2025-04-02 13:30:02 | [maml_trainer] Logging to /home/h2khalil/MetaRL-Assistive-Robotics/data/local/experiment/maml_trainer_1 2025-04-02 13:35:21 | [maml_trainer] Obtaining samples... 2025-04-02 13:39:49 | [maml_trainer] epoch #0 | Sampling for adapation and meta-testing... 2025-04-02 13:40:57 | [maml_trainer] epoch #0 | Finished meta-testing... 2025-04-02 13:40:57 | [maml_trainer] epoch #0 | Saving snapshot... 2025-04-02 13:41:16 | [maml_trainer] epoch #0 | Saved 2025-04-02 13:41:16 | [maml_trainer] epoch #0 | Time 354.93 s 2025-04-02 13:41:16 | [maml_trainer] epoch #0 | EpochTime 354.93 s ------------------------------------------------- --------------- Average/AverageDiscountedReturn -75.0138 Average/AverageReturn -179.122 Average/Iteration 0 Average/MaxReturn -142.547 Average/MinReturn -256.108 Average/NumEpisodes 80 Average/StdReturn 13.1643 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.8512 GaussianMLPPolicy/KLAfter 0.0293924 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000417959 GaussianMLPPolicy/LossBefore 1.81794e-09 GaussianMLPPolicy/dLoss -0.000417957 Iteration 0 MetaTest/Average/AverageDiscountedReturn -173.938 MetaTest/Average/AverageReturn -173.938 MetaTest/Average/Iteration 0 MetaTest/Average/MaxReturn -149.767 MetaTest/Average/MinReturn -191.06 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.70461 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.938 MetaTest/__unnamed_task__/AverageReturn -173.938 MetaTest/__unnamed_task__/Iteration 0 MetaTest/__unnamed_task__/MaxReturn -149.767 MetaTest/__unnamed_task__/MinReturn -191.06 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.70461 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 32000 __unnamed_task__/AverageDiscountedReturn -75.0138 __unnamed_task__/AverageReturn -179.122 __unnamed_task__/Iteration 0 __unnamed_task__/MaxReturn -142.547 __unnamed_task__/MinReturn -256.108 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.1643 __unnamed_task__/TerminationRate 0 ------------------------------------------------- --------------- 2025-04-02 13:45:49 | [maml_trainer] epoch #1 | Sampling for adapation and meta-testing... 2025-04-02 13:46:59 | [maml_trainer] epoch #1 | Finished meta-testing... 2025-04-02 13:46:59 | [maml_trainer] epoch #1 | Saving snapshot... 2025-04-02 13:47:18 | [maml_trainer] epoch #1 | Saved 2025-04-02 13:47:18 | [maml_trainer] epoch #1 | Time 716.77 s 2025-04-02 13:47:18 | [maml_trainer] epoch #1 | EpochTime 361.84 s ------------------------------------------------- --------------- Average/AverageDiscountedReturn -72.7798 Average/AverageReturn -174.785 Average/Iteration 1 Average/MaxReturn -154.256 Average/MinReturn -196.673 Average/NumEpisodes 80 Average/StdReturn 9.3126 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.8377 GaussianMLPPolicy/KLAfter 0.0163152 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.91306e-05 GaussianMLPPolicy/LossBefore -3.05474e-09 GaussianMLPPolicy/dLoss -3.91337e-05 Iteration 1 MetaTest/Average/AverageDiscountedReturn -175.247 MetaTest/Average/AverageReturn -175.247 MetaTest/Average/Iteration 1 MetaTest/Average/MaxReturn -157.058 MetaTest/Average/MinReturn -206.201 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.2426 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.247 MetaTest/__unnamed_task__/AverageReturn -175.247 MetaTest/__unnamed_task__/Iteration 1 MetaTest/__unnamed_task__/MaxReturn -157.058 MetaTest/__unnamed_task__/MinReturn -206.201 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.2426 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 64000 __unnamed_task__/AverageDiscountedReturn -72.7798 __unnamed_task__/AverageReturn -174.785 __unnamed_task__/Iteration 1 __unnamed_task__/MaxReturn -154.256 __unnamed_task__/MinReturn -196.673 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 9.3126 __unnamed_task__/TerminationRate 0 ------------------------------------------------- --------------- 2025-04-02 13:51:53 | [maml_trainer] epoch #2 | Sampling for adapation and meta-testing... 2025-04-02 13:53:01 | [maml_trainer] epoch #2 | Finished meta-testing... 2025-04-02 13:53:01 | [maml_trainer] epoch #2 | Saving snapshot... 2025-04-02 13:53:19 | [maml_trainer] epoch #2 | Saved 2025-04-02 13:53:19 | [maml_trainer] epoch #2 | Time 1077.95 s 2025-04-02 13:53:19 | [maml_trainer] epoch #2 | EpochTime 361.18 s ------------------------------------------------- --------------- Average/AverageDiscountedReturn -72.9905 Average/AverageReturn -175.113 Average/Iteration 2 Average/MaxReturn -155.559 Average/MinReturn -211.63 Average/NumEpisodes 80 Average/StdReturn 10.338 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.8239 GaussianMLPPolicy/KLAfter 0.0127655 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.30731e-05 GaussianMLPPolicy/LossBefore 3.93391e-09 GaussianMLPPolicy/dLoss -7.30692e-05 Iteration 2 MetaTest/Average/AverageDiscountedReturn -177.682 MetaTest/Average/AverageReturn -177.682 MetaTest/Average/Iteration 2 MetaTest/Average/MaxReturn -154.717 MetaTest/Average/MinReturn -201.867 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.4574 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.682 MetaTest/__unnamed_task__/AverageReturn -177.682 MetaTest/__unnamed_task__/Iteration 2 MetaTest/__unnamed_task__/MaxReturn -154.717 MetaTest/__unnamed_task__/MinReturn -201.867 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.4574 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 96000 __unnamed_task__/AverageDiscountedReturn -72.9905 __unnamed_task__/AverageReturn -175.113 __unnamed_task__/Iteration 2 __unnamed_task__/MaxReturn -155.559 __unnamed_task__/MinReturn -211.63 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 10.338 __unnamed_task__/TerminationRate 0 ------------------------------------------------- --------------- 2025-04-02 13:57:49 | [maml_trainer] epoch #3 | Sampling for adapation and meta-testing... 2025-04-02 13:58:56 | [maml_trainer] epoch #3 | Finished meta-testing... 2025-04-02 13:58:56 | [maml_trainer] epoch #3 | Saving snapshot... 2025-04-02 13:59:16 | [maml_trainer] epoch #3 | Saved 2025-04-02 13:59:16 | [maml_trainer] epoch #3 | Time 1434.13 s 2025-04-02 13:59:16 | [maml_trainer] epoch #3 | EpochTime 356.18 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -73.7541 Average/AverageReturn -177.172 Average/Iteration 3 Average/MaxReturn -155.498 Average/MinReturn -242.1 Average/NumEpisodes 80 Average/StdReturn 13.1041 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.8101 GaussianMLPPolicy/KLAfter 0.0121306 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.52898e-06 GaussianMLPPolicy/LossBefore 2.45869e-09 GaussianMLPPolicy/dLoss -2.52652e-06 Iteration 3 MetaTest/Average/AverageDiscountedReturn -176.249 MetaTest/Average/AverageReturn -176.249 MetaTest/Average/Iteration 3 MetaTest/Average/MaxReturn -163.921 MetaTest/Average/MinReturn -206.719 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.52459 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.249 MetaTest/__unnamed_task__/AverageReturn -176.249 MetaTest/__unnamed_task__/Iteration 3 MetaTest/__unnamed_task__/MaxReturn -163.921 MetaTest/__unnamed_task__/MinReturn -206.719 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.52459 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 128000 __unnamed_task__/AverageDiscountedReturn -73.7541 __unnamed_task__/AverageReturn -177.172 __unnamed_task__/Iteration 3 __unnamed_task__/MaxReturn -155.498 __unnamed_task__/MinReturn -242.1 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.1041 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 14:03:52 | [maml_trainer] epoch #4 | Sampling for adapation and meta-testing... 2025-04-02 14:05:02 | [maml_trainer] epoch #4 | Finished meta-testing... 2025-04-02 14:05:02 | [maml_trainer] epoch #4 | Saving snapshot... 2025-04-02 14:05:23 | [maml_trainer] epoch #4 | Saved 2025-04-02 14:05:23 | [maml_trainer] epoch #4 | Time 1801.30 s 2025-04-02 14:05:23 | [maml_trainer] epoch #4 | EpochTime 367.17 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -73.6308 Average/AverageReturn -176.054 Average/Iteration 4 Average/MaxReturn -157.157 Average/MinReturn -280.311 Average/NumEpisodes 80 Average/StdReturn 14.6026 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7979 GaussianMLPPolicy/KLAfter 0.00842935 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.61326e-05 GaussianMLPPolicy/LossBefore -3.8743e-09 GaussianMLPPolicy/dLoss -2.61365e-05 Iteration 4 MetaTest/Average/AverageDiscountedReturn -176.47 MetaTest/Average/AverageReturn -176.47 MetaTest/Average/Iteration 4 MetaTest/Average/MaxReturn -159.291 MetaTest/Average/MinReturn -200.868 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.1801 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.47 MetaTest/__unnamed_task__/AverageReturn -176.47 MetaTest/__unnamed_task__/Iteration 4 MetaTest/__unnamed_task__/MaxReturn -159.291 MetaTest/__unnamed_task__/MinReturn -200.868 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.1801 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 160000 __unnamed_task__/AverageDiscountedReturn -73.6308 __unnamed_task__/AverageReturn -176.054 __unnamed_task__/Iteration 4 __unnamed_task__/MaxReturn -157.157 __unnamed_task__/MinReturn -280.311 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.6026 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 14:09:58 | [maml_trainer] epoch #5 | Sampling for adapation and meta-testing... 2025-04-02 14:11:05 | [maml_trainer] epoch #5 | Finished meta-testing... 2025-04-02 14:11:05 | [maml_trainer] epoch #5 | Saving snapshot... 2025-04-02 14:11:26 | [maml_trainer] epoch #5 | Saved 2025-04-02 14:11:26 | [maml_trainer] epoch #5 | Time 2164.24 s 2025-04-02 14:11:26 | [maml_trainer] epoch #5 | EpochTime 362.94 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -72.3182 Average/AverageReturn -173.458 Average/Iteration 5 Average/MaxReturn -157.439 Average/MinReturn -203.94 Average/NumEpisodes 80 Average/StdReturn 9.12518 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7881 GaussianMLPPolicy/KLAfter 0.00673696 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.53467e-05 GaussianMLPPolicy/LossBefore 5.31971e-09 GaussianMLPPolicy/dLoss -1.53414e-05 Iteration 5 MetaTest/Average/AverageDiscountedReturn -169.398 MetaTest/Average/AverageReturn -169.398 MetaTest/Average/Iteration 5 MetaTest/Average/MaxReturn -156.011 MetaTest/Average/MinReturn -182.036 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.43762 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.398 MetaTest/__unnamed_task__/AverageReturn -169.398 MetaTest/__unnamed_task__/Iteration 5 MetaTest/__unnamed_task__/MaxReturn -156.011 MetaTest/__unnamed_task__/MinReturn -182.036 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.43762 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 192000 __unnamed_task__/AverageDiscountedReturn -72.3182 __unnamed_task__/AverageReturn -173.458 __unnamed_task__/Iteration 5 __unnamed_task__/MaxReturn -157.439 __unnamed_task__/MinReturn -203.94 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 9.12518 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 14:16:02 | [maml_trainer] epoch #6 | Sampling for adapation and meta-testing... 2025-04-02 14:17:12 | [maml_trainer] epoch #6 | Finished meta-testing... 2025-04-02 14:17:12 | [maml_trainer] epoch #6 | Saving snapshot... 2025-04-02 14:17:31 | [maml_trainer] epoch #6 | Saved 2025-04-02 14:17:31 | [maml_trainer] epoch #6 | Time 2529.99 s 2025-04-02 14:17:31 | [maml_trainer] epoch #6 | EpochTime 365.74 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -73.3679 Average/AverageReturn -175.418 Average/Iteration 6 Average/MaxReturn -157.139 Average/MinReturn -236.461 Average/NumEpisodes 80 Average/StdReturn 12.751 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7794 GaussianMLPPolicy/KLAfter 0.0058501 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.09646e-05 GaussianMLPPolicy/LossBefore -1.50502e-09 GaussianMLPPolicy/dLoss 4.09631e-05 Iteration 6 MetaTest/Average/AverageDiscountedReturn -169.735 MetaTest/Average/AverageReturn -169.735 MetaTest/Average/Iteration 6 MetaTest/Average/MaxReturn -154.577 MetaTest/Average/MinReturn -196.266 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.02865 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.735 MetaTest/__unnamed_task__/AverageReturn -169.735 MetaTest/__unnamed_task__/Iteration 6 MetaTest/__unnamed_task__/MaxReturn -154.577 MetaTest/__unnamed_task__/MinReturn -196.266 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.02865 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 224000 __unnamed_task__/AverageDiscountedReturn -73.3679 __unnamed_task__/AverageReturn -175.418 __unnamed_task__/Iteration 6 __unnamed_task__/MaxReturn -157.139 __unnamed_task__/MinReturn -236.461 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 12.751 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 14:22:06 | [maml_trainer] epoch #7 | Sampling for adapation and meta-testing... 2025-04-02 14:23:15 | [maml_trainer] epoch #7 | Finished meta-testing... 2025-04-02 14:23:15 | [maml_trainer] epoch #7 | Saving snapshot... 2025-04-02 14:23:35 | [maml_trainer] epoch #7 | Saved 2025-04-02 14:23:35 | [maml_trainer] epoch #7 | Time 2893.28 s 2025-04-02 14:23:35 | [maml_trainer] epoch #7 | EpochTime 363.29 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -72.3254 Average/AverageReturn -171.739 Average/Iteration 7 Average/MaxReturn -154.284 Average/MinReturn -274.633 Average/NumEpisodes 80 Average/StdReturn 14.5315 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7691 GaussianMLPPolicy/KLAfter 0.00639265 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.31397e-05 GaussianMLPPolicy/LossBefore 9.26852e-09 GaussianMLPPolicy/dLoss 7.31489e-05 Iteration 7 MetaTest/Average/AverageDiscountedReturn -173.486 MetaTest/Average/AverageReturn -173.486 MetaTest/Average/Iteration 7 MetaTest/Average/MaxReturn -160.689 MetaTest/Average/MinReturn -207.277 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.0113 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.486 MetaTest/__unnamed_task__/AverageReturn -173.486 MetaTest/__unnamed_task__/Iteration 7 MetaTest/__unnamed_task__/MaxReturn -160.689 MetaTest/__unnamed_task__/MinReturn -207.277 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.0113 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 256000 __unnamed_task__/AverageDiscountedReturn -72.3254 __unnamed_task__/AverageReturn -171.739 __unnamed_task__/Iteration 7 __unnamed_task__/MaxReturn -154.284 __unnamed_task__/MinReturn -274.633 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.5315 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 14:28:14 | [maml_trainer] epoch #8 | Sampling for adapation and meta-testing... 2025-04-02 14:29:22 | [maml_trainer] epoch #8 | Finished meta-testing... 2025-04-02 14:29:22 | [maml_trainer] epoch #8 | Saving snapshot... 2025-04-02 14:29:42 | [maml_trainer] epoch #8 | Saved 2025-04-02 14:29:42 | [maml_trainer] epoch #8 | Time 3260.57 s 2025-04-02 14:29:42 | [maml_trainer] epoch #8 | EpochTime 367.28 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -71.2884 Average/AverageReturn -169.847 Average/Iteration 8 Average/MaxReturn -150.479 Average/MinReturn -206.957 Average/NumEpisodes 80 Average/StdReturn 10.2425 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.76 GaussianMLPPolicy/KLAfter 0.00523702 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.24274e-05 GaussianMLPPolicy/LossBefore -2.05636e-09 GaussianMLPPolicy/dLoss 2.24253e-05 Iteration 8 MetaTest/Average/AverageDiscountedReturn -169.176 MetaTest/Average/AverageReturn -169.176 MetaTest/Average/Iteration 8 MetaTest/Average/MaxReturn -159.636 MetaTest/Average/MinReturn -192.749 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.34766 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.176 MetaTest/__unnamed_task__/AverageReturn -169.176 MetaTest/__unnamed_task__/Iteration 8 MetaTest/__unnamed_task__/MaxReturn -159.636 MetaTest/__unnamed_task__/MinReturn -192.749 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.34766 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 288000 __unnamed_task__/AverageDiscountedReturn -71.2884 __unnamed_task__/AverageReturn -169.847 __unnamed_task__/Iteration 8 __unnamed_task__/MaxReturn -150.479 __unnamed_task__/MinReturn -206.957 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 10.2425 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 14:34:17 | [maml_trainer] epoch #9 | Sampling for adapation and meta-testing... 2025-04-02 14:35:26 | [maml_trainer] epoch #9 | Finished meta-testing... 2025-04-02 14:35:26 | [maml_trainer] epoch #9 | Saving snapshot... 2025-04-02 14:35:45 | [maml_trainer] epoch #9 | Saved 2025-04-02 14:35:45 | [maml_trainer] epoch #9 | Time 3623.64 s 2025-04-02 14:35:45 | [maml_trainer] epoch #9 | EpochTime 363.06 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -72.365 Average/AverageReturn -170.969 Average/Iteration 9 Average/MaxReturn -151.324 Average/MinReturn -245.646 Average/NumEpisodes 80 Average/StdReturn 13.1982 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7538 GaussianMLPPolicy/KLAfter 0.00426195 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.46094e-06 GaussianMLPPolicy/LossBefore -9.17912e-09 GaussianMLPPolicy/dLoss 1.45176e-06 Iteration 9 MetaTest/Average/AverageDiscountedReturn -165.123 MetaTest/Average/AverageReturn -165.123 MetaTest/Average/Iteration 9 MetaTest/Average/MaxReturn -151.293 MetaTest/Average/MinReturn -191.03 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.21081 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.123 MetaTest/__unnamed_task__/AverageReturn -165.123 MetaTest/__unnamed_task__/Iteration 9 MetaTest/__unnamed_task__/MaxReturn -151.293 MetaTest/__unnamed_task__/MinReturn -191.03 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.21081 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 320000 __unnamed_task__/AverageDiscountedReturn -72.365 __unnamed_task__/AverageReturn -170.969 __unnamed_task__/Iteration 9 __unnamed_task__/MaxReturn -151.324 __unnamed_task__/MinReturn -245.646 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.1982 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 14:40:22 | [maml_trainer] epoch #10 | Sampling for adapation and meta-testing... 2025-04-02 14:41:30 | [maml_trainer] epoch #10 | Finished meta-testing... 2025-04-02 14:41:30 | [maml_trainer] epoch #10 | Saving snapshot... 2025-04-02 14:41:49 | [maml_trainer] epoch #10 | Saved 2025-04-02 14:41:49 | [maml_trainer] epoch #10 | Time 3987.58 s 2025-04-02 14:41:49 | [maml_trainer] epoch #10 | EpochTime 363.94 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -71.6424 Average/AverageReturn -169.674 Average/Iteration 10 Average/MaxReturn -151.784 Average/MinReturn -242.653 Average/NumEpisodes 80 Average/StdReturn 14.7401 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7511 GaussianMLPPolicy/KLAfter 0.00465591 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.1722e-05 GaussianMLPPolicy/LossBefore 1.68383e-09 GaussianMLPPolicy/dLoss 3.17237e-05 Iteration 10 MetaTest/Average/AverageDiscountedReturn -167.534 MetaTest/Average/AverageReturn -167.534 MetaTest/Average/Iteration 10 MetaTest/Average/MaxReturn -153.1 MetaTest/Average/MinReturn -194.426 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.67205 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.534 MetaTest/__unnamed_task__/AverageReturn -167.534 MetaTest/__unnamed_task__/Iteration 10 MetaTest/__unnamed_task__/MaxReturn -153.1 MetaTest/__unnamed_task__/MinReturn -194.426 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.67205 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 352000 __unnamed_task__/AverageDiscountedReturn -71.6424 __unnamed_task__/AverageReturn -169.674 __unnamed_task__/Iteration 10 __unnamed_task__/MaxReturn -151.784 __unnamed_task__/MinReturn -242.653 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.7401 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 14:46:24 | [maml_trainer] epoch #11 | Sampling for adapation and meta-testing... 2025-04-02 14:47:32 | [maml_trainer] epoch #11 | Finished meta-testing... 2025-04-02 14:47:32 | [maml_trainer] epoch #11 | Saving snapshot... 2025-04-02 14:47:52 | [maml_trainer] epoch #11 | Saved 2025-04-02 14:47:52 | [maml_trainer] epoch #11 | Time 4350.93 s 2025-04-02 14:47:52 | [maml_trainer] epoch #11 | EpochTime 363.35 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -71.6056 Average/AverageReturn -169.223 Average/Iteration 11 Average/MaxReturn -150.552 Average/MinReturn -229.048 Average/NumEpisodes 80 Average/StdReturn 13.5238 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7465 GaussianMLPPolicy/KLAfter 0.00523354 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.45049e-06 GaussianMLPPolicy/LossBefore -5.96046e-10 GaussianMLPPolicy/dLoss 5.44989e-06 Iteration 11 MetaTest/Average/AverageDiscountedReturn -164.941 MetaTest/Average/AverageReturn -164.941 MetaTest/Average/Iteration 11 MetaTest/Average/MaxReturn -155.209 MetaTest/Average/MinReturn -175.621 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.77966 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.941 MetaTest/__unnamed_task__/AverageReturn -164.941 MetaTest/__unnamed_task__/Iteration 11 MetaTest/__unnamed_task__/MaxReturn -155.209 MetaTest/__unnamed_task__/MinReturn -175.621 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.77966 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 384000 __unnamed_task__/AverageDiscountedReturn -71.6056 __unnamed_task__/AverageReturn -169.223 __unnamed_task__/Iteration 11 __unnamed_task__/MaxReturn -150.552 __unnamed_task__/MinReturn -229.048 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.5238 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 14:52:25 | [maml_trainer] epoch #12 | Sampling for adapation and meta-testing... 2025-04-02 14:53:33 | [maml_trainer] epoch #12 | Finished meta-testing... 2025-04-02 14:53:33 | [maml_trainer] epoch #12 | Saving snapshot... 2025-04-02 14:53:52 | [maml_trainer] epoch #12 | Saved 2025-04-02 14:53:52 | [maml_trainer] epoch #12 | Time 4711.11 s 2025-04-02 14:53:52 | [maml_trainer] epoch #12 | EpochTime 360.17 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -72.4268 Average/AverageReturn -170.532 Average/Iteration 12 Average/MaxReturn -143.902 Average/MinReturn -244.639 Average/NumEpisodes 80 Average/StdReturn 18.4226 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7453 GaussianMLPPolicy/KLAfter 0.00459388 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.18635e-05 GaussianMLPPolicy/LossBefore 2.68221e-09 GaussianMLPPolicy/dLoss -1.18609e-05 Iteration 12 MetaTest/Average/AverageDiscountedReturn -171.786 MetaTest/Average/AverageReturn -171.786 MetaTest/Average/Iteration 12 MetaTest/Average/MaxReturn -150.097 MetaTest/Average/MinReturn -236.11 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.9584 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.786 MetaTest/__unnamed_task__/AverageReturn -171.786 MetaTest/__unnamed_task__/Iteration 12 MetaTest/__unnamed_task__/MaxReturn -150.097 MetaTest/__unnamed_task__/MinReturn -236.11 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.9584 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 416000 __unnamed_task__/AverageDiscountedReturn -72.4268 __unnamed_task__/AverageReturn -170.532 __unnamed_task__/Iteration 12 __unnamed_task__/MaxReturn -143.902 __unnamed_task__/MinReturn -244.639 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.4226 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 14:58:29 | [maml_trainer] epoch #13 | Sampling for adapation and meta-testing... 2025-04-02 14:59:37 | [maml_trainer] epoch #13 | Finished meta-testing... 2025-04-02 14:59:37 | [maml_trainer] epoch #13 | Saving snapshot... 2025-04-02 14:59:56 | [maml_trainer] epoch #13 | Saved 2025-04-02 14:59:56 | [maml_trainer] epoch #13 | Time 5074.96 s 2025-04-02 14:59:56 | [maml_trainer] epoch #13 | EpochTime 363.84 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -71.6226 Average/AverageReturn -168.53 Average/Iteration 13 Average/MaxReturn -148.999 Average/MinReturn -237.727 Average/NumEpisodes 80 Average/StdReturn 17.5229 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7436 GaussianMLPPolicy/KLAfter 0.0039096 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.53291e-05 GaussianMLPPolicy/LossBefore -4.29153e-09 GaussianMLPPolicy/dLoss 3.53249e-05 Iteration 13 MetaTest/Average/AverageDiscountedReturn -165.461 MetaTest/Average/AverageReturn -165.461 MetaTest/Average/Iteration 13 MetaTest/Average/MaxReturn -156.631 MetaTest/Average/MinReturn -184.738 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.54982 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.461 MetaTest/__unnamed_task__/AverageReturn -165.461 MetaTest/__unnamed_task__/Iteration 13 MetaTest/__unnamed_task__/MaxReturn -156.631 MetaTest/__unnamed_task__/MinReturn -184.738 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.54982 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 448000 __unnamed_task__/AverageDiscountedReturn -71.6226 __unnamed_task__/AverageReturn -168.53 __unnamed_task__/Iteration 13 __unnamed_task__/MaxReturn -148.999 __unnamed_task__/MinReturn -237.727 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.5229 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 15:04:39 | [maml_trainer] epoch #14 | Sampling for adapation and meta-testing... 2025-04-02 15:05:52 | [maml_trainer] epoch #14 | Finished meta-testing... 2025-04-02 15:05:52 | [maml_trainer] epoch #14 | Saving snapshot... 2025-04-02 15:06:12 | [maml_trainer] epoch #14 | Saved 2025-04-02 15:06:12 | [maml_trainer] epoch #14 | Time 5450.38 s 2025-04-02 15:06:12 | [maml_trainer] epoch #14 | EpochTime 375.42 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -71.1152 Average/AverageReturn -167.072 Average/Iteration 14 Average/MaxReturn -150.474 Average/MinReturn -269.697 Average/NumEpisodes 80 Average/StdReturn 16.7935 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7418 GaussianMLPPolicy/KLAfter 0.00252159 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.86693e-05 GaussianMLPPolicy/LossBefore -7.01845e-09 GaussianMLPPolicy/dLoss 2.86623e-05 Iteration 14 MetaTest/Average/AverageDiscountedReturn -162.156 MetaTest/Average/AverageReturn -162.156 MetaTest/Average/Iteration 14 MetaTest/Average/MaxReturn -149.54 MetaTest/Average/MinReturn -175.216 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.62052 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -162.156 MetaTest/__unnamed_task__/AverageReturn -162.156 MetaTest/__unnamed_task__/Iteration 14 MetaTest/__unnamed_task__/MaxReturn -149.54 MetaTest/__unnamed_task__/MinReturn -175.216 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.62052 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 480000 __unnamed_task__/AverageDiscountedReturn -71.1152 __unnamed_task__/AverageReturn -167.072 __unnamed_task__/Iteration 14 __unnamed_task__/MaxReturn -150.474 __unnamed_task__/MinReturn -269.697 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.7935 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 15:11:01 | [maml_trainer] epoch #15 | Sampling for adapation and meta-testing... 2025-04-02 15:12:12 | [maml_trainer] epoch #15 | Finished meta-testing... 2025-04-02 15:12:12 | [maml_trainer] epoch #15 | Saving snapshot... 2025-04-02 15:12:33 | [maml_trainer] epoch #15 | Saved 2025-04-02 15:12:33 | [maml_trainer] epoch #15 | Time 5832.00 s 2025-04-02 15:12:33 | [maml_trainer] epoch #15 | EpochTime 381.61 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -71.556 Average/AverageReturn -167.271 Average/Iteration 15 Average/MaxReturn -145.611 Average/MinReturn -251.626 Average/NumEpisodes 80 Average/StdReturn 17.3989 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7373 GaussianMLPPolicy/KLAfter 0.00255537 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.34301e-06 GaussianMLPPolicy/LossBefore -5.57303e-09 GaussianMLPPolicy/dLoss 6.33743e-06 Iteration 15 MetaTest/Average/AverageDiscountedReturn -173.938 MetaTest/Average/AverageReturn -173.938 MetaTest/Average/Iteration 15 MetaTest/Average/MaxReturn -151.943 MetaTest/Average/MinReturn -247.831 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.4678 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.938 MetaTest/__unnamed_task__/AverageReturn -173.938 MetaTest/__unnamed_task__/Iteration 15 MetaTest/__unnamed_task__/MaxReturn -151.943 MetaTest/__unnamed_task__/MinReturn -247.831 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.4678 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 512000 __unnamed_task__/AverageDiscountedReturn -71.556 __unnamed_task__/AverageReturn -167.271 __unnamed_task__/Iteration 15 __unnamed_task__/MaxReturn -145.611 __unnamed_task__/MinReturn -251.626 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.3989 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 15:17:19 | [maml_trainer] epoch #16 | Sampling for adapation and meta-testing... 2025-04-02 15:18:31 | [maml_trainer] epoch #16 | Finished meta-testing... 2025-04-02 15:18:31 | [maml_trainer] epoch #16 | Saving snapshot... 2025-04-02 15:18:52 | [maml_trainer] epoch #16 | Saved 2025-04-02 15:18:52 | [maml_trainer] epoch #16 | Time 6210.71 s 2025-04-02 15:18:52 | [maml_trainer] epoch #16 | EpochTime 378.71 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -71.1988 Average/AverageReturn -167.621 Average/Iteration 16 Average/MaxReturn -149.459 Average/MinReturn -229.78 Average/NumEpisodes 80 Average/StdReturn 15.9137 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7325 GaussianMLPPolicy/KLAfter 0.00298558 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.0819e-05 GaussianMLPPolicy/LossBefore -5.51343e-10 GaussianMLPPolicy/dLoss -1.08195e-05 Iteration 16 MetaTest/Average/AverageDiscountedReturn -167.136 MetaTest/Average/AverageReturn -167.136 MetaTest/Average/Iteration 16 MetaTest/Average/MaxReturn -157.873 MetaTest/Average/MinReturn -195.587 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.8006 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.136 MetaTest/__unnamed_task__/AverageReturn -167.136 MetaTest/__unnamed_task__/Iteration 16 MetaTest/__unnamed_task__/MaxReturn -157.873 MetaTest/__unnamed_task__/MinReturn -195.587 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.8006 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 544000 __unnamed_task__/AverageDiscountedReturn -71.1988 __unnamed_task__/AverageReturn -167.621 __unnamed_task__/Iteration 16 __unnamed_task__/MaxReturn -149.459 __unnamed_task__/MinReturn -229.78 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.9137 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 15:23:42 | [maml_trainer] epoch #17 | Sampling for adapation and meta-testing... 2025-04-02 15:24:54 | [maml_trainer] epoch #17 | Finished meta-testing... 2025-04-02 15:24:54 | [maml_trainer] epoch #17 | Saving snapshot... 2025-04-02 15:25:15 | [maml_trainer] epoch #17 | Saved 2025-04-02 15:25:15 | [maml_trainer] epoch #17 | Time 6593.60 s 2025-04-02 15:25:15 | [maml_trainer] epoch #17 | EpochTime 382.88 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -70.0974 Average/AverageReturn -165.138 Average/Iteration 17 Average/MaxReturn -146.544 Average/MinReturn -216.202 Average/NumEpisodes 80 Average/StdReturn 10.4774 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7268 GaussianMLPPolicy/KLAfter 0.00310437 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.48679e-05 GaussianMLPPolicy/LossBefore 5.1558e-09 GaussianMLPPolicy/dLoss 1.4873e-05 Iteration 17 MetaTest/Average/AverageDiscountedReturn -164.91 MetaTest/Average/AverageReturn -164.91 MetaTest/Average/Iteration 17 MetaTest/Average/MaxReturn -153.03 MetaTest/Average/MinReturn -182.641 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.04312 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.91 MetaTest/__unnamed_task__/AverageReturn -164.91 MetaTest/__unnamed_task__/Iteration 17 MetaTest/__unnamed_task__/MaxReturn -153.03 MetaTest/__unnamed_task__/MinReturn -182.641 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.04312 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 576000 __unnamed_task__/AverageDiscountedReturn -70.0974 __unnamed_task__/AverageReturn -165.138 __unnamed_task__/Iteration 17 __unnamed_task__/MaxReturn -146.544 __unnamed_task__/MinReturn -216.202 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 10.4774 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 15:29:57 | [maml_trainer] epoch #18 | Sampling for adapation and meta-testing... 2025-04-02 15:31:09 | [maml_trainer] epoch #18 | Finished meta-testing... 2025-04-02 15:31:09 | [maml_trainer] epoch #18 | Saving snapshot... 2025-04-02 15:31:29 | [maml_trainer] epoch #18 | Saved 2025-04-02 15:31:29 | [maml_trainer] epoch #18 | Time 6967.67 s 2025-04-02 15:31:29 | [maml_trainer] epoch #18 | EpochTime 374.07 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -70.7903 Average/AverageReturn -167.036 Average/Iteration 18 Average/MaxReturn -146.978 Average/MinReturn -232.639 Average/NumEpisodes 80 Average/StdReturn 13.6199 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7191 GaussianMLPPolicy/KLAfter 0.00477303 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.14285e-05 GaussianMLPPolicy/LossBefore -3.53158e-09 GaussianMLPPolicy/dLoss 1.1425e-05 Iteration 18 MetaTest/Average/AverageDiscountedReturn -164.221 MetaTest/Average/AverageReturn -164.221 MetaTest/Average/Iteration 18 MetaTest/Average/MaxReturn -151.208 MetaTest/Average/MinReturn -190.284 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.1563 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.221 MetaTest/__unnamed_task__/AverageReturn -164.221 MetaTest/__unnamed_task__/Iteration 18 MetaTest/__unnamed_task__/MaxReturn -151.208 MetaTest/__unnamed_task__/MinReturn -190.284 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.1563 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 608000 __unnamed_task__/AverageDiscountedReturn -70.7903 __unnamed_task__/AverageReturn -167.036 __unnamed_task__/Iteration 18 __unnamed_task__/MaxReturn -146.978 __unnamed_task__/MinReturn -232.639 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.6199 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 15:36:16 | [maml_trainer] epoch #19 | Sampling for adapation and meta-testing... 2025-04-02 15:37:28 | [maml_trainer] epoch #19 | Finished meta-testing... 2025-04-02 15:37:28 | [maml_trainer] epoch #19 | Saving snapshot... 2025-04-02 15:37:48 | [maml_trainer] epoch #19 | Saved 2025-04-02 15:37:48 | [maml_trainer] epoch #19 | Time 7346.73 s 2025-04-02 15:37:48 | [maml_trainer] epoch #19 | EpochTime 379.05 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -70.6742 Average/AverageReturn -166.933 Average/Iteration 19 Average/MaxReturn -147.182 Average/MinReturn -211.547 Average/NumEpisodes 80 Average/StdReturn 13.3413 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.712 GaussianMLPPolicy/KLAfter 0.00502437 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.24107e-06 GaussianMLPPolicy/LossBefore -9.07481e-09 GaussianMLPPolicy/dLoss 7.232e-06 Iteration 19 MetaTest/Average/AverageDiscountedReturn -169.149 MetaTest/Average/AverageReturn -169.149 MetaTest/Average/Iteration 19 MetaTest/Average/MaxReturn -154.766 MetaTest/Average/MinReturn -213.841 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.0812 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.149 MetaTest/__unnamed_task__/AverageReturn -169.149 MetaTest/__unnamed_task__/Iteration 19 MetaTest/__unnamed_task__/MaxReturn -154.766 MetaTest/__unnamed_task__/MinReturn -213.841 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.0812 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 640000 __unnamed_task__/AverageDiscountedReturn -70.6742 __unnamed_task__/AverageReturn -166.933 __unnamed_task__/Iteration 19 __unnamed_task__/MaxReturn -147.182 __unnamed_task__/MinReturn -211.547 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.3413 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 15:42:35 | [maml_trainer] epoch #20 | Sampling for adapation and meta-testing... 2025-04-02 15:43:43 | [maml_trainer] epoch #20 | Finished meta-testing... 2025-04-02 15:43:43 | [maml_trainer] epoch #20 | Saving snapshot... 2025-04-02 15:44:02 | [maml_trainer] epoch #20 | Saved 2025-04-02 15:44:02 | [maml_trainer] epoch #20 | Time 7720.85 s 2025-04-02 15:44:02 | [maml_trainer] epoch #20 | EpochTime 374.12 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -70.6256 Average/AverageReturn -166.056 Average/Iteration 20 Average/MaxReturn -146.597 Average/MinReturn -241.906 Average/NumEpisodes 80 Average/StdReturn 13.4134 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7077 GaussianMLPPolicy/KLAfter 0.00488629 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.15406e-05 GaussianMLPPolicy/LossBefore 4.38094e-09 GaussianMLPPolicy/dLoss 7.1545e-05 Iteration 20 MetaTest/Average/AverageDiscountedReturn -168.166 MetaTest/Average/AverageReturn -168.166 MetaTest/Average/Iteration 20 MetaTest/Average/MaxReturn -147.433 MetaTest/Average/MinReturn -253.194 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.956 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.166 MetaTest/__unnamed_task__/AverageReturn -168.166 MetaTest/__unnamed_task__/Iteration 20 MetaTest/__unnamed_task__/MaxReturn -147.433 MetaTest/__unnamed_task__/MinReturn -253.194 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.956 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 672000 __unnamed_task__/AverageDiscountedReturn -70.6256 __unnamed_task__/AverageReturn -166.056 __unnamed_task__/Iteration 20 __unnamed_task__/MaxReturn -146.597 __unnamed_task__/MinReturn -241.906 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.4134 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 15:48:36 | [maml_trainer] epoch #21 | Sampling for adapation and meta-testing... 2025-04-02 15:49:48 | [maml_trainer] epoch #21 | Finished meta-testing... 2025-04-02 15:49:48 | [maml_trainer] epoch #21 | Saving snapshot... 2025-04-02 15:50:09 | [maml_trainer] epoch #21 | Saved 2025-04-02 15:50:09 | [maml_trainer] epoch #21 | Time 8087.34 s 2025-04-02 15:50:09 | [maml_trainer] epoch #21 | EpochTime 366.49 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -71.4561 Average/AverageReturn -167.755 Average/Iteration 21 Average/MaxReturn -147.629 Average/MinReturn -267.346 Average/NumEpisodes 80 Average/StdReturn 15.6501 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.7031 GaussianMLPPolicy/KLAfter 0.00421476 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.68139e-05 GaussianMLPPolicy/LossBefore -7.30157e-10 GaussianMLPPolicy/dLoss 2.68132e-05 Iteration 21 MetaTest/Average/AverageDiscountedReturn -164.07 MetaTest/Average/AverageReturn -164.07 MetaTest/Average/Iteration 21 MetaTest/Average/MaxReturn -149.213 MetaTest/Average/MinReturn -195.154 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.44078 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.07 MetaTest/__unnamed_task__/AverageReturn -164.07 MetaTest/__unnamed_task__/Iteration 21 MetaTest/__unnamed_task__/MaxReturn -149.213 MetaTest/__unnamed_task__/MinReturn -195.154 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.44078 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 704000 __unnamed_task__/AverageDiscountedReturn -71.4561 __unnamed_task__/AverageReturn -167.755 __unnamed_task__/Iteration 21 __unnamed_task__/MaxReturn -147.629 __unnamed_task__/MinReturn -267.346 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.6501 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 15:54:58 | [maml_trainer] epoch #22 | Sampling for adapation and meta-testing... 2025-04-02 15:56:09 | [maml_trainer] epoch #22 | Finished meta-testing... 2025-04-02 15:56:09 | [maml_trainer] epoch #22 | Saving snapshot... 2025-04-02 15:56:30 | [maml_trainer] epoch #22 | Saved 2025-04-02 15:56:30 | [maml_trainer] epoch #22 | Time 8469.04 s 2025-04-02 15:56:30 | [maml_trainer] epoch #22 | EpochTime 381.69 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -71.1372 Average/AverageReturn -167.523 Average/Iteration 22 Average/MaxReturn -150.522 Average/MinReturn -226.674 Average/NumEpisodes 80 Average/StdReturn 14.8474 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6972 GaussianMLPPolicy/KLAfter 0.00298392 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.15843e-05 GaussianMLPPolicy/LossBefore 4.61936e-09 GaussianMLPPolicy/dLoss 4.15889e-05 Iteration 22 MetaTest/Average/AverageDiscountedReturn -169.321 MetaTest/Average/AverageReturn -169.321 MetaTest/Average/Iteration 22 MetaTest/Average/MaxReturn -148.959 MetaTest/Average/MinReturn -283.402 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 28.8397 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.321 MetaTest/__unnamed_task__/AverageReturn -169.321 MetaTest/__unnamed_task__/Iteration 22 MetaTest/__unnamed_task__/MaxReturn -148.959 MetaTest/__unnamed_task__/MinReturn -283.402 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 28.8397 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 736000 __unnamed_task__/AverageDiscountedReturn -71.1372 __unnamed_task__/AverageReturn -167.523 __unnamed_task__/Iteration 22 __unnamed_task__/MaxReturn -150.522 __unnamed_task__/MinReturn -226.674 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.8474 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 16:01:17 | [maml_trainer] epoch #23 | Sampling for adapation and meta-testing... 2025-04-02 16:02:27 | [maml_trainer] epoch #23 | Finished meta-testing... 2025-04-02 16:02:27 | [maml_trainer] epoch #23 | Saving snapshot... 2025-04-02 16:02:46 | [maml_trainer] epoch #23 | Saved 2025-04-02 16:02:46 | [maml_trainer] epoch #23 | Time 8845.08 s 2025-04-02 16:02:46 | [maml_trainer] epoch #23 | EpochTime 376.04 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -72.8914 Average/AverageReturn -171.209 Average/Iteration 23 Average/MaxReturn -148.132 Average/MinReturn -234.671 Average/NumEpisodes 80 Average/StdReturn 18.5031 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6924 GaussianMLPPolicy/KLAfter 0.00343269 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.25473e-05 GaussianMLPPolicy/LossBefore 4.08292e-09 GaussianMLPPolicy/dLoss 3.25513e-05 Iteration 23 MetaTest/Average/AverageDiscountedReturn -164.361 MetaTest/Average/AverageReturn -164.361 MetaTest/Average/Iteration 23 MetaTest/Average/MaxReturn -152.414 MetaTest/Average/MinReturn -186.653 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.51712 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.361 MetaTest/__unnamed_task__/AverageReturn -164.361 MetaTest/__unnamed_task__/Iteration 23 MetaTest/__unnamed_task__/MaxReturn -152.414 MetaTest/__unnamed_task__/MinReturn -186.653 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.51712 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 768000 __unnamed_task__/AverageDiscountedReturn -72.8914 __unnamed_task__/AverageReturn -171.209 __unnamed_task__/Iteration 23 __unnamed_task__/MaxReturn -148.132 __unnamed_task__/MinReturn -234.671 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.5031 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 16:07:20 | [maml_trainer] epoch #24 | Sampling for adapation and meta-testing... 2025-04-02 16:08:26 | [maml_trainer] epoch #24 | Finished meta-testing... 2025-04-02 16:08:26 | [maml_trainer] epoch #24 | Saving snapshot... 2025-04-02 16:08:45 | [maml_trainer] epoch #24 | Saved 2025-04-02 16:08:45 | [maml_trainer] epoch #24 | Time 9203.78 s 2025-04-02 16:08:45 | [maml_trainer] epoch #24 | EpochTime 358.70 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -68.9849 Average/AverageReturn -162.373 Average/Iteration 24 Average/MaxReturn -133.631 Average/MinReturn -206.705 Average/NumEpisodes 80 Average/StdReturn 9.92864 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6906 GaussianMLPPolicy/KLAfter 0.00335641 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.23789e-05 GaussianMLPPolicy/LossBefore -2.48849e-09 GaussianMLPPolicy/dLoss -4.23814e-05 Iteration 24 MetaTest/Average/AverageDiscountedReturn -164.073 MetaTest/Average/AverageReturn -164.073 MetaTest/Average/Iteration 24 MetaTest/Average/MaxReturn -147.185 MetaTest/Average/MinReturn -222.503 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.7373 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.073 MetaTest/__unnamed_task__/AverageReturn -164.073 MetaTest/__unnamed_task__/Iteration 24 MetaTest/__unnamed_task__/MaxReturn -147.185 MetaTest/__unnamed_task__/MinReturn -222.503 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.7373 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 800000 __unnamed_task__/AverageDiscountedReturn -68.9849 __unnamed_task__/AverageReturn -162.373 __unnamed_task__/Iteration 24 __unnamed_task__/MaxReturn -133.631 __unnamed_task__/MinReturn -206.705 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 9.92864 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 16:13:17 | [maml_trainer] epoch #25 | Sampling for adapation and meta-testing... 2025-04-02 16:14:25 | [maml_trainer] epoch #25 | Finished meta-testing... 2025-04-02 16:14:25 | [maml_trainer] epoch #25 | Saving snapshot... 2025-04-02 16:14:45 | [maml_trainer] epoch #25 | Saved 2025-04-02 16:14:45 | [maml_trainer] epoch #25 | Time 9563.53 s 2025-04-02 16:14:45 | [maml_trainer] epoch #25 | EpochTime 359.74 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -72.9309 Average/AverageReturn -170.843 Average/Iteration 25 Average/MaxReturn -142.684 Average/MinReturn -288.643 Average/NumEpisodes 80 Average/StdReturn 21.8927 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6887 GaussianMLPPolicy/KLAfter 0.00343144 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.97696e-05 GaussianMLPPolicy/LossBefore -4.94719e-09 GaussianMLPPolicy/dLoss -3.97746e-05 Iteration 25 MetaTest/Average/AverageDiscountedReturn -163.653 MetaTest/Average/AverageReturn -163.653 MetaTest/Average/Iteration 25 MetaTest/Average/MaxReturn -145.693 MetaTest/Average/MinReturn -202.275 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.2585 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -163.653 MetaTest/__unnamed_task__/AverageReturn -163.653 MetaTest/__unnamed_task__/Iteration 25 MetaTest/__unnamed_task__/MaxReturn -145.693 MetaTest/__unnamed_task__/MinReturn -202.275 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.2585 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 832000 __unnamed_task__/AverageDiscountedReturn -72.9309 __unnamed_task__/AverageReturn -170.843 __unnamed_task__/Iteration 25 __unnamed_task__/MaxReturn -142.684 __unnamed_task__/MinReturn -288.643 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.8927 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 16:19:17 | [maml_trainer] epoch #26 | Sampling for adapation and meta-testing... 2025-04-02 16:20:25 | [maml_trainer] epoch #26 | Finished meta-testing... 2025-04-02 16:20:25 | [maml_trainer] epoch #26 | Saving snapshot... 2025-04-02 16:20:44 | [maml_trainer] epoch #26 | Saved 2025-04-02 16:20:44 | [maml_trainer] epoch #26 | Time 9923.02 s 2025-04-02 16:20:44 | [maml_trainer] epoch #26 | EpochTime 359.49 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -71.9707 Average/AverageReturn -167.953 Average/Iteration 26 Average/MaxReturn -148.042 Average/MinReturn -241.667 Average/NumEpisodes 80 Average/StdReturn 18.5947 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.684 GaussianMLPPolicy/KLAfter 0.00261665 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.29467e-06 GaussianMLPPolicy/LossBefore 1.92225e-09 GaussianMLPPolicy/dLoss 7.29659e-06 Iteration 26 MetaTest/Average/AverageDiscountedReturn -165.847 MetaTest/Average/AverageReturn -165.847 MetaTest/Average/Iteration 26 MetaTest/Average/MaxReturn -151.825 MetaTest/Average/MinReturn -207.858 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.2208 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.847 MetaTest/__unnamed_task__/AverageReturn -165.847 MetaTest/__unnamed_task__/Iteration 26 MetaTest/__unnamed_task__/MaxReturn -151.825 MetaTest/__unnamed_task__/MinReturn -207.858 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.2208 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 864000 __unnamed_task__/AverageDiscountedReturn -71.9707 __unnamed_task__/AverageReturn -167.953 __unnamed_task__/Iteration 26 __unnamed_task__/MaxReturn -148.042 __unnamed_task__/MinReturn -241.667 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.5947 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 16:25:18 | [maml_trainer] epoch #27 | Sampling for adapation and meta-testing... 2025-04-02 16:26:28 | [maml_trainer] epoch #27 | Finished meta-testing... 2025-04-02 16:26:28 | [maml_trainer] epoch #27 | Saving snapshot... 