated weights for policy 0, policy_version 190240 (0.0005) [2023-03-08 05:51:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10816.2). Total num frames: 97415168. Throughput: 0: 10862.0. Samples: 97414004. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:51:14,595][320945] Avg episode reward: [(0, '4845.090')] [2023-03-08 05:51:16,993][321237] Updated weights for policy 0, policy_version 190320 (0.0005) [2023-03-08 05:51:19,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10854.4, 300 sec: 10830.1). Total num frames: 97472512. Throughput: 0: 10881.5. Samples: 97447348. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:51:19,595][320945] Avg episode reward: [(0, '4863.993')] [2023-03-08 05:51:20,541][321237] Updated weights for policy 0, policy_version 190400 (0.0004) [2023-03-08 05:51:24,025][321237] Updated weights for policy 0, policy_version 190480 (0.0004) [2023-03-08 05:51:24,594][320945] Fps is (10 sec: 11468.7, 60 sec: 10922.7, 300 sec: 10844.0). Total num frames: 97529856. Throughput: 0: 10920.7. Samples: 97516768. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:51:24,595][320945] Avg episode reward: [(0, '4864.542')] [2023-03-08 05:51:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000190488_97529856.pth... [2023-03-08 05:51:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000189848_97202176.pth [2023-03-08 05:51:27,546][321237] Updated weights for policy 0, policy_version 190560 (0.0004) [2023-03-08 05:51:29,594][320945] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 10857.9). Total num frames: 97587200. Throughput: 0: 10928.9. Samples: 97587208. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:51:29,595][320945] Avg episode reward: [(0, '4862.864')] [2023-03-08 05:51:31,246][321237] Updated weights for policy 0, policy_version 190640 (0.0004) [2023-03-08 05:51:34,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 10871.8). Total num frames: 97644544. Throughput: 0: 10926.5. Samples: 97619660. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:51:34,595][320945] Avg episode reward: [(0, '4864.095')] [2023-03-08 05:51:34,842][321237] Updated weights for policy 0, policy_version 190720 (0.0005) [2023-03-08 05:51:38,364][321237] Updated weights for policy 0, policy_version 190800 (0.0004) [2023-03-08 05:51:39,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11059.2, 300 sec: 10885.6). Total num frames: 97701888. Throughput: 0: 11071.3. Samples: 97688716. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 05:51:39,595][320945] Avg episode reward: [(0, '4864.234')] [2023-03-08 05:51:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000190824_97701888.pth... [2023-03-08 05:51:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000190160_97361920.pth [2023-03-08 05:51:41,919][321237] Updated weights for policy 0, policy_version 190880 (0.0004) [2023-03-08 05:51:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 10885.6). Total num frames: 97759232. Throughput: 0: 11181.6. Samples: 97758376. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:51:44,595][320945] Avg episode reward: [(0, '4864.304')] [2023-03-08 05:51:45,499][321237] Updated weights for policy 0, policy_version 190960 (0.0004) [2023-03-08 05:51:49,316][321237] Updated weights for policy 0, policy_version 191040 (0.0005) [2023-03-08 05:51:49,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11059.2, 300 sec: 10899.5). Total num frames: 97812480. Throughput: 0: 11183.7. Samples: 97790760. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:51:49,595][320945] Avg episode reward: [(0, '4863.831')] [2023-03-08 05:51:53,074][321237] Updated weights for policy 0, policy_version 191120 (0.0005) [2023-03-08 05:51:54,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 10913.4). Total num frames: 97869824. Throughput: 0: 11245.8. Samples: 97855764. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:51:54,595][320945] Avg episode reward: [(0, '4861.500')] [2023-03-08 05:51:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000191152_97869824.pth... [2023-03-08 05:51:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000190488_97529856.pth [2023-03-08 05:51:56,684][321237] Updated weights for policy 0, policy_version 191200 (0.0004) [2023-03-08 05:51:59,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11195.7, 300 sec: 10913.4). Total num frames: 97927168. Throughput: 0: 11319.4. Samples: 97923376. