[2023-03-03 13:35:22,745][21315] Saving configuration to /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/config.json... [2023-03-03 13:35:22,768][21315] Rollout worker 0 uses device cpu [2023-03-03 13:35:22,769][21315] Rollout worker 1 uses device cpu [2023-03-03 13:35:22,769][21315] Rollout worker 2 uses device cpu [2023-03-03 13:35:22,769][21315] Rollout worker 3 uses device cpu [2023-03-03 13:35:22,769][21315] Rollout worker 4 uses device cpu [2023-03-03 13:35:22,769][21315] Rollout worker 5 uses device cpu [2023-03-03 13:35:22,769][21315] Rollout worker 6 uses device cpu [2023-03-03 13:35:22,769][21315] Rollout worker 7 uses device cpu [2023-03-03 13:35:22,971][21315] InferenceWorker_p0-w0: min num requests: 2 [2023-03-03 13:35:23,009][21315] Starting all processes... [2023-03-03 13:35:23,009][21315] Starting process learner_proc0 [2023-03-03 13:35:23,070][21315] Starting all processes... [2023-03-03 13:35:23,100][21315] Starting process inference_proc0-0 [2023-03-03 13:35:23,100][21315] Starting process rollout_proc0 [2023-03-03 13:35:23,100][21315] Starting process rollout_proc1 [2023-03-03 13:35:23,101][21315] Starting process rollout_proc2 [2023-03-03 13:35:23,103][21315] Starting process rollout_proc3 [2023-03-03 13:35:23,110][21315] Starting process rollout_proc4 [2023-03-03 13:35:23,112][21315] Starting process rollout_proc5 [2023-03-03 13:35:23,112][21315] Starting process rollout_proc6 [2023-03-03 13:35:23,112][21315] Starting process rollout_proc7 [2023-03-03 13:35:27,359][21356] WARNING! It is generally recommended to enable Fixed KL loss (https://arxiv.org/pdf/1707.06347.pdf) for continuous action tasks to avoid potential numerical issues. I.e. set --kl_loss_coeff=0.1 [2023-03-03 13:35:27,360][21356] Starting seed is not provided [2023-03-03 13:35:27,360][21356] Initializing actor-critic model on device cpu [2023-03-03 13:35:27,360][21356] RunningMeanStd input shape: (39,) [2023-03-03 13:35:27,361][21356] RunningMeanStd input shape: (1,) [2023-03-03 13:35:27,498][21359] On MacOS, not setting affinity [2023-03-03 13:35:27,518][21356] Created Actor Critic model with architecture: [2023-03-03 13:35:27,518][21356] 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=ELU) (2): RecursiveScriptModule(original_name=Linear) (3): RecursiveScriptModule(original_name=ELU) ) ) ) ) (core): ModelCoreRNN( (core): GRU(512, 512) ) (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=512, out_features=1, bias=True) (action_parameterization): ActionParameterizationDefault( (distribution_linear): Linear(in_features=512, out_features=8, bias=True) ) ) [2023-03-03 13:35:27,523][21356] Using optimizer [2023-03-03 13:35:27,524][21356] No checkpoints found [2023-03-03 13:35:27,524][21356] Did not load from checkpoint, starting from scratch! [2023-03-03 13:35:27,525][21356] Initialized policy 0 weights for model version 0 [2023-03-03 13:35:27,527][21356] LearnerWorker_p0 finished initialization! [2023-03-03 13:35:27,529][21364] On MacOS, not setting affinity [2023-03-03 13:35:27,604][21363] On MacOS, not setting affinity [2023-03-03 13:35:27,802][21361] On MacOS, not setting affinity [2023-03-03 13:35:28,177][21357] RunningMeanStd input shape: (39,) [2023-03-03 13:35:28,180][21357] RunningMeanStd input shape: (1,) [2023-03-03 13:35:28,285][21358] On MacOS, not setting affinity [2023-03-03 13:35:28,372][21315] Inference worker 0-0 is ready! [2023-03-03 13:35:28,376][21315] All inference workers are ready! Signal rollout workers to start! [2023-03-03 13:35:28,424][21362] On MacOS, not setting affinity [2023-03-03 13:35:28,453][21360] On MacOS, not setting affinity [2023-03-03 13:35:28,632][21365] On MacOS, not setting affinity [2023-03-03 13:35:30,165][21363] Decorrelating experience for 0 frames... [2023-03-03 13:35:30,219][21358] Decorrelating experience for 0 frames... [2023-03-03 13:35:30,223][21364] Decorrelating experience for 0 frames... [2023-03-03 13:35:30,245][21360] Decorrelating experience for 0 frames... [2023-03-03 13:35:30,249][21359] Decorrelating experience for 0 frames... [2023-03-03 13:35:30,260][21361] Decorrelating experience for 0 frames... [2023-03-03 13:35:30,388][21365] Decorrelating experience for 0 frames... [2023-03-03 13:35:30,396][21362] Decorrelating experience for 0 frames... [2023-03-03 13:35:30,915][21315] 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) [2023-03-03 13:35:31,596][21363] Decorrelating experience for 32 frames... [2023-03-03 13:35:31,609][21359] Decorrelating experience for 32 frames... [2023-03-03 13:35:31,624][21358] Decorrelating experience for 32 frames... [2023-03-03 13:35:31,657][21364] Decorrelating experience for 32 frames... [2023-03-03 13:35:31,672][21361] Decorrelating experience for 32 frames... [2023-03-03 13:35:31,742][21360] Decorrelating experience for 32 frames... [2023-03-03 13:35:31,799][21362] Decorrelating experience for 32 frames... [2023-03-03 13:35:31,808][21365] Decorrelating experience for 32 frames... [2023-03-03 13:35:32,568][21356] Signal inference workers to stop experience collection... [2023-03-03 13:35:32,572][21356] Signal inference workers to resume experience collection... [2023-03-03 13:35:32,576][21357] InferenceWorker_p0-w0: stopping experience collection [2023-03-03 13:35:32,580][21357] InferenceWorker_p0-w0: resuming experience collection [2023-03-03 13:35:35,705][21357] Updated weights for policy 0, policy_version 10 (0.0011) [2023-03-03 13:35:35,914][21315] Fps is (10 sec: 2047.8, 60 sec: 2047.8, 300 sec: 2047.8). Total num frames: 10240. Throughput: 0: 1581.4. Samples: 7908. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:35:35,916][21315] Avg episode reward: [(0, '4.567')] [2023-03-03 13:35:39,709][21357] Updated weights for policy 0, policy_version 20 (0.0010) [2023-03-03 13:35:40,910][21315] Fps is (10 sec: 2356.1, 60 sec: 2356.1, 300 sec: 2356.1). Total num frames: 23552. Throughput: 0: 2304.2. Samples: 23034. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:35:40,912][21315] Avg episode reward: [(0, '4.809')] [2023-03-03 13:35:42,946][21315] Heartbeat connected on Batcher_0 [2023-03-03 13:35:42,971][21315] Heartbeat connected on LearnerWorker_p0 [2023-03-03 13:35:42,977][21315] Heartbeat connected on InferenceWorker_p0-w0 [2023-03-03 13:35:42,979][21315] Heartbeat connected on RolloutWorker_w0 [2023-03-03 13:35:42,984][21315] Heartbeat connected on RolloutWorker_w1 [2023-03-03 13:35:42,987][21315] Heartbeat connected on RolloutWorker_w2 [2023-03-03 13:35:42,992][21315] Heartbeat connected on RolloutWorker_w3 [2023-03-03 13:35:42,996][21315] Heartbeat connected on RolloutWorker_w4 [2023-03-03 13:35:43,001][21315] Heartbeat connected on RolloutWorker_w5 [2023-03-03 13:35:43,005][21315] Heartbeat connected on RolloutWorker_w6 [2023-03-03 13:35:43,010][21315] Heartbeat connected on RolloutWorker_w7 [2023-03-03 13:35:43,368][21357] Updated weights for policy 0, policy_version 30 (0.0008) [2023-03-03 13:35:45,910][21315] Fps is (10 sec: 2766.0, 60 sec: 2526.5, 300 sec: 2526.5). Total num frames: 37888. Throughput: 0: 2098.8. Samples: 31474. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:35:45,910][21315] Avg episode reward: [(0, '4.925')] [2023-03-03 13:35:46,984][21357] Updated weights for policy 0, policy_version 40 (0.0008) [2023-03-03 13:35:50,557][21357] Updated weights for policy 0, policy_version 50 (0.0009) [2023-03-03 13:35:50,911][21315] Fps is (10 sec: 2764.6, 60 sec: 2560.4, 300 sec: 2560.4). Total num frames: 51200. Throughput: 0: 2420.9. Samples: 48410. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:35:50,911][21315] Avg episode reward: [(0, '4.991')] [2023-03-03 13:35:54,162][21357] Updated weights for policy 0, policy_version 60 (0.0009) [2023-03-03 13:35:55,913][21315] Fps is (10 sec: 2866.4, 60 sec: 2662.5, 300 sec: 2662.5). Total num frames: 66560. Throughput: 0: 2635.4. Samples: 65881. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:35:55,913][21315] Avg episode reward: [(0, '5.496')] [2023-03-03 13:35:57,847][21357] Updated weights for policy 0, policy_version 70 (0.0009) [2023-03-03 13:36:00,910][21315] Fps is (10 sec: 2765.1, 60 sec: 2628.6, 300 sec: 2628.6). Total num frames: 78848. Throughput: 0: 2456.6. Samples: 73689. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:36:00,912][21315] Avg episode reward: [(0, '7.134')] [2023-03-03 13:36:02,521][21357] Updated weights for policy 0, policy_version 80 (0.0011) [2023-03-03 13:36:05,912][21315] Fps is (10 sec: 2150.6, 60 sec: 2516.3, 300 sec: 2516.3). Total num frames: 88064. Throughput: 0: 2472.8. Samples: 86542. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:36:05,915][21315] Avg episode reward: [(0, '7.849')] [2023-03-03 13:36:07,430][21357] Updated weights for policy 0, policy_version 90 (0.0014) [2023-03-03 13:36:10,912][21315] Fps is (10 sec: 2149.8, 60 sec: 2508.9, 300 sec: 2508.9). Total num frames: 100352. Throughput: 0: 2508.0. Samples: 100317. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:36:10,914][21315] Avg episode reward: [(0, '8.340')] [2023-03-03 13:36:10,920][21356] Saving new best policy, reward=8.340! [2023-03-03 13:36:11,552][21357] Updated weights for policy 0, policy_version 100 (0.0009) [2023-03-03 13:36:15,888][21357] Updated weights for policy 0, policy_version 110 (0.0010) [2023-03-03 13:36:15,914][21315] Fps is (10 sec: 2457.1, 60 sec: 2503.1, 300 sec: 2503.1). Total num frames: 112640. Throughput: 0: 2378.8. Samples: 107045. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:36:15,916][21315] Avg episode reward: [(0, '9.162')] [2023-03-03 13:36:15,917][21356] Saving new best policy, reward=9.162! [2023-03-03 13:36:19,615][21357] Updated weights for policy 0, policy_version 120 (0.0010) [2023-03-03 13:36:20,912][21315] Fps is (10 sec: 2560.2, 60 sec: 2519.1, 300 sec: 2519.1). Total num frames: 125952. Throughput: 0: 2559.2. Samples: 123066. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:36:20,912][21315] Avg episode reward: [(0, '9.980')] [2023-03-03 13:36:21,016][21356] Saving new best policy, reward=9.980! [2023-03-03 13:36:23,191][21357] Updated weights for policy 0, policy_version 130 (0.0009) [2023-03-03 13:36:25,911][21315] Fps is (10 sec: 2765.6, 60 sec: 2550.8, 300 sec: 2550.8). Total num frames: 140288. Throughput: 0: 2598.4. Samples: 139963. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:36:25,912][21315] Avg episode reward: [(0, '10.329')] [2023-03-03 13:36:25,913][21356] Saving new best policy, reward=10.329! [2023-03-03 13:36:26,975][21357] Updated weights for policy 0, policy_version 140 (0.0010) [2023-03-03 13:36:30,901][21357] Updated weights for policy 0, policy_version 150 (0.0010) [2023-03-03 13:36:30,911][21315] Fps is (10 sec: 2764.9, 60 sec: 2560.1, 300 sec: 2560.1). Total num frames: 153600. Throughput: 0: 2580.2. Samples: 147589. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:36:30,913][21315] Avg episode reward: [(0, '12.091')] [2023-03-03 13:36:30,918][21356] Saving new best policy, reward=12.091! [2023-03-03 13:36:34,477][21357] Updated weights for policy 0, policy_version 160 (0.0009) [2023-03-03 13:36:35,910][21315] Fps is (10 sec: 2662.7, 60 sec: 2611.4, 300 sec: 2568.0). Total num frames: 166912. Throughput: 0: 2577.8. Samples: 164407. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:36:35,911][21315] Avg episode reward: [(0, '15.209')] [2023-03-03 13:36:35,952][21356] Saving new best policy, reward=15.209! [2023-03-03 13:36:38,322][21357] Updated weights for policy 0, policy_version 170 (0.0010) [2023-03-03 13:36:40,914][21315] Fps is (10 sec: 2661.7, 60 sec: 2611.0, 300 sec: 2574.6). Total num frames: 180224. Throughput: 0: 2549.2. Samples: 180599. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:36:40,916][21315] Avg episode reward: [(0, '15.772')] [2023-03-03 13:36:40,935][21356] Saving new best policy, reward=15.772! [2023-03-03 13:36:42,177][21357] Updated weights for policy 0, policy_version 180 (0.0010) [2023-03-03 13:36:45,915][21315] Fps is (10 sec: 2660.9, 60 sec: 2593.9, 300 sec: 2580.4). Total num frames: 193536. Throughput: 0: 2557.3. Samples: 188781. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:36:45,917][21315] Avg episode reward: [(0, '16.845')] [2023-03-03 13:36:45,918][21356] Saving new best policy, reward=16.845! [2023-03-03 13:36:46,272][21357] Updated weights for policy 0, policy_version 190 (0.0029) [2023-03-03 13:36:50,917][21315] Fps is (10 sec: 2150.0, 60 sec: 2508.6, 300 sec: 2521.5). Total num frames: 201728. Throughput: 0: 2552.2. Samples: 201402. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:36:50,921][21315] Avg episode reward: [(0, '17.196')] [2023-03-03 13:36:50,951][21356] Saving new best policy, reward=17.196! [2023-03-03 13:36:52,206][21357] Updated weights for policy 0, policy_version 200 (0.0016) [2023-03-03 13:36:55,914][21315] Fps is (10 sec: 1945.9, 60 sec: 2440.5, 300 sec: 2505.8). Total num frames: 212992. Throughput: 0: 2499.4. Samples: 212792. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:36:55,918][21315] Avg episode reward: [(0, '15.453')] [2023-03-03 13:36:56,652][21357] Updated weights for policy 0, policy_version 210 (0.0010) [2023-03-03 13:37:00,760][21357] Updated weights for policy 0, policy_version 220 (0.0010) [2023-03-03 13:37:00,914][21315] Fps is (10 sec: 2355.6, 60 sec: 2440.4, 300 sec: 2503.1). Total num frames: 225280. Throughput: 0: 2506.6. Samples: 219845. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:37:00,914][21315] Avg episode reward: [(0, '15.324')] [2023-03-03 13:37:04,889][21357] Updated weights for policy 0, policy_version 230 (0.0009) [2023-03-03 13:37:05,914][21315] Fps is (10 sec: 2458.1, 60 sec: 2491.7, 300 sec: 2500.8). Total num frames: 237568. Throughput: 0: 2489.8. Samples: 235107. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:37:05,919][21315] Avg episode reward: [(0, '15.590')] [2023-03-03 13:37:08,617][21357] Updated weights for policy 0, policy_version 240 (0.0009) [2023-03-03 13:37:10,917][21315] Fps is (10 sec: 2457.0, 60 sec: 2491.6, 300 sec: 2498.5). Total num frames: 249856. Throughput: 0: 2455.7. Samples: 250484. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:37:10,959][21315] Avg episode reward: [(0, '16.535')] [2023-03-03 13:37:13,474][21357] Updated weights for policy 0, policy_version 250 (0.0022) [2023-03-03 13:37:15,914][21315] Fps is (10 sec: 2355.0, 60 sec: 2474.7, 300 sec: 2486.9). Total num frames: 261120. Throughput: 0: 2426.9. Samples: 256803. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 13:37:15,918][21315] Avg episode reward: [(0, '16.458')] [2023-03-03 13:37:18,552][21357] Updated weights for policy 0, policy_version 260 (0.0012) [2023-03-03 13:37:20,917][21315] Fps is (10 sec: 2252.8, 60 sec: 2440.3, 300 sec: 2476.2). Total num frames: 272384. Throughput: 0: 2331.3. Samples: 269333. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:37:20,921][21315] Avg episode reward: [(0, '18.122')] [2023-03-03 13:37:20,969][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000000267_273408.pth... [2023-03-03 13:37:21,055][21356] Saving new best policy, reward=18.122! [2023-03-03 13:37:22,144][21357] Updated weights for policy 0, policy_version 270 (0.0007) [2023-03-03 13:37:25,681][21357] Updated weights for policy 0, policy_version 280 (0.0008) [2023-03-03 13:37:25,914][21315] Fps is (10 sec: 2559.7, 60 sec: 2440.4, 300 sec: 2493.2). Total num frames: 286720. Throughput: 0: 2354.5. Samples: 286554. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:37:25,916][21315] Avg episode reward: [(0, '17.743')] [2023-03-03 13:37:28,808][21357] Updated weights for policy 0, policy_version 290 (0.0007) [2023-03-03 13:37:30,913][21315] Fps is (10 sec: 3072.9, 60 sec: 2491.6, 300 sec: 2525.9). Total num frames: 303104. Throughput: 0: 2393.7. Samples: 296491. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 13:37:30,914][21315] Avg episode reward: [(0, '18.045')] [2023-03-03 13:37:31,864][21357] Updated weights for policy 0, policy_version 300 (0.0007) [2023-03-03 13:37:35,790][21357] Updated weights for policy 0, policy_version 310 (0.0009) [2023-03-03 13:37:35,910][21315] Fps is (10 sec: 3073.3, 60 sec: 2508.8, 300 sec: 2539.6). Total num frames: 317440. Throughput: 0: 2528.8. Samples: 315181. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:37:35,912][21315] Avg episode reward: [(0, '17.842')] [2023-03-03 13:37:39,314][21357] Updated weights for policy 0, policy_version 320 (0.0010) [2023-03-03 13:37:40,914][21315] Fps is (10 sec: 2867.1, 60 sec: 2525.9, 300 sec: 2552.1). Total num frames: 331776. Throughput: 0: 2653.2. Samples: 332187. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:37:40,917][21315] Avg episode reward: [(0, '19.137')] [2023-03-03 13:37:40,955][21356] Saving new best policy, reward=19.137! [2023-03-03 13:37:42,587][21357] Updated weights for policy 0, policy_version 330 (0.0008) [2023-03-03 13:37:45,760][21357] Updated weights for policy 0, policy_version 340 (0.0007) [2023-03-03 13:37:45,911][21315] Fps is (10 sec: 3071.6, 60 sec: 2577.3, 300 sec: 2579.0). Total num frames: 348160. Throughput: 0: 2695.0. Samples: 341110. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:37:45,912][21315] Avg episode reward: [(0, '20.517')] [2023-03-03 13:37:46,123][21356] Saving new best policy, reward=20.517! [2023-03-03 13:37:49,077][21357] Updated weights for policy 0, policy_version 350 (0.0007) [2023-03-03 13:37:50,912][21315] Fps is (10 sec: 3277.5, 60 sec: 2713.8, 300 sec: 2603.9). Total num frames: 364544. Throughput: 0: 2779.9. Samples: 360201. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:37:50,913][21315] Avg episode reward: [(0, '22.686')] [2023-03-03 13:37:50,916][21356] Saving new best policy, reward=22.686! [2023-03-03 13:37:52,206][21357] Updated weights for policy 0, policy_version 360 (0.0007) [2023-03-03 13:37:55,320][21357] Updated weights for policy 0, policy_version 370 (0.0006) [2023-03-03 13:37:55,914][21315] Fps is (10 sec: 3173.3, 60 sec: 2781.8, 300 sec: 2620.0). Total num frames: 379904. Throughput: 0: 2876.7. Samples: 379932. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:37:55,915][21315] Avg episode reward: [(0, '23.136')] [2023-03-03 13:37:56,005][21356] Saving new best policy, reward=23.136! [2023-03-03 13:37:58,633][21357] Updated weights for policy 0, policy_version 380 (0.0007) [2023-03-03 13:38:00,913][21315] Fps is (10 sec: 3071.5, 60 sec: 2833.1, 300 sec: 2635.1). Total num frames: 395264. Throughput: 0: 2940.7. Samples: 389137. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:38:00,915][21315] Avg episode reward: [(0, '22.477')] [2023-03-03 13:38:01,991][21357] Updated weights for policy 0, policy_version 390 (0.0007) [2023-03-03 13:38:05,107][21357] Updated weights for policy 0, policy_version 400 (0.0007) [2023-03-03 13:38:05,914][21315] Fps is (10 sec: 3174.5, 60 sec: 2901.2, 300 sec: 2655.8). Total num frames: 411648. Throughput: 0: 3087.1. Samples: 408245. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:38:05,915][21315] Avg episode reward: [(0, '20.927')] [2023-03-03 13:38:08,269][21357] Updated weights for policy 0, policy_version 410 (0.0006) [2023-03-03 13:38:10,913][21315] Fps is (10 sec: 3277.0, 60 sec: 2969.8, 300 sec: 2675.2). Total num frames: 428032. Throughput: 0: 3135.8. Samples: 427662. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:38:10,914][21315] Avg episode reward: [(0, '20.190')] [2023-03-03 13:38:11,309][21357] Updated weights for policy 0, policy_version 420 (0.0007) [2023-03-03 13:38:14,364][21357] Updated weights for policy 0, policy_version 430 (0.0006) [2023-03-03 13:38:15,916][21315] Fps is (10 sec: 3276.2, 60 sec: 3054.8, 300 sec: 2693.4). Total num frames: 444416. Throughput: 0: 3140.3. Samples: 437813. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:38:15,917][21315] Avg episode reward: [(0, '21.262')] [2023-03-03 13:38:17,938][21357] Updated weights for policy 0, policy_version 440 (0.0008) [2023-03-03 13:38:20,913][21315] Fps is (10 sec: 3174.4, 60 sec: 3123.4, 300 sec: 2704.6). Total num frames: 459776. Throughput: 0: 3123.2. Samples: 455735. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:38:20,914][21315] Avg episode reward: [(0, '21.436')] [2023-03-03 13:38:21,160][21357] Updated weights for policy 0, policy_version 450 (0.0007) [2023-03-03 13:38:24,255][21357] Updated weights for policy 0, policy_version 460 (0.0006) [2023-03-03 13:38:25,912][21315] Fps is (10 sec: 3175.7, 60 sec: 3157.5, 300 sec: 2720.9). Total num frames: 476160. Throughput: 0: 3192.6. Samples: 475846. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 13:38:25,912][21315] Avg episode reward: [(0, '22.889')] [2023-03-03 13:38:27,346][21357] Updated weights for policy 0, policy_version 470 (0.0006) [2023-03-03 13:38:30,359][21357] Updated weights for policy 0, policy_version 480 (0.0007) [2023-03-03 13:38:30,911][21315] Fps is (10 sec: 3277.5, 60 sec: 3157.5, 300 sec: 2736.4). Total num frames: 492544. Throughput: 0: 3216.7. Samples: 485859. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 13:38:30,917][21315] Avg episode reward: [(0, '23.045')] [2023-03-03 13:38:33,583][21357] Updated weights for policy 0, policy_version 490 (0.0008) [2023-03-03 13:38:35,914][21315] Fps is (10 sec: 3276.1, 60 sec: 3191.3, 300 sec: 2751.0). Total num frames: 508928. Throughput: 0: 3222.1. Samples: 505203. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:38:35,915][21315] Avg episode reward: [(0, '22.768')] [2023-03-03 13:38:36,646][21357] Updated weights for policy 0, policy_version 500 (0.0007) [2023-03-03 13:38:39,809][21357] Updated weights for policy 0, policy_version 510 (0.0006) [2023-03-03 13:38:40,913][21315] Fps is (10 sec: 3275.9, 60 sec: 3225.6, 300 sec: 2764.8). Total num frames: 525312. Throughput: 0: 3228.9. Samples: 525228. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0) [2023-03-03 13:38:40,914][21315] Avg episode reward: [(0, '26.383')] [2023-03-03 13:38:40,959][21356] Saving new best policy, reward=26.383! [2023-03-03 13:38:42,897][21357] Updated weights for policy 0, policy_version 520 (0.0006) [2023-03-03 13:38:45,911][21315] Fps is (10 sec: 3277.9, 60 sec: 3225.6, 300 sec: 2778.0). Total num frames: 541696. Throughput: 0: 3242.7. Samples: 535047. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:38:45,913][21315] Avg episode reward: [(0, '28.098')] [2023-03-03 13:38:45,941][21356] Saving new best policy, reward=28.098! [2023-03-03 13:38:45,941][21357] Updated weights for policy 0, policy_version 530 (0.0008) [2023-03-03 13:38:49,099][21357] Updated weights for policy 0, policy_version 540 (0.0007) [2023-03-03 13:38:50,913][21315] Fps is (10 sec: 3276.7, 60 sec: 3225.5, 300 sec: 2790.4). Total num frames: 558080. Throughput: 0: 3257.1. Samples: 554813. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:38:50,914][21315] Avg episode reward: [(0, '25.282')] [2023-03-03 13:38:52,154][21357] Updated weights for policy 0, policy_version 550 (0.0007) [2023-03-03 13:38:55,249][21357] Updated weights for policy 0, policy_version 560 (0.0006) [2023-03-03 13:38:55,910][21315] Fps is (10 sec: 3379.3, 60 sec: 3260.0, 300 sec: 2807.3). Total num frames: 575488. Throughput: 0: 3269.8. Samples: 574794. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:38:55,910][21315] Avg episode reward: [(0, '27.592')] [2023-03-03 13:38:58,531][21357] Updated weights for policy 0, policy_version 570 (0.0007) [2023-03-03 13:39:00,914][21315] Fps is (10 sec: 3276.7, 60 sec: 3259.7, 300 sec: 2813.6). Total num frames: 590848. Throughput: 0: 3252.4. Samples: 584166. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:39:00,915][21315] Avg episode reward: [(0, '45.599')] [2023-03-03 13:39:00,975][21356] Saving new best policy, reward=45.599! [2023-03-03 13:39:01,669][21357] Updated weights for policy 0, policy_version 580 (0.0007) [2023-03-03 13:39:04,772][21357] Updated weights for policy 0, policy_version 590 (0.0006) [2023-03-03 13:39:05,910][21315] Fps is (10 sec: 3174.5, 60 sec: 3260.0, 300 sec: 2824.4). Total num frames: 607232. Throughput: 0: 3289.4. Samples: 603749. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:39:05,910][21315] Avg episode reward: [(0, '62.645')] [2023-03-03 13:39:05,988][21356] Saving new best policy, reward=62.645! [2023-03-03 13:39:08,003][21357] Updated weights for policy 0, policy_version 600 (0.0007) [2023-03-03 13:39:10,914][21315] Fps is (10 sec: 3276.7, 60 sec: 3259.7, 300 sec: 2834.6). Total num frames: 623616. Throughput: 0: 3268.0. Samples: 622915. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:39:10,915][21315] Avg episode reward: [(0, '67.194')] [2023-03-03 13:39:10,921][21356] Saving new best policy, reward=67.194! [2023-03-03 13:39:11,352][21357] Updated weights for policy 0, policy_version 610 (0.0008) [2023-03-03 13:39:15,683][21357] Updated weights for policy 0, policy_version 620 (0.0010) [2023-03-03 13:39:15,914][21315] Fps is (10 sec: 2763.7, 60 sec: 3174.5, 300 sec: 2821.7). Total num frames: 634880. Throughput: 0: 3220.7. Samples: 630802. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:39:15,915][21315] Avg episode reward: [(0, '71.476')] [2023-03-03 13:39:16,133][21356] Saving new best policy, reward=71.476! [2023-03-03 13:39:20,156][21357] Updated weights for policy 0, policy_version 630 (0.0008) [2023-03-03 13:39:20,914][21315] Fps is (10 sec: 2252.8, 60 sec: 3106.1, 300 sec: 2809.3). Total num frames: 646144. Throughput: 0: 3085.9. Samples: 644072. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:39:20,916][21315] Avg episode reward: [(0, '55.157')] [2023-03-03 13:39:21,008][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000000632_647168.pth... [2023-03-03 13:39:23,744][21357] Updated weights for policy 0, policy_version 640 (0.0007) [2023-03-03 13:39:25,913][21315] Fps is (10 sec: 2662.5, 60 sec: 3089.0, 300 sec: 2814.9). Total num frames: 661504. Throughput: 0: 3018.2. Samples: 661047. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:39:25,915][21315] Avg episode reward: [(0, '88.286')] [2023-03-03 13:39:25,918][21356] Saving new best policy, reward=88.286! [2023-03-03 13:39:27,327][21357] Updated weights for policy 0, policy_version 650 (0.0007) [2023-03-03 13:39:30,914][21315] Fps is (10 sec: 2867.4, 60 sec: 3037.7, 300 sec: 2811.7). Total num frames: 674816. Throughput: 0: 2987.9. Samples: 669512. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 13:39:30,915][21315] Avg episode reward: [(0, '75.840')] [2023-03-03 13:39:31,155][21357] Updated weights for policy 0, policy_version 660 (0.0007) [2023-03-03 13:39:35,427][21357] Updated weights for policy 0, policy_version 670 (0.0009) [2023-03-03 13:39:35,914][21315] Fps is (10 sec: 2559.9, 60 sec: 2969.6, 300 sec: 2804.5). Total num frames: 687104. Throughput: 0: 2904.3. Samples: 685505. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:39:35,915][21315] Avg episode reward: [(0, '70.022')] [2023-03-03 13:39:38,930][21357] Updated weights for policy 0, policy_version 680 (0.0008) [2023-03-03 13:39:40,915][21315] Fps is (10 sec: 2662.2, 60 sec: 2935.4, 300 sec: 2805.8). Total num frames: 701440. Throughput: 0: 2804.8. Samples: 701021. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:39:40,916][21315] Avg episode reward: [(0, '74.332')] [2023-03-03 13:39:42,705][21357] Updated weights for policy 0, policy_version 690 (0.0008) [2023-03-03 13:39:45,915][21315] Fps is (10 sec: 2662.1, 60 sec: 2867.0, 300 sec: 2798.9). Total num frames: 713728. Throughput: 0: 2773.9. Samples: 708993. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:39:45,918][21315] Avg episode reward: [(0, '33.124')] [2023-03-03 13:39:46,714][21357] Updated weights for policy 0, policy_version 700 (0.0007) [2023-03-03 13:39:50,864][21357] Updated weights for policy 0, policy_version 710 (0.0009) [2023-03-03 13:39:50,915][21315] Fps is (10 sec: 2560.1, 60 sec: 2816.0, 300 sec: 2796.3). Total num frames: 727040. Throughput: 0: 2680.2. Samples: 724371. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:39:50,916][21315] Avg episode reward: [(0, '33.114')] [2023-03-03 13:39:54,579][21357] Updated weights for policy 0, policy_version 720 (0.0009) [2023-03-03 13:39:55,911][21315] Fps is (10 sec: 2663.3, 60 sec: 2747.7, 300 sec: 2793.8). Total num frames: 740352. Throughput: 0: 2610.7. Samples: 740391. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:39:55,912][21315] Avg episode reward: [(0, '33.907')] [2023-03-03 13:39:58,241][21357] Updated weights for policy 0, policy_version 730 (0.0008) [2023-03-03 13:40:00,914][21315] Fps is (10 sec: 2764.9, 60 sec: 2730.7, 300 sec: 2795.1). Total num frames: 754688. Throughput: 0: 2616.1. Samples: 748525. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:40:00,915][21315] Avg episode reward: [(0, '35.648')] [2023-03-03 13:40:01,658][21357] Updated weights for policy 0, policy_version 740 (0.0009) [2023-03-03 13:40:05,192][21357] Updated weights for policy 0, policy_version 750 (0.0007) [2023-03-03 13:40:05,913][21315] Fps is (10 sec: 2969.0, 60 sec: 2713.4, 300 sec: 2800.2). Total num frames: 770048. Throughput: 0: 2720.9. Samples: 766509. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:40:05,915][21315] Avg episode reward: [(0, '36.972')] [2023-03-03 13:40:08,465][21357] Updated weights for policy 0, policy_version 760 (0.0008) [2023-03-03 13:40:10,913][21315] Fps is (10 sec: 3072.1, 60 sec: 2696.6, 300 sec: 2805.0). Total num frames: 785408. Throughput: 0: 2753.4. Samples: 784949. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:40:10,914][21315] Avg episode reward: [(0, '45.084')] [2023-03-03 13:40:11,722][21357] Updated weights for policy 0, policy_version 770 (0.0007) [2023-03-03 13:40:14,996][21357] Updated weights for policy 0, policy_version 780 (0.0008) [2023-03-03 13:40:15,911][21315] Fps is (10 sec: 3072.7, 60 sec: 2764.9, 300 sec: 2809.7). Total num frames: 800768. Throughput: 0: 2771.4. Samples: 794218. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:40:15,911][21315] Avg episode reward: [(0, '37.637')] [2023-03-03 13:40:18,559][21357] Updated weights for policy 0, policy_version 790 (0.0007) [2023-03-03 13:40:20,912][21315] Fps is (10 sec: 3072.4, 60 sec: 2833.2, 300 sec: 2814.2). Total num frames: 816128. Throughput: 0: 2819.2. Samples: 812366. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:40:20,913][21315] Avg episode reward: [(0, '39.811')] [2023-03-03 13:40:21,832][21357] Updated weights for policy 0, policy_version 800 (0.0007) [2023-03-03 13:40:25,194][21357] Updated weights for policy 0, policy_version 810 (0.0007) [2023-03-03 13:40:25,914][21315] Fps is (10 sec: 3070.9, 60 sec: 2833.0, 300 sec: 2818.6). Total num frames: 831488. Throughput: 0: 2885.1. Samples: 830849. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:40:25,915][21315] Avg episode reward: [(0, '36.865')] [2023-03-03 13:40:28,504][21357] Updated weights for policy 0, policy_version 820 (0.0007) [2023-03-03 13:40:30,909][21315] Fps is (10 sec: 3073.0, 60 sec: 2867.4, 300 sec: 2836.0). Total num frames: 846848. Throughput: 0: 2913.8. Samples: 840098. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:40:30,909][21315] Avg episode reward: [(0, '37.203')] [2023-03-03 13:40:31,795][21357] Updated weights for policy 0, policy_version 830 (0.0007) [2023-03-03 13:40:35,067][21357] Updated weights for policy 0, policy_version 840 (0.0007) [2023-03-03 13:40:35,911][21315] Fps is (10 sec: 3073.0, 60 sec: 2918.5, 300 sec: 2842.9). Total num frames: 862208. Throughput: 0: 2990.5. Samples: 858935. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:40:35,912][21315] Avg episode reward: [(0, '39.053')] [2023-03-03 13:40:38,330][21357] Updated weights for policy 0, policy_version 850 (0.0007) [2023-03-03 13:40:40,914][21315] Fps is (10 sec: 3070.6, 60 sec: 2935.5, 300 sec: 2846.3). Total num frames: 877568. Throughput: 0: 3048.9. Samples: 877600. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:40:40,914][21315] Avg episode reward: [(0, '32.666')] [2023-03-03 13:40:41,577][21357] Updated weights for policy 0, policy_version 860 (0.0007) [2023-03-03 13:40:44,912][21357] Updated weights for policy 0, policy_version 870 (0.0008) [2023-03-03 13:40:45,909][21315] Fps is (10 sec: 3072.8, 60 sec: 2987.0, 300 sec: 2853.3). Total num frames: 892928. Throughput: 0: 3073.6. Samples: 886822. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:40:45,910][21315] Avg episode reward: [(0, '30.905')] [2023-03-03 13:40:48,431][21357] Updated weights for policy 0, policy_version 880 (0.0008) [2023-03-03 13:40:50,912][21315] Fps is (10 sec: 3072.4, 60 sec: 3020.9, 300 sec: 2853.3). Total num frames: 908288. Throughput: 0: 3076.4. Samples: 904942. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:40:50,913][21315] Avg episode reward: [(0, '29.699')] [2023-03-03 13:40:51,686][21357] Updated weights for policy 0, policy_version 890 (0.0007) [2023-03-03 13:40:54,922][21357] Updated weights for policy 0, policy_version 900 (0.0006) [2023-03-03 13:40:55,914][21315] Fps is (10 sec: 3172.8, 60 sec: 3071.9, 300 sec: 2867.2). Total num frames: 924672. Throughput: 0: 3090.9. Samples: 924040. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:40:55,914][21315] Avg episode reward: [(0, '27.103')] [2023-03-03 13:40:58,153][21357] Updated weights for policy 0, policy_version 910 (0.0007) [2023-03-03 13:41:00,914][21315] Fps is (10 sec: 3173.8, 60 sec: 3089.0, 300 sec: 2888.0). Total num frames: 940032. Throughput: 0: 3093.6. Samples: 933441. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:41:00,914][21315] Avg episode reward: [(0, '32.011')] [2023-03-03 13:41:01,411][21357] Updated weights for policy 0, policy_version 920 (0.0007) [2023-03-03 13:41:04,735][21357] Updated weights for policy 0, policy_version 930 (0.0008) [2023-03-03 13:41:05,914][21315] Fps is (10 sec: 3072.0, 60 sec: 3089.0, 300 sec: 2898.4). Total num frames: 955392. Throughput: 0: 3103.9. Samples: 952046. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:41:05,914][21315] Avg episode reward: [(0, '32.029')] [2023-03-03 13:41:08,189][21357] Updated weights for policy 0, policy_version 940 (0.0008) [2023-03-03 13:41:10,910][21315] Fps is (10 sec: 3073.2, 60 sec: 3089.2, 300 sec: 2908.9). Total num frames: 970752. Throughput: 0: 3096.0. Samples: 970154. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:41:10,911][21315] Avg episode reward: [(0, '36.289')] [2023-03-03 13:41:11,444][21357] Updated weights for policy 0, policy_version 950 (0.0007) [2023-03-03 13:41:14,721][21357] Updated weights for policy 0, policy_version 960 (0.0008) [2023-03-03 13:41:15,912][21315] Fps is (10 sec: 3072.5, 60 sec: 3089.0, 300 sec: 2915.8). Total num frames: 986112. Throughput: 0: 3098.7. Samples: 979550. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:41:15,913][21315] Avg episode reward: [(0, '35.416')] [2023-03-03 13:41:18,785][21357] Updated weights for policy 0, policy_version 970 (0.0008) [2023-03-03 13:41:20,910][21315] Fps is (10 sec: 2765.0, 60 sec: 3038.0, 300 sec: 2908.9). Total num frames: 998400. Throughput: 0: 3038.8. Samples: 995677. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:41:20,911][21315] Avg episode reward: [(0, '36.575')] [2023-03-03 13:41:21,064][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000000976_999424.pth... [2023-03-03 13:41:21,158][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000000267_273408.pth [2023-03-03 13:41:22,432][21357] Updated weights for policy 0, policy_version 980 (0.0008) [2023-03-03 13:41:25,714][21357] Updated weights for policy 0, policy_version 990 (0.0007) [2023-03-03 13:41:25,912][21315] Fps is (10 sec: 2764.8, 60 sec: 3038.0, 300 sec: 2915.8). Total num frames: 1013760. Throughput: 0: 3019.4. Samples: 1013468. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:41:25,913][21315] Avg episode reward: [(0, '34.008')] [2023-03-03 13:41:29,050][21357] Updated weights for policy 0, policy_version 1000 (0.0007) [2023-03-03 13:41:30,909][21315] Fps is (10 sec: 3072.1, 60 sec: 3037.9, 300 sec: 2922.7). Total num frames: 1029120. Throughput: 0: 3024.2. Samples: 1022910. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:41:30,909][21315] Avg episode reward: [(0, '40.554')] [2023-03-03 13:41:32,335][21357] Updated weights for policy 0, policy_version 1010 (0.0007) [2023-03-03 13:41:35,662][21357] Updated weights for policy 0, policy_version 1020 (0.0008) [2023-03-03 13:41:35,910][21315] Fps is (10 sec: 3072.6, 60 sec: 3037.9, 300 sec: 2929.7). Total num frames: 1044480. Throughput: 0: 3035.0. Samples: 1041513. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:41:35,911][21315] Avg episode reward: [(0, '34.280')] [2023-03-03 13:41:39,293][21357] Updated weights for policy 0, policy_version 1030 (0.0008) [2023-03-03 13:41:40,910][21315] Fps is (10 sec: 2969.3, 60 sec: 3021.0, 300 sec: 2933.2). Total num frames: 1058816. Throughput: 0: 2992.0. Samples: 1058669. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:41:40,911][21315] Avg episode reward: [(0, '37.922')] [2023-03-03 13:41:42,801][21357] Updated weights for policy 0, policy_version 1040 (0.0008) [2023-03-03 13:41:45,913][21315] Fps is (10 sec: 2968.9, 60 sec: 3020.6, 300 sec: 2957.5). Total num frames: 1074176. Throughput: 0: 2981.5. Samples: 1067606. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:41:45,914][21315] Avg episode reward: [(0, '28.984')] [2023-03-03 13:41:46,134][21357] Updated weights for policy 0, policy_version 1050 (0.0008) [2023-03-03 13:41:49,401][21357] Updated weights for policy 0, policy_version 1060 (0.0007) [2023-03-03 13:41:50,913][21315] Fps is (10 sec: 3071.0, 60 sec: 3020.7, 300 sec: 2971.3). Total num frames: 1089536. Throughput: 0: 2981.0. Samples: 1086189. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:41:50,914][21315] Avg episode reward: [(0, '27.524')] [2023-03-03 13:41:52,731][21357] Updated weights for policy 0, policy_version 1070 (0.0007) [2023-03-03 13:41:55,912][21315] Fps is (10 sec: 3072.1, 60 sec: 3003.8, 300 sec: 2981.8). Total num frames: 1104896. Throughput: 0: 2990.1. Samples: 1104715. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:41:55,913][21315] Avg episode reward: [(0, '26.501')] [2023-03-03 13:41:56,061][21357] Updated weights for policy 0, policy_version 1080 (0.0008) [2023-03-03 13:41:59,389][21357] Updated weights for policy 0, policy_version 1090 (0.0007) [2023-03-03 13:42:00,910][21315] Fps is (10 sec: 3072.9, 60 sec: 3003.9, 300 sec: 2992.2). Total num frames: 1120256. Throughput: 0: 2986.8. Samples: 1113953. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:42:00,911][21315] Avg episode reward: [(0, '24.359')] [2023-03-03 13:42:02,637][21357] Updated weights for policy 0, policy_version 1100 (0.0007) [2023-03-03 13:42:05,912][21315] Fps is (10 sec: 3072.2, 60 sec: 3003.8, 300 sec: 3002.6). Total num frames: 1135616. Throughput: 0: 3036.8. Samples: 1132341. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:42:05,914][21315] Avg episode reward: [(0, '22.348')] [2023-03-03 13:42:06,376][21357] Updated weights for policy 0, policy_version 1110 (0.0007) [2023-03-03 13:42:10,752][21357] Updated weights for policy 0, policy_version 1120 (0.0011) [2023-03-03 13:42:10,913][21315] Fps is (10 sec: 2661.6, 60 sec: 2935.3, 300 sec: 3002.6). Total num frames: 1146880. Throughput: 0: 2960.5. Samples: 1146694. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:42:10,915][21315] Avg episode reward: [(0, '21.832')] [2023-03-03 13:42:15,274][21357] Updated weights for policy 0, policy_version 1130 (0.0008) [2023-03-03 13:42:15,909][21315] Fps is (10 sec: 2253.4, 60 sec: 2867.4, 300 sec: 3002.7). Total num frames: 1158144. Throughput: 0: 2893.2. Samples: 1153102. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:42:15,910][21315] Avg episode reward: [(0, '22.390')] [2023-03-03 13:42:19,015][21357] Updated weights for policy 0, policy_version 1140 (0.0009) [2023-03-03 13:42:20,914][21315] Fps is (10 sec: 2560.0, 60 sec: 2901.1, 300 sec: 3002.6). Total num frames: 1172480. Throughput: 0: 2838.0. Samples: 1169232. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:42:20,924][21315] Avg episode reward: [(0, '23.341')] [2023-03-03 13:42:22,454][21357] Updated weights for policy 0, policy_version 1150 (0.0008) [2023-03-03 13:42:25,741][21357] Updated weights for policy 0, policy_version 1160 (0.0007) [2023-03-03 13:42:25,914][21315] Fps is (10 sec: 2968.2, 60 sec: 2901.3, 300 sec: 2999.1). Total num frames: 1187840. Throughput: 0: 2861.5. Samples: 1187447. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:42:25,914][21315] Avg episode reward: [(0, '24.239')] [2023-03-03 13:42:29,203][21357] Updated weights for policy 0, policy_version 1170 (0.0008) [2023-03-03 13:42:30,915][21315] Fps is (10 sec: 2969.3, 60 sec: 2884.0, 300 sec: 2999.1). Total num frames: 1202176. Throughput: 0: 2870.9. Samples: 1196800. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:42:30,916][21315] Avg episode reward: [(0, '24.348')] [2023-03-03 13:42:32,624][21357] Updated weights for policy 0, policy_version 1180 (0.0008) [2023-03-03 13:42:35,851][21357] Updated weights for policy 0, policy_version 1190 (0.0008) [2023-03-03 13:42:35,913][21315] Fps is (10 sec: 3072.1, 60 sec: 2901.2, 300 sec: 3006.1). Total num frames: 1218560. Throughput: 0: 2861.8. Samples: 1214968. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:42:35,914][21315] Avg episode reward: [(0, '24.732')] [2023-03-03 13:42:39,162][21357] Updated weights for policy 0, policy_version 1200 (0.0007) [2023-03-03 13:42:40,910][21315] Fps is (10 sec: 3073.4, 60 sec: 2901.3, 300 sec: 2999.1). Total num frames: 1232896. Throughput: 0: 2854.0. Samples: 1233138. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:42:40,911][21315] Avg episode reward: [(0, '24.621')] [2023-03-03 13:42:42,510][21357] Updated weights for policy 0, policy_version 1210 (0.0007) [2023-03-03 13:42:45,914][21315] Fps is (10 sec: 2969.5, 60 sec: 2901.3, 300 sec: 2995.6). Total num frames: 1248256. Throughput: 0: 2854.0. Samples: 1242393. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:42:45,916][21315] Avg episode reward: [(0, '25.193')] [2023-03-03 13:42:45,954][21357] Updated weights for policy 0, policy_version 1220 (0.0008) [2023-03-03 13:42:49,485][21357] Updated weights for policy 0, policy_version 1230 (0.0008) [2023-03-03 13:42:50,910][21315] Fps is (10 sec: 3072.1, 60 sec: 2901.5, 300 sec: 2995.7). Total num frames: 1263616. Throughput: 0: 2838.1. Samples: 1260050. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:42:50,911][21315] Avg episode reward: [(0, '26.343')] [2023-03-03 13:42:52,797][21357] Updated weights for policy 0, policy_version 1240 (0.0007) [2023-03-03 13:42:55,910][21315] Fps is (10 sec: 2970.9, 60 sec: 2884.4, 300 sec: 2992.2). Total num frames: 1277952. Throughput: 0: 2918.5. Samples: 1278015. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:42:55,911][21315] Avg episode reward: [(0, '27.788')] [2023-03-03 13:42:56,251][21357] Updated weights for policy 0, policy_version 1250 (0.0010) [2023-03-03 13:42:59,580][21357] Updated weights for policy 0, policy_version 1260 (0.0009) [2023-03-03 13:43:00,914][21315] Fps is (10 sec: 2968.2, 60 sec: 2884.1, 300 sec: 2988.7). Total num frames: 1293312. Throughput: 0: 2984.7. Samples: 1287429. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:43:00,915][21315] Avg episode reward: [(0, '26.974')] [2023-03-03 13:43:02,921][21357] Updated weights for policy 0, policy_version 1270 (0.0006) [2023-03-03 13:43:05,909][21315] Fps is (10 sec: 3174.4, 60 sec: 2901.4, 300 sec: 2988.7). Total num frames: 1309696. Throughput: 0: 3041.7. Samples: 1306095. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:43:05,910][21315] Avg episode reward: [(0, '27.172')] [2023-03-03 13:43:06,172][21357] Updated weights for policy 0, policy_version 1280 (0.0006) [2023-03-03 13:43:09,474][21357] Updated weights for policy 0, policy_version 1290 (0.0007) [2023-03-03 13:43:10,912][21315] Fps is (10 sec: 3175.2, 60 sec: 2969.7, 300 sec: 2985.3). Total num frames: 1325056. Throughput: 0: 3044.4. Samples: 1324438. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:43:10,913][21315] Avg episode reward: [(0, '26.587')] [2023-03-03 13:43:12,810][21357] Updated weights for policy 0, policy_version 1300 (0.0008) [2023-03-03 13:43:15,909][21315] Fps is (10 sec: 3072.1, 60 sec: 3037.9, 300 sec: 2985.3). Total num frames: 1340416. Throughput: 0: 3043.4. Samples: 1333736. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:43:15,910][21315] Avg episode reward: [(0, '29.172')] [2023-03-03 13:43:16,189][21357] Updated weights for policy 0, policy_version 1310 (0.0008) [2023-03-03 13:43:19,459][21357] Updated weights for policy 0, policy_version 1320 (0.0007) [2023-03-03 13:43:20,914][21315] Fps is (10 sec: 3071.3, 60 sec: 3054.9, 300 sec: 2981.7). Total num frames: 1355776. Throughput: 0: 3051.4. Samples: 1352285. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:43:20,915][21315] Avg episode reward: [(0, '28.854')] [2023-03-03 13:43:21,094][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000001325_1356800.pth... [2023-03-03 13:43:21,173][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000000632_647168.pth [2023-03-03 13:43:22,734][21357] Updated weights for policy 0, policy_version 1330 (0.0008) [2023-03-03 13:43:25,915][21315] Fps is (10 sec: 3070.1, 60 sec: 3054.8, 300 sec: 2978.2). Total num frames: 1371136. Throughput: 0: 3063.1. Samples: 1370994. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:43:25,916][21315] Avg episode reward: [(0, '28.450')] [2023-03-03 13:43:26,152][21357] Updated weights for policy 0, policy_version 1340 (0.0011) [2023-03-03 13:43:30,203][21357] Updated weights for policy 0, policy_version 1350 (0.0008) [2023-03-03 13:43:30,909][21315] Fps is (10 sec: 2868.7, 60 sec: 3038.2, 300 sec: 2967.9). Total num frames: 1384448. Throughput: 0: 3033.2. Samples: 1378875. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:43:30,910][21315] Avg episode reward: [(0, '29.071')] [2023-03-03 13:43:34,171][21357] Updated weights for policy 0, policy_version 1360 (0.0010) [2023-03-03 13:43:35,918][21315] Fps is (10 sec: 2661.9, 60 sec: 2986.5, 300 sec: 2957.4). Total num frames: 1397760. Throughput: 0: 2979.7. Samples: 1394161. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-03-03 13:43:35,919][21315] Avg episode reward: [(0, '29.978')] [2023-03-03 13:43:38,011][21357] Updated weights for policy 0, policy_version 1370 (0.0008) [2023-03-03 13:43:40,913][21315] Fps is (10 sec: 2456.5, 60 sec: 2935.3, 300 sec: 2940.1). Total num frames: 1409024. Throughput: 0: 2923.2. Samples: 1409572. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:43:40,914][21315] Avg episode reward: [(0, '30.582')] [2023-03-03 13:43:42,210][21357] Updated weights for policy 0, policy_version 1380 (0.0009) [2023-03-03 13:43:45,914][21315] Fps is (10 sec: 2458.4, 60 sec: 2901.3, 300 sec: 2929.7). Total num frames: 1422336. Throughput: 0: 2874.0. Samples: 1416759. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:43:45,915][21315] Avg episode reward: [(0, '30.726')] [2023-03-03 13:43:46,219][21357] Updated weights for policy 0, policy_version 1390 (0.0009) [2023-03-03 13:43:50,601][21357] Updated weights for policy 0, policy_version 1400 (0.0014) [2023-03-03 13:43:50,918][21315] Fps is (10 sec: 2456.7, 60 sec: 2832.7, 300 sec: 2908.8). Total num frames: 1433600. Throughput: 0: 2789.5. Samples: 1431644. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:43:50,920][21315] Avg episode reward: [(0, '33.386')] [2023-03-03 13:43:55,038][21357] Updated weights for policy 0, policy_version 1410 (0.0010) [2023-03-03 13:43:55,910][21315] Fps is (10 sec: 2356.1, 60 sec: 2798.9, 300 sec: 2898.5). Total num frames: 1445888. Throughput: 0: 2689.3. Samples: 1445454. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:43:55,912][21315] Avg episode reward: [(0, '34.654')] [2023-03-03 13:43:59,103][21357] Updated weights for policy 0, policy_version 1420 (0.0025) [2023-03-03 13:44:00,910][21315] Fps is (10 sec: 2459.3, 60 sec: 2747.9, 300 sec: 2884.6). Total num frames: 1458176. Throughput: 0: 2642.2. Samples: 1452637. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:44:00,912][21315] Avg episode reward: [(0, '37.264')] [2023-03-03 13:44:03,445][21357] Updated weights for policy 0, policy_version 1430 (0.0010) [2023-03-03 13:44:05,912][21315] Fps is (10 sec: 2457.3, 60 sec: 2679.4, 300 sec: 2870.7). Total num frames: 1470464. Throughput: 0: 2552.0. Samples: 1467117. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:44:05,914][21315] Avg episode reward: [(0, '42.268')] [2023-03-03 13:44:07,081][21357] Updated weights for policy 0, policy_version 1440 (0.0009) [2023-03-03 13:44:10,729][21357] Updated weights for policy 0, policy_version 1450 (0.0009) [2023-03-03 13:44:10,916][21315] Fps is (10 sec: 2660.8, 60 sec: 2662.2, 300 sec: 2881.1). Total num frames: 1484800. Throughput: 0: 2521.3. Samples: 1484453. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:44:10,917][21315] Avg episode reward: [(0, '36.265')] [2023-03-03 13:44:14,050][21357] Updated weights for policy 0, policy_version 1460 (0.0007) [2023-03-03 13:44:15,914][21315] Fps is (10 sec: 2866.5, 60 sec: 2645.1, 300 sec: 2891.5). Total num frames: 1499136. Throughput: 0: 2555.5. Samples: 1493886. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:44:15,916][21315] Avg episode reward: [(0, '36.250')] [2023-03-03 13:44:17,734][21357] Updated weights for policy 0, policy_version 1470 (0.0009) [2023-03-03 13:44:20,909][21315] Fps is (10 sec: 2971.8, 60 sec: 2645.6, 300 sec: 2891.5). Total num frames: 1514496. Throughput: 0: 2599.8. Samples: 1511128. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:44:20,909][21315] Avg episode reward: [(0, '25.343')] [2023-03-03 13:44:21,068][21357] Updated weights for policy 0, policy_version 1480 (0.0007) [2023-03-03 13:44:24,325][21357] Updated weights for policy 0, policy_version 1490 (0.0007) [2023-03-03 13:44:25,911][21315] Fps is (10 sec: 3072.8, 60 sec: 2645.5, 300 sec: 2898.5). Total num frames: 1529856. Throughput: 0: 2667.9. Samples: 1529624. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:44:25,912][21315] Avg episode reward: [(0, '25.568')] [2023-03-03 13:44:28,216][21357] Updated weights for policy 0, policy_version 1500 (0.0010) [2023-03-03 13:44:30,910][21315] Fps is (10 sec: 2764.6, 60 sec: 2628.2, 300 sec: 2898.5). Total num frames: 1542144. Throughput: 0: 2675.5. Samples: 1537142. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:44:30,912][21315] Avg episode reward: [(0, '27.251')] [2023-03-03 13:44:32,564][21357] Updated weights for policy 0, policy_version 1510 (0.0008) [2023-03-03 13:44:35,913][21315] Fps is (10 sec: 2354.7, 60 sec: 2594.3, 300 sec: 2888.0). Total num frames: 1553408. Throughput: 0: 2657.4. Samples: 1551219. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:44:35,914][21315] Avg episode reward: [(0, '26.490')] [2023-03-03 13:44:36,756][21357] Updated weights for policy 0, policy_version 1520 (0.0011) [2023-03-03 13:44:40,025][21357] Updated weights for policy 0, policy_version 1530 (0.0008) [2023-03-03 13:44:40,910][21315] Fps is (10 sec: 2662.1, 60 sec: 2662.5, 300 sec: 2898.5). Total num frames: 1568768. Throughput: 0: 2735.0. Samples: 1568529. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:44:40,911][21315] Avg episode reward: [(0, '24.526')] [2023-03-03 13:44:43,349][21357] Updated weights for policy 0, policy_version 1540 (0.0008) [2023-03-03 13:44:45,909][21315] Fps is (10 sec: 3073.3, 60 sec: 2696.8, 300 sec: 2905.4). Total num frames: 1584128. Throughput: 0: 2782.3. Samples: 1577838. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:44:45,910][21315] Avg episode reward: [(0, '23.258')] [2023-03-03 13:44:46,854][21357] Updated weights for policy 0, policy_version 1550 (0.0008) [2023-03-03 13:44:50,389][21357] Updated weights for policy 0, policy_version 1560 (0.0007) [2023-03-03 13:44:50,909][21315] Fps is (10 sec: 2970.1, 60 sec: 2748.1, 300 sec: 2908.9). Total num frames: 1598464. Throughput: 0: 2845.2. Samples: 1595145. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:44:50,910][21315] Avg episode reward: [(0, '19.733')] [2023-03-03 13:44:53,647][21357] Updated weights for policy 0, policy_version 1570 (0.0007) [2023-03-03 13:44:55,914][21315] Fps is (10 sec: 2968.4, 60 sec: 2798.8, 300 sec: 2912.3). Total num frames: 1613824. Throughput: 0: 2875.6. Samples: 1613847. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:44:55,914][21315] Avg episode reward: [(0, '19.096')] [2023-03-03 13:44:56,885][21357] Updated weights for policy 0, policy_version 1580 (0.0007) [2023-03-03 13:45:00,191][21357] Updated weights for policy 0, policy_version 1590 (0.0008) [2023-03-03 13:45:00,913][21315] Fps is (10 sec: 3173.2, 60 sec: 2867.1, 300 sec: 2915.8). Total num frames: 1630208. Throughput: 0: 2871.8. Samples: 1623111. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:45:00,914][21315] Avg episode reward: [(0, '21.732')] [2023-03-03 13:45:03,496][21357] Updated weights for policy 0, policy_version 1600 (0.0007) [2023-03-03 13:45:05,912][21315] Fps is (10 sec: 3174.9, 60 sec: 2918.4, 300 sec: 2915.8). Total num frames: 1645568. Throughput: 0: 2909.6. Samples: 1642067. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:45:05,913][21315] Avg episode reward: [(0, '24.289')] [2023-03-03 13:45:06,751][21357] Updated weights for policy 0, policy_version 1610 (0.0007) [2023-03-03 13:45:09,970][21357] Updated weights for policy 0, policy_version 1620 (0.0007) [2023-03-03 13:45:10,912][21315] Fps is (10 sec: 3072.1, 60 sec: 2935.7, 300 sec: 2915.8). Total num frames: 1660928. Throughput: 0: 2920.8. Samples: 1661064. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:45:10,913][21315] Avg episode reward: [(0, '24.655')] [2023-03-03 13:45:13,302][21357] Updated weights for policy 0, policy_version 1630 (0.0007) [2023-03-03 13:45:15,912][21315] Fps is (10 sec: 3071.8, 60 sec: 2952.6, 300 sec: 2915.8). Total num frames: 1676288. Throughput: 0: 2952.8. Samples: 1670026. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:45:15,913][21315] Avg episode reward: [(0, '23.375')] [2023-03-03 13:45:16,772][21357] Updated weights for policy 0, policy_version 1640 (0.0008) [2023-03-03 13:45:20,028][21357] Updated weights for policy 0, policy_version 1650 (0.0007) [2023-03-03 13:45:20,913][21315] Fps is (10 sec: 3071.6, 60 sec: 2952.3, 300 sec: 2915.8). Total num frames: 1691648. Throughput: 0: 3046.8. Samples: 1688326. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:45:20,914][21315] Avg episode reward: [(0, '22.505')] [2023-03-03 13:45:20,958][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000001653_1692672.pth... [2023-03-03 13:45:21,041][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000000976_999424.pth [2023-03-03 13:45:23,289][21357] Updated weights for policy 0, policy_version 1660 (0.0007) [2023-03-03 13:45:25,911][21315] Fps is (10 sec: 3174.8, 60 sec: 2969.6, 300 sec: 2919.2). Total num frames: 1708032. Throughput: 0: 3081.1. Samples: 1707181. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:45:25,912][21315] Avg episode reward: [(0, '20.597')] [2023-03-03 13:45:26,540][21357] Updated weights for policy 0, policy_version 1670 (0.0007) [2023-03-03 13:45:29,862][21357] Updated weights for policy 0, policy_version 1680 (0.0008) [2023-03-03 13:45:30,911][21315] Fps is (10 sec: 3072.7, 60 sec: 3003.6, 300 sec: 2915.8). Total num frames: 1722368. Throughput: 0: 3080.0. Samples: 1716445. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:45:30,914][21315] Avg episode reward: [(0, '19.354')] [2023-03-03 13:45:33,426][21357] Updated weights for policy 0, policy_version 1690 (0.0009) [2023-03-03 13:45:35,913][21315] Fps is (10 sec: 2969.2, 60 sec: 3072.0, 300 sec: 2915.8). Total num frames: 1737728. Throughput: 0: 3098.2. Samples: 1734575. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:45:35,914][21315] Avg episode reward: [(0, '18.699')] [2023-03-03 13:45:36,667][21357] Updated weights for policy 0, policy_version 1700 (0.0007) [2023-03-03 13:45:39,910][21357] Updated weights for policy 0, policy_version 1710 (0.0007) [2023-03-03 13:45:40,913][21315] Fps is (10 sec: 3071.5, 60 sec: 3071.9, 300 sec: 2915.8). Total num frames: 1753088. Throughput: 0: 3101.9. Samples: 1753429. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:45:40,913][21315] Avg episode reward: [(0, '18.600')] [2023-03-03 13:45:43,567][21357] Updated weights for policy 0, policy_version 1720 (0.0008) [2023-03-03 13:45:45,914][21315] Fps is (10 sec: 2969.1, 60 sec: 3054.7, 300 sec: 2912.3). Total num frames: 1767424. Throughput: 0: 3078.9. Samples: 1761666. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:45:45,915][21315] Avg episode reward: [(0, '17.781')] [2023-03-03 13:45:46,974][21357] Updated weights for policy 0, policy_version 1730 (0.0010) [2023-03-03 13:45:50,238][21357] Updated weights for policy 0, policy_version 1740 (0.0007) [2023-03-03 13:45:50,910][21315] Fps is (10 sec: 3072.9, 60 sec: 3089.0, 300 sec: 2912.4). Total num frames: 1783808. Throughput: 0: 3063.9. Samples: 1779935. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:45:50,911][21315] Avg episode reward: [(0, '18.683')] [2023-03-03 13:45:53,496][21357] Updated weights for policy 0, policy_version 1750 (0.0007) [2023-03-03 13:45:55,912][21315] Fps is (10 sec: 3175.0, 60 sec: 3089.1, 300 sec: 2912.3). Total num frames: 1799168. Throughput: 0: 3058.1. Samples: 1798677. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:45:55,914][21315] Avg episode reward: [(0, '19.919')] [2023-03-03 13:45:56,746][21357] Updated weights for policy 0, policy_version 1760 (0.0007) [2023-03-03 13:46:00,023][21357] Updated weights for policy 0, policy_version 1770 (0.0007) [2023-03-03 13:46:00,909][21315] Fps is (10 sec: 3072.3, 60 sec: 3072.2, 300 sec: 2912.4). Total num frames: 1814528. Throughput: 0: 3066.8. Samples: 1808020. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:46:00,910][21315] Avg episode reward: [(0, '21.494')] [2023-03-03 13:46:03,363][21357] Updated weights for policy 0, policy_version 1780 (0.0007) [2023-03-03 13:46:05,913][21315] Fps is (10 sec: 3071.7, 60 sec: 3071.9, 300 sec: 2912.3). Total num frames: 1829888. Throughput: 0: 3069.3. Samples: 1826443. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:46:05,914][21315] Avg episode reward: [(0, '21.981')] [2023-03-03 13:46:06,830][21357] Updated weights for policy 0, policy_version 1790 (0.0006) [2023-03-03 13:46:10,070][21357] Updated weights for policy 0, policy_version 1800 (0.0006) [2023-03-03 13:46:10,912][21315] Fps is (10 sec: 3070.9, 60 sec: 3072.0, 300 sec: 2912.3). Total num frames: 1845248. Throughput: 0: 3061.8. Samples: 1844965. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:46:10,913][21315] Avg episode reward: [(0, '22.764')] [2023-03-03 13:46:13,384][21357] Updated weights for policy 0, policy_version 1810 (0.0009) [2023-03-03 13:46:15,913][21315] Fps is (10 sec: 3072.1, 60 sec: 3072.0, 300 sec: 2922.7). Total num frames: 1860608. Throughput: 0: 3062.3. Samples: 1854254. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:46:15,913][21315] Avg episode reward: [(0, '22.525')] [2023-03-03 13:46:16,766][21357] Updated weights for policy 0, policy_version 1820 (0.0008) [2023-03-03 13:46:20,019][21357] Updated weights for policy 0, policy_version 1830 (0.0007) [2023-03-03 13:46:20,913][21315] Fps is (10 sec: 3071.7, 60 sec: 3072.0, 300 sec: 2922.7). Total num frames: 1875968. Throughput: 0: 3068.1. Samples: 1872644. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:46:20,915][21315] Avg episode reward: [(0, '25.649')] [2023-03-03 13:46:23,280][21357] Updated weights for policy 0, policy_version 1840 (0.0008) [2023-03-03 13:46:25,910][21315] Fps is (10 sec: 3072.8, 60 sec: 3055.0, 300 sec: 2922.7). Total num frames: 1891328. Throughput: 0: 3053.2. Samples: 1890815. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:46:25,912][21315] Avg episode reward: [(0, '28.413')] [2023-03-03 13:46:26,751][21357] Updated weights for policy 0, policy_version 1850 (0.0008) [2023-03-03 13:46:30,056][21357] Updated weights for policy 0, policy_version 1860 (0.0007) [2023-03-03 13:46:30,913][21315] Fps is (10 sec: 3072.0, 60 sec: 3071.9, 300 sec: 2922.7). Total num frames: 1906688. Throughput: 0: 3078.5. Samples: 1900196. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 13:46:30,914][21315] Avg episode reward: [(0, '30.387')] [2023-03-03 13:46:33,522][21357] Updated weights for policy 0, policy_version 1870 (0.0009) [2023-03-03 13:46:35,913][21315] Fps is (10 sec: 3071.0, 60 sec: 3072.0, 300 sec: 2926.2). Total num frames: 1922048. Throughput: 0: 3078.6. Samples: 1918483. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:46:35,914][21315] Avg episode reward: [(0, '29.594')] [2023-03-03 13:46:36,761][21357] Updated weights for policy 0, policy_version 1880 (0.0007) [2023-03-03 13:46:40,026][21357] Updated weights for policy 0, policy_version 1890 (0.0007) [2023-03-03 13:46:40,909][21315] Fps is (10 sec: 3073.4, 60 sec: 3072.2, 300 sec: 2926.2). Total num frames: 1937408. Throughput: 0: 3078.2. Samples: 1937183. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:46:40,910][21315] Avg episode reward: [(0, '27.414')] [2023-03-03 13:46:43,327][21357] Updated weights for policy 0, policy_version 1900 (0.0009) [2023-03-03 13:46:45,911][21315] Fps is (10 sec: 3072.8, 60 sec: 3089.3, 300 sec: 2926.2). Total num frames: 1952768. Throughput: 0: 3076.9. Samples: 1946488. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:46:45,912][21315] Avg episode reward: [(0, '26.446')] [2023-03-03 13:46:46,697][21357] Updated weights for policy 0, policy_version 1910 (0.0008) [2023-03-03 13:46:49,956][21357] Updated weights for policy 0, policy_version 1920 (0.0007) [2023-03-03 13:46:50,910][21315] Fps is (10 sec: 3174.2, 60 sec: 3089.1, 300 sec: 2929.7). Total num frames: 1969152. Throughput: 0: 3079.5. Samples: 1965010. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:46:50,910][21315] Avg episode reward: [(0, '23.344')] [2023-03-03 13:46:53,211][21357] Updated weights for policy 0, policy_version 1930 (0.0007) [2023-03-03 13:46:55,913][21315] Fps is (10 sec: 3173.6, 60 sec: 3089.0, 300 sec: 2929.7). Total num frames: 1984512. Throughput: 0: 3087.0. Samples: 1983884. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:46:55,914][21315] Avg episode reward: [(0, '23.404')] [2023-03-03 13:46:56,456][21357] Updated weights for policy 0, policy_version 1940 (0.0006) [2023-03-03 13:46:59,770][21357] Updated weights for policy 0, policy_version 1950 (0.0007) [2023-03-03 13:47:00,913][21315] Fps is (10 sec: 3070.8, 60 sec: 3088.8, 300 sec: 2929.7). Total num frames: 1999872. Throughput: 0: 3089.8. Samples: 1993297. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:47:00,914][21315] Avg episode reward: [(0, '22.219')] [2023-03-03 13:47:03,079][21357] Updated weights for policy 0, policy_version 1960 (0.0008) [2023-03-03 13:47:05,914][21315] Fps is (10 sec: 2969.4, 60 sec: 3072.0, 300 sec: 2940.1). Total num frames: 2014208. Throughput: 0: 3091.6. Samples: 2011769. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:47:05,915][21315] Avg episode reward: [(0, '23.157')] [2023-03-03 13:47:06,559][21357] Updated weights for policy 0, policy_version 1970 (0.0008) [2023-03-03 13:47:09,785][21357] Updated weights for policy 0, policy_version 1980 (0.0008) [2023-03-03 13:47:10,911][21315] Fps is (10 sec: 3072.6, 60 sec: 3089.1, 300 sec: 2957.4). Total num frames: 2030592. Throughput: 0: 3095.3. Samples: 2030106. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:47:10,912][21315] Avg episode reward: [(0, '24.644')] [2023-03-03 13:47:13,482][21357] Updated weights for policy 0, policy_version 1990 (0.0007) [2023-03-03 13:47:15,910][21315] Fps is (10 sec: 2970.9, 60 sec: 3055.1, 300 sec: 2954.0). Total num frames: 2043904. Throughput: 0: 3068.6. Samples: 2038272. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:47:15,911][21315] Avg episode reward: [(0, '24.482')] [2023-03-03 13:47:17,048][21357] Updated weights for policy 0, policy_version 2000 (0.0007) [2023-03-03 13:47:20,469][21357] Updated weights for policy 0, policy_version 2010 (0.0007) [2023-03-03 13:47:20,910][21315] Fps is (10 sec: 2867.6, 60 sec: 3055.1, 300 sec: 2954.0). Total num frames: 2059264. Throughput: 0: 3049.1. Samples: 2055683. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 13:47:20,911][21315] Avg episode reward: [(0, '24.556')] [2023-03-03 13:47:21,111][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000002012_2060288.pth... [2023-03-03 13:47:21,188][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000001325_1356800.pth [2023-03-03 13:47:23,816][21357] Updated weights for policy 0, policy_version 2020 (0.0007) [2023-03-03 13:47:25,914][21315] Fps is (10 sec: 2968.2, 60 sec: 3037.7, 300 sec: 2954.0). Total num frames: 2073600. Throughput: 0: 3027.0. Samples: 2073413. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 13:47:25,916][21315] Avg episode reward: [(0, '24.176')] [2023-03-03 13:47:27,356][21357] Updated weights for policy 0, policy_version 2030 (0.0007) [2023-03-03 13:47:30,670][21357] Updated weights for policy 0, policy_version 2040 (0.0007) [2023-03-03 13:47:30,911][21315] Fps is (10 sec: 2969.4, 60 sec: 3038.0, 300 sec: 2950.5). Total num frames: 2088960. Throughput: 0: 3029.7. Samples: 2082824. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:47:30,912][21315] Avg episode reward: [(0, '23.392')] [2023-03-03 13:47:33,878][21357] Updated weights for policy 0, policy_version 2050 (0.0008) [2023-03-03 13:47:35,913][21315] Fps is (10 sec: 3174.7, 60 sec: 3054.9, 300 sec: 2957.4). Total num frames: 2105344. Throughput: 0: 3038.9. Samples: 2101771. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 13:47:35,914][21315] Avg episode reward: [(0, '23.902')] [2023-03-03 13:47:37,124][21357] Updated weights for policy 0, policy_version 2060 (0.0006) [2023-03-03 13:47:40,371][21357] Updated weights for policy 0, policy_version 2070 (0.0007) [2023-03-03 13:47:40,913][21315] Fps is (10 sec: 3173.7, 60 sec: 3054.7, 300 sec: 2957.5). Total num frames: 2120704. Throughput: 0: 3036.3. Samples: 2120517. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:47:40,914][21315] Avg episode reward: [(0, '24.660')] [2023-03-03 13:47:43,763][21357] Updated weights for policy 0, policy_version 2080 (0.0009) [2023-03-03 13:47:45,913][21315] Fps is (10 sec: 3072.2, 60 sec: 3054.8, 300 sec: 2957.4). Total num frames: 2136064. Throughput: 0: 3032.7. Samples: 2129765. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:47:45,914][21315] Avg episode reward: [(0, '26.254')] [2023-03-03 13:47:47,167][21357] Updated weights for policy 0, policy_version 2090 (0.0007) [2023-03-03 13:47:50,904][21357] Updated weights for policy 0, policy_version 2100 (0.0010) [2023-03-03 13:47:50,909][21315] Fps is (10 sec: 2970.7, 60 sec: 3020.8, 300 sec: 2957.4). Total num frames: 2150400. Throughput: 0: 3022.8. Samples: 2147780. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:47:50,910][21315] Avg episode reward: [(0, '26.728')] [2023-03-03 13:47:54,723][21357] Updated weights for policy 0, policy_version 2110 (0.0010) [2023-03-03 13:47:55,909][21315] Fps is (10 sec: 2765.8, 60 sec: 2986.9, 300 sec: 2950.6). Total num frames: 2163712. Throughput: 0: 2964.7. Samples: 2163508. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:47:55,910][21315] Avg episode reward: [(0, '29.947')] [2023-03-03 13:47:57,998][21357] Updated weights for policy 0, policy_version 2120 (0.0008) [2023-03-03 13:48:00,913][21315] Fps is (10 sec: 2661.4, 60 sec: 2952.5, 300 sec: 2940.1). Total num frames: 2177024. Throughput: 0: 2993.0. Samples: 2172967. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:48:00,914][21315] Avg episode reward: [(0, '33.460')] [2023-03-03 13:48:02,161][21357] Updated weights for policy 0, policy_version 2130 (0.0011) [2023-03-03 13:48:05,415][21357] Updated weights for policy 0, policy_version 2140 (0.0008) [2023-03-03 13:48:05,912][21315] Fps is (10 sec: 2866.4, 60 sec: 2969.7, 300 sec: 2940.1). Total num frames: 2192384. Throughput: 0: 2960.7. Samples: 2188921. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:48:05,912][21315] Avg episode reward: [(0, '38.835')] [2023-03-03 13:48:08,692][21357] Updated weights for policy 0, policy_version 2150 (0.0007) [2023-03-03 13:48:10,915][21315] Fps is (10 sec: 2969.4, 60 sec: 2935.3, 300 sec: 2936.6). Total num frames: 2206720. Throughput: 0: 2965.9. Samples: 2206880. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:48:10,921][21315] Avg episode reward: [(0, '38.167')] [2023-03-03 13:48:13,230][21357] Updated weights for policy 0, policy_version 2160 (0.0025) [2023-03-03 13:48:15,913][21315] Fps is (10 sec: 2457.4, 60 sec: 2884.1, 300 sec: 2919.3). Total num frames: 2216960. Throughput: 0: 2893.2. Samples: 2213023. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-03-03 13:48:15,914][21315] Avg episode reward: [(0, '36.465')] [2023-03-03 13:48:17,731][21357] Updated weights for policy 0, policy_version 2170 (0.0008) [2023-03-03 13:48:20,913][21315] Fps is (10 sec: 2253.0, 60 sec: 2832.9, 300 sec: 2908.9). Total num frames: 2229248. Throughput: 0: 2780.9. Samples: 2226911. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:48:20,914][21315] Avg episode reward: [(0, '35.088')] [2023-03-03 13:48:22,020][21357] Updated weights for policy 0, policy_version 2180 (0.0011) [2023-03-03 13:48:25,912][21315] Fps is (10 sec: 2355.4, 60 sec: 2782.0, 300 sec: 2901.9). Total num frames: 2240512. Throughput: 0: 2673.2. Samples: 2240805. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:48:25,914][21315] Avg episode reward: [(0, '39.693')] [2023-03-03 13:48:26,459][21357] Updated weights for policy 0, policy_version 2190 (0.0015) [2023-03-03 13:48:29,792][21357] Updated weights for policy 0, policy_version 2200 (0.0006) [2023-03-03 13:48:30,913][21315] Fps is (10 sec: 2662.3, 60 sec: 2781.8, 300 sec: 2908.9). Total num frames: 2255872. Throughput: 0: 2654.6. Samples: 2249226. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:48:30,914][21315] Avg episode reward: [(0, '46.972')] [2023-03-03 13:48:33,290][21357] Updated weights for policy 0, policy_version 2210 (0.0007) [2023-03-03 13:48:35,909][21315] Fps is (10 sec: 2970.4, 60 sec: 2747.9, 300 sec: 2919.3). Total num frames: 2270208. Throughput: 0: 2650.8. Samples: 2267064. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:48:35,910][21315] Avg episode reward: [(0, '45.540')] [2023-03-03 13:48:36,612][21357] Updated weights for policy 0, policy_version 2220 (0.0007) [2023-03-03 13:48:39,869][21357] Updated weights for policy 0, policy_version 2230 (0.0007) [2023-03-03 13:48:40,910][21315] Fps is (10 sec: 2970.7, 60 sec: 2747.9, 300 sec: 2926.3). Total num frames: 2285568. Throughput: 0: 2717.5. Samples: 2285796. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:48:40,910][21315] Avg episode reward: [(0, '46.256')] [2023-03-03 13:48:43,985][21357] Updated weights for policy 0, policy_version 2240 (0.0012) [2023-03-03 13:48:45,914][21315] Fps is (10 sec: 2865.9, 60 sec: 2713.6, 300 sec: 2933.2). Total num frames: 2298880. Throughput: 0: 2670.3. Samples: 2293133. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:48:45,916][21315] Avg episode reward: [(0, '35.496')] [2023-03-03 13:48:47,531][21357] Updated weights for policy 0, policy_version 2250 (0.0007) [2023-03-03 13:48:50,913][21315] Fps is (10 sec: 2763.7, 60 sec: 2713.4, 300 sec: 2940.1). Total num frames: 2313216. Throughput: 0: 2701.7. Samples: 2310502. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:48:50,914][21315] Avg episode reward: [(0, '29.230')] [2023-03-03 13:48:50,970][21357] Updated weights for policy 0, policy_version 2260 (0.0008) [2023-03-03 13:48:54,200][21357] Updated weights for policy 0, policy_version 2270 (0.0007) [2023-03-03 13:48:55,913][21315] Fps is (10 sec: 2969.7, 60 sec: 2747.5, 300 sec: 2950.5). Total num frames: 2328576. Throughput: 0: 2703.7. Samples: 2328543. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:48:55,914][21315] Avg episode reward: [(0, '30.783')] [2023-03-03 13:48:57,619][21357] Updated weights for policy 0, policy_version 2280 (0.0008) [2023-03-03 13:49:00,886][21357] Updated weights for policy 0, policy_version 2290 (0.0009) [2023-03-03 13:49:00,911][21315] Fps is (10 sec: 3175.2, 60 sec: 2799.0, 300 sec: 2964.4). Total num frames: 2344960. Throughput: 0: 2772.2. Samples: 2337766. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:49:00,911][21315] Avg episode reward: [(0, '30.035')] [2023-03-03 13:49:04,223][21357] Updated weights for policy 0, policy_version 2300 (0.0007) [2023-03-03 13:49:05,914][21315] Fps is (10 sec: 3174.2, 60 sec: 2798.8, 300 sec: 2967.9). Total num frames: 2360320. Throughput: 0: 2882.2. Samples: 2356611. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:49:05,914][21315] Avg episode reward: [(0, '27.348')] [2023-03-03 13:49:07,559][21357] Updated weights for policy 0, policy_version 2310 (0.0006) [2023-03-03 13:49:10,857][21357] Updated weights for policy 0, policy_version 2320 (0.0007) [2023-03-03 13:49:10,913][21315] Fps is (10 sec: 3071.2, 60 sec: 2816.0, 300 sec: 2971.3). Total num frames: 2375680. Throughput: 0: 2982.3. Samples: 2375014. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:49:10,914][21315] Avg episode reward: [(0, '22.926')] [2023-03-03 13:49:14,111][21357] Updated weights for policy 0, policy_version 2330 (0.0007) [2023-03-03 13:49:15,910][21315] Fps is (10 sec: 3073.1, 60 sec: 2901.5, 300 sec: 2971.3). Total num frames: 2391040. Throughput: 0: 3004.0. Samples: 2384397. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:49:15,911][21315] Avg episode reward: [(0, '24.022')] [2023-03-03 13:49:17,453][21357] Updated weights for policy 0, policy_version 2340 (0.0007) [2023-03-03 13:49:20,909][21315] Fps is (10 sec: 2970.9, 60 sec: 2935.7, 300 sec: 2967.9). Total num frames: 2405376. Throughput: 0: 3010.7. Samples: 2402546. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:49:20,910][21315] Avg episode reward: [(0, '25.787')] [2023-03-03 13:49:20,915][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000002349_2405376.pth... [2023-03-03 13:49:20,998][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000001653_1692672.pth [2023-03-03 13:49:21,209][21357] Updated weights for policy 0, policy_version 2350 (0.0010) [2023-03-03 13:49:24,512][21357] Updated weights for policy 0, policy_version 2360 (0.0007) [2023-03-03 13:49:25,909][21315] Fps is (10 sec: 2970.0, 60 sec: 3003.9, 300 sec: 2978.3). Total num frames: 2420736. Throughput: 0: 2982.3. Samples: 2419998. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:49:25,909][21315] Avg episode reward: [(0, '27.579')] [2023-03-03 13:49:27,813][21357] Updated weights for policy 0, policy_version 2370 (0.0007) [2023-03-03 13:49:30,912][21315] Fps is (10 sec: 2968.6, 60 sec: 2986.7, 300 sec: 2988.7). Total num frames: 2435072. Throughput: 0: 3021.9. Samples: 2429115. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:49:30,913][21315] Avg episode reward: [(0, '31.300')] [2023-03-03 13:49:31,297][21357] Updated weights for policy 0, policy_version 2380 (0.0007) [2023-03-03 13:49:34,887][21357] Updated weights for policy 0, policy_version 2390 (0.0008) [2023-03-03 13:49:35,914][21315] Fps is (10 sec: 2968.2, 60 sec: 3003.5, 300 sec: 2988.7). Total num frames: 2450432. Throughput: 0: 3022.8. Samples: 2446529. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:49:35,915][21315] Avg episode reward: [(0, '29.966')] [2023-03-03 13:49:38,134][21357] Updated weights for policy 0, policy_version 2400 (0.0008) [2023-03-03 13:49:40,914][21315] Fps is (10 sec: 3071.4, 60 sec: 3003.5, 300 sec: 2988.6). Total num frames: 2465792. Throughput: 0: 3037.7. Samples: 2465242. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:49:40,915][21315] Avg episode reward: [(0, '34.169')] [2023-03-03 13:49:41,419][21357] Updated weights for policy 0, policy_version 2410 (0.0007) [2023-03-03 13:49:45,793][21357] Updated weights for policy 0, policy_version 2420 (0.0010) [2023-03-03 13:49:45,916][21315] Fps is (10 sec: 2764.1, 60 sec: 2986.6, 300 sec: 2981.7). Total num frames: 2478080. Throughput: 0: 3014.9. Samples: 2473453. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:49:45,917][21315] Avg episode reward: [(0, '35.575')] [2023-03-03 13:49:50,279][21357] Updated weights for policy 0, policy_version 2430 (0.0008) [2023-03-03 13:49:50,910][21315] Fps is (10 sec: 2356.3, 60 sec: 2935.7, 300 sec: 2967.9). Total num frames: 2489344. Throughput: 0: 2897.2. Samples: 2486975. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-03-03 13:49:50,910][21315] Avg episode reward: [(0, '37.643')] [2023-03-03 13:49:53,781][21357] Updated weights for policy 0, policy_version 2440 (0.0009) [2023-03-03 13:49:55,911][21315] Fps is (10 sec: 2663.8, 60 sec: 2935.6, 300 sec: 2964.4). Total num frames: 2504704. Throughput: 0: 2869.5. Samples: 2504132. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:49:55,911][21315] Avg episode reward: [(0, '35.965')] [2023-03-03 13:49:57,079][21357] Updated weights for policy 0, policy_version 2450 (0.0007) [2023-03-03 13:50:00,331][21357] Updated weights for policy 0, policy_version 2460 (0.0008) [2023-03-03 13:50:00,913][21315] Fps is (10 sec: 3071.0, 60 sec: 2918.3, 300 sec: 2964.4). Total num frames: 2520064. Throughput: 0: 2866.6. Samples: 2513401. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:50:00,913][21315] Avg episode reward: [(0, '29.484')] [2023-03-03 13:50:03,749][21357] Updated weights for policy 0, policy_version 2470 (0.0008) [2023-03-03 13:50:05,913][21315] Fps is (10 sec: 3071.2, 60 sec: 2918.4, 300 sec: 2964.4). Total num frames: 2535424. Throughput: 0: 2875.3. Samples: 2531947. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:50:05,914][21315] Avg episode reward: [(0, '27.830')] [2023-03-03 13:50:07,100][21357] Updated weights for policy 0, policy_version 2480 (0.0007) [2023-03-03 13:50:10,491][21357] Updated weights for policy 0, policy_version 2490 (0.0008) [2023-03-03 13:50:10,911][21315] Fps is (10 sec: 3072.6, 60 sec: 2918.5, 300 sec: 2964.4). Total num frames: 2550784. Throughput: 0: 2892.0. Samples: 2550144. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:50:10,912][21315] Avg episode reward: [(0, '33.537')] [2023-03-03 13:50:13,736][21357] Updated weights for policy 0, policy_version 2500 (0.0007) [2023-03-03 13:50:15,909][21315] Fps is (10 sec: 3073.2, 60 sec: 2918.4, 300 sec: 2964.4). Total num frames: 2566144. Throughput: 0: 2899.7. Samples: 2559593. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:50:15,910][21315] Avg episode reward: [(0, '38.123')] [2023-03-03 13:50:17,147][21357] Updated weights for policy 0, policy_version 2510 (0.0008) [2023-03-03 13:50:20,478][21357] Updated weights for policy 0, policy_version 2520 (0.0007) [2023-03-03 13:50:20,909][21315] Fps is (10 sec: 3072.6, 60 sec: 2935.5, 300 sec: 2960.9). Total num frames: 2581504. Throughput: 0: 2922.8. Samples: 2578043. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-03-03 13:50:20,909][21315] Avg episode reward: [(0, '38.707')] [2023-03-03 13:50:24,095][21357] Updated weights for policy 0, policy_version 2530 (0.0010) [2023-03-03 13:50:25,910][21315] Fps is (10 sec: 2867.0, 60 sec: 2901.3, 300 sec: 2957.5). Total num frames: 2594816. Throughput: 0: 2876.9. Samples: 2594692. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-03-03 13:50:25,912][21315] Avg episode reward: [(0, '33.229')] [2023-03-03 13:50:27,622][21357] Updated weights for policy 0, policy_version 2540 (0.0008) [2023-03-03 13:50:30,912][21315] Fps is (10 sec: 2866.2, 60 sec: 2918.4, 300 sec: 2957.5). Total num frames: 2610176. Throughput: 0: 2891.8. Samples: 2603575. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:50:30,914][21315] Avg episode reward: [(0, '29.335')] [2023-03-03 13:50:31,103][21357] Updated weights for policy 0, policy_version 2550 (0.0007) [2023-03-03 13:50:34,387][21357] Updated weights for policy 0, policy_version 2560 (0.0007) [2023-03-03 13:50:35,913][21315] Fps is (10 sec: 3071.1, 60 sec: 2918.4, 300 sec: 2957.4). Total num frames: 2625536. Throughput: 0: 3004.0. Samples: 2622165. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:50:35,914][21315] Avg episode reward: [(0, '29.259')] [2023-03-03 13:50:37,655][21357] Updated weights for policy 0, policy_version 2570 (0.0007) [2023-03-03 13:50:40,914][21315] Fps is (10 sec: 3071.4, 60 sec: 2918.4, 300 sec: 2960.9). Total num frames: 2640896. Throughput: 0: 3041.1. Samples: 2640993. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:50:40,915][21315] Avg episode reward: [(0, '26.555')] [2023-03-03 13:50:40,918][21357] Updated weights for policy 0, policy_version 2580 (0.0008) [2023-03-03 13:50:44,178][21357] Updated weights for policy 0, policy_version 2590 (0.0008) [2023-03-03 13:50:45,916][21315] Fps is (10 sec: 3071.9, 60 sec: 2969.7, 300 sec: 2957.4). Total num frames: 2656256. Throughput: 0: 3044.5. Samples: 2650403. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:50:45,924][21315] Avg episode reward: [(0, '26.858')] [2023-03-03 13:50:47,931][21357] Updated weights for policy 0, policy_version 2600 (0.0007) [2023-03-03 13:50:50,910][21315] Fps is (10 sec: 3073.2, 60 sec: 3037.8, 300 sec: 2957.5). Total num frames: 2671616. Throughput: 0: 3020.8. Samples: 2667874. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:50:50,911][21315] Avg episode reward: [(0, '27.098')] [2023-03-03 13:50:51,201][21357] Updated weights for policy 0, policy_version 2610 (0.0007) [2023-03-03 13:50:54,470][21357] Updated weights for policy 0, policy_version 2620 (0.0007) [2023-03-03 13:50:55,911][21315] Fps is (10 sec: 2970.3, 60 sec: 3020.8, 300 sec: 2954.0). Total num frames: 2685952. Throughput: 0: 3022.6. Samples: 2686161. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:50:55,913][21315] Avg episode reward: [(0, '29.931')] [2023-03-03 13:50:57,874][21357] Updated weights for policy 0, policy_version 2630 (0.0008) [2023-03-03 13:51:00,915][21315] Fps is (10 sec: 2865.8, 60 sec: 3003.6, 300 sec: 2950.5). Total num frames: 2700288. Throughput: 0: 3016.1. Samples: 2695333. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:51:00,917][21315] Avg episode reward: [(0, '29.041')] [2023-03-03 13:51:01,966][21357] Updated weights for policy 0, policy_version 2640 (0.0009) [2023-03-03 13:51:05,913][21315] Fps is (10 sec: 2661.8, 60 sec: 2952.5, 300 sec: 2940.1). Total num frames: 2712576. Throughput: 0: 2928.5. Samples: 2709838. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:51:05,914][21315] Avg episode reward: [(0, '34.816')] [2023-03-03 13:51:06,120][21357] Updated weights for policy 0, policy_version 2650 (0.0009) [2023-03-03 13:51:10,117][21357] Updated weights for policy 0, policy_version 2660 (0.0012) [2023-03-03 13:51:10,912][21315] Fps is (10 sec: 2560.8, 60 sec: 2918.3, 300 sec: 2933.2). Total num frames: 2725888. Throughput: 0: 2901.1. Samples: 2725246. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:51:10,913][21315] Avg episode reward: [(0, '34.556')] [2023-03-03 13:51:14,207][21357] Updated weights for policy 0, policy_version 2670 (0.0009) [2023-03-03 13:51:15,910][21315] Fps is (10 sec: 2561.0, 60 sec: 2867.2, 300 sec: 2922.8). Total num frames: 2738176. Throughput: 0: 2875.6. Samples: 2732970. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:51:15,911][21315] Avg episode reward: [(0, '37.494')] [2023-03-03 13:51:18,186][21357] Updated weights for policy 0, policy_version 2680 (0.0010) [2023-03-03 13:51:20,909][21315] Fps is (10 sec: 2560.8, 60 sec: 2833.1, 300 sec: 2915.8). Total num frames: 2751488. Throughput: 0: 2797.3. Samples: 2748033. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:51:20,909][21315] Avg episode reward: [(0, '37.714')] [2023-03-03 13:51:20,915][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000002687_2751488.pth... [2023-03-03 13:51:21,001][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000002012_2060288.pth [2023-03-03 13:51:21,789][21357] Updated weights for policy 0, policy_version 2690 (0.0011) [2023-03-03 13:51:25,021][21357] Updated weights for policy 0, policy_version 2700 (0.0007) [2023-03-03 13:51:25,909][21315] Fps is (10 sec: 2867.4, 60 sec: 2867.3, 300 sec: 2915.8). Total num frames: 2766848. Throughput: 0: 2793.2. Samples: 2766672. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:51:25,909][21315] Avg episode reward: [(0, '36.030')] [2023-03-03 13:51:28,321][21357] Updated weights for policy 0, policy_version 2710 (0.0007) [2023-03-03 13:51:30,909][21315] Fps is (10 sec: 3071.8, 60 sec: 2867.3, 300 sec: 2915.8). Total num frames: 2782208. Throughput: 0: 2790.0. Samples: 2775942. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:51:30,910][21315] Avg episode reward: [(0, '35.666')] [2023-03-03 13:51:31,701][21357] Updated weights for policy 0, policy_version 2720 (0.0008) [2023-03-03 13:51:34,951][21357] Updated weights for policy 0, policy_version 2730 (0.0007) [2023-03-03 13:51:35,912][21315] Fps is (10 sec: 3173.2, 60 sec: 2884.3, 300 sec: 2919.2). Total num frames: 2798592. Throughput: 0: 2813.2. Samples: 2794475. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:51:35,913][21315] Avg episode reward: [(0, '33.202')] [2023-03-03 13:51:38,184][21357] Updated weights for policy 0, policy_version 2740 (0.0007) [2023-03-03 13:51:40,913][21315] Fps is (10 sec: 3071.0, 60 sec: 2867.3, 300 sec: 2915.8). Total num frames: 2812928. Throughput: 0: 2820.8. Samples: 2813101. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:51:40,914][21315] Avg episode reward: [(0, '31.725')] [2023-03-03 13:51:41,608][21357] Updated weights for policy 0, policy_version 2750 (0.0008) [2023-03-03 13:51:44,952][21357] Updated weights for policy 0, policy_version 2760 (0.0008) [2023-03-03 13:51:45,914][21315] Fps is (10 sec: 2969.1, 60 sec: 2867.2, 300 sec: 2912.3). Total num frames: 2828288. Throughput: 0: 2820.5. Samples: 2822250. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:51:45,915][21315] Avg episode reward: [(0, '28.503')] [2023-03-03 13:51:48,396][21357] Updated weights for policy 0, policy_version 2770 (0.0007) [2023-03-03 13:51:50,913][21315] Fps is (10 sec: 3071.9, 60 sec: 2867.1, 300 sec: 2912.3). Total num frames: 2843648. Throughput: 0: 2899.9. Samples: 2840333. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:51:50,914][21315] Avg episode reward: [(0, '24.833')] [2023-03-03 13:51:51,697][21357] Updated weights for policy 0, policy_version 2780 (0.0008) [2023-03-03 13:51:54,933][21357] Updated weights for policy 0, policy_version 2790 (0.0007) [2023-03-03 13:51:55,911][21315] Fps is (10 sec: 3072.8, 60 sec: 2884.3, 300 sec: 2912.3). Total num frames: 2859008. Throughput: 0: 2980.0. Samples: 2859344. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:51:55,912][21315] Avg episode reward: [(0, '35.790')] [2023-03-03 13:51:58,162][21357] Updated weights for policy 0, policy_version 2800 (0.0009) [2023-03-03 13:52:00,912][21315] Fps is (10 sec: 3174.7, 60 sec: 2918.6, 300 sec: 2919.3). Total num frames: 2875392. Throughput: 0: 3014.5. Samples: 2868633. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:52:00,913][21315] Avg episode reward: [(0, '37.904')] [2023-03-03 13:52:01,588][21357] Updated weights for policy 0, policy_version 2810 (0.0007) [2023-03-03 13:52:04,851][21357] Updated weights for policy 0, policy_version 2820 (0.0007) [2023-03-03 13:52:05,913][21315] Fps is (10 sec: 3173.8, 60 sec: 2969.6, 300 sec: 2915.8). Total num frames: 2890752. Throughput: 0: 3088.9. Samples: 2887047. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:52:05,914][21315] Avg episode reward: [(0, '40.737')] [2023-03-03 13:52:08,157][21357] Updated weights for policy 0, policy_version 2830 (0.0006) [2023-03-03 13:52:10,913][21315] Fps is (10 sec: 3071.7, 60 sec: 3003.7, 300 sec: 2922.7). Total num frames: 2906112. Throughput: 0: 3086.4. Samples: 2905575. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:52:10,913][21315] Avg episode reward: [(0, '28.844')] [2023-03-03 13:52:11,557][21357] Updated weights for policy 0, policy_version 2840 (0.0008) [2023-03-03 13:52:14,909][21357] Updated weights for policy 0, policy_version 2850 (0.0007) [2023-03-03 13:52:15,913][21315] Fps is (10 sec: 2969.5, 60 sec: 3037.7, 300 sec: 2919.2). Total num frames: 2920448. Throughput: 0: 3078.3. Samples: 2914480. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:52:15,914][21315] Avg episode reward: [(0, '26.529')] [2023-03-03 13:52:18,427][21357] Updated weights for policy 0, policy_version 2860 (0.0007) [2023-03-03 13:52:20,915][21315] Fps is (10 sec: 2764.5, 60 sec: 3037.6, 300 sec: 2915.8). Total num frames: 2933760. Throughput: 0: 3046.5. Samples: 2931572. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:52:20,927][21315] Avg episode reward: [(0, '26.846')] [2023-03-03 13:52:22,574][21357] Updated weights for policy 0, policy_version 2870 (0.0009) [2023-03-03 13:52:25,913][21315] Fps is (10 sec: 2560.1, 60 sec: 2986.5, 300 sec: 2905.4). Total num frames: 2946048. Throughput: 0: 2961.4. Samples: 2946363. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:52:25,915][21315] Avg episode reward: [(0, '28.480')] [2023-03-03 13:52:26,685][21357] Updated weights for policy 0, policy_version 2880 (0.0010) [2023-03-03 13:52:30,052][21357] Updated weights for policy 0, policy_version 2890 (0.0007) [2023-03-03 13:52:30,913][21315] Fps is (10 sec: 2662.7, 60 sec: 2969.4, 300 sec: 2898.4). Total num frames: 2960384. Throughput: 0: 2953.6. Samples: 2955160. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:52:30,916][21315] Avg episode reward: [(0, '27.610')] [2023-03-03 13:52:34,747][21357] Updated weights for policy 0, policy_version 2900 (0.0011) [2023-03-03 13:52:35,913][21315] Fps is (10 sec: 2560.0, 60 sec: 2884.2, 300 sec: 2884.6). Total num frames: 2971648. Throughput: 0: 2872.1. Samples: 2969580. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:52:35,916][21315] Avg episode reward: [(0, '28.073')] [2023-03-03 13:52:38,265][21357] Updated weights for policy 0, policy_version 2910 (0.0008) [2023-03-03 13:52:40,912][21315] Fps is (10 sec: 2662.6, 60 sec: 2901.4, 300 sec: 2884.6). Total num frames: 2987008. Throughput: 0: 2839.7. Samples: 2987133. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:52:40,912][21315] Avg episode reward: [(0, '28.775')] [2023-03-03 13:52:41,764][21357] Updated weights for policy 0, policy_version 2920 (0.0008) [2023-03-03 13:52:45,268][21357] Updated weights for policy 0, policy_version 2930 (0.0007) [2023-03-03 13:52:45,912][21315] Fps is (10 sec: 2970.1, 60 sec: 2884.4, 300 sec: 2884.5). Total num frames: 3001344. Throughput: 0: 2823.3. Samples: 2995678. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:52:45,914][21315] Avg episode reward: [(0, '30.601')] [2023-03-03 13:52:49,798][21357] Updated weights for policy 0, policy_version 2940 (0.0010) [2023-03-03 13:52:50,909][21315] Fps is (10 sec: 2560.8, 60 sec: 2816.2, 300 sec: 2877.6). Total num frames: 3012608. Throughput: 0: 2741.5. Samples: 3010402. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:52:50,911][21315] Avg episode reward: [(0, '34.636')] [2023-03-03 13:52:54,517][21357] Updated weights for policy 0, policy_version 2950 (0.0010) [2023-03-03 13:52:55,910][21315] Fps is (10 sec: 2253.2, 60 sec: 2747.8, 300 sec: 2870.7). Total num frames: 3023872. Throughput: 0: 2623.5. Samples: 3023622. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:52:55,911][21315] Avg episode reward: [(0, '35.242')] [2023-03-03 13:52:59,134][21357] Updated weights for policy 0, policy_version 2960 (0.0011) [2023-03-03 13:53:00,913][21315] Fps is (10 sec: 2149.5, 60 sec: 2645.3, 300 sec: 2853.3). Total num frames: 3034112. Throughput: 0: 2568.8. Samples: 3030074. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-03-03 13:53:00,914][21315] Avg episode reward: [(0, '37.724')] [2023-03-03 13:53:03,698][21357] Updated weights for policy 0, policy_version 2970 (0.0012) [2023-03-03 13:53:05,913][21315] Fps is (10 sec: 2252.1, 60 sec: 2594.1, 300 sec: 2846.4). Total num frames: 3046400. Throughput: 0: 2495.6. Samples: 3043872. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:53:05,915][21315] Avg episode reward: [(0, '38.137')] [2023-03-03 13:53:07,484][21357] Updated weights for policy 0, policy_version 2980 (0.0008) [2023-03-03 13:53:10,905][21357] Updated weights for policy 0, policy_version 2990 (0.0007) [2023-03-03 13:53:10,910][21315] Fps is (10 sec: 2765.7, 60 sec: 2594.3, 300 sec: 2863.8). Total num frames: 3061760. Throughput: 0: 2546.7. Samples: 3060957. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:53:10,911][21315] Avg episode reward: [(0, '42.807')] [2023-03-03 13:53:14,618][21357] Updated weights for policy 0, policy_version 3000 (0.0007) [2023-03-03 13:53:15,912][21315] Fps is (10 sec: 2765.1, 60 sec: 2560.1, 300 sec: 2863.7). Total num frames: 3074048. Throughput: 0: 2539.4. Samples: 3069432. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:53:15,914][21315] Avg episode reward: [(0, '45.341')] [2023-03-03 13:53:18,429][21357] Updated weights for policy 0, policy_version 3010 (0.0009) [2023-03-03 13:53:20,911][21315] Fps is (10 sec: 2764.3, 60 sec: 2594.2, 300 sec: 2877.6). Total num frames: 3089408. Throughput: 0: 2586.9. Samples: 3085985. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:53:20,912][21315] Avg episode reward: [(0, '42.915')] [2023-03-03 13:53:20,918][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000003017_3089408.pth... [2023-03-03 13:53:20,982][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000002349_2405376.pth [2023-03-03 13:53:21,855][21357] Updated weights for policy 0, policy_version 3020 (0.0008) [2023-03-03 13:53:25,560][21357] Updated weights for policy 0, policy_version 3030 (0.0009) [2023-03-03 13:53:25,910][21315] Fps is (10 sec: 2867.9, 60 sec: 2611.4, 300 sec: 2870.7). Total num frames: 3102720. Throughput: 0: 2576.8. Samples: 3103083. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:53:25,911][21315] Avg episode reward: [(0, '33.064')] [2023-03-03 13:53:29,220][21357] Updated weights for policy 0, policy_version 3040 (0.0009) [2023-03-03 13:53:30,912][21315] Fps is (10 sec: 2662.3, 60 sec: 2594.2, 300 sec: 2867.2). Total num frames: 3116032. Throughput: 0: 2575.2. Samples: 3111561. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:53:30,915][21315] Avg episode reward: [(0, '31.019')] [2023-03-03 13:53:33,721][21357] Updated weights for policy 0, policy_version 3050 (0.0011) [2023-03-03 13:53:35,913][21315] Fps is (10 sec: 2456.8, 60 sec: 2594.1, 300 sec: 2853.3). Total num frames: 3127296. Throughput: 0: 2552.3. Samples: 3125264. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:53:35,914][21315] Avg episode reward: [(0, '30.524')] [2023-03-03 13:53:38,327][21357] Updated weights for policy 0, policy_version 3060 (0.0009) [2023-03-03 13:53:40,911][21315] Fps is (10 sec: 2355.3, 60 sec: 2543.0, 300 sec: 2849.9). Total num frames: 3139584. Throughput: 0: 2585.0. Samples: 3139951. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:53:40,912][21315] Avg episode reward: [(0, '31.300')] [2023-03-03 13:53:41,992][21357] Updated weights for policy 0, policy_version 3070 (0.0008) [2023-03-03 13:53:45,801][21357] Updated weights for policy 0, policy_version 3080 (0.0009) [2023-03-03 13:53:45,913][21315] Fps is (10 sec: 2662.4, 60 sec: 2542.9, 300 sec: 2849.8). Total num frames: 3153920. Throughput: 0: 2624.5. Samples: 3148178. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:53:45,914][21315] Avg episode reward: [(0, '31.395')] [2023-03-03 13:53:50,243][21357] Updated weights for policy 0, policy_version 3090 (0.0009) [2023-03-03 13:53:50,911][21315] Fps is (10 sec: 2662.5, 60 sec: 2559.9, 300 sec: 2839.5). Total num frames: 3166208. Throughput: 0: 2643.4. Samples: 3162819. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:53:50,912][21315] Avg episode reward: [(0, '30.941')] [2023-03-03 13:53:53,498][21357] Updated weights for policy 0, policy_version 3100 (0.0006) [2023-03-03 13:53:55,913][21315] Fps is (10 sec: 2764.8, 60 sec: 2628.1, 300 sec: 2835.9). Total num frames: 3181568. Throughput: 0: 2666.5. Samples: 3180960. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:53:55,914][21315] Avg episode reward: [(0, '34.064')] [2023-03-03 13:53:56,809][21357] Updated weights for policy 0, policy_version 3110 (0.0008) [2023-03-03 13:54:00,778][21357] Updated weights for policy 0, policy_version 3120 (0.0011) [2023-03-03 13:54:00,912][21315] Fps is (10 sec: 2866.8, 60 sec: 2679.5, 300 sec: 2829.0). Total num frames: 3194880. Throughput: 0: 2681.0. Samples: 3190078. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:54:00,913][21315] Avg episode reward: [(0, '36.481')] [2023-03-03 13:54:05,066][21357] Updated weights for policy 0, policy_version 3130 (0.0010) [2023-03-03 13:54:05,912][21315] Fps is (10 sec: 2457.7, 60 sec: 2662.4, 300 sec: 2815.1). Total num frames: 3206144. Throughput: 0: 2628.4. Samples: 3204266. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:54:05,913][21315] Avg episode reward: [(0, '35.763')] [2023-03-03 13:54:09,367][21357] Updated weights for policy 0, policy_version 3140 (0.0008) [2023-03-03 13:54:10,912][21315] Fps is (10 sec: 2355.2, 60 sec: 2611.1, 300 sec: 2804.7). Total num frames: 3218432. Throughput: 0: 2561.0. Samples: 3218336. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:54:10,914][21315] Avg episode reward: [(0, '33.849')] [2023-03-03 13:54:13,782][21357] Updated weights for policy 0, policy_version 3150 (0.0009) [2023-03-03 13:54:15,911][21315] Fps is (10 sec: 2355.5, 60 sec: 2594.2, 300 sec: 2794.3). Total num frames: 3229696. Throughput: 0: 2531.3. Samples: 3225468. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:54:15,912][21315] Avg episode reward: [(0, '34.330')] [2023-03-03 13:54:18,211][21357] Updated weights for policy 0, policy_version 3160 (0.0008) [2023-03-03 13:54:20,910][21315] Fps is (10 sec: 2253.3, 60 sec: 2525.9, 300 sec: 2780.4). Total num frames: 3240960. Throughput: 0: 2538.3. Samples: 3239479. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:54:20,913][21315] Avg episode reward: [(0, '31.709')] [2023-03-03 13:54:23,254][21357] Updated weights for policy 0, policy_version 3170 (0.0008) [2023-03-03 13:54:25,910][21315] Fps is (10 sec: 2355.5, 60 sec: 2508.8, 300 sec: 2773.5). Total num frames: 3253248. Throughput: 0: 2505.4. Samples: 3252689. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:54:25,911][21315] Avg episode reward: [(0, '32.242')] [2023-03-03 13:54:27,028][21357] Updated weights for policy 0, policy_version 3180 (0.0010) [2023-03-03 13:54:30,539][21357] Updated weights for policy 0, policy_version 3190 (0.0009) [2023-03-03 13:54:30,913][21315] Fps is (10 sec: 2559.3, 60 sec: 2508.8, 300 sec: 2766.5). Total num frames: 3266560. Throughput: 0: 2506.5. Samples: 3260969. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:54:30,914][21315] Avg episode reward: [(0, '28.474')] [2023-03-03 13:54:34,292][21357] Updated weights for policy 0, policy_version 3200 (0.0008) [2023-03-03 13:54:35,914][21315] Fps is (10 sec: 2763.8, 60 sec: 2560.0, 300 sec: 2763.1). Total num frames: 3280896. Throughput: 0: 2556.9. Samples: 3277886. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:54:35,914][21315] Avg episode reward: [(0, '27.949')] [2023-03-03 13:54:37,860][21357] Updated weights for policy 0, policy_version 3210 (0.0007) [2023-03-03 13:54:40,910][21315] Fps is (10 sec: 2868.1, 60 sec: 2594.2, 300 sec: 2770.1). Total num frames: 3295232. Throughput: 0: 2534.3. Samples: 3294994. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:54:40,910][21315] Avg episode reward: [(0, '34.271')] [2023-03-03 13:54:41,520][21357] Updated weights for policy 0, policy_version 3220 (0.0008) [2023-03-03 13:54:45,165][21357] Updated weights for policy 0, policy_version 3230 (0.0007) [2023-03-03 13:54:45,911][21315] Fps is (10 sec: 2867.9, 60 sec: 2594.2, 300 sec: 2780.4). Total num frames: 3309568. Throughput: 0: 2514.5. Samples: 3303229. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:54:45,912][21315] Avg episode reward: [(0, '36.713')] [2023-03-03 13:54:48,509][21357] Updated weights for policy 0, policy_version 3240 (0.0007) [2023-03-03 13:54:50,911][21315] Fps is (10 sec: 2969.3, 60 sec: 2645.3, 300 sec: 2780.4). Total num frames: 3324928. Throughput: 0: 2599.6. Samples: 3321244. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:54:50,911][21315] Avg episode reward: [(0, '36.032')] [2023-03-03 13:54:51,792][21357] Updated weights for policy 0, policy_version 3250 (0.0008) [2023-03-03 13:54:55,241][21357] Updated weights for policy 0, policy_version 3260 (0.0008) [2023-03-03 13:54:55,913][21315] Fps is (10 sec: 2969.1, 60 sec: 2628.3, 300 sec: 2776.9). Total num frames: 3339264. Throughput: 0: 2688.0. Samples: 3339299. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:54:55,913][21315] Avg episode reward: [(0, '34.051')] [2023-03-03 13:54:58,851][21357] Updated weights for policy 0, policy_version 3270 (0.0009) [2023-03-03 13:55:00,910][21315] Fps is (10 sec: 2867.4, 60 sec: 2645.4, 300 sec: 2773.5). Total num frames: 3353600. Throughput: 0: 2718.8. Samples: 3347810. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:55:00,911][21315] Avg episode reward: [(0, '29.409')] [2023-03-03 13:55:02,355][21357] Updated weights for policy 0, policy_version 3280 (0.0007) [2023-03-03 13:55:05,794][21357] Updated weights for policy 0, policy_version 3290 (0.0007) [2023-03-03 13:55:05,912][21315] Fps is (10 sec: 2969.8, 60 sec: 2713.6, 300 sec: 2773.5). Total num frames: 3368960. Throughput: 0: 2797.2. Samples: 3365360. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:55:05,913][21315] Avg episode reward: [(0, '31.629')] [2023-03-03 13:55:09,429][21357] Updated weights for policy 0, policy_version 3300 (0.0006) [2023-03-03 13:55:10,909][21315] Fps is (10 sec: 2970.0, 60 sec: 2747.9, 300 sec: 2770.0). Total num frames: 3383296. Throughput: 0: 2891.0. Samples: 3382780. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:55:10,910][21315] Avg episode reward: [(0, '31.457')] [2023-03-03 13:55:13,241][21357] Updated weights for policy 0, policy_version 3310 (0.0010) [2023-03-03 13:55:15,913][21315] Fps is (10 sec: 2764.5, 60 sec: 2781.8, 300 sec: 2763.0). Total num frames: 3396608. Throughput: 0: 2882.7. Samples: 3390690. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:55:15,915][21315] Avg episode reward: [(0, '40.514')] [2023-03-03 13:55:16,635][21357] Updated weights for policy 0, policy_version 3320 (0.0010) [2023-03-03 13:55:20,030][21357] Updated weights for policy 0, policy_version 3330 (0.0007) [2023-03-03 13:55:20,913][21315] Fps is (10 sec: 2866.1, 60 sec: 2850.0, 300 sec: 2770.0). Total num frames: 3411968. Throughput: 0: 2913.5. Samples: 3408992. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:55:20,913][21315] Avg episode reward: [(0, '47.993')] [2023-03-03 13:55:20,999][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000003333_3412992.pth... [2023-03-03 13:55:21,081][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000002687_2751488.pth [2023-03-03 13:55:23,342][21357] Updated weights for policy 0, policy_version 3340 (0.0007) [2023-03-03 13:55:25,913][21315] Fps is (10 sec: 3072.2, 60 sec: 2901.2, 300 sec: 2770.0). Total num frames: 3427328. Throughput: 0: 2938.5. Samples: 3427235. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:55:25,915][21315] Avg episode reward: [(0, '56.299')] [2023-03-03 13:55:26,642][21357] Updated weights for policy 0, policy_version 3350 (0.0007) [2023-03-03 13:55:30,164][21357] Updated weights for policy 0, policy_version 3360 (0.0010) [2023-03-03 13:55:30,920][21315] Fps is (10 sec: 3069.9, 60 sec: 2935.1, 300 sec: 2769.9). Total num frames: 3442688. Throughput: 0: 2951.4. Samples: 3436066. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:55:30,921][21315] Avg episode reward: [(0, '54.585')] [2023-03-03 13:55:33,593][21357] Updated weights for policy 0, policy_version 3370 (0.0007) [2023-03-03 13:55:35,912][21315] Fps is (10 sec: 3072.2, 60 sec: 2952.6, 300 sec: 2770.0). Total num frames: 3458048. Throughput: 0: 2955.4. Samples: 3454243. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:55:35,913][21315] Avg episode reward: [(0, '67.133')] [2023-03-03 13:55:36,914][21357] Updated weights for policy 0, policy_version 3380 (0.0009) [2023-03-03 13:55:40,167][21357] Updated weights for policy 0, policy_version 3390 (0.0007) [2023-03-03 13:55:40,911][21315] Fps is (10 sec: 3074.8, 60 sec: 2969.6, 300 sec: 2770.0). Total num frames: 3473408. Throughput: 0: 2964.6. Samples: 3472700. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:55:40,911][21315] Avg episode reward: [(0, '65.254')] [2023-03-03 13:55:43,585][21357] Updated weights for policy 0, policy_version 3400 (0.0007) [2023-03-03 13:55:45,911][21315] Fps is (10 sec: 3072.5, 60 sec: 2986.7, 300 sec: 2770.0). Total num frames: 3488768. Throughput: 0: 2977.2. Samples: 3481785. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:55:45,911][21315] Avg episode reward: [(0, '68.896')] [2023-03-03 13:55:46,929][21357] Updated weights for policy 0, policy_version 3410 (0.0007) [2023-03-03 13:55:50,317][21357] Updated weights for policy 0, policy_version 3420 (0.0008) [2023-03-03 13:55:50,913][21315] Fps is (10 sec: 2969.0, 60 sec: 2969.5, 300 sec: 2770.0). Total num frames: 3503104. Throughput: 0: 2999.8. Samples: 3500350. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:55:50,915][21315] Avg episode reward: [(0, '61.310')] [2023-03-03 13:55:53,830][21357] Updated weights for policy 0, policy_version 3430 (0.0007) [2023-03-03 13:55:55,909][21315] Fps is (10 sec: 2867.5, 60 sec: 2969.8, 300 sec: 2770.1). Total num frames: 3517440. Throughput: 0: 2995.4. Samples: 3517573. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:55:55,910][21315] Avg episode reward: [(0, '59.036')] [2023-03-03 13:55:57,269][21357] Updated weights for policy 0, policy_version 3440 (0.0008) [2023-03-03 13:56:00,733][21357] Updated weights for policy 0, policy_version 3450 (0.0008) [2023-03-03 13:56:00,910][21315] Fps is (10 sec: 2970.5, 60 sec: 2986.7, 300 sec: 2780.5). Total num frames: 3532800. Throughput: 0: 3022.0. Samples: 3526668. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:56:00,910][21315] Avg episode reward: [(0, '67.842')] [2023-03-03 13:56:04,123][21357] Updated weights for policy 0, policy_version 3460 (0.0007) [2023-03-03 13:56:05,912][21315] Fps is (10 sec: 3071.2, 60 sec: 2986.7, 300 sec: 2787.4). Total num frames: 3548160. Throughput: 0: 3013.4. Samples: 3544594. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:56:05,913][21315] Avg episode reward: [(0, '90.302')] [2023-03-03 13:56:05,915][21356] Saving new best policy, reward=90.302! [2023-03-03 13:56:07,578][21357] Updated weights for policy 0, policy_version 3470 (0.0008) [2023-03-03 13:56:10,914][21315] Fps is (10 sec: 2968.3, 60 sec: 2986.4, 300 sec: 2794.3). Total num frames: 3562496. Throughput: 0: 3009.5. Samples: 3562668. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:56:10,915][21315] Avg episode reward: [(0, '100.831')] [2023-03-03 13:56:10,945][21356] Saving new best policy, reward=100.831! [2023-03-03 13:56:10,947][21357] Updated weights for policy 0, policy_version 3480 (0.0008) [2023-03-03 13:56:14,399][21357] Updated weights for policy 0, policy_version 3490 (0.0007) [2023-03-03 13:56:15,913][21315] Fps is (10 sec: 2969.4, 60 sec: 3020.8, 300 sec: 2801.2). Total num frames: 3577856. Throughput: 0: 3016.5. Samples: 3571787. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:56:15,914][21315] Avg episode reward: [(0, '103.193')] [2023-03-03 13:56:15,915][21356] Saving new best policy, reward=103.193! [2023-03-03 13:56:18,057][21357] Updated weights for policy 0, policy_version 3500 (0.0008) [2023-03-03 13:56:20,915][21315] Fps is (10 sec: 2764.5, 60 sec: 2969.5, 300 sec: 2790.8). Total num frames: 3590144. Throughput: 0: 2958.7. Samples: 3587391. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:56:20,916][21315] Avg episode reward: [(0, '105.636')] [2023-03-03 13:56:21,021][21356] Saving new best policy, reward=105.636! [2023-03-03 13:56:22,062][21357] Updated weights for policy 0, policy_version 3510 (0.0011) [2023-03-03 13:56:25,377][21357] Updated weights for policy 0, policy_version 3520 (0.0010) [2023-03-03 13:56:25,909][21315] Fps is (10 sec: 2765.7, 60 sec: 2969.8, 300 sec: 2790.8). Total num frames: 3605504. Throughput: 0: 2945.2. Samples: 3605231. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:56:25,910][21315] Avg episode reward: [(0, '114.438')] [2023-03-03 13:56:25,992][21356] Saving new best policy, reward=114.438! [2023-03-03 13:56:28,635][21357] Updated weights for policy 0, policy_version 3530 (0.0007) [2023-03-03 13:56:30,913][21315] Fps is (10 sec: 3072.6, 60 sec: 2969.9, 300 sec: 2787.4). Total num frames: 3620864. Throughput: 0: 2953.0. Samples: 3614679. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:56:30,914][21315] Avg episode reward: [(0, '121.338')] [2023-03-03 13:56:31,067][21356] Saving new best policy, reward=121.338! [2023-03-03 13:56:32,015][21357] Updated weights for policy 0, policy_version 3540 (0.0007) [2023-03-03 13:56:35,274][21357] Updated weights for policy 0, policy_version 3550 (0.0009) [2023-03-03 13:56:35,913][21315] Fps is (10 sec: 3070.9, 60 sec: 2969.6, 300 sec: 2790.8). Total num frames: 3636224. Throughput: 0: 2948.5. Samples: 3633034. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:56:35,914][21315] Avg episode reward: [(0, '107.303')] [2023-03-03 13:56:38,552][21357] Updated weights for policy 0, policy_version 3560 (0.0007) [2023-03-03 13:56:40,912][21315] Fps is (10 sec: 3174.8, 60 sec: 2986.6, 300 sec: 2794.3). Total num frames: 3652608. Throughput: 0: 2993.0. Samples: 3652263. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:56:40,914][21315] Avg episode reward: [(0, '71.237')] [2023-03-03 13:56:41,782][21357] Updated weights for policy 0, policy_version 3570 (0.0007) [2023-03-03 13:56:45,051][21357] Updated weights for policy 0, policy_version 3580 (0.0008) [2023-03-03 13:56:45,912][21315] Fps is (10 sec: 3174.7, 60 sec: 2986.6, 300 sec: 2794.3). Total num frames: 3667968. Throughput: 0: 3003.0. Samples: 3661810. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:56:45,913][21315] Avg episode reward: [(0, '63.187')] [2023-03-03 13:56:48,313][21357] Updated weights for policy 0, policy_version 3590 (0.0008) [2023-03-03 13:56:50,910][21315] Fps is (10 sec: 3072.5, 60 sec: 3003.9, 300 sec: 2794.3). Total num frames: 3683328. Throughput: 0: 3007.0. Samples: 3679901. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:56:50,910][21315] Avg episode reward: [(0, '86.527')] [2023-03-03 13:56:51,787][21357] Updated weights for policy 0, policy_version 3600 (0.0008) [2023-03-03 13:56:55,097][21357] Updated weights for policy 0, policy_version 3610 (0.0007) [2023-03-03 13:56:55,910][21315] Fps is (10 sec: 3072.4, 60 sec: 3020.7, 300 sec: 2790.9). Total num frames: 3698688. Throughput: 0: 3015.8. Samples: 3698368. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:56:55,911][21315] Avg episode reward: [(0, '79.976')] [2023-03-03 13:56:58,286][21357] Updated weights for policy 0, policy_version 3620 (0.0007) [2023-03-03 13:57:00,909][21315] Fps is (10 sec: 3174.7, 60 sec: 3037.9, 300 sec: 2794.3). Total num frames: 3715072. Throughput: 0: 3027.1. Samples: 3707996. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:57:00,909][21315] Avg episode reward: [(0, '77.638')] [2023-03-03 13:57:01,471][21357] Updated weights for policy 0, policy_version 3630 (0.0006) [2023-03-03 13:57:04,665][21357] Updated weights for policy 0, policy_version 3640 (0.0007) [2023-03-03 13:57:05,909][21315] Fps is (10 sec: 3174.9, 60 sec: 3038.0, 300 sec: 2794.3). Total num frames: 3730432. Throughput: 0: 3107.0. Samples: 3727188. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:57:05,910][21315] Avg episode reward: [(0, '39.917')] [2023-03-03 13:57:07,885][21357] Updated weights for policy 0, policy_version 3650 (0.0006) [2023-03-03 13:57:10,913][21315] Fps is (10 sec: 3173.2, 60 sec: 3072.1, 300 sec: 2801.3). Total num frames: 3746816. Throughput: 0: 3131.5. Samples: 3746158. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:57:10,914][21315] Avg episode reward: [(0, '46.780')] [2023-03-03 13:57:11,222][21357] Updated weights for policy 0, policy_version 3660 (0.0007) [2023-03-03 13:57:14,595][21357] Updated weights for policy 0, policy_version 3670 (0.0007) [2023-03-03 13:57:15,913][21315] Fps is (10 sec: 3070.8, 60 sec: 3054.9, 300 sec: 2804.7). Total num frames: 3761152. Throughput: 0: 3125.0. Samples: 3755305. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:57:15,914][21315] Avg episode reward: [(0, '64.175')] [2023-03-03 13:57:18,027][21357] Updated weights for policy 0, policy_version 3680 (0.0007) [2023-03-03 13:57:20,914][21315] Fps is (10 sec: 2867.0, 60 sec: 3089.1, 300 sec: 2811.7). Total num frames: 3775488. Throughput: 0: 3098.7. Samples: 3772476. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:57:20,915][21315] Avg episode reward: [(0, '71.203')] [2023-03-03 13:57:20,928][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000003688_3776512.pth... [2023-03-03 13:57:21,006][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000003017_3089408.pth [2023-03-03 13:57:21,587][21357] Updated weights for policy 0, policy_version 3690 (0.0007) [2023-03-03 13:57:24,928][21357] Updated weights for policy 0, policy_version 3700 (0.0007) [2023-03-03 13:57:25,911][21315] Fps is (10 sec: 2970.2, 60 sec: 3089.0, 300 sec: 2815.1). Total num frames: 3790848. Throughput: 0: 3079.2. Samples: 3790825. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-03-03 13:57:25,913][21315] Avg episode reward: [(0, '88.465')] [2023-03-03 13:57:28,279][21357] Updated weights for policy 0, policy_version 3710 (0.0009) [2023-03-03 13:57:30,910][21315] Fps is (10 sec: 3175.5, 60 sec: 3106.3, 300 sec: 2832.5). Total num frames: 3807232. Throughput: 0: 3072.9. Samples: 3800086. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:57:30,911][21315] Avg episode reward: [(0, '77.701')] [2023-03-03 13:57:31,476][21357] Updated weights for policy 0, policy_version 3720 (0.0007) [2023-03-03 13:57:34,659][21357] Updated weights for policy 0, policy_version 3730 (0.0007) [2023-03-03 13:57:35,912][21315] Fps is (10 sec: 3173.9, 60 sec: 3106.2, 300 sec: 2832.5). Total num frames: 3822592. Throughput: 0: 3097.0. Samples: 3819274. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:57:35,913][21315] Avg episode reward: [(0, '84.592')] [2023-03-03 13:57:37,976][21357] Updated weights for policy 0, policy_version 3740 (0.0006) [2023-03-03 13:57:40,909][21315] Fps is (10 sec: 3174.7, 60 sec: 3106.3, 300 sec: 2839.5). Total num frames: 3838976. Throughput: 0: 3106.4. Samples: 3838150. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:57:40,909][21315] Avg episode reward: [(0, '70.620')] [2023-03-03 13:57:41,275][21357] Updated weights for policy 0, policy_version 3750 (0.0007) [2023-03-03 13:57:44,480][21357] Updated weights for policy 0, policy_version 3760 (0.0007) [2023-03-03 13:57:45,910][21315] Fps is (10 sec: 3175.2, 60 sec: 3106.2, 300 sec: 2853.3). Total num frames: 3854336. Throughput: 0: 3103.1. Samples: 3847637. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:57:45,910][21315] Avg episode reward: [(0, '64.801')] [2023-03-03 13:57:47,726][21357] Updated weights for policy 0, policy_version 3770 (0.0006) [2023-03-03 13:57:50,913][21315] Fps is (10 sec: 3070.9, 60 sec: 3106.0, 300 sec: 2867.2). Total num frames: 3869696. Throughput: 0: 3090.4. Samples: 3866270. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 13:57:50,913][21315] Avg episode reward: [(0, '42.811')] [2023-03-03 13:57:50,962][21357] Updated weights for policy 0, policy_version 3780 (0.0008) [2023-03-03 13:57:54,213][21357] Updated weights for policy 0, policy_version 3790 (0.0007) [2023-03-03 13:57:55,912][21315] Fps is (10 sec: 3173.6, 60 sec: 3123.1, 300 sec: 2888.0). Total num frames: 3886080. Throughput: 0: 3093.6. Samples: 3885370. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:57:55,913][21315] Avg episode reward: [(0, '39.339')] [2023-03-03 13:57:57,499][21357] Updated weights for policy 0, policy_version 3800 (0.0007) [2023-03-03 13:58:00,675][21357] Updated weights for policy 0, policy_version 3810 (0.0007) [2023-03-03 13:58:00,909][21315] Fps is (10 sec: 3175.6, 60 sec: 3106.1, 300 sec: 2898.5). Total num frames: 3901440. Throughput: 0: 3102.7. Samples: 3894915. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:58:00,910][21315] Avg episode reward: [(0, '63.838')] [2023-03-03 13:58:03,909][21357] Updated weights for policy 0, policy_version 3820 (0.0006) [2023-03-03 13:58:05,909][21315] Fps is (10 sec: 3072.9, 60 sec: 3106.1, 300 sec: 2898.4). Total num frames: 3916800. Throughput: 0: 3136.3. Samples: 3913598. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:58:05,911][21315] Avg episode reward: [(0, '51.496')] [2023-03-03 13:58:07,267][21357] Updated weights for policy 0, policy_version 3830 (0.0008) [2023-03-03 13:58:10,669][21357] Updated weights for policy 0, policy_version 3840 (0.0007) [2023-03-03 13:58:10,912][21315] Fps is (10 sec: 3070.9, 60 sec: 3089.1, 300 sec: 2908.8). Total num frames: 3932160. Throughput: 0: 3141.5. Samples: 3932197. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:58:10,913][21315] Avg episode reward: [(0, '66.201')] [2023-03-03 13:58:13,903][21357] Updated weights for policy 0, policy_version 3850 (0.0007) [2023-03-03 13:58:15,913][21315] Fps is (10 sec: 3173.3, 60 sec: 3123.2, 300 sec: 2912.3). Total num frames: 3948544. Throughput: 0: 3145.4. Samples: 3941636. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 13:58:15,913][21315] Avg episode reward: [(0, '81.397')] [2023-03-03 13:58:17,165][21357] Updated weights for policy 0, policy_version 3860 (0.0007) [2023-03-03 13:58:20,376][21357] Updated weights for policy 0, policy_version 3870 (0.0007) [2023-03-03 13:58:20,910][21315] Fps is (10 sec: 3175.3, 60 sec: 3140.5, 300 sec: 2919.3). Total num frames: 3963904. Throughput: 0: 3135.5. Samples: 3960365. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:58:20,910][21315] Avg episode reward: [(0, '95.400')] [2023-03-03 13:58:23,561][21357] Updated weights for policy 0, policy_version 3880 (0.0007) [2023-03-03 13:58:25,911][21315] Fps is (10 sec: 3174.9, 60 sec: 3157.3, 300 sec: 2929.7). Total num frames: 3980288. Throughput: 0: 3141.8. Samples: 3979537. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:58:25,912][21315] Avg episode reward: [(0, '91.852')] [2023-03-03 13:58:26,846][21357] Updated weights for policy 0, policy_version 3890 (0.0007) [2023-03-03 13:58:30,106][21357] Updated weights for policy 0, policy_version 3900 (0.0007) [2023-03-03 13:58:30,912][21315] Fps is (10 sec: 3173.7, 60 sec: 3140.2, 300 sec: 2943.6). Total num frames: 3995648. Throughput: 0: 3143.5. Samples: 3989103. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:58:30,913][21315] Avg episode reward: [(0, '88.290')] [2023-03-03 13:58:33,325][21357] Updated weights for policy 0, policy_version 3910 (0.0007) [2023-03-03 13:58:35,909][21315] Fps is (10 sec: 3175.0, 60 sec: 3157.5, 300 sec: 2957.5). Total num frames: 4012032. Throughput: 0: 3154.3. Samples: 4008200. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 13:58:35,910][21315] Avg episode reward: [(0, '77.590')] [2023-03-03 13:58:36,530][21357] Updated weights for policy 0, policy_version 3920 (0.0007) [2023-03-03 13:58:39,729][21357] Updated weights for policy 0, policy_version 3930 (0.0008) [2023-03-03 13:58:40,912][21315] Fps is (10 sec: 3174.3, 60 sec: 3140.1, 300 sec: 2960.9). Total num frames: 4027392. Throughput: 0: 3149.5. Samples: 4027098. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:58:40,913][21315] Avg episode reward: [(0, '81.221')] [2023-03-03 13:58:42,971][21357] Updated weights for policy 0, policy_version 3940 (0.0007) [2023-03-03 13:58:45,910][21315] Fps is (10 sec: 3174.2, 60 sec: 3157.3, 300 sec: 2974.8). Total num frames: 4043776. Throughput: 0: 3148.8. Samples: 4036612. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 13:58:45,910][21315] Avg episode reward: [(0, '78.369')] [2023-03-03 13:58:46,221][21357] Updated weights for policy 0, policy_version 3950 (0.0008) [2023-03-03 13:58:49,437][21357] Updated weights for policy 0, policy_version 3960 (0.0006) [2023-03-03 13:58:50,912][21315] Fps is (10 sec: 3174.4, 60 sec: 3157.3, 300 sec: 2974.8). Total num frames: 4059136. Throughput: 0: 3159.4. Samples: 4055783. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:58:50,913][21315] Avg episode reward: [(0, '94.731')] [2023-03-03 13:58:52,641][21357] Updated weights for policy 0, policy_version 3970 (0.0007) [2023-03-03 13:58:55,911][21315] Fps is (10 sec: 3071.5, 60 sec: 3140.3, 300 sec: 2981.8). Total num frames: 4074496. Throughput: 0: 3154.2. Samples: 4074132. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:58:55,912][21315] Avg episode reward: [(0, '94.499')] [2023-03-03 13:58:56,042][21357] Updated weights for policy 0, policy_version 3980 (0.0007) [2023-03-03 13:58:59,252][21357] Updated weights for policy 0, policy_version 3990 (0.0007) [2023-03-03 13:59:00,913][21315] Fps is (10 sec: 3071.9, 60 sec: 3140.1, 300 sec: 2995.6). Total num frames: 4089856. Throughput: 0: 3157.5. Samples: 4083726. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:59:00,913][21315] Avg episode reward: [(0, '83.044')] [2023-03-03 13:59:02,576][21357] Updated weights for policy 0, policy_version 4000 (0.0006) [2023-03-03 13:59:05,911][21315] Fps is (10 sec: 3072.0, 60 sec: 3140.2, 300 sec: 3006.1). Total num frames: 4105216. Throughput: 0: 3168.9. Samples: 4102969. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:59:05,912][21315] Avg episode reward: [(0, '62.328')] [2023-03-03 13:59:06,041][21357] Updated weights for policy 0, policy_version 4010 (0.0008) [2023-03-03 13:59:10,180][21357] Updated weights for policy 0, policy_version 4020 (0.0008) [2023-03-03 13:59:10,910][21315] Fps is (10 sec: 2765.4, 60 sec: 3089.2, 300 sec: 3009.5). Total num frames: 4117504. Throughput: 0: 3069.5. Samples: 4117664. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:59:10,911][21315] Avg episode reward: [(0, '57.065')] [2023-03-03 13:59:14,663][21357] Updated weights for policy 0, policy_version 4030 (0.0009) [2023-03-03 13:59:15,909][21315] Fps is (10 sec: 2355.7, 60 sec: 3003.9, 300 sec: 3009.5). Total num frames: 4128768. Throughput: 0: 3009.8. Samples: 4124535. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:59:15,910][21315] Avg episode reward: [(0, '68.174')] [2023-03-03 13:59:18,774][21357] Updated weights for policy 0, policy_version 4040 (0.0008) [2023-03-03 13:59:20,912][21315] Fps is (10 sec: 2354.9, 60 sec: 2952.4, 300 sec: 3009.5). Total num frames: 4141056. Throughput: 0: 2905.1. Samples: 4138938. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:59:20,913][21315] Avg episode reward: [(0, '83.762')] [2023-03-03 13:59:21,012][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000004045_4142080.pth... [2023-03-03 13:59:21,088][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000003333_3412992.pth [2023-03-03 13:59:23,276][21357] Updated weights for policy 0, policy_version 4050 (0.0012) [2023-03-03 13:59:25,913][21315] Fps is (10 sec: 2559.0, 60 sec: 2901.2, 300 sec: 3009.5). Total num frames: 4154368. Throughput: 0: 2817.4. Samples: 4153881. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:59:25,914][21315] Avg episode reward: [(0, '76.975')] [2023-03-03 13:59:26,677][21357] Updated weights for policy 0, policy_version 4060 (0.0009) [2023-03-03 13:59:30,588][21357] Updated weights for policy 0, policy_version 4070 (0.0008) [2023-03-03 13:59:30,915][21315] Fps is (10 sec: 2661.6, 60 sec: 2867.1, 300 sec: 3006.0). Total num frames: 4167680. Throughput: 0: 2788.5. Samples: 4162108. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 13:59:30,916][21315] Avg episode reward: [(0, '80.633')] [2023-03-03 13:59:34,141][21357] Updated weights for policy 0, policy_version 4080 (0.0008) [2023-03-03 13:59:35,912][21315] Fps is (10 sec: 2867.4, 60 sec: 2850.0, 300 sec: 3009.5). Total num frames: 4183040. Throughput: 0: 2751.5. Samples: 4179600. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:59:35,913][21315] Avg episode reward: [(0, '78.597')] [2023-03-03 13:59:37,382][21357] Updated weights for policy 0, policy_version 4090 (0.0007) [2023-03-03 13:59:40,693][21357] Updated weights for policy 0, policy_version 4100 (0.0008) [2023-03-03 13:59:40,912][21315] Fps is (10 sec: 3072.7, 60 sec: 2850.1, 300 sec: 3013.0). Total num frames: 4198400. Throughput: 0: 2764.4. Samples: 4198531. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:59:40,913][21315] Avg episode reward: [(0, '88.809')] [2023-03-03 13:59:44,120][21357] Updated weights for policy 0, policy_version 4110 (0.0008) [2023-03-03 13:59:45,911][21315] Fps is (10 sec: 3072.5, 60 sec: 2833.0, 300 sec: 3013.0). Total num frames: 4213760. Throughput: 0: 2744.9. Samples: 4207239. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-03-03 13:59:45,911][21315] Avg episode reward: [(0, '120.784')] [2023-03-03 13:59:47,350][21357] Updated weights for policy 0, policy_version 4120 (0.0008) [2023-03-03 13:59:50,519][21357] Updated weights for policy 0, policy_version 4130 (0.0007) [2023-03-03 13:59:50,909][21315] Fps is (10 sec: 3175.5, 60 sec: 2850.3, 300 sec: 3020.0). Total num frames: 4230144. Throughput: 0: 2737.0. Samples: 4226126. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:59:50,909][21315] Avg episode reward: [(0, '115.214')] [2023-03-03 13:59:53,693][21357] Updated weights for policy 0, policy_version 4140 (0.0007) [2023-03-03 13:59:55,911][21315] Fps is (10 sec: 3174.2, 60 sec: 2850.1, 300 sec: 3023.4). Total num frames: 4245504. Throughput: 0: 2839.1. Samples: 4245424. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 13:59:55,912][21315] Avg episode reward: [(0, '115.218')] [2023-03-03 13:59:56,941][21357] Updated weights for policy 0, policy_version 4150 (0.0007) [2023-03-03 14:00:00,192][21357] Updated weights for policy 0, policy_version 4160 (0.0008) [2023-03-03 14:00:00,913][21315] Fps is (10 sec: 3173.3, 60 sec: 2867.2, 300 sec: 3026.9). Total num frames: 4261888. Throughput: 0: 2900.6. Samples: 4255072. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:00:00,913][21315] Avg episode reward: [(0, '97.430')] [2023-03-03 14:00:03,424][21357] Updated weights for policy 0, policy_version 4170 (0.0007) [2023-03-03 14:00:05,913][21315] Fps is (10 sec: 3174.0, 60 sec: 2867.1, 300 sec: 3030.3). Total num frames: 4277248. Throughput: 0: 3000.6. Samples: 4273966. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:00:05,914][21315] Avg episode reward: [(0, '74.558')] [2023-03-03 14:00:06,690][21357] Updated weights for policy 0, policy_version 4180 (0.0007) [2023-03-03 14:00:09,858][21357] Updated weights for policy 0, policy_version 4190 (0.0007) [2023-03-03 14:00:10,910][21315] Fps is (10 sec: 3175.1, 60 sec: 2935.5, 300 sec: 3040.8). Total num frames: 4293632. Throughput: 0: 3089.1. Samples: 4292882. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:00:10,911][21315] Avg episode reward: [(0, '64.359')] [2023-03-03 14:00:13,342][21357] Updated weights for policy 0, policy_version 4200 (0.0008) [2023-03-03 14:00:15,909][21315] Fps is (10 sec: 3073.2, 60 sec: 2986.7, 300 sec: 3037.3). Total num frames: 4307968. Throughput: 0: 3101.3. Samples: 4301648. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:00:15,909][21315] Avg episode reward: [(0, '61.877')] [2023-03-03 14:00:16,605][21357] Updated weights for policy 0, policy_version 4210 (0.0007) [2023-03-03 14:00:19,936][21357] Updated weights for policy 0, policy_version 4220 (0.0007) [2023-03-03 14:00:20,912][21315] Fps is (10 sec: 3071.4, 60 sec: 3054.9, 300 sec: 3040.8). Total num frames: 4324352. Throughput: 0: 3124.9. Samples: 4320220. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:00:20,913][21315] Avg episode reward: [(0, '103.268')] [2023-03-03 14:00:23,526][21357] Updated weights for policy 0, policy_version 4230 (0.0007) [2023-03-03 14:00:25,912][21315] Fps is (10 sec: 2968.6, 60 sec: 3055.0, 300 sec: 3033.9). Total num frames: 4337664. Throughput: 0: 3078.8. Samples: 4337078. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:00:25,913][21315] Avg episode reward: [(0, '95.816')] [2023-03-03 14:00:27,154][21357] Updated weights for policy 0, policy_version 4240 (0.0009) [2023-03-03 14:00:30,737][21357] Updated weights for policy 0, policy_version 4250 (0.0009) [2023-03-03 14:00:30,912][21315] Fps is (10 sec: 2764.9, 60 sec: 3072.1, 300 sec: 3030.3). Total num frames: 4352000. Throughput: 0: 3080.0. Samples: 4345844. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:00:30,913][21315] Avg episode reward: [(0, '101.040')] [2023-03-03 14:00:34,166][21357] Updated weights for policy 0, policy_version 4260 (0.0007) [2023-03-03 14:00:35,913][21315] Fps is (10 sec: 2764.5, 60 sec: 3037.8, 300 sec: 3023.4). Total num frames: 4365312. Throughput: 0: 3054.6. Samples: 4363596. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:00:35,914][21315] Avg episode reward: [(0, '83.716')] [2023-03-03 14:00:38,134][21357] Updated weights for policy 0, policy_version 4270 (0.0008) [2023-03-03 14:00:40,912][21315] Fps is (10 sec: 2662.3, 60 sec: 3003.7, 300 sec: 3016.4). Total num frames: 4378624. Throughput: 0: 2967.7. Samples: 4378972. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:00:40,914][21315] Avg episode reward: [(0, '61.430')] [2023-03-03 14:00:42,347][21357] Updated weights for policy 0, policy_version 4280 (0.0008) [2023-03-03 14:00:45,565][21357] Updated weights for policy 0, policy_version 4290 (0.0007) [2023-03-03 14:00:45,913][21315] Fps is (10 sec: 2867.4, 60 sec: 3003.6, 300 sec: 3019.9). Total num frames: 4393984. Throughput: 0: 2924.6. Samples: 4386679. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:00:45,913][21315] Avg episode reward: [(0, '54.781')] [2023-03-03 14:00:48,797][21357] Updated weights for policy 0, policy_version 4300 (0.0007) [2023-03-03 14:00:50,910][21315] Fps is (10 sec: 3072.9, 60 sec: 2986.6, 300 sec: 3023.4). Total num frames: 4409344. Throughput: 0: 2928.0. Samples: 4405715. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:00:50,910][21315] Avg episode reward: [(0, '81.525')] [2023-03-03 14:00:52,081][21357] Updated weights for policy 0, policy_version 4310 (0.0007) [2023-03-03 14:00:55,256][21357] Updated weights for policy 0, policy_version 4320 (0.0007) [2023-03-03 14:00:55,913][21315] Fps is (10 sec: 3174.4, 60 sec: 3003.7, 300 sec: 3026.8). Total num frames: 4425728. Throughput: 0: 2934.9. Samples: 4424961. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:00:55,913][21315] Avg episode reward: [(0, '82.912')] [2023-03-03 14:00:58,480][21357] Updated weights for policy 0, policy_version 4330 (0.0008) [2023-03-03 14:01:00,910][21315] Fps is (10 sec: 3071.8, 60 sec: 2969.7, 300 sec: 3023.4). Total num frames: 4440064. Throughput: 0: 2951.6. Samples: 4434473. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:01:00,911][21315] Avg episode reward: [(0, '91.534')] [2023-03-03 14:01:02,321][21357] Updated weights for policy 0, policy_version 4340 (0.0008) [2023-03-03 14:01:05,911][21315] Fps is (10 sec: 2662.8, 60 sec: 2918.5, 300 sec: 3016.5). Total num frames: 4452352. Throughput: 0: 2895.7. Samples: 4450522. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:01:05,912][21315] Avg episode reward: [(0, '90.638')] [2023-03-03 14:01:06,381][21357] Updated weights for policy 0, policy_version 4350 (0.0007) [2023-03-03 14:01:09,902][21357] Updated weights for policy 0, policy_version 4360 (0.0009) [2023-03-03 14:01:10,913][21315] Fps is (10 sec: 2661.7, 60 sec: 2884.2, 300 sec: 3013.0). Total num frames: 4466688. Throughput: 0: 2876.7. Samples: 4466529. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:01:10,914][21315] Avg episode reward: [(0, '86.429')] [2023-03-03 14:01:13,438][21357] Updated weights for policy 0, policy_version 4370 (0.0007) [2023-03-03 14:01:15,910][21315] Fps is (10 sec: 2970.0, 60 sec: 2901.3, 300 sec: 3023.5). Total num frames: 4482048. Throughput: 0: 2883.8. Samples: 4475606. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:01:15,911][21315] Avg episode reward: [(0, '94.491')] [2023-03-03 14:01:16,946][21357] Updated weights for policy 0, policy_version 4380 (0.0009) [2023-03-03 14:01:20,854][21357] Updated weights for policy 0, policy_version 4390 (0.0010) [2023-03-03 14:01:20,912][21315] Fps is (10 sec: 2867.5, 60 sec: 2850.2, 300 sec: 3016.4). Total num frames: 4495360. Throughput: 0: 2846.6. Samples: 4491690. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:01:20,912][21315] Avg episode reward: [(0, '95.314')] [2023-03-03 14:01:20,916][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000004390_4495360.pth... [2023-03-03 14:01:20,997][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000003688_3776512.pth [2023-03-03 14:01:24,027][21357] Updated weights for policy 0, policy_version 4400 (0.0006) [2023-03-03 14:01:25,910][21315] Fps is (10 sec: 2867.2, 60 sec: 2884.4, 300 sec: 3016.5). Total num frames: 4510720. Throughput: 0: 2925.6. Samples: 4510618. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:01:25,911][21315] Avg episode reward: [(0, '59.139')] [2023-03-03 14:01:27,701][21357] Updated weights for policy 0, policy_version 4410 (0.0008) [2023-03-03 14:01:30,911][21315] Fps is (10 sec: 2867.3, 60 sec: 2867.2, 300 sec: 3009.5). Total num frames: 4524032. Throughput: 0: 2936.1. Samples: 4518799. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:01:30,912][21315] Avg episode reward: [(0, '45.896')] [2023-03-03 14:01:31,489][21357] Updated weights for policy 0, policy_version 4420 (0.0009) [2023-03-03 14:01:35,577][21357] Updated weights for policy 0, policy_version 4430 (0.0012) [2023-03-03 14:01:35,913][21315] Fps is (10 sec: 2559.3, 60 sec: 2850.2, 300 sec: 2995.6). Total num frames: 4536320. Throughput: 0: 2856.3. Samples: 4534258. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:01:35,913][21315] Avg episode reward: [(0, '39.820')] [2023-03-03 14:01:39,515][21357] Updated weights for policy 0, policy_version 4440 (0.0008) [2023-03-03 14:01:40,915][21315] Fps is (10 sec: 2661.3, 60 sec: 2867.1, 300 sec: 2992.1). Total num frames: 4550656. Throughput: 0: 2783.0. Samples: 4550202. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:01:40,926][21315] Avg episode reward: [(0, '38.126')] [2023-03-03 14:01:43,376][21357] Updated weights for policy 0, policy_version 4450 (0.0007) [2023-03-03 14:01:45,909][21315] Fps is (10 sec: 2663.2, 60 sec: 2816.1, 300 sec: 2981.8). Total num frames: 4562944. Throughput: 0: 2735.3. Samples: 4557559. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:01:45,910][21315] Avg episode reward: [(0, '50.391')] [2023-03-03 14:01:47,478][21357] Updated weights for policy 0, policy_version 4460 (0.0009) [2023-03-03 14:01:50,909][21315] Fps is (10 sec: 2561.6, 60 sec: 2781.9, 300 sec: 2974.8). Total num frames: 4576256. Throughput: 0: 2716.5. Samples: 4572760. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:01:50,910][21315] Avg episode reward: [(0, '54.763')] [2023-03-03 14:01:51,228][21357] Updated weights for policy 0, policy_version 4470 (0.0007) [2023-03-03 14:01:54,537][21357] Updated weights for policy 0, policy_version 4480 (0.0007) [2023-03-03 14:01:55,910][21315] Fps is (10 sec: 2764.6, 60 sec: 2747.8, 300 sec: 2967.9). Total num frames: 4590592. Throughput: 0: 2765.1. Samples: 4590953. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:01:55,911][21315] Avg episode reward: [(0, '43.847')] [2023-03-03 14:01:57,775][21357] Updated weights for policy 0, policy_version 4490 (0.0007) [2023-03-03 14:02:00,912][21315] Fps is (10 sec: 3071.0, 60 sec: 2781.8, 300 sec: 2971.3). Total num frames: 4606976. Throughput: 0: 2770.8. Samples: 4600298. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:02:00,913][21315] Avg episode reward: [(0, '38.604')] [2023-03-03 14:02:01,052][21357] Updated weights for policy 0, policy_version 4500 (0.0007) [2023-03-03 14:02:04,473][21357] Updated weights for policy 0, policy_version 4510 (0.0009) [2023-03-03 14:02:05,913][21315] Fps is (10 sec: 3071.1, 60 sec: 2815.9, 300 sec: 2964.4). Total num frames: 4621312. Throughput: 0: 2824.7. Samples: 4618807. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:02:05,914][21315] Avg episode reward: [(0, '38.931')] [2023-03-03 14:02:08,031][21357] Updated weights for policy 0, policy_version 4520 (0.0007) [2023-03-03 14:02:10,910][21315] Fps is (10 sec: 2970.4, 60 sec: 2833.2, 300 sec: 2967.9). Total num frames: 4636672. Throughput: 0: 2802.5. Samples: 4636730. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:02:10,911][21315] Avg episode reward: [(0, '43.961')] [2023-03-03 14:02:11,239][21357] Updated weights for policy 0, policy_version 4530 (0.0007) [2023-03-03 14:02:14,824][21357] Updated weights for policy 0, policy_version 4540 (0.0009) [2023-03-03 14:02:15,912][21315] Fps is (10 sec: 3072.4, 60 sec: 2833.0, 300 sec: 2971.4). Total num frames: 4652032. Throughput: 0: 2814.3. Samples: 4645444. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:02:15,913][21315] Avg episode reward: [(0, '47.490')] [2023-03-03 14:02:18,577][21357] Updated weights for policy 0, policy_version 4550 (0.0007) [2023-03-03 14:02:20,910][21315] Fps is (10 sec: 2867.3, 60 sec: 2833.2, 300 sec: 2964.4). Total num frames: 4665344. Throughput: 0: 2846.5. Samples: 4662339. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:02:20,911][21315] Avg episode reward: [(0, '49.096')] [2023-03-03 14:02:22,012][21357] Updated weights for policy 0, policy_version 4560 (0.0007) [2023-03-03 14:02:25,901][21357] Updated weights for policy 0, policy_version 4570 (0.0007) [2023-03-03 14:02:25,910][21315] Fps is (10 sec: 2765.3, 60 sec: 2816.0, 300 sec: 2957.4). Total num frames: 4679680. Throughput: 0: 2864.5. Samples: 4679088. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:02:25,911][21315] Avg episode reward: [(0, '67.546')] [2023-03-03 14:02:29,359][21357] Updated weights for policy 0, policy_version 4580 (0.0009) [2023-03-03 14:02:30,910][21315] Fps is (10 sec: 2866.9, 60 sec: 2833.1, 300 sec: 2954.0). Total num frames: 4694016. Throughput: 0: 2907.8. Samples: 4688413. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:02:30,911][21315] Avg episode reward: [(0, '73.085')] [2023-03-03 14:02:33,316][21357] Updated weights for policy 0, policy_version 4590 (0.0011) [2023-03-03 14:02:35,910][21315] Fps is (10 sec: 2560.1, 60 sec: 2816.1, 300 sec: 2936.6). Total num frames: 4705280. Throughput: 0: 2901.1. Samples: 4703310. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:02:35,911][21315] Avg episode reward: [(0, '63.832')] [2023-03-03 14:02:37,642][21357] Updated weights for policy 0, policy_version 4600 (0.0012) [2023-03-03 14:02:40,856][21357] Updated weights for policy 0, policy_version 4610 (0.0007) [2023-03-03 14:02:40,912][21315] Fps is (10 sec: 2661.9, 60 sec: 2833.2, 300 sec: 2936.6). Total num frames: 4720640. Throughput: 0: 2866.6. Samples: 4719954. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:02:40,913][21315] Avg episode reward: [(0, '44.144')] [2023-03-03 14:02:44,052][21357] Updated weights for policy 0, policy_version 4620 (0.0009) [2023-03-03 14:02:45,910][21315] Fps is (10 sec: 3071.9, 60 sec: 2884.2, 300 sec: 2936.7). Total num frames: 4736000. Throughput: 0: 2870.0. Samples: 4729443. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:02:45,910][21315] Avg episode reward: [(0, '26.764')] [2023-03-03 14:02:47,240][21357] Updated weights for policy 0, policy_version 4630 (0.0007) [2023-03-03 14:02:50,502][21357] Updated weights for policy 0, policy_version 4640 (0.0007) [2023-03-03 14:02:50,909][21315] Fps is (10 sec: 3175.4, 60 sec: 2935.5, 300 sec: 2936.7). Total num frames: 4752384. Throughput: 0: 2888.4. Samples: 4748774. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:02:50,910][21315] Avg episode reward: [(0, '39.939')] [2023-03-03 14:02:53,695][21357] Updated weights for policy 0, policy_version 4650 (0.0007) [2023-03-03 14:02:55,909][21315] Fps is (10 sec: 3277.1, 60 sec: 2969.7, 300 sec: 2940.1). Total num frames: 4768768. Throughput: 0: 2920.2. Samples: 4768137. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:02:55,910][21315] Avg episode reward: [(0, '40.534')] [2023-03-03 14:02:56,838][21357] Updated weights for policy 0, policy_version 4660 (0.0007) [2023-03-03 14:03:00,013][21357] Updated weights for policy 0, policy_version 4670 (0.0007) [2023-03-03 14:03:00,909][21315] Fps is (10 sec: 3174.5, 60 sec: 2952.7, 300 sec: 2940.1). Total num frames: 4784128. Throughput: 0: 2938.0. Samples: 4777644. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:03:00,910][21315] Avg episode reward: [(0, '32.353')] [2023-03-03 14:03:03,201][21357] Updated weights for policy 0, policy_version 4680 (0.0006) [2023-03-03 14:03:05,913][21315] Fps is (10 sec: 3173.1, 60 sec: 2986.7, 300 sec: 2943.6). Total num frames: 4800512. Throughput: 0: 2987.9. Samples: 4796804. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:03:05,914][21315] Avg episode reward: [(0, '27.793')] [2023-03-03 14:03:06,727][21357] Updated weights for policy 0, policy_version 4690 (0.0009) [2023-03-03 14:03:10,275][21357] Updated weights for policy 0, policy_version 4700 (0.0008) [2023-03-03 14:03:10,910][21315] Fps is (10 sec: 3071.7, 60 sec: 2969.6, 300 sec: 2936.7). Total num frames: 4814848. Throughput: 0: 2998.9. Samples: 4814036. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:03:10,912][21315] Avg episode reward: [(0, '31.541')] [2023-03-03 14:03:13,473][21357] Updated weights for policy 0, policy_version 4710 (0.0006) [2023-03-03 14:03:15,909][21315] Fps is (10 sec: 2970.8, 60 sec: 2969.7, 300 sec: 2936.6). Total num frames: 4830208. Throughput: 0: 3003.4. Samples: 4823562. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:03:15,910][21315] Avg episode reward: [(0, '41.413')] [2023-03-03 14:03:16,735][21357] Updated weights for policy 0, policy_version 4720 (0.0008) [2023-03-03 14:03:20,166][21357] Updated weights for policy 0, policy_version 4730 (0.0007) [2023-03-03 14:03:20,910][21315] Fps is (10 sec: 3072.0, 60 sec: 3003.7, 300 sec: 2933.2). Total num frames: 4845568. Throughput: 0: 3086.9. Samples: 4842222. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:03:20,910][21315] Avg episode reward: [(0, '60.944')] [2023-03-03 14:03:20,915][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000004732_4845568.pth... [2023-03-03 14:03:20,995][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000004045_4142080.pth [2023-03-03 14:03:23,527][21357] Updated weights for policy 0, policy_version 4740 (0.0007) [2023-03-03 14:03:25,911][21315] Fps is (10 sec: 3071.4, 60 sec: 3020.7, 300 sec: 2933.2). Total num frames: 4860928. Throughput: 0: 3128.0. Samples: 4860711. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:03:25,912][21315] Avg episode reward: [(0, '68.941')] [2023-03-03 14:03:26,743][21357] Updated weights for policy 0, policy_version 4750 (0.0007) [2023-03-03 14:03:30,046][21357] Updated weights for policy 0, policy_version 4760 (0.0007) [2023-03-03 14:03:30,913][21315] Fps is (10 sec: 3071.2, 60 sec: 3037.8, 300 sec: 2929.6). Total num frames: 4876288. Throughput: 0: 3125.7. Samples: 4870106. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:03:30,914][21315] Avg episode reward: [(0, '64.225')] [2023-03-03 14:03:33,861][21357] Updated weights for policy 0, policy_version 4770 (0.0007) [2023-03-03 14:03:35,912][21315] Fps is (10 sec: 2969.3, 60 sec: 3088.9, 300 sec: 2926.2). Total num frames: 4890624. Throughput: 0: 3065.6. Samples: 4886737. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:03:35,913][21315] Avg episode reward: [(0, '46.954')] [2023-03-03 14:03:37,172][21357] Updated weights for policy 0, policy_version 4780 (0.0008) [2023-03-03 14:03:40,390][21357] Updated weights for policy 0, policy_version 4790 (0.0007) [2023-03-03 14:03:40,912][21315] Fps is (10 sec: 2969.6, 60 sec: 3089.1, 300 sec: 2922.7). Total num frames: 4905984. Throughput: 0: 3058.6. Samples: 4905782. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:03:40,913][21315] Avg episode reward: [(0, '36.256')] [2023-03-03 14:03:43,624][21357] Updated weights for policy 0, policy_version 4800 (0.0006) [2023-03-03 14:03:45,912][21315] Fps is (10 sec: 3071.9, 60 sec: 3088.9, 300 sec: 2922.7). Total num frames: 4921344. Throughput: 0: 3058.0. Samples: 4915265. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:03:45,913][21315] Avg episode reward: [(0, '35.973')] [2023-03-03 14:03:47,053][21357] Updated weights for policy 0, policy_version 4810 (0.0009) [2023-03-03 14:03:50,408][21357] Updated weights for policy 0, policy_version 4820 (0.0008) [2023-03-03 14:03:50,913][21315] Fps is (10 sec: 3071.7, 60 sec: 3071.8, 300 sec: 2922.7). Total num frames: 4936704. Throughput: 0: 3037.1. Samples: 4933476. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:03:50,915][21315] Avg episode reward: [(0, '29.785')] [2023-03-03 14:03:53,617][21357] Updated weights for policy 0, policy_version 4830 (0.0007) [2023-03-03 14:03:55,909][21315] Fps is (10 sec: 3175.5, 60 sec: 3072.0, 300 sec: 2926.2). Total num frames: 4953088. Throughput: 0: 3078.0. Samples: 4952545. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:03:55,910][21315] Avg episode reward: [(0, '29.498')] [2023-03-03 14:03:56,807][21357] Updated weights for policy 0, policy_version 4840 (0.0006) [2023-03-03 14:03:59,992][21357] Updated weights for policy 0, policy_version 4850 (0.0006) [2023-03-03 14:04:00,910][21315] Fps is (10 sec: 3175.5, 60 sec: 3072.0, 300 sec: 2926.2). Total num frames: 4968448. Throughput: 0: 3076.5. Samples: 4962008. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:04:00,910][21315] Avg episode reward: [(0, '36.134')] [2023-03-03 14:04:03,153][21357] Updated weights for policy 0, policy_version 4860 (0.0006) [2023-03-03 14:04:05,909][21315] Fps is (10 sec: 3071.9, 60 sec: 3055.1, 300 sec: 2936.6). Total num frames: 4983808. Throughput: 0: 3077.3. Samples: 4980700. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:04:05,910][21315] Avg episode reward: [(0, '45.327')] [2023-03-03 14:04:06,660][21357] Updated weights for policy 0, policy_version 4870 (0.0009) [2023-03-03 14:04:10,088][21357] Updated weights for policy 0, policy_version 4880 (0.0007) [2023-03-03 14:04:10,912][21315] Fps is (10 sec: 3071.3, 60 sec: 3071.9, 300 sec: 2950.5). Total num frames: 4999168. Throughput: 0: 3069.7. Samples: 4998849. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:04:10,913][21315] Avg episode reward: [(0, '56.274')] [2023-03-03 14:04:13,292][21357] Updated weights for policy 0, policy_version 4890 (0.0007) [2023-03-03 14:04:15,909][21315] Fps is (10 sec: 3174.5, 60 sec: 3089.1, 300 sec: 2964.4). Total num frames: 5015552. Throughput: 0: 3074.8. Samples: 5008463. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:04:15,909][21315] Avg episode reward: [(0, '54.171')] [2023-03-03 14:04:16,508][21357] Updated weights for policy 0, policy_version 4900 (0.0008) [2023-03-03 14:04:19,633][21357] Updated weights for policy 0, policy_version 4910 (0.0006) [2023-03-03 14:04:20,911][21315] Fps is (10 sec: 3174.9, 60 sec: 3089.0, 300 sec: 2971.4). Total num frames: 5030912. Throughput: 0: 3132.6. Samples: 5027699. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:04:20,911][21315] Avg episode reward: [(0, '41.040')] [2023-03-03 14:04:22,840][21357] Updated weights for policy 0, policy_version 4920 (0.0007) [2023-03-03 14:04:25,910][21315] Fps is (10 sec: 3174.1, 60 sec: 3106.2, 300 sec: 2981.8). Total num frames: 5047296. Throughput: 0: 3139.7. Samples: 5047060. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:04:25,911][21315] Avg episode reward: [(0, '24.231')] [2023-03-03 14:04:26,082][21357] Updated weights for policy 0, policy_version 4930 (0.0006) [2023-03-03 14:04:30,230][21357] Updated weights for policy 0, policy_version 4940 (0.0011) [2023-03-03 14:04:30,913][21315] Fps is (10 sec: 2866.5, 60 sec: 3054.9, 300 sec: 2971.3). Total num frames: 5059584. Throughput: 0: 3100.7. Samples: 5054797. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:04:30,914][21315] Avg episode reward: [(0, '29.870')] [2023-03-03 14:04:34,271][21357] Updated weights for policy 0, policy_version 4950 (0.0010) [2023-03-03 14:04:35,909][21315] Fps is (10 sec: 2560.2, 60 sec: 3038.0, 300 sec: 2964.4). Total num frames: 5072896. Throughput: 0: 3030.9. Samples: 5069855. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:04:35,910][21315] Avg episode reward: [(0, '38.097')] [2023-03-03 14:04:38,095][21357] Updated weights for policy 0, policy_version 4960 (0.0007) [2023-03-03 14:04:40,912][21315] Fps is (10 sec: 2765.0, 60 sec: 3020.8, 300 sec: 2960.9). Total num frames: 5087232. Throughput: 0: 2983.3. Samples: 5086805. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:04:40,913][21315] Avg episode reward: [(0, '43.684')] [2023-03-03 14:04:41,452][21357] Updated weights for policy 0, policy_version 4970 (0.0007) [2023-03-03 14:04:44,813][21357] Updated weights for policy 0, policy_version 4980 (0.0008) [2023-03-03 14:04:45,911][21315] Fps is (10 sec: 2969.1, 60 sec: 3020.9, 300 sec: 2957.4). Total num frames: 5102592. Throughput: 0: 2979.9. Samples: 5096105. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:04:45,911][21315] Avg episode reward: [(0, '42.657')] [2023-03-03 14:04:48,113][21357] Updated weights for policy 0, policy_version 4990 (0.0007) [2023-03-03 14:04:50,910][21315] Fps is (10 sec: 3072.8, 60 sec: 3021.0, 300 sec: 2957.5). Total num frames: 5117952. Throughput: 0: 2976.5. Samples: 5114644. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:04:50,910][21315] Avg episode reward: [(0, '24.920')] [2023-03-03 14:04:51,303][21357] Updated weights for policy 0, policy_version 5000 (0.0007) [2023-03-03 14:04:55,072][21357] Updated weights for policy 0, policy_version 5010 (0.0010) [2023-03-03 14:04:55,912][21315] Fps is (10 sec: 2969.1, 60 sec: 2986.5, 300 sec: 2950.5). Total num frames: 5132288. Throughput: 0: 2955.7. Samples: 5131856. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:04:55,913][21315] Avg episode reward: [(0, '25.977')] [2023-03-03 14:04:58,384][21357] Updated weights for policy 0, policy_version 5020 (0.0007) [2023-03-03 14:05:00,909][21315] Fps is (10 sec: 2969.8, 60 sec: 2986.7, 300 sec: 2950.5). Total num frames: 5147648. Throughput: 0: 2950.0. Samples: 5141215. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:05:00,909][21315] Avg episode reward: [(0, '17.438')] [2023-03-03 14:05:01,851][21357] Updated weights for policy 0, policy_version 5030 (0.0007) [2023-03-03 14:05:05,057][21357] Updated weights for policy 0, policy_version 5040 (0.0007) [2023-03-03 14:05:05,914][21315] Fps is (10 sec: 3071.6, 60 sec: 2986.4, 300 sec: 2947.0). Total num frames: 5163008. Throughput: 0: 2928.1. Samples: 5159474. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:05:05,914][21315] Avg episode reward: [(0, '19.389')] [2023-03-03 14:05:08,260][21357] Updated weights for policy 0, policy_version 5050 (0.0007) [2023-03-03 14:05:10,909][21315] Fps is (10 sec: 3174.3, 60 sec: 3003.9, 300 sec: 2954.0). Total num frames: 5179392. Throughput: 0: 2925.2. Samples: 5178694. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:05:10,910][21315] Avg episode reward: [(0, '19.185')] [2023-03-03 14:05:11,461][21357] Updated weights for policy 0, policy_version 5060 (0.0007) [2023-03-03 14:05:14,735][21357] Updated weights for policy 0, policy_version 5070 (0.0007) [2023-03-03 14:05:15,912][21315] Fps is (10 sec: 3174.9, 60 sec: 2986.5, 300 sec: 2950.5). Total num frames: 5194752. Throughput: 0: 2963.4. Samples: 5188147. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-03-03 14:05:15,913][21315] Avg episode reward: [(0, '18.231')] [2023-03-03 14:05:18,036][21357] Updated weights for policy 0, policy_version 5080 (0.0008) [2023-03-03 14:05:20,911][21315] Fps is (10 sec: 3071.5, 60 sec: 2986.6, 300 sec: 2957.5). Total num frames: 5210112. Throughput: 0: 3051.1. Samples: 5207160. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:05:20,918][21315] Avg episode reward: [(0, '14.771')] [2023-03-03 14:05:21,076][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000005089_5211136.pth... [2023-03-03 14:05:21,154][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000004390_4495360.pth [2023-03-03 14:05:21,418][21357] Updated weights for policy 0, policy_version 5090 (0.0008) [2023-03-03 14:05:24,613][21357] Updated weights for policy 0, policy_version 5100 (0.0006) [2023-03-03 14:05:25,912][21315] Fps is (10 sec: 3174.3, 60 sec: 2986.5, 300 sec: 2964.4). Total num frames: 5226496. Throughput: 0: 3090.5. Samples: 5225876. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:05:25,913][21315] Avg episode reward: [(0, '17.814')] [2023-03-03 14:05:27,774][21357] Updated weights for policy 0, policy_version 5110 (0.0008) [2023-03-03 14:05:30,911][21315] Fps is (10 sec: 3174.4, 60 sec: 3038.0, 300 sec: 2971.4). Total num frames: 5241856. Throughput: 0: 3096.6. Samples: 5235452. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:05:30,912][21315] Avg episode reward: [(0, '17.001')] [2023-03-03 14:05:31,036][21357] Updated weights for policy 0, policy_version 5120 (0.0008) [2023-03-03 14:05:35,915][21315] Fps is (10 sec: 2457.1, 60 sec: 2969.3, 300 sec: 2957.4). Total num frames: 5251072. Throughput: 0: 3001.7. Samples: 5249733. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-03-03 14:05:35,917][21315] Avg episode reward: [(0, '17.053')] [2023-03-03 14:05:36,560][21357] Updated weights for policy 0, policy_version 5130 (0.0013) [2023-03-03 14:05:40,911][21315] Fps is (10 sec: 1945.6, 60 sec: 2901.4, 300 sec: 2940.1). Total num frames: 5261312. Throughput: 0: 2891.1. Samples: 5261952. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:05:40,914][21315] Avg episode reward: [(0, '17.210')] [2023-03-03 14:05:41,532][21357] Updated weights for policy 0, policy_version 5140 (0.0013) [2023-03-03 14:05:45,912][21315] Fps is (10 sec: 2150.9, 60 sec: 2833.0, 300 sec: 2926.2). Total num frames: 5272576. Throughput: 0: 2809.9. Samples: 5267668. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:05:45,914][21315] Avg episode reward: [(0, '14.366')] [2023-03-03 14:05:46,402][21357] Updated weights for policy 0, policy_version 5150 (0.0009) [2023-03-03 14:05:50,348][21357] Updated weights for policy 0, policy_version 5160 (0.0010) [2023-03-03 14:05:50,912][21315] Fps is (10 sec: 2355.0, 60 sec: 2781.8, 300 sec: 2912.3). Total num frames: 5284864. Throughput: 0: 2721.3. Samples: 5281929. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:05:50,913][21315] Avg episode reward: [(0, '14.579')] [2023-03-03 14:05:53,741][21357] Updated weights for policy 0, policy_version 5170 (0.0008) [2023-03-03 14:05:55,911][21315] Fps is (10 sec: 2765.2, 60 sec: 2799.0, 300 sec: 2915.8). Total num frames: 5300224. Throughput: 0: 2687.3. Samples: 5299625. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:05:55,912][21315] Avg episode reward: [(0, '15.102')] [2023-03-03 14:05:57,195][21357] Updated weights for policy 0, policy_version 5180 (0.0008) [2023-03-03 14:06:00,419][21357] Updated weights for policy 0, policy_version 5190 (0.0007) [2023-03-03 14:06:00,909][21315] Fps is (10 sec: 3072.8, 60 sec: 2798.9, 300 sec: 2926.2). Total num frames: 5315584. Throughput: 0: 2687.9. Samples: 5309095. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:06:00,910][21315] Avg episode reward: [(0, '15.935')] [2023-03-03 14:06:03,595][21357] Updated weights for policy 0, policy_version 5200 (0.0008) [2023-03-03 14:06:05,910][21315] Fps is (10 sec: 3174.7, 60 sec: 2816.2, 300 sec: 2933.2). Total num frames: 5331968. Throughput: 0: 2691.2. Samples: 5328261. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:06:05,910][21315] Avg episode reward: [(0, '16.689')] [2023-03-03 14:06:06,790][21357] Updated weights for policy 0, policy_version 5210 (0.0007) [2023-03-03 14:06:10,185][21357] Updated weights for policy 0, policy_version 5220 (0.0008) [2023-03-03 14:06:10,912][21315] Fps is (10 sec: 3173.4, 60 sec: 2798.8, 300 sec: 2933.1). Total num frames: 5347328. Throughput: 0: 2684.6. Samples: 5346682. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:06:10,913][21315] Avg episode reward: [(0, '16.130')] [2023-03-03 14:06:13,409][21357] Updated weights for policy 0, policy_version 5230 (0.0007) [2023-03-03 14:06:15,913][21315] Fps is (10 sec: 3071.2, 60 sec: 2798.9, 300 sec: 2940.1). Total num frames: 5362688. Throughput: 0: 2682.4. Samples: 5356165. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:06:15,914][21315] Avg episode reward: [(0, '15.589')] [2023-03-03 14:06:16,626][21357] Updated weights for policy 0, policy_version 5240 (0.0008) [2023-03-03 14:06:20,047][21357] Updated weights for policy 0, policy_version 5250 (0.0009) [2023-03-03 14:06:20,914][21315] Fps is (10 sec: 2969.2, 60 sec: 2781.8, 300 sec: 2936.6). Total num frames: 5377024. Throughput: 0: 2786.9. Samples: 5375139. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:06:20,919][21315] Avg episode reward: [(0, '14.037')] [2023-03-03 14:06:24,163][21357] Updated weights for policy 0, policy_version 5260 (0.0008) [2023-03-03 14:06:25,909][21315] Fps is (10 sec: 2868.1, 60 sec: 2747.9, 300 sec: 2940.1). Total num frames: 5391360. Throughput: 0: 2863.5. Samples: 5390806. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:06:25,910][21315] Avg episode reward: [(0, '14.621')] [2023-03-03 14:06:27,492][21357] Updated weights for policy 0, policy_version 5270 (0.0007) [2023-03-03 14:06:30,687][21357] Updated weights for policy 0, policy_version 5280 (0.0007) [2023-03-03 14:06:30,912][21315] Fps is (10 sec: 2970.0, 60 sec: 2747.7, 300 sec: 2950.5). Total num frames: 5406720. Throughput: 0: 2946.0. Samples: 5400239. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:06:30,913][21315] Avg episode reward: [(0, '14.568')] [2023-03-03 14:06:34,538][21357] Updated weights for policy 0, policy_version 5290 (0.0008) [2023-03-03 14:06:35,910][21315] Fps is (10 sec: 2867.1, 60 sec: 2816.2, 300 sec: 2947.1). Total num frames: 5420032. Throughput: 0: 3010.0. Samples: 5417372. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:06:35,910][21315] Avg episode reward: [(0, '15.192')] [2023-03-03 14:06:38,262][21357] Updated weights for policy 0, policy_version 5300 (0.0008) [2023-03-03 14:06:40,912][21315] Fps is (10 sec: 2867.2, 60 sec: 2901.3, 300 sec: 2957.4). Total num frames: 5435392. Throughput: 0: 3003.5. Samples: 5434787. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:06:40,913][21315] Avg episode reward: [(0, '17.052')] [2023-03-03 14:06:41,497][21357] Updated weights for policy 0, policy_version 5310 (0.0007) [2023-03-03 14:06:44,662][21357] Updated weights for policy 0, policy_version 5320 (0.0007) [2023-03-03 14:06:45,909][21315] Fps is (10 sec: 3072.3, 60 sec: 2969.8, 300 sec: 2964.4). Total num frames: 5450752. Throughput: 0: 3004.0. Samples: 5444272. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:06:45,910][21315] Avg episode reward: [(0, '19.339')] [2023-03-03 14:06:48,066][21357] Updated weights for policy 0, policy_version 5330 (0.0006) [2023-03-03 14:06:50,912][21315] Fps is (10 sec: 2969.6, 60 sec: 3003.7, 300 sec: 2964.4). Total num frames: 5465088. Throughput: 0: 2988.5. Samples: 5462750. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:06:50,913][21315] Avg episode reward: [(0, '20.791')] [2023-03-03 14:06:52,027][21357] Updated weights for policy 0, policy_version 5340 (0.0009) [2023-03-03 14:06:55,910][21315] Fps is (10 sec: 2662.1, 60 sec: 2952.6, 300 sec: 2950.5). Total num frames: 5477376. Throughput: 0: 2894.9. Samples: 5476946. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:06:55,910][21315] Avg episode reward: [(0, '21.917')] [2023-03-03 14:06:56,264][21357] Updated weights for policy 0, policy_version 5350 (0.0009) [2023-03-03 14:06:59,512][21357] Updated weights for policy 0, policy_version 5360 (0.0007) [2023-03-03 14:07:00,912][21315] Fps is (10 sec: 2764.8, 60 sec: 2952.4, 300 sec: 2954.0). Total num frames: 5492736. Throughput: 0: 2882.0. Samples: 5485855. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:07:00,913][21315] Avg episode reward: [(0, '23.361')] [2023-03-03 14:07:02,784][21357] Updated weights for policy 0, policy_version 5370 (0.0007) [2023-03-03 14:07:05,910][21315] Fps is (10 sec: 3072.2, 60 sec: 2935.5, 300 sec: 2954.0). Total num frames: 5508096. Throughput: 0: 2887.2. Samples: 5505049. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:07:05,911][21315] Avg episode reward: [(0, '21.977')] [2023-03-03 14:07:05,961][21357] Updated weights for policy 0, policy_version 5380 (0.0008) [2023-03-03 14:07:10,021][21357] Updated weights for policy 0, policy_version 5390 (0.0012) [2023-03-03 14:07:10,910][21315] Fps is (10 sec: 2765.5, 60 sec: 2884.4, 300 sec: 2943.6). Total num frames: 5520384. Throughput: 0: 2891.4. Samples: 5520921. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:07:10,910][21315] Avg episode reward: [(0, '21.050')] [2023-03-03 14:07:15,030][21357] Updated weights for policy 0, policy_version 5400 (0.0014) [2023-03-03 14:07:15,913][21315] Fps is (10 sec: 2252.1, 60 sec: 2798.9, 300 sec: 2933.1). Total num frames: 5530624. Throughput: 0: 2814.9. Samples: 5526912. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:07:15,916][21315] Avg episode reward: [(0, '19.062')] [2023-03-03 14:07:19,806][21357] Updated weights for policy 0, policy_version 5410 (0.0014) [2023-03-03 14:07:20,912][21315] Fps is (10 sec: 2150.0, 60 sec: 2747.8, 300 sec: 2922.7). Total num frames: 5541888. Throughput: 0: 2719.2. Samples: 5539739. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:07:20,913][21315] Avg episode reward: [(0, '18.715')] [2023-03-03 14:07:20,929][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000005412_5541888.pth... [2023-03-03 14:07:21,033][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000004732_4845568.pth [2023-03-03 14:07:24,462][21357] Updated weights for policy 0, policy_version 5420 (0.0012) [2023-03-03 14:07:25,909][21315] Fps is (10 sec: 2253.5, 60 sec: 2696.5, 300 sec: 2912.3). Total num frames: 5553152. Throughput: 0: 2624.4. Samples: 5552876. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:07:25,910][21315] Avg episode reward: [(0, '18.753')] [2023-03-03 14:07:28,678][21357] Updated weights for policy 0, policy_version 5430 (0.0008) [2023-03-03 14:07:30,912][21315] Fps is (10 sec: 2355.5, 60 sec: 2645.4, 300 sec: 2915.8). Total num frames: 5565440. Throughput: 0: 2582.3. Samples: 5560477. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:07:30,914][21315] Avg episode reward: [(0, '19.029')] [2023-03-03 14:07:32,784][21357] Updated weights for policy 0, policy_version 5440 (0.0009) [2023-03-03 14:07:35,909][21315] Fps is (10 sec: 2662.5, 60 sec: 2662.4, 300 sec: 2912.4). Total num frames: 5579776. Throughput: 0: 2518.9. Samples: 5576091. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:07:35,910][21315] Avg episode reward: [(0, '23.143')] [2023-03-03 14:07:36,310][21357] Updated weights for policy 0, policy_version 5450 (0.0008) [2023-03-03 14:07:39,674][21357] Updated weights for policy 0, policy_version 5460 (0.0008) [2023-03-03 14:07:40,911][21315] Fps is (10 sec: 2867.0, 60 sec: 2645.4, 300 sec: 2908.8). Total num frames: 5594112. Throughput: 0: 2606.5. Samples: 5594242. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:07:40,911][21315] Avg episode reward: [(0, '29.867')] [2023-03-03 14:07:43,090][21357] Updated weights for policy 0, policy_version 5470 (0.0007) [2023-03-03 14:07:45,909][21315] Fps is (10 sec: 2969.7, 60 sec: 2645.3, 300 sec: 2905.4). Total num frames: 5609472. Throughput: 0: 2601.8. Samples: 5602926. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:07:45,910][21315] Avg episode reward: [(0, '42.248')] [2023-03-03 14:07:46,377][21357] Updated weights for policy 0, policy_version 5480 (0.0007) [2023-03-03 14:07:49,740][21357] Updated weights for policy 0, policy_version 5490 (0.0007) [2023-03-03 14:07:50,914][21315] Fps is (10 sec: 3071.0, 60 sec: 2662.3, 300 sec: 2901.9). Total num frames: 5624832. Throughput: 0: 2589.3. Samples: 5621581. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:07:50,915][21315] Avg episode reward: [(0, '43.770')] [2023-03-03 14:07:53,011][21357] Updated weights for policy 0, policy_version 5500 (0.0007) [2023-03-03 14:07:55,911][21315] Fps is (10 sec: 3071.2, 60 sec: 2713.5, 300 sec: 2901.9). Total num frames: 5640192. Throughput: 0: 2653.5. Samples: 5640333. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:07:55,912][21315] Avg episode reward: [(0, '36.778')] [2023-03-03 14:07:56,248][21357] Updated weights for policy 0, policy_version 5510 (0.0007) [2023-03-03 14:07:59,548][21357] Updated weights for policy 0, policy_version 5520 (0.0007) [2023-03-03 14:08:00,911][21315] Fps is (10 sec: 3072.8, 60 sec: 2713.6, 300 sec: 2898.5). Total num frames: 5655552. Throughput: 0: 2729.2. Samples: 5649721. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:08:00,913][21315] Avg episode reward: [(0, '28.155')] [2023-03-03 14:08:03,168][21357] Updated weights for policy 0, policy_version 5530 (0.0010) [2023-03-03 14:08:05,909][21315] Fps is (10 sec: 2970.3, 60 sec: 2696.6, 300 sec: 2898.5). Total num frames: 5669888. Throughput: 0: 2825.8. Samples: 5666892. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:08:05,909][21315] Avg episode reward: [(0, '29.325')] [2023-03-03 14:08:06,784][21357] Updated weights for policy 0, policy_version 5540 (0.0007) [2023-03-03 14:08:10,289][21357] Updated weights for policy 0, policy_version 5550 (0.0008) [2023-03-03 14:08:10,909][21315] Fps is (10 sec: 2867.7, 60 sec: 2730.7, 300 sec: 2895.0). Total num frames: 5684224. Throughput: 0: 2921.0. Samples: 5684322. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:08:10,911][21315] Avg episode reward: [(0, '23.560')] [2023-03-03 14:08:13,881][21357] Updated weights for policy 0, policy_version 5560 (0.0007) [2023-03-03 14:08:15,911][21315] Fps is (10 sec: 2968.9, 60 sec: 2816.1, 300 sec: 2895.0). Total num frames: 5699584. Throughput: 0: 2943.0. Samples: 5692917. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:08:15,912][21315] Avg episode reward: [(0, '17.105')] [2023-03-03 14:08:17,473][21357] Updated weights for policy 0, policy_version 5570 (0.0007) [2023-03-03 14:08:20,906][21357] Updated weights for policy 0, policy_version 5580 (0.0008) [2023-03-03 14:08:20,909][21315] Fps is (10 sec: 2969.6, 60 sec: 2867.3, 300 sec: 2891.5). Total num frames: 5713920. Throughput: 0: 2976.7. Samples: 5710044. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:08:20,910][21315] Avg episode reward: [(0, '17.166')] [2023-03-03 14:08:24,236][21357] Updated weights for policy 0, policy_version 5590 (0.0008) [2023-03-03 14:08:25,913][21315] Fps is (10 sec: 2866.7, 60 sec: 2918.2, 300 sec: 2888.0). Total num frames: 5728256. Throughput: 0: 2979.2. Samples: 5728314. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:08:25,913][21315] Avg episode reward: [(0, '17.474')] [2023-03-03 14:08:27,571][21357] Updated weights for policy 0, policy_version 5600 (0.0007) [2023-03-03 14:08:30,910][21315] Fps is (10 sec: 2867.1, 60 sec: 2952.5, 300 sec: 2888.0). Total num frames: 5742592. Throughput: 0: 2997.6. Samples: 5737822. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:08:30,914][21315] Avg episode reward: [(0, '17.292')] [2023-03-03 14:08:31,331][21357] Updated weights for policy 0, policy_version 5610 (0.0008) [2023-03-03 14:08:34,585][21357] Updated weights for policy 0, policy_version 5620 (0.0009) [2023-03-03 14:08:35,912][21315] Fps is (10 sec: 2969.8, 60 sec: 2969.5, 300 sec: 2888.0). Total num frames: 5757952. Throughput: 0: 2965.9. Samples: 5755041. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:08:35,912][21315] Avg episode reward: [(0, '17.426')] [2023-03-03 14:08:37,774][21357] Updated weights for policy 0, policy_version 5630 (0.0007) [2023-03-03 14:08:40,909][21315] Fps is (10 sec: 3174.8, 60 sec: 3003.8, 300 sec: 2891.5). Total num frames: 5774336. Throughput: 0: 2977.4. Samples: 5774310. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:08:40,909][21315] Avg episode reward: [(0, '16.528')] [2023-03-03 14:08:41,038][21357] Updated weights for policy 0, policy_version 5640 (0.0006) [2023-03-03 14:08:44,281][21357] Updated weights for policy 0, policy_version 5650 (0.0006) [2023-03-03 14:08:45,909][21315] Fps is (10 sec: 3175.3, 60 sec: 3003.7, 300 sec: 2891.5). Total num frames: 5789696. Throughput: 0: 2978.6. Samples: 5783750. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:08:45,910][21315] Avg episode reward: [(0, '20.694')] [2023-03-03 14:08:47,756][21357] Updated weights for policy 0, policy_version 5660 (0.0007) [2023-03-03 14:08:50,909][21315] Fps is (10 sec: 3071.8, 60 sec: 3004.0, 300 sec: 2888.0). Total num frames: 5805056. Throughput: 0: 2984.8. Samples: 5801210. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:08:50,910][21315] Avg episode reward: [(0, '20.557')] [2023-03-03 14:08:51,123][21357] Updated weights for policy 0, policy_version 5670 (0.0006) [2023-03-03 14:08:54,297][21357] Updated weights for policy 0, policy_version 5680 (0.0007) [2023-03-03 14:08:55,911][21315] Fps is (10 sec: 3173.9, 60 sec: 3020.8, 300 sec: 2891.5). Total num frames: 5821440. Throughput: 0: 3027.9. Samples: 5820580. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:08:55,911][21315] Avg episode reward: [(0, '20.676')] [2023-03-03 14:08:57,679][21357] Updated weights for policy 0, policy_version 5690 (0.0008) [2023-03-03 14:09:00,867][21357] Updated weights for policy 0, policy_version 5700 (0.0007) [2023-03-03 14:09:00,909][21315] Fps is (10 sec: 3174.6, 60 sec: 3020.9, 300 sec: 2891.5). Total num frames: 5836800. Throughput: 0: 3040.5. Samples: 5829731. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:09:00,909][21315] Avg episode reward: [(0, '17.094')] [2023-03-03 14:09:04,110][21357] Updated weights for policy 0, policy_version 5710 (0.0007) [2023-03-03 14:09:05,912][21315] Fps is (10 sec: 2969.2, 60 sec: 3020.6, 300 sec: 2888.0). Total num frames: 5851136. Throughput: 0: 3073.7. Samples: 5848368. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:09:05,913][21315] Avg episode reward: [(0, '18.393')] [2023-03-03 14:09:08,190][21357] Updated weights for policy 0, policy_version 5720 (0.0007) [2023-03-03 14:09:10,909][21315] Fps is (10 sec: 2969.5, 60 sec: 3037.9, 300 sec: 2884.6). Total num frames: 5866496. Throughput: 0: 3054.5. Samples: 5865757. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:09:10,910][21315] Avg episode reward: [(0, '20.459')] [2023-03-03 14:09:11,207][21357] Updated weights for policy 0, policy_version 5730 (0.0006) [2023-03-03 14:09:14,245][21357] Updated weights for policy 0, policy_version 5740 (0.0006) [2023-03-03 14:09:15,912][21315] Fps is (10 sec: 3174.3, 60 sec: 3054.9, 300 sec: 2888.0). Total num frames: 5882880. Throughput: 0: 3062.6. Samples: 5875645. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:09:15,913][21315] Avg episode reward: [(0, '24.581')] [2023-03-03 14:09:17,240][21357] Updated weights for policy 0, policy_version 5750 (0.0007) [2023-03-03 14:09:20,202][21357] Updated weights for policy 0, policy_version 5760 (0.0007) [2023-03-03 14:09:20,910][21315] Fps is (10 sec: 3379.1, 60 sec: 3106.1, 300 sec: 2891.5). Total num frames: 5900288. Throughput: 0: 3134.1. Samples: 5896069. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:09:20,910][21315] Avg episode reward: [(0, '32.901')] [2023-03-03 14:09:20,914][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000005762_5900288.pth... [2023-03-03 14:09:20,991][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000005089_5211136.pth [2023-03-03 14:09:23,346][21357] Updated weights for policy 0, policy_version 5770 (0.0007) [2023-03-03 14:09:25,912][21315] Fps is (10 sec: 3379.4, 60 sec: 3140.3, 300 sec: 2905.4). Total num frames: 5916672. Throughput: 0: 3151.7. Samples: 5916147. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:09:25,912][21315] Avg episode reward: [(0, '28.572')] [2023-03-03 14:09:26,338][21357] Updated weights for policy 0, policy_version 5780 (0.0006) [2023-03-03 14:09:29,336][21357] Updated weights for policy 0, policy_version 5790 (0.0006) [2023-03-03 14:09:30,912][21315] Fps is (10 sec: 3378.5, 60 sec: 3191.4, 300 sec: 2919.2). Total num frames: 5934080. Throughput: 0: 3172.3. Samples: 5926512. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:09:30,912][21315] Avg episode reward: [(0, '24.169')] [2023-03-03 14:09:32,324][21357] Updated weights for policy 0, policy_version 5800 (0.0007) [2023-03-03 14:09:35,319][21357] Updated weights for policy 0, policy_version 5810 (0.0006) [2023-03-03 14:09:35,909][21315] Fps is (10 sec: 3482.5, 60 sec: 3225.7, 300 sec: 2929.7). Total num frames: 5951488. Throughput: 0: 3247.0. Samples: 5947323. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:09:35,910][21315] Avg episode reward: [(0, '14.925')] [2023-03-03 14:09:38,339][21357] Updated weights for policy 0, policy_version 5820 (0.0007) [2023-03-03 14:09:40,912][21315] Fps is (10 sec: 3379.1, 60 sec: 3225.4, 300 sec: 2933.1). Total num frames: 5967872. Throughput: 0: 3264.6. Samples: 5967493. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:09:40,913][21315] Avg episode reward: [(0, '16.994')] [2023-03-03 14:09:41,272][21357] Updated weights for policy 0, policy_version 5830 (0.0007) [2023-03-03 14:09:44,153][21357] Updated weights for policy 0, policy_version 5840 (0.0007) [2023-03-03 14:09:45,918][21315] Fps is (10 sec: 3478.6, 60 sec: 3276.3, 300 sec: 2943.5). Total num frames: 5986304. Throughput: 0: 3298.1. Samples: 5978175. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:09:45,920][21315] Avg episode reward: [(0, '18.080')] [2023-03-03 14:09:47,008][21357] Updated weights for policy 0, policy_version 5850 (0.0006) [2023-03-03 14:09:49,882][21357] Updated weights for policy 0, policy_version 5860 (0.0006) [2023-03-03 14:09:50,912][21315] Fps is (10 sec: 3584.0, 60 sec: 3310.8, 300 sec: 2954.0). Total num frames: 6003712. Throughput: 0: 3360.5. Samples: 5999590. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:09:50,912][21315] Avg episode reward: [(0, '18.385')] [2023-03-03 14:09:52,752][21357] Updated weights for policy 0, policy_version 5870 (0.0006) [2023-03-03 14:09:55,640][21357] Updated weights for policy 0, policy_version 5880 (0.0006) [2023-03-03 14:09:55,910][21315] Fps is (10 sec: 3484.5, 60 sec: 3328.0, 300 sec: 2960.9). Total num frames: 6021120. Throughput: 0: 3449.5. Samples: 6020988. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:09:55,910][21315] Avg episode reward: [(0, '16.723')] [2023-03-03 14:09:58,563][21357] Updated weights for policy 0, policy_version 5890 (0.0007) [2023-03-03 14:10:00,910][21315] Fps is (10 sec: 3584.8, 60 sec: 3379.1, 300 sec: 2971.4). Total num frames: 6039552. Throughput: 0: 3465.8. Samples: 6031598. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:10:00,910][21315] Avg episode reward: [(0, '14.976')] [2023-03-03 14:10:01,503][21357] Updated weights for policy 0, policy_version 5900 (0.0007) [2023-03-03 14:10:04,441][21357] Updated weights for policy 0, policy_version 5910 (0.0007) [2023-03-03 14:10:05,912][21315] Fps is (10 sec: 3583.3, 60 sec: 3430.4, 300 sec: 2974.8). Total num frames: 6056960. Throughput: 0: 3474.9. Samples: 6052448. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:10:05,913][21315] Avg episode reward: [(0, '15.100')] [2023-03-03 14:10:07,367][21357] Updated weights for policy 0, policy_version 5920 (0.0006) [2023-03-03 14:10:10,264][21357] Updated weights for policy 0, policy_version 5930 (0.0006) [2023-03-03 14:10:10,912][21315] Fps is (10 sec: 3480.9, 60 sec: 3464.4, 300 sec: 2981.8). Total num frames: 6074368. Throughput: 0: 3498.6. Samples: 6073583. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:10:10,912][21315] Avg episode reward: [(0, '15.627')] [2023-03-03 14:10:13,163][21357] Updated weights for policy 0, policy_version 5940 (0.0007) [2023-03-03 14:10:15,909][21315] Fps is (10 sec: 3482.6, 60 sec: 3481.8, 300 sec: 2988.7). Total num frames: 6091776. Throughput: 0: 3504.4. Samples: 6084201. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:10:15,913][21315] Avg episode reward: [(0, '15.131')] [2023-03-03 14:10:16,088][21357] Updated weights for policy 0, policy_version 5950 (0.0006) [2023-03-03 14:10:18,975][21357] Updated weights for policy 0, policy_version 5960 (0.0006) [2023-03-03 14:10:20,912][21315] Fps is (10 sec: 3481.6, 60 sec: 3481.5, 300 sec: 2992.2). Total num frames: 6109184. Throughput: 0: 3511.5. Samples: 6105350. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:10:20,913][21315] Avg episode reward: [(0, '15.672')] [2023-03-03 14:10:21,882][21357] Updated weights for policy 0, policy_version 5970 (0.0006) [2023-03-03 14:10:24,810][21357] Updated weights for policy 0, policy_version 5980 (0.0006) [2023-03-03 14:10:25,910][21315] Fps is (10 sec: 3481.1, 60 sec: 3498.8, 300 sec: 2999.1). Total num frames: 6126592. Throughput: 0: 3529.4. Samples: 6126309. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:10:25,911][21315] Avg episode reward: [(0, '16.140')] [2023-03-03 14:10:27,726][21357] Updated weights for policy 0, policy_version 5990 (0.0006) [2023-03-03 14:10:30,626][21357] Updated weights for policy 0, policy_version 6000 (0.0007) [2023-03-03 14:10:30,912][21315] Fps is (10 sec: 3481.6, 60 sec: 3498.7, 300 sec: 3026.9). Total num frames: 6144000. Throughput: 0: 3521.8. Samples: 6136634. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:10:30,913][21315] Avg episode reward: [(0, '16.171')] [2023-03-03 14:10:33,581][21357] Updated weights for policy 0, policy_version 6010 (0.0006) [2023-03-03 14:10:35,910][21315] Fps is (10 sec: 3481.7, 60 sec: 3498.6, 300 sec: 3051.2). Total num frames: 6161408. Throughput: 0: 3511.8. Samples: 6157614. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:10:35,911][21315] Avg episode reward: [(0, '16.311')] [2023-03-03 14:10:36,592][21357] Updated weights for policy 0, policy_version 6020 (0.0006) [2023-03-03 14:10:39,492][21357] Updated weights for policy 0, policy_version 6030 (0.0006) [2023-03-03 14:10:40,911][21315] Fps is (10 sec: 3584.2, 60 sec: 3532.8, 300 sec: 3075.5). Total num frames: 6179840. Throughput: 0: 3505.2. Samples: 6178727. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:10:40,912][21315] Avg episode reward: [(0, '15.689')] [2023-03-03 14:10:42,491][21357] Updated weights for policy 0, policy_version 6040 (0.0006) [2023-03-03 14:10:45,384][21357] Updated weights for policy 0, policy_version 6050 (0.0006) [2023-03-03 14:10:45,912][21315] Fps is (10 sec: 3481.0, 60 sec: 3499.0, 300 sec: 3089.4). Total num frames: 6196224. Throughput: 0: 3499.3. Samples: 6189076. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:10:45,912][21315] Avg episode reward: [(0, '16.426')] [2023-03-03 14:10:48,275][21357] Updated weights for policy 0, policy_version 6060 (0.0006) [2023-03-03 14:10:50,910][21315] Fps is (10 sec: 3379.8, 60 sec: 3498.8, 300 sec: 3096.3). Total num frames: 6213632. Throughput: 0: 3506.8. Samples: 6210245. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:10:50,911][21315] Avg episode reward: [(0, '32.194')] [2023-03-03 14:10:51,196][21357] Updated weights for policy 0, policy_version 6070 (0.0006) [2023-03-03 14:10:54,109][21357] Updated weights for policy 0, policy_version 6080 (0.0006) [2023-03-03 14:10:55,912][21315] Fps is (10 sec: 3584.0, 60 sec: 3515.6, 300 sec: 3106.7). Total num frames: 6232064. Throughput: 0: 3501.0. Samples: 6231126. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:10:55,912][21315] Avg episode reward: [(0, '32.610')] [2023-03-03 14:10:56,993][21357] Updated weights for policy 0, policy_version 6090 (0.0007) [2023-03-03 14:10:59,863][21357] Updated weights for policy 0, policy_version 6100 (0.0006) [2023-03-03 14:11:00,912][21315] Fps is (10 sec: 3583.2, 60 sec: 3498.6, 300 sec: 3110.2). Total num frames: 6249472. Throughput: 0: 3501.2. Samples: 6241763. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:11:00,912][21315] Avg episode reward: [(0, '32.499')] [2023-03-03 14:11:02,782][21357] Updated weights for policy 0, policy_version 6110 (0.0007) [2023-03-03 14:11:05,681][21357] Updated weights for policy 0, policy_version 6120 (0.0007) [2023-03-03 14:11:05,912][21315] Fps is (10 sec: 3481.6, 60 sec: 3498.7, 300 sec: 3117.1). Total num frames: 6266880. Throughput: 0: 3503.9. Samples: 6263024. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:11:05,912][21315] Avg episode reward: [(0, '17.770')] [2023-03-03 14:11:08,673][21357] Updated weights for policy 0, policy_version 6130 (0.0007) [2023-03-03 14:11:10,912][21315] Fps is (10 sec: 3481.4, 60 sec: 3498.6, 300 sec: 3124.1). Total num frames: 6284288. Throughput: 0: 3501.5. Samples: 6283883. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:11:10,913][21315] Avg episode reward: [(0, '26.390')] [2023-03-03 14:11:11,641][21357] Updated weights for policy 0, policy_version 6140 (0.0006) [2023-03-03 14:11:14,577][21357] Updated weights for policy 0, policy_version 6150 (0.0006) [2023-03-03 14:11:15,911][21315] Fps is (10 sec: 3481.7, 60 sec: 3498.5, 300 sec: 3134.5). Total num frames: 6301696. Throughput: 0: 3509.2. Samples: 6294548. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:11:15,913][21315] Avg episode reward: [(0, '25.608')] [2023-03-03 14:11:17,486][21357] Updated weights for policy 0, policy_version 6160 (0.0006) [2023-03-03 14:11:20,378][21357] Updated weights for policy 0, policy_version 6170 (0.0007) [2023-03-03 14:11:20,910][21315] Fps is (10 sec: 3482.3, 60 sec: 3498.8, 300 sec: 3144.9). Total num frames: 6319104. Throughput: 0: 3506.2. Samples: 6315392. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:11:20,911][21315] Avg episode reward: [(0, '25.790')] [2023-03-03 14:11:20,934][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000006172_6320128.pth... [2023-03-03 14:11:21,005][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000005412_5541888.pth [2023-03-03 14:11:23,291][21357] Updated weights for policy 0, policy_version 6180 (0.0007) [2023-03-03 14:11:25,912][21315] Fps is (10 sec: 3481.4, 60 sec: 3498.6, 300 sec: 3151.8). Total num frames: 6336512. Throughput: 0: 3500.5. Samples: 6336252. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:11:25,913][21315] Avg episode reward: [(0, '17.835')] [2023-03-03 14:11:26,288][21357] Updated weights for policy 0, policy_version 6190 (0.0006) [2023-03-03 14:11:29,193][21357] Updated weights for policy 0, policy_version 6200 (0.0007) [2023-03-03 14:11:30,911][21315] Fps is (10 sec: 3481.3, 60 sec: 3498.7, 300 sec: 3165.7). Total num frames: 6353920. Throughput: 0: 3501.8. Samples: 6346655. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:11:30,912][21315] Avg episode reward: [(0, '19.086')] [2023-03-03 14:11:32,074][21357] Updated weights for policy 0, policy_version 6210 (0.0006) [2023-03-03 14:11:34,984][21357] Updated weights for policy 0, policy_version 6220 (0.0006) [2023-03-03 14:11:35,910][21315] Fps is (10 sec: 3482.3, 60 sec: 3498.7, 300 sec: 3172.7). Total num frames: 6371328. Throughput: 0: 3503.6. Samples: 6367909. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:11:35,910][21315] Avg episode reward: [(0, '18.411')] [2023-03-03 14:11:37,891][21357] Updated weights for policy 0, policy_version 6230 (0.0006) [2023-03-03 14:11:40,836][21357] Updated weights for policy 0, policy_version 6240 (0.0007) [2023-03-03 14:11:40,909][21315] Fps is (10 sec: 3584.6, 60 sec: 3498.8, 300 sec: 3183.1). Total num frames: 6389760. Throughput: 0: 3513.1. Samples: 6389205. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:11:40,910][21315] Avg episode reward: [(0, '22.059')] [2023-03-03 14:11:43,758][21357] Updated weights for policy 0, policy_version 6250 (0.0006) [2023-03-03 14:11:45,909][21315] Fps is (10 sec: 3584.3, 60 sec: 3515.9, 300 sec: 3193.5). Total num frames: 6407168. Throughput: 0: 3507.8. Samples: 6399606. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:11:45,910][21315] Avg episode reward: [(0, '22.775')] [2023-03-03 14:11:46,655][21357] Updated weights for policy 0, policy_version 6260 (0.0006) [2023-03-03 14:11:49,584][21357] Updated weights for policy 0, policy_version 6270 (0.0006) [2023-03-03 14:11:50,912][21315] Fps is (10 sec: 3480.7, 60 sec: 3515.6, 300 sec: 3210.8). Total num frames: 6424576. Throughput: 0: 3501.4. Samples: 6420589. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:11:50,913][21315] Avg episode reward: [(0, '18.458')] [2023-03-03 14:11:52,517][21357] Updated weights for policy 0, policy_version 6280 (0.0006) [2023-03-03 14:11:55,439][21357] Updated weights for policy 0, policy_version 6290 (0.0006) [2023-03-03 14:11:55,909][21315] Fps is (10 sec: 3481.5, 60 sec: 3498.8, 300 sec: 3217.8). Total num frames: 6441984. Throughput: 0: 3504.6. Samples: 6441579. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:11:55,910][21315] Avg episode reward: [(0, '19.516')] [2023-03-03 14:11:58,330][21357] Updated weights for policy 0, policy_version 6300 (0.0007) [2023-03-03 14:12:00,911][21315] Fps is (10 sec: 3482.0, 60 sec: 3498.7, 300 sec: 3224.7). Total num frames: 6459392. Throughput: 0: 3504.2. Samples: 6452235. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:12:00,912][21315] Avg episode reward: [(0, '17.322')] [2023-03-03 14:12:01,216][21357] Updated weights for policy 0, policy_version 6310 (0.0006) [2023-03-03 14:12:04,255][21357] Updated weights for policy 0, policy_version 6320 (0.0006) [2023-03-03 14:12:05,912][21315] Fps is (10 sec: 3480.6, 60 sec: 3498.7, 300 sec: 3242.1). Total num frames: 6476800. Throughput: 0: 3501.4. Samples: 6472962. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:12:05,913][21315] Avg episode reward: [(0, '19.068')] [2023-03-03 14:12:07,267][21357] Updated weights for policy 0, policy_version 6330 (0.0007) [2023-03-03 14:12:10,243][21357] Updated weights for policy 0, policy_version 6340 (0.0007) [2023-03-03 14:12:10,911][21315] Fps is (10 sec: 3481.6, 60 sec: 3498.8, 300 sec: 3266.4). Total num frames: 6494208. Throughput: 0: 3491.2. Samples: 6493354. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:12:10,911][21315] Avg episode reward: [(0, '17.022')] [2023-03-03 14:12:13,195][21357] Updated weights for policy 0, policy_version 6350 (0.0006) [2023-03-03 14:12:15,910][21315] Fps is (10 sec: 3482.3, 60 sec: 3498.8, 300 sec: 3287.2). Total num frames: 6511616. Throughput: 0: 3494.6. Samples: 6503908. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:12:15,910][21315] Avg episode reward: [(0, '17.683')] [2023-03-03 14:12:16,122][21357] Updated weights for policy 0, policy_version 6360 (0.0006) [2023-03-03 14:12:19,008][21357] Updated weights for policy 0, policy_version 6370 (0.0006) [2023-03-03 14:12:20,912][21315] Fps is (10 sec: 3481.3, 60 sec: 3498.6, 300 sec: 3308.0). Total num frames: 6529024. Throughput: 0: 3493.4. Samples: 6525117. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-03-03 14:12:20,912][21315] Avg episode reward: [(0, '19.663')] [2023-03-03 14:12:22,077][21357] Updated weights for policy 0, policy_version 6380 (0.0007) [2023-03-03 14:12:24,960][21357] Updated weights for policy 0, policy_version 6390 (0.0006) [2023-03-03 14:12:25,913][21315] Fps is (10 sec: 3480.6, 60 sec: 3498.6, 300 sec: 3325.4). Total num frames: 6546432. Throughput: 0: 3478.1. Samples: 6545731. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:12:25,913][21315] Avg episode reward: [(0, '19.166')] [2023-03-03 14:12:27,828][21357] Updated weights for policy 0, policy_version 6400 (0.0006) [2023-03-03 14:12:30,733][21357] Updated weights for policy 0, policy_version 6410 (0.0006) [2023-03-03 14:12:30,912][21315] Fps is (10 sec: 3481.6, 60 sec: 3498.6, 300 sec: 3335.8). Total num frames: 6563840. Throughput: 0: 3483.8. Samples: 6556388. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:12:30,912][21315] Avg episode reward: [(0, '19.776')] [2023-03-03 14:12:33,606][21357] Updated weights for policy 0, policy_version 6420 (0.0006) [2023-03-03 14:12:35,910][21315] Fps is (10 sec: 3482.4, 60 sec: 3498.6, 300 sec: 3346.2). Total num frames: 6581248. Throughput: 0: 3484.7. Samples: 6577397. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:12:35,911][21315] Avg episode reward: [(0, '20.698')] [2023-03-03 14:12:36,508][21357] Updated weights for policy 0, policy_version 6430 (0.0006) [2023-03-03 14:12:39,419][21357] Updated weights for policy 0, policy_version 6440 (0.0007) [2023-03-03 14:12:40,912][21315] Fps is (10 sec: 3584.0, 60 sec: 3498.5, 300 sec: 3356.6). Total num frames: 6599680. Throughput: 0: 3489.3. Samples: 6598606. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:12:40,912][21315] Avg episode reward: [(0, '21.179')] [2023-03-03 14:12:42,340][21357] Updated weights for policy 0, policy_version 6450 (0.0007) [2023-03-03 14:12:45,274][21357] Updated weights for policy 0, policy_version 6460 (0.0007) [2023-03-03 14:12:45,912][21315] Fps is (10 sec: 3583.5, 60 sec: 3498.5, 300 sec: 3363.6). Total num frames: 6617088. Throughput: 0: 3490.4. Samples: 6609308. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:12:45,912][21315] Avg episode reward: [(0, '22.408')] [2023-03-03 14:12:48,166][21357] Updated weights for policy 0, policy_version 6470 (0.0006) [2023-03-03 14:12:50,912][21315] Fps is (10 sec: 3481.5, 60 sec: 3498.7, 300 sec: 3370.5). Total num frames: 6634496. Throughput: 0: 3503.6. Samples: 6630624. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:12:50,912][21315] Avg episode reward: [(0, '21.361')] [2023-03-03 14:12:51,076][21357] Updated weights for policy 0, policy_version 6480 (0.0007) [2023-03-03 14:12:53,991][21357] Updated weights for policy 0, policy_version 6490 (0.0007) [2023-03-03 14:12:55,909][21315] Fps is (10 sec: 3482.5, 60 sec: 3498.7, 300 sec: 3377.5). Total num frames: 6651904. Throughput: 0: 3518.1. Samples: 6651661. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:12:55,910][21315] Avg episode reward: [(0, '21.290')] [2023-03-03 14:12:56,879][21357] Updated weights for policy 0, policy_version 6500 (0.0006) [2023-03-03 14:12:59,755][21357] Updated weights for policy 0, policy_version 6510 (0.0006) [2023-03-03 14:13:00,912][21315] Fps is (10 sec: 3583.9, 60 sec: 3515.7, 300 sec: 3391.3). Total num frames: 6670336. Throughput: 0: 3517.0. Samples: 6662183. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:13:00,913][21315] Avg episode reward: [(0, '20.570')] [2023-03-03 14:13:02,699][21357] Updated weights for policy 0, policy_version 6520 (0.0006) [2023-03-03 14:13:05,618][21357] Updated weights for policy 0, policy_version 6530 (0.0006) [2023-03-03 14:13:05,909][21315] Fps is (10 sec: 3583.9, 60 sec: 3515.9, 300 sec: 3401.8). Total num frames: 6687744. Throughput: 0: 3509.4. Samples: 6683033. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:13:05,910][21315] Avg episode reward: [(0, '20.451')] [2023-03-03 14:13:08,515][21357] Updated weights for policy 0, policy_version 6540 (0.0006) [2023-03-03 14:13:10,911][21315] Fps is (10 sec: 3481.9, 60 sec: 3515.7, 300 sec: 3408.7). Total num frames: 6705152. Throughput: 0: 3524.4. Samples: 6704325. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:13:10,912][21315] Avg episode reward: [(0, '20.449')] [2023-03-03 14:13:11,393][21357] Updated weights for policy 0, policy_version 6550 (0.0006) [2023-03-03 14:13:14,333][21357] Updated weights for policy 0, policy_version 6560 (0.0006) [2023-03-03 14:13:15,913][21315] Fps is (10 sec: 3480.4, 60 sec: 3515.6, 300 sec: 3419.1). Total num frames: 6722560. Throughput: 0: 3523.0. Samples: 6714925. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:13:15,914][21315] Avg episode reward: [(0, '19.558')] [2023-03-03 14:13:17,339][21357] Updated weights for policy 0, policy_version 6570 (0.0006) [2023-03-03 14:13:20,428][21357] Updated weights for policy 0, policy_version 6580 (0.0007) [2023-03-03 14:13:20,910][21315] Fps is (10 sec: 3379.6, 60 sec: 3498.8, 300 sec: 3426.1). Total num frames: 6738944. Throughput: 0: 3514.3. Samples: 6735540. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:13:20,910][21315] Avg episode reward: [(0, '17.968')] [2023-03-03 14:13:21,015][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000006582_6739968.pth... [2023-03-03 14:13:21,093][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000005762_5900288.pth [2023-03-03 14:13:23,450][21357] Updated weights for policy 0, policy_version 6590 (0.0007) [2023-03-03 14:13:25,910][21315] Fps is (10 sec: 3380.1, 60 sec: 3498.8, 300 sec: 3436.5). Total num frames: 6756352. Throughput: 0: 3486.5. Samples: 6755492. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:13:25,911][21315] Avg episode reward: [(0, '17.951')] [2023-03-03 14:13:26,479][21357] Updated weights for policy 0, policy_version 6600 (0.0006) [2023-03-03 14:13:29,497][21357] Updated weights for policy 0, policy_version 6610 (0.0007) [2023-03-03 14:13:30,910][21315] Fps is (10 sec: 3379.2, 60 sec: 3481.7, 300 sec: 3440.0). Total num frames: 6772736. Throughput: 0: 3473.1. Samples: 6765592. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:13:30,910][21315] Avg episode reward: [(0, '18.353')] [2023-03-03 14:13:32,558][21357] Updated weights for policy 0, policy_version 6620 (0.0007) [2023-03-03 14:13:35,589][21357] Updated weights for policy 0, policy_version 6630 (0.0006) [2023-03-03 14:13:35,912][21315] Fps is (10 sec: 3276.3, 60 sec: 3464.5, 300 sec: 3439.9). Total num frames: 6789120. Throughput: 0: 3445.3. Samples: 6785664. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:13:35,912][21315] Avg episode reward: [(0, '19.790')] [2023-03-03 14:13:38,679][21357] Updated weights for policy 0, policy_version 6640 (0.0006) [2023-03-03 14:13:40,910][21315] Fps is (10 sec: 3379.3, 60 sec: 3447.6, 300 sec: 3446.9). Total num frames: 6806528. Throughput: 0: 3431.4. Samples: 6806078. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:13:40,910][21315] Avg episode reward: [(0, '18.383')] [2023-03-03 14:13:41,742][21357] Updated weights for policy 0, policy_version 6650 (0.0006) [2023-03-03 14:13:44,771][21357] Updated weights for policy 0, policy_version 6660 (0.0006) [2023-03-03 14:13:45,911][21315] Fps is (10 sec: 3379.3, 60 sec: 3430.4, 300 sec: 3450.3). Total num frames: 6822912. Throughput: 0: 3422.9. Samples: 6816213. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:13:45,912][21315] Avg episode reward: [(0, '17.170')] [2023-03-03 14:13:47,795][21357] Updated weights for policy 0, policy_version 6670 (0.0006) [2023-03-03 14:13:50,856][21357] Updated weights for policy 0, policy_version 6680 (0.0006) [2023-03-03 14:13:50,909][21315] Fps is (10 sec: 3379.5, 60 sec: 3430.6, 300 sec: 3453.9). Total num frames: 6840320. Throughput: 0: 3406.4. Samples: 6836321. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:13:50,909][21315] Avg episode reward: [(0, '16.532')] [2023-03-03 14:13:53,866][21357] Updated weights for policy 0, policy_version 6690 (0.0006) [2023-03-03 14:13:55,913][21315] Fps is (10 sec: 3378.8, 60 sec: 3413.1, 300 sec: 3457.3). Total num frames: 6856704. Throughput: 0: 3377.9. Samples: 6856336. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:13:55,913][21315] Avg episode reward: [(0, '17.471')] [2023-03-03 14:13:56,885][21357] Updated weights for policy 0, policy_version 6700 (0.0006) [2023-03-03 14:13:59,932][21357] Updated weights for policy 0, policy_version 6710 (0.0007) [2023-03-03 14:14:00,912][21315] Fps is (10 sec: 3378.3, 60 sec: 3396.3, 300 sec: 3467.7). Total num frames: 6874112. Throughput: 0: 3368.5. Samples: 6866504. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:14:00,912][21315] Avg episode reward: [(0, '21.337')] [2023-03-03 14:14:03,035][21357] Updated weights for policy 0, policy_version 6720 (0.0007) [2023-03-03 14:14:05,913][21315] Fps is (10 sec: 3174.5, 60 sec: 3344.9, 300 sec: 3464.2). Total num frames: 6888448. Throughput: 0: 3338.8. Samples: 6885795. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:14:05,914][21315] Avg episode reward: [(0, '21.741')] [2023-03-03 14:14:06,825][21357] Updated weights for policy 0, policy_version 6730 (0.0009) [2023-03-03 14:14:10,274][21357] Updated weights for policy 0, policy_version 6740 (0.0007) [2023-03-03 14:14:10,912][21315] Fps is (10 sec: 2867.2, 60 sec: 3293.9, 300 sec: 3457.3). Total num frames: 6902784. Throughput: 0: 3276.9. Samples: 6902959. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:14:10,913][21315] Avg episode reward: [(0, '20.749')] [2023-03-03 14:14:13,792][21357] Updated weights for policy 0, policy_version 6750 (0.0008) [2023-03-03 14:14:15,911][21315] Fps is (10 sec: 2765.1, 60 sec: 3225.7, 300 sec: 3443.4). Total num frames: 6916096. Throughput: 0: 3248.7. Samples: 6911787. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:14:15,912][21315] Avg episode reward: [(0, '20.394')] [2023-03-03 14:14:17,570][21357] Updated weights for policy 0, policy_version 6760 (0.0009) [2023-03-03 14:14:20,797][21357] Updated weights for policy 0, policy_version 6770 (0.0007) [2023-03-03 14:14:20,912][21315] Fps is (10 sec: 2969.6, 60 sec: 3225.5, 300 sec: 3443.4). Total num frames: 6932480. Throughput: 0: 3183.2. Samples: 6928907. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:14:20,912][21315] Avg episode reward: [(0, '18.569')] [2023-03-03 14:14:24,875][21357] Updated weights for policy 0, policy_version 6780 (0.0009) [2023-03-03 14:14:25,909][21315] Fps is (10 sec: 2970.2, 60 sec: 3157.4, 300 sec: 3429.6). Total num frames: 6945792. Throughput: 0: 3093.4. Samples: 6945278. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:14:25,910][21315] Avg episode reward: [(0, '18.660')] [2023-03-03 14:14:28,025][21357] Updated weights for policy 0, policy_version 6790 (0.0006) [2023-03-03 14:14:30,911][21315] Fps is (10 sec: 2867.3, 60 sec: 3140.2, 300 sec: 3422.6). Total num frames: 6961152. Throughput: 0: 3084.2. Samples: 6955001. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 14:14:30,913][21315] Avg episode reward: [(0, '20.768')] [2023-03-03 14:14:31,294][21357] Updated weights for policy 0, policy_version 6800 (0.0006) [2023-03-03 14:14:34,528][21357] Updated weights for policy 0, policy_version 6810 (0.0008) [2023-03-03 14:14:35,910][21315] Fps is (10 sec: 3174.1, 60 sec: 3140.4, 300 sec: 3422.6). Total num frames: 6977536. Throughput: 0: 3058.0. Samples: 6973934. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:14:35,910][21315] Avg episode reward: [(0, '19.807')] [2023-03-03 14:14:37,692][21357] Updated weights for policy 0, policy_version 6820 (0.0007) [2023-03-03 14:14:40,912][21315] Fps is (10 sec: 3174.3, 60 sec: 3106.0, 300 sec: 3412.3). Total num frames: 6992896. Throughput: 0: 3032.7. Samples: 6992804. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:14:40,912][21315] Avg episode reward: [(0, '20.912')] [2023-03-03 14:14:41,070][21357] Updated weights for policy 0, policy_version 6830 (0.0009) [2023-03-03 14:14:44,338][21357] Updated weights for policy 0, policy_version 6840 (0.0007) [2023-03-03 14:14:45,909][21315] Fps is (10 sec: 3174.7, 60 sec: 3106.3, 300 sec: 3408.7). Total num frames: 7009280. Throughput: 0: 3014.2. Samples: 7002133. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:14:45,909][21315] Avg episode reward: [(0, '20.868')] [2023-03-03 14:14:47,581][21357] Updated weights for policy 0, policy_version 6850 (0.0010) [2023-03-03 14:14:50,912][21315] Fps is (10 sec: 3072.0, 60 sec: 3054.8, 300 sec: 3398.3). Total num frames: 7023616. Throughput: 0: 2987.2. Samples: 7020218. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:14:50,912][21315] Avg episode reward: [(0, '20.829')] [2023-03-03 14:14:51,194][21357] Updated weights for policy 0, policy_version 6860 (0.0006) [2023-03-03 14:14:55,199][21357] Updated weights for policy 0, policy_version 6870 (0.0009) [2023-03-03 14:14:55,910][21315] Fps is (10 sec: 2764.6, 60 sec: 3003.9, 300 sec: 3380.9). Total num frames: 7036928. Throughput: 0: 2966.7. Samples: 7036454. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:14:55,910][21315] Avg episode reward: [(0, '19.871')] [2023-03-03 14:14:58,779][21357] Updated weights for policy 0, policy_version 6880 (0.0007) [2023-03-03 14:15:00,909][21315] Fps is (10 sec: 2765.5, 60 sec: 2952.7, 300 sec: 3370.6). Total num frames: 7051264. Throughput: 0: 2955.9. Samples: 7044797. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:15:00,910][21315] Avg episode reward: [(0, '19.153')] [2023-03-03 14:15:02,111][21357] Updated weights for policy 0, policy_version 6890 (0.0008) [2023-03-03 14:15:05,413][21357] Updated weights for policy 0, policy_version 6900 (0.0007) [2023-03-03 14:15:05,909][21315] Fps is (10 sec: 2969.8, 60 sec: 2969.8, 300 sec: 3363.6). Total num frames: 7066624. Throughput: 0: 2988.7. Samples: 7063389. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:15:05,910][21315] Avg episode reward: [(0, '20.670')] [2023-03-03 14:15:08,534][21357] Updated weights for policy 0, policy_version 6910 (0.0007) [2023-03-03 14:15:10,912][21315] Fps is (10 sec: 3071.2, 60 sec: 2986.7, 300 sec: 3356.6). Total num frames: 7081984. Throughput: 0: 3049.8. Samples: 7082529. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:15:10,912][21315] Avg episode reward: [(0, '42.539')] [2023-03-03 14:15:12,254][21357] Updated weights for policy 0, policy_version 6920 (0.0010) [2023-03-03 14:15:15,909][21315] Fps is (10 sec: 2867.1, 60 sec: 2986.8, 300 sec: 3342.8). Total num frames: 7095296. Throughput: 0: 3002.4. Samples: 7090101. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:15:15,910][21315] Avg episode reward: [(0, '42.876')] [2023-03-03 14:15:16,106][21357] Updated weights for policy 0, policy_version 6930 (0.0009) [2023-03-03 14:15:19,358][21357] Updated weights for policy 0, policy_version 6940 (0.0008) [2023-03-03 14:15:20,911][21315] Fps is (10 sec: 2969.9, 60 sec: 2986.7, 300 sec: 3339.3). Total num frames: 7111680. Throughput: 0: 2969.7. Samples: 7107573. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:15:20,911][21315] Avg episode reward: [(0, '44.601')] [2023-03-03 14:15:20,917][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000006945_7111680.pth... [2023-03-03 14:15:21,000][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000006172_6320128.pth [2023-03-03 14:15:22,503][21357] Updated weights for policy 0, policy_version 6950 (0.0007) [2023-03-03 14:15:25,556][21357] Updated weights for policy 0, policy_version 6960 (0.0007) [2023-03-03 14:15:25,910][21315] Fps is (10 sec: 3276.5, 60 sec: 3037.8, 300 sec: 3335.8). Total num frames: 7128064. Throughput: 0: 2990.9. Samples: 7127392. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:15:25,911][21315] Avg episode reward: [(0, '21.603')] [2023-03-03 14:15:28,636][21357] Updated weights for policy 0, policy_version 6970 (0.0006) [2023-03-03 14:15:30,912][21315] Fps is (10 sec: 3276.5, 60 sec: 3054.9, 300 sec: 3332.3). Total num frames: 7144448. Throughput: 0: 3004.3. Samples: 7137336. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:15:30,912][21315] Avg episode reward: [(0, '23.347')] [2023-03-03 14:15:31,864][21357] Updated weights for policy 0, policy_version 6980 (0.0007) [2023-03-03 14:15:35,040][21357] Updated weights for policy 0, policy_version 6990 (0.0007) [2023-03-03 14:15:35,912][21315] Fps is (10 sec: 3174.0, 60 sec: 3037.8, 300 sec: 3321.9). Total num frames: 7159808. Throughput: 0: 3034.2. Samples: 7156758. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:15:35,912][21315] Avg episode reward: [(0, '24.003')] [2023-03-03 14:15:38,396][21357] Updated weights for policy 0, policy_version 7000 (0.0008) [2023-03-03 14:15:40,912][21315] Fps is (10 sec: 3071.8, 60 sec: 3037.8, 300 sec: 3318.4). Total num frames: 7175168. Throughput: 0: 3088.4. Samples: 7175440. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 14:15:40,913][21315] Avg episode reward: [(0, '23.704')] [2023-03-03 14:15:41,615][21357] Updated weights for policy 0, policy_version 7010 (0.0006) [2023-03-03 14:15:45,016][21357] Updated weights for policy 0, policy_version 7020 (0.0007) [2023-03-03 14:15:45,909][21315] Fps is (10 sec: 3072.8, 60 sec: 3020.8, 300 sec: 3311.5). Total num frames: 7190528. Throughput: 0: 3097.8. Samples: 7184200. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:15:45,911][21315] Avg episode reward: [(0, '20.677')] [2023-03-03 14:15:48,606][21357] Updated weights for policy 0, policy_version 7030 (0.0031) [2023-03-03 14:15:50,914][21315] Fps is (10 sec: 3071.6, 60 sec: 3037.8, 300 sec: 3301.1). Total num frames: 7205888. Throughput: 0: 3086.1. Samples: 7202280. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:15:50,915][21315] Avg episode reward: [(0, '21.691')] [2023-03-03 14:15:51,740][21357] Updated weights for policy 0, policy_version 7040 (0.0008) [2023-03-03 14:15:55,093][21357] Updated weights for policy 0, policy_version 7050 (0.0007) [2023-03-03 14:15:55,911][21315] Fps is (10 sec: 3071.6, 60 sec: 3072.0, 300 sec: 3294.2). Total num frames: 7221248. Throughput: 0: 3076.6. Samples: 7220971. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:15:55,914][21315] Avg episode reward: [(0, '20.693')] [2023-03-03 14:15:58,294][21357] Updated weights for policy 0, policy_version 7060 (0.0006) [2023-03-03 14:16:00,909][21315] Fps is (10 sec: 3175.8, 60 sec: 3106.1, 300 sec: 3290.7). Total num frames: 7237632. Throughput: 0: 3123.1. Samples: 7230642. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:16:00,910][21315] Avg episode reward: [(0, '20.029')] [2023-03-03 14:16:01,404][21357] Updated weights for policy 0, policy_version 7070 (0.0007) [2023-03-03 14:16:04,549][21357] Updated weights for policy 0, policy_version 7080 (0.0007) [2023-03-03 14:16:05,909][21315] Fps is (10 sec: 3277.2, 60 sec: 3123.2, 300 sec: 3287.2). Total num frames: 7254016. Throughput: 0: 3173.1. Samples: 7250358. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:16:05,910][21315] Avg episode reward: [(0, '19.742')] [2023-03-03 14:16:07,623][21357] Updated weights for policy 0, policy_version 7090 (0.0007) [2023-03-03 14:16:10,739][21357] Updated weights for policy 0, policy_version 7100 (0.0006) [2023-03-03 14:16:10,909][21315] Fps is (10 sec: 3276.9, 60 sec: 3140.4, 300 sec: 3283.8). Total num frames: 7270400. Throughput: 0: 3171.2. Samples: 7270090. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 14:16:10,910][21315] Avg episode reward: [(0, '22.255')] [2023-03-03 14:16:13,802][21357] Updated weights for policy 0, policy_version 7110 (0.0008) [2023-03-03 14:16:15,911][21315] Fps is (10 sec: 3276.4, 60 sec: 3191.4, 300 sec: 3280.3). Total num frames: 7286784. Throughput: 0: 3171.7. Samples: 7280058. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 14:16:15,911][21315] Avg episode reward: [(0, '24.250')] [2023-03-03 14:16:16,894][21357] Updated weights for policy 0, policy_version 7120 (0.0007) [2023-03-03 14:16:18,339][21356] KL-divergence is very high: 180.7348 [2023-03-03 14:16:19,950][21357] Updated weights for policy 0, policy_version 7130 (0.0007) [2023-03-03 14:16:20,909][21315] Fps is (10 sec: 3276.9, 60 sec: 3191.6, 300 sec: 3276.8). Total num frames: 7303168. Throughput: 0: 3182.7. Samples: 7299972. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:16:20,910][21315] Avg episode reward: [(0, '24.415')] [2023-03-03 14:16:23,059][21357] Updated weights for policy 0, policy_version 7140 (0.0008) [2023-03-03 14:16:25,912][21315] Fps is (10 sec: 3378.9, 60 sec: 3208.5, 300 sec: 3276.8). Total num frames: 7320576. Throughput: 0: 3211.2. Samples: 7319942. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:16:25,912][21315] Avg episode reward: [(0, '22.948')] [2023-03-03 14:16:26,194][21357] Updated weights for policy 0, policy_version 7150 (0.0006) [2023-03-03 14:16:29,289][21357] Updated weights for policy 0, policy_version 7160 (0.0006) [2023-03-03 14:16:30,912][21315] Fps is (10 sec: 3378.3, 60 sec: 3208.5, 300 sec: 3273.3). Total num frames: 7336960. Throughput: 0: 3238.5. Samples: 7329942. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 14:16:30,912][21315] Avg episode reward: [(0, '21.476')] [2023-03-03 14:16:32,409][21357] Updated weights for policy 0, policy_version 7170 (0.0006) [2023-03-03 14:16:35,473][21357] Updated weights for policy 0, policy_version 7180 (0.0007) [2023-03-03 14:16:35,911][21315] Fps is (10 sec: 3276.8, 60 sec: 3225.6, 300 sec: 3266.4). Total num frames: 7353344. Throughput: 0: 3272.4. Samples: 7349532. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 14:16:35,912][21315] Avg episode reward: [(0, '21.014')] [2023-03-03 14:16:38,519][21357] Updated weights for policy 0, policy_version 7190 (0.0006) [2023-03-03 14:16:40,912][21315] Fps is (10 sec: 3276.8, 60 sec: 3242.7, 300 sec: 3262.9). Total num frames: 7369728. Throughput: 0: 3301.7. Samples: 7369550. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:16:40,913][21315] Avg episode reward: [(0, '19.316')] [2023-03-03 14:16:41,551][21357] Updated weights for policy 0, policy_version 7200 (0.0006) [2023-03-03 14:16:44,603][21357] Updated weights for policy 0, policy_version 7210 (0.0006) [2023-03-03 14:16:45,912][21315] Fps is (10 sec: 3379.2, 60 sec: 3276.7, 300 sec: 3262.9). Total num frames: 7387136. Throughput: 0: 3311.4. Samples: 7379662. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:16:45,912][21315] Avg episode reward: [(0, '19.790')] [2023-03-03 14:16:47,700][21357] Updated weights for policy 0, policy_version 7220 (0.0007) [2023-03-03 14:16:50,843][21357] Updated weights for policy 0, policy_version 7230 (0.0007) [2023-03-03 14:16:50,911][21315] Fps is (10 sec: 3379.3, 60 sec: 3294.0, 300 sec: 3259.4). Total num frames: 7403520. Throughput: 0: 3319.3. Samples: 7399735. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:16:50,912][21315] Avg episode reward: [(0, '20.256')] [2023-03-03 14:16:53,895][21357] Updated weights for policy 0, policy_version 7240 (0.0007) [2023-03-03 14:16:55,909][21315] Fps is (10 sec: 3277.6, 60 sec: 3311.0, 300 sec: 3256.0). Total num frames: 7419904. Throughput: 0: 3327.1. Samples: 7419809. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:16:55,910][21315] Avg episode reward: [(0, '19.470')] [2023-03-03 14:16:56,945][21357] Updated weights for policy 0, policy_version 7250 (0.0006) [2023-03-03 14:16:59,983][21357] Updated weights for policy 0, policy_version 7260 (0.0007) [2023-03-03 14:17:00,909][21315] Fps is (10 sec: 3379.9, 60 sec: 3328.0, 300 sec: 3256.0). Total num frames: 7437312. Throughput: 0: 3325.8. Samples: 7429716. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:17:00,910][21315] Avg episode reward: [(0, '17.696')] [2023-03-03 14:17:03,035][21357] Updated weights for policy 0, policy_version 7270 (0.0007) [2023-03-03 14:17:05,909][21315] Fps is (10 sec: 3276.8, 60 sec: 3310.9, 300 sec: 3249.0). Total num frames: 7452672. Throughput: 0: 3317.6. Samples: 7449264. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:17:05,910][21315] Avg episode reward: [(0, '15.937')] [2023-03-03 14:17:06,242][21357] Updated weights for policy 0, policy_version 7280 (0.0007) [2023-03-03 14:17:09,339][21357] Updated weights for policy 0, policy_version 7290 (0.0006) [2023-03-03 14:17:10,910][21315] Fps is (10 sec: 3276.7, 60 sec: 3328.0, 300 sec: 3249.0). Total num frames: 7470080. Throughput: 0: 3322.8. Samples: 7469460. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:17:10,910][21315] Avg episode reward: [(0, '15.607')] [2023-03-03 14:17:12,367][21357] Updated weights for policy 0, policy_version 7300 (0.0006) [2023-03-03 14:17:15,469][21357] Updated weights for policy 0, policy_version 7310 (0.0006) [2023-03-03 14:17:15,909][21315] Fps is (10 sec: 3379.1, 60 sec: 3328.1, 300 sec: 3245.6). Total num frames: 7486464. Throughput: 0: 3326.1. Samples: 7479608. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 14:17:15,910][21315] Avg episode reward: [(0, '18.760')] [2023-03-03 14:17:18,509][21357] Updated weights for policy 0, policy_version 7320 (0.0007) [2023-03-03 14:17:20,910][21315] Fps is (10 sec: 3276.7, 60 sec: 3327.9, 300 sec: 3242.1). Total num frames: 7502848. Throughput: 0: 3335.7. Samples: 7499632. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 14:17:20,911][21315] Avg episode reward: [(0, '19.741')] [2023-03-03 14:17:21,057][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000007328_7503872.pth... [2023-03-03 14:17:21,139][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000006582_6739968.pth [2023-03-03 14:17:21,665][21357] Updated weights for policy 0, policy_version 7330 (0.0007) [2023-03-03 14:17:24,701][21357] Updated weights for policy 0, policy_version 7340 (0.0006) [2023-03-03 14:17:25,909][21315] Fps is (10 sec: 3276.9, 60 sec: 3311.1, 300 sec: 3238.6). Total num frames: 7519232. Throughput: 0: 3322.3. Samples: 7519043. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:17:25,910][21315] Avg episode reward: [(0, '22.997')] [2023-03-03 14:17:27,801][21357] Updated weights for policy 0, policy_version 7350 (0.0007) [2023-03-03 14:17:30,912][21315] Fps is (10 sec: 3276.0, 60 sec: 3310.9, 300 sec: 3235.1). Total num frames: 7535616. Throughput: 0: 3320.7. Samples: 7529097. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:17:30,913][21315] Avg episode reward: [(0, '22.906')] [2023-03-03 14:17:30,937][21357] Updated weights for policy 0, policy_version 7360 (0.0007) [2023-03-03 14:17:33,974][21357] Updated weights for policy 0, policy_version 7370 (0.0006) [2023-03-03 14:17:35,913][21315] Fps is (10 sec: 3377.8, 60 sec: 3327.9, 300 sec: 3231.7). Total num frames: 7553024. Throughput: 0: 3322.0. Samples: 7549230. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:17:35,914][21315] Avg episode reward: [(0, '21.557')] [2023-03-03 14:17:37,053][21357] Updated weights for policy 0, policy_version 7380 (0.0006) [2023-03-03 14:17:40,117][21357] Updated weights for policy 0, policy_version 7390 (0.0006) [2023-03-03 14:17:40,909][21315] Fps is (10 sec: 3380.1, 60 sec: 3328.1, 300 sec: 3228.2). Total num frames: 7569408. Throughput: 0: 3319.0. Samples: 7569164. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:17:40,910][21315] Avg episode reward: [(0, '18.925')] [2023-03-03 14:17:43,171][21357] Updated weights for policy 0, policy_version 7400 (0.0007) [2023-03-03 14:17:45,910][21315] Fps is (10 sec: 3277.9, 60 sec: 3311.0, 300 sec: 3224.8). Total num frames: 7585792. Throughput: 0: 3323.5. Samples: 7579273. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:17:45,910][21315] Avg episode reward: [(0, '18.753')] [2023-03-03 14:17:46,230][21357] Updated weights for policy 0, policy_version 7410 (0.0007) [2023-03-03 14:17:49,339][21357] Updated weights for policy 0, policy_version 7420 (0.0006) [2023-03-03 14:17:50,912][21315] Fps is (10 sec: 3378.4, 60 sec: 3328.0, 300 sec: 3224.7). Total num frames: 7603200. Throughput: 0: 3328.9. Samples: 7599072. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:17:50,912][21315] Avg episode reward: [(0, '19.339')] [2023-03-03 14:17:52,364][21357] Updated weights for policy 0, policy_version 7430 (0.0006) [2023-03-03 14:17:55,387][21357] Updated weights for policy 0, policy_version 7440 (0.0006) [2023-03-03 14:17:55,909][21315] Fps is (10 sec: 3379.3, 60 sec: 3328.0, 300 sec: 3217.8). Total num frames: 7619584. Throughput: 0: 3331.6. Samples: 7619381. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:17:55,910][21315] Avg episode reward: [(0, '18.954')] [2023-03-03 14:17:58,438][21357] Updated weights for policy 0, policy_version 7450 (0.0006) [2023-03-03 14:18:00,909][21315] Fps is (10 sec: 3380.2, 60 sec: 3328.0, 300 sec: 3217.8). Total num frames: 7636992. Throughput: 0: 3331.3. Samples: 7629517. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:18:00,909][21315] Avg episode reward: [(0, '18.155')] [2023-03-03 14:18:01,505][21357] Updated weights for policy 0, policy_version 7460 (0.0006) [2023-03-03 14:18:04,569][21357] Updated weights for policy 0, policy_version 7470 (0.0007) [2023-03-03 14:18:05,909][21315] Fps is (10 sec: 3379.3, 60 sec: 3345.1, 300 sec: 3214.3). Total num frames: 7653376. Throughput: 0: 3332.0. Samples: 7649571. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:18:05,910][21315] Avg episode reward: [(0, '19.613')] [2023-03-03 14:18:07,601][21357] Updated weights for policy 0, policy_version 7480 (0.0007) [2023-03-03 14:18:10,679][21357] Updated weights for policy 0, policy_version 7490 (0.0007) [2023-03-03 14:18:10,909][21315] Fps is (10 sec: 3276.8, 60 sec: 3328.0, 300 sec: 3210.9). Total num frames: 7669760. Throughput: 0: 3350.1. Samples: 7669799. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:18:10,910][21315] Avg episode reward: [(0, '27.049')] [2023-03-03 14:18:13,733][21357] Updated weights for policy 0, policy_version 7500 (0.0007) [2023-03-03 14:18:15,910][21315] Fps is (10 sec: 3379.0, 60 sec: 3345.1, 300 sec: 3214.3). Total num frames: 7687168. Throughput: 0: 3349.5. Samples: 7679817. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:18:15,910][21315] Avg episode reward: [(0, '25.729')] [2023-03-03 14:18:16,793][21357] Updated weights for policy 0, policy_version 7510 (0.0006) [2023-03-03 14:18:19,826][21357] Updated weights for policy 0, policy_version 7520 (0.0006) [2023-03-03 14:18:20,909][21315] Fps is (10 sec: 3379.1, 60 sec: 3345.1, 300 sec: 3210.9). Total num frames: 7703552. Throughput: 0: 3346.5. Samples: 7699809. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:18:20,910][21315] Avg episode reward: [(0, '19.897')] [2023-03-03 14:18:22,874][21357] Updated weights for policy 0, policy_version 7530 (0.0007) [2023-03-03 14:18:25,911][21315] Fps is (10 sec: 3276.2, 60 sec: 3344.9, 300 sec: 3210.8). Total num frames: 7719936. Throughput: 0: 3340.4. Samples: 7719490. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:18:25,912][21315] Avg episode reward: [(0, '18.699')] [2023-03-03 14:18:26,084][21357] Updated weights for policy 0, policy_version 7540 (0.0007) [2023-03-03 14:18:29,108][21357] Updated weights for policy 0, policy_version 7550 (0.0007) [2023-03-03 14:18:30,909][21315] Fps is (10 sec: 3276.9, 60 sec: 3345.2, 300 sec: 3210.9). Total num frames: 7736320. Throughput: 0: 3340.3. Samples: 7729585. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:18:30,910][21315] Avg episode reward: [(0, '19.347')] [2023-03-03 14:18:32,219][21357] Updated weights for policy 0, policy_version 7560 (0.0007) [2023-03-03 14:18:35,340][21357] Updated weights for policy 0, policy_version 7570 (0.0007) [2023-03-03 14:18:35,909][21315] Fps is (10 sec: 3277.6, 60 sec: 3328.2, 300 sec: 3207.4). Total num frames: 7752704. Throughput: 0: 3347.7. Samples: 7749708. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:18:35,910][21315] Avg episode reward: [(0, '20.151')] [2023-03-03 14:18:38,385][21357] Updated weights for policy 0, policy_version 7580 (0.0006) [2023-03-03 14:18:40,909][21315] Fps is (10 sec: 3379.2, 60 sec: 3345.1, 300 sec: 3210.9). Total num frames: 7770112. Throughput: 0: 3337.6. Samples: 7769571. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:18:40,909][21315] Avg episode reward: [(0, '19.212')] [2023-03-03 14:18:41,416][21357] Updated weights for policy 0, policy_version 7590 (0.0007) [2023-03-03 14:18:44,492][21357] Updated weights for policy 0, policy_version 7600 (0.0007) [2023-03-03 14:18:45,912][21315] Fps is (10 sec: 3378.1, 60 sec: 3344.9, 300 sec: 3207.3). Total num frames: 7786496. Throughput: 0: 3333.8. Samples: 7779548. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:18:45,913][21315] Avg episode reward: [(0, '20.959')] [2023-03-03 14:18:47,521][21357] Updated weights for policy 0, policy_version 7610 (0.0006) [2023-03-03 14:18:50,590][21357] Updated weights for policy 0, policy_version 7620 (0.0007) [2023-03-03 14:18:50,909][21315] Fps is (10 sec: 3379.1, 60 sec: 3345.2, 300 sec: 3210.9). Total num frames: 7803904. Throughput: 0: 3335.9. Samples: 7799685. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:18:50,910][21315] Avg episode reward: [(0, '21.987')] [2023-03-03 14:18:53,650][21357] Updated weights for policy 0, policy_version 7630 (0.0007) [2023-03-03 14:18:55,909][21315] Fps is (10 sec: 3380.3, 60 sec: 3345.1, 300 sec: 3207.4). Total num frames: 7820288. Throughput: 0: 3336.3. Samples: 7819933. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:18:55,910][21315] Avg episode reward: [(0, '23.549')] [2023-03-03 14:18:56,734][21357] Updated weights for policy 0, policy_version 7640 (0.0007) [2023-03-03 14:18:59,777][21357] Updated weights for policy 0, policy_version 7650 (0.0006) [2023-03-03 14:19:00,911][21315] Fps is (10 sec: 3276.2, 60 sec: 3327.9, 300 sec: 3214.3). Total num frames: 7836672. Throughput: 0: 3338.7. Samples: 7830065. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:19:00,912][21315] Avg episode reward: [(0, '23.376')] [2023-03-03 14:19:02,816][21357] Updated weights for policy 0, policy_version 7660 (0.0007) [2023-03-03 14:19:05,831][21357] Updated weights for policy 0, policy_version 7670 (0.0006) [2023-03-03 14:19:05,911][21315] Fps is (10 sec: 3378.3, 60 sec: 3344.9, 300 sec: 3224.7). Total num frames: 7854080. Throughput: 0: 3338.7. Samples: 7850059. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:19:05,912][21315] Avg episode reward: [(0, '22.141')] [2023-03-03 14:19:08,882][21357] Updated weights for policy 0, policy_version 7680 (0.0006) [2023-03-03 14:19:10,909][21315] Fps is (10 sec: 3379.8, 60 sec: 3345.0, 300 sec: 3235.2). Total num frames: 7870464. Throughput: 0: 3347.9. Samples: 7870138. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:19:10,910][21315] Avg episode reward: [(0, '20.795')] [2023-03-03 14:19:11,892][21357] Updated weights for policy 0, policy_version 7690 (0.0007) [2023-03-03 14:19:15,022][21357] Updated weights for policy 0, policy_version 7700 (0.0007) [2023-03-03 14:19:15,911][21315] Fps is (10 sec: 3276.9, 60 sec: 3327.9, 300 sec: 3235.2). Total num frames: 7886848. Throughput: 0: 3346.0. Samples: 7880162. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:19:15,912][21315] Avg episode reward: [(0, '21.702')] [2023-03-03 14:19:18,142][21357] Updated weights for policy 0, policy_version 7710 (0.0007) [2023-03-03 14:19:20,910][21315] Fps is (10 sec: 3379.1, 60 sec: 3345.1, 300 sec: 3249.0). Total num frames: 7904256. Throughput: 0: 3344.6. Samples: 7900217. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:19:20,910][21315] Avg episode reward: [(0, '24.398')] [2023-03-03 14:19:20,915][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000007719_7904256.pth... [2023-03-03 14:19:20,998][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000006945_7111680.pth [2023-03-03 14:19:21,222][21357] Updated weights for policy 0, policy_version 7720 (0.0006) [2023-03-03 14:19:24,266][21357] Updated weights for policy 0, policy_version 7730 (0.0007) [2023-03-03 14:19:25,911][21315] Fps is (10 sec: 3379.1, 60 sec: 3345.1, 300 sec: 3252.5). Total num frames: 7920640. Throughput: 0: 3349.3. Samples: 7920298. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 14:19:25,912][21315] Avg episode reward: [(0, '24.878')] [2023-03-03 14:19:27,312][21357] Updated weights for policy 0, policy_version 7740 (0.0006) [2023-03-03 14:19:30,380][21357] Updated weights for policy 0, policy_version 7750 (0.0007) [2023-03-03 14:19:30,911][21315] Fps is (10 sec: 3276.2, 60 sec: 3344.9, 300 sec: 3252.5). Total num frames: 7937024. Throughput: 0: 3347.8. Samples: 7930195. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:19:30,912][21315] Avg episode reward: [(0, '21.113')] [2023-03-03 14:19:33,435][21357] Updated weights for policy 0, policy_version 7760 (0.0006) [2023-03-03 14:19:35,914][21315] Fps is (10 sec: 3378.4, 60 sec: 3361.9, 300 sec: 3259.4). Total num frames: 7954432. Throughput: 0: 3340.8. Samples: 7950036. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:19:35,914][21315] Avg episode reward: [(0, '19.264')] [2023-03-03 14:19:36,543][21357] Updated weights for policy 0, policy_version 7770 (0.0006) [2023-03-03 14:19:39,641][21357] Updated weights for policy 0, policy_version 7780 (0.0006) [2023-03-03 14:19:40,912][21315] Fps is (10 sec: 3379.2, 60 sec: 3344.9, 300 sec: 3259.4). Total num frames: 7970816. Throughput: 0: 3339.0. Samples: 7970195. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:19:40,913][21315] Avg episode reward: [(0, '19.504')] [2023-03-03 14:19:42,693][21357] Updated weights for policy 0, policy_version 7790 (0.0006) [2023-03-03 14:19:45,751][21357] Updated weights for policy 0, policy_version 7800 (0.0006) [2023-03-03 14:19:45,909][21315] Fps is (10 sec: 3278.4, 60 sec: 3345.3, 300 sec: 3266.4). Total num frames: 7987200. Throughput: 0: 3337.5. Samples: 7980247. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:19:45,909][21315] Avg episode reward: [(0, '20.332')] [2023-03-03 14:19:48,791][21357] Updated weights for policy 0, policy_version 7810 (0.0007) [2023-03-03 14:19:50,911][21315] Fps is (10 sec: 3276.8, 60 sec: 3327.9, 300 sec: 3276.8). Total num frames: 8003584. Throughput: 0: 3340.5. Samples: 8000381. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:19:50,912][21315] Avg episode reward: [(0, '20.370')] [2023-03-03 14:19:51,849][21357] Updated weights for policy 0, policy_version 7820 (0.0006) [2023-03-03 14:19:54,882][21357] Updated weights for policy 0, policy_version 7830 (0.0007) [2023-03-03 14:19:55,910][21315] Fps is (10 sec: 3378.9, 60 sec: 3345.0, 300 sec: 3287.2). Total num frames: 8020992. Throughput: 0: 3336.0. Samples: 8020260. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:19:55,910][21315] Avg episode reward: [(0, '20.506')] [2023-03-03 14:19:58,000][21357] Updated weights for policy 0, policy_version 7840 (0.0007) [2023-03-03 14:20:00,909][21315] Fps is (10 sec: 3380.0, 60 sec: 3345.2, 300 sec: 3290.7). Total num frames: 8037376. Throughput: 0: 3334.2. Samples: 8030197. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:20:00,910][21315] Avg episode reward: [(0, '20.200')] [2023-03-03 14:20:01,101][21357] Updated weights for policy 0, policy_version 7850 (0.0007) [2023-03-03 14:20:04,137][21357] Updated weights for policy 0, policy_version 7860 (0.0006) [2023-03-03 14:20:05,911][21315] Fps is (10 sec: 3276.4, 60 sec: 3328.0, 300 sec: 3294.2). Total num frames: 8053760. Throughput: 0: 3337.8. Samples: 8050424. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:20:05,912][21315] Avg episode reward: [(0, '18.522')] [2023-03-03 14:20:07,153][21357] Updated weights for policy 0, policy_version 7870 (0.0006) [2023-03-03 14:20:10,145][21357] Updated weights for policy 0, policy_version 7880 (0.0006) [2023-03-03 14:20:10,911][21315] Fps is (10 sec: 3378.5, 60 sec: 3345.0, 300 sec: 3308.0). Total num frames: 8071168. Throughput: 0: 3345.7. Samples: 8070854. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:20:10,912][21315] Avg episode reward: [(0, '18.164')] [2023-03-03 14:20:13,194][21357] Updated weights for policy 0, policy_version 7890 (0.0006) [2023-03-03 14:20:15,912][21315] Fps is (10 sec: 3378.8, 60 sec: 3345.0, 300 sec: 3308.0). Total num frames: 8087552. Throughput: 0: 3349.2. Samples: 8080913. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:20:15,913][21315] Avg episode reward: [(0, '19.695')] [2023-03-03 14:20:16,274][21357] Updated weights for policy 0, policy_version 7900 (0.0006) [2023-03-03 14:20:19,334][21357] Updated weights for policy 0, policy_version 7910 (0.0007) [2023-03-03 14:20:20,911][21315] Fps is (10 sec: 3379.3, 60 sec: 3345.0, 300 sec: 3311.5). Total num frames: 8104960. Throughput: 0: 3352.1. Samples: 8100871. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:20:20,912][21315] Avg episode reward: [(0, '23.907')] [2023-03-03 14:20:22,416][21357] Updated weights for policy 0, policy_version 7920 (0.0007) [2023-03-03 14:20:25,502][21357] Updated weights for policy 0, policy_version 7930 (0.0006) [2023-03-03 14:20:25,911][21315] Fps is (10 sec: 3379.7, 60 sec: 3345.1, 300 sec: 3311.5). Total num frames: 8121344. Throughput: 0: 3347.8. Samples: 8120842. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:20:25,911][21315] Avg episode reward: [(0, '23.103')] [2023-03-03 14:20:28,533][21357] Updated weights for policy 0, policy_version 7940 (0.0007) [2023-03-03 14:20:30,909][21315] Fps is (10 sec: 3277.5, 60 sec: 3345.2, 300 sec: 3315.0). Total num frames: 8137728. Throughput: 0: 3349.9. Samples: 8130992. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:20:30,911][21315] Avg episode reward: [(0, '23.347')] [2023-03-03 14:20:31,626][21357] Updated weights for policy 0, policy_version 7950 (0.0006) [2023-03-03 14:20:34,657][21357] Updated weights for policy 0, policy_version 7960 (0.0006) [2023-03-03 14:20:35,910][21315] Fps is (10 sec: 3277.0, 60 sec: 3328.2, 300 sec: 3318.5). Total num frames: 8154112. Throughput: 0: 3345.1. Samples: 8150905. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:20:35,911][21315] Avg episode reward: [(0, '20.074')] [2023-03-03 14:20:37,769][21357] Updated weights for policy 0, policy_version 7970 (0.0007) [2023-03-03 14:20:40,819][21357] Updated weights for policy 0, policy_version 7980 (0.0006) [2023-03-03 14:20:40,910][21315] Fps is (10 sec: 3379.0, 60 sec: 3345.2, 300 sec: 3325.4). Total num frames: 8171520. Throughput: 0: 3349.2. Samples: 8170973. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:20:40,910][21315] Avg episode reward: [(0, '22.167')] [2023-03-03 14:20:43,927][21357] Updated weights for policy 0, policy_version 7990 (0.0007) [2023-03-03 14:20:45,912][21315] Fps is (10 sec: 3378.5, 60 sec: 3344.9, 300 sec: 3328.9). Total num frames: 8187904. Throughput: 0: 3352.2. Samples: 8181055. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:20:45,913][21315] Avg episode reward: [(0, '21.954')] [2023-03-03 14:20:46,973][21357] Updated weights for policy 0, policy_version 8000 (0.0006) [2023-03-03 14:20:49,995][21357] Updated weights for policy 0, policy_version 8010 (0.0007) [2023-03-03 14:20:50,916][21315] Fps is (10 sec: 3274.6, 60 sec: 3344.8, 300 sec: 3332.3). Total num frames: 8204288. Throughput: 0: 3344.9. Samples: 8200961. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:20:50,917][21315] Avg episode reward: [(0, '31.655')] [2023-03-03 14:20:53,260][21357] Updated weights for policy 0, policy_version 8020 (0.0007) [2023-03-03 14:20:55,914][21315] Fps is (10 sec: 3276.2, 60 sec: 3327.8, 300 sec: 3332.3). Total num frames: 8220672. Throughput: 0: 3322.4. Samples: 8220368. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:20:55,916][21315] Avg episode reward: [(0, '29.195')] [2023-03-03 14:20:56,426][21357] Updated weights for policy 0, policy_version 8030 (0.0007) [2023-03-03 14:20:59,523][21357] Updated weights for policy 0, policy_version 8040 (0.0006) [2023-03-03 14:21:00,909][21315] Fps is (10 sec: 3279.2, 60 sec: 3328.0, 300 sec: 3332.3). Total num frames: 8237056. Throughput: 0: 3314.3. Samples: 8230046. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:21:00,910][21315] Avg episode reward: [(0, '28.888')] [2023-03-03 14:21:02,759][21357] Updated weights for policy 0, policy_version 8050 (0.0007) [2023-03-03 14:21:05,863][21357] Updated weights for policy 0, policy_version 8060 (0.0006) [2023-03-03 14:21:05,916][21315] Fps is (10 sec: 3276.0, 60 sec: 3327.7, 300 sec: 3332.3). Total num frames: 8253440. Throughput: 0: 3298.7. Samples: 8249331. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 14:21:05,917][21315] Avg episode reward: [(0, '20.100')] [2023-03-03 14:21:09,042][21357] Updated weights for policy 0, policy_version 8070 (0.0007) [2023-03-03 14:21:10,915][21315] Fps is (10 sec: 3172.6, 60 sec: 3293.7, 300 sec: 3328.8). Total num frames: 8268800. Throughput: 0: 3284.8. Samples: 8268671. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 14:21:10,915][21315] Avg episode reward: [(0, '20.538')] [2023-03-03 14:21:12,202][21357] Updated weights for policy 0, policy_version 8080 (0.0007) [2023-03-03 14:21:15,345][21357] Updated weights for policy 0, policy_version 8090 (0.0007) [2023-03-03 14:21:15,910][21315] Fps is (10 sec: 3176.5, 60 sec: 3294.0, 300 sec: 3328.9). Total num frames: 8285184. Throughput: 0: 3274.4. Samples: 8278341. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) [2023-03-03 14:21:15,912][21315] Avg episode reward: [(0, '20.656')] [2023-03-03 14:21:18,681][21357] Updated weights for policy 0, policy_version 8100 (0.0007) [2023-03-03 14:21:20,912][21315] Fps is (10 sec: 3277.7, 60 sec: 3276.8, 300 sec: 3325.4). Total num frames: 8301568. Throughput: 0: 3256.8. Samples: 8297468. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:21:20,913][21315] Avg episode reward: [(0, '18.483')] [2023-03-03 14:21:20,919][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000008107_8301568.pth... [2023-03-03 14:21:20,999][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000007328_7503872.pth [2023-03-03 14:21:21,949][21357] Updated weights for policy 0, policy_version 8110 (0.0008) [2023-03-03 14:21:25,152][21357] Updated weights for policy 0, policy_version 8120 (0.0007) [2023-03-03 14:21:25,910][21315] Fps is (10 sec: 3174.2, 60 sec: 3259.8, 300 sec: 3321.9). Total num frames: 8316928. Throughput: 0: 3235.6. Samples: 8316577. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:21:25,911][21315] Avg episode reward: [(0, '19.158')] [2023-03-03 14:21:28,192][21357] Updated weights for policy 0, policy_version 8130 (0.0006) [2023-03-03 14:21:30,910][21315] Fps is (10 sec: 3175.2, 60 sec: 3259.7, 300 sec: 3321.9). Total num frames: 8333312. Throughput: 0: 3235.5. Samples: 8326645. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:21:30,910][21315] Avg episode reward: [(0, '17.730')] [2023-03-03 14:21:31,242][21357] Updated weights for policy 0, policy_version 8140 (0.0007) [2023-03-03 14:21:34,349][21357] Updated weights for policy 0, policy_version 8150 (0.0006) [2023-03-03 14:21:35,910][21315] Fps is (10 sec: 3276.8, 60 sec: 3259.7, 300 sec: 3321.9). Total num frames: 8349696. Throughput: 0: 3235.2. Samples: 8346524. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:21:35,911][21315] Avg episode reward: [(0, '20.391')] [2023-03-03 14:21:37,495][21357] Updated weights for policy 0, policy_version 8160 (0.0006) [2023-03-03 14:21:40,671][21357] Updated weights for policy 0, policy_version 8170 (0.0006) [2023-03-03 14:21:40,910][21315] Fps is (10 sec: 3276.8, 60 sec: 3242.7, 300 sec: 3318.5). Total num frames: 8366080. Throughput: 0: 3235.0. Samples: 8365929. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:21:40,910][21315] Avg episode reward: [(0, '21.280')] [2023-03-03 14:21:43,780][21357] Updated weights for policy 0, policy_version 8180 (0.0007) [2023-03-03 14:21:45,912][21315] Fps is (10 sec: 3276.3, 60 sec: 3242.7, 300 sec: 3318.5). Total num frames: 8382464. Throughput: 0: 3239.5. Samples: 8375830. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:21:45,914][21315] Avg episode reward: [(0, '21.729')] [2023-03-03 14:21:46,905][21357] Updated weights for policy 0, policy_version 8190 (0.0007) [2023-03-03 14:21:50,063][21357] Updated weights for policy 0, policy_version 8200 (0.0007) [2023-03-03 14:21:50,909][21315] Fps is (10 sec: 3276.9, 60 sec: 3243.1, 300 sec: 3318.5). Total num frames: 8398848. Throughput: 0: 3243.8. Samples: 8395277. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:21:50,911][21315] Avg episode reward: [(0, '18.581')] [2023-03-03 14:21:53,140][21357] Updated weights for policy 0, policy_version 8210 (0.0006) [2023-03-03 14:21:55,916][21315] Fps is (10 sec: 3275.3, 60 sec: 3242.5, 300 sec: 3314.9). Total num frames: 8415232. Throughput: 0: 3256.6. Samples: 8415222. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:21:55,917][21315] Avg episode reward: [(0, '18.206')] [2023-03-03 14:21:56,292][21357] Updated weights for policy 0, policy_version 8220 (0.0008) [2023-03-03 14:21:59,416][21357] Updated weights for policy 0, policy_version 8230 (0.0007) [2023-03-03 14:22:00,913][21315] Fps is (10 sec: 3275.6, 60 sec: 3242.5, 300 sec: 3318.4). Total num frames: 8431616. Throughput: 0: 3262.2. Samples: 8425150. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:22:00,914][21315] Avg episode reward: [(0, '19.861')] [2023-03-03 14:22:02,561][21357] Updated weights for policy 0, policy_version 8240 (0.0007) [2023-03-03 14:22:05,623][21357] Updated weights for policy 0, policy_version 8250 (0.0006) [2023-03-03 14:22:05,914][21315] Fps is (10 sec: 3277.5, 60 sec: 3242.8, 300 sec: 3314.9). Total num frames: 8448000. Throughput: 0: 3269.3. Samples: 8444594. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:22:05,915][21315] Avg episode reward: [(0, '21.798')] [2023-03-03 14:22:08,683][21357] Updated weights for policy 0, policy_version 8260 (0.0006) [2023-03-03 14:22:10,916][21315] Fps is (10 sec: 3378.2, 60 sec: 3276.7, 300 sec: 3318.4). Total num frames: 8465408. Throughput: 0: 3289.6. Samples: 8464629. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:22:10,916][21315] Avg episode reward: [(0, '20.669')] [2023-03-03 14:22:11,754][21357] Updated weights for policy 0, policy_version 8270 (0.0006) [2023-03-03 14:22:14,861][21357] Updated weights for policy 0, policy_version 8280 (0.0006) [2023-03-03 14:22:15,909][21315] Fps is (10 sec: 3381.0, 60 sec: 3276.8, 300 sec: 3318.5). Total num frames: 8481792. Throughput: 0: 3288.6. Samples: 8474630. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:22:15,909][21315] Avg episode reward: [(0, '19.754')] [2023-03-03 14:22:18,014][21357] Updated weights for policy 0, policy_version 8290 (0.0006) [2023-03-03 14:22:20,916][21315] Fps is (10 sec: 3276.7, 60 sec: 3276.6, 300 sec: 3318.4). Total num frames: 8498176. Throughput: 0: 3289.5. Samples: 8494571. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:22:20,917][21315] Avg episode reward: [(0, '20.562')] [2023-03-03 14:22:21,173][21357] Updated weights for policy 0, policy_version 8300 (0.0007) [2023-03-03 14:22:24,318][21357] Updated weights for policy 0, policy_version 8310 (0.0006) [2023-03-03 14:22:25,916][21315] Fps is (10 sec: 3274.4, 60 sec: 3293.5, 300 sec: 3318.4). Total num frames: 8514560. Throughput: 0: 3291.3. Samples: 8514059. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:22:25,917][21315] Avg episode reward: [(0, '20.030')] [2023-03-03 14:22:27,349][21357] Updated weights for policy 0, policy_version 8320 (0.0006) [2023-03-03 14:22:30,421][21357] Updated weights for policy 0, policy_version 8330 (0.0007) [2023-03-03 14:22:30,916][21315] Fps is (10 sec: 3276.8, 60 sec: 3293.5, 300 sec: 3314.9). Total num frames: 8530944. Throughput: 0: 3292.2. Samples: 8523996. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:22:30,917][21315] Avg episode reward: [(0, '18.398')] [2023-03-03 14:22:33,435][21357] Updated weights for policy 0, policy_version 8340 (0.0007) [2023-03-03 14:22:35,916][21315] Fps is (10 sec: 3379.2, 60 sec: 3310.6, 300 sec: 3318.4). Total num frames: 8548352. Throughput: 0: 3303.0. Samples: 8543936. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:22:35,917][21315] Avg episode reward: [(0, '18.773')] [2023-03-03 14:22:36,451][21357] Updated weights for policy 0, policy_version 8350 (0.0007) [2023-03-03 14:22:39,463][21357] Updated weights for policy 0, policy_version 8360 (0.0007) [2023-03-03 14:22:40,916][21315] Fps is (10 sec: 3379.3, 60 sec: 3310.6, 300 sec: 3318.4). Total num frames: 8564736. Throughput: 0: 3320.5. Samples: 8564645. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:22:40,917][21315] Avg episode reward: [(0, '19.695')] [2023-03-03 14:22:42,470][21357] Updated weights for policy 0, policy_version 8370 (0.0006) [2023-03-03 14:22:45,447][21357] Updated weights for policy 0, policy_version 8380 (0.0007) [2023-03-03 14:22:45,916][21315] Fps is (10 sec: 3379.2, 60 sec: 3327.7, 300 sec: 3318.4). Total num frames: 8582144. Throughput: 0: 3329.6. Samples: 8574994. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:22:45,917][21315] Avg episode reward: [(0, '24.121')] [2023-03-03 14:22:48,426][21357] Updated weights for policy 0, policy_version 8390 (0.0006) [2023-03-03 14:22:50,909][21315] Fps is (10 sec: 3484.0, 60 sec: 3345.1, 300 sec: 3321.9). Total num frames: 8599552. Throughput: 0: 3356.0. Samples: 8595599. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:22:50,910][21315] Avg episode reward: [(0, '23.752')] [2023-03-03 14:22:51,385][21357] Updated weights for policy 0, policy_version 8400 (0.0006) [2023-03-03 14:22:54,358][21357] Updated weights for policy 0, policy_version 8410 (0.0007) [2023-03-03 14:22:55,909][21315] Fps is (10 sec: 3484.0, 60 sec: 3362.5, 300 sec: 3321.9). Total num frames: 8616960. Throughput: 0: 3366.3. Samples: 8616090. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:22:55,910][21315] Avg episode reward: [(0, '22.392')] [2023-03-03 14:22:57,317][21357] Updated weights for policy 0, policy_version 8420 (0.0007) [2023-03-03 14:23:00,273][21357] Updated weights for policy 0, policy_version 8430 (0.0006) [2023-03-03 14:23:00,913][21315] Fps is (10 sec: 3480.3, 60 sec: 3379.2, 300 sec: 3325.4). Total num frames: 8634368. Throughput: 0: 3373.0. Samples: 8626431. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:23:00,914][21315] Avg episode reward: [(0, '19.242')] [2023-03-03 14:23:03,416][21357] Updated weights for policy 0, policy_version 8440 (0.0007) [2023-03-03 14:23:05,914][21315] Fps is (10 sec: 3377.6, 60 sec: 3379.2, 300 sec: 3325.3). Total num frames: 8650752. Throughput: 0: 3372.5. Samples: 8646328. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:23:05,915][21315] Avg episode reward: [(0, '18.757')] [2023-03-03 14:23:06,556][21357] Updated weights for policy 0, policy_version 8450 (0.0006) [2023-03-03 14:23:09,534][21357] Updated weights for policy 0, policy_version 8460 (0.0006) [2023-03-03 14:23:10,916][21315] Fps is (10 sec: 3275.7, 60 sec: 3362.1, 300 sec: 3321.9). Total num frames: 8667136. Throughput: 0: 3396.6. Samples: 8666905. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:23:10,917][21315] Avg episode reward: [(0, '21.500')] [2023-03-03 14:23:12,520][21357] Updated weights for policy 0, policy_version 8470 (0.0007) [2023-03-03 14:23:15,464][21357] Updated weights for policy 0, policy_version 8480 (0.0007) [2023-03-03 14:23:15,909][21315] Fps is (10 sec: 3381.0, 60 sec: 3379.2, 300 sec: 3325.4). Total num frames: 8684544. Throughput: 0: 3406.8. Samples: 8677277. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:23:15,910][21315] Avg episode reward: [(0, '23.016')] [2023-03-03 14:23:18,380][21357] Updated weights for policy 0, policy_version 8490 (0.0006) [2023-03-03 14:23:20,913][21315] Fps is (10 sec: 3482.8, 60 sec: 3396.5, 300 sec: 3328.9). Total num frames: 8701952. Throughput: 0: 3429.2. Samples: 8698238. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:23:20,913][21315] Avg episode reward: [(0, '22.562')] [2023-03-03 14:23:21,016][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000008499_8702976.pth... [2023-03-03 14:23:21,070][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000007719_7904256.pth [2023-03-03 14:23:21,309][21357] Updated weights for policy 0, policy_version 8500 (0.0007) [2023-03-03 14:23:24,259][21357] Updated weights for policy 0, policy_version 8510 (0.0006) [2023-03-03 14:23:25,915][21315] Fps is (10 sec: 3479.7, 60 sec: 3413.4, 300 sec: 3332.3). Total num frames: 8719360. Throughput: 0: 3427.1. Samples: 8718857. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:23:25,916][21315] Avg episode reward: [(0, '19.383')] [2023-03-03 14:23:27,189][21357] Updated weights for policy 0, policy_version 8520 (0.0007) [2023-03-03 14:23:30,158][21357] Updated weights for policy 0, policy_version 8530 (0.0006) [2023-03-03 14:23:30,910][21315] Fps is (10 sec: 3482.6, 60 sec: 3430.8, 300 sec: 3335.8). Total num frames: 8736768. Throughput: 0: 3430.4. Samples: 8729338. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:23:30,910][21315] Avg episode reward: [(0, '18.133')] [2023-03-03 14:23:33,176][21357] Updated weights for policy 0, policy_version 8540 (0.0007) [2023-03-03 14:23:35,910][21315] Fps is (10 sec: 3483.0, 60 sec: 3430.7, 300 sec: 3335.8). Total num frames: 8754176. Throughput: 0: 3433.4. Samples: 8750107. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:23:35,911][21315] Avg episode reward: [(0, '20.549')] [2023-03-03 14:23:36,153][21357] Updated weights for policy 0, policy_version 8550 (0.0006) [2023-03-03 14:23:39,105][21357] Updated weights for policy 0, policy_version 8560 (0.0006) [2023-03-03 14:23:40,915][21315] Fps is (10 sec: 3479.6, 60 sec: 3447.5, 300 sec: 3339.2). Total num frames: 8771584. Throughput: 0: 3441.8. Samples: 8770990. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:23:40,916][21315] Avg episode reward: [(0, '21.083')] [2023-03-03 14:23:42,048][21357] Updated weights for policy 0, policy_version 8570 (0.0006) [2023-03-03 14:23:44,980][21357] Updated weights for policy 0, policy_version 8580 (0.0006) [2023-03-03 14:23:45,909][21315] Fps is (10 sec: 3482.1, 60 sec: 3447.9, 300 sec: 3339.3). Total num frames: 8788992. Throughput: 0: 3443.9. Samples: 8781392. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:23:45,910][21315] Avg episode reward: [(0, '20.941')] [2023-03-03 14:23:47,896][21357] Updated weights for policy 0, policy_version 8590 (0.0007) [2023-03-03 14:23:50,863][21357] Updated weights for policy 0, policy_version 8600 (0.0007) [2023-03-03 14:23:50,910][21315] Fps is (10 sec: 3483.4, 60 sec: 3447.4, 300 sec: 3342.7). Total num frames: 8806400. Throughput: 0: 3461.1. Samples: 8802061. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:23:50,911][21315] Avg episode reward: [(0, '18.861')] [2023-03-03 14:23:53,795][21357] Updated weights for policy 0, policy_version 8610 (0.0007) [2023-03-03 14:23:55,909][21315] Fps is (10 sec: 3481.7, 60 sec: 3447.5, 300 sec: 3346.2). Total num frames: 8823808. Throughput: 0: 3467.1. Samples: 8822897. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:23:55,909][21315] Avg episode reward: [(0, '19.053')] [2023-03-03 14:23:56,746][21357] Updated weights for policy 0, policy_version 8620 (0.0007) [2023-03-03 14:23:59,694][21357] Updated weights for policy 0, policy_version 8630 (0.0006) [2023-03-03 14:24:00,912][21315] Fps is (10 sec: 3378.5, 60 sec: 3430.4, 300 sec: 3342.7). Total num frames: 8840192. Throughput: 0: 3469.3. Samples: 8833407. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:24:00,913][21315] Avg episode reward: [(0, '19.437')] [2023-03-03 14:24:02,707][21357] Updated weights for policy 0, policy_version 8640 (0.0006) [2023-03-03 14:24:05,672][21357] Updated weights for policy 0, policy_version 8650 (0.0007) [2023-03-03 14:24:05,916][21315] Fps is (10 sec: 3376.7, 60 sec: 3447.4, 300 sec: 3346.1). Total num frames: 8857600. Throughput: 0: 3466.7. Samples: 8854252. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:24:05,918][21315] Avg episode reward: [(0, '20.549')] [2023-03-03 14:24:08,613][21357] Updated weights for policy 0, policy_version 8660 (0.0007) [2023-03-03 14:24:10,913][21315] Fps is (10 sec: 3481.2, 60 sec: 3464.7, 300 sec: 3349.7). Total num frames: 8875008. Throughput: 0: 3468.4. Samples: 8874932. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:24:10,914][21315] Avg episode reward: [(0, '20.618')] [2023-03-03 14:24:11,565][21357] Updated weights for policy 0, policy_version 8670 (0.0006) [2023-03-03 14:24:14,548][21357] Updated weights for policy 0, policy_version 8680 (0.0007) [2023-03-03 14:24:15,910][21315] Fps is (10 sec: 3483.8, 60 sec: 3464.5, 300 sec: 3349.7). Total num frames: 8892416. Throughput: 0: 3459.7. Samples: 8885028. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:24:15,910][21315] Avg episode reward: [(0, '21.355')] [2023-03-03 14:24:17,501][21357] Updated weights for policy 0, policy_version 8690 (0.0006) [2023-03-03 14:24:20,424][21357] Updated weights for policy 0, policy_version 8700 (0.0006) [2023-03-03 14:24:20,914][21315] Fps is (10 sec: 3481.3, 60 sec: 3464.4, 300 sec: 3353.1). Total num frames: 8909824. Throughput: 0: 3461.2. Samples: 8905874. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:24:20,915][21315] Avg episode reward: [(0, '21.109')] [2023-03-03 14:24:23,361][21357] Updated weights for policy 0, policy_version 8710 (0.0007) [2023-03-03 14:24:25,909][21315] Fps is (10 sec: 3481.9, 60 sec: 3464.9, 300 sec: 3356.7). Total num frames: 8927232. Throughput: 0: 3464.4. Samples: 8926865. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:24:25,910][21315] Avg episode reward: [(0, '20.266')] [2023-03-03 14:24:26,410][21357] Updated weights for policy 0, policy_version 8720 (0.0006) [2023-03-03 14:24:29,373][21357] Updated weights for policy 0, policy_version 8730 (0.0006) [2023-03-03 14:24:30,915][21315] Fps is (10 sec: 3481.3, 60 sec: 3464.2, 300 sec: 3356.6). Total num frames: 8944640. Throughput: 0: 3458.5. Samples: 8937046. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:24:30,915][21315] Avg episode reward: [(0, '20.367')] [2023-03-03 14:24:32,366][21357] Updated weights for policy 0, policy_version 8740 (0.0007) [2023-03-03 14:24:35,389][21357] Updated weights for policy 0, policy_version 8750 (0.0006) [2023-03-03 14:24:35,912][21315] Fps is (10 sec: 3378.3, 60 sec: 3447.4, 300 sec: 3356.6). Total num frames: 8961024. Throughput: 0: 3458.7. Samples: 8957710. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:24:35,913][21315] Avg episode reward: [(0, '20.450')] [2023-03-03 14:24:38,747][21357] Updated weights for policy 0, policy_version 8760 (0.0007) [2023-03-03 14:24:40,910][21315] Fps is (10 sec: 3278.4, 60 sec: 3430.7, 300 sec: 3356.6). Total num frames: 8977408. Throughput: 0: 3413.9. Samples: 8976527. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:24:40,912][21315] Avg episode reward: [(0, '19.074')] [2023-03-03 14:24:41,761][21357] Updated weights for policy 0, policy_version 8770 (0.0006) [2023-03-03 14:24:44,842][21357] Updated weights for policy 0, policy_version 8780 (0.0006) [2023-03-03 14:24:45,916][21315] Fps is (10 sec: 3275.4, 60 sec: 3412.9, 300 sec: 3356.6). Total num frames: 8993792. Throughput: 0: 3402.7. Samples: 8986540. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:24:45,916][21315] Avg episode reward: [(0, '18.050')] [2023-03-03 14:24:47,883][21357] Updated weights for policy 0, policy_version 8790 (0.0006) [2023-03-03 14:24:50,916][21315] Fps is (10 sec: 3274.8, 60 sec: 3395.9, 300 sec: 3353.1). Total num frames: 9010176. Throughput: 0: 3390.2. Samples: 9006812. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:24:50,917][21315] Avg episode reward: [(0, '18.733')] [2023-03-03 14:24:51,016][21357] Updated weights for policy 0, policy_version 8800 (0.0007) [2023-03-03 14:24:54,301][21357] Updated weights for policy 0, policy_version 8810 (0.0006) [2023-03-03 14:24:55,917][21315] Fps is (10 sec: 3276.7, 60 sec: 3378.8, 300 sec: 3353.1). Total num frames: 9026560. Throughput: 0: 3358.4. Samples: 9026068. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:24:55,919][21315] Avg episode reward: [(0, '20.029')] [2023-03-03 14:24:57,440][21357] Updated weights for policy 0, policy_version 8820 (0.0006) [2023-03-03 14:25:00,540][21357] Updated weights for policy 0, policy_version 8830 (0.0007) [2023-03-03 14:25:00,910][21315] Fps is (10 sec: 3278.9, 60 sec: 3379.3, 300 sec: 3353.2). Total num frames: 9042944. Throughput: 0: 3346.8. Samples: 9035634. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:25:00,910][21315] Avg episode reward: [(0, '21.100')] [2023-03-03 14:25:03,458][21357] Updated weights for policy 0, policy_version 8840 (0.0006) [2023-03-03 14:25:05,916][21315] Fps is (10 sec: 3379.3, 60 sec: 3379.2, 300 sec: 3353.1). Total num frames: 9060352. Throughput: 0: 3338.2. Samples: 9056099. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:25:05,917][21315] Avg episode reward: [(0, '18.461')] [2023-03-03 14:25:06,379][21357] Updated weights for policy 0, policy_version 8850 (0.0006) [2023-03-03 14:25:09,303][21357] Updated weights for policy 0, policy_version 8860 (0.0006) [2023-03-03 14:25:10,911][21315] Fps is (10 sec: 3481.3, 60 sec: 3379.3, 300 sec: 3356.7). Total num frames: 9077760. Throughput: 0: 3339.3. Samples: 9077138. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:25:10,911][21315] Avg episode reward: [(0, '18.123')] [2023-03-03 14:25:12,302][21357] Updated weights for policy 0, policy_version 8870 (0.0007) [2023-03-03 14:25:15,304][21357] Updated weights for policy 0, policy_version 8880 (0.0007) [2023-03-03 14:25:15,910][21315] Fps is (10 sec: 3381.3, 60 sec: 3362.1, 300 sec: 3353.2). Total num frames: 9094144. Throughput: 0: 3342.7. Samples: 9087450. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) [2023-03-03 14:25:15,911][21315] Avg episode reward: [(0, '16.888')] [2023-03-03 14:25:18,341][21357] Updated weights for policy 0, policy_version 8890 (0.0006) [2023-03-03 14:25:20,914][21315] Fps is (10 sec: 3378.1, 60 sec: 3362.1, 300 sec: 3356.6). Total num frames: 9111552. Throughput: 0: 3336.4. Samples: 9107854. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:25:20,915][21315] Avg episode reward: [(0, '16.174')] [2023-03-03 14:25:21,094][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000008899_9112576.pth... [2023-03-03 14:25:21,169][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000008107_8301568.pth [2023-03-03 14:25:21,414][21357] Updated weights for policy 0, policy_version 8900 (0.0006) [2023-03-03 14:25:24,482][21357] Updated weights for policy 0, policy_version 8910 (0.0007) [2023-03-03 14:25:25,916][21315] Fps is (10 sec: 3377.1, 60 sec: 3344.7, 300 sec: 3356.6). Total num frames: 9127936. Throughput: 0: 3361.8. Samples: 9127828. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:25:25,917][21315] Avg episode reward: [(0, '16.795')] [2023-03-03 14:25:27,884][21357] Updated weights for policy 0, policy_version 8920 (0.0007) [2023-03-03 14:25:30,912][21315] Fps is (10 sec: 3175.2, 60 sec: 3311.1, 300 sec: 3353.1). Total num frames: 9143296. Throughput: 0: 3330.0. Samples: 9136376. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-03 14:25:30,913][21315] Avg episode reward: [(0, '17.570')] [2023-03-03 14:25:31,109][21357] Updated weights for policy 0, policy_version 8930 (0.0007) [2023-03-03 14:25:34,709][21357] Updated weights for policy 0, policy_version 8940 (0.0008) [2023-03-03 14:25:35,911][21315] Fps is (10 sec: 2868.6, 60 sec: 3259.8, 300 sec: 3339.3). Total num frames: 9156608. Throughput: 0: 3286.8. Samples: 9154699. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:25:35,913][21315] Avg episode reward: [(0, '18.322')] [2023-03-03 14:25:38,418][21357] Updated weights for policy 0, policy_version 8950 (0.0008) [2023-03-03 14:25:40,909][21315] Fps is (10 sec: 2867.9, 60 sec: 3242.7, 300 sec: 3335.8). Total num frames: 9171968. Throughput: 0: 3236.3. Samples: 9171677. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) [2023-03-03 14:25:40,910][21315] Avg episode reward: [(0, '18.841')] [2023-03-03 14:25:41,584][21357] Updated weights for policy 0, policy_version 8960 (0.0006) [2023-03-03 14:25:44,665][21357] Updated weights for policy 0, policy_version 8970 (0.0006) [2023-03-03 14:25:45,910][21315] Fps is (10 sec: 3174.9, 60 sec: 3243.0, 300 sec: 3335.9). Total num frames: 9188352. Throughput: 0: 3248.3. Samples: 9181804. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:25:45,911][21315] Avg episode reward: [(0, '17.928')] [2023-03-03 14:25:48,459][21357] Updated weights for policy 0, policy_version 8980 (0.0010) [2023-03-03 14:25:50,911][21315] Fps is (10 sec: 3071.5, 60 sec: 3208.8, 300 sec: 3328.9). Total num frames: 9202688. Throughput: 0: 3178.3. Samples: 9199108. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-03-03 14:25:50,912][21315] Avg episode reward: [(0, '17.818')] [2023-03-03 14:25:51,716][21357] Updated weights for policy 0, policy_version 8990 (0.0007) [2023-03-03 14:25:53,657][21315] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 21315], exiting... [2023-03-03 14:25:53,662][21315] Runner profile tree view: main_loop: 3030.6515 [2023-03-03 14:25:53,663][21315] Collected {0: 9210880}, FPS: 3039.2 [2023-03-03 14:25:53,662][21356] Stopping Batcher_0... [2023-03-03 14:25:53,664][21356] Loop batcher_evt_loop terminating... [2023-03-03 14:25:53,665][21362] Stopping RolloutWorker_w4... [2023-03-03 14:25:53,665][21361] Stopping RolloutWorker_w3... [2023-03-03 14:25:53,680][21362] Loop rollout_proc4_evt_loop terminating... [2023-03-03 14:25:53,684][21361] Loop rollout_proc3_evt_loop terminating... [2023-03-03 14:25:53,674][21364] Stopping RolloutWorker_w6... [2023-03-03 14:25:53,675][21363] Stopping RolloutWorker_w5... [2023-03-03 14:25:53,689][21364] Loop rollout_proc6_evt_loop terminating... [2023-03-03 14:25:53,677][21360] Stopping RolloutWorker_w2... [2023-03-03 14:25:53,692][21363] Loop rollout_proc5_evt_loop terminating... [2023-03-03 14:25:53,691][21360] Loop rollout_proc2_evt_loop terminating... [2023-03-03 14:25:53,680][21358] Stopping RolloutWorker_w1... [2023-03-03 14:25:53,695][21358] Loop rollout_proc1_evt_loop terminating... [2023-03-03 14:25:53,686][21359] Stopping RolloutWorker_w0... [2023-03-03 14:25:53,689][21365] Stopping RolloutWorker_w7... [2023-03-03 14:25:53,699][21359] Loop rollout_proc0_evt_loop terminating... [2023-03-03 14:25:53,701][21365] Loop rollout_proc7_evt_loop terminating... [2023-03-03 14:25:53,730][21356] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000008996_9211904.pth... [2023-03-03 14:25:53,802][21356] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000008499_8702976.pth [2023-03-03 14:25:53,844][21356] Stopping LearnerWorker_p0... [2023-03-03 14:25:53,844][21356] Loop learner_proc0_evt_loop terminating... [2023-03-03 14:25:54,149][21357] Weights refcount: 2 0 [2023-03-03 14:25:54,263][21357] Stopping InferenceWorker_p0-w0... [2023-03-03 14:25:54,268][21357] Loop inference_proc0-0_evt_loop terminating...