2025-04-02 16:26:48 | [maml_trainer] epoch #27 | Saved 2025-04-02 16:26:48 | [maml_trainer] epoch #27 | Time 10286.49 s 2025-04-02 16:26:48 | [maml_trainer] epoch #27 | EpochTime 363.46 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -70.6908 Average/AverageReturn -166.569 Average/Iteration 27 Average/MaxReturn -144.807 Average/MinReturn -207.19 Average/NumEpisodes 80 Average/StdReturn 12.8088 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6813 GaussianMLPPolicy/KLAfter 0.00288408 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.03253e-06 GaussianMLPPolicy/LossBefore -2.84612e-09 GaussianMLPPolicy/dLoss 6.02968e-06 Iteration 27 MetaTest/Average/AverageDiscountedReturn -171.79 MetaTest/Average/AverageReturn -171.79 MetaTest/Average/Iteration 27 MetaTest/Average/MaxReturn -148.905 MetaTest/Average/MinReturn -283.049 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 31.2218 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.79 MetaTest/__unnamed_task__/AverageReturn -171.79 MetaTest/__unnamed_task__/Iteration 27 MetaTest/__unnamed_task__/MaxReturn -148.905 MetaTest/__unnamed_task__/MinReturn -283.049 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 31.2218 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 896000 __unnamed_task__/AverageDiscountedReturn -70.6908 __unnamed_task__/AverageReturn -166.569 __unnamed_task__/Iteration 27 __unnamed_task__/MaxReturn -144.807 __unnamed_task__/MinReturn -207.19 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 12.8088 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 16:33:09 | [maml_trainer] epoch #28 | Sampling for adapation and meta-testing... 2025-04-02 16:34:22 | [maml_trainer] epoch #28 | Finished meta-testing... 2025-04-02 16:34:22 | [maml_trainer] epoch #28 | Saving snapshot... 2025-04-02 16:34:43 | [maml_trainer] epoch #28 | Saved 2025-04-02 16:34:43 | [maml_trainer] epoch #28 | Time 10761.97 s 2025-04-02 16:34:43 | [maml_trainer] epoch #28 | EpochTime 475.48 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -70.8336 Average/AverageReturn -166.202 Average/Iteration 28 Average/MaxReturn -146.999 Average/MinReturn -247.562 Average/NumEpisodes 80 Average/StdReturn 18.0236 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6757 GaussianMLPPolicy/KLAfter 0.0023898 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.37121e-06 GaussianMLPPolicy/LossBefore -8.49366e-10 GaussianMLPPolicy/dLoss 5.37036e-06 Iteration 28 MetaTest/Average/AverageDiscountedReturn -164.897 MetaTest/Average/AverageReturn -164.897 MetaTest/Average/Iteration 28 MetaTest/Average/MaxReturn -148.309 MetaTest/Average/MinReturn -196.775 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.9723 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.897 MetaTest/__unnamed_task__/AverageReturn -164.897 MetaTest/__unnamed_task__/Iteration 28 MetaTest/__unnamed_task__/MaxReturn -148.309 MetaTest/__unnamed_task__/MinReturn -196.775 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.9723 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 928000 __unnamed_task__/AverageDiscountedReturn -70.8336 __unnamed_task__/AverageReturn -166.202 __unnamed_task__/Iteration 28 __unnamed_task__/MaxReturn -146.999 __unnamed_task__/MinReturn -247.562 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.0236 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 16:39:36 | [maml_trainer] epoch #29 | Sampling for adapation and meta-testing... 2025-04-02 16:40:49 | [maml_trainer] epoch #29 | Finished meta-testing... 2025-04-02 16:40:49 | [maml_trainer] epoch #29 | Saving snapshot... 2025-04-02 16:41:09 | [maml_trainer] epoch #29 | Saved 2025-04-02 16:41:09 | [maml_trainer] epoch #29 | Time 11148.02 s 2025-04-02 16:41:09 | [maml_trainer] epoch #29 | EpochTime 386.04 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -71.8309 Average/AverageReturn -168.413 Average/Iteration 29 Average/MaxReturn -143.435 Average/MinReturn -240.021 Average/NumEpisodes 80 Average/StdReturn 18.0539 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6678 GaussianMLPPolicy/KLAfter 0.00236432 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.80969e-05 GaussianMLPPolicy/LossBefore 1.69873e-09 GaussianMLPPolicy/dLoss -2.80952e-05 Iteration 29 MetaTest/Average/AverageDiscountedReturn -168.653 MetaTest/Average/AverageReturn -168.653 MetaTest/Average/Iteration 29 MetaTest/Average/MaxReturn -145.533 MetaTest/Average/MinReturn -241.538 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.2388 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.653 MetaTest/__unnamed_task__/AverageReturn -168.653 MetaTest/__unnamed_task__/Iteration 29 MetaTest/__unnamed_task__/MaxReturn -145.533 MetaTest/__unnamed_task__/MinReturn -241.538 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.2388 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 960000 __unnamed_task__/AverageDiscountedReturn -71.8309 __unnamed_task__/AverageReturn -168.413 __unnamed_task__/Iteration 29 __unnamed_task__/MaxReturn -143.435 __unnamed_task__/MinReturn -240.021 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.0539 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 16:46:00 | [maml_trainer] epoch #30 | Sampling for adapation and meta-testing... 2025-04-02 16:47:13 | [maml_trainer] epoch #30 | Finished meta-testing... 2025-04-02 16:47:13 | [maml_trainer] epoch #30 | Saving snapshot... 2025-04-02 16:47:34 | [maml_trainer] epoch #30 | Saved 2025-04-02 16:47:34 | [maml_trainer] epoch #30 | Time 11532.27 s 2025-04-02 16:47:34 | [maml_trainer] epoch #30 | EpochTime 384.24 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -70.296 Average/AverageReturn -164.378 Average/Iteration 30 Average/MaxReturn -147.289 Average/MinReturn -233.064 Average/NumEpisodes 80 Average/StdReturn 15.1827 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6594 GaussianMLPPolicy/KLAfter 0.00230621 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.40797e-05 GaussianMLPPolicy/LossBefore 2.47359e-09 GaussianMLPPolicy/dLoss -2.40772e-05 Iteration 30 MetaTest/Average/AverageDiscountedReturn -170.585 MetaTest/Average/AverageReturn -170.585 MetaTest/Average/Iteration 30 MetaTest/Average/MaxReturn -153.001 MetaTest/Average/MinReturn -222.044 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.4473 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.585 MetaTest/__unnamed_task__/AverageReturn -170.585 MetaTest/__unnamed_task__/Iteration 30 MetaTest/__unnamed_task__/MaxReturn -153.001 MetaTest/__unnamed_task__/MinReturn -222.044 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.4473 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 992000 __unnamed_task__/AverageDiscountedReturn -70.296 __unnamed_task__/AverageReturn -164.378 __unnamed_task__/Iteration 30 __unnamed_task__/MaxReturn -147.289 __unnamed_task__/MinReturn -233.064 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.1827 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-02 16:52:27 | [maml_trainer] epoch #31 | Sampling for adapation and meta-testing... 2025-04-02 16:53:40 | [maml_trainer] epoch #31 | Finished meta-testing... 2025-04-02 16:53:40 | [maml_trainer] epoch #31 | Saving snapshot... 2025-04-02 16:54:00 | [maml_trainer] epoch #31 | Saved 2025-04-02 16:54:00 | [maml_trainer] epoch #31 | Time 11919.07 s 2025-04-02 16:54:00 | [maml_trainer] epoch #31 | EpochTime 386.80 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.1884 Average/AverageReturn -164.309 Average/Iteration 31 Average/MaxReturn -147.137 Average/MinReturn -245.498 Average/NumEpisodes 80 Average/StdReturn 16.6923 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6505 GaussianMLPPolicy/KLAfter 0.00233092 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.49288e-05 GaussianMLPPolicy/LossBefore -7.34627e-09 GaussianMLPPolicy/dLoss 1.49214e-05 Iteration 31 MetaTest/Average/AverageDiscountedReturn -165.502 MetaTest/Average/AverageReturn -165.502 MetaTest/Average/Iteration 31 MetaTest/Average/MaxReturn -144.497 MetaTest/Average/MinReturn -203.316 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.7763 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.502 MetaTest/__unnamed_task__/AverageReturn -165.502 MetaTest/__unnamed_task__/Iteration 31 MetaTest/__unnamed_task__/MaxReturn -144.497 MetaTest/__unnamed_task__/MinReturn -203.316 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.7763 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.024e+06 __unnamed_task__/AverageDiscountedReturn -70.1884 __unnamed_task__/AverageReturn -164.309 __unnamed_task__/Iteration 31 __unnamed_task__/MaxReturn -147.137 __unnamed_task__/MinReturn -245.498 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.6923 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 16:58:51 | [maml_trainer] epoch #32 | Sampling for adapation and meta-testing... 2025-04-02 17:00:02 | [maml_trainer] epoch #32 | Finished meta-testing... 2025-04-02 17:00:02 | [maml_trainer] epoch #32 | Saving snapshot... 2025-04-02 17:00:23 | [maml_trainer] epoch #32 | Saved 2025-04-02 17:00:23 | [maml_trainer] epoch #32 | Time 12302.10 s 2025-04-02 17:00:23 | [maml_trainer] epoch #32 | EpochTime 383.03 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.1157 Average/AverageReturn -163.343 Average/Iteration 32 Average/MaxReturn -141.454 Average/MinReturn -234.343 Average/NumEpisodes 80 Average/StdReturn 15.1464 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6426 GaussianMLPPolicy/KLAfter 0.00396476 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.91252e-06 GaussianMLPPolicy/LossBefore -5.36442e-10 GaussianMLPPolicy/dLoss -9.91306e-06 Iteration 32 MetaTest/Average/AverageDiscountedReturn -167.501 MetaTest/Average/AverageReturn -167.501 MetaTest/Average/Iteration 32 MetaTest/Average/MaxReturn -144.169 MetaTest/Average/MinReturn -213.645 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.6715 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.501 MetaTest/__unnamed_task__/AverageReturn -167.501 MetaTest/__unnamed_task__/Iteration 32 MetaTest/__unnamed_task__/MaxReturn -144.169 MetaTest/__unnamed_task__/MinReturn -213.645 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.6715 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.056e+06 __unnamed_task__/AverageDiscountedReturn -70.1157 __unnamed_task__/AverageReturn -163.343 __unnamed_task__/Iteration 32 __unnamed_task__/MaxReturn -141.454 __unnamed_task__/MinReturn -234.343 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.1464 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 17:05:14 | [maml_trainer] epoch #33 | Sampling for adapation and meta-testing... 2025-04-02 17:06:28 | [maml_trainer] epoch #33 | Finished meta-testing... 2025-04-02 17:06:28 | [maml_trainer] epoch #33 | Saving snapshot... 2025-04-02 17:06:49 | [maml_trainer] epoch #33 | Saved 2025-04-02 17:06:49 | [maml_trainer] epoch #33 | Time 12687.99 s 2025-04-02 17:06:49 | [maml_trainer] epoch #33 | EpochTime 385.88 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -69.0353 Average/AverageReturn -160.172 Average/Iteration 33 Average/MaxReturn -143.329 Average/MinReturn -219.284 Average/NumEpisodes 80 Average/StdReturn 12.1503 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6329 GaussianMLPPolicy/KLAfter 0.00392108 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.82422e-05 GaussianMLPPolicy/LossBefore -1.3262e-09 GaussianMLPPolicy/dLoss 2.82409e-05 Iteration 33 MetaTest/Average/AverageDiscountedReturn -169.789 MetaTest/Average/AverageReturn -169.789 MetaTest/Average/Iteration 33 MetaTest/Average/MaxReturn -147.376 MetaTest/Average/MinReturn -216.909 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.0451 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.789 MetaTest/__unnamed_task__/AverageReturn -169.789 MetaTest/__unnamed_task__/Iteration 33 MetaTest/__unnamed_task__/MaxReturn -147.376 MetaTest/__unnamed_task__/MinReturn -216.909 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.0451 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.088e+06 __unnamed_task__/AverageDiscountedReturn -69.0353 __unnamed_task__/AverageReturn -160.172 __unnamed_task__/Iteration 33 __unnamed_task__/MaxReturn -143.329 __unnamed_task__/MinReturn -219.284 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 12.1503 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 17:11:27 | [maml_trainer] epoch #34 | Sampling for adapation and meta-testing... 2025-04-02 17:12:40 | [maml_trainer] epoch #34 | Finished meta-testing... 2025-04-02 17:12:40 | [maml_trainer] epoch #34 | Saving snapshot... 2025-04-02 17:13:02 | [maml_trainer] epoch #34 | Saved 2025-04-02 17:13:02 | [maml_trainer] epoch #34 | Time 13060.23 s 2025-04-02 17:13:02 | [maml_trainer] epoch #34 | EpochTime 372.24 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.4144 Average/AverageReturn -164.649 Average/Iteration 34 Average/MaxReturn -146.467 Average/MinReturn -211.95 Average/NumEpisodes 80 Average/StdReturn 14.4405 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6252 GaussianMLPPolicy/KLAfter 0.0035162 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.43626e-06 GaussianMLPPolicy/LossBefore -4.70877e-09 GaussianMLPPolicy/dLoss 5.43155e-06 Iteration 34 MetaTest/Average/AverageDiscountedReturn -173.281 MetaTest/Average/AverageReturn -173.281 MetaTest/Average/Iteration 34 MetaTest/Average/MaxReturn -150.059 MetaTest/Average/MinReturn -210.134 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.0305 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.281 MetaTest/__unnamed_task__/AverageReturn -173.281 MetaTest/__unnamed_task__/Iteration 34 MetaTest/__unnamed_task__/MaxReturn -150.059 MetaTest/__unnamed_task__/MinReturn -210.134 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.0305 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.12e+06 __unnamed_task__/AverageDiscountedReturn -70.4144 __unnamed_task__/AverageReturn -164.649 __unnamed_task__/Iteration 34 __unnamed_task__/MaxReturn -146.467 __unnamed_task__/MinReturn -211.95 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.4405 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 17:17:54 | [maml_trainer] epoch #35 | Sampling for adapation and meta-testing... 2025-04-02 17:19:07 | [maml_trainer] epoch #35 | Finished meta-testing... 2025-04-02 17:19:07 | [maml_trainer] epoch #35 | Saving snapshot... 2025-04-02 17:19:27 | [maml_trainer] epoch #35 | Saved 2025-04-02 17:19:27 | [maml_trainer] epoch #35 | Time 13445.79 s 2025-04-02 17:19:27 | [maml_trainer] epoch #35 | EpochTime 385.56 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.1967 Average/AverageReturn -165.288 Average/Iteration 35 Average/MaxReturn -144.654 Average/MinReturn -240.281 Average/NumEpisodes 80 Average/StdReturn 14.6969 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6213 GaussianMLPPolicy/KLAfter 0.00402779 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.1524e-05 GaussianMLPPolicy/LossBefore 4.44055e-09 GaussianMLPPolicy/dLoss 2.15284e-05 Iteration 35 MetaTest/Average/AverageDiscountedReturn -167.537 MetaTest/Average/AverageReturn -167.537 MetaTest/Average/Iteration 35 MetaTest/Average/MaxReturn -147.149 MetaTest/Average/MinReturn -204.69 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.2591 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.537 MetaTest/__unnamed_task__/AverageReturn -167.537 MetaTest/__unnamed_task__/Iteration 35 MetaTest/__unnamed_task__/MaxReturn -147.149 MetaTest/__unnamed_task__/MinReturn -204.69 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.2591 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.152e+06 __unnamed_task__/AverageDiscountedReturn -71.1967 __unnamed_task__/AverageReturn -165.288 __unnamed_task__/Iteration 35 __unnamed_task__/MaxReturn -144.654 __unnamed_task__/MinReturn -240.281 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.6969 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 17:24:30 | [maml_trainer] epoch #36 | Sampling for adapation and meta-testing... 2025-04-02 17:25:43 | [maml_trainer] epoch #36 | Finished meta-testing... 2025-04-02 17:25:43 | [maml_trainer] epoch #36 | Saving snapshot... 2025-04-02 17:26:03 | [maml_trainer] epoch #36 | Saved 2025-04-02 17:26:03 | [maml_trainer] epoch #36 | Time 13841.81 s 2025-04-02 17:26:03 | [maml_trainer] epoch #36 | EpochTime 396.02 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -69.8919 Average/AverageReturn -162.706 Average/Iteration 36 Average/MaxReturn -146.269 Average/MinReturn -213.005 Average/NumEpisodes 80 Average/StdReturn 9.98592 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6159 GaussianMLPPolicy/KLAfter 0.00445043 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.03836e-05 GaussianMLPPolicy/LossBefore 3.05474e-09 GaussianMLPPolicy/dLoss 2.03867e-05 Iteration 36 MetaTest/Average/AverageDiscountedReturn -166.983 MetaTest/Average/AverageReturn -166.983 MetaTest/Average/Iteration 36 MetaTest/Average/MaxReturn -150.482 MetaTest/Average/MinReturn -213.681 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.6181 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.983 MetaTest/__unnamed_task__/AverageReturn -166.983 MetaTest/__unnamed_task__/Iteration 36 MetaTest/__unnamed_task__/MaxReturn -150.482 MetaTest/__unnamed_task__/MinReturn -213.681 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.6181 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.184e+06 __unnamed_task__/AverageDiscountedReturn -69.8919 __unnamed_task__/AverageReturn -162.706 __unnamed_task__/Iteration 36 __unnamed_task__/MaxReturn -146.269 __unnamed_task__/MinReturn -213.005 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 9.98592 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 17:30:53 | [maml_trainer] epoch #37 | Sampling for adapation and meta-testing... 2025-04-02 17:32:05 | [maml_trainer] epoch #37 | Finished meta-testing... 2025-04-02 17:32:05 | [maml_trainer] epoch #37 | Saving snapshot... 2025-04-02 17:32:27 | [maml_trainer] epoch #37 | Saved 2025-04-02 17:32:27 | [maml_trainer] epoch #37 | Time 14225.59 s 2025-04-02 17:32:27 | [maml_trainer] epoch #37 | EpochTime 383.78 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.3258 Average/AverageReturn -168.362 Average/Iteration 37 Average/MaxReturn -141.43 Average/MinReturn -249.459 Average/NumEpisodes 80 Average/StdReturn 19.342 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6098 GaussianMLPPolicy/KLAfter 0.00359539 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.84439e-05 GaussianMLPPolicy/LossBefore -6.25849e-10 GaussianMLPPolicy/dLoss -1.84446e-05 Iteration 37 MetaTest/Average/AverageDiscountedReturn -165.787 MetaTest/Average/AverageReturn -165.787 MetaTest/Average/Iteration 37 MetaTest/Average/MaxReturn -148.805 MetaTest/Average/MinReturn -201.189 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.1041 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.787 MetaTest/__unnamed_task__/AverageReturn -165.787 MetaTest/__unnamed_task__/Iteration 37 MetaTest/__unnamed_task__/MaxReturn -148.805 MetaTest/__unnamed_task__/MinReturn -201.189 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.1041 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.216e+06 __unnamed_task__/AverageDiscountedReturn -72.3258 __unnamed_task__/AverageReturn -168.362 __unnamed_task__/Iteration 37 __unnamed_task__/MaxReturn -141.43 __unnamed_task__/MinReturn -249.459 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.342 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 17:37:03 | [maml_trainer] epoch #38 | Sampling for adapation and meta-testing... 2025-04-02 17:38:16 | [maml_trainer] epoch #38 | Finished meta-testing... 2025-04-02 17:38:16 | [maml_trainer] epoch #38 | Saving snapshot... 2025-04-02 17:38:37 | [maml_trainer] epoch #38 | Saved 2025-04-02 17:38:37 | [maml_trainer] epoch #38 | Time 14595.60 s 2025-04-02 17:38:37 | [maml_trainer] epoch #38 | EpochTime 370.00 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.3005 Average/AverageReturn -163.791 Average/Iteration 38 Average/MaxReturn -149.764 Average/MinReturn -202.091 Average/NumEpisodes 80 Average/StdReturn 9.85371 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6062 GaussianMLPPolicy/KLAfter 0.00361439 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.7904e-05 GaussianMLPPolicy/LossBefore -6.09458e-09 GaussianMLPPolicy/dLoss 1.78979e-05 Iteration 38 MetaTest/Average/AverageDiscountedReturn -168.72 MetaTest/Average/AverageReturn -168.72 MetaTest/Average/Iteration 38 MetaTest/Average/MaxReturn -150.713 MetaTest/Average/MinReturn -205.652 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.4793 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.72 MetaTest/__unnamed_task__/AverageReturn -168.72 MetaTest/__unnamed_task__/Iteration 38 MetaTest/__unnamed_task__/MaxReturn -150.713 MetaTest/__unnamed_task__/MinReturn -205.652 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.4793 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.248e+06 __unnamed_task__/AverageDiscountedReturn -70.3005 __unnamed_task__/AverageReturn -163.791 __unnamed_task__/Iteration 38 __unnamed_task__/MaxReturn -149.764 __unnamed_task__/MinReturn -202.091 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 9.85371 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 17:43:27 | [maml_trainer] epoch #39 | Sampling for adapation and meta-testing... 2025-04-02 17:44:40 | [maml_trainer] epoch #39 | Finished meta-testing... 2025-04-02 17:44:40 | [maml_trainer] epoch #39 | Saving snapshot... 2025-04-02 17:45:01 | [maml_trainer] epoch #39 | Saved 2025-04-02 17:45:01 | [maml_trainer] epoch #39 | Time 14979.80 s 2025-04-02 17:45:01 | [maml_trainer] epoch #39 | EpochTime 384.20 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.7768 Average/AverageReturn -169.524 Average/Iteration 39 Average/MaxReturn -149.039 Average/MinReturn -294.631 Average/NumEpisodes 80 Average/StdReturn 20.2351 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6018 GaussianMLPPolicy/KLAfter 0.00350577 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.42819e-05 GaussianMLPPolicy/LossBefore -6.49691e-09 GaussianMLPPolicy/dLoss 3.42754e-05 Iteration 39 MetaTest/Average/AverageDiscountedReturn -166.397 MetaTest/Average/AverageReturn -166.397 MetaTest/Average/Iteration 39 MetaTest/Average/MaxReturn -152.799 MetaTest/Average/MinReturn -202.004 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.5785 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.397 MetaTest/__unnamed_task__/AverageReturn -166.397 MetaTest/__unnamed_task__/Iteration 39 MetaTest/__unnamed_task__/MaxReturn -152.799 MetaTest/__unnamed_task__/MinReturn -202.004 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.5785 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.28e+06 __unnamed_task__/AverageDiscountedReturn -72.7768 __unnamed_task__/AverageReturn -169.524 __unnamed_task__/Iteration 39 __unnamed_task__/MaxReturn -149.039 __unnamed_task__/MinReturn -294.631 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.2351 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 17:49:52 | [maml_trainer] epoch #40 | Sampling for adapation and meta-testing... 2025-04-02 17:51:04 | [maml_trainer] epoch #40 | Finished meta-testing... 2025-04-02 17:51:04 | [maml_trainer] epoch #40 | Saving snapshot... 2025-04-02 17:51:25 | [maml_trainer] epoch #40 | Saved 2025-04-02 17:51:25 | [maml_trainer] epoch #40 | Time 15363.37 s 2025-04-02 17:51:25 | [maml_trainer] epoch #40 | EpochTime 383.56 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.5583 Average/AverageReturn -169.385 Average/Iteration 40 Average/MaxReturn -149.655 Average/MinReturn -237.268 Average/NumEpisodes 80 Average/StdReturn 17.1973 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5987 GaussianMLPPolicy/KLAfter 0.002284 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.88184e-07 GaussianMLPPolicy/LossBefore -9.70066e-09 GaussianMLPPolicy/dLoss 8.78483e-07 Iteration 40 MetaTest/Average/AverageDiscountedReturn -176.082 MetaTest/Average/AverageReturn -176.082 MetaTest/Average/Iteration 40 MetaTest/Average/MaxReturn -156.255 MetaTest/Average/MinReturn -239.463 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.3135 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.082 MetaTest/__unnamed_task__/AverageReturn -176.082 MetaTest/__unnamed_task__/Iteration 40 MetaTest/__unnamed_task__/MaxReturn -156.255 MetaTest/__unnamed_task__/MinReturn -239.463 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.3135 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.312e+06 __unnamed_task__/AverageDiscountedReturn -72.5583 __unnamed_task__/AverageReturn -169.385 __unnamed_task__/Iteration 40 __unnamed_task__/MaxReturn -149.655 __unnamed_task__/MinReturn -237.268 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.1973 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 17:56:14 | [maml_trainer] epoch #41 | Sampling for adapation and meta-testing... 2025-04-02 17:57:26 | [maml_trainer] epoch #41 | Finished meta-testing... 2025-04-02 17:57:26 | [maml_trainer] epoch #41 | Saving snapshot... 2025-04-02 17:57:47 | [maml_trainer] epoch #41 | Saved 2025-04-02 17:57:47 | [maml_trainer] epoch #41 | Time 15745.76 s 2025-04-02 17:57:47 | [maml_trainer] epoch #41 | EpochTime 382.39 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.8891 Average/AverageReturn -171.098 Average/Iteration 41 Average/MaxReturn -147.558 Average/MinReturn -233.276 Average/NumEpisodes 80 Average/StdReturn 18.7151 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5971 GaussianMLPPolicy/KLAfter 0.00224349 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.0498e-05 GaussianMLPPolicy/LossBefore -3.17395e-09 GaussianMLPPolicy/dLoss -3.05012e-05 Iteration 41 MetaTest/Average/AverageDiscountedReturn -167.373 MetaTest/Average/AverageReturn -167.373 MetaTest/Average/Iteration 41 MetaTest/Average/MaxReturn -152.748 MetaTest/Average/MinReturn -206.917 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.9268 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.373 MetaTest/__unnamed_task__/AverageReturn -167.373 MetaTest/__unnamed_task__/Iteration 41 MetaTest/__unnamed_task__/MaxReturn -152.748 MetaTest/__unnamed_task__/MinReturn -206.917 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.9268 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.344e+06 __unnamed_task__/AverageDiscountedReturn -72.8891 __unnamed_task__/AverageReturn -171.098 __unnamed_task__/Iteration 41 __unnamed_task__/MaxReturn -147.558 __unnamed_task__/MinReturn -233.276 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.7151 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 18:02:36 | [maml_trainer] epoch #42 | Sampling for adapation and meta-testing... 2025-04-02 18:03:48 | [maml_trainer] epoch #42 | Finished meta-testing... 2025-04-02 18:03:48 | [maml_trainer] epoch #42 | Saving snapshot... 2025-04-02 18:04:10 | [maml_trainer] epoch #42 | Saved 2025-04-02 18:04:10 | [maml_trainer] epoch #42 | Time 16128.35 s 2025-04-02 18:04:10 | [maml_trainer] epoch #42 | EpochTime 382.59 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.5559 Average/AverageReturn -167.42 Average/Iteration 42 Average/MaxReturn -146.848 Average/MinReturn -216.718 Average/NumEpisodes 80 Average/StdReturn 12.4661 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5967 GaussianMLPPolicy/KLAfter 0.00184167 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.22262e-06 GaussianMLPPolicy/LossBefore 5.06639e-09 GaussianMLPPolicy/dLoss -5.21755e-06 Iteration 42 MetaTest/Average/AverageDiscountedReturn -171.381 MetaTest/Average/AverageReturn -171.381 MetaTest/Average/Iteration 42 MetaTest/Average/MaxReturn -150.906 MetaTest/Average/MinReturn -236.774 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.1854 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.381 MetaTest/__unnamed_task__/AverageReturn -171.381 MetaTest/__unnamed_task__/Iteration 42 MetaTest/__unnamed_task__/MaxReturn -150.906 MetaTest/__unnamed_task__/MinReturn -236.774 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.1854 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.376e+06 __unnamed_task__/AverageDiscountedReturn -71.5559 __unnamed_task__/AverageReturn -167.42 __unnamed_task__/Iteration 42 __unnamed_task__/MaxReturn -146.848 __unnamed_task__/MinReturn -216.718 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 12.4661 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 18:08:59 | [maml_trainer] epoch #43 | Sampling for adapation and meta-testing... 2025-04-02 18:10:10 | [maml_trainer] epoch #43 | Finished meta-testing... 2025-04-02 18:10:10 | [maml_trainer] epoch #43 | Saving snapshot... 2025-04-02 18:10:31 | [maml_trainer] epoch #43 | Saved 2025-04-02 18:10:31 | [maml_trainer] epoch #43 | Time 16509.87 s 2025-04-02 18:10:31 | [maml_trainer] epoch #43 | EpochTime 381.51 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.9419 Average/AverageReturn -168.973 Average/Iteration 43 Average/MaxReturn -151.856 Average/MinReturn -213.675 Average/NumEpisodes 80 Average/StdReturn 13.7419 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5992 GaussianMLPPolicy/KLAfter 0.00277554 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.80902e-06 GaussianMLPPolicy/LossBefore 4.88758e-09 GaussianMLPPolicy/dLoss -2.80413e-06 Iteration 43 MetaTest/Average/AverageDiscountedReturn -173.769 MetaTest/Average/AverageReturn -173.769 MetaTest/Average/Iteration 43 MetaTest/Average/MaxReturn -157.499 MetaTest/Average/MinReturn -224.425 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.6946 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.769 MetaTest/__unnamed_task__/AverageReturn -173.769 MetaTest/__unnamed_task__/Iteration 43 MetaTest/__unnamed_task__/MaxReturn -157.499 MetaTest/__unnamed_task__/MinReturn -224.425 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.6946 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.408e+06 __unnamed_task__/AverageDiscountedReturn -71.9419 __unnamed_task__/AverageReturn -168.973 __unnamed_task__/Iteration 43 __unnamed_task__/MaxReturn -151.856 __unnamed_task__/MinReturn -213.675 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.7419 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 18:15:20 | [maml_trainer] epoch #44 | Sampling for adapation and meta-testing... 2025-04-02 18:16:33 | [maml_trainer] epoch #44 | Finished meta-testing... 2025-04-02 18:16:33 | [maml_trainer] epoch #44 | Saving snapshot... 2025-04-02 18:16:53 | [maml_trainer] epoch #44 | Saved 2025-04-02 18:16:53 | [maml_trainer] epoch #44 | Time 16892.03 s 2025-04-02 18:16:53 | [maml_trainer] epoch #44 | EpochTime 382.16 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.6661 Average/AverageReturn -168.263 Average/Iteration 44 Average/MaxReturn -151.448 Average/MinReturn -220.303 Average/NumEpisodes 80 Average/StdReturn 11.4389 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6041 GaussianMLPPolicy/KLAfter 0.00179973 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.00515e-05 GaussianMLPPolicy/LossBefore 3.51667e-09 GaussianMLPPolicy/dLoss -2.0048e-05 Iteration 44 MetaTest/Average/AverageDiscountedReturn -162.921 MetaTest/Average/AverageReturn -162.921 MetaTest/Average/Iteration 44 MetaTest/Average/MaxReturn -149.682 MetaTest/Average/MinReturn -172.729 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.14014 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -162.921 MetaTest/__unnamed_task__/AverageReturn -162.921 MetaTest/__unnamed_task__/Iteration 44 MetaTest/__unnamed_task__/MaxReturn -149.682 MetaTest/__unnamed_task__/MinReturn -172.729 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.14014 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.44e+06 __unnamed_task__/AverageDiscountedReturn -71.6661 __unnamed_task__/AverageReturn -168.263 __unnamed_task__/Iteration 44 __unnamed_task__/MaxReturn -151.448 __unnamed_task__/MinReturn -220.303 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 11.4389 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 18:21:40 | [maml_trainer] epoch #45 | Sampling for adapation and meta-testing... 2025-04-02 18:22:53 | [maml_trainer] epoch #45 | Finished meta-testing... 2025-04-02 18:22:53 | [maml_trainer] epoch #45 | Saving snapshot... 2025-04-02 18:23:14 | [maml_trainer] epoch #45 | Saved 2025-04-02 18:23:14 | [maml_trainer] epoch #45 | Time 17272.91 s 2025-04-02 18:23:14 | [maml_trainer] epoch #45 | EpochTime 380.87 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.0975 Average/AverageReturn -171.044 Average/Iteration 45 Average/MaxReturn -148.632 Average/MinReturn -273.276 Average/NumEpisodes 80 Average/StdReturn 17.8674 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6094 GaussianMLPPolicy/KLAfter 0.00160816 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.80491e-05 GaussianMLPPolicy/LossBefore 4.61936e-09 GaussianMLPPolicy/dLoss 1.80537e-05 Iteration 45 MetaTest/Average/AverageDiscountedReturn -172.159 MetaTest/Average/AverageReturn -172.159 MetaTest/Average/Iteration 45 MetaTest/Average/MaxReturn -155.048 MetaTest/Average/MinReturn -231.868 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.2064 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.159 MetaTest/__unnamed_task__/AverageReturn -172.159 MetaTest/__unnamed_task__/Iteration 45 MetaTest/__unnamed_task__/MaxReturn -155.048 MetaTest/__unnamed_task__/MinReturn -231.868 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.2064 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.472e+06 __unnamed_task__/AverageDiscountedReturn -73.0975 __unnamed_task__/AverageReturn -171.044 __unnamed_task__/Iteration 45 __unnamed_task__/MaxReturn -148.632 __unnamed_task__/MinReturn -273.276 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.8674 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 18:28:01 | [maml_trainer] epoch #46 | Sampling for adapation and meta-testing... 2025-04-02 18:29:13 | [maml_trainer] epoch #46 | Finished meta-testing... 2025-04-02 18:29:13 | [maml_trainer] epoch #46 | Saving snapshot... 2025-04-02 18:29:35 | [maml_trainer] epoch #46 | Saved 2025-04-02 18:29:35 | [maml_trainer] epoch #46 | Time 17653.43 s 2025-04-02 18:29:35 | [maml_trainer] epoch #46 | EpochTime 380.52 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.1427 Average/AverageReturn -168.621 Average/Iteration 46 Average/MaxReturn -151.138 Average/MinReturn -235.955 Average/NumEpisodes 80 Average/StdReturn 17.007 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6147 GaussianMLPPolicy/KLAfter 0.00203657 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.17573e-05 GaussianMLPPolicy/LossBefore -2.48849e-09 GaussianMLPPolicy/dLoss -2.17598e-05 Iteration 46 MetaTest/Average/AverageDiscountedReturn -169.051 MetaTest/Average/AverageReturn -169.051 MetaTest/Average/Iteration 46 MetaTest/Average/MaxReturn -150.922 MetaTest/Average/MinReturn -210.151 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.9755 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.051 MetaTest/__unnamed_task__/AverageReturn -169.051 MetaTest/__unnamed_task__/Iteration 46 MetaTest/__unnamed_task__/MaxReturn -150.922 MetaTest/__unnamed_task__/MinReturn -210.151 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.9755 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.504e+06 __unnamed_task__/AverageDiscountedReturn -72.1427 __unnamed_task__/AverageReturn -168.621 __unnamed_task__/Iteration 46 __unnamed_task__/MaxReturn -151.138 __unnamed_task__/MinReturn -235.955 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.007 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 18:34:24 | [maml_trainer] epoch #47 | Sampling for adapation and meta-testing... 2025-04-02 18:35:36 | [maml_trainer] epoch #47 | Finished meta-testing... 2025-04-02 18:35:36 | [maml_trainer] epoch #47 | Saving snapshot... 2025-04-02 18:35:58 | [maml_trainer] epoch #47 | Saved 2025-04-02 18:35:58 | [maml_trainer] epoch #47 | Time 18036.75 s 2025-04-02 18:35:58 | [maml_trainer] epoch #47 | EpochTime 383.31 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.8236 Average/AverageReturn -170.964 Average/Iteration 47 Average/MaxReturn -151.601 Average/MinReturn -226.16 Average/NumEpisodes 80 Average/StdReturn 15.5126 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6178 GaussianMLPPolicy/KLAfter 0.00138915 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.96696e-06 GaussianMLPPolicy/LossBefore -1.80304e-09 GaussianMLPPolicy/dLoss -2.96876e-06 Iteration 47 MetaTest/Average/AverageDiscountedReturn -163.926 MetaTest/Average/AverageReturn -163.926 MetaTest/Average/Iteration 47 MetaTest/Average/MaxReturn -150.645 MetaTest/Average/MinReturn -178.12 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.71231 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -163.926 MetaTest/__unnamed_task__/AverageReturn -163.926 MetaTest/__unnamed_task__/Iteration 47 MetaTest/__unnamed_task__/MaxReturn -150.645 MetaTest/__unnamed_task__/MinReturn -178.12 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.71231 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.536e+06 __unnamed_task__/AverageDiscountedReturn -72.8236 __unnamed_task__/AverageReturn -170.964 __unnamed_task__/Iteration 47 __unnamed_task__/MaxReturn -151.601 __unnamed_task__/MinReturn -226.16 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.5126 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 18:40:40 | [maml_trainer] epoch #48 | Sampling for adapation and meta-testing... 2025-04-02 18:41:52 | [maml_trainer] epoch #48 | Finished meta-testing... 2025-04-02 18:41:52 | [maml_trainer] epoch #48 | Saving snapshot... 2025-04-02 18:42:13 | [maml_trainer] epoch #48 | Saved 2025-04-02 18:42:13 | [maml_trainer] epoch #48 | Time 18411.76 s 2025-04-02 18:42:13 | [maml_trainer] epoch #48 | EpochTime 375.01 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.9289 Average/AverageReturn -168.47 Average/Iteration 48 Average/MaxReturn -150.346 Average/MinReturn -238.16 Average/NumEpisodes 80 Average/StdReturn 12.931 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.62 GaussianMLPPolicy/KLAfter 0.00143354 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.06499e-06 GaussianMLPPolicy/LossBefore 6.69062e-09 GaussianMLPPolicy/dLoss 9.07168e-06 Iteration 48 MetaTest/Average/AverageDiscountedReturn -169.054 MetaTest/Average/AverageReturn -169.054 MetaTest/Average/Iteration 48 MetaTest/Average/MaxReturn -158.452 MetaTest/Average/MinReturn -224.701 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.9219 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.054 MetaTest/__unnamed_task__/AverageReturn -169.054 MetaTest/__unnamed_task__/Iteration 48 MetaTest/__unnamed_task__/MaxReturn -158.452 MetaTest/__unnamed_task__/MinReturn -224.701 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.9219 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.568e+06 __unnamed_task__/AverageDiscountedReturn -71.9289 __unnamed_task__/AverageReturn -168.47 __unnamed_task__/Iteration 48 __unnamed_task__/MaxReturn -150.346 __unnamed_task__/MinReturn -238.16 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 12.931 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 18:47:01 | [maml_trainer] epoch #49 | Sampling for adapation and meta-testing... 2025-04-02 18:48:13 | [maml_trainer] epoch #49 | Finished meta-testing... 2025-04-02 18:48:13 | [maml_trainer] epoch #49 | Saving snapshot... 2025-04-02 18:48:34 | [maml_trainer] epoch #49 | Saved 2025-04-02 18:48:34 | [maml_trainer] epoch #49 | Time 18792.88 s 2025-04-02 18:48:34 | [maml_trainer] epoch #49 | EpochTime 381.11 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.6095 Average/AverageReturn -170.26 Average/Iteration 49 Average/MaxReturn -151.903 Average/MinReturn -233.563 Average/NumEpisodes 80 Average/StdReturn 13.2155 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6195 GaussianMLPPolicy/KLAfter 0.0021001 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.27031e-05 GaussianMLPPolicy/LossBefore -3.17395e-09 GaussianMLPPolicy/dLoss 2.27e-05 Iteration 49 MetaTest/Average/AverageDiscountedReturn -167.887 MetaTest/Average/AverageReturn -167.887 MetaTest/Average/Iteration 49 MetaTest/Average/MaxReturn -152.682 MetaTest/Average/MinReturn -206.139 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.3346 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.887 MetaTest/__unnamed_task__/AverageReturn -167.887 MetaTest/__unnamed_task__/Iteration 49 MetaTest/__unnamed_task__/MaxReturn -152.682 MetaTest/__unnamed_task__/MinReturn -206.139 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.3346 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6e+06 __unnamed_task__/AverageDiscountedReturn -72.6095 __unnamed_task__/AverageReturn -170.26 __unnamed_task__/Iteration 49 __unnamed_task__/MaxReturn -151.903 __unnamed_task__/MinReturn -233.563 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.2155 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 18:53:22 | [maml_trainer] epoch #50 | Sampling for adapation and meta-testing... 2025-04-02 18:54:34 | [maml_trainer] epoch #50 | Finished meta-testing... 2025-04-02 18:54:34 | [maml_trainer] epoch #50 | Saving snapshot... 2025-04-02 18:54:55 | [maml_trainer] epoch #50 | Saved 2025-04-02 18:54:56 | [maml_trainer] epoch #50 | Time 19174.11 s 2025-04-02 18:54:56 | [maml_trainer] epoch #50 | EpochTime 381.23 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.7906 Average/AverageReturn -170.724 Average/Iteration 50 Average/MaxReturn -151.975 Average/MinReturn -244.725 Average/NumEpisodes 80 Average/StdReturn 17.0917 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6189 GaussianMLPPolicy/KLAfter 0.00200618 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.9925e-05 GaussianMLPPolicy/LossBefore -2.5481e-09 GaussianMLPPolicy/dLoss 1.99225e-05 Iteration 50 MetaTest/Average/AverageDiscountedReturn -169.227 MetaTest/Average/AverageReturn -169.227 MetaTest/Average/Iteration 50 MetaTest/Average/MaxReturn -153.631 MetaTest/Average/MinReturn -207.631 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.4566 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.227 MetaTest/__unnamed_task__/AverageReturn -169.227 MetaTest/__unnamed_task__/Iteration 50 MetaTest/__unnamed_task__/MaxReturn -153.631 MetaTest/__unnamed_task__/MinReturn -207.631 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.4566 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.632e+06 __unnamed_task__/AverageDiscountedReturn -72.7906 __unnamed_task__/AverageReturn -170.724 __unnamed_task__/Iteration 50 __unnamed_task__/MaxReturn -151.975 __unnamed_task__/MinReturn -244.725 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.0917 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 18:59:45 | [maml_trainer] epoch #51 | Sampling for adapation and meta-testing... 2025-04-02 19:00:58 | [maml_trainer] epoch #51 | Finished meta-testing... 2025-04-02 19:00:58 | [maml_trainer] epoch #51 | Saving snapshot... 2025-04-02 19:01:20 | [maml_trainer] epoch #51 | Saved 2025-04-02 19:01:20 | [maml_trainer] epoch #51 | Time 19558.68 s 2025-04-02 19:01:20 | [maml_trainer] epoch #51 | EpochTime 384.56 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.5963 Average/AverageReturn -169.396 Average/Iteration 51 Average/MaxReturn -148.018 Average/MinReturn -237.722 Average/NumEpisodes 80 Average/StdReturn 18.4142 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6186 GaussianMLPPolicy/KLAfter 0.00198278 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.53742e-05 GaussianMLPPolicy/LossBefore 1.41561e-09 GaussianMLPPolicy/dLoss 1.53756e-05 Iteration 51 MetaTest/Average/AverageDiscountedReturn -164.63 MetaTest/Average/AverageReturn -164.63 MetaTest/Average/Iteration 51 MetaTest/Average/MaxReturn -149.452 MetaTest/Average/MinReturn -197.45 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.5693 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.63 MetaTest/__unnamed_task__/AverageReturn -164.63 MetaTest/__unnamed_task__/Iteration 51 MetaTest/__unnamed_task__/MaxReturn -149.452 MetaTest/__unnamed_task__/MinReturn -197.45 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.5693 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.664e+06 __unnamed_task__/AverageDiscountedReturn -72.5963 __unnamed_task__/AverageReturn -169.396 __unnamed_task__/Iteration 51 __unnamed_task__/MaxReturn -148.018 __unnamed_task__/MinReturn -237.722 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.4142 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 19:06:13 | [maml_trainer] epoch #52 | Sampling for adapation and meta-testing... 2025-04-02 19:07:26 | [maml_trainer] epoch #52 | Finished meta-testing... 2025-04-02 19:07:26 | [maml_trainer] epoch #52 | Saving snapshot... 2025-04-02 19:07:45 | [maml_trainer] epoch #52 | Saved 2025-04-02 19:07:45 | [maml_trainer] epoch #52 | Time 19943.69 s 2025-04-02 19:07:45 | [maml_trainer] epoch #52 | EpochTime 385.00 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.3229 Average/AverageReturn -168.669 Average/Iteration 52 Average/MaxReturn -146.821 Average/MinReturn -261.159 Average/NumEpisodes 80 Average/StdReturn 17.9493 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6203 GaussianMLPPolicy/KLAfter 0.00290244 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.5673e-05 GaussianMLPPolicy/LossBefore -3.32296e-09 GaussianMLPPolicy/dLoss 2.56697e-05 Iteration 52 MetaTest/Average/AverageDiscountedReturn -160.271 MetaTest/Average/AverageReturn -160.271 MetaTest/Average/Iteration 52 MetaTest/Average/MaxReturn -147.87 MetaTest/Average/MinReturn -171.685 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.0229 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -160.271 MetaTest/__unnamed_task__/AverageReturn -160.271 MetaTest/__unnamed_task__/Iteration 52 MetaTest/__unnamed_task__/MaxReturn -147.87 MetaTest/__unnamed_task__/MinReturn -171.685 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.0229 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.696e+06 __unnamed_task__/AverageDiscountedReturn -72.3229 __unnamed_task__/AverageReturn -168.669 __unnamed_task__/Iteration 52 __unnamed_task__/MaxReturn -146.821 __unnamed_task__/MinReturn -261.159 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.9493 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 19:12:20 | [maml_trainer] epoch #53 | Sampling for adapation and meta-testing... 2025-04-02 19:13:29 | [maml_trainer] epoch #53 | Finished meta-testing... 2025-04-02 19:13:29 | [maml_trainer] epoch #53 | Saving snapshot... 2025-04-02 19:13:49 | [maml_trainer] epoch #53 | Saved 2025-04-02 19:13:49 | [maml_trainer] epoch #53 | Time 20307.53 s 2025-04-02 19:13:49 | [maml_trainer] epoch #53 | EpochTime 363.84 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.3784 Average/AverageReturn -165.431 Average/Iteration 53 Average/MaxReturn -149.019 Average/MinReturn -245.785 Average/NumEpisodes 80 Average/StdReturn 15.1969 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6219 GaussianMLPPolicy/KLAfter 0.00324446 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.35877e-06 GaussianMLPPolicy/LossBefore 1.08778e-09 GaussianMLPPolicy/dLoss 7.35986e-06 Iteration 53 MetaTest/Average/AverageDiscountedReturn -170.526 MetaTest/Average/AverageReturn -170.526 MetaTest/Average/Iteration 53 MetaTest/Average/MaxReturn -152.683 MetaTest/Average/MinReturn -251.454 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.2112 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.526 MetaTest/__unnamed_task__/AverageReturn -170.526 MetaTest/__unnamed_task__/Iteration 53 MetaTest/__unnamed_task__/MaxReturn -152.683 MetaTest/__unnamed_task__/MinReturn -251.454 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.2112 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.728e+06 __unnamed_task__/AverageDiscountedReturn -71.3784 __unnamed_task__/AverageReturn -165.431 __unnamed_task__/Iteration 53 __unnamed_task__/MaxReturn -149.019 __unnamed_task__/MinReturn -245.785 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.1969 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 19:18:28 | [maml_trainer] epoch #54 | Sampling for adapation and meta-testing... 2025-04-02 19:19:39 | [maml_trainer] epoch #54 | Finished meta-testing... 2025-04-02 19:19:39 | [maml_trainer] epoch #54 | Saving snapshot... 2025-04-02 19:20:01 | [maml_trainer] epoch #54 | Saved 2025-04-02 19:20:01 | [maml_trainer] epoch #54 | Time 20679.49 s 2025-04-02 19:20:01 | [maml_trainer] epoch #54 | EpochTime 371.96 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.2979 Average/AverageReturn -165.757 Average/Iteration 54 Average/MaxReturn -146.669 Average/MinReturn -222.975 Average/NumEpisodes 80 Average/StdReturn 17.9668 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6243 GaussianMLPPolicy/KLAfter 0.00224091 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.289e-06 GaussianMLPPolicy/LossBefore -1.84774e-09 GaussianMLPPolicy/dLoss -3.29085e-06 Iteration 54 MetaTest/Average/AverageDiscountedReturn -161.856 MetaTest/Average/AverageReturn -161.856 MetaTest/Average/Iteration 54 MetaTest/Average/MaxReturn -150.293 MetaTest/Average/MinReturn -175.767 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.73415 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -161.856 MetaTest/__unnamed_task__/AverageReturn -161.856 MetaTest/__unnamed_task__/Iteration 54 MetaTest/__unnamed_task__/MaxReturn -150.293 MetaTest/__unnamed_task__/MinReturn -175.767 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.73415 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.76e+06 __unnamed_task__/AverageDiscountedReturn -71.2979 __unnamed_task__/AverageReturn -165.757 __unnamed_task__/Iteration 54 __unnamed_task__/MaxReturn -146.669 __unnamed_task__/MinReturn -222.975 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.9668 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 19:24:52 | [maml_trainer] epoch #55 | Sampling for adapation and meta-testing... 2025-04-02 19:26:03 | [maml_trainer] epoch #55 | Finished meta-testing... 2025-04-02 19:26:03 | [maml_trainer] epoch #55 | Saving snapshot... 