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:51:59,595][320945] Avg episode reward: [(0, '4865.067')] [2023-03-08 05:52:00,302][321237] Updated weights for policy 0, policy_version 191280 (0.0005) [2023-03-08 05:52:03,879][321237] Updated weights for policy 0, policy_version 191360 (0.0004) [2023-03-08 05:52:04,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 10913.4). Total num frames: 97984512. Throughput: 0: 11343.7. Samples: 97957816. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:52:04,595][320945] Avg episode reward: [(0, '4865.509')] [2023-03-08 05:52:07,635][321237] Updated weights for policy 0, policy_version 191440 (0.0005) [2023-03-08 05:52:09,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 10913.4). Total num frames: 98037760. Throughput: 0: 11280.1. Samples: 98024372. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:52:09,595][320945] Avg episode reward: [(0, '4864.239')] [2023-03-08 05:52:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000191480_98037760.pth... [2023-03-08 05:52:09,599][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000190824_97701888.pth [2023-03-08 05:52:11,514][321237] Updated weights for policy 0, policy_version 191520 (0.0005) [2023-03-08 05:52:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 10913.4). Total num frames: 98091008. Throughput: 0: 11157.2. Samples: 98089280. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:52:14,595][320945] Avg episode reward: [(0, '4864.173')] [2023-03-08 05:52:15,120][321237] Updated weights for policy 0, policy_version 191600 (0.0004) [2023-03-08 05:52:18,711][321237] Updated weights for policy 0, policy_version 191680 (0.0004) [2023-03-08 05:52:19,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 10927.3). Total num frames: 98148352. Throughput: 0: 11201.0. Samples: 98123704. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:52:19,595][320945] Avg episode reward: [(0, '4861.762')] [2023-03-08 05:52:22,268][321237] Updated weights for policy 0, policy_version 191760 (0.0004) [2023-03-08 05:52:24,594][320945] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 10941.2). Total num frames: 98205696. Throughput: 0: 11189.9. Samples: 98192264. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:52:24,595][320945] Avg episode reward: [(0, '4865.844')] [2023-03-08 05:52:24,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000191808_98205696.pth... [2023-03-08 05:52:24,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000191152_97869824.pth [2023-03-08 05:52:25,906][321237] Updated weights for policy 0, policy_version 191840 (0.0005) [2023-03-08 05:52:29,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 10941.2). Total num frames: 98258944. Throughput: 0: 11124.0. Samples: 98258956. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:52:29,595][320945] Avg episode reward: [(0, '4862.369')] [2023-03-08 05:52:29,651][321237] Updated weights for policy 0, policy_version 191920 (0.0005) [2023-03-08 05:52:33,291][321237] Updated weights for policy 0, policy_version 192000 (0.0005) [2023-03-08 05:52:34,594][320945] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 10955.1). Total num frames: 98316288. Throughput: 0: 11133.9. Samples: 98291784. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:52:34,595][320945] Avg episode reward: [(0, '4863.230')] [2023-03-08 05:52:36,827][321237] Updated weights for policy 0, policy_version 192080 (0.0004) [2023-03-08 05:52:39,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 10968.9). Total num frames: 98373632. Throughput: 0: 11231.4. Samples: 98361176. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:52:39,595][320945] Avg episode reward: [(0, '4863.999')] [2023-03-08 05:52:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000192136_98373632.pth... [2023-03-08 05:52:39,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000191480_98037760.pth [2023-03-08 05:52:40,484][321237] Updated weights for policy 0, policy_version 192160 (0.0005) [2023-03-08 05:52:44,114][321237] Updated weights for policy 0, policy_version 192240 (0.0004) [2023-03-08 05:52:44,594][320945] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 10982.8). Total num frames: 98430976. Throughput: 0: 11222.2. Samples: 98428376. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 05:52:44,595][320945] Avg episode reward: [(0, '4865.672')] [2023-03-08 05:52:47,957][321237] Updated weights for policy 0, policy_version 192320 (0.0005) [2023-03-08 05:52:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 10982.8). Total num frames: 98484224. Throughput: 0: 11165.3. Samples: 98460256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:52:49,595][320945] Avg episode reward: [(0, '4864.682')] [2023-03-08 05:52:51,720][321237] Updated weights for policy 0, policy_version 192400 (0.0005) [2023-03-08 05:52:54,594][320945] Fps is (10 sec: 10649.5, 60 sec: 11127.5, 300 sec: 10982.8). Total num frames: 98537472. Throughput: 0: 11130.6. Samples: 98525248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:52:54,595][320945] Avg episode reward: [(0, '4864.183')] [2023-03-08 05:52:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000192456_98537472.pth... [2023-03-08 05:52:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000191808_98205696.pth [2023-03-08 05:52:55,482][321237] Updated weights for policy 0, policy_version 192480 (0.0005) [2023-03-08 05:52:59,355][321237] Updated weights for policy 0, policy_version 192560 (0.0005) [2023-03-08 05:52:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 10982.8). Total num frames: 98590720. Throughput: 0: 11135.6. Samples: 98590380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:52:59,595][320945] Avg episode reward: [(0, '4865.272')] [2023-03-08 05:53:03,236][321237] Updated weights for policy 0, policy_version 192640 (0.0005) [2023-03-08 05:53:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10982.8). Total num frames: 98643968. Throughput: 0: 11060.6. Samples: 98621432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:53:04,595][320945] Avg episode reward: [(0, '4865.657')] [2023-03-08 05:53:06,984][321237] Updated weights for policy 0, policy_version 192720 (0.0004) [2023-03-08 05:53:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10982.8). Total num frames: 98697216. Throughput: 0: 10977.1. Samples: 98686232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:53:09,594][320945] Avg episode reward: [(0, '4865.937')] [2023-03-08 05:53:09,597][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000192768_98697216.pth... [2023-03-08 05:53:09,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000192136_98373632.pth [2023-03-08 05:53:10,809][321237] Updated weights for policy 0, policy_version 192800 (0.0005) [2023-03-08 05:53:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10982.8). Total num frames: 98750464. Throughput: 0: 10924.0. Samples: 98750536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:53:14,595][320945] Avg episode reward: [(0, '4864.909')] [2023-03-08 05:53:14,639][321237] Updated weights for policy 0, policy_version 192880 (0.0005) [2023-03-08 05:53:18,495][321237] Updated weights for policy 0, policy_version 192960 (0.0004) [2023-03-08 05:53:19,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10922.7, 300 sec: 10982.8). Total num frames: 98803712. Throughput: 0: 10920.9. Samples: 98783224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:53:19,605][320945] Avg episode reward: [(0, '4863.487')] [2023-03-08 05:53:22,313][321237] Updated weights for policy 0, policy_version 193040 (0.0005) [2023-03-08 05:53:24,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10982.8). Total num frames: 98856960. Throughput: 0: 10787.8. Samples: 98846628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:53:24,605][320945] Avg episode reward: [(0, '4865.117')] [2023-03-08 05:53:24,609][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000193088_98861056.pth... [2023-03-08 05:53:24,610][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000192456_98537472.pth [2023-03-08 05:53:26,152][321237] Updated weights for policy 0, policy_version 193120 (0.0005) [2023-03-08 05:53:29,594][320945] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 10996.7). Total num frames: 98914304. Throughput: 0: 10725.6. Samples: 98911028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:53:29,595][320945] Avg episode reward: [(0, '4864.349')] [2023-03-08 05:53:29,943][321237] Updated weights for policy 0, policy_version 193200 (0.0005) [2023-03-08 05:53:33,850][321237] Updated weights for policy 0, policy_version 193280 (0.0005) [2023-03-08 05:53:34,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10982.8). Total num frames: 98963456. Throughput: 0: 10727.3. Samples: 98942984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:53:34,595][320945] Avg episode reward: [(0, '4864.847')] [2023-03-08 05:53:37,588][321237] Updated weights for policy 0, policy_version 193360 (0.0004) [2023-03-08 05:53:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10996.7). Total num frames: 99020800. Throughput: 0: 10739.7. Samples: 99008536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:53:39,595][320945] Avg episode reward: [(0, '4865.200')] [2023-03-08 05:53:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000193400_99020800.pth... [2023-03-08 05:53:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000192768_98697216.pth [2023-03-08 05:53:41,091][321237] Updated weights for policy 0, policy_version 193440 (0.0004) [2023-03-08 05:53:44,594][320945] Fps is (10 sec: 11468.9, 60 sec: 10786.1, 300 sec: 10996.7). Total num frames: 99078144. Throughput: 0: 10840.6. Samples: 99078208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:53:44,594][320945] Avg episode reward: [(0, '4865.255')] [2023-03-08 05:53:44,622][321237] Updated weights for policy 0, policy_version 193520 (0.0004) [2023-03-08 05:53:48,442][321237] Updated weights for policy 0, policy_version 193600 (0.0005) [2023-03-08 05:53:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 10982.8). Total num frames: 99131392. Throughput: 0: 10877.6. Samples: 99110924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:53:49,595][320945] Avg episode reward: [(0, '4863.092')] [2023-03-08 05:53:52,384][321237] Updated weights for policy 0, policy_version 193680 (0.0005) [2023-03-08 05:53:54,594][320945] Fps is (10 sec: 10649.5, 60 sec: 10786.1, 300 sec: 10968.9). Total num frames: 99184640. Throughput: 0: 10818.9. Samples: 99173084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:53:54,595][320945] Avg episode reward: [(0, '4863.585')] [2023-03-08 05:53:54,599][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000193720_99184640.pth... [2023-03-08 05:53:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000193088_98861056.pth [2023-03-08 05:53:56,200][321237] Updated weights for policy 0, policy_version 193760 (0.0005) [2023-03-08 05:53:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10955.1). Total num frames: 99237888. Throughput: 0: 10817.8. Samples: 99237336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:53:59,595][320945] Avg episode reward: [(0, '4864.290')] [2023-03-08 05:54:00,123][321237] Updated weights for policy 0, policy_version 193840 (0.0005) [2023-03-08 05:54:03,968][321237] Updated weights for policy 0, policy_version 193920 (0.0005) [2023-03-08 05:54:04,594][320945] Fps is (10 sec: 10649.7, 60 sec: 10786.1, 300 sec: 10955.1). Total num frames: 99291136. Throughput: 0: 10800.4. Samples: 99269244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:54:04,595][320945] Avg episode reward: [(0, '4866.475')] [2023-03-08 05:54:07,796][321237] Updated weights for policy 0, policy_version 194000 (0.0005) [2023-03-08 05:54:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10955.1). Total num frames: 99344384. Throughput: 0: 10806.3. Samples: 99332912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:54:09,595][320945] Avg episode reward: [(0, '4863.557')] [2023-03-08 05:54:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000194032_99344384.pth... [2023-03-08 05:54:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000193400_99020800.pth [2023-03-08 05:54:11,616][321237] Updated weights for policy 0, policy_version 194080 (0.0005) [2023-03-08 05:54:14,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10941.2). Total num frames: 99397632. Throughput: 0: 10810.3. Samples: 99397492. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:54:14,595][320945] Avg episode reward: [(0, '4863.991')] [2023-03-08 05:54:15,499][321237] Updated weights for policy 0, policy_version 194160 (0.0005) [2023-03-08 05:54:19,260][321237] Updated weights for policy 0, policy_version 194240 (0.0005) [2023-03-08 05:54:19,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10941.2). Total num frames: 99450880. Throughput: 0: 10818.6. Samples: 99429820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:54:19,595][320945] Avg episode reward: [(0, '4862.215')] [2023-03-08 05:54:23,121][321237] Updated weights for policy 0, policy_version 194320 (0.0005) [2023-03-08 05:54:24,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10941.2). Total num frames: 99504128. Throughput: 0: 10775.6. Samples: 99493436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:54:24,595][320945] Avg episode reward: [(0, '4865.179')] [2023-03-08 05:54:24,660][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000194352_99508224.pth... [2023-03-08 05:54:24,661][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000193720_99184640.pth [2023-03-08 05:54:26,930][321237] Updated weights for policy 0, policy_version 194400 (0.0005) [2023-03-08 05:54:29,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10941.2). Total num frames: 99557376. Throughput: 0: 10648.4. Samples: 99557388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:54:29,595][320945] Avg episode reward: [(0, '4864.545')] [2023-03-08 