2025-04-02 19:26:25 | [maml_trainer] epoch #55 | Saved 2025-04-02 19:26:25 | [maml_trainer] epoch #55 | Time 21063.76 s 2025-04-02 19:26:25 | [maml_trainer] epoch #55 | EpochTime 384.26 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.2126 Average/AverageReturn -165.644 Average/Iteration 55 Average/MaxReturn -144.784 Average/MinReturn -231.458 Average/NumEpisodes 80 Average/StdReturn 16.8513 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6271 GaussianMLPPolicy/KLAfter 0.00243954 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.16466e-05 GaussianMLPPolicy/LossBefore 4.20213e-09 GaussianMLPPolicy/dLoss -3.16424e-05 Iteration 55 MetaTest/Average/AverageDiscountedReturn -165.463 MetaTest/Average/AverageReturn -165.463 MetaTest/Average/Iteration 55 MetaTest/Average/MaxReturn -148.965 MetaTest/Average/MinReturn -215.989 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.0392 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.463 MetaTest/__unnamed_task__/AverageReturn -165.463 MetaTest/__unnamed_task__/Iteration 55 MetaTest/__unnamed_task__/MaxReturn -148.965 MetaTest/__unnamed_task__/MinReturn -215.989 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.0392 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.792e+06 __unnamed_task__/AverageDiscountedReturn -71.2126 __unnamed_task__/AverageReturn -165.644 __unnamed_task__/Iteration 55 __unnamed_task__/MaxReturn -144.784 __unnamed_task__/MinReturn -231.458 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.8513 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 19:31:18 | [maml_trainer] epoch #56 | Sampling for adapation and meta-testing... 2025-04-02 19:32:30 | [maml_trainer] epoch #56 | Finished meta-testing... 2025-04-02 19:32:30 | [maml_trainer] epoch #56 | Saving snapshot... 2025-04-02 19:32:52 | [maml_trainer] epoch #56 | Saved 2025-04-02 19:32:52 | [maml_trainer] epoch #56 | Time 21450.87 s 2025-04-02 19:32:52 | [maml_trainer] epoch #56 | EpochTime 387.11 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.8671 Average/AverageReturn -168.477 Average/Iteration 56 Average/MaxReturn -145.44 Average/MinReturn -287.914 Average/NumEpisodes 80 Average/StdReturn 25.991 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6303 GaussianMLPPolicy/KLAfter 0.00222239 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.15512e-05 GaussianMLPPolicy/LossBefore -1.78814e-10 GaussianMLPPolicy/dLoss -1.15514e-05 Iteration 56 MetaTest/Average/AverageDiscountedReturn -162.363 MetaTest/Average/AverageReturn -162.363 MetaTest/Average/Iteration 56 MetaTest/Average/MaxReturn -146.35 MetaTest/Average/MinReturn -199.648 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.5345 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -162.363 MetaTest/__unnamed_task__/AverageReturn -162.363 MetaTest/__unnamed_task__/Iteration 56 MetaTest/__unnamed_task__/MaxReturn -146.35 MetaTest/__unnamed_task__/MinReturn -199.648 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.5345 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.824e+06 __unnamed_task__/AverageDiscountedReturn -72.8671 __unnamed_task__/AverageReturn -168.477 __unnamed_task__/Iteration 56 __unnamed_task__/MaxReturn -145.44 __unnamed_task__/MinReturn -287.914 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 25.991 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 19:37:42 | [maml_trainer] epoch #57 | Sampling for adapation and meta-testing... 2025-04-02 19:38:54 | [maml_trainer] epoch #57 | Finished meta-testing... 2025-04-02 19:38:54 | [maml_trainer] epoch #57 | Saving snapshot... 2025-04-02 19:39:15 | [maml_trainer] epoch #57 | Saved 2025-04-02 19:39:15 | [maml_trainer] epoch #57 | Time 21834.09 s 2025-04-02 19:39:15 | [maml_trainer] epoch #57 | EpochTime 383.22 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.1722 Average/AverageReturn -162.574 Average/Iteration 57 Average/MaxReturn -143.975 Average/MinReturn -217.284 Average/NumEpisodes 80 Average/StdReturn 15.8579 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6326 GaussianMLPPolicy/KLAfter 0.00227881 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.19588e-06 GaussianMLPPolicy/LossBefore -7.07805e-09 GaussianMLPPolicy/dLoss 1.1888e-06 Iteration 57 MetaTest/Average/AverageDiscountedReturn -167.084 MetaTest/Average/AverageReturn -167.084 MetaTest/Average/Iteration 57 MetaTest/Average/MaxReturn -146.364 MetaTest/Average/MinReturn -232.416 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.8059 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.084 MetaTest/__unnamed_task__/AverageReturn -167.084 MetaTest/__unnamed_task__/Iteration 57 MetaTest/__unnamed_task__/MaxReturn -146.364 MetaTest/__unnamed_task__/MinReturn -232.416 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.8059 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.856e+06 __unnamed_task__/AverageDiscountedReturn -70.1722 __unnamed_task__/AverageReturn -162.574 __unnamed_task__/Iteration 57 __unnamed_task__/MaxReturn -143.975 __unnamed_task__/MinReturn -217.284 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.8579 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 19:43:58 | [maml_trainer] epoch #58 | Sampling for adapation and meta-testing... 2025-04-02 19:45:06 | [maml_trainer] epoch #58 | Finished meta-testing... 2025-04-02 19:45:06 | [maml_trainer] epoch #58 | Saving snapshot... 2025-04-02 19:45:28 | [maml_trainer] epoch #58 | Saved 2025-04-02 19:45:28 | [maml_trainer] epoch #58 | Time 22206.19 s 2025-04-02 19:45:28 | [maml_trainer] epoch #58 | EpochTime 372.09 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.0276 Average/AverageReturn -165.267 Average/Iteration 58 Average/MaxReturn -147.951 Average/MinReturn -230.661 Average/NumEpisodes 80 Average/StdReturn 16.348 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6334 GaussianMLPPolicy/KLAfter 0.00206368 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.15061e-05 GaussianMLPPolicy/LossBefore -1.3262e-09 GaussianMLPPolicy/dLoss -3.15074e-05 Iteration 58 MetaTest/Average/AverageDiscountedReturn -170.574 MetaTest/Average/AverageReturn -170.574 MetaTest/Average/Iteration 58 MetaTest/Average/MaxReturn -138.522 MetaTest/Average/MinReturn -226.152 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.2611 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.574 MetaTest/__unnamed_task__/AverageReturn -170.574 MetaTest/__unnamed_task__/Iteration 58 MetaTest/__unnamed_task__/MaxReturn -138.522 MetaTest/__unnamed_task__/MinReturn -226.152 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.2611 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.888e+06 __unnamed_task__/AverageDiscountedReturn -71.0276 __unnamed_task__/AverageReturn -165.267 __unnamed_task__/Iteration 58 __unnamed_task__/MaxReturn -147.951 __unnamed_task__/MinReturn -230.661 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.348 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 19:50:20 | [maml_trainer] epoch #59 | Sampling for adapation and meta-testing... 2025-04-02 19:51:32 | [maml_trainer] epoch #59 | Finished meta-testing... 2025-04-02 19:51:32 | [maml_trainer] epoch #59 | Saving snapshot... 2025-04-02 19:51:54 | [maml_trainer] epoch #59 | Saved 2025-04-02 19:51:54 | [maml_trainer] epoch #59 | Time 22592.96 s 2025-04-02 19:51:54 | [maml_trainer] epoch #59 | EpochTime 386.77 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -69.2702 Average/AverageReturn -161.242 Average/Iteration 59 Average/MaxReturn -142.851 Average/MinReturn -209.015 Average/NumEpisodes 80 Average/StdReturn 11.3295 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6342 GaussianMLPPolicy/KLAfter 0.00236786 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.06094e-06 GaussianMLPPolicy/LossBefore 8.24034e-09 GaussianMLPPolicy/dLoss 5.06918e-06 Iteration 59 MetaTest/Average/AverageDiscountedReturn -168.402 MetaTest/Average/AverageReturn -168.402 MetaTest/Average/Iteration 59 MetaTest/Average/MaxReturn -148.235 MetaTest/Average/MinReturn -236.561 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.6845 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.402 MetaTest/__unnamed_task__/AverageReturn -168.402 MetaTest/__unnamed_task__/Iteration 59 MetaTest/__unnamed_task__/MaxReturn -148.235 MetaTest/__unnamed_task__/MinReturn -236.561 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.6845 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.92e+06 __unnamed_task__/AverageDiscountedReturn -69.2702 __unnamed_task__/AverageReturn -161.242 __unnamed_task__/Iteration 59 __unnamed_task__/MaxReturn -142.851 __unnamed_task__/MinReturn -209.015 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 11.3295 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 19:56:46 | [maml_trainer] epoch #60 | Sampling for adapation and meta-testing... 2025-04-02 19:57:59 | [maml_trainer] epoch #60 | Finished meta-testing... 2025-04-02 19:57:59 | [maml_trainer] epoch #60 | Saving snapshot... 2025-04-02 19:58:21 | [maml_trainer] epoch #60 | Saved 2025-04-02 19:58:21 | [maml_trainer] epoch #60 | Time 22979.78 s 2025-04-02 19:58:21 | [maml_trainer] epoch #60 | EpochTime 386.82 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.9368 Average/AverageReturn -165.039 Average/Iteration 60 Average/MaxReturn -142.42 Average/MinReturn -241.333 Average/NumEpisodes 80 Average/StdReturn 20.628 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6346 GaussianMLPPolicy/KLAfter 0.00237811 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.30315e-05 GaussianMLPPolicy/LossBefore -5.39422e-09 GaussianMLPPolicy/dLoss -1.30368e-05 Iteration 60 MetaTest/Average/AverageDiscountedReturn -169.413 MetaTest/Average/AverageReturn -169.413 MetaTest/Average/Iteration 60 MetaTest/Average/MaxReturn -147.519 MetaTest/Average/MinReturn -234.137 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.6143 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.413 MetaTest/__unnamed_task__/AverageReturn -169.413 MetaTest/__unnamed_task__/Iteration 60 MetaTest/__unnamed_task__/MaxReturn -147.519 MetaTest/__unnamed_task__/MinReturn -234.137 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.6143 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.952e+06 __unnamed_task__/AverageDiscountedReturn -70.9368 __unnamed_task__/AverageReturn -165.039 __unnamed_task__/Iteration 60 __unnamed_task__/MaxReturn -142.42 __unnamed_task__/MinReturn -241.333 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.628 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 20:03:14 | [maml_trainer] epoch #61 | Sampling for adapation and meta-testing... 2025-04-02 20:04:27 | [maml_trainer] epoch #61 | Finished meta-testing... 2025-04-02 20:04:27 | [maml_trainer] epoch #61 | Saving snapshot... 2025-04-02 20:04:48 | [maml_trainer] epoch #61 | Saved 2025-04-02 20:04:48 | [maml_trainer] epoch #61 | Time 23366.48 s 2025-04-02 20:04:48 | [maml_trainer] epoch #61 | EpochTime 386.69 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -69.3462 Average/AverageReturn -162.054 Average/Iteration 61 Average/MaxReturn -146.936 Average/MinReturn -195.168 Average/NumEpisodes 80 Average/StdReturn 10.917 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6322 GaussianMLPPolicy/KLAfter 0.00276805 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.77823e-05 GaussianMLPPolicy/LossBefore 9.96888e-09 GaussianMLPPolicy/dLoss 1.77923e-05 Iteration 61 MetaTest/Average/AverageDiscountedReturn -165.798 MetaTest/Average/AverageReturn -165.798 MetaTest/Average/Iteration 61 MetaTest/Average/MaxReturn -146.477 MetaTest/Average/MinReturn -221.145 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.6854 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.798 MetaTest/__unnamed_task__/AverageReturn -165.798 MetaTest/__unnamed_task__/Iteration 61 MetaTest/__unnamed_task__/MaxReturn -146.477 MetaTest/__unnamed_task__/MinReturn -221.145 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.6854 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.984e+06 __unnamed_task__/AverageDiscountedReturn -69.3462 __unnamed_task__/AverageReturn -162.054 __unnamed_task__/Iteration 61 __unnamed_task__/MaxReturn -146.936 __unnamed_task__/MinReturn -195.168 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 10.917 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 20:09:40 | [maml_trainer] epoch #62 | Sampling for adapation and meta-testing... 2025-04-02 20:10:51 | [maml_trainer] epoch #62 | Finished meta-testing... 2025-04-02 20:10:51 | [maml_trainer] epoch #62 | Saving snapshot... 2025-04-02 20:11:13 | [maml_trainer] epoch #62 | Saved 2025-04-02 20:11:13 | [maml_trainer] epoch #62 | Time 23751.41 s 2025-04-02 20:11:13 | [maml_trainer] epoch #62 | EpochTime 384.94 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.3625 Average/AverageReturn -166.696 Average/Iteration 62 Average/MaxReturn -142.01 Average/MinReturn -262.872 Average/NumEpisodes 80 Average/StdReturn 17.5382 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6308 GaussianMLPPolicy/KLAfter 0.00271977 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.82832e-05 GaussianMLPPolicy/LossBefore -1.03563e-08 GaussianMLPPolicy/dLoss -1.82936e-05 Iteration 62 MetaTest/Average/AverageDiscountedReturn -163.534 MetaTest/Average/AverageReturn -163.534 MetaTest/Average/Iteration 62 MetaTest/Average/MaxReturn -153.973 MetaTest/Average/MinReturn -193.519 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.8588 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -163.534 MetaTest/__unnamed_task__/AverageReturn -163.534 MetaTest/__unnamed_task__/Iteration 62 MetaTest/__unnamed_task__/MaxReturn -153.973 MetaTest/__unnamed_task__/MinReturn -193.519 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.8588 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.016e+06 __unnamed_task__/AverageDiscountedReturn -71.3625 __unnamed_task__/AverageReturn -166.696 __unnamed_task__/Iteration 62 __unnamed_task__/MaxReturn -142.01 __unnamed_task__/MinReturn -262.872 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.5382 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 20:15:50 | [maml_trainer] epoch #63 | Sampling for adapation and meta-testing... 2025-04-02 20:17:00 | [maml_trainer] epoch #63 | Finished meta-testing... 2025-04-02 20:17:00 | [maml_trainer] epoch #63 | Saving snapshot... 2025-04-02 20:17:21 | [maml_trainer] epoch #63 | Saved 2025-04-02 20:17:21 | [maml_trainer] epoch #63 | Time 24120.00 s 2025-04-02 20:17:21 | [maml_trainer] epoch #63 | EpochTime 368.58 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.538 Average/AverageReturn -165.563 Average/Iteration 63 Average/MaxReturn -145.652 Average/MinReturn -225.651 Average/NumEpisodes 80 Average/StdReturn 15.3177 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6294 GaussianMLPPolicy/KLAfter 0.00204281 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.27467e-05 GaussianMLPPolicy/LossBefore 4.91738e-10 GaussianMLPPolicy/dLoss -3.27462e-05 Iteration 63 MetaTest/Average/AverageDiscountedReturn -167.586 MetaTest/Average/AverageReturn -167.586 MetaTest/Average/Iteration 63 MetaTest/Average/MaxReturn -147.559 MetaTest/Average/MinReturn -236.611 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.5536 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.586 MetaTest/__unnamed_task__/AverageReturn -167.586 MetaTest/__unnamed_task__/Iteration 63 MetaTest/__unnamed_task__/MaxReturn -147.559 MetaTest/__unnamed_task__/MinReturn -236.611 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.5536 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.048e+06 __unnamed_task__/AverageDiscountedReturn -70.538 __unnamed_task__/AverageReturn -165.563 __unnamed_task__/Iteration 63 __unnamed_task__/MaxReturn -145.652 __unnamed_task__/MinReturn -225.651 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.3177 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 20:22:14 | [maml_trainer] epoch #64 | Sampling for adapation and meta-testing... 2025-04-02 20:23:25 | [maml_trainer] epoch #64 | Finished meta-testing... 2025-04-02 20:23:25 | [maml_trainer] epoch #64 | Saving snapshot... 2025-04-02 20:23:46 | [maml_trainer] epoch #64 | Saved 2025-04-02 20:23:46 | [maml_trainer] epoch #64 | Time 24504.73 s 2025-04-02 20:23:46 | [maml_trainer] epoch #64 | EpochTime 384.73 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.5651 Average/AverageReturn -169.641 Average/Iteration 64 Average/MaxReturn -143.479 Average/MinReturn -294.445 Average/NumEpisodes 80 Average/StdReturn 21.6612 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6267 GaussianMLPPolicy/KLAfter 0.00166979 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.53063e-05 GaussianMLPPolicy/LossBefore -4.91738e-10 GaussianMLPPolicy/dLoss -1.53068e-05 Iteration 64 MetaTest/Average/AverageDiscountedReturn -167.87 MetaTest/Average/AverageReturn -167.87 MetaTest/Average/Iteration 64 MetaTest/Average/MaxReturn -150.064 MetaTest/Average/MinReturn -218.953 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.071 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.87 MetaTest/__unnamed_task__/AverageReturn -167.87 MetaTest/__unnamed_task__/Iteration 64 MetaTest/__unnamed_task__/MaxReturn -150.064 MetaTest/__unnamed_task__/MinReturn -218.953 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.071 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.08e+06 __unnamed_task__/AverageDiscountedReturn -72.5651 __unnamed_task__/AverageReturn -169.641 __unnamed_task__/Iteration 64 __unnamed_task__/MaxReturn -143.479 __unnamed_task__/MinReturn -294.445 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.6612 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 20:28:22 | [maml_trainer] epoch #65 | Sampling for adapation and meta-testing... 2025-04-02 20:29:32 | [maml_trainer] epoch #65 | Finished meta-testing... 2025-04-02 20:29:32 | [maml_trainer] epoch #65 | Saving snapshot... 2025-04-02 20:29:52 | [maml_trainer] epoch #65 | Saved 2025-04-02 20:29:52 | [maml_trainer] epoch #65 | Time 24870.61 s 2025-04-02 20:29:52 | [maml_trainer] epoch #65 | EpochTime 365.87 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.3874 Average/AverageReturn -170.316 Average/Iteration 65 Average/MaxReturn -149.504 Average/MinReturn -241.864 Average/NumEpisodes 80 Average/StdReturn 19.5339 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.623 GaussianMLPPolicy/KLAfter 0.00184619 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.30978e-05 GaussianMLPPolicy/LossBefore -5.21541e-09 GaussianMLPPolicy/dLoss -1.3103e-05 Iteration 65 MetaTest/Average/AverageDiscountedReturn -166.652 MetaTest/Average/AverageReturn -166.652 MetaTest/Average/Iteration 65 MetaTest/Average/MaxReturn -151.462 MetaTest/Average/MinReturn -223.344 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.3971 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.652 MetaTest/__unnamed_task__/AverageReturn -166.652 MetaTest/__unnamed_task__/Iteration 65 MetaTest/__unnamed_task__/MaxReturn -151.462 MetaTest/__unnamed_task__/MinReturn -223.344 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.3971 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.112e+06 __unnamed_task__/AverageDiscountedReturn -72.3874 __unnamed_task__/AverageReturn -170.316 __unnamed_task__/Iteration 65 __unnamed_task__/MaxReturn -149.504 __unnamed_task__/MinReturn -241.864 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.5339 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 20:34:34 | [maml_trainer] epoch #66 | Sampling for adapation and meta-testing... 2025-04-02 20:35:47 | [maml_trainer] epoch #66 | Finished meta-testing... 2025-04-02 20:35:47 | [maml_trainer] epoch #66 | Saving snapshot... 2025-04-02 20:36:09 | [maml_trainer] epoch #66 | Saved 2025-04-02 20:36:09 | [maml_trainer] epoch #66 | Time 25248.00 s 2025-04-02 20:36:09 | [maml_trainer] epoch #66 | EpochTime 377.39 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.4207 Average/AverageReturn -168.878 Average/Iteration 66 Average/MaxReturn -146.966 Average/MinReturn -225.036 Average/NumEpisodes 80 Average/StdReturn 15.7116 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6208 GaussianMLPPolicy/KLAfter 0.00164325 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.90111e-07 GaussianMLPPolicy/LossBefore -1.96695e-09 GaussianMLPPolicy/dLoss 2.88144e-07 Iteration 66 MetaTest/Average/AverageDiscountedReturn -167.795 MetaTest/Average/AverageReturn -167.795 MetaTest/Average/Iteration 66 MetaTest/Average/MaxReturn -150.609 MetaTest/Average/MinReturn -199.238 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.5709 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.795 MetaTest/__unnamed_task__/AverageReturn -167.795 MetaTest/__unnamed_task__/Iteration 66 MetaTest/__unnamed_task__/MaxReturn -150.609 MetaTest/__unnamed_task__/MinReturn -199.238 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.5709 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.144e+06 __unnamed_task__/AverageDiscountedReturn -71.4207 __unnamed_task__/AverageReturn -168.878 __unnamed_task__/Iteration 66 __unnamed_task__/MaxReturn -146.966 __unnamed_task__/MinReturn -225.036 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.7116 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 20:40:59 | [maml_trainer] epoch #67 | Sampling for adapation and meta-testing... 2025-04-02 20:42:11 | [maml_trainer] epoch #67 | Finished meta-testing... 2025-04-02 20:42:11 | [maml_trainer] epoch #67 | Saving snapshot... 2025-04-02 20:42:34 | [maml_trainer] epoch #67 | Saved 2025-04-02 20:42:34 | [maml_trainer] epoch #67 | Time 25632.29 s 2025-04-02 20:42:34 | [maml_trainer] epoch #67 | EpochTime 384.29 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.3484 Average/AverageReturn -168.767 Average/Iteration 67 Average/MaxReturn -146.102 Average/MinReturn -219.453 Average/NumEpisodes 80 Average/StdReturn 14.7419 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6204 GaussianMLPPolicy/KLAfter 0.00229178 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.97764e-06 GaussianMLPPolicy/LossBefore 1.16229e-09 GaussianMLPPolicy/dLoss 4.97881e-06 Iteration 67 MetaTest/Average/AverageDiscountedReturn -166.137 MetaTest/Average/AverageReturn -166.137 MetaTest/Average/Iteration 67 MetaTest/Average/MaxReturn -150.255 MetaTest/Average/MinReturn -178.423 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.18828 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.137 MetaTest/__unnamed_task__/AverageReturn -166.137 MetaTest/__unnamed_task__/Iteration 67 MetaTest/__unnamed_task__/MaxReturn -150.255 MetaTest/__unnamed_task__/MinReturn -178.423 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.18828 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.176e+06 __unnamed_task__/AverageDiscountedReturn -71.3484 __unnamed_task__/AverageReturn -168.767 __unnamed_task__/Iteration 67 __unnamed_task__/MaxReturn -146.102 __unnamed_task__/MinReturn -219.453 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.7419 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 20:47:24 | [maml_trainer] epoch #68 | Sampling for adapation and meta-testing... 2025-04-02 20:48:39 | [maml_trainer] epoch #68 | Finished meta-testing... 2025-04-02 20:48:39 | [maml_trainer] epoch #68 | Saving snapshot... 2025-04-02 20:49:02 | [maml_trainer] epoch #68 | Saved 2025-04-02 20:49:02 | [maml_trainer] epoch #68 | Time 26020.42 s 2025-04-02 20:49:02 | [maml_trainer] epoch #68 | EpochTime 388.13 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.6654 Average/AverageReturn -171.452 Average/Iteration 68 Average/MaxReturn -143.925 Average/MinReturn -245.286 Average/NumEpisodes 80 Average/StdReturn 19.9555 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6191 GaussianMLPPolicy/KLAfter 0.00234555 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.31583e-05 GaussianMLPPolicy/LossBefore 4.76837e-10 GaussianMLPPolicy/dLoss -1.31578e-05 Iteration 68 MetaTest/Average/AverageDiscountedReturn -172.691 MetaTest/Average/AverageReturn -172.691 MetaTest/Average/Iteration 68 MetaTest/Average/MaxReturn -150.057 MetaTest/Average/MinReturn -233.203 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.3905 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.691 MetaTest/__unnamed_task__/AverageReturn -172.691 MetaTest/__unnamed_task__/Iteration 68 MetaTest/__unnamed_task__/MaxReturn -150.057 MetaTest/__unnamed_task__/MinReturn -233.203 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.3905 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.208e+06 __unnamed_task__/AverageDiscountedReturn -72.6654 __unnamed_task__/AverageReturn -171.452 __unnamed_task__/Iteration 68 __unnamed_task__/MaxReturn -143.925 __unnamed_task__/MinReturn -245.286 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.9555 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 20:53:58 | [maml_trainer] epoch #69 | Sampling for adapation and meta-testing... 2025-04-02 20:55:12 | [maml_trainer] epoch #69 | Finished meta-testing... 2025-04-02 20:55:12 | [maml_trainer] epoch #69 | Saving snapshot... 2025-04-02 20:55:34 | [maml_trainer] epoch #69 | Saved 2025-04-02 20:55:34 | [maml_trainer] epoch #69 | Time 26412.29 s 2025-04-02 20:55:34 | [maml_trainer] epoch #69 | EpochTime 391.86 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.6368 Average/AverageReturn -168.294 Average/Iteration 69 Average/MaxReturn -148.036 Average/MinReturn -284.705 Average/NumEpisodes 80 Average/StdReturn 17.8408 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6187 GaussianMLPPolicy/KLAfter 0.00228197 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.66965e-05 GaussianMLPPolicy/LossBefore 2.68221e-09 GaussianMLPPolicy/dLoss -3.66939e-05 Iteration 69 MetaTest/Average/AverageDiscountedReturn -172.05 MetaTest/Average/AverageReturn -172.05 MetaTest/Average/Iteration 69 MetaTest/Average/MaxReturn -157.02 MetaTest/Average/MinReturn -216.634 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.8021 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.05 MetaTest/__unnamed_task__/AverageReturn -172.05 MetaTest/__unnamed_task__/Iteration 69 MetaTest/__unnamed_task__/MaxReturn -157.02 MetaTest/__unnamed_task__/MinReturn -216.634 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.8021 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.24e+06 __unnamed_task__/AverageDiscountedReturn -71.6368 __unnamed_task__/AverageReturn -168.294 __unnamed_task__/Iteration 69 __unnamed_task__/MaxReturn -148.036 __unnamed_task__/MinReturn -284.705 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.8408 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 21:00:24 | [maml_trainer] epoch #70 | Sampling for adapation and meta-testing... 2025-04-02 21:01:38 | [maml_trainer] epoch #70 | Finished meta-testing... 2025-04-02 21:01:38 | [maml_trainer] epoch #70 | Saving snapshot... 2025-04-02 21:01:59 | [maml_trainer] epoch #70 | Saved 2025-04-02 21:01:59 | [maml_trainer] epoch #70 | Time 26797.89 s 2025-04-02 21:01:59 | [maml_trainer] epoch #70 | EpochTime 385.60 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.0247 Average/AverageReturn -167.399 Average/Iteration 70 Average/MaxReturn -149.343 Average/MinReturn -247.396 Average/NumEpisodes 80 Average/StdReturn 16.1196 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6169 GaussianMLPPolicy/KLAfter 0.00191537 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.73548e-06 GaussianMLPPolicy/LossBefore 1.07288e-09 GaussianMLPPolicy/dLoss 2.73655e-06 Iteration 70 MetaTest/Average/AverageDiscountedReturn -169.269 MetaTest/Average/AverageReturn -169.269 MetaTest/Average/Iteration 70 MetaTest/Average/MaxReturn -150.815 MetaTest/Average/MinReturn -221.621 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.5827 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.269 MetaTest/__unnamed_task__/AverageReturn -169.269 MetaTest/__unnamed_task__/Iteration 70 MetaTest/__unnamed_task__/MaxReturn -150.815 MetaTest/__unnamed_task__/MinReturn -221.621 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.5827 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.272e+06 __unnamed_task__/AverageDiscountedReturn -71.0247 __unnamed_task__/AverageReturn -167.399 __unnamed_task__/Iteration 70 __unnamed_task__/MaxReturn -149.343 __unnamed_task__/MinReturn -247.396 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.1196 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 21:06:47 | [maml_trainer] epoch #71 | Sampling for adapation and meta-testing... 2025-04-02 21:08:01 | [maml_trainer] epoch #71 | Finished meta-testing... 2025-04-02 21:08:01 | [maml_trainer] epoch #71 | Saving snapshot... 2025-04-02 21:08:23 | [maml_trainer] epoch #71 | Saved 2025-04-02 21:08:23 | [maml_trainer] epoch #71 | Time 27182.06 s 2025-04-02 21:08:23 | [maml_trainer] epoch #71 | EpochTime 384.17 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.6935 Average/AverageReturn -168.964 Average/Iteration 71 Average/MaxReturn -148.929 Average/MinReturn -233.732 Average/NumEpisodes 80 Average/StdReturn 15.8081 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6157 GaussianMLPPolicy/KLAfter 0.00264418 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.87955e-05 GaussianMLPPolicy/LossBefore -6.07967e-09 GaussianMLPPolicy/dLoss -1.88016e-05 Iteration 71 MetaTest/Average/AverageDiscountedReturn -170.185 MetaTest/Average/AverageReturn -170.185 MetaTest/Average/Iteration 71 MetaTest/Average/MaxReturn -146.715 MetaTest/Average/MinReturn -244.02 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.1384 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.185 MetaTest/__unnamed_task__/AverageReturn -170.185 MetaTest/__unnamed_task__/Iteration 71 MetaTest/__unnamed_task__/MaxReturn -146.715 MetaTest/__unnamed_task__/MinReturn -244.02 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.1384 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.304e+06 __unnamed_task__/AverageDiscountedReturn -71.6935 __unnamed_task__/AverageReturn -168.964 __unnamed_task__/Iteration 71 __unnamed_task__/MaxReturn -148.929 __unnamed_task__/MinReturn -233.732 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.8081 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 21:13:12 | [maml_trainer] epoch #72 | Sampling for adapation and meta-testing... 2025-04-02 21:14:24 | [maml_trainer] epoch #72 | Finished meta-testing... 2025-04-02 21:14:24 | [maml_trainer] epoch #72 | Saving snapshot... 2025-04-02 21:14:46 | [maml_trainer] epoch #72 | Saved 2025-04-02 21:14:46 | [maml_trainer] epoch #72 | Time 27564.68 s 2025-04-02 21:14:46 | [maml_trainer] epoch #72 | EpochTime 382.62 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.7486 Average/AverageReturn -166.899 Average/Iteration 72 Average/MaxReturn -144.702 Average/MinReturn -226.86 Average/NumEpisodes 80 Average/StdReturn 16.0541 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6159 GaussianMLPPolicy/KLAfter 0.00377653 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.75879e-05 GaussianMLPPolicy/LossBefore 7.62939e-09 GaussianMLPPolicy/dLoss 1.75955e-05 Iteration 72 MetaTest/Average/AverageDiscountedReturn -165.201 MetaTest/Average/AverageReturn -165.201 MetaTest/Average/Iteration 72 MetaTest/Average/MaxReturn -147.355 MetaTest/Average/MinReturn -205.456 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.0771 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.201 MetaTest/__unnamed_task__/AverageReturn -165.201 MetaTest/__unnamed_task__/Iteration 72 MetaTest/__unnamed_task__/MaxReturn -147.355 MetaTest/__unnamed_task__/MinReturn -205.456 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.0771 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.336e+06 __unnamed_task__/AverageDiscountedReturn -70.7486 __unnamed_task__/AverageReturn -166.899 __unnamed_task__/Iteration 72 __unnamed_task__/MaxReturn -144.702 __unnamed_task__/MinReturn -226.86 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.0541 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 21:19:39 | [maml_trainer] epoch #73 | Sampling for adapation and meta-testing... 2025-04-02 21:20:52 | [maml_trainer] epoch #73 | Finished meta-testing... 2025-04-02 21:20:52 | [maml_trainer] epoch #73 | Saving snapshot... 2025-04-02 21:21:14 | [maml_trainer] epoch #73 | Saved 2025-04-02 21:21:14 | [maml_trainer] epoch #73 | Time 27953.08 s 2025-04-02 21:21:14 | [maml_trainer] epoch #73 | EpochTime 388.40 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.5999 Average/AverageReturn -165.849 Average/Iteration 73 Average/MaxReturn -140.155 Average/MinReturn -236.826 Average/NumEpisodes 80 Average/StdReturn 16.3423 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6145 GaussianMLPPolicy/KLAfter 0.00348556 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.55233e-05 GaussianMLPPolicy/LossBefore 2.08616e-10 GaussianMLPPolicy/dLoss 2.55235e-05 Iteration 73 MetaTest/Average/AverageDiscountedReturn -162.502 MetaTest/Average/AverageReturn -162.502 MetaTest/Average/Iteration 73 MetaTest/Average/MaxReturn -149.091 MetaTest/Average/MinReturn -176.56 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.95084 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -162.502 MetaTest/__unnamed_task__/AverageReturn -162.502 MetaTest/__unnamed_task__/Iteration 73 MetaTest/__unnamed_task__/MaxReturn -149.091 MetaTest/__unnamed_task__/MinReturn -176.56 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.95084 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.368e+06 __unnamed_task__/AverageDiscountedReturn -70.5999 __unnamed_task__/AverageReturn -165.849 __unnamed_task__/Iteration 73 __unnamed_task__/MaxReturn -140.155 __unnamed_task__/MinReturn -236.826 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.3423 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 21:26:10 | [maml_trainer] epoch #74 | Sampling for adapation and meta-testing... 2025-04-02 21:27:23 | [maml_trainer] epoch #74 | Finished meta-testing... 2025-04-02 21:27:23 | [maml_trainer] epoch #74 | Saving snapshot... 2025-04-02 21:27:44 | [maml_trainer] epoch #74 | Saved 2025-04-02 21:27:44 | [maml_trainer] epoch #74 | Time 28342.86 s 2025-04-02 21:27:44 | [maml_trainer] epoch #74 | EpochTime 389.77 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.9906 Average/AverageReturn -167.696 Average/Iteration 74 Average/MaxReturn -134.251 Average/MinReturn -219.267 Average/NumEpisodes 80 Average/StdReturn 17.0244 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6146 GaussianMLPPolicy/KLAfter 0.00339943 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.4978e-06 GaussianMLPPolicy/LossBefore 6.21378e-09 GaussianMLPPolicy/dLoss -8.49159e-06 Iteration 74 MetaTest/Average/AverageDiscountedReturn -165.068 MetaTest/Average/AverageReturn -165.068 MetaTest/Average/Iteration 74 MetaTest/Average/MaxReturn -146.853 MetaTest/Average/MinReturn -216.516 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.327 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.068 MetaTest/__unnamed_task__/AverageReturn -165.068 MetaTest/__unnamed_task__/Iteration 74 MetaTest/__unnamed_task__/MaxReturn -146.853 MetaTest/__unnamed_task__/MinReturn -216.516 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.327 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.4e+06 __unnamed_task__/AverageDiscountedReturn -70.9906 __unnamed_task__/AverageReturn -167.696 __unnamed_task__/Iteration 74 __unnamed_task__/MaxReturn -134.251 __unnamed_task__/MinReturn -219.267 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.0244 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 21:32:34 | [maml_trainer] epoch #75 | Sampling for adapation and meta-testing... 2025-04-02 21:33:42 | [maml_trainer] epoch #75 | Finished meta-testing... 2025-04-02 21:33:42 | [maml_trainer] epoch #75 | Saving snapshot... 2025-04-02 21:34:04 | [maml_trainer] epoch #75 | Saved 2025-04-02 21:34:04 | [maml_trainer] epoch #75 | Time 28722.32 s 2025-04-02 21:34:04 | [maml_trainer] epoch #75 | EpochTime 379.46 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.8818 Average/AverageReturn -166.85 Average/Iteration 75 Average/MaxReturn -145.842 Average/MinReturn -228.329 Average/NumEpisodes 80 Average/StdReturn 15.1036 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6152 GaussianMLPPolicy/KLAfter 0.00251808 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.74248e-05 GaussianMLPPolicy/LossBefore 6.25849e-09 GaussianMLPPolicy/dLoss 4.7431e-05 Iteration 75 MetaTest/Average/AverageDiscountedReturn -165.43 MetaTest/Average/AverageReturn -165.43 MetaTest/Average/Iteration 75 MetaTest/Average/MaxReturn -146.118 MetaTest/Average/MinReturn -198.671 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.9166 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.43 MetaTest/__unnamed_task__/AverageReturn -165.43 MetaTest/__unnamed_task__/Iteration 75 MetaTest/__unnamed_task__/MaxReturn -146.118 MetaTest/__unnamed_task__/MinReturn -198.671 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.9166 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.432e+06 __unnamed_task__/AverageDiscountedReturn -70.8818 __unnamed_task__/AverageReturn -166.85 __unnamed_task__/Iteration 75 __unnamed_task__/MaxReturn -145.842 __unnamed_task__/MinReturn -228.329 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.1036 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 21:38:41 | [maml_trainer] epoch #76 | Sampling for adapation and meta-testing... 2025-04-02 21:39:50 | [maml_trainer] epoch #76 | Finished meta-testing... 2025-04-02 21:39:50 | [maml_trainer] epoch #76 | Saving snapshot... 2025-04-02 21:40:11 | [maml_trainer] epoch #76 | Saved 2025-04-02 21:40:11 | [maml_trainer] epoch #76 | Time 29089.23 s 2025-04-02 21:40:11 | [maml_trainer] epoch #76 | EpochTime 366.91 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.7167 Average/AverageReturn -168.439 Average/Iteration 76 Average/MaxReturn -144.837 Average/MinReturn -246.314 Average/NumEpisodes 80 Average/StdReturn 21.7999 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6176 GaussianMLPPolicy/KLAfter 0.00220466 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.39505e-05 GaussianMLPPolicy/LossBefore -5.91576e-09 GaussianMLPPolicy/dLoss 1.39446e-05 Iteration 76 MetaTest/Average/AverageDiscountedReturn -165.997 MetaTest/Average/AverageReturn -165.997 MetaTest/Average/Iteration 76 MetaTest/Average/MaxReturn -143.593 MetaTest/Average/MinReturn -234.385 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.6875 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.997 MetaTest/__unnamed_task__/AverageReturn -165.997 MetaTest/__unnamed_task__/Iteration 76 MetaTest/__unnamed_task__/MaxReturn -143.593 MetaTest/__unnamed_task__/MinReturn -234.385 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.6875 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.464e+06 __unnamed_task__/AverageDiscountedReturn -71.7167 __unnamed_task__/AverageReturn -168.439 __unnamed_task__/Iteration 76 __unnamed_task__/MaxReturn -144.837 __unnamed_task__/MinReturn -246.314 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.7999 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 21:44:47 | [maml_trainer] epoch #77 | Sampling for adapation and meta-testing... 2025-04-02 21:45:58 | [maml_trainer] epoch #77 | Finished meta-testing... 2025-04-02 21:45:58 | [maml_trainer] epoch #77 | Saving snapshot... 2025-04-02 21:46:19 | [maml_trainer] epoch #77 | Saved 2025-04-02 21:46:19 | [maml_trainer] epoch #77 | Time 29457.99 s 2025-04-02 21:46:19 | [maml_trainer] epoch #77 | EpochTime 368.75 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.6794 Average/AverageReturn -170.593 Average/Iteration 77 Average/MaxReturn -144.429 Average/MinReturn -246.919 Average/NumEpisodes 80 Average/StdReturn 22.3038 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6193 GaussianMLPPolicy/KLAfter 0.00258349 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.50936e-06 GaussianMLPPolicy/LossBefore -7.27177e-09 GaussianMLPPolicy/dLoss 6.50209e-06 Iteration 77 MetaTest/Average/AverageDiscountedReturn -163.157 MetaTest/Average/AverageReturn -163.157 MetaTest/Average/Iteration 77 MetaTest/Average/MaxReturn -143.953 MetaTest/Average/MinReturn -180.791 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.78368 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -163.157 MetaTest/__unnamed_task__/AverageReturn -163.157 MetaTest/__unnamed_task__/Iteration 77 MetaTest/__unnamed_task__/MaxReturn -143.953 MetaTest/__unnamed_task__/MinReturn -180.791 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.78368 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.496e+06 __unnamed_task__/AverageDiscountedReturn -72.6794 __unnamed_task__/AverageReturn -170.593 __unnamed_task__/Iteration 77 __unnamed_task__/MaxReturn -144.429 __unnamed_task__/MinReturn -246.919 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.3038 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 21:50:59 | [maml_trainer] epoch #78 | Sampling for adapation and meta-testing... 2025-04-02 21:52:08 | [maml_trainer] epoch #78 | Finished meta-testing... 2025-04-02 21:52:08 | [maml_trainer] epoch #78 | Saving snapshot... 2025-04-02 21:52:28 | [maml_trainer] epoch #78 | Saved 2025-04-02 21:52:28 | [maml_trainer] epoch #78 | Time 29826.50 s 2025-04-02 21:52:28 | [maml_trainer] epoch #78 | EpochTime 368.51 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.1443 Average/AverageReturn -164.582 Average/Iteration 78 Average/MaxReturn -142.075 Average/MinReturn -220.748 Average/NumEpisodes 80 Average/StdReturn 14.9133 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6224 GaussianMLPPolicy/KLAfter 0.00259562 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.15413e-05 GaussianMLPPolicy/LossBefore -5.93066e-09 GaussianMLPPolicy/dLoss -4.15472e-05 Iteration 78 MetaTest/Average/AverageDiscountedReturn -171.035 MetaTest/Average/AverageReturn -171.035 MetaTest/Average/Iteration 78 MetaTest/Average/MaxReturn -147.326 MetaTest/Average/MinReturn -249.624 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.5377 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.035 MetaTest/__unnamed_task__/AverageReturn -171.035 MetaTest/__unnamed_task__/Iteration 78 MetaTest/__unnamed_task__/MaxReturn -147.326 MetaTest/__unnamed_task__/MinReturn -249.624 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.5377 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.528e+06 __unnamed_task__/AverageDiscountedReturn -70.1443 __unnamed_task__/AverageReturn -164.582 __unnamed_task__/Iteration 78 __unnamed_task__/MaxReturn -142.075 __unnamed_task__/MinReturn -220.748 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.9133 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 21:57:05 | [maml_trainer] epoch #79 | Sampling for adapation and meta-testing... 2025-04-02 21:58:14 | [maml_trainer] epoch #79 | Finished meta-testing... 2025-04-02 21:58:14 | [maml_trainer] epoch #79 | Saving snapshot... 2025-04-02 21:58:35 | [maml_trainer] epoch #79 | Saved 2025-04-02 21:58:35 | [maml_trainer] epoch #79 | Time 30193.91 s 2025-04-02 21:58:35 | [maml_trainer] epoch #79 | EpochTime 367.40 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -69.3274 Average/AverageReturn -161.816 Average/Iteration 79 Average/MaxReturn -142.706 Average/MinReturn -211.506 Average/NumEpisodes 80 Average/StdReturn 14.0808 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.625 GaussianMLPPolicy/KLAfter 0.00226528 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.50397e-06 GaussianMLPPolicy/LossBefore 4.38094e-09 GaussianMLPPolicy/dLoss -8.49959e-06 Iteration 79 MetaTest/Average/AverageDiscountedReturn -169.262 MetaTest/Average/AverageReturn -169.262 MetaTest/Average/Iteration 79 MetaTest/Average/MaxReturn -145.16 MetaTest/Average/MinReturn -242.765 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.2661 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.262 MetaTest/__unnamed_task__/AverageReturn -169.262 MetaTest/__unnamed_task__/Iteration 79 MetaTest/__unnamed_task__/MaxReturn -145.16 MetaTest/__unnamed_task__/MinReturn -242.765 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.2661 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.56e+06 __unnamed_task__/AverageDiscountedReturn -69.3274 __unnamed_task__/AverageReturn -161.816 __unnamed_task__/Iteration 79 __unnamed_task__/MaxReturn -142.706 __unnamed_task__/MinReturn -211.506 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.0808 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 22:03:14 | [maml_trainer] epoch #80 | Sampling for adapation and meta-testing... 2025-04-02 22:04:30 | [maml_trainer] epoch #80 | Finished meta-testing... 2025-04-02 22:04:30 | [maml_trainer] epoch #80 | Saving snapshot... 2025-04-02 22:04:59 | [maml_trainer] epoch #80 | Saved 2025-04-02 22:04:59 | [maml_trainer] epoch #80 | Time 30577.49 s 2025-04-02 22:04:59 | [maml_trainer] epoch #80 | EpochTime 383.58 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -69.8768 Average/AverageReturn -162.749 Average/Iteration 80 Average/MaxReturn -140.651 Average/MinReturn -240.716 Average/NumEpisodes 80 Average/StdReturn 21.5795 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6288 GaussianMLPPolicy/KLAfter 0.00196833 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.26365e-06 GaussianMLPPolicy/LossBefore 5.36442e-10 GaussianMLPPolicy/dLoss 7.26418e-06 Iteration 80 MetaTest/Average/AverageDiscountedReturn -168.515 MetaTest/Average/AverageReturn -168.515 MetaTest/Average/Iteration 80 MetaTest/Average/MaxReturn -143.472 MetaTest/Average/MinReturn -224.495 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.996 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.515 MetaTest/__unnamed_task__/AverageReturn -168.515 MetaTest/__unnamed_task__/Iteration 80 MetaTest/__unnamed_task__/MaxReturn -143.472 MetaTest/__unnamed_task__/MinReturn -224.495 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.996 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.592e+06 __unnamed_task__/AverageDiscountedReturn -69.8768 __unnamed_task__/AverageReturn -162.749 __unnamed_task__/Iteration 80 __unnamed_task__/MaxReturn -140.651 __unnamed_task__/MinReturn -240.716 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.5795 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 22:09:57 | [maml_trainer] epoch #81 | Sampling for adapation and meta-testing... 2025-04-02 22:11:07 | [maml_trainer] epoch #81 | Finished meta-testing... 2025-04-02 22:11:07 | [maml_trainer] epoch #81 | Saving snapshot... 2025-04-02 22:11:28 | [maml_trainer] epoch #81 | Saved 2025-04-02 22:11:28 | [maml_trainer] epoch #81 | Time 30966.35 s 2025-04-02 22:11:28 | [maml_trainer] epoch #81 | EpochTime 388.85 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.0523 Average/AverageReturn -163.124 Average/Iteration 81 Average/MaxReturn -143.174 Average/MinReturn -240.485 Average/NumEpisodes 80 Average/StdReturn 19.1272 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6301 GaussianMLPPolicy/KLAfter 0.00211687 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.74903e-05 GaussianMLPPolicy/LossBefore 5.126e-09 GaussianMLPPolicy/dLoss -3.74851e-05 Iteration 81 MetaTest/Average/AverageDiscountedReturn -177.74 MetaTest/Average/AverageReturn -177.74 MetaTest/Average/Iteration 81 MetaTest/Average/MaxReturn -142.601 MetaTest/Average/MinReturn -254.415 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 32.8162 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.74 MetaTest/__unnamed_task__/AverageReturn -177.74 MetaTest/__unnamed_task__/Iteration 81 MetaTest/__unnamed_task__/MaxReturn -142.601 MetaTest/__unnamed_task__/MinReturn -254.415 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 32.8162 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.624e+06 __unnamed_task__/AverageDiscountedReturn -70.0523 __unnamed_task__/AverageReturn -163.124 __unnamed_task__/Iteration 81 __unnamed_task__/MaxReturn -143.174 __unnamed_task__/MinReturn -240.485 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.1272 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 22:16:11 | [maml_trainer] epoch #82 | Sampling for adapation and meta-testing... 2025-04-02 22:17:20 | [maml_trainer] epoch #82 | Finished meta-testing... 2025-04-02 22:17:20 | [maml_trainer] epoch #82 | Saving snapshot... 2025-04-02 22:17:40 | [maml_trainer] epoch #82 | Saved 2025-04-02 22:17:40 | [maml_trainer] epoch #82 | Time 31338.22 s 2025-04-02 22:17:40 | [maml_trainer] epoch #82 | EpochTime 371.86 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.0088 Average/AverageReturn -163.606 Average/Iteration 82 Average/MaxReturn -139.113 Average/MinReturn -235.116 Average/NumEpisodes 80 Average/StdReturn 19.6023 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6336 GaussianMLPPolicy/KLAfter 0.00193306 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.87451e-05 GaussianMLPPolicy/LossBefore 5.37932e-09 GaussianMLPPolicy/dLoss 1.87505e-05 Iteration 82 MetaTest/Average/AverageDiscountedReturn -166.592 MetaTest/Average/AverageReturn -166.592 MetaTest/Average/Iteration 82 MetaTest/Average/MaxReturn -144.187 MetaTest/Average/MinReturn -228.431 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.3356 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.592 MetaTest/__unnamed_task__/AverageReturn -166.592 MetaTest/__unnamed_task__/Iteration 82 MetaTest/__unnamed_task__/MaxReturn -144.187 MetaTest/__unnamed_task__/MinReturn -228.431 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.3356 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.656e+06 __unnamed_task__/AverageDiscountedReturn -70.0088 __unnamed_task__/AverageReturn -163.606 __unnamed_task__/Iteration 82 __unnamed_task__/MaxReturn -139.113 __unnamed_task__/MinReturn -235.116 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.6023 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 22:22:15 | [maml_trainer] epoch #83 | Sampling for adapation and meta-testing... 2025-04-02 22:23:27 | [maml_trainer] epoch #83 | Finished meta-testing... 2025-04-02 22:23:27 | [maml_trainer] epoch #83 | Saving snapshot... 2025-04-02 22:23:49 | [maml_trainer] epoch #83 | Saved 2025-04-02 22:23:49 | [maml_trainer] epoch #83 | Time 31707.14 s 2025-04-02 22:23:49 | [maml_trainer] epoch #83 | EpochTime 368.93 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.2339 Average/AverageReturn -166.283 Average/Iteration 83 Average/MaxReturn -140.72 Average/MinReturn -239.5 Average/NumEpisodes 80 Average/StdReturn 22.45 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6371 GaussianMLPPolicy/KLAfter 0.00295173 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.18924e-05 GaussianMLPPolicy/LossBefore -3.65078e-09 GaussianMLPPolicy/dLoss 3.18888e-05 Iteration 83 MetaTest/Average/AverageDiscountedReturn -166.162 MetaTest/Average/AverageReturn -166.162 MetaTest/Average/Iteration 83 MetaTest/Average/MaxReturn -144.772 MetaTest/Average/MinReturn -203.019 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.5497 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.162 MetaTest/__unnamed_task__/AverageReturn -166.162 MetaTest/__unnamed_task__/Iteration 83 MetaTest/__unnamed_task__/MaxReturn -144.772 MetaTest/__unnamed_task__/MinReturn -203.019 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.5497 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.688e+06 __unnamed_task__/AverageDiscountedReturn -71.2339 __unnamed_task__/AverageReturn -166.283 __unnamed_task__/Iteration 83 __unnamed_task__/MaxReturn -140.72 __unnamed_task__/MinReturn -239.5 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.45 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 22:28:34 | [maml_trainer] epoch #84 | Sampling for adapation and meta-testing... 2025-04-02 22:29:46 | [maml_trainer] epoch #84 | Finished meta-testing... 2025-04-02 22:29:46 | [maml_trainer] epoch #84 | Saving snapshot... 2025-04-02 22:30:09 | [maml_trainer] epoch #84 | Saved 2025-04-02 22:30:09 | [maml_trainer] epoch #84 | Time 32087.30 s 2025-04-02 22:30:09 | [maml_trainer] epoch #84 | EpochTime 380.15 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.3814 Average/AverageReturn -166.28 Average/Iteration 84 Average/MaxReturn -143.965 Average/MinReturn -279.576 Average/NumEpisodes 80 Average/StdReturn 22.5781 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6398 GaussianMLPPolicy/KLAfter 0.00265747 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.67415e-05 GaussianMLPPolicy/LossBefore 5.27501e-09 GaussianMLPPolicy/dLoss -1.67363e-05 Iteration 84 MetaTest/Average/AverageDiscountedReturn -162.877 MetaTest/Average/AverageReturn -162.877 MetaTest/Average/Iteration 84 MetaTest/Average/MaxReturn -145.009 MetaTest/Average/MinReturn -196.638 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.5678 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -162.877 MetaTest/__unnamed_task__/AverageReturn -162.877 MetaTest/__unnamed_task__/Iteration 84 MetaTest/__unnamed_task__/MaxReturn -145.009 MetaTest/__unnamed_task__/MinReturn -196.638 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.5678 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.72e+06 __unnamed_task__/AverageDiscountedReturn -71.3814 __unnamed_task__/AverageReturn -166.28 __unnamed_task__/Iteration 84 __unnamed_task__/MaxReturn -143.965 __unnamed_task__/MinReturn -279.576 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.5781 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 22:34:58 | [maml_trainer] epoch #85 | Sampling for adapation and meta-testing... 2025-04-02 22:36:06 | [maml_trainer] epoch #85 | Finished meta-testing... 2025-04-02 22:36:06 | [maml_trainer] epoch #85 | Saving snapshot... 2025-04-02 22:36:28 | [maml_trainer] epoch #85 | Saved 2025-04-02 22:36:28 | [maml_trainer] epoch #85 | Time 32466.44 s 2025-04-02 22:36:28 | [maml_trainer] epoch #85 | EpochTime 379.14 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.1993 Average/AverageReturn -166.007 Average/Iteration 85 Average/MaxReturn -139.307 Average/MinReturn -242.726 Average/NumEpisodes 80 Average/StdReturn 20.8673 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6413 GaussianMLPPolicy/KLAfter 0.00236659 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.45965e-06 GaussianMLPPolicy/LossBefore 1.63913e-10 GaussianMLPPolicy/dLoss 2.45981e-06 Iteration 85 MetaTest/Average/AverageDiscountedReturn -165.64 MetaTest/Average/AverageReturn -165.64 MetaTest/Average/Iteration 85 MetaTest/Average/MaxReturn -139.677 MetaTest/Average/MinReturn -230.099 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 27.8261 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.64 MetaTest/__unnamed_task__/AverageReturn -165.64 MetaTest/__unnamed_task__/Iteration 85 MetaTest/__unnamed_task__/MaxReturn -139.677 MetaTest/__unnamed_task__/MinReturn -230.099 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 27.8261 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.752e+06 __unnamed_task__/AverageDiscountedReturn -71.1993 __unnamed_task__/AverageReturn -166.007 __unnamed_task__/Iteration 85 __unnamed_task__/MaxReturn -139.307 __unnamed_task__/MinReturn -242.726 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.8673 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 22:41:05 | [maml_trainer] epoch #86 | Sampling for adapation and meta-testing... 2025-04-02 22:42:13 | [maml_trainer] epoch #86 | Finished meta-testing... 2025-04-02 22:42:13 | [maml_trainer] epoch #86 | Saving snapshot... 2025-04-02 22:42:35 | [maml_trainer] epoch #86 | Saved 2025-04-02 22:42:35 | [maml_trainer] epoch #86 | Time 32833.27 s 2025-04-02 22:42:35 | [maml_trainer] epoch #86 | EpochTime 366.83 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -69.7929 Average/AverageReturn -162.942 Average/Iteration 86 Average/MaxReturn -139.768 Average/MinReturn -247.189 Average/NumEpisodes 80 Average/StdReturn 18.5588 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6437 GaussianMLPPolicy/KLAfter 0.00270349 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.53639e-06 GaussianMLPPolicy/LossBefore 1.00136e-08 GaussianMLPPolicy/dLoss -4.52638e-06 Iteration 86 MetaTest/Average/AverageDiscountedReturn -168.276 MetaTest/Average/AverageReturn -168.276 MetaTest/Average/Iteration 86 MetaTest/Average/MaxReturn -142.564 MetaTest/Average/MinReturn -221.133 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.5675 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.276 MetaTest/__unnamed_task__/AverageReturn -168.276 MetaTest/__unnamed_task__/Iteration 86 MetaTest/__unnamed_task__/MaxReturn -142.564 MetaTest/__unnamed_task__/MinReturn -221.133 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.5675 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.784e+06 __unnamed_task__/AverageDiscountedReturn -69.7929 __unnamed_task__/AverageReturn -162.942 __unnamed_task__/Iteration 86 __unnamed_task__/MaxReturn -139.768 __unnamed_task__/MinReturn -247.189 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.5588 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 22:47:14 | [maml_trainer] epoch #87 | Sampling for adapation and meta-testing... 2025-04-02 22:48:27 | [maml_trainer] epoch #87 | Finished meta-testing... 2025-04-02 22:48:27 | [maml_trainer] epoch #87 | Saving snapshot... 2025-04-02 22:48:48 | [maml_trainer] epoch #87 | Saved 2025-04-02 22:48:48 | [maml_trainer] epoch #87 | Time 33206.85 s 2025-04-02 22:48:48 | [maml_trainer] epoch #87 | EpochTime 373.58 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.2323 Average/AverageReturn -166.206 Average/Iteration 87 Average/MaxReturn -138.045 Average/MinReturn -236.035 Average/NumEpisodes 80 Average/StdReturn 21.3971 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6459 GaussianMLPPolicy/KLAfter 0.00242449 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.98939e-05 GaussianMLPPolicy/LossBefore -1.2517e-09 GaussianMLPPolicy/dLoss -1.98951e-05 Iteration 87 MetaTest/Average/AverageDiscountedReturn -175.557 MetaTest/Average/AverageReturn -175.557 MetaTest/Average/Iteration 87 MetaTest/Average/MaxReturn -146.772 MetaTest/Average/MinReturn -258.211 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 28.9693 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.557 MetaTest/__unnamed_task__/AverageReturn -175.557 MetaTest/__unnamed_task__/Iteration 87 MetaTest/__unnamed_task__/MaxReturn -146.772 MetaTest/__unnamed_task__/MinReturn -258.211 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 28.9693 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.816e+06 __unnamed_task__/AverageDiscountedReturn -71.2323 __unnamed_task__/AverageReturn -166.206 __unnamed_task__/Iteration 87 __unnamed_task__/MaxReturn -138.045 __unnamed_task__/MinReturn -236.035 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.3971 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 22:53:31 | [maml_trainer] epoch #88 | Sampling for adapation and meta-testing... 2025-04-02 22:54:40 | [maml_trainer] epoch #88 | Finished meta-testing... 2025-04-02 22:54:40 | [maml_trainer] epoch #88 | Saving snapshot... 2025-04-02 22:55:02 | [maml_trainer] epoch #88 | Saved 2025-04-02 22:55:02 | [maml_trainer] epoch #88 | Time 33580.42 s 2025-04-02 22:55:02 | [maml_trainer] epoch #88 | EpochTime 373.56 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.8038 Average/AverageReturn -166.057 Average/Iteration 88 Average/MaxReturn -144.85 Average/MinReturn -222.661 Average/NumEpisodes 80 Average/StdReturn 17.7739 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6476 GaussianMLPPolicy/KLAfter 0.00267529 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.3777e-07 GaussianMLPPolicy/LossBefore -1.86265e-09 GaussianMLPPolicy/dLoss -6.39632e-07 Iteration 88 MetaTest/Average/AverageDiscountedReturn -177.847 MetaTest/Average/AverageReturn -177.847 MetaTest/Average/Iteration 88 MetaTest/Average/MaxReturn -145.34 MetaTest/Average/MinReturn -245.373 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 27.5545 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.847 MetaTest/__unnamed_task__/AverageReturn -177.847 MetaTest/__unnamed_task__/Iteration 88 MetaTest/__unnamed_task__/MaxReturn -145.34 MetaTest/__unnamed_task__/MinReturn -245.373 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 27.5545 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.848e+06 __unnamed_task__/AverageDiscountedReturn -70.8038 __unnamed_task__/AverageReturn -166.057 __unnamed_task__/Iteration 88 __unnamed_task__/MaxReturn -144.85 __unnamed_task__/MinReturn -222.661 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.7739 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 22:59:43 | [maml_trainer] epoch #89 | Sampling for adapation and meta-testing... 2025-04-02 23:00:51 | [maml_trainer] epoch #89 | Finished meta-testing... 2025-04-02 23:00:51 | [maml_trainer] epoch #89 | Saving snapshot... 2025-04-02 23:01:12 | [maml_trainer] epoch #89 | Saved 2025-04-02 23:01:12 | [maml_trainer] epoch #89 | Time 33950.20 s 2025-04-02 23:01:12 | [maml_trainer] epoch #89 | EpochTime 369.78 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.12 Average/AverageReturn -167.496 Average/Iteration 89 Average/MaxReturn -142.518 Average/MinReturn -247.124 Average/NumEpisodes 80 Average/StdReturn 20.0232 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6501 GaussianMLPPolicy/KLAfter 0.00267123 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.0926e-05 GaussianMLPPolicy/LossBefore 1.65403e-09 GaussianMLPPolicy/dLoss -2.09243e-05 Iteration 89 MetaTest/Average/AverageDiscountedReturn -168.233 MetaTest/Average/AverageReturn -168.233 MetaTest/Average/Iteration 89 MetaTest/Average/MaxReturn -144.818 MetaTest/Average/MinReturn -218.344 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.8049 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.233 MetaTest/__unnamed_task__/AverageReturn -168.233 MetaTest/__unnamed_task__/Iteration 89 MetaTest/__unnamed_task__/MaxReturn -144.818 MetaTest/__unnamed_task__/MinReturn -218.344 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.8049 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.88e+06 __unnamed_task__/AverageDiscountedReturn -71.12 __unnamed_task__/AverageReturn -167.496 __unnamed_task__/Iteration 89 __unnamed_task__/MaxReturn -142.518 __unnamed_task__/MinReturn -247.124 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.0232 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 23:05:53 | [maml_trainer] epoch #90 | Sampling for adapation and meta-testing... 2025-04-02 23:07:03 | [maml_trainer] epoch #90 | Finished meta-testing... 2025-04-02 23:07:03 | [maml_trainer] epoch #90 | Saving snapshot... 2025-04-02 23:07:24 | [maml_trainer] epoch #90 | Saved 2025-04-02 23:07:24 | [maml_trainer] epoch #90 | Time 34322.49 s 2025-04-02 23:07:24 | [maml_trainer] epoch #90 | EpochTime 372.29 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.5498 Average/AverageReturn -165.72 Average/Iteration 90 Average/MaxReturn -141.372 Average/MinReturn -236.522 Average/NumEpisodes 80 Average/StdReturn 19.3145 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6498 GaussianMLPPolicy/KLAfter 0.00210965 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.69524e-05 GaussianMLPPolicy/LossBefore 4.29153e-09 GaussianMLPPolicy/dLoss 3.69567e-05 Iteration 90 MetaTest/Average/AverageDiscountedReturn -167.964 MetaTest/Average/AverageReturn -167.964 MetaTest/Average/Iteration 90 MetaTest/Average/MaxReturn -147.731 MetaTest/Average/MinReturn -222.876 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.0496 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.964 MetaTest/__unnamed_task__/AverageReturn -167.964 MetaTest/__unnamed_task__/Iteration 90 MetaTest/__unnamed_task__/MaxReturn -147.731 MetaTest/__unnamed_task__/MinReturn -222.876 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.0496 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.912e+06 __unnamed_task__/AverageDiscountedReturn -70.5498 __unnamed_task__/AverageReturn -165.72 __unnamed_task__/Iteration 90 __unnamed_task__/MaxReturn -141.372 __unnamed_task__/MinReturn -236.522 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.3145 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 23:12:11 | [maml_trainer] epoch #91 | Sampling for adapation and meta-testing... 2025-04-02 23:13:21 | [maml_trainer] epoch #91 | Finished meta-testing... 2025-04-02 23:13:21 | [maml_trainer] epoch #91 | Saving snapshot... 2025-04-02 23:13:42 | [maml_trainer] epoch #91 | Saved 2025-04-02 23:13:42 | [maml_trainer] epoch #91 | Time 34700.91 s 2025-04-02 23:13:42 | [maml_trainer] epoch #91 | EpochTime 378.42 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.8874 Average/AverageReturn -168.595 Average/Iteration 91 Average/MaxReturn -141.954 Average/MinReturn -243.937 Average/NumEpisodes 80 Average/StdReturn 23.137 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6498 GaussianMLPPolicy/KLAfter 0.00203597 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.29727e-05 GaussianMLPPolicy/LossBefore -6.52671e-09 GaussianMLPPolicy/dLoss -4.29792e-05 Iteration 91 MetaTest/Average/AverageDiscountedReturn -170.371 MetaTest/Average/AverageReturn -170.371 MetaTest/Average/Iteration 91 MetaTest/Average/MaxReturn -145.335 MetaTest/Average/MinReturn -226.965 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.2126 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.371 MetaTest/__unnamed_task__/AverageReturn -170.371 MetaTest/__unnamed_task__/Iteration 91 MetaTest/__unnamed_task__/MaxReturn -145.335 MetaTest/__unnamed_task__/MinReturn -226.965 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.2126 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.944e+06 __unnamed_task__/AverageDiscountedReturn -71.8874 __unnamed_task__/AverageReturn -168.595 __unnamed_task__/Iteration 91 __unnamed_task__/MaxReturn -141.954 __unnamed_task__/MinReturn -243.937 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.137 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 23:18:28 | [maml_trainer] epoch #92 | Sampling for adapation and meta-testing... 2025-04-02 23:19:37 | [maml_trainer] epoch #92 | Finished meta-testing... 2025-04-02 23:19:37 | [maml_trainer] epoch #92 | Saving snapshot... 2025-04-02 23:19:58 | [maml_trainer] epoch #92 | Saved 2025-04-02 23:19:58 | [maml_trainer] epoch #92 | Time 35076.97 s 2025-04-02 23:19:58 | [maml_trainer] epoch #92 | EpochTime 376.05 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.1116 Average/AverageReturn -167.274 Average/Iteration 92 Average/MaxReturn -137.116 Average/MinReturn -244.417 Average/NumEpisodes 80 Average/StdReturn 21.4729 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6496 GaussianMLPPolicy/KLAfter 0.00234504 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.51831e-06 GaussianMLPPolicy/LossBefore -8.49366e-10 GaussianMLPPolicy/dLoss 3.51746e-06 Iteration 92 MetaTest/Average/AverageDiscountedReturn -162.43 MetaTest/Average/AverageReturn -162.43 MetaTest/Average/Iteration 92 MetaTest/Average/MaxReturn -147.8 MetaTest/Average/MinReturn -192.621 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.4866 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -162.43 MetaTest/__unnamed_task__/AverageReturn -162.43 MetaTest/__unnamed_task__/Iteration 92 MetaTest/__unnamed_task__/MaxReturn -147.8 MetaTest/__unnamed_task__/MinReturn -192.621 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.4866 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.976e+06 __unnamed_task__/AverageDiscountedReturn -71.1116 __unnamed_task__/AverageReturn -167.274 __unnamed_task__/Iteration 92 __unnamed_task__/MaxReturn -137.116 __unnamed_task__/MinReturn -244.417 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.4729 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 23:24:42 | [maml_trainer] epoch #93 | Sampling for adapation and meta-testing... 2025-04-02 23:25:54 | [maml_trainer] epoch #93 | Finished meta-testing... 2025-04-02 23:25:54 | [maml_trainer] epoch #93 | Saving snapshot... 2025-04-02 23:26:16 | [maml_trainer] epoch #93 | Saved 2025-04-02 23:26:16 | [maml_trainer] epoch #93 | Time 35455.05 s 2025-04-02 23:26:16 | [maml_trainer] epoch #93 | EpochTime 378.08 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.4897 Average/AverageReturn -168.285 Average/Iteration 93 Average/MaxReturn -140.813 Average/MinReturn -236.068 Average/NumEpisodes 80 Average/StdReturn 19.0464 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6499 GaussianMLPPolicy/KLAfter 0.00257908 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.91857e-06 GaussianMLPPolicy/LossBefore -5.39422e-09 GaussianMLPPolicy/dLoss 2.91318e-06 Iteration 93 MetaTest/Average/AverageDiscountedReturn -173.905 MetaTest/Average/AverageReturn -173.905 MetaTest/Average/Iteration 93 MetaTest/Average/MaxReturn -145.114 MetaTest/Average/MinReturn -250.287 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 29.3861 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.905 MetaTest/__unnamed_task__/AverageReturn -173.905 MetaTest/__unnamed_task__/Iteration 93 MetaTest/__unnamed_task__/MaxReturn -145.114 MetaTest/__unnamed_task__/MinReturn -250.287 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 29.3861 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.008e+06 __unnamed_task__/AverageDiscountedReturn -71.4897 __unnamed_task__/AverageReturn -168.285 __unnamed_task__/Iteration 93 __unnamed_task__/MaxReturn -140.813 __unnamed_task__/MinReturn -236.068 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.0464 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 23:31:10 | [maml_trainer] epoch #94 | Sampling for adapation and meta-testing... 2025-04-02 23:32:22 | [maml_trainer] epoch #94 | Finished meta-testing... 2025-04-02 23:32:22 | [maml_trainer] epoch #94 | Saving snapshot... 2025-04-02 23:32:44 | [maml_trainer] epoch #94 | Saved 2025-04-02 23:32:44 | [maml_trainer] epoch #94 | Time 35842.85 s 2025-04-02 23:32:44 | [maml_trainer] epoch #94 | EpochTime 387.80 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.185 Average/AverageReturn -170.501 Average/Iteration 94 Average/MaxReturn -141.111 Average/MinReturn -234.767 Average/NumEpisodes 80 Average/StdReturn 19.4725 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6506 GaussianMLPPolicy/KLAfter 0.00244182 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.19153e-05 GaussianMLPPolicy/LossBefore 3.57628e-10 GaussianMLPPolicy/dLoss 3.19156e-05 Iteration 94 MetaTest/Average/AverageDiscountedReturn -162.82 MetaTest/Average/AverageReturn -162.82 MetaTest/Average/Iteration 94 MetaTest/Average/MaxReturn -146.113 MetaTest/Average/MinReturn -193.06 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.3619 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -162.82 MetaTest/__unnamed_task__/AverageReturn -162.82 MetaTest/__unnamed_task__/Iteration 94 MetaTest/__unnamed_task__/MaxReturn -146.113 MetaTest/__unnamed_task__/MinReturn -193.06 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.3619 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.04e+06 __unnamed_task__/AverageDiscountedReturn -72.185 __unnamed_task__/AverageReturn -170.501 __unnamed_task__/Iteration 94 __unnamed_task__/MaxReturn -141.111 __unnamed_task__/MinReturn -234.767 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.4725 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 23:37:31 | [maml_trainer] epoch #95 | Sampling for adapation and meta-testing... 2025-04-02 23:38:41 | [maml_trainer] epoch #95 | Finished meta-testing... 2025-04-02 23:38:41 | [maml_trainer] epoch #95 | Saving snapshot... 2025-04-02 23:39:00 | [maml_trainer] epoch #95 | Saved 2025-04-02 23:39:00 | [maml_trainer] epoch #95 | Time 36219.09 s 2025-04-02 23:39:00 | [maml_trainer] epoch #95 | EpochTime 376.23 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.8697 Average/AverageReturn -169.753 Average/Iteration 95 Average/MaxReturn -145.457 Average/MinReturn -248.318 Average/NumEpisodes 80 Average/StdReturn 21.9509 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6513 GaussianMLPPolicy/KLAfter 0.00265194 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.11988e-05 GaussianMLPPolicy/LossBefore -1.19209e-09 GaussianMLPPolicy/dLoss -5.12e-05 Iteration 95 MetaTest/Average/AverageDiscountedReturn -168.115 MetaTest/Average/AverageReturn -168.115 MetaTest/Average/Iteration 95 MetaTest/Average/MaxReturn -141.446 MetaTest/Average/MinReturn -244.341 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.1494 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.115 MetaTest/__unnamed_task__/AverageReturn -168.115 MetaTest/__unnamed_task__/Iteration 95 MetaTest/__unnamed_task__/MaxReturn -141.446 MetaTest/__unnamed_task__/MinReturn -244.341 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.1494 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.072e+06 __unnamed_task__/AverageDiscountedReturn -71.8697 __unnamed_task__/AverageReturn -169.753 __unnamed_task__/Iteration 95 __unnamed_task__/MaxReturn -145.457 __unnamed_task__/MinReturn -248.318 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.9509 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 23:43:36 | [maml_trainer] epoch #96 | Sampling for adapation and meta-testing... 2025-04-02 23:44:46 | [maml_trainer] epoch #96 | Finished meta-testing... 2025-04-02 23:44:46 | [maml_trainer] epoch #96 | Saving snapshot... 2025-04-02 23:45:07 | [maml_trainer] epoch #96 | Saved 2025-04-02 23:45:07 | [maml_trainer] epoch #96 | Time 36585.97 s 2025-04-02 23:45:07 | [maml_trainer] epoch #96 | EpochTime 366.88 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.0881 Average/AverageReturn -167.594 Average/Iteration 96 Average/MaxReturn -145.163 Average/MinReturn -226.649 Average/NumEpisodes 80 Average/StdReturn 16.8416 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6507 GaussianMLPPolicy/KLAfter 0.00309159 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.31993e-06 GaussianMLPPolicy/LossBefore -9.20892e-09 GaussianMLPPolicy/dLoss 8.31072e-06 Iteration 96 MetaTest/Average/AverageDiscountedReturn -172.455 MetaTest/Average/AverageReturn -172.455 MetaTest/Average/Iteration 96 MetaTest/Average/MaxReturn -145.938 MetaTest/Average/MinReturn -230.585 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.4821 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.455 MetaTest/__unnamed_task__/AverageReturn -172.455 MetaTest/__unnamed_task__/Iteration 96 MetaTest/__unnamed_task__/MaxReturn -145.938 MetaTest/__unnamed_task__/MinReturn -230.585 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.4821 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.104e+06 __unnamed_task__/AverageDiscountedReturn -71.0881 __unnamed_task__/AverageReturn -167.594 __unnamed_task__/Iteration 96 __unnamed_task__/MaxReturn -145.163 __unnamed_task__/MinReturn -226.649 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.8416 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 23:49:53 | [maml_trainer] epoch #97 | Sampling for adapation and meta-testing... 2025-04-02 23:51:06 | [maml_trainer] epoch #97 | Finished meta-testing... 2025-04-02 23:51:06 | [maml_trainer] epoch #97 | Saving snapshot... 2025-04-02 23:51:33 | [maml_trainer] epoch #97 | Saved 2025-04-02 23:51:33 | [maml_trainer] epoch #97 | Time 36971.83 s 2025-04-02 23:51:33 | [maml_trainer] epoch #97 | EpochTime 385.85 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.2009 Average/AverageReturn -169.973 Average/Iteration 97 Average/MaxReturn -147.524 Average/MinReturn -277.524 Average/NumEpisodes 80 Average/StdReturn 20.2395 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6509 GaussianMLPPolicy/KLAfter 0.00244373 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.06619e-05 GaussianMLPPolicy/LossBefore 4.54485e-09 GaussianMLPPolicy/dLoss -1.06574e-05 Iteration 97 MetaTest/Average/AverageDiscountedReturn -169.523 MetaTest/Average/AverageReturn -169.523 MetaTest/Average/Iteration 97 MetaTest/Average/MaxReturn -147.421 MetaTest/Average/MinReturn -234.126 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.95 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.523 MetaTest/__unnamed_task__/AverageReturn -169.523 MetaTest/__unnamed_task__/Iteration 97 MetaTest/__unnamed_task__/MaxReturn -147.421 MetaTest/__unnamed_task__/MinReturn -234.126 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.95 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.136e+06 __unnamed_task__/AverageDiscountedReturn -72.2009 __unnamed_task__/AverageReturn -169.973 __unnamed_task__/Iteration 97 __unnamed_task__/MaxReturn -147.524 __unnamed_task__/MinReturn -277.524 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.2395 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-02 23:56:29 | [maml_trainer] epoch #98 | Sampling for adapation and meta-testing... 2025-04-02 23:57:42 | [maml_trainer] epoch #98 | Finished meta-testing... 2025-04-02 23:57:42 | [maml_trainer] epoch #98 | Saving snapshot... 2025-04-02 23:58:05 | [maml_trainer] epoch #98 | Saved 2025-04-02 23:58:05 | [maml_trainer] epoch #98 | Time 37363.20 s 2025-04-02 23:58:05 | [maml_trainer] epoch #98 | EpochTime 391.36 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.2687 Average/AverageReturn -168.236 Average/Iteration 98 Average/MaxReturn -142.109 Average/MinReturn -234.093 Average/NumEpisodes 80 Average/StdReturn 17.9657 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6508 GaussianMLPPolicy/KLAfter 0.00248001 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.57345e-05 GaussianMLPPolicy/LossBefore 1.71363e-09 GaussianMLPPolicy/dLoss 1.57362e-05 Iteration 98 MetaTest/Average/AverageDiscountedReturn -171.098 MetaTest/Average/AverageReturn -171.098 MetaTest/Average/Iteration 98 MetaTest/Average/MaxReturn -142.015 MetaTest/Average/MinReturn -231.19 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.4192 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.098 MetaTest/__unnamed_task__/AverageReturn -171.098 MetaTest/__unnamed_task__/Iteration 98 MetaTest/__unnamed_task__/MaxReturn -142.015 MetaTest/__unnamed_task__/MinReturn -231.19 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.4192 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.168e+06 __unnamed_task__/AverageDiscountedReturn -71.2687 __unnamed_task__/AverageReturn -168.236 __unnamed_task__/Iteration 98 __unnamed_task__/MaxReturn -142.109 __unnamed_task__/MinReturn -234.093 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.9657 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 00:02:55 | [maml_trainer] epoch #99 | Sampling for adapation and meta-testing... 2025-04-03 00:04:09 | [maml_trainer] epoch #99 | Finished meta-testing... 2025-04-03 00:04:09 | [maml_trainer] epoch #99 | Saving snapshot... 2025-04-03 00:04:31 | [maml_trainer] epoch #99 | Saved 2025-04-03 00:04:31 | [maml_trainer] epoch #99 | Time 37749.67 s 2025-04-03 00:04:31 | [maml_trainer] epoch #99 | EpochTime 386.47 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.1276 Average/AverageReturn -170.102 Average/Iteration 99 Average/MaxReturn -142.234 Average/MinReturn -235.931 Average/NumEpisodes 80 Average/StdReturn 18.8219 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6508 GaussianMLPPolicy/KLAfter 0.00236899 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.99016e-06 GaussianMLPPolicy/LossBefore 3.8743e-10 GaussianMLPPolicy/dLoss -2.98977e-06 Iteration 99 MetaTest/Average/AverageDiscountedReturn -174.656 MetaTest/Average/AverageReturn -174.656 MetaTest/Average/Iteration 99 MetaTest/Average/MaxReturn -150.32 MetaTest/Average/MinReturn -247.659 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.0763 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.656 MetaTest/__unnamed_task__/AverageReturn -174.656 MetaTest/__unnamed_task__/Iteration 99 MetaTest/__unnamed_task__/MaxReturn -150.32 MetaTest/__unnamed_task__/MinReturn -247.659 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.0763 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.2e+06 __unnamed_task__/AverageDiscountedReturn -72.1276 __unnamed_task__/AverageReturn -170.102 __unnamed_task__/Iteration 99 __unnamed_task__/MaxReturn -142.234 __unnamed_task__/MinReturn -235.931 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.8219 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 00:09:19 | [maml_trainer] epoch #100 | Sampling for adapation and meta-testing... 2025-04-03 00:10:27 | [maml_trainer] epoch #100 | Finished meta-testing... 2025-04-03 00:10:27 | [maml_trainer] epoch #100 | Saving snapshot... 2025-04-03 00:10:48 | [maml_trainer] epoch #100 | Saved 2025-04-03 00:10:48 | [maml_trainer] epoch #100 | Time 38127.05 s 2025-04-03 00:10:48 | [maml_trainer] epoch #100 | EpochTime 377.38 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.0865 Average/AverageReturn -174.998 Average/Iteration 100 Average/MaxReturn -147.995 Average/MinReturn -249.959 Average/NumEpisodes 80 Average/StdReturn 23.2312 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6487 GaussianMLPPolicy/KLAfter 0.00229703 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.57e-05 GaussianMLPPolicy/LossBefore -2.25008e-09 GaussianMLPPolicy/dLoss 1.56977e-05 Iteration 100 MetaTest/Average/AverageDiscountedReturn -163.326 MetaTest/Average/AverageReturn -163.326 MetaTest/Average/Iteration 100 MetaTest/Average/MaxReturn -148.082 MetaTest/Average/MinReturn -188.003 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.3437 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -163.326 MetaTest/__unnamed_task__/AverageReturn -163.326 MetaTest/__unnamed_task__/Iteration 100 MetaTest/__unnamed_task__/MaxReturn -148.082 MetaTest/__unnamed_task__/MinReturn -188.003 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.3437 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.232e+06 __unnamed_task__/AverageDiscountedReturn -74.0865 __unnamed_task__/AverageReturn -174.998 __unnamed_task__/Iteration 100 __unnamed_task__/MaxReturn -147.995 __unnamed_task__/MinReturn -249.959 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.2312 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 00:15:36 | [maml_trainer] epoch #101 | Sampling for adapation and meta-testing... 2025-04-03 00:16:49 | [maml_trainer] epoch #101 | Finished meta-testing... 2025-04-03 00:16:49 | [maml_trainer] epoch #101 | Saving snapshot... 2025-04-03 00:17:12 | [maml_trainer] epoch #101 | Saved 2025-04-03 00:17:12 | [maml_trainer] epoch #101 | Time 38510.61 s 2025-04-03 00:17:12 | [maml_trainer] epoch #101 | EpochTime 383.55 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.2083 Average/AverageReturn -170.183 Average/Iteration 101 Average/MaxReturn -147.793 Average/MinReturn -234.805 Average/NumEpisodes 80 Average/StdReturn 19.1678 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6463 GaussianMLPPolicy/KLAfter 0.00200527 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.0146e-05 GaussianMLPPolicy/LossBefore -9.68575e-09 GaussianMLPPolicy/dLoss 2.01364e-05 Iteration 101 MetaTest/Average/AverageDiscountedReturn -168.061 MetaTest/Average/AverageReturn -168.061 MetaTest/Average/Iteration 101 MetaTest/Average/MaxReturn -143.843 MetaTest/Average/MinReturn -218.617 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.8678 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.061 MetaTest/__unnamed_task__/AverageReturn -168.061 MetaTest/__unnamed_task__/Iteration 101 MetaTest/__unnamed_task__/MaxReturn -143.843 MetaTest/__unnamed_task__/MinReturn -218.617 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.8678 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.264e+06 __unnamed_task__/AverageDiscountedReturn -72.2083 __unnamed_task__/AverageReturn -170.183 __unnamed_task__/Iteration 101 __unnamed_task__/MaxReturn -147.793 __unnamed_task__/MinReturn -234.805 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.1678 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 00:22:05 | [maml_trainer] epoch #102 | Sampling for adapation and meta-testing... 2025-04-03 00:23:16 | [maml_trainer] epoch #102 | Finished meta-testing... 2025-04-03 00:23:16 | [maml_trainer] epoch #102 | Saving snapshot... 2025-04-03 00:23:38 | [maml_trainer] epoch #102 | Saved 2025-04-03 00:23:38 | [maml_trainer] epoch #102 | Time 38896.20 s 2025-04-03 00:23:38 | [maml_trainer] epoch #102 | EpochTime 385.59 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.2412 Average/AverageReturn -165.07 Average/Iteration 102 Average/MaxReturn -141.815 Average/MinReturn -219.558 Average/NumEpisodes 80 Average/StdReturn 17.323 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6442 GaussianMLPPolicy/KLAfter 0.0015532 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.94057e-05 GaussianMLPPolicy/LossBefore -4.47035e-09 GaussianMLPPolicy/dLoss -2.94102e-05 Iteration 102 MetaTest/Average/AverageDiscountedReturn -167.821 MetaTest/Average/AverageReturn -167.821 MetaTest/Average/Iteration 102 MetaTest/Average/MaxReturn -145.048 MetaTest/Average/MinReturn -235.488 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.4283 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.821 MetaTest/__unnamed_task__/AverageReturn -167.821 MetaTest/__unnamed_task__/Iteration 102 MetaTest/__unnamed_task__/MaxReturn -145.048 MetaTest/__unnamed_task__/MinReturn -235.488 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.4283 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.296e+06 __unnamed_task__/AverageDiscountedReturn -70.2412 __unnamed_task__/AverageReturn -165.07 __unnamed_task__/Iteration 102 __unnamed_task__/MaxReturn -141.815 __unnamed_task__/MinReturn -219.558 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.323 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 00:28:18 | [maml_trainer] epoch #103 | Sampling for adapation and meta-testing... 2025-04-03 00:29:30 | [maml_trainer] epoch #103 | Finished meta-testing... 2025-04-03 00:29:30 | [maml_trainer] epoch #103 | Saving snapshot... 2025-04-03 00:29:51 | [maml_trainer] epoch #103 | Saved 2025-04-03 00:29:51 | [maml_trainer] epoch #103 | Time 39269.69 s 2025-04-03 00:29:51 | [maml_trainer] epoch #103 | EpochTime 373.48 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.3992 Average/AverageReturn -168.253 Average/Iteration 103 Average/MaxReturn -142.687 Average/MinReturn -235.461 Average/NumEpisodes 80 Average/StdReturn 19.2065 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6425 GaussianMLPPolicy/KLAfter 0.00145216 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.54094e-06 GaussianMLPPolicy/LossBefore -9.17912e-09 GaussianMLPPolicy/dLoss -1.55012e-06 Iteration 103 MetaTest/Average/AverageDiscountedReturn -175.382 MetaTest/Average/AverageReturn -175.382 MetaTest/Average/Iteration 103 MetaTest/Average/MaxReturn -143.837 MetaTest/Average/MinReturn -238.914 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 27.4743 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.382 MetaTest/__unnamed_task__/AverageReturn -175.382 MetaTest/__unnamed_task__/Iteration 103 MetaTest/__unnamed_task__/MaxReturn -143.837 MetaTest/__unnamed_task__/MinReturn -238.914 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 27.4743 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.328e+06 __unnamed_task__/AverageDiscountedReturn -71.3992 __unnamed_task__/AverageReturn -168.253 __unnamed_task__/Iteration 103 __unnamed_task__/MaxReturn -142.687 __unnamed_task__/MinReturn -235.461 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.2065 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 00:34:39 | [maml_trainer] epoch #104 | Sampling for adapation and meta-testing... 2025-04-03 00:35:49 | [maml_trainer] epoch #104 | Finished meta-testing... 2025-04-03 00:35:49 | [maml_trainer] epoch #104 | Saving snapshot... 2025-04-03 00:36:10 | [maml_trainer] epoch #104 | Saved 2025-04-03 00:36:10 | [maml_trainer] epoch #104 | Time 39648.63 s 2025-04-03 00:36:10 | [maml_trainer] epoch #104 | EpochTime 378.94 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.1076 Average/AverageReturn -166.589 Average/Iteration 104 Average/MaxReturn -139.96 Average/MinReturn -248.336 Average/NumEpisodes 80 Average/StdReturn 19.0739 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6404 GaussianMLPPolicy/KLAfter 0.00150799 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.73551e-06 GaussianMLPPolicy/LossBefore 1.41561e-09 GaussianMLPPolicy/dLoss -8.73409e-06 Iteration 104 MetaTest/Average/AverageDiscountedReturn -164.009 MetaTest/Average/AverageReturn -164.009 MetaTest/Average/Iteration 104 MetaTest/Average/MaxReturn -140.131 MetaTest/Average/MinReturn -222.961 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.3557 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.009 MetaTest/__unnamed_task__/AverageReturn -164.009 MetaTest/__unnamed_task__/Iteration 104 MetaTest/__unnamed_task__/MaxReturn -140.131 MetaTest/__unnamed_task__/MinReturn -222.961 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.3557 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.36e+06 __unnamed_task__/AverageDiscountedReturn -71.1076 __unnamed_task__/AverageReturn -166.589 __unnamed_task__/Iteration 104 __unnamed_task__/MaxReturn -139.96 __unnamed_task__/MinReturn -248.336 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.0739 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 00:40:57 | [maml_trainer] epoch #105 | Sampling for adapation and meta-testing... 2025-04-03 00:42:07 | [maml_trainer] epoch #105 | Finished meta-testing... 2025-04-03 00:42:07 | [maml_trainer] epoch #105 | Saving snapshot... 2025-04-03 00:42:29 | [maml_trainer] epoch #105 | Saved 2025-04-03 00:42:29 | [maml_trainer] epoch #105 | Time 40027.92 s 2025-04-03 00:42:29 | [maml_trainer] epoch #105 | EpochTime 379.29 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.8465 Average/AverageReturn -167.358 Average/Iteration 105 Average/MaxReturn -145.225 Average/MinReturn -230.948 Average/NumEpisodes 80 Average/StdReturn 17.3507 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6382 GaussianMLPPolicy/KLAfter 0.00113225 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.75926e-06 GaussianMLPPolicy/LossBefore -3.60608e-09 GaussianMLPPolicy/dLoss -7.76286e-06 Iteration 105 MetaTest/Average/AverageDiscountedReturn -159.772 MetaTest/Average/AverageReturn -159.772 MetaTest/Average/Iteration 105 MetaTest/Average/MaxReturn -141.89 MetaTest/Average/MinReturn -186.638 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.7558 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -159.772 MetaTest/__unnamed_task__/AverageReturn -159.772 MetaTest/__unnamed_task__/Iteration 105 MetaTest/__unnamed_task__/MaxReturn -141.89 MetaTest/__unnamed_task__/MinReturn -186.638 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.7558 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.392e+06 __unnamed_task__/AverageDiscountedReturn -70.8465 __unnamed_task__/AverageReturn -167.358 __unnamed_task__/Iteration 105 __unnamed_task__/MaxReturn -145.225 __unnamed_task__/MinReturn -230.948 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.3507 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 00:47:09 | [maml_trainer] epoch #106 | Sampling for adapation and meta-testing... 2025-04-03 00:48:21 | [maml_trainer] epoch #106 | Finished meta-testing... 2025-04-03 00:48:21 | [maml_trainer] epoch #106 | Saving snapshot... 2025-04-03 00:48:43 | [maml_trainer] epoch #106 | Saved 2025-04-03 00:48:43 | [maml_trainer] epoch #106 | Time 40401.82 s 2025-04-03 00:48:43 | [maml_trainer] epoch #106 | EpochTime 373.89 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.8528 Average/AverageReturn -169.211 Average/Iteration 106 Average/MaxReturn -142.944 Average/MinReturn -261.25 Average/NumEpisodes 80 Average/StdReturn 24.3109 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6358 GaussianMLPPolicy/KLAfter 0.00130113 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.77823e-06 GaussianMLPPolicy/LossBefore -7.19726e-09 GaussianMLPPolicy/dLoss -1.78543e-06 Iteration 106 MetaTest/Average/AverageDiscountedReturn -171.577 MetaTest/Average/AverageReturn -171.577 MetaTest/Average/Iteration 106 MetaTest/Average/MaxReturn -148.075 MetaTest/Average/MinReturn -225.015 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.0019 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.577 MetaTest/__unnamed_task__/AverageReturn -171.577 MetaTest/__unnamed_task__/Iteration 106 MetaTest/__unnamed_task__/MaxReturn -148.075 MetaTest/__unnamed_task__/MinReturn -225.015 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.0019 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.424e+06 __unnamed_task__/AverageDiscountedReturn -71.8528 __unnamed_task__/AverageReturn -169.211 __unnamed_task__/Iteration 106 __unnamed_task__/MaxReturn -142.944 __unnamed_task__/MinReturn -261.25 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.3109 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 00:53:32 | [maml_trainer] epoch #107 | Sampling for adapation and meta-testing... 2025-04-03 00:54:44 | [maml_trainer] epoch #107 | Finished meta-testing... 2025-04-03 00:54:44 | [maml_trainer] epoch #107 | Saving snapshot... 2025-04-03 00:55:06 | [maml_trainer] epoch #107 | Saved 2025-04-03 00:55:06 | [maml_trainer] epoch #107 | Time 40784.33 s 2025-04-03 00:55:06 | [maml_trainer] epoch #107 | EpochTime 382.51 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.5335 Average/AverageReturn -170.717 Average/Iteration 107 Average/MaxReturn -146.034 Average/MinReturn -236.203 Average/NumEpisodes 80 Average/StdReturn 19.5893 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6337 GaussianMLPPolicy/KLAfter 0.00153322 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.23494e-06 GaussianMLPPolicy/LossBefore -3.75509e-09 GaussianMLPPolicy/dLoss -2.23869e-06 Iteration 107 MetaTest/Average/AverageDiscountedReturn -169.858 MetaTest/Average/AverageReturn -169.858 MetaTest/Average/Iteration 107 MetaTest/Average/MaxReturn -140.158 MetaTest/Average/MinReturn -223.841 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.3668 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.858 MetaTest/__unnamed_task__/AverageReturn -169.858 MetaTest/__unnamed_task__/Iteration 107 MetaTest/__unnamed_task__/MaxReturn -140.158 MetaTest/__unnamed_task__/MinReturn -223.841 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.3668 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.456e+06 __unnamed_task__/AverageDiscountedReturn -72.5335 __unnamed_task__/AverageReturn -170.717 __unnamed_task__/Iteration 107 __unnamed_task__/MaxReturn -146.034 __unnamed_task__/MinReturn -236.203 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.5893 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 00:59:59 | [maml_trainer] epoch #108 | Sampling for adapation and meta-testing... 2025-04-03 01:01:13 | [maml_trainer] epoch #108 | Finished meta-testing... 2025-04-03 01:01:13 | [maml_trainer] epoch #108 | Saving snapshot... 2025-04-03 01:01:35 | [maml_trainer] epoch #108 | Saved 2025-04-03 01:01:35 | [maml_trainer] epoch #108 | Time 41173.48 s 2025-04-03 01:01:35 | [maml_trainer] epoch #108 | EpochTime 389.15 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.9958 Average/AverageReturn -168.108 Average/Iteration 108 Average/MaxReturn -142.698 Average/MinReturn -258.4 Average/NumEpisodes 80 Average/StdReturn 24.916 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6319 GaussianMLPPolicy/KLAfter 0.00242614 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.43762e-05 GaussianMLPPolicy/LossBefore 1.72853e-09 GaussianMLPPolicy/dLoss -2.43745e-05 Iteration 108 MetaTest/Average/AverageDiscountedReturn -182.235 MetaTest/Average/AverageReturn -182.235 MetaTest/Average/Iteration 108 MetaTest/Average/MaxReturn -144.248 MetaTest/Average/MinReturn -238.773 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.8491 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -182.235 MetaTest/__unnamed_task__/AverageReturn -182.235 MetaTest/__unnamed_task__/Iteration 108 MetaTest/__unnamed_task__/MaxReturn -144.248 MetaTest/__unnamed_task__/MinReturn -238.773 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.8491 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.488e+06 __unnamed_task__/AverageDiscountedReturn -71.9958 __unnamed_task__/AverageReturn -168.108 __unnamed_task__/Iteration 108 __unnamed_task__/MaxReturn -142.698 __unnamed_task__/MinReturn -258.4 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.916 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 01:06:22 | [maml_trainer] epoch #109 | Sampling for adapation and meta-testing... 2025-04-03 01:07:34 | [maml_trainer] epoch #109 | Finished meta-testing... 2025-04-03 01:07:34 | [maml_trainer] epoch #109 | Saving snapshot... 2025-04-03 01:07:56 | [maml_trainer] epoch #109 | Saved 2025-04-03 01:07:56 | [maml_trainer] epoch #109 | Time 41555.07 s 2025-04-03 01:07:56 | [maml_trainer] epoch #109 | EpochTime 381.58 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -69.8059 Average/AverageReturn -163.682 Average/Iteration 109 Average/MaxReturn -142.265 Average/MinReturn -246.01 Average/NumEpisodes 80 Average/StdReturn 16.9768 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6322 GaussianMLPPolicy/KLAfter 0.00245014 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.61102e-05 GaussianMLPPolicy/LossBefore -1.19209e-09 GaussianMLPPolicy/dLoss -1.61114e-05 Iteration 109 MetaTest/Average/AverageDiscountedReturn -175.7 MetaTest/Average/AverageReturn -175.7 MetaTest/Average/Iteration 109 MetaTest/Average/MaxReturn -153.5 MetaTest/Average/MinReturn -241.719 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.7084 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.7 MetaTest/__unnamed_task__/AverageReturn -175.7 MetaTest/__unnamed_task__/Iteration 109 MetaTest/__unnamed_task__/MaxReturn -153.5 MetaTest/__unnamed_task__/MinReturn -241.719 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.7084 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.52e+06 __unnamed_task__/AverageDiscountedReturn -69.8059 __unnamed_task__/AverageReturn -163.682 __unnamed_task__/Iteration 109 __unnamed_task__/MaxReturn -142.265 __unnamed_task__/MinReturn -246.01 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.9768 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 01:12:48 | [maml_trainer] epoch #110 | Sampling for adapation and meta-testing... 2025-04-03 01:13:59 | [maml_trainer] epoch #110 | Finished meta-testing... 2025-04-03 01:13:59 | [maml_trainer] epoch #110 | Saving snapshot... 2025-04-03 01:14:22 | [maml_trainer] epoch #110 | Saved 2025-04-03 01:14:22 | [maml_trainer] epoch #110 | Time 41940.52 s 2025-04-03 01:14:22 | [maml_trainer] epoch #110 | EpochTime 385.45 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.7444 Average/AverageReturn -170.388 Average/Iteration 110 Average/MaxReturn -138.113 Average/MinReturn -266.882 Average/NumEpisodes 80 Average/StdReturn 23.8321 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6342 GaussianMLPPolicy/KLAfter 0.00286785 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.51289e-05 GaussianMLPPolicy/LossBefore 1.34408e-08 GaussianMLPPolicy/dLoss 1.51423e-05 Iteration 110 MetaTest/Average/AverageDiscountedReturn -176.806 MetaTest/Average/AverageReturn -176.806 MetaTest/Average/Iteration 110 MetaTest/Average/MaxReturn -147.465 MetaTest/Average/MinReturn -226.103 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.6506 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.806 MetaTest/__unnamed_task__/AverageReturn -176.806 MetaTest/__unnamed_task__/Iteration 110 MetaTest/__unnamed_task__/MaxReturn -147.465 MetaTest/__unnamed_task__/MinReturn -226.103 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.6506 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.552e+06 __unnamed_task__/AverageDiscountedReturn -72.7444 __unnamed_task__/AverageReturn -170.388 __unnamed_task__/Iteration 110 __unnamed_task__/MaxReturn -138.113 __unnamed_task__/MinReturn -266.882 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.8321 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 01:19:11 | [maml_trainer] epoch #111 | Sampling for adapation and meta-testing... 