05:54:30,850][321237] Updated weights for policy 0, policy_version 194480 (0.0005) [2023-03-08 05:54:34,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10927.3). Total num frames: 99610624. Throughput: 0: 10628.3. Samples: 99589196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:54:34,595][320945] Avg episode reward: [(0, '4867.133')] [2023-03-08 05:54:34,702][321237] Updated weights for policy 0, policy_version 194560 (0.0005) [2023-03-08 05:54:38,576][321237] Updated weights for policy 0, policy_version 194640 (0.0005) [2023-03-08 05:54:39,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10913.4). Total num frames: 99663872. Throughput: 0: 10650.6. Samples: 99652360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:54:39,595][320945] Avg episode reward: [(0, '4864.330')] [2023-03-08 05:54:39,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000194656_99663872.pth... [2023-03-08 05:54:39,600][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000194032_99344384.pth [2023-03-08 05:54:42,183][321237] Updated weights for policy 0, policy_version 194720 (0.0004) [2023-03-08 05:54:44,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 10927.3). Total num frames: 99721216. Throughput: 0: 10733.2. Samples: 99720332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:54:44,595][320945] Avg episode reward: [(0, '4862.369')] [2023-03-08 05:54:45,912][321237] Updated weights for policy 0, policy_version 194800 (0.0005) [2023-03-08 05:54:49,594][320945] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 10927.3). Total num frames: 99774464. Throughput: 0: 10752.1. Samples: 99753088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:54:49,595][320945] Avg episode reward: [(0, '4864.542')] [2023-03-08 05:54:49,627][321237] Updated weights for policy 0, policy_version 194880 (0.0005) [2023-03-08 05:54:53,656][321237] Updated weights for policy 0, policy_version 194960 (0.0005) [2023-03-08 05:54:54,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10927.3). Total num frames: 99827712. Throughput: 0: 10722.9. Samples: 99815444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:54:54,595][320945] Avg episode reward: [(0, '4864.793')] [2023-03-08 05:54:54,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000194976_99827712.pth... [2023-03-08 05:54:54,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000194352_99508224.pth [2023-03-08 05:54:57,490][321237] Updated weights for policy 0, policy_version 195040 (0.0005) [2023-03-08 05:54:59,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10927.3). Total num frames: 99880960. Throughput: 0: 10712.2. Samples: 99879540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:54:59,595][320945] Avg episode reward: [(0, '4863.469')] [2023-03-08 05:55:01,352][321237] Updated weights for policy 0, policy_version 195120 (0.0005) [2023-03-08 05:55:04,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10913.4). Total num frames: 99934208. Throughput: 0: 10686.2. Samples: 99910700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:55:04,595][320945] Avg episode reward: [(0, '4865.651')] [2023-03-08 05:55:05,260][321237] Updated weights for policy 0, policy_version 195200 (0.0005) [2023-03-08 05:55:09,090][321237] Updated weights for policy 0, policy_version 195280 (0.0005) [2023-03-08 05:55:09,594][320945] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10913.4). Total num frames: 99987456. Throughput: 0: 10705.2. Samples: 99975168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 05:55:09,595][320945] Avg episode reward: [(0, '4864.820')] [2023-03-08 05:55:09,598][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000195288_99987456.pth... [2023-03-08 05:55:09,601][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000194656_99663872.pth [2023-03-08 05:55:11,037][321188] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 [2023-03-08 05:55:11,409][321188] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 [2023-03-08 05:55:11,410][321235] Stopping RolloutWorker_w4... [2023-03-08 05:55:11,410][321238] Stopping RolloutWorker_w0... [2023-03-08 05:55:11,410][321233] Stopping RolloutWorker_w1... [2023-03-08 05:55:11,410][321239] Stopping RolloutWorker_w2... [2023-03-08 05:55:11,410][321271] Stopping RolloutWorker_w7... [2023-03-08 05:55:11,410][321234] Stopping RolloutWorker_w6... [2023-03-08 05:55:11,410][321232] Stopping RolloutWorker_w3... [2023-03-08 05:55:11,410][321236] Stopping RolloutWorker_w5... [2023-03-08 05:55:11,411][321235] Loop rollout_proc4_evt_loop terminating... [2023-03-08 05:55:11,411][321238] Loop