2025-04-03 01:20:24 | [maml_trainer] epoch #111 | Finished meta-testing... 2025-04-03 01:20:24 | [maml_trainer] epoch #111 | Saving snapshot... 2025-04-03 01:20:46 | [maml_trainer] epoch #111 | Saved 2025-04-03 01:20:46 | [maml_trainer] epoch #111 | Time 42324.31 s 2025-04-03 01:20:46 | [maml_trainer] epoch #111 | EpochTime 383.78 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.5211 Average/AverageReturn -173.409 Average/Iteration 111 Average/MaxReturn -142.011 Average/MinReturn -272.77 Average/NumEpisodes 80 Average/StdReturn 26.1544 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6371 GaussianMLPPolicy/KLAfter 0.00318482 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.08324e-05 GaussianMLPPolicy/LossBefore 1.72853e-09 GaussianMLPPolicy/dLoss -2.08306e-05 Iteration 111 MetaTest/Average/AverageDiscountedReturn -175.265 MetaTest/Average/AverageReturn -175.265 MetaTest/Average/Iteration 111 MetaTest/Average/MaxReturn -146.971 MetaTest/Average/MinReturn -249.076 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 30.9382 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.265 MetaTest/__unnamed_task__/AverageReturn -175.265 MetaTest/__unnamed_task__/Iteration 111 MetaTest/__unnamed_task__/MaxReturn -146.971 MetaTest/__unnamed_task__/MinReturn -249.076 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 30.9382 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.584e+06 __unnamed_task__/AverageDiscountedReturn -74.5211 __unnamed_task__/AverageReturn -173.409 __unnamed_task__/Iteration 111 __unnamed_task__/MaxReturn -142.011 __unnamed_task__/MinReturn -272.77 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 26.1544 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 01:25:34 | [maml_trainer] epoch #112 | Sampling for adapation and meta-testing... 2025-04-03 01:26:47 | [maml_trainer] epoch #112 | Finished meta-testing... 2025-04-03 01:26:47 | [maml_trainer] epoch #112 | Saving snapshot... 2025-04-03 01:27:08 | [maml_trainer] epoch #112 | Saved 2025-04-03 01:27:08 | [maml_trainer] epoch #112 | Time 42706.86 s 2025-04-03 01:27:08 | [maml_trainer] epoch #112 | EpochTime 382.55 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.5407 Average/AverageReturn -174.086 Average/Iteration 112 Average/MaxReturn -144.832 Average/MinReturn -248.694 Average/NumEpisodes 80 Average/StdReturn 23.6731 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.64 GaussianMLPPolicy/KLAfter 0.00319607 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.56347e-05 GaussianMLPPolicy/LossBefore -5.0962e-09 GaussianMLPPolicy/dLoss 6.56296e-05 Iteration 112 MetaTest/Average/AverageDiscountedReturn -166.072 MetaTest/Average/AverageReturn -166.072 MetaTest/Average/Iteration 112 MetaTest/Average/MaxReturn -143.88 MetaTest/Average/MinReturn -201.823 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.4988 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.072 MetaTest/__unnamed_task__/AverageReturn -166.072 MetaTest/__unnamed_task__/Iteration 112 MetaTest/__unnamed_task__/MaxReturn -143.88 MetaTest/__unnamed_task__/MinReturn -201.823 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.4988 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.616e+06 __unnamed_task__/AverageDiscountedReturn -73.5407 __unnamed_task__/AverageReturn -174.086 __unnamed_task__/Iteration 112 __unnamed_task__/MaxReturn -144.832 __unnamed_task__/MinReturn -248.694 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.6731 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 01:31:56 | [maml_trainer] epoch #113 | Sampling for adapation and meta-testing... 2025-04-03 01:33:08 | [maml_trainer] epoch #113 | Finished meta-testing... 2025-04-03 01:33:08 | [maml_trainer] epoch #113 | Saving snapshot... 2025-04-03 01:33:31 | [maml_trainer] epoch #113 | Saved 2025-04-03 01:33:31 | [maml_trainer] epoch #113 | Time 43089.22 s 2025-04-03 01:33:31 | [maml_trainer] epoch #113 | EpochTime 382.36 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.7315 Average/AverageReturn -171.407 Average/Iteration 113 Average/MaxReturn -136.631 Average/MinReturn -242.775 Average/NumEpisodes 80 Average/StdReturn 23.1529 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6413 GaussianMLPPolicy/KLAfter 0.0019425 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.16485e-05 GaussianMLPPolicy/LossBefore 3.8743e-10 GaussianMLPPolicy/dLoss 3.16489e-05 Iteration 113 MetaTest/Average/AverageDiscountedReturn -170.395 MetaTest/Average/AverageReturn -170.395 MetaTest/Average/Iteration 113 MetaTest/Average/MaxReturn -145.998 MetaTest/Average/MinReturn -212.71 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.2261 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.395 MetaTest/__unnamed_task__/AverageReturn -170.395 MetaTest/__unnamed_task__/Iteration 113 MetaTest/__unnamed_task__/MaxReturn -145.998 MetaTest/__unnamed_task__/MinReturn -212.71 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.2261 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.648e+06 __unnamed_task__/AverageDiscountedReturn -72.7315 __unnamed_task__/AverageReturn -171.407 __unnamed_task__/Iteration 113 __unnamed_task__/MaxReturn -136.631 __unnamed_task__/MinReturn -242.775 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.1529 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 01:38:22 | [maml_trainer] epoch #114 | Sampling for adapation and meta-testing... 2025-04-03 01:39:34 | [maml_trainer] epoch #114 | Finished meta-testing... 2025-04-03 01:39:34 | [maml_trainer] epoch #114 | Saving snapshot... 2025-04-03 01:39:57 | [maml_trainer] epoch #114 | Saved 2025-04-03 01:39:57 | [maml_trainer] epoch #114 | Time 43475.93 s 2025-04-03 01:39:57 | [maml_trainer] epoch #114 | EpochTime 386.70 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.5111 Average/AverageReturn -168.484 Average/Iteration 114 Average/MaxReturn -140.654 Average/MinReturn -238.254 Average/NumEpisodes 80 Average/StdReturn 18.0328 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6425 GaussianMLPPolicy/KLAfter 0.00215491 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.9797e-05 GaussianMLPPolicy/LossBefore 1.2219e-09 GaussianMLPPolicy/dLoss 2.97982e-05 Iteration 114 MetaTest/Average/AverageDiscountedReturn -172.748 MetaTest/Average/AverageReturn -172.748 MetaTest/Average/Iteration 114 MetaTest/Average/MaxReturn -145.624 MetaTest/Average/MinReturn -232.883 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.789 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.748 MetaTest/__unnamed_task__/AverageReturn -172.748 MetaTest/__unnamed_task__/Iteration 114 MetaTest/__unnamed_task__/MaxReturn -145.624 MetaTest/__unnamed_task__/MinReturn -232.883 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.789 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.68e+06 __unnamed_task__/AverageDiscountedReturn -71.5111 __unnamed_task__/AverageReturn -168.484 __unnamed_task__/Iteration 114 __unnamed_task__/MaxReturn -140.654 __unnamed_task__/MinReturn -238.254 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.0328 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 01:44:48 | [maml_trainer] epoch #115 | Sampling for adapation and meta-testing... 2025-04-03 01:46:00 | [maml_trainer] epoch #115 | Finished meta-testing... 2025-04-03 01:46:00 | [maml_trainer] epoch #115 | Saving snapshot... 2025-04-03 01:46:22 | [maml_trainer] epoch #115 | Saved 2025-04-03 01:46:22 | [maml_trainer] epoch #115 | Time 43861.11 s 2025-04-03 01:46:22 | [maml_trainer] epoch #115 | EpochTime 385.17 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.4117 Average/AverageReturn -173.974 Average/Iteration 115 Average/MaxReturn -150.022 Average/MinReturn -233.789 Average/NumEpisodes 80 Average/StdReturn 19.2364 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6435 GaussianMLPPolicy/KLAfter 0.00269606 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.64892e-05 GaussianMLPPolicy/LossBefore 5.94556e-09 GaussianMLPPolicy/dLoss -1.64833e-05 Iteration 115 MetaTest/Average/AverageDiscountedReturn -172.705 MetaTest/Average/AverageReturn -172.705 MetaTest/Average/Iteration 115 MetaTest/Average/MaxReturn -148.741 MetaTest/Average/MinReturn -219.338 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.4251 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.705 MetaTest/__unnamed_task__/AverageReturn -172.705 MetaTest/__unnamed_task__/Iteration 115 MetaTest/__unnamed_task__/MaxReturn -148.741 MetaTest/__unnamed_task__/MinReturn -219.338 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.4251 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.712e+06 __unnamed_task__/AverageDiscountedReturn -73.4117 __unnamed_task__/AverageReturn -173.974 __unnamed_task__/Iteration 115 __unnamed_task__/MaxReturn -150.022 __unnamed_task__/MinReturn -233.789 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.2364 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 01:51:16 | [maml_trainer] epoch #116 | Sampling for adapation and meta-testing... 2025-04-03 01:52:27 | [maml_trainer] epoch #116 | Finished meta-testing... 2025-04-03 01:52:27 | [maml_trainer] epoch #116 | Saving snapshot... 2025-04-03 01:52:49 | [maml_trainer] epoch #116 | Saved 2025-04-03 01:52:49 | [maml_trainer] epoch #116 | Time 44247.50 s 2025-04-03 01:52:49 | [maml_trainer] epoch #116 | EpochTime 386.40 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.0223 Average/AverageReturn -167.194 Average/Iteration 116 Average/MaxReturn -145.919 Average/MinReturn -239.882 Average/NumEpisodes 80 Average/StdReturn 17.5694 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6458 GaussianMLPPolicy/KLAfter 0.00197041 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.94056e-05 GaussianMLPPolicy/LossBefore 5.37932e-09 GaussianMLPPolicy/dLoss 2.9411e-05 Iteration 116 MetaTest/Average/AverageDiscountedReturn -168.665 MetaTest/Average/AverageReturn -168.665 MetaTest/Average/Iteration 116 MetaTest/Average/MaxReturn -150.615 MetaTest/Average/MinReturn -202.493 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.8235 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.665 MetaTest/__unnamed_task__/AverageReturn -168.665 MetaTest/__unnamed_task__/Iteration 116 MetaTest/__unnamed_task__/MaxReturn -150.615 MetaTest/__unnamed_task__/MinReturn -202.493 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.8235 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.744e+06 __unnamed_task__/AverageDiscountedReturn -71.0223 __unnamed_task__/AverageReturn -167.194 __unnamed_task__/Iteration 116 __unnamed_task__/MaxReturn -145.919 __unnamed_task__/MinReturn -239.882 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.5694 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 01:57:37 | [maml_trainer] epoch #117 | Sampling for adapation and meta-testing... 2025-04-03 01:58:49 | [maml_trainer] epoch #117 | Finished meta-testing... 2025-04-03 01:58:49 | [maml_trainer] epoch #117 | Saving snapshot... 2025-04-03 01:59:12 | [maml_trainer] epoch #117 | Saved 2025-04-03 01:59:12 | [maml_trainer] epoch #117 | Time 44630.13 s 2025-04-03 01:59:12 | [maml_trainer] epoch #117 | EpochTime 382.62 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.5691 Average/AverageReturn -171.201 Average/Iteration 117 Average/MaxReturn -145.869 Average/MinReturn -236.284 Average/NumEpisodes 80 Average/StdReturn 20.0076 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6479 GaussianMLPPolicy/KLAfter 0.00115833 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.19964e-07 GaussianMLPPolicy/LossBefore -2.33948e-09 GaussianMLPPolicy/dLoss 7.17625e-07 Iteration 117 MetaTest/Average/AverageDiscountedReturn -174.58 MetaTest/Average/AverageReturn -174.58 MetaTest/Average/Iteration 117 MetaTest/Average/MaxReturn -148.172 MetaTest/Average/MinReturn -233.198 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.254 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.58 MetaTest/__unnamed_task__/AverageReturn -174.58 MetaTest/__unnamed_task__/Iteration 117 MetaTest/__unnamed_task__/MaxReturn -148.172 MetaTest/__unnamed_task__/MinReturn -233.198 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.254 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.776e+06 __unnamed_task__/AverageDiscountedReturn -72.5691 __unnamed_task__/AverageReturn -171.201 __unnamed_task__/Iteration 117 __unnamed_task__/MaxReturn -145.869 __unnamed_task__/MinReturn -236.284 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.0076 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 02:04:02 | [maml_trainer] epoch #118 | Sampling for adapation and meta-testing... 2025-04-03 02:05:14 | [maml_trainer] epoch #118 | Finished meta-testing... 2025-04-03 02:05:14 | [maml_trainer] epoch #118 | Saving snapshot... 2025-04-03 02:05:37 | [maml_trainer] epoch #118 | Saved 2025-04-03 02:05:37 | [maml_trainer] epoch #118 | Time 45015.37 s 2025-04-03 02:05:37 | [maml_trainer] epoch #118 | EpochTime 385.24 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.0422 Average/AverageReturn -171.723 Average/Iteration 118 Average/MaxReturn -141.811 Average/MinReturn -257.578 Average/NumEpisodes 80 Average/StdReturn 23.4244 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6498 GaussianMLPPolicy/KLAfter 0.00201455 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.93225e-05 GaussianMLPPolicy/LossBefore -5.76675e-09 GaussianMLPPolicy/dLoss 3.93168e-05 Iteration 118 MetaTest/Average/AverageDiscountedReturn -171.852 MetaTest/Average/AverageReturn -171.852 MetaTest/Average/Iteration 118 MetaTest/Average/MaxReturn -146.392 MetaTest/Average/MinReturn -243.817 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.9275 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.852 MetaTest/__unnamed_task__/AverageReturn -171.852 MetaTest/__unnamed_task__/Iteration 118 MetaTest/__unnamed_task__/MaxReturn -146.392 MetaTest/__unnamed_task__/MinReturn -243.817 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.9275 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.808e+06 __unnamed_task__/AverageDiscountedReturn -73.0422 __unnamed_task__/AverageReturn -171.723 __unnamed_task__/Iteration 118 __unnamed_task__/MaxReturn -141.811 __unnamed_task__/MinReturn -257.578 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.4244 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 02:10:28 | [maml_trainer] epoch #119 | Sampling for adapation and meta-testing... 2025-04-03 02:11:40 | [maml_trainer] epoch #119 | Finished meta-testing... 2025-04-03 02:11:40 | [maml_trainer] epoch #119 | Saving snapshot... 2025-04-03 02:12:03 | [maml_trainer] epoch #119 | Saved 2025-04-03 02:12:03 | [maml_trainer] epoch #119 | Time 45401.91 s 2025-04-03 02:12:03 | [maml_trainer] epoch #119 | EpochTime 386.53 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.4257 Average/AverageReturn -168.407 Average/Iteration 119 Average/MaxReturn -126.108 Average/MinReturn -241.241 Average/NumEpisodes 80 Average/StdReturn 18.5482 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6509 GaussianMLPPolicy/KLAfter 0.00162193 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.17579e-06 GaussianMLPPolicy/LossBefore -1.69873e-09 GaussianMLPPolicy/dLoss -3.17749e-06 Iteration 119 MetaTest/Average/AverageDiscountedReturn -169.13 MetaTest/Average/AverageReturn -169.13 MetaTest/Average/Iteration 119 MetaTest/Average/MaxReturn -143.291 MetaTest/Average/MinReturn -219.318 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.7314 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.13 MetaTest/__unnamed_task__/AverageReturn -169.13 MetaTest/__unnamed_task__/Iteration 119 MetaTest/__unnamed_task__/MaxReturn -143.291 MetaTest/__unnamed_task__/MinReturn -219.318 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.7314 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.84e+06 __unnamed_task__/AverageDiscountedReturn -71.4257 __unnamed_task__/AverageReturn -168.407 __unnamed_task__/Iteration 119 __unnamed_task__/MaxReturn -126.108 __unnamed_task__/MinReturn -241.241 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.5482 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 02:16:52 | [maml_trainer] epoch #120 | Sampling for adapation and meta-testing... 2025-04-03 02:18:06 | [maml_trainer] epoch #120 | Finished meta-testing... 2025-04-03 02:18:06 | [maml_trainer] epoch #120 | Saving snapshot... 2025-04-03 02:18:27 | [maml_trainer] epoch #120 | Saved 2025-04-03 02:18:27 | [maml_trainer] epoch #120 | Time 45785.97 s 2025-04-03 02:18:27 | [maml_trainer] epoch #120 | EpochTime 384.06 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.5246 Average/AverageReturn -168.862 Average/Iteration 120 Average/MaxReturn -146.435 Average/MinReturn -241.424 Average/NumEpisodes 80 Average/StdReturn 16.1487 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6493 GaussianMLPPolicy/KLAfter 0.00224598 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.64501e-06 GaussianMLPPolicy/LossBefore -3.76999e-09 GaussianMLPPolicy/dLoss -7.64878e-06 Iteration 120 MetaTest/Average/AverageDiscountedReturn -177.785 MetaTest/Average/AverageReturn -177.785 MetaTest/Average/Iteration 120 MetaTest/Average/MaxReturn -147.142 MetaTest/Average/MinReturn -257.896 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 27.7551 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.785 MetaTest/__unnamed_task__/AverageReturn -177.785 MetaTest/__unnamed_task__/Iteration 120 MetaTest/__unnamed_task__/MaxReturn -147.142 MetaTest/__unnamed_task__/MinReturn -257.896 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 27.7551 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.872e+06 __unnamed_task__/AverageDiscountedReturn -71.5246 __unnamed_task__/AverageReturn -168.862 __unnamed_task__/Iteration 120 __unnamed_task__/MaxReturn -146.435 __unnamed_task__/MinReturn -241.424 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.1487 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 02:23:15 | [maml_trainer] epoch #121 | Sampling for adapation and meta-testing... 2025-04-03 02:24:29 | [maml_trainer] epoch #121 | Finished meta-testing... 2025-04-03 02:24:29 | [maml_trainer] epoch #121 | Saving snapshot... 2025-04-03 02:24:51 | [maml_trainer] epoch #121 | Saved 2025-04-03 02:24:51 | [maml_trainer] epoch #121 | Time 46169.84 s 2025-04-03 02:24:51 | [maml_trainer] epoch #121 | EpochTime 383.86 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.4156 Average/AverageReturn -171.351 Average/Iteration 121 Average/MaxReturn -147.337 Average/MinReturn -241.864 Average/NumEpisodes 80 Average/StdReturn 20.6355 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6489 GaussianMLPPolicy/KLAfter 0.00195299 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.21048e-05 GaussianMLPPolicy/LossBefore -2.16067e-09 GaussianMLPPolicy/dLoss -3.2107e-05 Iteration 121 MetaTest/Average/AverageDiscountedReturn -180.287 MetaTest/Average/AverageReturn -180.287 MetaTest/Average/Iteration 121 MetaTest/Average/MaxReturn -154.41 MetaTest/Average/MinReturn -237.215 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.856 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -180.287 MetaTest/__unnamed_task__/AverageReturn -180.287 MetaTest/__unnamed_task__/Iteration 121 MetaTest/__unnamed_task__/MaxReturn -154.41 MetaTest/__unnamed_task__/MinReturn -237.215 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.856 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.904e+06 __unnamed_task__/AverageDiscountedReturn -72.4156 __unnamed_task__/AverageReturn -171.351 __unnamed_task__/Iteration 121 __unnamed_task__/MaxReturn -147.337 __unnamed_task__/MinReturn -241.864 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.6355 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 02:29:39 | [maml_trainer] epoch #122 | Sampling for adapation and meta-testing... 2025-04-03 02:30:52 | [maml_trainer] epoch #122 | Finished meta-testing... 2025-04-03 02:30:52 | [maml_trainer] epoch #122 | Saving snapshot... 2025-04-03 02:31:15 | [maml_trainer] epoch #122 | Saved 2025-04-03 02:31:15 | [maml_trainer] epoch #122 | Time 46553.79 s 2025-04-03 02:31:15 | [maml_trainer] epoch #122 | EpochTime 383.95 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.3625 Average/AverageReturn -176.011 Average/Iteration 122 Average/MaxReturn -149.088 Average/MinReturn -241.443 Average/NumEpisodes 80 Average/StdReturn 22.321 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6489 GaussianMLPPolicy/KLAfter 0.0020698 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.53075e-06 GaussianMLPPolicy/LossBefore 1.38581e-09 GaussianMLPPolicy/dLoss -7.52936e-06 Iteration 122 MetaTest/Average/AverageDiscountedReturn -166.518 MetaTest/Average/AverageReturn -166.518 MetaTest/Average/Iteration 122 MetaTest/Average/MaxReturn -154.12 MetaTest/Average/MinReturn -181.648 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.49088 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.518 MetaTest/__unnamed_task__/AverageReturn -166.518 MetaTest/__unnamed_task__/Iteration 122 MetaTest/__unnamed_task__/MaxReturn -154.12 MetaTest/__unnamed_task__/MinReturn -181.648 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.49088 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.936e+06 __unnamed_task__/AverageDiscountedReturn -74.3625 __unnamed_task__/AverageReturn -176.011 __unnamed_task__/Iteration 122 __unnamed_task__/MaxReturn -149.088 __unnamed_task__/MinReturn -241.443 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.321 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 02:36:06 | [maml_trainer] epoch #123 | Sampling for adapation and meta-testing... 2025-04-03 02:37:19 | [maml_trainer] epoch #123 | Finished meta-testing... 2025-04-03 02:37:19 | [maml_trainer] epoch #123 | Saving snapshot... 2025-04-03 02:37:42 | [maml_trainer] epoch #123 | Saved 2025-04-03 02:37:42 | [maml_trainer] epoch #123 | Time 46940.88 s 2025-04-03 02:37:42 | [maml_trainer] epoch #123 | EpochTime 387.09 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.5661 Average/AverageReturn -172.501 Average/Iteration 123 Average/MaxReturn -150.433 Average/MinReturn -229.364 Average/NumEpisodes 80 Average/StdReturn 14.3932 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6465 GaussianMLPPolicy/KLAfter 0.00208592 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.14895e-05 GaussianMLPPolicy/LossBefore -2.5928e-09 GaussianMLPPolicy/dLoss -3.14921e-05 Iteration 123 MetaTest/Average/AverageDiscountedReturn -175.993 MetaTest/Average/AverageReturn -175.993 MetaTest/Average/Iteration 123 MetaTest/Average/MaxReturn -155.263 MetaTest/Average/MinReturn -246.359 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.5869 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.993 MetaTest/__unnamed_task__/AverageReturn -175.993 MetaTest/__unnamed_task__/Iteration 123 MetaTest/__unnamed_task__/MaxReturn -155.263 MetaTest/__unnamed_task__/MinReturn -246.359 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.5869 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.968e+06 __unnamed_task__/AverageDiscountedReturn -72.5661 __unnamed_task__/AverageReturn -172.501 __unnamed_task__/Iteration 123 __unnamed_task__/MaxReturn -150.433 __unnamed_task__/MinReturn -229.364 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.3932 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 02:42:36 | [maml_trainer] epoch #124 | Sampling for adapation and meta-testing... 2025-04-03 02:43:50 | [maml_trainer] epoch #124 | Finished meta-testing... 2025-04-03 02:43:50 | [maml_trainer] epoch #124 | Saving snapshot... 2025-04-03 02:44:12 | [maml_trainer] epoch #124 | Saved 2025-04-03 02:44:12 | [maml_trainer] epoch #124 | Time 47330.61 s 2025-04-03 02:44:12 | [maml_trainer] epoch #124 | EpochTime 389.72 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.6923 Average/AverageReturn -172.233 Average/Iteration 124 Average/MaxReturn -145.377 Average/MinReturn -241.343 Average/NumEpisodes 80 Average/StdReturn 13.8331 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6462 GaussianMLPPolicy/KLAfter 0.00146036 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.94544e-05 GaussianMLPPolicy/LossBefore -1.49012e-10 GaussianMLPPolicy/dLoss -1.94545e-05 Iteration 124 MetaTest/Average/AverageDiscountedReturn -176.269 MetaTest/Average/AverageReturn -176.269 MetaTest/Average/Iteration 124 MetaTest/Average/MaxReturn -155.138 MetaTest/Average/MinReturn -231.025 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.3807 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.269 MetaTest/__unnamed_task__/AverageReturn -176.269 MetaTest/__unnamed_task__/Iteration 124 MetaTest/__unnamed_task__/MaxReturn -155.138 MetaTest/__unnamed_task__/MinReturn -231.025 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.3807 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4e+06 __unnamed_task__/AverageDiscountedReturn -72.6923 __unnamed_task__/AverageReturn -172.233 __unnamed_task__/Iteration 124 __unnamed_task__/MaxReturn -145.377 __unnamed_task__/MinReturn -241.343 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.8331 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 02:49:02 | [maml_trainer] epoch #125 | Sampling for adapation and meta-testing... 2025-04-03 02:50:15 | [maml_trainer] epoch #125 | Finished meta-testing... 2025-04-03 02:50:15 | [maml_trainer] epoch #125 | Saving snapshot... 2025-04-03 02:50:37 | [maml_trainer] epoch #125 | Saved 2025-04-03 02:50:37 | [maml_trainer] epoch #125 | Time 47716.00 s 2025-04-03 02:50:37 | [maml_trainer] epoch #125 | EpochTime 385.39 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.8469 Average/AverageReturn -174.681 Average/Iteration 125 Average/MaxReturn -150.479 Average/MinReturn -252.851 Average/NumEpisodes 80 Average/StdReturn 20.1054 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6482 GaussianMLPPolicy/KLAfter 0.00119682 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.06486e-05 GaussianMLPPolicy/LossBefore 5.66244e-10 GaussianMLPPolicy/dLoss -3.0648e-05 Iteration 125 MetaTest/Average/AverageDiscountedReturn -175.986 MetaTest/Average/AverageReturn -175.986 MetaTest/Average/Iteration 125 MetaTest/Average/MaxReturn -155.766 MetaTest/Average/MinReturn -218.523 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.7248 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.986 MetaTest/__unnamed_task__/AverageReturn -175.986 MetaTest/__unnamed_task__/Iteration 125 MetaTest/__unnamed_task__/MaxReturn -155.766 MetaTest/__unnamed_task__/MinReturn -218.523 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.7248 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.032e+06 __unnamed_task__/AverageDiscountedReturn -73.8469 __unnamed_task__/AverageReturn -174.681 __unnamed_task__/Iteration 125 __unnamed_task__/MaxReturn -150.479 __unnamed_task__/MinReturn -252.851 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.1054 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 02:55:29 | [maml_trainer] epoch #126 | Sampling for adapation and meta-testing... 2025-04-03 02:56:43 | [maml_trainer] epoch #126 | Finished meta-testing... 2025-04-03 02:56:43 | [maml_trainer] epoch #126 | Saving snapshot... 2025-04-03 02:57:06 | [maml_trainer] epoch #126 | Saved 2025-04-03 02:57:06 | [maml_trainer] epoch #126 | Time 48104.45 s 2025-04-03 02:57:06 | [maml_trainer] epoch #126 | EpochTime 388.45 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.2142 Average/AverageReturn -174.117 Average/Iteration 126 Average/MaxReturn -145.362 Average/MinReturn -257.896 Average/NumEpisodes 80 Average/StdReturn 20.4819 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6502 GaussianMLPPolicy/KLAfter 0.0011337 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.3964e-06 GaussianMLPPolicy/LossBefore -9.59635e-09 GaussianMLPPolicy/dLoss 5.3868e-06 Iteration 126 MetaTest/Average/AverageDiscountedReturn -183.76 MetaTest/Average/AverageReturn -183.76 MetaTest/Average/Iteration 126 MetaTest/Average/MaxReturn -155.355 MetaTest/Average/MinReturn -249.414 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.8531 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -183.76 MetaTest/__unnamed_task__/AverageReturn -183.76 MetaTest/__unnamed_task__/Iteration 126 MetaTest/__unnamed_task__/MaxReturn -155.355 MetaTest/__unnamed_task__/MinReturn -249.414 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.8531 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.064e+06 __unnamed_task__/AverageDiscountedReturn -73.2142 __unnamed_task__/AverageReturn -174.117 __unnamed_task__/Iteration 126 __unnamed_task__/MaxReturn -145.362 __unnamed_task__/MinReturn -257.896 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.4819 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 03:01:57 | [maml_trainer] epoch #127 | Sampling for adapation and meta-testing... 2025-04-03 03:03:09 | [maml_trainer] epoch #127 | Finished meta-testing... 2025-04-03 03:03:09 | [maml_trainer] epoch #127 | Saving snapshot... 2025-04-03 03:03:32 | [maml_trainer] epoch #127 | Saved 2025-04-03 03:03:32 | [maml_trainer] epoch #127 | Time 48490.49 s 2025-04-03 03:03:32 | [maml_trainer] epoch #127 | EpochTime 386.03 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.3054 Average/AverageReturn -174.005 Average/Iteration 127 Average/MaxReturn -154.667 Average/MinReturn -219.327 Average/NumEpisodes 80 Average/StdReturn 14.0775 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6516 GaussianMLPPolicy/KLAfter 0.00129186 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.5308e-05 GaussianMLPPolicy/LossBefore -3.59118e-09 GaussianMLPPolicy/dLoss 6.53044e-05 Iteration 127 MetaTest/Average/AverageDiscountedReturn -170.738 MetaTest/Average/AverageReturn -170.738 MetaTest/Average/Iteration 127 MetaTest/Average/MaxReturn -156.215 MetaTest/Average/MinReturn -203.257 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.0214 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.738 MetaTest/__unnamed_task__/AverageReturn -170.738 MetaTest/__unnamed_task__/Iteration 127 MetaTest/__unnamed_task__/MaxReturn -156.215 MetaTest/__unnamed_task__/MinReturn -203.257 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.0214 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.096e+06 __unnamed_task__/AverageDiscountedReturn -73.3054 __unnamed_task__/AverageReturn -174.005 __unnamed_task__/Iteration 127 __unnamed_task__/MaxReturn -154.667 __unnamed_task__/MinReturn -219.327 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.0775 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 03:08:23 | [maml_trainer] epoch #128 | Sampling for adapation and meta-testing... 2025-04-03 03:09:35 | [maml_trainer] epoch #128 | Finished meta-testing... 2025-04-03 03:09:35 | [maml_trainer] epoch #128 | Saving snapshot... 2025-04-03 03:09:59 | [maml_trainer] epoch #128 | Saved 2025-04-03 03:09:59 | [maml_trainer] epoch #128 | Time 48877.13 s 2025-04-03 03:09:59 | [maml_trainer] epoch #128 | EpochTime 386.64 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.2584 Average/AverageReturn -175.582 Average/Iteration 128 Average/MaxReturn -155.458 Average/MinReturn -311.307 Average/NumEpisodes 80 Average/StdReturn 23.4979 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6544 GaussianMLPPolicy/KLAfter 0.00149354 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.28176e-05 GaussianMLPPolicy/LossBefore 2.14577e-09 GaussianMLPPolicy/dLoss 2.28197e-05 Iteration 128 MetaTest/Average/AverageDiscountedReturn -174.326 MetaTest/Average/AverageReturn -174.326 MetaTest/Average/Iteration 128 MetaTest/Average/MaxReturn -152.908 MetaTest/Average/MinReturn -213.823 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.9726 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.326 MetaTest/__unnamed_task__/AverageReturn -174.326 MetaTest/__unnamed_task__/Iteration 128 MetaTest/__unnamed_task__/MaxReturn -152.908 MetaTest/__unnamed_task__/MinReturn -213.823 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.9726 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.128e+06 __unnamed_task__/AverageDiscountedReturn -74.2584 __unnamed_task__/AverageReturn -175.582 __unnamed_task__/Iteration 128 __unnamed_task__/MaxReturn -155.458 __unnamed_task__/MinReturn -311.307 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.4979 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 03:14:50 | [maml_trainer] epoch #129 | Sampling for adapation and meta-testing... 2025-04-03 03:16:04 | [maml_trainer] epoch #129 | Finished meta-testing... 2025-04-03 03:16:04 | [maml_trainer] epoch #129 | Saving snapshot... 2025-04-03 03:16:25 | [maml_trainer] epoch #129 | Saved 2025-04-03 03:16:25 | [maml_trainer] epoch #129 | Time 49263.63 s 2025-04-03 03:16:25 | [maml_trainer] epoch #129 | EpochTime 386.49 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -76.7156 Average/AverageReturn -178.381 Average/Iteration 129 Average/MaxReturn -152.584 Average/MinReturn -374.038 Average/NumEpisodes 80 Average/StdReturn 29.5027 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6577 GaussianMLPPolicy/KLAfter 0.00137696 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.35272e-05 GaussianMLPPolicy/LossBefore -2.5779e-09 GaussianMLPPolicy/dLoss 1.35246e-05 Iteration 129 MetaTest/Average/AverageDiscountedReturn -172.978 MetaTest/Average/AverageReturn -172.978 MetaTest/Average/Iteration 129 MetaTest/Average/MaxReturn -157.583 MetaTest/Average/MinReturn -227.417 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.6139 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.978 MetaTest/__unnamed_task__/AverageReturn -172.978 MetaTest/__unnamed_task__/Iteration 129 MetaTest/__unnamed_task__/MaxReturn -157.583 MetaTest/__unnamed_task__/MinReturn -227.417 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.6139 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.16e+06 __unnamed_task__/AverageDiscountedReturn -76.7156 __unnamed_task__/AverageReturn -178.381 __unnamed_task__/Iteration 129 __unnamed_task__/MaxReturn -152.584 __unnamed_task__/MinReturn -374.038 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 29.5027 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 03:21:16 | [maml_trainer] epoch #130 | Sampling for adapation and meta-testing... 2025-04-03 03:22:28 | [maml_trainer] epoch #130 | Finished meta-testing... 2025-04-03 03:22:28 | [maml_trainer] epoch #130 | Saving snapshot... 2025-04-03 03:22:51 | [maml_trainer] epoch #130 | Saved 2025-04-03 03:22:51 | [maml_trainer] epoch #130 | Time 49649.99 s 2025-04-03 03:22:51 | [maml_trainer] epoch #130 | EpochTime 386.36 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.4063 Average/AverageReturn -176.071 Average/Iteration 130 Average/MaxReturn -141.99 Average/MinReturn -253.01 Average/NumEpisodes 80 Average/StdReturn 21.3981 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6608 GaussianMLPPolicy/KLAfter 0.0012904 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.46664e-05 GaussianMLPPolicy/LossBefore 2.90573e-09 GaussianMLPPolicy/dLoss 1.46693e-05 Iteration 130 MetaTest/Average/AverageDiscountedReturn -171.289 MetaTest/Average/AverageReturn -171.289 MetaTest/Average/Iteration 130 MetaTest/Average/MaxReturn -156.922 MetaTest/Average/MinReturn -191.083 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.30379 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.289 MetaTest/__unnamed_task__/AverageReturn -171.289 MetaTest/__unnamed_task__/Iteration 130 MetaTest/__unnamed_task__/MaxReturn -156.922 MetaTest/__unnamed_task__/MinReturn -191.083 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.30379 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.192e+06 __unnamed_task__/AverageDiscountedReturn -74.4063 __unnamed_task__/AverageReturn -176.071 __unnamed_task__/Iteration 130 __unnamed_task__/MaxReturn -141.99 __unnamed_task__/MinReturn -253.01 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.3981 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 03:27:45 | [maml_trainer] epoch #131 | Sampling for adapation and meta-testing... 2025-04-03 03:28:58 | [maml_trainer] epoch #131 | Finished meta-testing... 2025-04-03 03:28:58 | [maml_trainer] epoch #131 | Saving snapshot... 2025-04-03 03:29:21 | [maml_trainer] epoch #131 | Saved 2025-04-03 03:29:21 | [maml_trainer] epoch #131 | Time 50039.37 s 2025-04-03 03:29:21 | [maml_trainer] epoch #131 | EpochTime 389.37 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.4424 Average/AverageReturn -174.842 Average/Iteration 131 Average/MaxReturn -150.849 Average/MinReturn -245.771 Average/NumEpisodes 80 Average/StdReturn 18.0447 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6636 GaussianMLPPolicy/KLAfter 0.00188119 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.78123e-06 GaussianMLPPolicy/LossBefore 5.96047e-11 GaussianMLPPolicy/dLoss 9.78129e-06 Iteration 131 MetaTest/Average/AverageDiscountedReturn -176.814 MetaTest/Average/AverageReturn -176.814 MetaTest/Average/Iteration 131 MetaTest/Average/MaxReturn -164.091 MetaTest/Average/MinReturn -244.683 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.3142 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.814 MetaTest/__unnamed_task__/AverageReturn -176.814 MetaTest/__unnamed_task__/Iteration 131 MetaTest/__unnamed_task__/MaxReturn -164.091 MetaTest/__unnamed_task__/MinReturn -244.683 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.3142 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.224e+06 __unnamed_task__/AverageDiscountedReturn -73.4424 __unnamed_task__/AverageReturn -174.842 __unnamed_task__/Iteration 131 __unnamed_task__/MaxReturn -150.849 __unnamed_task__/MinReturn -245.771 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.0447 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 03:34:15 | [maml_trainer] epoch #132 | Sampling for adapation and meta-testing... 2025-04-03 03:35:28 | [maml_trainer] epoch #132 | Finished meta-testing... 2025-04-03 03:35:28 | [maml_trainer] epoch #132 | Saving snapshot... 2025-04-03 03:35:51 | [maml_trainer] epoch #132 | Saved 2025-04-03 03:35:51 | [maml_trainer] epoch #132 | Time 50429.22 s 2025-04-03 03:35:51 | [maml_trainer] epoch #132 | EpochTime 389.85 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.7596 Average/AverageReturn -177.465 Average/Iteration 132 Average/MaxReturn -154.986 Average/MinReturn -244.244 Average/NumEpisodes 80 Average/StdReturn 20.746 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6667 GaussianMLPPolicy/KLAfter 0.00183823 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.52964e-05 GaussianMLPPolicy/LossBefore 5.31971e-09 GaussianMLPPolicy/dLoss -4.52911e-05 Iteration 132 MetaTest/Average/AverageDiscountedReturn -171.971 MetaTest/Average/AverageReturn -171.971 MetaTest/Average/Iteration 132 MetaTest/Average/MaxReturn -154.53 MetaTest/Average/MinReturn -227.558 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.1948 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.971 MetaTest/__unnamed_task__/AverageReturn -171.971 MetaTest/__unnamed_task__/Iteration 132 MetaTest/__unnamed_task__/MaxReturn -154.53 MetaTest/__unnamed_task__/MinReturn -227.558 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.1948 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.256e+06 __unnamed_task__/AverageDiscountedReturn -74.7596 __unnamed_task__/AverageReturn -177.465 __unnamed_task__/Iteration 132 __unnamed_task__/MaxReturn -154.986 __unnamed_task__/MinReturn -244.244 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.746 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 03:40:43 | [maml_trainer] epoch #133 | Sampling for adapation and meta-testing... 2025-04-03 03:41:55 | [maml_trainer] epoch #133 | Finished meta-testing... 2025-04-03 03:41:55 | [maml_trainer] epoch #133 | Saving snapshot... 2025-04-03 03:42:17 | [maml_trainer] epoch #133 | Saved 2025-04-03 03:42:17 | [maml_trainer] epoch #133 | Time 50815.27 s 2025-04-03 03:42:17 | [maml_trainer] epoch #133 | EpochTime 386.04 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.2001 Average/AverageReturn -174.443 Average/Iteration 133 Average/MaxReturn -151.281 Average/MinReturn -242.541 Average/NumEpisodes 80 Average/StdReturn 16.6489 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6686 GaussianMLPPolicy/KLAfter 0.00178409 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.46806e-05 GaussianMLPPolicy/LossBefore -4.79817e-09 GaussianMLPPolicy/dLoss 4.46758e-05 Iteration 133 MetaTest/Average/AverageDiscountedReturn -177.702 MetaTest/Average/AverageReturn -177.702 MetaTest/Average/Iteration 133 MetaTest/Average/MaxReturn -155.312 MetaTest/Average/MinReturn -234.521 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.6909 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.702 MetaTest/__unnamed_task__/AverageReturn -177.702 MetaTest/__unnamed_task__/Iteration 133 MetaTest/__unnamed_task__/MaxReturn -155.312 MetaTest/__unnamed_task__/MinReturn -234.521 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.6909 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.288e+06 __unnamed_task__/AverageDiscountedReturn -73.2001 __unnamed_task__/AverageReturn -174.443 __unnamed_task__/Iteration 133 __unnamed_task__/MaxReturn -151.281 __unnamed_task__/MinReturn -242.541 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.6489 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 03:47:08 | [maml_trainer] epoch #134 | Sampling for adapation and meta-testing... 2025-04-03 03:48:21 | [maml_trainer] epoch #134 | Finished meta-testing... 2025-04-03 03:48:21 | [maml_trainer] epoch #134 | Saving snapshot... 2025-04-03 03:48:44 | [maml_trainer] epoch #134 | Saved 2025-04-03 03:48:44 | [maml_trainer] epoch #134 | Time 51202.45 s 2025-04-03 03:48:44 | [maml_trainer] epoch #134 | EpochTime 387.18 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.2025 Average/AverageReturn -173.989 Average/Iteration 134 Average/MaxReturn -147.978 Average/MinReturn -235.511 Average/NumEpisodes 80 Average/StdReturn 16.0477 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6693 GaussianMLPPolicy/KLAfter 0.00211372 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.67534e-05 GaussianMLPPolicy/LossBefore -1.71363e-09 GaussianMLPPolicy/dLoss -3.67552e-05 Iteration 134 MetaTest/Average/AverageDiscountedReturn -172.935 MetaTest/Average/AverageReturn -172.935 MetaTest/Average/Iteration 134 MetaTest/Average/MaxReturn -158.188 MetaTest/Average/MinReturn -196.823 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.9924 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.935 MetaTest/__unnamed_task__/AverageReturn -172.935 MetaTest/__unnamed_task__/Iteration 134 MetaTest/__unnamed_task__/MaxReturn -158.188 MetaTest/__unnamed_task__/MinReturn -196.823 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.9924 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.32e+06 __unnamed_task__/AverageDiscountedReturn -73.2025 __unnamed_task__/AverageReturn -173.989 __unnamed_task__/Iteration 134 __unnamed_task__/MaxReturn -147.978 __unnamed_task__/MinReturn -235.511 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.0477 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 03:53:37 | [maml_trainer] epoch #135 | Sampling for adapation and meta-testing... 2025-04-03 03:54:49 | [maml_trainer] epoch #135 | Finished meta-testing... 2025-04-03 03:54:49 | [maml_trainer] epoch #135 | Saving snapshot... 2025-04-03 03:55:12 | [maml_trainer] epoch #135 | Saved 2025-04-03 03:55:12 | [maml_trainer] epoch #135 | Time 51590.53 s 2025-04-03 03:55:12 | [maml_trainer] epoch #135 | EpochTime 388.08 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.5556 Average/AverageReturn -177.48 Average/Iteration 135 Average/MaxReturn -154.487 Average/MinReturn -237.41 Average/NumEpisodes 80 Average/StdReturn 19.3708 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6689 GaussianMLPPolicy/KLAfter 0.00225238 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.91516e-05 GaussianMLPPolicy/LossBefore 4.38094e-09 GaussianMLPPolicy/dLoss 2.9156e-05 Iteration 135 MetaTest/Average/AverageDiscountedReturn -180.981 MetaTest/Average/AverageReturn -180.981 MetaTest/Average/Iteration 135 MetaTest/Average/MaxReturn -157.448 MetaTest/Average/MinReturn -240.322 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.8187 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -180.981 MetaTest/__unnamed_task__/AverageReturn -180.981 MetaTest/__unnamed_task__/Iteration 135 MetaTest/__unnamed_task__/MaxReturn -157.448 MetaTest/__unnamed_task__/MinReturn -240.322 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.8187 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.352e+06 __unnamed_task__/AverageDiscountedReturn -74.5556 __unnamed_task__/AverageReturn -177.48 __unnamed_task__/Iteration 135 __unnamed_task__/MaxReturn -154.487 __unnamed_task__/MinReturn -237.41 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.3708 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 04:00:06 | [maml_trainer] epoch #136 | Sampling for adapation and meta-testing... 2025-04-03 04:01:19 | [maml_trainer] epoch #136 | Finished meta-testing... 2025-04-03 04:01:19 | [maml_trainer] epoch #136 | Saving snapshot... 2025-04-03 04:01:42 | [maml_trainer] epoch #136 | Saved 2025-04-03 04:01:42 | [maml_trainer] epoch #136 | Time 51980.41 s 2025-04-03 04:01:42 | [maml_trainer] epoch #136 | EpochTime 389.88 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.2992 Average/AverageReturn -174.209 Average/Iteration 136 Average/MaxReturn -152.058 Average/MinReturn -239.275 Average/NumEpisodes 80 Average/StdReturn 15.4918 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6652 GaussianMLPPolicy/KLAfter 0.00270544 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.14834e-05 GaussianMLPPolicy/LossBefore 3.65078e-09 GaussianMLPPolicy/dLoss -4.14797e-05 Iteration 136 MetaTest/Average/AverageDiscountedReturn -175.039 MetaTest/Average/AverageReturn -175.039 MetaTest/Average/Iteration 136 MetaTest/Average/MaxReturn -156.982 MetaTest/Average/MinReturn -201.997 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.3568 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.039 MetaTest/__unnamed_task__/AverageReturn -175.039 MetaTest/__unnamed_task__/Iteration 136 MetaTest/__unnamed_task__/MaxReturn -156.982 MetaTest/__unnamed_task__/MinReturn -201.997 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.3568 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.384e+06 __unnamed_task__/AverageDiscountedReturn -73.2992 __unnamed_task__/AverageReturn -174.209 __unnamed_task__/Iteration 136 __unnamed_task__/MaxReturn -152.058 __unnamed_task__/MinReturn -239.275 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.4918 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 04:06:35 | [maml_trainer] epoch #137 | Sampling for adapation and meta-testing... 2025-04-03 04:07:49 | [maml_trainer] epoch #137 | Finished meta-testing... 2025-04-03 04:07:49 | [maml_trainer] epoch #137 | Saving snapshot... 2025-04-03 04:08:11 | [maml_trainer] epoch #137 | Saved 2025-04-03 04:08:11 | [maml_trainer] epoch #137 | Time 52369.42 s 2025-04-03 04:08:11 | [maml_trainer] epoch #137 | EpochTime 389.01 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -75.4072 Average/AverageReturn -179.247 Average/Iteration 137 Average/MaxReturn -155.465 Average/MinReturn -240.59 Average/NumEpisodes 80 Average/StdReturn 19.3157 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6619 GaussianMLPPolicy/KLAfter 0.00259683 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.39312e-06 GaussianMLPPolicy/LossBefore 3.06964e-09 GaussianMLPPolicy/dLoss -8.39005e-06 Iteration 137 MetaTest/Average/AverageDiscountedReturn -176.027 MetaTest/Average/AverageReturn -176.027 MetaTest/Average/Iteration 137 MetaTest/Average/MaxReturn -155.221 MetaTest/Average/MinReturn -232.345 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.4928 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.027 MetaTest/__unnamed_task__/AverageReturn -176.027 MetaTest/__unnamed_task__/Iteration 137 MetaTest/__unnamed_task__/MaxReturn -155.221 MetaTest/__unnamed_task__/MinReturn -232.345 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.4928 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.416e+06 __unnamed_task__/AverageDiscountedReturn -75.4072 __unnamed_task__/AverageReturn -179.247 __unnamed_task__/Iteration 137 __unnamed_task__/MaxReturn -155.465 __unnamed_task__/MinReturn -240.59 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.3157 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 04:13:02 | [maml_trainer] epoch #138 | Sampling for adapation and meta-testing... 2025-04-03 04:14:15 | [maml_trainer] epoch #138 | Finished meta-testing... 2025-04-03 04:14:15 | [maml_trainer] epoch #138 | Saving snapshot... 2025-04-03 04:14:38 | [maml_trainer] epoch #138 | Saved 2025-04-03 04:14:38 | [maml_trainer] epoch #138 | Time 52756.66 s 2025-04-03 04:14:38 | [maml_trainer] epoch #138 | EpochTime 387.23 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.4801 Average/AverageReturn -177.14 Average/Iteration 138 Average/MaxReturn -157.142 Average/MinReturn -242.864 Average/NumEpisodes 80 Average/StdReturn 19.1679 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6564 GaussianMLPPolicy/KLAfter 0.00256376 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.45661e-05 GaussianMLPPolicy/LossBefore 4.61936e-10 GaussianMLPPolicy/dLoss -5.45656e-05 Iteration 138 MetaTest/Average/AverageDiscountedReturn -180.034 MetaTest/Average/AverageReturn -180.034 MetaTest/Average/Iteration 138 MetaTest/Average/MaxReturn -158.123 MetaTest/Average/MinReturn -233.162 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.2312 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -180.034 MetaTest/__unnamed_task__/AverageReturn -180.034 MetaTest/__unnamed_task__/Iteration 138 MetaTest/__unnamed_task__/MaxReturn -158.123 MetaTest/__unnamed_task__/MinReturn -233.162 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.2312 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.448e+06 __unnamed_task__/AverageDiscountedReturn -74.4801 __unnamed_task__/AverageReturn -177.14 __unnamed_task__/Iteration 138 __unnamed_task__/MaxReturn -157.142 __unnamed_task__/MinReturn -242.864 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.1679 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 04:19:32 | [maml_trainer] epoch #139 | Sampling for adapation and meta-testing... 2025-04-03 04:20:45 | [maml_trainer] epoch #139 | Finished meta-testing... 2025-04-03 04:20:45 | [maml_trainer] epoch #139 | Saving snapshot... 2025-04-03 04:21:08 | [maml_trainer] epoch #139 | Saved 2025-04-03 04:21:08 | [maml_trainer] epoch #139 | Time 53146.82 s 2025-04-03 04:21:08 | [maml_trainer] epoch #139 | EpochTime 390.16 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.9671 Average/AverageReturn -176.352 Average/Iteration 139 Average/MaxReturn -148.725 Average/MinReturn -288.673 Average/NumEpisodes 80 Average/StdReturn 18.514 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6496 GaussianMLPPolicy/KLAfter 0.00233454 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.69884e-05 GaussianMLPPolicy/LossBefore -3.12924e-09 GaussianMLPPolicy/dLoss 1.69853e-05 Iteration 139 MetaTest/Average/AverageDiscountedReturn -179.101 MetaTest/Average/AverageReturn -179.101 MetaTest/Average/Iteration 139 MetaTest/Average/MaxReturn -158.98 MetaTest/Average/MinReturn -248.853 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.937 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -179.101 MetaTest/__unnamed_task__/AverageReturn -179.101 MetaTest/__unnamed_task__/Iteration 139 MetaTest/__unnamed_task__/MaxReturn -158.98 MetaTest/__unnamed_task__/MinReturn -248.853 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.937 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.48e+06 __unnamed_task__/AverageDiscountedReturn -74.9671 __unnamed_task__/AverageReturn -176.352 __unnamed_task__/Iteration 139 __unnamed_task__/MaxReturn -148.725 __unnamed_task__/MinReturn -288.673 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.514 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 04:26:03 | [maml_trainer] epoch #140 | Sampling for adapation and meta-testing... 2025-04-03 04:27:18 | [maml_trainer] epoch #140 | Finished meta-testing... 2025-04-03 04:27:18 | [maml_trainer] epoch #140 | Saving snapshot... 2025-04-03 04:27:41 | [maml_trainer] epoch #140 | Saved 2025-04-03 04:27:41 | [maml_trainer] epoch #140 | Time 53540.00 s 2025-04-03 04:27:41 | [maml_trainer] epoch #140 | EpochTime 393.17 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.4424 Average/AverageReturn -177.22 Average/Iteration 140 Average/MaxReturn -156.053 Average/MinReturn -239.506 Average/NumEpisodes 80 Average/StdReturn 18.0228 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6428 GaussianMLPPolicy/KLAfter 0.00183634 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.34664e-05 GaussianMLPPolicy/LossBefore -3.8296e-09 GaussianMLPPolicy/dLoss 3.34626e-05 Iteration 140 MetaTest/Average/AverageDiscountedReturn -175.232 MetaTest/Average/AverageReturn -175.232 MetaTest/Average/Iteration 140 MetaTest/Average/MaxReturn -158.846 MetaTest/Average/MinReturn -195.128 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.2853 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.232 MetaTest/__unnamed_task__/AverageReturn -175.232 MetaTest/__unnamed_task__/Iteration 140 MetaTest/__unnamed_task__/MaxReturn -158.846 MetaTest/__unnamed_task__/MinReturn -195.128 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.2853 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.512e+06 __unnamed_task__/AverageDiscountedReturn -74.4424 __unnamed_task__/AverageReturn -177.22 __unnamed_task__/Iteration 140 __unnamed_task__/MaxReturn -156.053 __unnamed_task__/MinReturn -239.506 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.0228 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 04:32:36 | [maml_trainer] epoch #141 | Sampling for adapation and meta-testing... 2025-04-03 04:33:49 | [maml_trainer] epoch #141 | Finished meta-testing... 2025-04-03 04:33:49 | [maml_trainer] epoch #141 | Saving snapshot... 2025-04-03 04:34:11 | [maml_trainer] epoch #141 | Saved 2025-04-03 04:34:11 | [maml_trainer] epoch #141 | Time 53929.80 s 2025-04-03 04:34:11 | [maml_trainer] epoch #141 | EpochTime 389.80 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.4869 Average/AverageReturn -176.996 Average/Iteration 141 Average/MaxReturn -152.867 Average/MinReturn -237.025 Average/NumEpisodes 80 Average/StdReturn 20.1881 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6373 GaussianMLPPolicy/KLAfter 0.00216882 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.48118e-05 GaussianMLPPolicy/LossBefore 3.8743e-10 GaussianMLPPolicy/dLoss 1.48122e-05 Iteration 141 MetaTest/Average/AverageDiscountedReturn -171.301 MetaTest/Average/AverageReturn -171.301 MetaTest/Average/Iteration 141 MetaTest/Average/MaxReturn -140.105 MetaTest/Average/MinReturn -193.558 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.366 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.301 MetaTest/__unnamed_task__/AverageReturn -171.301 MetaTest/__unnamed_task__/Iteration 141 MetaTest/__unnamed_task__/MaxReturn -140.105 MetaTest/__unnamed_task__/MinReturn -193.558 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.366 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.544e+06 __unnamed_task__/AverageDiscountedReturn -74.4869 __unnamed_task__/AverageReturn -176.996 __unnamed_task__/Iteration 141 __unnamed_task__/MaxReturn -152.867 __unnamed_task__/MinReturn -237.025 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.1881 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 04:39:03 | [maml_trainer] epoch #142 | Sampling for adapation and meta-testing... 2025-04-03 04:40:17 | [maml_trainer] epoch #142 | Finished meta-testing... 2025-04-03 04:40:17 | [maml_trainer] epoch #142 | Saving snapshot... 2025-04-03 04:40:39 | [maml_trainer] epoch #142 | Saved 2025-04-03 04:40:39 | [maml_trainer] epoch #142 | Time 54318.11 s 2025-04-03 04:40:39 | [maml_trainer] epoch #142 | EpochTime 388.31 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.7287 Average/AverageReturn -172.582 Average/Iteration 142 Average/MaxReturn -154.948 Average/MinReturn -234.632 Average/NumEpisodes 80 Average/StdReturn 13.3491 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6313 GaussianMLPPolicy/KLAfter 0.00211673 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.89971e-06 GaussianMLPPolicy/LossBefore 2.16067e-09 GaussianMLPPolicy/dLoss -3.89755e-06 Iteration 142 MetaTest/Average/AverageDiscountedReturn -174.021 MetaTest/Average/AverageReturn -174.021 MetaTest/Average/Iteration 142 MetaTest/Average/MaxReturn -161.758 MetaTest/Average/MinReturn -235.492 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.3197 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.021 MetaTest/__unnamed_task__/AverageReturn -174.021 MetaTest/__unnamed_task__/Iteration 142 MetaTest/__unnamed_task__/MaxReturn -161.758 MetaTest/__unnamed_task__/MinReturn -235.492 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.3197 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.576e+06 __unnamed_task__/AverageDiscountedReturn -72.7287 __unnamed_task__/AverageReturn -172.582 __unnamed_task__/Iteration 142 __unnamed_task__/MaxReturn -154.948 __unnamed_task__/MinReturn -234.632 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.3491 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 04:45:34 | [maml_trainer] epoch #143 | Sampling for adapation and meta-testing... 2025-04-03 04:46:47 | [maml_trainer] epoch #143 | Finished meta-testing... 2025-04-03 04:46:47 | [maml_trainer] epoch #143 | Saving snapshot... 2025-04-03 04:47:10 | [maml_trainer] epoch #143 | Saved 2025-04-03 04:47:10 | [maml_trainer] epoch #143 | Time 54708.81 s 2025-04-03 04:47:10 | [maml_trainer] epoch #143 | EpochTime 390.69 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -75.5849 Average/AverageReturn -178.783 Average/Iteration 143 Average/MaxReturn -152.715 Average/MinReturn -259.527 Average/NumEpisodes 80 Average/StdReturn 20.6051 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6249 GaussianMLPPolicy/KLAfter 0.00261572 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.18342e-06 GaussianMLPPolicy/LossBefore 3.15905e-09 GaussianMLPPolicy/dLoss 3.18658e-06 Iteration 143 MetaTest/Average/AverageDiscountedReturn -177.338 MetaTest/Average/AverageReturn -177.338 MetaTest/Average/Iteration 143 MetaTest/Average/MaxReturn -155.606 MetaTest/Average/MinReturn -250.469 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.1887 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.338 MetaTest/__unnamed_task__/AverageReturn -177.338 MetaTest/__unnamed_task__/Iteration 143 MetaTest/__unnamed_task__/MaxReturn -155.606 MetaTest/__unnamed_task__/MinReturn -250.469 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.1887 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.608e+06 __unnamed_task__/AverageDiscountedReturn -75.5849 __unnamed_task__/AverageReturn -178.783 __unnamed_task__/Iteration 143 __unnamed_task__/MaxReturn -152.715 __unnamed_task__/MinReturn -259.527 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.6051 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 04:52:06 | [maml_trainer] epoch #144 | Sampling for adapation and meta-testing... 2025-04-03 04:53:19 | [maml_trainer] epoch #144 | Finished meta-testing... 2025-04-03 04:53:19 | [maml_trainer] epoch #144 | Saving snapshot... 2025-04-03 04:53:42 | [maml_trainer] epoch #144 | Saved 2025-04-03 04:53:42 | [maml_trainer] epoch #144 | Time 55100.82 s 2025-04-03 04:53:42 | [maml_trainer] epoch #144 | EpochTime 392.01 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -75.0153 Average/AverageReturn -177.808 Average/Iteration 144 Average/MaxReturn -155.259 Average/MinReturn -301.834 Average/NumEpisodes 80 Average/StdReturn 21.6625 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6189 GaussianMLPPolicy/KLAfter 0.0022756 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.10432e-06 GaussianMLPPolicy/LossBefore 5.0813e-09 GaussianMLPPolicy/dLoss 8.10941e-06 Iteration 144 MetaTest/Average/AverageDiscountedReturn -183.271 MetaTest/Average/AverageReturn -183.271 MetaTest/Average/Iteration 144 MetaTest/Average/MaxReturn -152.119 MetaTest/Average/MinReturn -226.058 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.7415 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -183.271 MetaTest/__unnamed_task__/AverageReturn -183.271 MetaTest/__unnamed_task__/Iteration 144 MetaTest/__unnamed_task__/MaxReturn -152.119 MetaTest/__unnamed_task__/MinReturn -226.058 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.7415 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.64e+06 __unnamed_task__/AverageDiscountedReturn -75.0153 __unnamed_task__/AverageReturn -177.808 __unnamed_task__/Iteration 144 __unnamed_task__/MaxReturn -155.259 __unnamed_task__/MinReturn -301.834 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.6625 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 04:58:40 | [maml_trainer] epoch #145 | Sampling for adapation and meta-testing... 2025-04-03 04:59:53 | [maml_trainer] epoch #145 | Finished meta-testing... 2025-04-03 04:59:53 | [maml_trainer] epoch #145 | Saving snapshot... 2025-04-03 05:00:16 | [maml_trainer] epoch #145 | Saved 2025-04-03 05:00:16 | [maml_trainer] epoch #145 | Time 55494.68 s 2025-04-03 05:00:16 | [maml_trainer] epoch #145 | EpochTime 393.85 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -75.6043 Average/AverageReturn -179.288 Average/Iteration 145 Average/MaxReturn -158.914 Average/MinReturn -324.292 Average/NumEpisodes 80 Average/StdReturn 22.9105 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6107 GaussianMLPPolicy/KLAfter 0.00225173 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.73369e-07 GaussianMLPPolicy/LossBefore 6.16908e-09 GaussianMLPPolicy/dLoss -6.67199e-07 Iteration 145 MetaTest/Average/AverageDiscountedReturn -177.807 MetaTest/Average/AverageReturn -177.807 MetaTest/Average/Iteration 145 MetaTest/Average/MaxReturn -159.263 MetaTest/Average/MinReturn -270.886 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.2105 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.807 MetaTest/__unnamed_task__/AverageReturn -177.807 MetaTest/__unnamed_task__/Iteration 145 MetaTest/__unnamed_task__/MaxReturn -159.263 MetaTest/__unnamed_task__/MinReturn -270.886 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.2105 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.672e+06 __unnamed_task__/AverageDiscountedReturn -75.6043 __unnamed_task__/AverageReturn -179.288 __unnamed_task__/Iteration 145 __unnamed_task__/MaxReturn -158.914 __unnamed_task__/MinReturn -324.292 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.9105 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 05:05:11 | [maml_trainer] epoch #146 | Sampling for adapation and meta-testing... 2025-04-03 05:06:22 | [maml_trainer] epoch #146 | Finished meta-testing... 2025-04-03 05:06:22 | [maml_trainer] epoch #146 | Saving snapshot... 2025-04-03 05:06:44 | [maml_trainer] epoch #146 | Saved 2025-04-03 05:06:44 | [maml_trainer] epoch #146 | Time 55882.83 s 2025-04-03 05:06:44 | [maml_trainer] epoch #146 | EpochTime 388.15 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.8754 Average/AverageReturn -175.796 Average/Iteration 146 Average/MaxReturn -153.744 Average/MinReturn -236.674 Average/NumEpisodes 80 Average/StdReturn 17.9286 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.6024 GaussianMLPPolicy/KLAfter 0.00210442 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.47727e-05 GaussianMLPPolicy/LossBefore 3.09944e-09 GaussianMLPPolicy/dLoss -1.47696e-05 Iteration 146 MetaTest/Average/AverageDiscountedReturn -173.77 MetaTest/Average/AverageReturn -173.77 MetaTest/Average/Iteration 146 MetaTest/Average/MaxReturn -158.152 MetaTest/Average/MinReturn -226.989 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.3486 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.77 MetaTest/__unnamed_task__/AverageReturn -173.77 MetaTest/__unnamed_task__/Iteration 146 MetaTest/__unnamed_task__/MaxReturn -158.152 MetaTest/__unnamed_task__/MinReturn -226.989 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.3486 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.704e+06 __unnamed_task__/AverageDiscountedReturn -73.8754 __unnamed_task__/AverageReturn -175.796 __unnamed_task__/Iteration 146 __unnamed_task__/MaxReturn -153.744 __unnamed_task__/MinReturn -236.674 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.9286 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 05:11:36 | [maml_trainer] epoch #147 | Sampling for adapation and meta-testing... 2025-04-03 05:12:49 | [maml_trainer] epoch #147 | Finished meta-testing... 2025-04-03 05:12:49 | [maml_trainer] epoch #147 | Saving snapshot... 2025-04-03 05:13:12 | [maml_trainer] epoch #147 | Saved 2025-04-03 05:13:12 | [maml_trainer] epoch #147 | Time 56271.08 s 2025-04-03 05:13:12 | [maml_trainer] epoch #147 | EpochTime 388.25 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.8307 Average/AverageReturn -177.836 Average/Iteration 147 Average/MaxReturn -153.028 Average/MinReturn -236.819 Average/NumEpisodes 80 Average/StdReturn 19.6348 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5942 GaussianMLPPolicy/KLAfter 0.0023999 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.20605e-05 GaussianMLPPolicy/LossBefore -1.01179e-08 GaussianMLPPolicy/dLoss -1.20706e-05 Iteration 147 MetaTest/Average/AverageDiscountedReturn -176.718 MetaTest/Average/AverageReturn -176.718 MetaTest/Average/Iteration 147 MetaTest/Average/MaxReturn -153.852 MetaTest/Average/MinReturn -242.058 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.0627 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.718 MetaTest/__unnamed_task__/AverageReturn -176.718 MetaTest/__unnamed_task__/Iteration 147 MetaTest/__unnamed_task__/MaxReturn -153.852 MetaTest/__unnamed_task__/MinReturn -242.058 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.0627 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.736e+06 __unnamed_task__/AverageDiscountedReturn -74.8307 __unnamed_task__/AverageReturn -177.836 __unnamed_task__/Iteration 147 __unnamed_task__/MaxReturn -153.028 __unnamed_task__/MinReturn -236.819 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.6348 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 05:18:11 | [maml_trainer] epoch #148 | Sampling for adapation and meta-testing... 2025-04-03 05:19:24 | [maml_trainer] epoch #148 | Finished meta-testing... 2025-04-03 05:19:24 | [maml_trainer] epoch #148 | Saving snapshot... 2025-04-03 05:19:47 | [maml_trainer] epoch #148 | Saved 2025-04-03 05:19:47 | [maml_trainer] epoch #148 | Time 56665.47 s 2025-04-03 05:19:47 | [maml_trainer] epoch #148 | EpochTime 394.38 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.3513 Average/AverageReturn -174.418 Average/Iteration 148 Average/MaxReturn -155.047 Average/MinReturn -254.865 Average/NumEpisodes 80 Average/StdReturn 17.2695 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5876 GaussianMLPPolicy/KLAfter 0.00249329 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.11175e-05 GaussianMLPPolicy/LossBefore 7.25687e-09 GaussianMLPPolicy/dLoss 2.11248e-05 Iteration 148 MetaTest/Average/AverageDiscountedReturn -178.345 MetaTest/Average/AverageReturn -178.345 MetaTest/Average/Iteration 148 MetaTest/Average/MaxReturn -153.854 MetaTest/Average/MinReturn -232.372 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.6602 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -178.345 MetaTest/__unnamed_task__/AverageReturn -178.345 MetaTest/__unnamed_task__/Iteration 148 MetaTest/__unnamed_task__/MaxReturn -153.854 MetaTest/__unnamed_task__/MinReturn -232.372 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.6602 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.768e+06 __unnamed_task__/AverageDiscountedReturn -73.3513 __unnamed_task__/AverageReturn -174.418 __unnamed_task__/Iteration 148 __unnamed_task__/MaxReturn -155.047 __unnamed_task__/MinReturn -254.865 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.2695 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 05:24:42 | [maml_trainer] epoch #149 | Sampling for adapation and meta-testing... 2025-04-03 05:25:55 | [maml_trainer] epoch #149 | Finished meta-testing... 2025-04-03 05:25:55 | [maml_trainer] epoch #149 | Saving snapshot... 2025-04-03 05:26:18 | [maml_trainer] epoch #149 | Saved 2025-04-03 05:26:18 | [maml_trainer] epoch #149 | Time 57056.55 s 2025-04-03 05:26:18 | [maml_trainer] epoch #149 | EpochTime 391.08 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.2405 Average/AverageReturn -176.925 Average/Iteration 149 Average/MaxReturn -151.582 Average/MinReturn -237.732 Average/NumEpisodes 80 Average/StdReturn 16.561 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5816 GaussianMLPPolicy/KLAfter 0.0029615 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.47311e-06 GaussianMLPPolicy/LossBefore 4.85778e-09 GaussianMLPPolicy/dLoss -7.46825e-06 Iteration 149 MetaTest/Average/AverageDiscountedReturn -180.804 MetaTest/Average/AverageReturn -180.804 MetaTest/Average/Iteration 149 MetaTest/Average/MaxReturn -162.947 MetaTest/Average/MinReturn -249.872 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.5287 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -180.804 MetaTest/__unnamed_task__/AverageReturn -180.804 MetaTest/__unnamed_task__/Iteration 149 MetaTest/__unnamed_task__/MaxReturn -162.947 MetaTest/__unnamed_task__/MinReturn -249.872 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.5287 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.8e+06 __unnamed_task__/AverageDiscountedReturn -74.2405 __unnamed_task__/AverageReturn -176.925 __unnamed_task__/Iteration 149 __unnamed_task__/MaxReturn -151.582 __unnamed_task__/MinReturn -237.732 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.561 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 05:31:13 | [maml_trainer] epoch #150 | Sampling for adapation and meta-testing... 2025-04-03 05:32:26 | [maml_trainer] epoch #150 | Finished meta-testing... 2025-04-03 05:32:26 | [maml_trainer] epoch #150 | Saving snapshot... 2025-04-03 05:32:48 | [maml_trainer] epoch #150 | Saved 2025-04-03 05:32:48 | [maml_trainer] epoch #150 | Time 57446.73 s 2025-04-03 05:32:48 | [maml_trainer] epoch #150 | EpochTime 390.17 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.2022 Average/AverageReturn -176.888 Average/Iteration 150 Average/MaxReturn -156.09 Average/MinReturn -242.559 Average/NumEpisodes 80 Average/StdReturn 15.8653 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5766 GaussianMLPPolicy/KLAfter 0.003296 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.23092e-06 GaussianMLPPolicy/LossBefore 7.30157e-10 GaussianMLPPolicy/dLoss -4.23019e-06 Iteration 150 MetaTest/Average/AverageDiscountedReturn -166.74 MetaTest/Average/AverageReturn -166.74 MetaTest/Average/Iteration 150 MetaTest/Average/MaxReturn -152.876 MetaTest/Average/MinReturn -225.111 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.3813 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.74 MetaTest/__unnamed_task__/AverageReturn -166.74 MetaTest/__unnamed_task__/Iteration 150 MetaTest/__unnamed_task__/MaxReturn -152.876 MetaTest/__unnamed_task__/MinReturn -225.111 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.3813 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.832e+06 __unnamed_task__/AverageDiscountedReturn -74.2022 __unnamed_task__/AverageReturn -176.888 __unnamed_task__/Iteration 150 __unnamed_task__/MaxReturn -156.09 __unnamed_task__/MinReturn -242.559 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.8653 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 05:37:42 | [maml_trainer] epoch #151 | Sampling for adapation and meta-testing... 2025-04-03 05:38:55 | [maml_trainer] epoch #151 | Finished meta-testing... 2025-04-03 05:38:55 | [maml_trainer] epoch #151 | Saving snapshot... 2025-04-03 05:39:18 | [maml_trainer] epoch #151 | Saved 2025-04-03 05:39:18 | [maml_trainer] epoch #151 | Time 57836.62 s 2025-04-03 05:39:18 | [maml_trainer] epoch #151 | EpochTime 389.90 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.5636 Average/AverageReturn -177.246 Average/Iteration 151 Average/MaxReturn -149.956 Average/MinReturn -256.437 Average/NumEpisodes 80 Average/StdReturn 19.378 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.571 GaussianMLPPolicy/KLAfter 0.00282915 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.00839e-05 GaussianMLPPolicy/LossBefore -8.19564e-10 GaussianMLPPolicy/dLoss -2.00848e-05 Iteration 151 MetaTest/Average/AverageDiscountedReturn -178.522 MetaTest/Average/AverageReturn -178.522 MetaTest/Average/Iteration 151 MetaTest/Average/MaxReturn -154.925 MetaTest/Average/MinReturn -227.768 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.3114 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -178.522 MetaTest/__unnamed_task__/AverageReturn -178.522 MetaTest/__unnamed_task__/Iteration 151 MetaTest/__unnamed_task__/MaxReturn -154.925 MetaTest/__unnamed_task__/MinReturn -227.768 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.3114 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.864e+06 __unnamed_task__/AverageDiscountedReturn -74.5636 __unnamed_task__/AverageReturn -177.246 __unnamed_task__/Iteration 151 __unnamed_task__/MaxReturn -149.956 __unnamed_task__/MinReturn -256.437 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.378 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 05:44:13 | [maml_trainer] epoch #152 | Sampling for adapation and meta-testing... 2025-04-03 05:45:25 | [maml_trainer] epoch #152 | Finished meta-testing... 2025-04-03 05:45:25 | [maml_trainer] epoch #152 | Saving snapshot... 2025-04-03 05:45:49 | [maml_trainer] epoch #152 | Saved 2025-04-03 05:45:49 | [maml_trainer] epoch #152 | Time 58227.13 s 2025-04-03 05:45:49 | [maml_trainer] epoch #152 | EpochTime 390.50 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.0755 Average/AverageReturn -176.149 Average/Iteration 152 Average/MaxReturn -150.73 Average/MinReturn -268.107 Average/NumEpisodes 80 Average/StdReturn 17.9262 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5677 GaussianMLPPolicy/KLAfter 0.00275873 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.57226e-05 GaussianMLPPolicy/LossBefore -5.78165e-09 GaussianMLPPolicy/dLoss 4.57168e-05 Iteration 152 MetaTest/Average/AverageDiscountedReturn -177.106 MetaTest/Average/AverageReturn -177.106 MetaTest/Average/Iteration 152 MetaTest/Average/MaxReturn -160.558 MetaTest/Average/MinReturn -241.371 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.6903 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.106 MetaTest/__unnamed_task__/AverageReturn -177.106 MetaTest/__unnamed_task__/Iteration 152 MetaTest/__unnamed_task__/MaxReturn -160.558 MetaTest/__unnamed_task__/MinReturn -241.371 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.6903 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.896e+06 __unnamed_task__/AverageDiscountedReturn -74.0755 __unnamed_task__/AverageReturn -176.149 __unnamed_task__/Iteration 152 __unnamed_task__/MaxReturn -150.73 __unnamed_task__/MinReturn -268.107 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.9262 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 05:50:45 | [maml_trainer] epoch #153 | Sampling for adapation and meta-testing... 2025-04-03 05:51:58 | [maml_trainer] epoch #153 | Finished meta-testing... 2025-04-03 05:51:58 | [maml_trainer] epoch #153 | Saving snapshot... 2025-04-03 05:52:21 | [maml_trainer] epoch #153 | Saved 2025-04-03 05:52:21 | [maml_trainer] epoch #153 | Time 58619.69 s 2025-04-03 05:52:21 | [maml_trainer] epoch #153 | EpochTime 392.55 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.8495 Average/AverageReturn -172.798 Average/Iteration 153 Average/MaxReturn -156.923 Average/MinReturn -254.717 Average/NumEpisodes 80 Average/StdReturn 15.112 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5656 GaussianMLPPolicy/KLAfter 0.0023256 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.22256e-05 GaussianMLPPolicy/LossBefore 4.12762e-09 GaussianMLPPolicy/dLoss 2.22297e-05 Iteration 153 MetaTest/Average/AverageDiscountedReturn -174.72 MetaTest/Average/AverageReturn -174.72 MetaTest/Average/Iteration 153 MetaTest/Average/MaxReturn -158.125 MetaTest/Average/MinReturn -230.394 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.4099 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.72 MetaTest/__unnamed_task__/AverageReturn -174.72 MetaTest/__unnamed_task__/Iteration 153 MetaTest/__unnamed_task__/MaxReturn -158.125 MetaTest/__unnamed_task__/MinReturn -230.394 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.4099 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.928e+06 __unnamed_task__/AverageDiscountedReturn -72.8495 __unnamed_task__/AverageReturn -172.798 __unnamed_task__/Iteration 153 __unnamed_task__/MaxReturn -156.923 __unnamed_task__/MinReturn -254.717 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.112 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 05:57:16 | [maml_trainer] epoch #154 | Sampling for adapation and meta-testing... 2025-04-03 05:58:29 | [maml_trainer] epoch #154 | Finished meta-testing... 2025-04-03 05:58:29 | [maml_trainer] epoch #154 | Saving snapshot... 2025-04-03 05:58:50 | [maml_trainer] epoch #154 | Saved 2025-04-03 05:58:50 | [maml_trainer] epoch #154 | Time 59008.88 s 2025-04-03 05:58:50 | [maml_trainer] epoch #154 | EpochTime 389.19 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.6608 Average/AverageReturn -175.273 Average/Iteration 154 Average/MaxReturn -154.004 Average/MinReturn -231.142 Average/NumEpisodes 80 Average/StdReturn 17.7522 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5616 GaussianMLPPolicy/KLAfter 0.00212179 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.16636e-05 GaussianMLPPolicy/LossBefore 7.15256e-10 GaussianMLPPolicy/dLoss 2.16643e-05 Iteration 154 MetaTest/Average/AverageDiscountedReturn -172.08 MetaTest/Average/AverageReturn -172.08 MetaTest/Average/Iteration 154 MetaTest/Average/MaxReturn -154.29 MetaTest/Average/MinReturn -242.581 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.0281 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.08 MetaTest/__unnamed_task__/AverageReturn -172.08 MetaTest/__unnamed_task__/Iteration 154 MetaTest/__unnamed_task__/MaxReturn -154.29 MetaTest/__unnamed_task__/MinReturn -242.581 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.0281 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.96e+06 __unnamed_task__/AverageDiscountedReturn -73.6608 __unnamed_task__/AverageReturn -175.273 __unnamed_task__/Iteration 154 __unnamed_task__/MaxReturn -154.004 __unnamed_task__/MinReturn -231.142 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.7522 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 06:03:42 | [maml_trainer] epoch #155 | Sampling for adapation and meta-testing... 2025-04-03 06:04:56 | [maml_trainer] epoch #155 | Finished meta-testing... 2025-04-03 06:04:56 | [maml_trainer] epoch #155 | Saving snapshot... 2025-04-03 06:05:19 | [maml_trainer] epoch #155 | Saved 2025-04-03 06:05:19 | [maml_trainer] epoch #155 | Time 59397.53 s 2025-04-03 06:05:19 | [maml_trainer] epoch #155 | EpochTime 388.64 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -75.3121 Average/AverageReturn -178.898 Average/Iteration 155 Average/MaxReturn -155.531 Average/MinReturn -240.477 Average/NumEpisodes 80 Average/StdReturn 21.9092 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5587 GaussianMLPPolicy/KLAfter 0.001941 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.59447e-05 GaussianMLPPolicy/LossBefore -4.52995e-09 GaussianMLPPolicy/dLoss 1.59402e-05 Iteration 155 MetaTest/Average/AverageDiscountedReturn -170.718 MetaTest/Average/AverageReturn -170.718 MetaTest/Average/Iteration 155 MetaTest/Average/MaxReturn -156.411 MetaTest/Average/MinReturn -210.04 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.2295 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.718 MetaTest/__unnamed_task__/AverageReturn -170.718 MetaTest/__unnamed_task__/Iteration 155 MetaTest/__unnamed_task__/MaxReturn -156.411 MetaTest/__unnamed_task__/MinReturn -210.04 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.2295 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.992e+06 __unnamed_task__/AverageDiscountedReturn -75.3121 __unnamed_task__/AverageReturn -178.898 __unnamed_task__/Iteration 155 __unnamed_task__/MaxReturn -155.531 __unnamed_task__/MinReturn -240.477 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.9092 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 06:10:15 | [maml_trainer] epoch #156 | Sampling for adapation and meta-testing... 2025-04-03 06:11:28 | [maml_trainer] epoch #156 | Finished meta-testing... 2025-04-03 06:11:28 | [maml_trainer] epoch #156 | Saving snapshot... 2025-04-03 06:11:51 | [maml_trainer] epoch #156 | Saved 2025-04-03 06:11:51 | [maml_trainer] epoch #156 | Time 59790.10 s 2025-04-03 06:11:51 | [maml_trainer] epoch #156 | EpochTime 392.57 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -75.2845 Average/AverageReturn -178.263 Average/Iteration 156 Average/MaxReturn -154.244 Average/MinReturn -250.947 Average/NumEpisodes 80 Average/StdReturn 22.8426 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5555 GaussianMLPPolicy/KLAfter 0.00287195 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.22024e-05 GaussianMLPPolicy/LossBefore -5.23031e-09 GaussianMLPPolicy/dLoss -1.22076e-05 Iteration 156 MetaTest/Average/AverageDiscountedReturn -171.386 MetaTest/Average/AverageReturn -171.386 MetaTest/Average/Iteration 156 MetaTest/Average/MaxReturn -154.466 MetaTest/Average/MinReturn -194.188 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.6025 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.386 MetaTest/__unnamed_task__/AverageReturn -171.386 MetaTest/__unnamed_task__/Iteration 156 MetaTest/__unnamed_task__/MaxReturn -154.466 MetaTest/__unnamed_task__/MinReturn -194.188 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.6025 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.024e+06 __unnamed_task__/AverageDiscountedReturn -75.2845 __unnamed_task__/AverageReturn -178.263 __unnamed_task__/Iteration 156 __unnamed_task__/MaxReturn -154.244 __unnamed_task__/MinReturn -250.947 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.8426 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 06:16:49 | [maml_trainer] epoch #157 | Sampling for adapation and meta-testing... 2025-04-03 06:18:02 | [maml_trainer] epoch #157 | Finished meta-testing... 2025-04-03 06:18:02 | [maml_trainer] epoch #157 | Saving snapshot... 2025-04-03 06:18:25 | [maml_trainer] epoch #157 | Saved 2025-04-03 06:18:25 | [maml_trainer] epoch #157 | Time 60184.09 s 2025-04-03 06:18:25 | [maml_trainer] epoch #157 | EpochTime 393.98 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -75.4845 Average/AverageReturn -176.869 Average/Iteration 157 Average/MaxReturn -153.471 Average/MinReturn -378.738 Average/NumEpisodes 80 Average/StdReturn 26.0672 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5532 GaussianMLPPolicy/KLAfter 0.00186374 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.1491e-05 GaussianMLPPolicy/LossBefore -2.5928e-09 GaussianMLPPolicy/dLoss -1.14936e-05 Iteration 157 MetaTest/Average/AverageDiscountedReturn -174.171 MetaTest/Average/AverageReturn -174.171 MetaTest/Average/Iteration 157 MetaTest/Average/MaxReturn -157.255 MetaTest/Average/MinReturn -230.03 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.3599 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.171 MetaTest/__unnamed_task__/AverageReturn -174.171 MetaTest/__unnamed_task__/Iteration 157 MetaTest/__unnamed_task__/MaxReturn -157.255 MetaTest/__unnamed_task__/MinReturn -230.03 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.3599 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.056e+06 __unnamed_task__/AverageDiscountedReturn -75.4845 __unnamed_task__/AverageReturn -176.869 __unnamed_task__/Iteration 157 __unnamed_task__/MaxReturn -153.471 __unnamed_task__/MinReturn -378.738 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 26.0672 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 06:23:24 | [maml_trainer] epoch #158 | Sampling for adapation and meta-testing... 2025-04-03 06:24:38 | [maml_trainer] epoch #158 | Finished meta-testing... 2025-04-03 06:24:38 | [maml_trainer] epoch #158 | Saving snapshot... 2025-04-03 06:25:00 | [maml_trainer] epoch #158 | Saved 2025-04-03 06:25:00 | [maml_trainer] epoch #158 | Time 60578.58 s 2025-04-03 06:25:00 | [maml_trainer] epoch #158 | EpochTime 394.49 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.8507 Average/AverageReturn -177.292 Average/Iteration 158 Average/MaxReturn -156.415 Average/MinReturn -279.88 Average/NumEpisodes 80 Average/StdReturn 22.8206 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.551 GaussianMLPPolicy/KLAfter 0.00165626 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.53861e-05 GaussianMLPPolicy/LossBefore -2.84612e-09 GaussianMLPPolicy/dLoss 2.53833e-05 Iteration 158 MetaTest/Average/AverageDiscountedReturn -175.596 MetaTest/Average/AverageReturn -175.596 MetaTest/Average/Iteration 158 MetaTest/Average/MaxReturn -153.616 MetaTest/Average/MinReturn -230.983 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.8321 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.596 MetaTest/__unnamed_task__/AverageReturn -175.596 MetaTest/__unnamed_task__/Iteration 158 MetaTest/__unnamed_task__/MaxReturn -153.616 MetaTest/__unnamed_task__/MinReturn -230.983 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.8321 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.088e+06 __unnamed_task__/AverageDiscountedReturn -74.8507 __unnamed_task__/AverageReturn -177.292 __unnamed_task__/Iteration 158 __unnamed_task__/MaxReturn -156.415 __unnamed_task__/MinReturn -279.88 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.8206 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 06:29:54 | [maml_trainer] epoch #159 | Sampling for adapation and meta-testing... 2025-04-03 06:31:07 | [maml_trainer] epoch #159 | Finished meta-testing... 2025-04-03 06:31:07 | [maml_trainer] epoch #159 | Saving snapshot... 2025-04-03 06:31:31 | [maml_trainer] epoch #159 | Saved 2025-04-03 06:31:31 | [maml_trainer] epoch #159 | Time 60969.27 s 2025-04-03 06:31:31 | [maml_trainer] epoch #159 | EpochTime 390.69 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.2776 Average/AverageReturn -173.78 Average/Iteration 159 Average/MaxReturn -149.988 Average/MinReturn -241.922 Average/NumEpisodes 80 Average/StdReturn 17.6879 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.55 GaussianMLPPolicy/KLAfter 0.00186658 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.87548e-06 GaussianMLPPolicy/LossBefore 4.90248e-09 GaussianMLPPolicy/dLoss 4.88038e-06 Iteration 159 MetaTest/Average/AverageDiscountedReturn -169.014 MetaTest/Average/AverageReturn -169.014 MetaTest/Average/Iteration 159 MetaTest/Average/MaxReturn -152.798 MetaTest/Average/MinReturn -232.244 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.801 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.014 MetaTest/__unnamed_task__/AverageReturn -169.014 MetaTest/__unnamed_task__/Iteration 159 MetaTest/__unnamed_task__/MaxReturn -152.798 MetaTest/__unnamed_task__/MinReturn -232.244 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.801 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.12e+06 __unnamed_task__/AverageDiscountedReturn -73.2776 __unnamed_task__/AverageReturn -173.78 __unnamed_task__/Iteration 159 __unnamed_task__/MaxReturn -149.988 __unnamed_task__/MinReturn -241.922 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.6879 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 06:36:26 | [maml_trainer] epoch #160 | Sampling for adapation and meta-testing... 2025-04-03 06:37:39 | [maml_trainer] epoch #160 | Finished meta-testing... 2025-04-03 06:37:39 | [maml_trainer] epoch #160 | Saving snapshot... 2025-04-03 06:38:02 | [maml_trainer] epoch #160 | Saved 2025-04-03 06:38:02 | [maml_trainer] epoch #160 | Time 61360.82 s 2025-04-03 06:38:02 | [maml_trainer] epoch #160 | EpochTime 391.54 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.522 Average/AverageReturn -176.989 Average/Iteration 160 Average/MaxReturn -148.695 Average/MinReturn -242.647 Average/NumEpisodes 80 Average/StdReturn 21.2737 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5492 GaussianMLPPolicy/KLAfter 0.00225742 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.87653e-05 GaussianMLPPolicy/LossBefore 1.13249e-09 GaussianMLPPolicy/dLoss -2.87642e-05 Iteration 160 MetaTest/Average/AverageDiscountedReturn -177.734 MetaTest/Average/AverageReturn -177.734 MetaTest/Average/Iteration 160 MetaTest/Average/MaxReturn -160.67 MetaTest/Average/MinReturn -234.731 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.8531 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.734 MetaTest/__unnamed_task__/AverageReturn -177.734 MetaTest/__unnamed_task__/Iteration 160 MetaTest/__unnamed_task__/MaxReturn -160.67 MetaTest/__unnamed_task__/MinReturn -234.731 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.8531 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.152e+06 __unnamed_task__/AverageDiscountedReturn -74.522 __unnamed_task__/AverageReturn -176.989 __unnamed_task__/Iteration 160 __unnamed_task__/MaxReturn -148.695 __unnamed_task__/MinReturn -242.647 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.2737 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 06:42:58 | [maml_trainer] epoch #161 | Sampling for adapation and meta-testing... 2025-04-03 06:44:10 | [maml_trainer] epoch #161 | Finished meta-testing... 2025-04-03 06:44:10 | [maml_trainer] epoch #161 | Saving snapshot... 2025-04-03 06:44:34 | [maml_trainer] epoch #161 | Saved 2025-04-03 06:44:34 | [maml_trainer] epoch #161 | Time 61752.28 s 2025-04-03 06:44:34 | [maml_trainer] epoch #161 | EpochTime 391.46 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.3331 Average/AverageReturn -171.546 Average/Iteration 161 Average/MaxReturn -152.395 Average/MinReturn -230.081 Average/NumEpisodes 80 Average/StdReturn 15.6404 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5477 GaussianMLPPolicy/KLAfter 0.00188276 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.30603e-05 GaussianMLPPolicy/LossBefore -6.88434e-09 GaussianMLPPolicy/dLoss 3.30534e-05 Iteration 161 MetaTest/Average/AverageDiscountedReturn -183.905 MetaTest/Average/AverageReturn -183.905 MetaTest/Average/Iteration 161 MetaTest/Average/MaxReturn -156.507 MetaTest/Average/MinReturn -225.682 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.6086 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -183.905 MetaTest/__unnamed_task__/AverageReturn -183.905 MetaTest/__unnamed_task__/Iteration 161 MetaTest/__unnamed_task__/MaxReturn -156.507 MetaTest/__unnamed_task__/MinReturn -225.682 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.6086 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.184e+06 __unnamed_task__/AverageDiscountedReturn -72.3331 __unnamed_task__/AverageReturn -171.546 __unnamed_task__/Iteration 161 __unnamed_task__/MaxReturn -152.395 __unnamed_task__/MinReturn -230.081 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.6404 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 06:49:28 | [maml_trainer] epoch #162 | Sampling for adapation and meta-testing... 2025-04-03 06:50:41 | [maml_trainer] epoch #162 | Finished meta-testing... 2025-04-03 06:50:41 | [maml_trainer] epoch #162 | Saving snapshot... 2025-04-03 06:51:03 | [maml_trainer] epoch #162 | Saved 2025-04-03 06:51:03 | [maml_trainer] epoch #162 | Time 62141.67 s 2025-04-03 06:51:03 | [maml_trainer] epoch #162 | EpochTime 389.39 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.6289 Average/AverageReturn -176.919 Average/Iteration 162 Average/MaxReturn -152.668 Average/MinReturn -238.404 Average/NumEpisodes 80 Average/StdReturn 20.3495 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5451 GaussianMLPPolicy/KLAfter 0.00166313 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.62553e-05 GaussianMLPPolicy/LossBefore -4.93228e-09 GaussianMLPPolicy/dLoss -2.62602e-05 Iteration 162 MetaTest/Average/AverageDiscountedReturn -178.855 MetaTest/Average/AverageReturn -178.855 MetaTest/Average/Iteration 162 MetaTest/Average/MaxReturn -154.415 MetaTest/Average/MinReturn -229.19 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.0371 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -178.855 MetaTest/__unnamed_task__/AverageReturn -178.855 MetaTest/__unnamed_task__/Iteration 162 MetaTest/__unnamed_task__/MaxReturn -154.415 MetaTest/__unnamed_task__/MinReturn -229.19 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.0371 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.216e+06 __unnamed_task__/AverageDiscountedReturn -74.6289 __unnamed_task__/AverageReturn -176.919 __unnamed_task__/Iteration 162 __unnamed_task__/MaxReturn -152.668 __unnamed_task__/MinReturn -238.404 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.3495 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 06:56:00 | [maml_trainer] epoch #163 | Sampling for adapation and meta-testing... 2025-04-03 06:57:14 | [maml_trainer] epoch #163 | Finished meta-testing... 2025-04-03 06:57:14 | [maml_trainer] epoch #163 | Saving snapshot... 2025-04-03 06:57:36 | [maml_trainer] epoch #163 | Saved 2025-04-03 06:57:36 | [maml_trainer] epoch #163 | Time 62534.15 s 2025-04-03 06:57:36 | [maml_trainer] epoch #163 | EpochTime 392.48 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.4912 Average/AverageReturn -174.686 Average/Iteration 163 Average/MaxReturn -150.693 Average/MinReturn -241.382 Average/NumEpisodes 80 Average/StdReturn 17.9196 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5424 GaussianMLPPolicy/KLAfter 0.00172704 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.21231e-05 GaussianMLPPolicy/LossBefore 1.78814e-09 GaussianMLPPolicy/dLoss -1.21213e-05 Iteration 163 MetaTest/Average/AverageDiscountedReturn -168.363 MetaTest/Average/AverageReturn -168.363 MetaTest/Average/Iteration 163 MetaTest/Average/MaxReturn -156.076 MetaTest/Average/MinReturn -193.236 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.639 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.363 MetaTest/__unnamed_task__/AverageReturn -168.363 MetaTest/__unnamed_task__/Iteration 163 MetaTest/__unnamed_task__/MaxReturn -156.076 MetaTest/__unnamed_task__/MinReturn -193.236 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.639 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.248e+06 __unnamed_task__/AverageDiscountedReturn -73.4912 __unnamed_task__/AverageReturn -174.686 __unnamed_task__/Iteration 163 __unnamed_task__/MaxReturn -150.693 __unnamed_task__/MinReturn -241.382 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.9196 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 07:02:27 | [maml_trainer] epoch #164 | Sampling for adapation and meta-testing... 2025-04-03 07:03:40 | [maml_trainer] epoch #164 | Finished meta-testing... 2025-04-03 07:03:40 | [maml_trainer] epoch #164 | Saving snapshot... 2025-04-03 07:04:03 | [maml_trainer] epoch #164 | Saved 2025-04-03 07:04:03 | [maml_trainer] epoch #164 | Time 62921.83 s 2025-04-03 07:04:03 | [maml_trainer] epoch #164 | EpochTime 387.67 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.2915 Average/AverageReturn -173.701 Average/Iteration 164 Average/MaxReturn -151.269 Average/MinReturn -251.281 Average/NumEpisodes 80 Average/StdReturn 18.4208 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5408 GaussianMLPPolicy/KLAfter 0.00173097 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.00863e-05 GaussianMLPPolicy/LossBefore -5.88596e-09 GaussianMLPPolicy/dLoss -2.00921e-05 Iteration 164 MetaTest/Average/AverageDiscountedReturn -171.092 MetaTest/Average/AverageReturn -171.092 MetaTest/Average/Iteration 164 MetaTest/Average/MaxReturn -156.978 MetaTest/Average/MinReturn -217.916 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.3894 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.092 MetaTest/__unnamed_task__/AverageReturn -171.092 MetaTest/__unnamed_task__/Iteration 164 MetaTest/__unnamed_task__/MaxReturn -156.978 MetaTest/__unnamed_task__/MinReturn -217.916 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.3894 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.28e+06 __unnamed_task__/AverageDiscountedReturn -73.2915 __unnamed_task__/AverageReturn -173.701 __unnamed_task__/Iteration 164 __unnamed_task__/MaxReturn -151.269 __unnamed_task__/MinReturn -251.281 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.4208 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 07:08:57 | [maml_trainer] epoch #165 | Sampling for adapation and meta-testing... 2025-04-03 07:10:11 | [maml_trainer] epoch #165 | Finished meta-testing... 2025-04-03 07:10:11 | [maml_trainer] epoch #165 | Saving snapshot... 2025-04-03 07:10:34 | [maml_trainer] epoch #165 | Saved 2025-04-03 07:10:34 | [maml_trainer] epoch #165 | Time 63312.80 s 2025-04-03 07:10:34 | [maml_trainer] epoch #165 | EpochTime 390.97 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.3959 Average/AverageReturn -173.923 Average/Iteration 165 Average/MaxReturn -153.445 Average/MinReturn -256.195 Average/NumEpisodes 80 Average/StdReturn 17.7702 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5384 GaussianMLPPolicy/KLAfter 0.00174377 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.39255e-07 GaussianMLPPolicy/LossBefore -5.1558e-09 GaussianMLPPolicy/dLoss -3.44411e-07 Iteration 165 MetaTest/Average/AverageDiscountedReturn -170.165 MetaTest/Average/AverageReturn -170.165 MetaTest/Average/Iteration 165 MetaTest/Average/MaxReturn -154.761 MetaTest/Average/MinReturn -206.604 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.0798 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.165 MetaTest/__unnamed_task__/AverageReturn -170.165 MetaTest/__unnamed_task__/Iteration 165 MetaTest/__unnamed_task__/MaxReturn -154.761 MetaTest/__unnamed_task__/MinReturn -206.604 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.0798 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.312e+06 __unnamed_task__/AverageDiscountedReturn -73.3959 __unnamed_task__/AverageReturn -173.923 __unnamed_task__/Iteration 165 __unnamed_task__/MaxReturn -153.445 __unnamed_task__/MinReturn -256.195 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.7702 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 07:15:27 | [maml_trainer] epoch #166 | Sampling for adapation and meta-testing... 