rollout_proc0_evt_loop terminating... [2023-03-08 05:55:11,411][321233] Loop rollout_proc1_evt_loop terminating... [2023-03-08 05:55:11,411][321239] Loop rollout_proc2_evt_loop terminating... [2023-03-08 05:55:11,411][321271] Loop rollout_proc7_evt_loop terminating... [2023-03-08 05:55:11,411][321234] Loop rollout_proc6_evt_loop terminating... [2023-03-08 05:55:11,411][321232] Loop rollout_proc3_evt_loop terminating... [2023-03-08 05:55:11,411][321236] Loop rollout_proc5_evt_loop terminating... [2023-03-08 05:55:11,411][321188] Stopping Batcher_0... [2023-03-08 05:55:11,411][320945] Component RolloutWorker_w4 stopped! [2023-03-08 05:55:11,411][321188] Loop batcher_evt_loop terminating... [2023-03-08 05:55:11,411][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000195328_100007936.pth... [2023-03-08 05:55:11,411][320945] Component RolloutWorker_w1 stopped! [2023-03-08 05:55:11,412][320945] Component RolloutWorker_w0 stopped! [2023-03-08 05:55:11,412][320945] Component RolloutWorker_w2 stopped! [2023-03-08 05:55:11,412][320945] Component RolloutWorker_w7 stopped! [2023-03-08 05:55:11,412][320945] Component RolloutWorker_w6 stopped! [2023-03-08 05:55:11,413][321188] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000194976_99827712.pth [2023-03-08 05:55:11,413][320945] Component RolloutWorker_w3 stopped! [2023-03-08 05:55:11,413][321188] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/drawer-close-v2/checkpoint_p0/checkpoint_000195328_100007936.pth... [2023-03-08 05:55:11,413][320945] Component RolloutWorker_w5 stopped! [2023-03-08 05:55:11,413][320945] Component Batcher_0 stopped! [2023-03-08 05:55:11,415][321188] Stopping LearnerWorker_p0... [2023-03-08 05:55:11,415][321188] Loop learner_proc0_evt_loop terminating... [2023-03-08 05:55:11,415][320945] Component LearnerWorker_p0 stopped! [2023-03-08 05:55:11,464][321237] Weights refcount: 2 0 [2023-03-08 05:55:11,465][321237] Stopping InferenceWorker_p0-w0... [2023-03-08 05:55:11,465][321237] Loop inference_proc0-0_evt_loop terminating... [2023-03-08 05:55:11,465][320945] Component InferenceWorker_p0-w0 stopped! [2023-03-08 05:55:11,466][320945] Waiting for process learner_proc0 to stop... [2023-03-08 05:55:11,843][320945] Waiting for process inference_proc0-0 to join... [2023-03-08 05:55:11,854][320945] Waiting for process rollout_proc0 to join... [2023-03-08 05:55:11,854][320945] Waiting for process rollout_proc1 to join... [2023-03-08 05:55:11,854][320945] Waiting for process rollout_proc2 to join... [2023-03-08 05:55:11,855][320945] Waiting for process rollout_proc3 to join... [2023-03-08 05:55:11,855][320945] Waiting for process rollout_proc4 to join... [2023-03-08 05:55:11,855][320945] Waiting for process rollout_proc5 to join... [2023-03-08 05:55:11,855][320945] Waiting for process rollout_proc6 to join... [2023-03-08 05:55:11,856][320945] Waiting for process rollout_proc7 to join... [2023-03-08 05:55:11,856][320945] Batcher 0 profile tree view: batching: 17.1780, releasing_batches: 14.3352 [2023-03-08 05:55:11,856][320945] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0051 wait_policy_total: 3087.7223 update_model: 97.0222 weight_update: 0.0005 one_step: 0.0005 handle_policy_step: 4921.4563 deserialize: 206.6919, stack: 49.6436, obs_to_device_normalize: 873.0745, forward: 2433.8341, send_messages: 367.5829 prepare_outputs: 561.5492 to_cpu: 87.5284 [2023-03-08 05:55:11,856][320945] Learner 0 profile tree view: misc: 0.1019, prepare_batch: 91.5701 train: 1182.7439 epoch_init: 0.3897, minibatch_init: 12.0881, losses_postprocess: 12.1370, kl_divergence: 4.3217, after_optimizer: 5.0797 calculate_losses: 486.2981 losses_init: 0.4221, forward_head: 241.4255, bptt_initial: 1.2767, bptt: 1.2694, tail: 114.0248, advantages_returns: 8.8348, losses: 104.7839 update: 646.2334 clip: 56.5765 [2023-03-08 05:55:11,856][320945] RolloutWorker_w0 profile tree view: wait_for_trajectories: 2.7656, enqueue_policy_requests: 124.3136, env_step: 5577.4634, overhead: 309.3808, complete_rollouts: 3.0576 save_policy_outputs: 320.8104 split_output_tensors: 157.8845 [2023-03-08 05:55:11,857][320945] RolloutWorker_w7 profile tree view: wait_for_trajectories: 2.6167, enqueue_policy_requests: 124.6888, env_step: 5638.6061, overhead: 309.9037, complete_rollouts: 3.2510 save_policy_outputs: 317.7907 split_output_tensors: 157.1279 [2023-03-08 05:55:11,857][320945] Loop Runner_EvtLoop terminating... [2023-03-08 05:55:11,857][320945] Runner profile tree view: main_loop: 8714.9436 [2023-03-08 05:55:11,857][320945] Collected {0: 100007936}, FPS: 11475.5