2025-04-03 07:16:41 | [maml_trainer] epoch #166 | Finished meta-testing... 2025-04-03 07:16:41 | [maml_trainer] epoch #166 | Saving snapshot... 2025-04-03 07:17:03 | [maml_trainer] epoch #166 | Saved 2025-04-03 07:17:03 | [maml_trainer] epoch #166 | Time 63702.08 s 2025-04-03 07:17:03 | [maml_trainer] epoch #166 | EpochTime 389.27 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.4248 Average/AverageReturn -173.825 Average/Iteration 166 Average/MaxReturn -151.972 Average/MinReturn -245.283 Average/NumEpisodes 80 Average/StdReturn 21.0152 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5354 GaussianMLPPolicy/KLAfter 0.00151268 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.93853e-05 GaussianMLPPolicy/LossBefore 1.86265e-09 GaussianMLPPolicy/dLoss -1.93834e-05 Iteration 166 MetaTest/Average/AverageDiscountedReturn -167.017 MetaTest/Average/AverageReturn -167.017 MetaTest/Average/Iteration 166 MetaTest/Average/MaxReturn -157.995 MetaTest/Average/MinReturn -189.739 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.99631 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.017 MetaTest/__unnamed_task__/AverageReturn -167.017 MetaTest/__unnamed_task__/Iteration 166 MetaTest/__unnamed_task__/MaxReturn -157.995 MetaTest/__unnamed_task__/MinReturn -189.739 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.99631 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.344e+06 __unnamed_task__/AverageDiscountedReturn -73.4248 __unnamed_task__/AverageReturn -173.825 __unnamed_task__/Iteration 166 __unnamed_task__/MaxReturn -151.972 __unnamed_task__/MinReturn -245.283 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.0152 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 07:21:56 | [maml_trainer] epoch #167 | Sampling for adapation and meta-testing... 2025-04-03 07:23:10 | [maml_trainer] epoch #167 | Finished meta-testing... 2025-04-03 07:23:10 | [maml_trainer] epoch #167 | Saving snapshot... 2025-04-03 07:23:33 | [maml_trainer] epoch #167 | Saved 2025-04-03 07:23:33 | [maml_trainer] epoch #167 | Time 64091.38 s 2025-04-03 07:23:33 | [maml_trainer] epoch #167 | EpochTime 389.30 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.3533 Average/AverageReturn -172.026 Average/Iteration 167 Average/MaxReturn -154.826 Average/MinReturn -216.333 Average/NumEpisodes 80 Average/StdReturn 12.9364 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5298 GaussianMLPPolicy/KLAfter 0.00150832 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.21639e-06 GaussianMLPPolicy/LossBefore 5.45382e-09 GaussianMLPPolicy/dLoss 5.22184e-06 Iteration 167 MetaTest/Average/AverageDiscountedReturn -169.664 MetaTest/Average/AverageReturn -169.664 MetaTest/Average/Iteration 167 MetaTest/Average/MaxReturn -154.66 MetaTest/Average/MinReturn -190.871 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.5899 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.664 MetaTest/__unnamed_task__/AverageReturn -169.664 MetaTest/__unnamed_task__/Iteration 167 MetaTest/__unnamed_task__/MaxReturn -154.66 MetaTest/__unnamed_task__/MinReturn -190.871 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.5899 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.376e+06 __unnamed_task__/AverageDiscountedReturn -72.3533 __unnamed_task__/AverageReturn -172.026 __unnamed_task__/Iteration 167 __unnamed_task__/MaxReturn -154.826 __unnamed_task__/MinReturn -216.333 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 12.9364 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 07:28:26 | [maml_trainer] epoch #168 | Sampling for adapation and meta-testing... 2025-04-03 07:29:39 | [maml_trainer] epoch #168 | Finished meta-testing... 2025-04-03 07:29:39 | [maml_trainer] epoch #168 | Saving snapshot... 2025-04-03 07:30:03 | [maml_trainer] epoch #168 | Saved 2025-04-03 07:30:03 | [maml_trainer] epoch #168 | Time 64481.27 s 2025-04-03 07:30:03 | [maml_trainer] epoch #168 | EpochTime 389.88 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.8505 Average/AverageReturn -172.569 Average/Iteration 168 Average/MaxReturn -151.699 Average/MinReturn -226.949 Average/NumEpisodes 80 Average/StdReturn 17.8132 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5248 GaussianMLPPolicy/KLAfter 0.0014005 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.33716e-07 GaussianMLPPolicy/LossBefore 1.2964e-09 GaussianMLPPolicy/dLoss -6.32419e-07 Iteration 168 MetaTest/Average/AverageDiscountedReturn -173.159 MetaTest/Average/AverageReturn -173.159 MetaTest/Average/Iteration 168 MetaTest/Average/MaxReturn -153.98 MetaTest/Average/MinReturn -201.91 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.3046 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.159 MetaTest/__unnamed_task__/AverageReturn -173.159 MetaTest/__unnamed_task__/Iteration 168 MetaTest/__unnamed_task__/MaxReturn -153.98 MetaTest/__unnamed_task__/MinReturn -201.91 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.3046 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.408e+06 __unnamed_task__/AverageDiscountedReturn -72.8505 __unnamed_task__/AverageReturn -172.569 __unnamed_task__/Iteration 168 __unnamed_task__/MaxReturn -151.699 __unnamed_task__/MinReturn -226.949 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.8132 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 07:34:57 | [maml_trainer] epoch #169 | Sampling for adapation and meta-testing... 2025-04-03 07:36:10 | [maml_trainer] epoch #169 | Finished meta-testing... 2025-04-03 07:36:10 | [maml_trainer] epoch #169 | Saving snapshot... 2025-04-03 07:36:34 | [maml_trainer] epoch #169 | Saved 2025-04-03 07:36:34 | [maml_trainer] epoch #169 | Time 64872.16 s 2025-04-03 07:36:34 | [maml_trainer] epoch #169 | EpochTime 390.89 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.147 Average/AverageReturn -170.706 Average/Iteration 169 Average/MaxReturn -151.525 Average/MinReturn -243.656 Average/NumEpisodes 80 Average/StdReturn 14.0192 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5202 GaussianMLPPolicy/KLAfter 0.00151264 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.43144e-05 GaussianMLPPolicy/LossBefore 9.0152e-09 GaussianMLPPolicy/dLoss 5.43234e-05 Iteration 169 MetaTest/Average/AverageDiscountedReturn -171.348 MetaTest/Average/AverageReturn -171.348 MetaTest/Average/Iteration 169 MetaTest/Average/MaxReturn -158.326 MetaTest/Average/MinReturn -196.512 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.22564 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.348 MetaTest/__unnamed_task__/AverageReturn -171.348 MetaTest/__unnamed_task__/Iteration 169 MetaTest/__unnamed_task__/MaxReturn -158.326 MetaTest/__unnamed_task__/MinReturn -196.512 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.22564 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.44e+06 __unnamed_task__/AverageDiscountedReturn -72.147 __unnamed_task__/AverageReturn -170.706 __unnamed_task__/Iteration 169 __unnamed_task__/MaxReturn -151.525 __unnamed_task__/MinReturn -243.656 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.0192 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 07:41:28 | [maml_trainer] epoch #170 | Sampling for adapation and meta-testing... 2025-04-03 07:42:39 | [maml_trainer] epoch #170 | Finished meta-testing... 2025-04-03 07:42:39 | [maml_trainer] epoch #170 | Saving snapshot... 2025-04-03 07:43:02 | [maml_trainer] epoch #170 | Saved 2025-04-03 07:43:02 | [maml_trainer] epoch #170 | Time 65260.81 s 2025-04-03 07:43:02 | [maml_trainer] epoch #170 | EpochTime 388.65 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.518 Average/AverageReturn -172.202 Average/Iteration 170 Average/MaxReturn -150.618 Average/MinReturn -234.759 Average/NumEpisodes 80 Average/StdReturn 15.2705 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5155 GaussianMLPPolicy/KLAfter 0.00137873 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.28372e-05 GaussianMLPPolicy/LossBefore 6.78003e-09 GaussianMLPPolicy/dLoss -3.28304e-05 Iteration 170 MetaTest/Average/AverageDiscountedReturn -171.273 MetaTest/Average/AverageReturn -171.273 MetaTest/Average/Iteration 170 MetaTest/Average/MaxReturn -157.154 MetaTest/Average/MinReturn -226.254 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.1135 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.273 MetaTest/__unnamed_task__/AverageReturn -171.273 MetaTest/__unnamed_task__/Iteration 170 MetaTest/__unnamed_task__/MaxReturn -157.154 MetaTest/__unnamed_task__/MinReturn -226.254 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.1135 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.472e+06 __unnamed_task__/AverageDiscountedReturn -72.518 __unnamed_task__/AverageReturn -172.202 __unnamed_task__/Iteration 170 __unnamed_task__/MaxReturn -150.618 __unnamed_task__/MinReturn -234.759 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.2705 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 07:47:54 | [maml_trainer] epoch #171 | Sampling for adapation and meta-testing... 2025-04-03 07:49:08 | [maml_trainer] epoch #171 | Finished meta-testing... 2025-04-03 07:49:08 | [maml_trainer] epoch #171 | Saving snapshot... 2025-04-03 07:49:30 | [maml_trainer] epoch #171 | Saved 2025-04-03 07:49:30 | [maml_trainer] epoch #171 | Time 65648.70 s 2025-04-03 07:49:30 | [maml_trainer] epoch #171 | EpochTime 387.88 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.0511 Average/AverageReturn -170.612 Average/Iteration 171 Average/MaxReturn -148.212 Average/MinReturn -242.477 Average/NumEpisodes 80 Average/StdReturn 15.505 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5101 GaussianMLPPolicy/KLAfter 0.00172038 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.3736e-05 GaussianMLPPolicy/LossBefore 5.31971e-09 GaussianMLPPolicy/dLoss -1.37307e-05 Iteration 171 MetaTest/Average/AverageDiscountedReturn -175.701 MetaTest/Average/AverageReturn -175.701 MetaTest/Average/Iteration 171 MetaTest/Average/MaxReturn -152.285 MetaTest/Average/MinReturn -234.257 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.1534 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.701 MetaTest/__unnamed_task__/AverageReturn -175.701 MetaTest/__unnamed_task__/Iteration 171 MetaTest/__unnamed_task__/MaxReturn -152.285 MetaTest/__unnamed_task__/MinReturn -234.257 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.1534 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.504e+06 __unnamed_task__/AverageDiscountedReturn -72.0511 __unnamed_task__/AverageReturn -170.612 __unnamed_task__/Iteration 171 __unnamed_task__/MaxReturn -148.212 __unnamed_task__/MinReturn -242.477 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.505 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 07:54:22 | [maml_trainer] epoch #172 | Sampling for adapation and meta-testing... 2025-04-03 07:55:35 | [maml_trainer] epoch #172 | Finished meta-testing... 2025-04-03 07:55:35 | [maml_trainer] epoch #172 | Saving snapshot... 2025-04-03 07:55:59 | [maml_trainer] epoch #172 | Saved 2025-04-03 07:55:59 | [maml_trainer] epoch #172 | Time 66037.36 s 2025-04-03 07:55:59 | [maml_trainer] epoch #172 | EpochTime 388.66 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.7541 Average/AverageReturn -170.069 Average/Iteration 172 Average/MaxReturn -154.543 Average/MinReturn -232.258 Average/NumEpisodes 80 Average/StdReturn 12.8163 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5056 GaussianMLPPolicy/KLAfter 0.00146552 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.6122e-05 GaussianMLPPolicy/LossBefore 6.64592e-09 GaussianMLPPolicy/dLoss -2.61154e-05 Iteration 172 MetaTest/Average/AverageDiscountedReturn -183.157 MetaTest/Average/AverageReturn -183.157 MetaTest/Average/Iteration 172 MetaTest/Average/MaxReturn -158.461 MetaTest/Average/MinReturn -243.993 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.0942 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -183.157 MetaTest/__unnamed_task__/AverageReturn -183.157 MetaTest/__unnamed_task__/Iteration 172 MetaTest/__unnamed_task__/MaxReturn -158.461 MetaTest/__unnamed_task__/MinReturn -243.993 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.0942 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.536e+06 __unnamed_task__/AverageDiscountedReturn -71.7541 __unnamed_task__/AverageReturn -170.069 __unnamed_task__/Iteration 172 __unnamed_task__/MaxReturn -154.543 __unnamed_task__/MinReturn -232.258 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 12.8163 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 08:00:53 | [maml_trainer] epoch #173 | Sampling for adapation and meta-testing... 2025-04-03 08:02:07 | [maml_trainer] epoch #173 | Finished meta-testing... 2025-04-03 08:02:07 | [maml_trainer] epoch #173 | Saving snapshot... 2025-04-03 08:02:30 | [maml_trainer] epoch #173 | Saved 2025-04-03 08:02:30 | [maml_trainer] epoch #173 | Time 66428.43 s 2025-04-03 08:02:30 | [maml_trainer] epoch #173 | EpochTime 391.07 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.7435 Average/AverageReturn -174.36 Average/Iteration 173 Average/MaxReturn -148.15 Average/MinReturn -258.353 Average/NumEpisodes 80 Average/StdReturn 20.1422 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.5008 GaussianMLPPolicy/KLAfter 0.00125188 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.02547e-06 GaussianMLPPolicy/LossBefore 3.8743e-09 GaussianMLPPolicy/dLoss -2.0216e-06 Iteration 173 MetaTest/Average/AverageDiscountedReturn -175.876 MetaTest/Average/AverageReturn -175.876 MetaTest/Average/Iteration 173 MetaTest/Average/MaxReturn -160.353 MetaTest/Average/MinReturn -215.5 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.9308 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.876 MetaTest/__unnamed_task__/AverageReturn -175.876 MetaTest/__unnamed_task__/Iteration 173 MetaTest/__unnamed_task__/MaxReturn -160.353 MetaTest/__unnamed_task__/MinReturn -215.5 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.9308 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.568e+06 __unnamed_task__/AverageDiscountedReturn -73.7435 __unnamed_task__/AverageReturn -174.36 __unnamed_task__/Iteration 173 __unnamed_task__/MaxReturn -148.15 __unnamed_task__/MinReturn -258.353 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.1422 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 08:07:27 | [maml_trainer] epoch #174 | Sampling for adapation and meta-testing... 2025-04-03 08:08:40 | [maml_trainer] epoch #174 | Finished meta-testing... 2025-04-03 08:08:40 | [maml_trainer] epoch #174 | Saving snapshot... 2025-04-03 08:09:03 | [maml_trainer] epoch #174 | Saved 2025-04-03 08:09:03 | [maml_trainer] epoch #174 | Time 66821.67 s 2025-04-03 08:09:03 | [maml_trainer] epoch #174 | EpochTime 393.24 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.2068 Average/AverageReturn -170.899 Average/Iteration 174 Average/MaxReturn -147.107 Average/MinReturn -226.985 Average/NumEpisodes 80 Average/StdReturn 13.8869 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4987 GaussianMLPPolicy/KLAfter 0.00231777 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.42853e-07 GaussianMLPPolicy/LossBefore -1.54972e-09 GaussianMLPPolicy/dLoss 7.41303e-07 Iteration 174 MetaTest/Average/AverageDiscountedReturn -169.274 MetaTest/Average/AverageReturn -169.274 MetaTest/Average/Iteration 174 MetaTest/Average/MaxReturn -154.813 MetaTest/Average/MinReturn -226.814 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.1204 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.274 MetaTest/__unnamed_task__/AverageReturn -169.274 MetaTest/__unnamed_task__/Iteration 174 MetaTest/__unnamed_task__/MaxReturn -154.813 MetaTest/__unnamed_task__/MinReturn -226.814 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.1204 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.6e+06 __unnamed_task__/AverageDiscountedReturn -72.2068 __unnamed_task__/AverageReturn -170.899 __unnamed_task__/Iteration 174 __unnamed_task__/MaxReturn -147.107 __unnamed_task__/MinReturn -226.985 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.8869 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 08:13:59 | [maml_trainer] epoch #175 | Sampling for adapation and meta-testing... 2025-04-03 08:15:12 | [maml_trainer] epoch #175 | Finished meta-testing... 2025-04-03 08:15:12 | [maml_trainer] epoch #175 | Saving snapshot... 2025-04-03 08:15:34 | [maml_trainer] epoch #175 | Saved 2025-04-03 08:15:34 | [maml_trainer] epoch #175 | Time 67212.45 s 2025-04-03 08:15:34 | [maml_trainer] epoch #175 | EpochTime 390.78 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.171 Average/AverageReturn -171.085 Average/Iteration 175 Average/MaxReturn -153.963 Average/MinReturn -240.836 Average/NumEpisodes 80 Average/StdReturn 16.6219 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4979 GaussianMLPPolicy/KLAfter 0.00175387 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.56659e-07 GaussianMLPPolicy/LossBefore -6.63102e-09 GaussianMLPPolicy/dLoss -3.6329e-07 Iteration 175 MetaTest/Average/AverageDiscountedReturn -169.554 MetaTest/Average/AverageReturn -169.554 MetaTest/Average/Iteration 175 MetaTest/Average/MaxReturn -154.132 MetaTest/Average/MinReturn -199.359 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.5053 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.554 MetaTest/__unnamed_task__/AverageReturn -169.554 MetaTest/__unnamed_task__/Iteration 175 MetaTest/__unnamed_task__/MaxReturn -154.132 MetaTest/__unnamed_task__/MinReturn -199.359 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.5053 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.632e+06 __unnamed_task__/AverageDiscountedReturn -72.171 __unnamed_task__/AverageReturn -171.085 __unnamed_task__/Iteration 175 __unnamed_task__/MaxReturn -153.963 __unnamed_task__/MinReturn -240.836 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.6219 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 08:20:27 | [maml_trainer] epoch #176 | Sampling for adapation and meta-testing... 2025-04-03 08:21:41 | [maml_trainer] epoch #176 | Finished meta-testing... 2025-04-03 08:21:41 | [maml_trainer] epoch #176 | Saving snapshot... 2025-04-03 08:22:04 | [maml_trainer] epoch #176 | Saved 2025-04-03 08:22:04 | [maml_trainer] epoch #176 | Time 67602.83 s 2025-04-03 08:22:04 | [maml_trainer] epoch #176 | EpochTime 390.38 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.8834 Average/AverageReturn -170.664 Average/Iteration 176 Average/MaxReturn -151.117 Average/MinReturn -229.187 Average/NumEpisodes 80 Average/StdReturn 14.8016 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4968 GaussianMLPPolicy/KLAfter 0.00176253 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.46393e-05 GaussianMLPPolicy/LossBefore -2.23517e-09 GaussianMLPPolicy/dLoss -1.46416e-05 Iteration 176 MetaTest/Average/AverageDiscountedReturn -177.527 MetaTest/Average/AverageReturn -177.527 MetaTest/Average/Iteration 176 MetaTest/Average/MaxReturn -159.755 MetaTest/Average/MinReturn -228.124 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.9711 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.527 MetaTest/__unnamed_task__/AverageReturn -177.527 MetaTest/__unnamed_task__/Iteration 176 MetaTest/__unnamed_task__/MaxReturn -159.755 MetaTest/__unnamed_task__/MinReturn -228.124 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.9711 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.664e+06 __unnamed_task__/AverageDiscountedReturn -71.8834 __unnamed_task__/AverageReturn -170.664 __unnamed_task__/Iteration 176 __unnamed_task__/MaxReturn -151.117 __unnamed_task__/MinReturn -229.187 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.8016 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 08:26:55 | [maml_trainer] epoch #177 | Sampling for adapation and meta-testing... 2025-04-03 08:28:07 | [maml_trainer] epoch #177 | Finished meta-testing... 2025-04-03 08:28:07 | [maml_trainer] epoch #177 | Saving snapshot... 2025-04-03 08:28:30 | [maml_trainer] epoch #177 | Saved 2025-04-03 08:28:30 | [maml_trainer] epoch #177 | Time 67988.95 s 2025-04-03 08:28:30 | [maml_trainer] epoch #177 | EpochTime 386.11 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.3954 Average/AverageReturn -171.205 Average/Iteration 177 Average/MaxReturn -153.12 Average/MinReturn -253.189 Average/NumEpisodes 80 Average/StdReturn 18.4679 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4957 GaussianMLPPolicy/KLAfter 0.00276101 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.91321e-05 GaussianMLPPolicy/LossBefore 1.07288e-09 GaussianMLPPolicy/dLoss -2.9131e-05 Iteration 177 MetaTest/Average/AverageDiscountedReturn -177.694 MetaTest/Average/AverageReturn -177.694 MetaTest/Average/Iteration 177 MetaTest/Average/MaxReturn -155.041 MetaTest/Average/MinReturn -243.764 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.2894 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.694 MetaTest/__unnamed_task__/AverageReturn -177.694 MetaTest/__unnamed_task__/Iteration 177 MetaTest/__unnamed_task__/MaxReturn -155.041 MetaTest/__unnamed_task__/MinReturn -243.764 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.2894 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.696e+06 __unnamed_task__/AverageDiscountedReturn -72.3954 __unnamed_task__/AverageReturn -171.205 __unnamed_task__/Iteration 177 __unnamed_task__/MaxReturn -153.12 __unnamed_task__/MinReturn -253.189 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.4679 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 08:33:22 | [maml_trainer] epoch #178 | Sampling for adapation and meta-testing... 2025-04-03 08:34:35 | [maml_trainer] epoch #178 | Finished meta-testing... 2025-04-03 08:34:35 | [maml_trainer] epoch #178 | Saving snapshot... 2025-04-03 08:34:58 | [maml_trainer] epoch #178 | Saved 2025-04-03 08:34:58 | [maml_trainer] epoch #178 | Time 68377.01 s 2025-04-03 08:34:58 | [maml_trainer] epoch #178 | EpochTime 388.06 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.5902 Average/AverageReturn -172.167 Average/Iteration 178 Average/MaxReturn -150.959 Average/MinReturn -236.373 Average/NumEpisodes 80 Average/StdReturn 16.1428 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4946 GaussianMLPPolicy/KLAfter 0.0021574 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.93925e-05 GaussianMLPPolicy/LossBefore -5.70714e-09 GaussianMLPPolicy/dLoss -1.93982e-05 Iteration 178 MetaTest/Average/AverageDiscountedReturn -171.513 MetaTest/Average/AverageReturn -171.513 MetaTest/Average/Iteration 178 MetaTest/Average/MaxReturn -157.451 MetaTest/Average/MinReturn -232.141 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.3887 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.513 MetaTest/__unnamed_task__/AverageReturn -171.513 MetaTest/__unnamed_task__/Iteration 178 MetaTest/__unnamed_task__/MaxReturn -157.451 MetaTest/__unnamed_task__/MinReturn -232.141 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.3887 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.728e+06 __unnamed_task__/AverageDiscountedReturn -72.5902 __unnamed_task__/AverageReturn -172.167 __unnamed_task__/Iteration 178 __unnamed_task__/MaxReturn -150.959 __unnamed_task__/MinReturn -236.373 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.1428 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 08:39:52 | [maml_trainer] epoch #179 | Sampling for adapation and meta-testing... 2025-04-03 08:41:05 | [maml_trainer] epoch #179 | Finished meta-testing... 2025-04-03 08:41:05 | [maml_trainer] epoch #179 | Saving snapshot... 2025-04-03 08:41:27 | [maml_trainer] epoch #179 | Saved 2025-04-03 08:41:27 | [maml_trainer] epoch #179 | Time 68765.55 s 2025-04-03 08:41:27 | [maml_trainer] epoch #179 | EpochTime 388.53 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.8009 Average/AverageReturn -174.381 Average/Iteration 179 Average/MaxReturn -152.794 Average/MinReturn -271.861 Average/NumEpisodes 80 Average/StdReturn 21.2488 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4931 GaussianMLPPolicy/KLAfter 0.00356276 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.97071e-05 GaussianMLPPolicy/LossBefore -4.47035e-09 GaussianMLPPolicy/dLoss 6.97027e-05 Iteration 179 MetaTest/Average/AverageDiscountedReturn -167.893 MetaTest/Average/AverageReturn -167.893 MetaTest/Average/Iteration 179 MetaTest/Average/MaxReturn -149.93 MetaTest/Average/MinReturn -194.483 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.7541 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.893 MetaTest/__unnamed_task__/AverageReturn -167.893 MetaTest/__unnamed_task__/Iteration 179 MetaTest/__unnamed_task__/MaxReturn -149.93 MetaTest/__unnamed_task__/MinReturn -194.483 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.7541 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.76e+06 __unnamed_task__/AverageDiscountedReturn -73.8009 __unnamed_task__/AverageReturn -174.381 __unnamed_task__/Iteration 179 __unnamed_task__/MaxReturn -152.794 __unnamed_task__/MinReturn -271.861 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.2488 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 08:46:20 | [maml_trainer] epoch #180 | Sampling for adapation and meta-testing... 2025-04-03 08:47:34 | [maml_trainer] epoch #180 | Finished meta-testing... 2025-04-03 08:47:34 | [maml_trainer] epoch #180 | Saving snapshot... 2025-04-03 08:47:57 | [maml_trainer] epoch #180 | Saved 2025-04-03 08:47:57 | [maml_trainer] epoch #180 | Time 69155.68 s 2025-04-03 08:47:57 | [maml_trainer] epoch #180 | EpochTime 390.13 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.7091 Average/AverageReturn -170.086 Average/Iteration 180 Average/MaxReturn -149.526 Average/MinReturn -230.559 Average/NumEpisodes 80 Average/StdReturn 15.5262 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4929 GaussianMLPPolicy/KLAfter 0.00724982 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.02789e-05 GaussianMLPPolicy/LossBefore -4.58956e-09 GaussianMLPPolicy/dLoss -1.02835e-05 Iteration 180 MetaTest/Average/AverageDiscountedReturn -172.942 MetaTest/Average/AverageReturn -172.942 MetaTest/Average/Iteration 180 MetaTest/Average/MaxReturn -153.956 MetaTest/Average/MinReturn -231.467 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.1353 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.942 MetaTest/__unnamed_task__/AverageReturn -172.942 MetaTest/__unnamed_task__/Iteration 180 MetaTest/__unnamed_task__/MaxReturn -153.956 MetaTest/__unnamed_task__/MinReturn -231.467 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.1353 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.792e+06 __unnamed_task__/AverageDiscountedReturn -71.7091 __unnamed_task__/AverageReturn -170.086 __unnamed_task__/Iteration 180 __unnamed_task__/MaxReturn -149.526 __unnamed_task__/MinReturn -230.559 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.5262 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 08:52:53 | [maml_trainer] epoch #181 | Sampling for adapation and meta-testing... 2025-04-03 08:54:07 | [maml_trainer] epoch #181 | Finished meta-testing... 2025-04-03 08:54:07 | [maml_trainer] epoch #181 | Saving snapshot... 2025-04-03 08:54:31 | [maml_trainer] epoch #181 | Saved 2025-04-03 08:54:31 | [maml_trainer] epoch #181 | Time 69549.73 s 2025-04-03 08:54:31 | [maml_trainer] epoch #181 | EpochTime 394.05 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.6075 Average/AverageReturn -174.671 Average/Iteration 181 Average/MaxReturn -146.738 Average/MinReturn -249.085 Average/NumEpisodes 80 Average/StdReturn 21.4989 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.492 GaussianMLPPolicy/KLAfter 0.00738738 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.11035e-05 GaussianMLPPolicy/LossBefore -1.80304e-09 GaussianMLPPolicy/dLoss 1.11017e-05 Iteration 181 MetaTest/Average/AverageDiscountedReturn -171.351 MetaTest/Average/AverageReturn -171.351 MetaTest/Average/Iteration 181 MetaTest/Average/MaxReturn -155.473 MetaTest/Average/MinReturn -229.96 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.9294 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.351 MetaTest/__unnamed_task__/AverageReturn -171.351 MetaTest/__unnamed_task__/Iteration 181 MetaTest/__unnamed_task__/MaxReturn -155.473 MetaTest/__unnamed_task__/MinReturn -229.96 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.9294 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.824e+06 __unnamed_task__/AverageDiscountedReturn -73.6075 __unnamed_task__/AverageReturn -174.671 __unnamed_task__/Iteration 181 __unnamed_task__/MaxReturn -146.738 __unnamed_task__/MinReturn -249.085 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.4989 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 08:59:15 | [maml_trainer] epoch #182 | Sampling for adapation and meta-testing... 2025-04-03 09:00:24 | [maml_trainer] epoch #182 | Finished meta-testing... 2025-04-03 09:00:24 | [maml_trainer] epoch #182 | Saving snapshot... 2025-04-03 09:00:47 | [maml_trainer] epoch #182 | Saved 2025-04-03 09:00:47 | [maml_trainer] epoch #182 | Time 69925.59 s 2025-04-03 09:00:47 | [maml_trainer] epoch #182 | EpochTime 375.86 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.9379 Average/AverageReturn -168.157 Average/Iteration 182 Average/MaxReturn -146.789 Average/MinReturn -224.853 Average/NumEpisodes 80 Average/StdReturn 12.0783 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4897 GaussianMLPPolicy/KLAfter 0.00855258 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.22132e-05 GaussianMLPPolicy/LossBefore -7.18236e-09 GaussianMLPPolicy/dLoss 4.2206e-05 Iteration 182 MetaTest/Average/AverageDiscountedReturn -175.199 MetaTest/Average/AverageReturn -175.199 MetaTest/Average/Iteration 182 MetaTest/Average/MaxReturn -156.17 MetaTest/Average/MinReturn -236.549 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.0463 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.199 MetaTest/__unnamed_task__/AverageReturn -175.199 MetaTest/__unnamed_task__/Iteration 182 MetaTest/__unnamed_task__/MaxReturn -156.17 MetaTest/__unnamed_task__/MinReturn -236.549 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.0463 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.856e+06 __unnamed_task__/AverageDiscountedReturn -70.9379 __unnamed_task__/AverageReturn -168.157 __unnamed_task__/Iteration 182 __unnamed_task__/MaxReturn -146.789 __unnamed_task__/MinReturn -224.853 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 12.0783 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 09:05:28 | [maml_trainer] epoch #183 | Sampling for adapation and meta-testing... 2025-04-03 09:06:37 | [maml_trainer] epoch #183 | Finished meta-testing... 2025-04-03 09:06:37 | [maml_trainer] epoch #183 | Saving snapshot... 2025-04-03 09:06:59 | [maml_trainer] epoch #183 | Saved 2025-04-03 09:06:59 | [maml_trainer] epoch #183 | Time 70297.62 s 2025-04-03 09:06:59 | [maml_trainer] epoch #183 | EpochTime 372.03 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.5883 Average/AverageReturn -174.274 Average/Iteration 183 Average/MaxReturn -145.691 Average/MinReturn -267.17 Average/NumEpisodes 80 Average/StdReturn 20.811 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.488 GaussianMLPPolicy/KLAfter 0.00824412 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.34861e-05 GaussianMLPPolicy/LossBefore -4.08292e-09 GaussianMLPPolicy/dLoss 6.3482e-05 Iteration 183 MetaTest/Average/AverageDiscountedReturn -168.428 MetaTest/Average/AverageReturn -168.428 MetaTest/Average/Iteration 183 MetaTest/Average/MaxReturn -153.934 MetaTest/Average/MinReturn -216.036 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.6535 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.428 MetaTest/__unnamed_task__/AverageReturn -168.428 MetaTest/__unnamed_task__/Iteration 183 MetaTest/__unnamed_task__/MaxReturn -153.934 MetaTest/__unnamed_task__/MinReturn -216.036 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.6535 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.888e+06 __unnamed_task__/AverageDiscountedReturn -73.5883 __unnamed_task__/AverageReturn -174.274 __unnamed_task__/Iteration 183 __unnamed_task__/MaxReturn -145.691 __unnamed_task__/MinReturn -267.17 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.811 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 09:11:39 | [maml_trainer] epoch #184 | Sampling for adapation and meta-testing... 2025-04-03 09:12:48 | [maml_trainer] epoch #184 | Finished meta-testing... 2025-04-03 09:12:48 | [maml_trainer] epoch #184 | Saving snapshot... 2025-04-03 09:13:09 | [maml_trainer] epoch #184 | Saved 2025-04-03 09:13:09 | [maml_trainer] epoch #184 | Time 70667.50 s 2025-04-03 09:13:09 | [maml_trainer] epoch #184 | EpochTime 369.88 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.3471 Average/AverageReturn -175.335 Average/Iteration 184 Average/MaxReturn -144.44 Average/MinReturn -277.645 Average/NumEpisodes 80 Average/StdReturn 24.6848 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.489 GaussianMLPPolicy/KLAfter 0.00599446 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.53933e-05 GaussianMLPPolicy/LossBefore -6.70552e-10 GaussianMLPPolicy/dLoss 2.53926e-05 Iteration 184 MetaTest/Average/AverageDiscountedReturn -169.928 MetaTest/Average/AverageReturn -169.928 MetaTest/Average/Iteration 184 MetaTest/Average/MaxReturn -155.591 MetaTest/Average/MinReturn -184.684 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.1298 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.928 MetaTest/__unnamed_task__/AverageReturn -169.928 MetaTest/__unnamed_task__/Iteration 184 MetaTest/__unnamed_task__/MaxReturn -155.591 MetaTest/__unnamed_task__/MinReturn -184.684 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.1298 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.92e+06 __unnamed_task__/AverageDiscountedReturn -74.3471 __unnamed_task__/AverageReturn -175.335 __unnamed_task__/Iteration 184 __unnamed_task__/MaxReturn -144.44 __unnamed_task__/MinReturn -277.645 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.6848 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 09:17:47 | [maml_trainer] epoch #185 | Sampling for adapation and meta-testing... 2025-04-03 09:18:58 | [maml_trainer] epoch #185 | Finished meta-testing... 2025-04-03 09:18:58 | [maml_trainer] epoch #185 | Saving snapshot... 2025-04-03 09:19:20 | [maml_trainer] epoch #185 | Saved 2025-04-03 09:19:20 | [maml_trainer] epoch #185 | Time 71038.50 s 2025-04-03 09:19:20 | [maml_trainer] epoch #185 | EpochTime 370.99 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.7524 Average/AverageReturn -175.695 Average/Iteration 185 Average/MaxReturn -148.309 Average/MinReturn -248.643 Average/NumEpisodes 80 Average/StdReturn 22.3658 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4888 GaussianMLPPolicy/KLAfter 0.00366192 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.8629e-05 GaussianMLPPolicy/LossBefore 1.69873e-09 GaussianMLPPolicy/dLoss -2.86273e-05 Iteration 185 MetaTest/Average/AverageDiscountedReturn -170.45 MetaTest/Average/AverageReturn -170.45 MetaTest/Average/Iteration 185 MetaTest/Average/MaxReturn -156.224 MetaTest/Average/MinReturn -213.768 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.4197 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.45 MetaTest/__unnamed_task__/AverageReturn -170.45 MetaTest/__unnamed_task__/Iteration 185 MetaTest/__unnamed_task__/MaxReturn -156.224 MetaTest/__unnamed_task__/MinReturn -213.768 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.4197 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.952e+06 __unnamed_task__/AverageDiscountedReturn -73.7524 __unnamed_task__/AverageReturn -175.695 __unnamed_task__/Iteration 185 __unnamed_task__/MaxReturn -148.309 __unnamed_task__/MinReturn -248.643 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.3658 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 09:24:00 | [maml_trainer] epoch #186 | Sampling for adapation and meta-testing... 2025-04-03 09:25:11 | [maml_trainer] epoch #186 | Finished meta-testing... 2025-04-03 09:25:11 | [maml_trainer] epoch #186 | Saving snapshot... 2025-04-03 09:25:33 | [maml_trainer] epoch #186 | Saved 2025-04-03 09:25:33 | [maml_trainer] epoch #186 | Time 71411.65 s 2025-04-03 09:25:33 | [maml_trainer] epoch #186 | EpochTime 373.15 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -75.0146 Average/AverageReturn -173.808 Average/Iteration 186 Average/MaxReturn -152.332 Average/MinReturn -492.943 Average/NumEpisodes 80 Average/StdReturn 38.3107 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4881 GaussianMLPPolicy/KLAfter 0.00335624 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.20332e-06 GaussianMLPPolicy/LossBefore -7.83801e-09 GaussianMLPPolicy/dLoss 6.19549e-06 Iteration 186 MetaTest/Average/AverageDiscountedReturn -166.918 MetaTest/Average/AverageReturn -166.918 MetaTest/Average/Iteration 186 MetaTest/Average/MaxReturn -143.005 MetaTest/Average/MinReturn -222.703 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.5894 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.918 MetaTest/__unnamed_task__/AverageReturn -166.918 MetaTest/__unnamed_task__/Iteration 186 MetaTest/__unnamed_task__/MaxReturn -143.005 MetaTest/__unnamed_task__/MinReturn -222.703 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.5894 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.984e+06 __unnamed_task__/AverageDiscountedReturn -75.0146 __unnamed_task__/AverageReturn -173.808 __unnamed_task__/Iteration 186 __unnamed_task__/MaxReturn -152.332 __unnamed_task__/MinReturn -492.943 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 38.3107 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 09:30:15 | [maml_trainer] epoch #187 | Sampling for adapation and meta-testing... 2025-04-03 09:31:23 | [maml_trainer] epoch #187 | Finished meta-testing... 2025-04-03 09:31:23 | [maml_trainer] epoch #187 | Saving snapshot... 2025-04-03 09:31:45 | [maml_trainer] epoch #187 | Saved 2025-04-03 09:31:45 | [maml_trainer] epoch #187 | Time 71784.02 s 2025-04-03 09:31:45 | [maml_trainer] epoch #187 | EpochTime 372.36 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.4119 Average/AverageReturn -170.07 Average/Iteration 187 Average/MaxReturn -149.881 Average/MinReturn -238.823 Average/NumEpisodes 80 Average/StdReturn 15.5632 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4887 GaussianMLPPolicy/KLAfter 0.00373477 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.06483e-05 GaussianMLPPolicy/LossBefore 6.63102e-09 GaussianMLPPolicy/dLoss -1.06417e-05 Iteration 187 MetaTest/Average/AverageDiscountedReturn -176.904 MetaTest/Average/AverageReturn -176.904 MetaTest/Average/Iteration 187 MetaTest/Average/MaxReturn -158.841 MetaTest/Average/MinReturn -230.662 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.9089 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.904 MetaTest/__unnamed_task__/AverageReturn -176.904 MetaTest/__unnamed_task__/Iteration 187 MetaTest/__unnamed_task__/MaxReturn -158.841 MetaTest/__unnamed_task__/MinReturn -230.662 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.9089 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.016e+06 __unnamed_task__/AverageDiscountedReturn -71.4119 __unnamed_task__/AverageReturn -170.07 __unnamed_task__/Iteration 187 __unnamed_task__/MaxReturn -149.881 __unnamed_task__/MinReturn -238.823 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.5632 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 09:36:24 | [maml_trainer] epoch #188 | Sampling for adapation and meta-testing... 2025-04-03 09:37:34 | [maml_trainer] epoch #188 | Finished meta-testing... 2025-04-03 09:37:34 | [maml_trainer] epoch #188 | Saving snapshot... 2025-04-03 09:37:55 | [maml_trainer] epoch #188 | Saved 2025-04-03 09:37:55 | [maml_trainer] epoch #188 | Time 72153.85 s 2025-04-03 09:37:55 | [maml_trainer] epoch #188 | EpochTime 369.83 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.0107 Average/AverageReturn -172.006 Average/Iteration 188 Average/MaxReturn -147.664 Average/MinReturn -232.018 Average/NumEpisodes 80 Average/StdReturn 16.8066 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4867 GaussianMLPPolicy/KLAfter 0.00311106 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.09215e-06 GaussianMLPPolicy/LossBefore -1.43051e-09 GaussianMLPPolicy/dLoss -8.09358e-06 Iteration 188 MetaTest/Average/AverageDiscountedReturn -170.913 MetaTest/Average/AverageReturn -170.913 MetaTest/Average/Iteration 188 MetaTest/Average/MaxReturn -151.405 MetaTest/Average/MinReturn -213.929 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.1048 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.913 MetaTest/__unnamed_task__/AverageReturn -170.913 MetaTest/__unnamed_task__/Iteration 188 MetaTest/__unnamed_task__/MaxReturn -151.405 MetaTest/__unnamed_task__/MinReturn -213.929 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.1048 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.048e+06 __unnamed_task__/AverageDiscountedReturn -72.0107 __unnamed_task__/AverageReturn -172.006 __unnamed_task__/Iteration 188 __unnamed_task__/MaxReturn -147.664 __unnamed_task__/MinReturn -232.018 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.8066 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 09:42:34 | [maml_trainer] epoch #189 | Sampling for adapation and meta-testing... 2025-04-03 09:43:43 | [maml_trainer] epoch #189 | Finished meta-testing... 2025-04-03 09:43:43 | [maml_trainer] epoch #189 | Saving snapshot... 2025-04-03 09:44:05 | [maml_trainer] epoch #189 | Saved 2025-04-03 09:44:05 | [maml_trainer] epoch #189 | Time 72523.84 s 2025-04-03 09:44:05 | [maml_trainer] epoch #189 | EpochTime 369.99 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.3268 Average/AverageReturn -174.351 Average/Iteration 189 Average/MaxReturn -152.691 Average/MinReturn -233.951 Average/NumEpisodes 80 Average/StdReturn 19.0583 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.484 GaussianMLPPolicy/KLAfter 0.00354673 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.05505e-05 GaussianMLPPolicy/LossBefore 4.18723e-09 GaussianMLPPolicy/dLoss -3.05463e-05 Iteration 189 MetaTest/Average/AverageDiscountedReturn -176.818 MetaTest/Average/AverageReturn -176.818 MetaTest/Average/Iteration 189 MetaTest/Average/MaxReturn -153.283 MetaTest/Average/MinReturn -235.618 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.417 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.818 MetaTest/__unnamed_task__/AverageReturn -176.818 MetaTest/__unnamed_task__/Iteration 189 MetaTest/__unnamed_task__/MaxReturn -153.283 MetaTest/__unnamed_task__/MinReturn -235.618 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.417 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.08e+06 __unnamed_task__/AverageDiscountedReturn -73.3268 __unnamed_task__/AverageReturn -174.351 __unnamed_task__/Iteration 189 __unnamed_task__/MaxReturn -152.691 __unnamed_task__/MinReturn -233.951 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.0583 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 09:48:47 | [maml_trainer] epoch #190 | Sampling for adapation and meta-testing... 2025-04-03 09:49:57 | [maml_trainer] epoch #190 | Finished meta-testing... 2025-04-03 09:49:57 | [maml_trainer] epoch #190 | Saving snapshot... 2025-04-03 09:50:20 | [maml_trainer] epoch #190 | Saved 2025-04-03 09:50:20 | [maml_trainer] epoch #190 | Time 72898.42 s 2025-04-03 09:50:20 | [maml_trainer] epoch #190 | EpochTime 374.57 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.1794 Average/AverageReturn -171.868 Average/Iteration 190 Average/MaxReturn -151.68 Average/MinReturn -238.28 Average/NumEpisodes 80 Average/StdReturn 17.4344 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4804 GaussianMLPPolicy/KLAfter 0.0034989 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.11826e-06 GaussianMLPPolicy/LossBefore -7.51019e-09 GaussianMLPPolicy/dLoss 8.11075e-06 Iteration 190 MetaTest/Average/AverageDiscountedReturn -165.575 MetaTest/Average/AverageReturn -165.575 MetaTest/Average/Iteration 190 MetaTest/Average/MaxReturn -151.023 MetaTest/Average/MinReturn -175.477 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.76388 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.575 MetaTest/__unnamed_task__/AverageReturn -165.575 MetaTest/__unnamed_task__/Iteration 190 MetaTest/__unnamed_task__/MaxReturn -151.023 MetaTest/__unnamed_task__/MinReturn -175.477 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.76388 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.112e+06 __unnamed_task__/AverageDiscountedReturn -72.1794 __unnamed_task__/AverageReturn -171.868 __unnamed_task__/Iteration 190 __unnamed_task__/MaxReturn -151.68 __unnamed_task__/MinReturn -238.28 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.4344 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 09:55:11 | [maml_trainer] epoch #191 | Sampling for adapation and meta-testing... 2025-04-03 09:56:24 | [maml_trainer] epoch #191 | Finished meta-testing... 2025-04-03 09:56:24 | [maml_trainer] epoch #191 | Saving snapshot... 2025-04-03 09:56:47 | [maml_trainer] epoch #191 | Saved 2025-04-03 09:56:47 | [maml_trainer] epoch #191 | Time 73285.62 s 2025-04-03 09:56:47 | [maml_trainer] epoch #191 | EpochTime 387.19 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.2354 Average/AverageReturn -174.645 Average/Iteration 191 Average/MaxReturn -151.594 Average/MinReturn -270.829 Average/NumEpisodes 80 Average/StdReturn 19.7564 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4757 GaussianMLPPolicy/KLAfter 0.00394861 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.74253e-05 GaussianMLPPolicy/LossBefore -1.56462e-09 GaussianMLPPolicy/dLoss -4.74269e-05 Iteration 191 MetaTest/Average/AverageDiscountedReturn -169.466 MetaTest/Average/AverageReturn -169.466 MetaTest/Average/Iteration 191 MetaTest/Average/MaxReturn -155.407 MetaTest/Average/MinReturn -220.426 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.9617 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.466 MetaTest/__unnamed_task__/AverageReturn -169.466 MetaTest/__unnamed_task__/Iteration 191 MetaTest/__unnamed_task__/MaxReturn -155.407 MetaTest/__unnamed_task__/MinReturn -220.426 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.9617 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.144e+06 __unnamed_task__/AverageDiscountedReturn -73.2354 __unnamed_task__/AverageReturn -174.645 __unnamed_task__/Iteration 191 __unnamed_task__/MaxReturn -151.594 __unnamed_task__/MinReturn -270.829 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.7564 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 10:01:41 | [maml_trainer] epoch #192 | Sampling for adapation and meta-testing... 2025-04-03 10:02:53 | [maml_trainer] epoch #192 | Finished meta-testing... 2025-04-03 10:02:53 | [maml_trainer] epoch #192 | Saving snapshot... 2025-04-03 10:03:15 | [maml_trainer] epoch #192 | Saved 2025-04-03 10:03:15 | [maml_trainer] epoch #192 | Time 73673.93 s 2025-04-03 10:03:15 | [maml_trainer] epoch #192 | EpochTime 388.31 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.6543 Average/AverageReturn -173.293 Average/Iteration 192 Average/MaxReturn -143.065 Average/MinReturn -226.143 Average/NumEpisodes 80 Average/StdReturn 16.9801 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4693 GaussianMLPPolicy/KLAfter 0.00611636 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.54909e-05 GaussianMLPPolicy/LossBefore -1.56462e-09 GaussianMLPPolicy/dLoss 3.54894e-05 Iteration 192 MetaTest/Average/AverageDiscountedReturn -173.424 MetaTest/Average/AverageReturn -173.424 MetaTest/Average/Iteration 192 MetaTest/Average/MaxReturn -150.616 MetaTest/Average/MinReturn -255.521 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.5029 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.424 MetaTest/__unnamed_task__/AverageReturn -173.424 MetaTest/__unnamed_task__/Iteration 192 MetaTest/__unnamed_task__/MaxReturn -150.616 MetaTest/__unnamed_task__/MinReturn -255.521 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.5029 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.176e+06 __unnamed_task__/AverageDiscountedReturn -72.6543 __unnamed_task__/AverageReturn -173.293 __unnamed_task__/Iteration 192 __unnamed_task__/MaxReturn -143.065 __unnamed_task__/MinReturn -226.143 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.9801 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 10:08:06 | [maml_trainer] epoch #193 | Sampling for adapation and meta-testing... 2025-04-03 10:09:18 | [maml_trainer] epoch #193 | Finished meta-testing... 2025-04-03 10:09:18 | [maml_trainer] epoch #193 | Saving snapshot... 2025-04-03 10:09:42 | [maml_trainer] epoch #193 | Saved 2025-04-03 10:09:42 | [maml_trainer] epoch #193 | Time 74060.54 s 2025-04-03 10:09:42 | [maml_trainer] epoch #193 | EpochTime 386.60 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.2135 Average/AverageReturn -172.01 Average/Iteration 193 Average/MaxReturn -152.824 Average/MinReturn -222.3 Average/NumEpisodes 80 Average/StdReturn 15.4261 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4634 GaussianMLPPolicy/KLAfter 0.00441854 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.57083e-05 GaussianMLPPolicy/LossBefore 1.89245e-09 GaussianMLPPolicy/dLoss 1.57102e-05 Iteration 193 MetaTest/Average/AverageDiscountedReturn -169.785 MetaTest/Average/AverageReturn -169.785 MetaTest/Average/Iteration 193 MetaTest/Average/MaxReturn -149.735 MetaTest/Average/MinReturn -220.124 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.9628 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.785 MetaTest/__unnamed_task__/AverageReturn -169.785 MetaTest/__unnamed_task__/Iteration 193 MetaTest/__unnamed_task__/MaxReturn -149.735 MetaTest/__unnamed_task__/MinReturn -220.124 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.9628 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.208e+06 __unnamed_task__/AverageDiscountedReturn -72.2135 __unnamed_task__/AverageReturn -172.01 __unnamed_task__/Iteration 193 __unnamed_task__/MaxReturn -152.824 __unnamed_task__/MinReturn -222.3 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.4261 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 10:14:35 | [maml_trainer] epoch #194 | Sampling for adapation and meta-testing... 2025-04-03 10:15:48 | [maml_trainer] epoch #194 | Finished meta-testing... 2025-04-03 10:15:48 | [maml_trainer] epoch #194 | Saving snapshot... 2025-04-03 10:16:12 | [maml_trainer] epoch #194 | Saved 2025-04-03 10:16:12 | [maml_trainer] epoch #194 | Time 74450.15 s 2025-04-03 10:16:12 | [maml_trainer] epoch #194 | EpochTime 389.61 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.4604 Average/AverageReturn -170.759 Average/Iteration 194 Average/MaxReturn -148.644 Average/MinReturn -229.209 Average/NumEpisodes 80 Average/StdReturn 15.4885 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4569 GaussianMLPPolicy/KLAfter 0.00460288 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.22281e-06 GaussianMLPPolicy/LossBefore 8.10623e-09 GaussianMLPPolicy/dLoss 6.23092e-06 Iteration 194 MetaTest/Average/AverageDiscountedReturn -175.066 MetaTest/Average/AverageReturn -175.066 MetaTest/Average/Iteration 194 MetaTest/Average/MaxReturn -146.831 MetaTest/Average/MinReturn -249.595 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.4845 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.066 MetaTest/__unnamed_task__/AverageReturn -175.066 MetaTest/__unnamed_task__/Iteration 194 MetaTest/__unnamed_task__/MaxReturn -146.831 MetaTest/__unnamed_task__/MinReturn -249.595 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.4845 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.24e+06 __unnamed_task__/AverageDiscountedReturn -71.4604 __unnamed_task__/AverageReturn -170.759 __unnamed_task__/Iteration 194 __unnamed_task__/MaxReturn -148.644 __unnamed_task__/MinReturn -229.209 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.4885 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 10:21:06 | [maml_trainer] epoch #195 | Sampling for adapation and meta-testing... 2025-04-03 10:22:19 | [maml_trainer] epoch #195 | Finished meta-testing... 2025-04-03 10:22:19 | [maml_trainer] epoch #195 | Saving snapshot... 2025-04-03 10:22:43 | [maml_trainer] epoch #195 | Saved 2025-04-03 10:22:43 | [maml_trainer] epoch #195 | Time 74841.23 s 2025-04-03 10:22:43 | [maml_trainer] epoch #195 | EpochTime 391.08 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.569 Average/AverageReturn -173.541 Average/Iteration 195 Average/MaxReturn -148.751 Average/MinReturn -229.753 Average/NumEpisodes 80 Average/StdReturn 14.4051 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4514 GaussianMLPPolicy/KLAfter 0.00334807 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.41809e-05 GaussianMLPPolicy/LossBefore -8.19564e-09 GaussianMLPPolicy/dLoss 2.41727e-05 Iteration 195 MetaTest/Average/AverageDiscountedReturn -174.684 MetaTest/Average/AverageReturn -174.684 MetaTest/Average/Iteration 195 MetaTest/Average/MaxReturn -153.499 MetaTest/Average/MinReturn -219.68 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.5744 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.684 MetaTest/__unnamed_task__/AverageReturn -174.684 MetaTest/__unnamed_task__/Iteration 195 MetaTest/__unnamed_task__/MaxReturn -153.499 MetaTest/__unnamed_task__/MinReturn -219.68 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.5744 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.272e+06 __unnamed_task__/AverageDiscountedReturn -72.569 __unnamed_task__/AverageReturn -173.541 __unnamed_task__/Iteration 195 __unnamed_task__/MaxReturn -148.751 __unnamed_task__/MinReturn -229.753 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.4051 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 10:27:39 | [maml_trainer] epoch #196 | Sampling for adapation and meta-testing... 2025-04-03 10:28:51 | [maml_trainer] epoch #196 | Finished meta-testing... 2025-04-03 10:28:51 | [maml_trainer] epoch #196 | Saving snapshot... 2025-04-03 10:29:14 | [maml_trainer] epoch #196 | Saved 2025-04-03 10:29:14 | [maml_trainer] epoch #196 | Time 75232.46 s 2025-04-03 10:29:14 | [maml_trainer] epoch #196 | EpochTime 391.23 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.0535 Average/AverageReturn -169.019 Average/Iteration 196 Average/MaxReturn -149.711 Average/MinReturn -230.572 Average/NumEpisodes 80 Average/StdReturn 12.9821 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4464 GaussianMLPPolicy/KLAfter 0.00261421 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.97768e-06 GaussianMLPPolicy/LossBefore -2.83122e-09 GaussianMLPPolicy/dLoss 2.97485e-06 Iteration 196 MetaTest/Average/AverageDiscountedReturn -171.325 MetaTest/Average/AverageReturn -171.325 MetaTest/Average/Iteration 196 MetaTest/Average/MaxReturn -155.191 MetaTest/Average/MinReturn -216.619 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.3194 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.325 MetaTest/__unnamed_task__/AverageReturn -171.325 MetaTest/__unnamed_task__/Iteration 196 MetaTest/__unnamed_task__/MaxReturn -155.191 MetaTest/__unnamed_task__/MinReturn -216.619 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.3194 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.304e+06 __unnamed_task__/AverageDiscountedReturn -71.0535 __unnamed_task__/AverageReturn -169.019 __unnamed_task__/Iteration 196 __unnamed_task__/MaxReturn -149.711 __unnamed_task__/MinReturn -230.572 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 12.9821 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 10:34:02 | [maml_trainer] epoch #197 | Sampling for adapation and meta-testing... 2025-04-03 10:35:15 | [maml_trainer] epoch #197 | Finished meta-testing... 2025-04-03 10:35:15 | [maml_trainer] epoch #197 | Saving snapshot... 2025-04-03 10:35:38 | [maml_trainer] epoch #197 | Saved 2025-04-03 10:35:38 | [maml_trainer] epoch #197 | Time 75617.00 s 2025-04-03 10:35:38 | [maml_trainer] epoch #197 | EpochTime 384.54 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.7298 Average/AverageReturn -170.644 Average/Iteration 197 Average/MaxReturn -148.536 Average/MinReturn -235.622 Average/NumEpisodes 80 Average/StdReturn 16.0787 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.44 GaussianMLPPolicy/KLAfter 0.00250695 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.22303e-05 GaussianMLPPolicy/LossBefore -1.19209e-10 GaussianMLPPolicy/dLoss 3.22302e-05 Iteration 197 MetaTest/Average/AverageDiscountedReturn -178.853 MetaTest/Average/AverageReturn -178.853 MetaTest/Average/Iteration 197 MetaTest/Average/MaxReturn -152.601 MetaTest/Average/MinReturn -235.277 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.2293 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -178.853 MetaTest/__unnamed_task__/AverageReturn -178.853 MetaTest/__unnamed_task__/Iteration 197 MetaTest/__unnamed_task__/MaxReturn -152.601 MetaTest/__unnamed_task__/MinReturn -235.277 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.2293 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.336e+06 __unnamed_task__/AverageDiscountedReturn -71.7298 __unnamed_task__/AverageReturn -170.644 __unnamed_task__/Iteration 197 __unnamed_task__/MaxReturn -148.536 __unnamed_task__/MinReturn -235.622 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.0787 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 10:40:32 | [maml_trainer] epoch #198 | Sampling for adapation and meta-testing... 2025-04-03 10:41:44 | [maml_trainer] epoch #198 | Finished meta-testing... 2025-04-03 10:41:44 | [maml_trainer] epoch #198 | Saving snapshot... 2025-04-03 10:42:08 | [maml_trainer] epoch #198 | Saved 2025-04-03 10:42:08 | [maml_trainer] epoch #198 | Time 76006.19 s 2025-04-03 10:42:08 | [maml_trainer] epoch #198 | EpochTime 389.18 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.3742 Average/AverageReturn -170.032 Average/Iteration 198 Average/MaxReturn -151.409 Average/MinReturn -230.068 Average/NumEpisodes 80 Average/StdReturn 12.6645 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4327 GaussianMLPPolicy/KLAfter 0.00380486 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.36153e-06 GaussianMLPPolicy/LossBefore -1.74344e-09 GaussianMLPPolicy/dLoss -9.36328e-06 Iteration 198 MetaTest/Average/AverageDiscountedReturn -178.505 MetaTest/Average/AverageReturn -178.505 MetaTest/Average/Iteration 198 MetaTest/Average/MaxReturn -160.186 MetaTest/Average/MinReturn -221.839 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.9681 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -178.505 MetaTest/__unnamed_task__/AverageReturn -178.505 MetaTest/__unnamed_task__/Iteration 198 MetaTest/__unnamed_task__/MaxReturn -160.186 MetaTest/__unnamed_task__/MinReturn -221.839 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.9681 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.368e+06 __unnamed_task__/AverageDiscountedReturn -71.3742 __unnamed_task__/AverageReturn -170.032 __unnamed_task__/Iteration 198 __unnamed_task__/MaxReturn -151.409 __unnamed_task__/MinReturn -230.068 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 12.6645 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 10:47:04 | [maml_trainer] epoch #199 | Sampling for adapation and meta-testing... 2025-04-03 10:48:16 | [maml_trainer] epoch #199 | Finished meta-testing... 2025-04-03 10:48:16 | [maml_trainer] epoch #199 | Saving snapshot... 2025-04-03 10:48:40 | [maml_trainer] epoch #199 | Saved 2025-04-03 10:48:40 | [maml_trainer] epoch #199 | Time 76398.56 s 2025-04-03 10:48:40 | [maml_trainer] epoch #199 | EpochTime 392.37 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.3596 Average/AverageReturn -172.166 Average/Iteration 199 Average/MaxReturn -154.617 Average/MinReturn -250.916 Average/NumEpisodes 80 Average/StdReturn 18.3191 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4259 GaussianMLPPolicy/KLAfter 0.00374439 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.78124e-06 GaussianMLPPolicy/LossBefore 6.67572e-09 GaussianMLPPolicy/dLoss 7.78791e-06 Iteration 199 MetaTest/Average/AverageDiscountedReturn -170.35 MetaTest/Average/AverageReturn -170.35 MetaTest/Average/Iteration 199 MetaTest/Average/MaxReturn -153.922 MetaTest/Average/MinReturn -206.514 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.5206 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.35 MetaTest/__unnamed_task__/AverageReturn -170.35 MetaTest/__unnamed_task__/Iteration 199 MetaTest/__unnamed_task__/MaxReturn -153.922 MetaTest/__unnamed_task__/MinReturn -206.514 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.5206 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.4e+06 __unnamed_task__/AverageDiscountedReturn -72.3596 __unnamed_task__/AverageReturn -172.166 __unnamed_task__/Iteration 199 __unnamed_task__/MaxReturn -154.617 __unnamed_task__/MinReturn -250.916 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.3191 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 10:53:36 | [maml_trainer] epoch #200 | Sampling for adapation and meta-testing... 2025-04-03 10:54:48 | [maml_trainer] epoch #200 | Finished meta-testing... 2025-04-03 10:54:48 | [maml_trainer] epoch #200 | Saving snapshot... 2025-04-03 10:55:10 | [maml_trainer] epoch #200 | Saved 2025-04-03 10:55:10 | [maml_trainer] epoch #200 | Time 76789.00 s 2025-04-03 10:55:10 | [maml_trainer] epoch #200 | EpochTime 390.44 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.3406 Average/AverageReturn -172.282 Average/Iteration 200 Average/MaxReturn -119.738 Average/MinReturn -250.411 Average/NumEpisodes 80 Average/StdReturn 17.9517 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4205 GaussianMLPPolicy/KLAfter 0.00425712 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.52458e-06 GaussianMLPPolicy/LossBefore -4.67896e-09 GaussianMLPPolicy/dLoss 7.5199e-06 Iteration 200 MetaTest/Average/AverageDiscountedReturn -174.059 MetaTest/Average/AverageReturn -174.059 MetaTest/Average/Iteration 200 MetaTest/Average/MaxReturn -157.483 MetaTest/Average/MinReturn -234.855 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.306 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.059 MetaTest/__unnamed_task__/AverageReturn -174.059 MetaTest/__unnamed_task__/Iteration 200 MetaTest/__unnamed_task__/MaxReturn -157.483 MetaTest/__unnamed_task__/MinReturn -234.855 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.306 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.432e+06 __unnamed_task__/AverageDiscountedReturn -72.3406 __unnamed_task__/AverageReturn -172.282 __unnamed_task__/Iteration 200 __unnamed_task__/MaxReturn -119.738 __unnamed_task__/MinReturn -250.411 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.9517 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 11:00:05 | [maml_trainer] epoch #201 | Sampling for adapation and meta-testing... 2025-04-03 11:01:18 | [maml_trainer] epoch #201 | Finished meta-testing... 2025-04-03 11:01:18 | [maml_trainer] epoch #201 | Saving snapshot... 2025-04-03 11:01:40 | [maml_trainer] epoch #201 | Saved 2025-04-03 11:01:40 | [maml_trainer] epoch #201 | Time 77178.84 s 2025-04-03 11:01:40 | [maml_trainer] epoch #201 | EpochTime 389.84 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.7318 Average/AverageReturn -175.446 Average/Iteration 201 Average/MaxReturn -151.226 Average/MinReturn -254.565 Average/NumEpisodes 80 Average/StdReturn 19.4602 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4162 GaussianMLPPolicy/KLAfter 0.00337832 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000119648 GaussianMLPPolicy/LossBefore 4.14252e-09 GaussianMLPPolicy/dLoss -0.000119644 Iteration 201 MetaTest/Average/AverageDiscountedReturn -171.998 MetaTest/Average/AverageReturn -171.998 MetaTest/Average/Iteration 201 MetaTest/Average/MaxReturn -153.857 MetaTest/Average/MinReturn -222.988 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.8082 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.998 MetaTest/__unnamed_task__/AverageReturn -171.998 MetaTest/__unnamed_task__/Iteration 201 MetaTest/__unnamed_task__/MaxReturn -153.857 MetaTest/__unnamed_task__/MinReturn -222.988 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.8082 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.464e+06 __unnamed_task__/AverageDiscountedReturn -73.7318 __unnamed_task__/AverageReturn -175.446 __unnamed_task__/Iteration 201 __unnamed_task__/MaxReturn -151.226 __unnamed_task__/MinReturn -254.565 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.4602 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 11:06:34 | [maml_trainer] epoch #202 | Sampling for adapation and meta-testing... 2025-04-03 11:07:47 | [maml_trainer] epoch #202 | Finished meta-testing... 2025-04-03 11:07:47 | [maml_trainer] epoch #202 | Saving snapshot... 2025-04-03 11:08:10 | [maml_trainer] epoch #202 | Saved 2025-04-03 11:08:10 | [maml_trainer] epoch #202 | Time 77568.76 s 2025-04-03 11:08:10 | [maml_trainer] epoch #202 | EpochTime 389.92 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.3048 Average/AverageReturn -172.325 Average/Iteration 202 Average/MaxReturn -153.732 Average/MinReturn -234.398 Average/NumEpisodes 80 Average/StdReturn 15.4998 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4113 GaussianMLPPolicy/KLAfter 0.003396 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.29593e-05 GaussianMLPPolicy/LossBefore 4.93228e-09 GaussianMLPPolicy/dLoss -2.29543e-05 Iteration 202 MetaTest/Average/AverageDiscountedReturn -173.854 MetaTest/Average/AverageReturn -173.854 MetaTest/Average/Iteration 202 MetaTest/Average/MaxReturn -156.38 MetaTest/Average/MinReturn -229.534 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.0335 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.854 MetaTest/__unnamed_task__/AverageReturn -173.854 MetaTest/__unnamed_task__/Iteration 202 MetaTest/__unnamed_task__/MaxReturn -156.38 MetaTest/__unnamed_task__/MinReturn -229.534 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.0335 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.496e+06 __unnamed_task__/AverageDiscountedReturn -72.3048 __unnamed_task__/AverageReturn -172.325 __unnamed_task__/Iteration 202 __unnamed_task__/MaxReturn -153.732 __unnamed_task__/MinReturn -234.398 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.4998 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 11:13:02 | [maml_trainer] epoch #203 | Sampling for adapation and meta-testing... 2025-04-03 11:14:15 | [maml_trainer] epoch #203 | Finished meta-testing... 2025-04-03 11:14:15 | [maml_trainer] epoch #203 | Saving snapshot... 2025-04-03 11:14:39 | [maml_trainer] epoch #203 | Saved 2025-04-03 11:14:39 | [maml_trainer] epoch #203 | Time 77957.60 s 2025-04-03 11:14:39 | [maml_trainer] epoch #203 | EpochTime 388.83 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.3215 Average/AverageReturn -172.099 Average/Iteration 203 Average/MaxReturn -149.741 Average/MinReturn -227.808 Average/NumEpisodes 80 Average/StdReturn 13.2421 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.407 GaussianMLPPolicy/KLAfter 0.00259991 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.35972e-05 GaussianMLPPolicy/LossBefore 2.83122e-10 GaussianMLPPolicy/dLoss -3.35969e-05 Iteration 203 MetaTest/Average/AverageDiscountedReturn -168.546 MetaTest/Average/AverageReturn -168.546 MetaTest/Average/Iteration 203 MetaTest/Average/MaxReturn -157.366 MetaTest/Average/MinReturn -183.89 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.28675 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.546 MetaTest/__unnamed_task__/AverageReturn -168.546 MetaTest/__unnamed_task__/Iteration 203 MetaTest/__unnamed_task__/MaxReturn -157.366 MetaTest/__unnamed_task__/MinReturn -183.89 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.28675 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.528e+06 __unnamed_task__/AverageDiscountedReturn -72.3215 __unnamed_task__/AverageReturn -172.099 __unnamed_task__/Iteration 203 __unnamed_task__/MaxReturn -149.741 __unnamed_task__/MinReturn -227.808 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 13.2421 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 11:19:33 | [maml_trainer] epoch #204 | Sampling for adapation and meta-testing... 2025-04-03 11:20:47 | [maml_trainer] epoch #204 | Finished meta-testing... 2025-04-03 11:20:47 | [maml_trainer] epoch #204 | Saving snapshot... 2025-04-03 11:21:11 | [maml_trainer] epoch #204 | Saved 2025-04-03 11:21:11 | [maml_trainer] epoch #204 | Time 78349.40 s 2025-04-03 11:21:11 | [maml_trainer] epoch #204 | EpochTime 391.80 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.7332 Average/AverageReturn -172.374 Average/Iteration 204 Average/MaxReturn -151.481 Average/MinReturn -240.545 Average/NumEpisodes 80 Average/StdReturn 15.496 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4039 GaussianMLPPolicy/KLAfter 0.00482965 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.47903e-05 GaussianMLPPolicy/LossBefore 2.5183e-09 GaussianMLPPolicy/dLoss 1.47929e-05 Iteration 204 MetaTest/Average/AverageDiscountedReturn -179.001 MetaTest/Average/AverageReturn -179.001 MetaTest/Average/Iteration 204 MetaTest/Average/MaxReturn -156.937 MetaTest/Average/MinReturn -247.703 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.1344 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -179.001 MetaTest/__unnamed_task__/AverageReturn -179.001 MetaTest/__unnamed_task__/Iteration 204 MetaTest/__unnamed_task__/MaxReturn -156.937 MetaTest/__unnamed_task__/MinReturn -247.703 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.1344 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.56e+06 __unnamed_task__/AverageDiscountedReturn -72.7332 __unnamed_task__/AverageReturn -172.374 __unnamed_task__/Iteration 204 __unnamed_task__/MaxReturn -151.481 __unnamed_task__/MinReturn -240.545 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.496 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 11:26:05 | [maml_trainer] epoch #205 | Sampling for adapation and meta-testing... 2025-04-03 11:27:18 | [maml_trainer] epoch #205 | Finished meta-testing... 2025-04-03 11:27:18 | [maml_trainer] epoch #205 | Saving snapshot... 2025-04-03 11:27:41 | [maml_trainer] epoch #205 | Saved 2025-04-03 11:27:41 | [maml_trainer] epoch #205 | Time 78739.23 s 2025-04-03 11:27:41 | [maml_trainer] epoch #205 | EpochTime 389.82 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.4171 Average/AverageReturn -169.618 Average/Iteration 205 Average/MaxReturn -151.861 Average/MinReturn -229.365 Average/NumEpisodes 80 Average/StdReturn 12.1097 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4022 GaussianMLPPolicy/KLAfter 0.00370394 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.62171e-06 GaussianMLPPolicy/LossBefore -1.89245e-09 GaussianMLPPolicy/dLoss 2.61982e-06 Iteration 205 MetaTest/Average/AverageDiscountedReturn -176.204 MetaTest/Average/AverageReturn -176.204 MetaTest/Average/Iteration 205 MetaTest/Average/MaxReturn -155.965 MetaTest/Average/MinReturn -212.274 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.242 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.204 MetaTest/__unnamed_task__/AverageReturn -176.204 MetaTest/__unnamed_task__/Iteration 205 MetaTest/__unnamed_task__/MaxReturn -155.965 MetaTest/__unnamed_task__/MinReturn -212.274 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.242 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.592e+06 __unnamed_task__/AverageDiscountedReturn -71.4171 __unnamed_task__/AverageReturn -169.618 __unnamed_task__/Iteration 205 __unnamed_task__/MaxReturn -151.861 __unnamed_task__/MinReturn -229.365 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 12.1097 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 11:32:33 | [maml_trainer] epoch #206 | Sampling for adapation and meta-testing... 2025-04-03 11:33:46 | [maml_trainer] epoch #206 | Finished meta-testing... 2025-04-03 11:33:46 | [maml_trainer] epoch #206 | Saving snapshot... 2025-04-03 11:34:09 | [maml_trainer] epoch #206 | Saved 2025-04-03 11:34:09 | [maml_trainer] epoch #206 | Time 79127.57 s 2025-04-03 11:34:09 | [maml_trainer] epoch #206 | EpochTime 388.34 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.8731 Average/AverageReturn -173.366 Average/Iteration 206 Average/MaxReturn -151.412 Average/MinReturn -240.445 Average/NumEpisodes 80 Average/StdReturn 19.0948 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.4012 GaussianMLPPolicy/KLAfter 0.00340824 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.35096e-05 GaussianMLPPolicy/LossBefore 4.26173e-09 GaussianMLPPolicy/dLoss -2.35053e-05 Iteration 206 MetaTest/Average/AverageDiscountedReturn -172.852 MetaTest/Average/AverageReturn -172.852 MetaTest/Average/Iteration 206 MetaTest/Average/MaxReturn -149.551 MetaTest/Average/MinReturn -225.42 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.5318 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.852 MetaTest/__unnamed_task__/AverageReturn -172.852 MetaTest/__unnamed_task__/Iteration 206 MetaTest/__unnamed_task__/MaxReturn -149.551 MetaTest/__unnamed_task__/MinReturn -225.42 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.5318 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.624e+06 __unnamed_task__/AverageDiscountedReturn -72.8731 __unnamed_task__/AverageReturn -173.366 __unnamed_task__/Iteration 206 __unnamed_task__/MaxReturn -151.412 __unnamed_task__/MinReturn -240.445 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.0948 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 11:39:00 | [maml_trainer] epoch #207 | Sampling for adapation and meta-testing... 2025-04-03 11:40:13 | [maml_trainer] epoch #207 | Finished meta-testing... 2025-04-03 11:40:13 | [maml_trainer] epoch #207 | Saving snapshot... 2025-04-03 11:40:37 | [maml_trainer] epoch #207 | Saved 2025-04-03 11:40:37 | [maml_trainer] epoch #207 | Time 79515.13 s 2025-04-03 11:40:37 | [maml_trainer] epoch #207 | EpochTime 387.55 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.411 Average/AverageReturn -169.181 Average/Iteration 207 Average/MaxReturn -145.279 Average/MinReturn -200.278 Average/NumEpisodes 80 Average/StdReturn 9.08822 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3996 GaussianMLPPolicy/KLAfter 0.00316732 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.83874e-06 GaussianMLPPolicy/LossBefore 4.11272e-09 GaussianMLPPolicy/dLoss 5.84285e-06 Iteration 207 MetaTest/Average/AverageDiscountedReturn -169.184 MetaTest/Average/AverageReturn -169.184 MetaTest/Average/Iteration 207 MetaTest/Average/MaxReturn -157.929 MetaTest/Average/MinReturn -185.371 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.10823 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.184 MetaTest/__unnamed_task__/AverageReturn -169.184 MetaTest/__unnamed_task__/Iteration 207 MetaTest/__unnamed_task__/MaxReturn -157.929 MetaTest/__unnamed_task__/MinReturn -185.371 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.10823 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.656e+06 __unnamed_task__/AverageDiscountedReturn -71.411 __unnamed_task__/AverageReturn -169.181 __unnamed_task__/Iteration 207 __unnamed_task__/MaxReturn -145.279 __unnamed_task__/MinReturn -200.278 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 9.08822 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 11:45:32 | [maml_trainer] epoch #208 | Sampling for adapation and meta-testing... 2025-04-03 11:46:45 | [maml_trainer] epoch #208 | Finished meta-testing... 2025-04-03 11:46:45 | [maml_trainer] epoch #208 | Saving snapshot... 2025-04-03 11:47:08 | [maml_trainer] epoch #208 | Saved 2025-04-03 11:47:08 | [maml_trainer] epoch #208 | Time 79907.10 s 2025-04-03 11:47:08 | [maml_trainer] epoch #208 | EpochTime 391.97 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.0881 Average/AverageReturn -173.451 Average/Iteration 208 Average/MaxReturn -152.508 Average/MinReturn -254.375 Average/NumEpisodes 80 Average/StdReturn 18.1932 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3964 GaussianMLPPolicy/KLAfter 0.00250068 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.1465e-05 GaussianMLPPolicy/LossBefore 1.66893e-09 GaussianMLPPolicy/dLoss -1.14633e-05 Iteration 208 MetaTest/Average/AverageDiscountedReturn -174.085 MetaTest/Average/AverageReturn -174.085 MetaTest/Average/Iteration 208 MetaTest/Average/MaxReturn -160.104 MetaTest/Average/MinReturn -219.369 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.6972 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.085 MetaTest/__unnamed_task__/AverageReturn -174.085 MetaTest/__unnamed_task__/Iteration 208 MetaTest/__unnamed_task__/MaxReturn -160.104 MetaTest/__unnamed_task__/MinReturn -219.369 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.6972 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.688e+06 __unnamed_task__/AverageDiscountedReturn -73.0881 __unnamed_task__/AverageReturn -173.451 __unnamed_task__/Iteration 208 __unnamed_task__/MaxReturn -152.508 __unnamed_task__/MinReturn -254.375 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.1932 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 11:52:05 | [maml_trainer] epoch #209 | Sampling for adapation and meta-testing... 2025-04-03 11:53:19 | [maml_trainer] epoch #209 | Finished meta-testing... 2025-04-03 11:53:19 | [maml_trainer] epoch #209 | Saving snapshot... 2025-04-03 11:53:42 | [maml_trainer] epoch #209 | Saved 2025-04-03 11:53:42 | [maml_trainer] epoch #209 | Time 80300.38 s 2025-04-03 11:53:42 | [maml_trainer] epoch #209 | EpochTime 393.28 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.2161 Average/AverageReturn -174.095 Average/Iteration 209 Average/MaxReturn -153.926 Average/MinReturn -248.431 Average/NumEpisodes 80 Average/StdReturn 15.2016 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3944 GaussianMLPPolicy/KLAfter 0.00238754 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.39746e-05 GaussianMLPPolicy/LossBefore 7.15256e-09 GaussianMLPPolicy/dLoss -1.39674e-05 Iteration 209 MetaTest/Average/AverageDiscountedReturn -179.621 MetaTest/Average/AverageReturn -179.621 MetaTest/Average/Iteration 209 MetaTest/Average/MaxReturn -157.865 MetaTest/Average/MinReturn -236.342 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.9299 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -179.621 MetaTest/__unnamed_task__/AverageReturn -179.621 MetaTest/__unnamed_task__/Iteration 209 MetaTest/__unnamed_task__/MaxReturn -157.865 MetaTest/__unnamed_task__/MinReturn -236.342 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.9299 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.72e+06 __unnamed_task__/AverageDiscountedReturn -73.2161 __unnamed_task__/AverageReturn -174.095 __unnamed_task__/Iteration 209 __unnamed_task__/MaxReturn -153.926 __unnamed_task__/MinReturn -248.431 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.2016 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 11:58:36 | [maml_trainer] epoch #210 | Sampling for adapation and meta-testing... 2025-04-03 11:59:49 | [maml_trainer] epoch #210 | Finished meta-testing... 2025-04-03 11:59:49 | [maml_trainer] epoch #210 | Saving snapshot... 2025-04-03 12:00:13 | [maml_trainer] epoch #210 | Saved 2025-04-03 12:00:13 | [maml_trainer] epoch #210 | Time 80691.23 s 2025-04-03 12:00:13 | [maml_trainer] epoch #210 | EpochTime 390.85 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.1016 Average/AverageReturn -174.082 Average/Iteration 210 Average/MaxReturn -153.492 Average/MinReturn -235.94 Average/NumEpisodes 80 Average/StdReturn 14.5668 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.393 GaussianMLPPolicy/KLAfter 0.00210559 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.23695e-05 GaussianMLPPolicy/LossBefore 7.15256e-10 GaussianMLPPolicy/dLoss 1.23702e-05 Iteration 210 MetaTest/Average/AverageDiscountedReturn -174.008 MetaTest/Average/AverageReturn -174.008 MetaTest/Average/Iteration 210 MetaTest/Average/MaxReturn -157.768 MetaTest/Average/MinReturn -227.339 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.667 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.008 MetaTest/__unnamed_task__/AverageReturn -174.008 MetaTest/__unnamed_task__/Iteration 210 MetaTest/__unnamed_task__/MaxReturn -157.768 MetaTest/__unnamed_task__/MinReturn -227.339 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.667 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.752e+06 __unnamed_task__/AverageDiscountedReturn -73.1016 __unnamed_task__/AverageReturn -174.082 __unnamed_task__/Iteration 210 __unnamed_task__/MaxReturn -153.492 __unnamed_task__/MinReturn -235.94 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.5668 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 12:05:06 | [maml_trainer] epoch #211 | Sampling for adapation and meta-testing... 2025-04-03 12:06:20 | [maml_trainer] epoch #211 | Finished meta-testing... 2025-04-03 12:06:20 | [maml_trainer] epoch #211 | Saving snapshot... 2025-04-03 12:06:44 | [maml_trainer] epoch #211 | Saved 2025-04-03 12:06:44 | [maml_trainer] epoch #211 | Time 81082.22 s 2025-04-03 12:06:44 | [maml_trainer] epoch #211 | EpochTime 390.98 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -75.2211 Average/AverageReturn -178.333 Average/Iteration 211 Average/MaxReturn -150.211 Average/MinReturn -248.349 Average/NumEpisodes 80 Average/StdReturn 22.3911 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3913 GaussianMLPPolicy/KLAfter 0.00196841 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.37948e-06 GaussianMLPPolicy/LossBefore 1.84774e-09 GaussianMLPPolicy/dLoss -3.37763e-06 Iteration 211 MetaTest/Average/AverageDiscountedReturn -170.131 MetaTest/Average/AverageReturn -170.131 MetaTest/Average/Iteration 211 MetaTest/Average/MaxReturn -159.123 MetaTest/Average/MinReturn -181.074 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.73866 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.131 MetaTest/__unnamed_task__/AverageReturn -170.131 MetaTest/__unnamed_task__/Iteration 211 MetaTest/__unnamed_task__/MaxReturn -159.123 MetaTest/__unnamed_task__/MinReturn -181.074 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.73866 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.784e+06 __unnamed_task__/AverageDiscountedReturn -75.2211 __unnamed_task__/AverageReturn -178.333 __unnamed_task__/Iteration 211 __unnamed_task__/MaxReturn -150.211 __unnamed_task__/MinReturn -248.349 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.3911 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 12:11:40 | [maml_trainer] epoch #212 | Sampling for adapation and meta-testing... 2025-04-03 12:12:52 | [maml_trainer] epoch #212 | Finished meta-testing... 2025-04-03 12:12:52 | [maml_trainer] epoch #212 | Saving snapshot... 2025-04-03 12:13:15 | [maml_trainer] epoch #212 | Saved 2025-04-03 12:13:15 | [maml_trainer] epoch #212 | Time 81473.78 s 2025-04-03 12:13:15 | [maml_trainer] epoch #212 | EpochTime 391.56 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.5858 Average/AverageReturn -172.018 Average/Iteration 212 Average/MaxReturn -157.63 Average/MinReturn -228.184 Average/NumEpisodes 80 Average/StdReturn 11.6646 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.39 GaussianMLPPolicy/KLAfter 0.00190608 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.66599e-05 GaussianMLPPolicy/LossBefore -3.21865e-09 GaussianMLPPolicy/dLoss -1.66631e-05 Iteration 212 MetaTest/Average/AverageDiscountedReturn -173.889 MetaTest/Average/AverageReturn -173.889 MetaTest/Average/Iteration 212 MetaTest/Average/MaxReturn -162.263 MetaTest/Average/MinReturn -217.345 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.3053 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.889 MetaTest/__unnamed_task__/AverageReturn -173.889 MetaTest/__unnamed_task__/Iteration 212 MetaTest/__unnamed_task__/MaxReturn -162.263 MetaTest/__unnamed_task__/MinReturn -217.345 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.3053 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.816e+06 __unnamed_task__/AverageDiscountedReturn -72.5858 __unnamed_task__/AverageReturn -172.018 __unnamed_task__/Iteration 212 __unnamed_task__/MaxReturn -157.63 __unnamed_task__/MinReturn -228.184 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 11.6646 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 12:18:07 | [maml_trainer] epoch #213 | Sampling for adapation and meta-testing... 2025-04-03 12:19:20 | [maml_trainer] epoch #213 | Finished meta-testing... 2025-04-03 12:19:20 | [maml_trainer] epoch #213 | Saving snapshot... 2025-04-03 12:19:42 | [maml_trainer] epoch #213 | Saved 2025-04-03 12:19:42 | [maml_trainer] epoch #213 | Time 81860.60 s 2025-04-03 12:19:42 | [maml_trainer] epoch #213 | EpochTime 386.82 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.4341 Average/AverageReturn -174.174 Average/Iteration 213 Average/MaxReturn -130.586 Average/MinReturn -232.057 Average/NumEpisodes 80 Average/StdReturn 18.6317 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3869 GaussianMLPPolicy/KLAfter 0.00170844 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.28664e-07 GaussianMLPPolicy/LossBefore 3.8743e-09 GaussianMLPPolicy/dLoss 5.32538e-07 Iteration 213 MetaTest/Average/AverageDiscountedReturn -173.799 MetaTest/Average/AverageReturn -173.799 MetaTest/Average/Iteration 213 MetaTest/Average/MaxReturn -159.671 MetaTest/Average/MinReturn -234.617 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.5871 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.799 MetaTest/__unnamed_task__/AverageReturn -173.799 MetaTest/__unnamed_task__/Iteration 213 MetaTest/__unnamed_task__/MaxReturn -159.671 MetaTest/__unnamed_task__/MinReturn -234.617 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.5871 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.848e+06 __unnamed_task__/AverageDiscountedReturn -73.4341 __unnamed_task__/AverageReturn -174.174 __unnamed_task__/Iteration 213 __unnamed_task__/MaxReturn -130.586 __unnamed_task__/MinReturn -232.057 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.6317 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 12:24:35 | [maml_trainer] epoch #214 | Sampling for adapation and meta-testing... 2025-04-03 12:25:49 | [maml_trainer] epoch #214 | Finished meta-testing... 2025-04-03 12:25:49 | [maml_trainer] epoch #214 | Saving snapshot... 2025-04-03 12:26:13 | [maml_trainer] epoch #214 | Saved 2025-04-03 12:26:13 | [maml_trainer] epoch #214 | Time 82251.47 s 2025-04-03 12:26:13 | [maml_trainer] epoch #214 | EpochTime 390.87 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.4778 Average/AverageReturn -174.206 Average/Iteration 214 Average/MaxReturn -152.352 Average/MinReturn -235.328 Average/NumEpisodes 80 Average/StdReturn 16.2969 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3847 GaussianMLPPolicy/KLAfter 0.0019233 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.52245e-05 GaussianMLPPolicy/LossBefore -7.52509e-09 GaussianMLPPolicy/dLoss 2.5217e-05 Iteration 214 MetaTest/Average/AverageDiscountedReturn -170.63 MetaTest/Average/AverageReturn -170.63 MetaTest/Average/Iteration 214 MetaTest/Average/MaxReturn -155.797 MetaTest/Average/MinReturn -182.31 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.06693 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.63 MetaTest/__unnamed_task__/AverageReturn -170.63 MetaTest/__unnamed_task__/Iteration 214 MetaTest/__unnamed_task__/MaxReturn -155.797 MetaTest/__unnamed_task__/MinReturn -182.31 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.06693 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.88e+06 __unnamed_task__/AverageDiscountedReturn -73.4778 __unnamed_task__/AverageReturn -174.206 __unnamed_task__/Iteration 214 __unnamed_task__/MaxReturn -152.352 __unnamed_task__/MinReturn -235.328 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.2969 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 12:31:07 | [maml_trainer] epoch #215 | Sampling for adapation and meta-testing... 2025-04-03 12:32:19 | [maml_trainer] epoch #215 | Finished meta-testing... 2025-04-03 12:32:19 | [maml_trainer] epoch #215 | Saving snapshot... 2025-04-03 12:32:42 | [maml_trainer] epoch #215 | Saved 2025-04-03 12:32:42 | [maml_trainer] epoch #215 | Time 82641.02 s 2025-04-03 12:32:42 | [maml_trainer] epoch #215 | EpochTime 389.55 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.7351 Average/AverageReturn -175.191 Average/Iteration 215 Average/MaxReturn -153.223 Average/MinReturn -274.058 Average/NumEpisodes 80 Average/StdReturn 18.7181 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.384 GaussianMLPPolicy/KLAfter 0.00204607 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.95209e-06 GaussianMLPPolicy/LossBefore 3.05474e-09 GaussianMLPPolicy/dLoss -7.94904e-06 Iteration 215 MetaTest/Average/AverageDiscountedReturn -174.386 MetaTest/Average/AverageReturn -174.386 MetaTest/Average/Iteration 215 MetaTest/Average/MaxReturn -159.198 MetaTest/Average/MinReturn -223.089 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.5241 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.386 MetaTest/__unnamed_task__/AverageReturn -174.386 MetaTest/__unnamed_task__/Iteration 215 MetaTest/__unnamed_task__/MaxReturn -159.198 MetaTest/__unnamed_task__/MinReturn -223.089 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.5241 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.912e+06 __unnamed_task__/AverageDiscountedReturn -73.7351 __unnamed_task__/AverageReturn -175.191 __unnamed_task__/Iteration 215 __unnamed_task__/MaxReturn -153.223 __unnamed_task__/MinReturn -274.058 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.7181 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 12:37:33 | [maml_trainer] epoch #216 | Sampling for adapation and meta-testing... 2025-04-03 12:38:47 | [maml_trainer] epoch #216 | Finished meta-testing... 2025-04-03 12:38:47 | [maml_trainer] epoch #216 | Saving snapshot... 2025-04-03 12:39:11 | [maml_trainer] epoch #216 | Saved 2025-04-03 12:39:11 | [maml_trainer] epoch #216 | Time 83029.25 s 2025-04-03 12:39:11 | [maml_trainer] epoch #216 | EpochTime 388.22 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.515 Average/AverageReturn -175.036 Average/Iteration 216 Average/MaxReturn -150.092 Average/MinReturn -253.681 Average/NumEpisodes 80 Average/StdReturn 19.7868 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3818 GaussianMLPPolicy/KLAfter 0.00167913 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.53935e-05 GaussianMLPPolicy/LossBefore -7.30157e-10 GaussianMLPPolicy/dLoss -2.53942e-05 Iteration 216 MetaTest/Average/AverageDiscountedReturn -171.736 MetaTest/Average/AverageReturn -171.736 MetaTest/Average/Iteration 216 MetaTest/Average/MaxReturn -153.818 MetaTest/Average/MinReturn -225.27 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.2821 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.736 MetaTest/__unnamed_task__/AverageReturn -171.736 MetaTest/__unnamed_task__/Iteration 216 MetaTest/__unnamed_task__/MaxReturn -153.818 MetaTest/__unnamed_task__/MinReturn -225.27 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.2821 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.944e+06 __unnamed_task__/AverageDiscountedReturn -73.515 __unnamed_task__/AverageReturn -175.036 __unnamed_task__/Iteration 216 __unnamed_task__/MaxReturn -150.092 __unnamed_task__/MinReturn -253.681 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.7868 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 12:44:05 | [maml_trainer] epoch #217 | Sampling for adapation and meta-testing... 2025-04-03 12:45:19 | [maml_trainer] epoch #217 | Finished meta-testing... 2025-04-03 12:45:19 | [maml_trainer] epoch #217 | Saving snapshot... 2025-04-03 12:45:42 | [maml_trainer] epoch #217 | Saved 2025-04-03 12:45:42 | [maml_trainer] epoch #217 | Time 83420.43 s 2025-04-03 12:45:42 | [maml_trainer] epoch #217 | EpochTime 391.18 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.5474 Average/AverageReturn -172.19 Average/Iteration 217 Average/MaxReturn -152.688 Average/MinReturn -239.071 Average/NumEpisodes 80 Average/StdReturn 17.0115 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3765 GaussianMLPPolicy/KLAfter 0.00230259 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.45145e-05 GaussianMLPPolicy/LossBefore -1.14739e-09 GaussianMLPPolicy/dLoss -2.45156e-05 Iteration 217 MetaTest/Average/AverageDiscountedReturn -171.219 MetaTest/Average/AverageReturn -171.219 MetaTest/Average/Iteration 217 MetaTest/Average/MaxReturn -158.927 MetaTest/Average/MinReturn -185.041 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.49434 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.219 MetaTest/__unnamed_task__/AverageReturn -171.219 MetaTest/__unnamed_task__/Iteration 217 MetaTest/__unnamed_task__/MaxReturn -158.927 MetaTest/__unnamed_task__/MinReturn -185.041 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.49434 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.976e+06 __unnamed_task__/AverageDiscountedReturn -72.5474 __unnamed_task__/AverageReturn -172.19 __unnamed_task__/Iteration 217 __unnamed_task__/MaxReturn -152.688 __unnamed_task__/MinReturn -239.071 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.0115 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 12:50:33 | [maml_trainer] epoch #218 | Sampling for adapation and meta-testing... 2025-04-03 12:51:45 | [maml_trainer] epoch #218 | Finished meta-testing... 2025-04-03 12:51:45 | [maml_trainer] epoch #218 | Saving snapshot... 2025-04-03 12:52:08 | [maml_trainer] epoch #218 | Saved 2025-04-03 12:52:08 | [maml_trainer] epoch #218 | Time 83806.31 s 2025-04-03 12:52:08 | [maml_trainer] epoch #218 | EpochTime 385.88 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.6632 Average/AverageReturn -170.837 Average/Iteration 218 Average/MaxReturn -151.088 Average/MinReturn -243.657 Average/NumEpisodes 80 Average/StdReturn 16.7336 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3728 GaussianMLPPolicy/KLAfter 0.00230569 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.10266e-05 GaussianMLPPolicy/LossBefore -1.93715e-10 GaussianMLPPolicy/dLoss 1.10264e-05 Iteration 218 MetaTest/Average/AverageDiscountedReturn -173.572 MetaTest/Average/AverageReturn -173.572 MetaTest/Average/Iteration 218 MetaTest/Average/MaxReturn -148.549 MetaTest/Average/MinReturn -235.956 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.8438 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.572 MetaTest/__unnamed_task__/AverageReturn -173.572 MetaTest/__unnamed_task__/Iteration 218 MetaTest/__unnamed_task__/MaxReturn -148.549 MetaTest/__unnamed_task__/MinReturn -235.956 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.8438 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.008e+06 __unnamed_task__/AverageDiscountedReturn -71.6632 __unnamed_task__/AverageReturn -170.837 __unnamed_task__/Iteration 218 __unnamed_task__/MaxReturn -151.088 __unnamed_task__/MinReturn -243.657 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 16.7336 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 12:57:05 | [maml_trainer] epoch #219 | Sampling for adapation and meta-testing... 2025-04-03 12:58:18 | [maml_trainer] epoch #219 | Finished meta-testing... 2025-04-03 12:58:18 | [maml_trainer] epoch #219 | Saving snapshot... 2025-04-03 12:58:42 | [maml_trainer] epoch #219 | Saved 2025-04-03 12:58:42 | [maml_trainer] epoch #219 | Time 84200.44 s 2025-04-03 12:58:42 | [maml_trainer] epoch #219 | EpochTime 394.12 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.8079 Average/AverageReturn -175.626 Average/Iteration 219 Average/MaxReturn -155.305 Average/MinReturn -251.816 Average/NumEpisodes 80 Average/StdReturn 21.0872 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3658 GaussianMLPPolicy/KLAfter 0.00309944 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.66713e-05 GaussianMLPPolicy/LossBefore 4.23193e-09 GaussianMLPPolicy/dLoss 1.66755e-05 Iteration 219 MetaTest/Average/AverageDiscountedReturn -173.545 MetaTest/Average/AverageReturn -173.545 MetaTest/Average/Iteration 219 MetaTest/Average/MaxReturn -157.512 MetaTest/Average/MinReturn -229.708 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.1845 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.545 MetaTest/__unnamed_task__/AverageReturn -173.545 MetaTest/__unnamed_task__/Iteration 219 MetaTest/__unnamed_task__/MaxReturn -157.512 MetaTest/__unnamed_task__/MinReturn -229.708 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.1845 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.04e+06 __unnamed_task__/AverageDiscountedReturn -73.8079 __unnamed_task__/AverageReturn -175.626 __unnamed_task__/Iteration 219 __unnamed_task__/MaxReturn -155.305 __unnamed_task__/MinReturn -251.816 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.0872 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 13:03:36 | [maml_trainer] epoch #220 | Sampling for adapation and meta-testing... 2025-04-03 13:04:48 | [maml_trainer] epoch #220 | Finished meta-testing... 2025-04-03 13:04:48 | [maml_trainer] epoch #220 | Saving snapshot... 2025-04-03 13:05:12 | [maml_trainer] epoch #220 | Saved 2025-04-03 13:05:12 | [maml_trainer] epoch #220 | Time 84590.12 s 2025-04-03 13:05:12 | [maml_trainer] epoch #220 | EpochTime 389.68 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.49 Average/AverageReturn -172.289 Average/Iteration 220 Average/MaxReturn -149.01 Average/MinReturn -238.363 Average/NumEpisodes 80 Average/StdReturn 17.2518 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3577 GaussianMLPPolicy/KLAfter 0.00177049 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.2015e-06 GaussianMLPPolicy/LossBefore -1.84774e-09 GaussianMLPPolicy/dLoss 1.19965e-06 Iteration 220 MetaTest/Average/AverageDiscountedReturn -171.378 MetaTest/Average/AverageReturn -171.378 MetaTest/Average/Iteration 220 MetaTest/Average/MaxReturn -157.906 MetaTest/Average/MinReturn -238.694 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.6815 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.378 MetaTest/__unnamed_task__/AverageReturn -171.378 MetaTest/__unnamed_task__/Iteration 220 MetaTest/__unnamed_task__/MaxReturn -157.906 MetaTest/__unnamed_task__/MinReturn -238.694 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.6815 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.072e+06 __unnamed_task__/AverageDiscountedReturn -72.49 __unnamed_task__/AverageReturn -172.289 __unnamed_task__/Iteration 220 __unnamed_task__/MaxReturn -149.01 __unnamed_task__/MinReturn -238.363 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.2518 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 13:10:03 | [maml_trainer] epoch #221 | Sampling for adapation and meta-testing... 2025-04-03 13:11:15 | [maml_trainer] epoch #221 | Finished meta-testing... 2025-04-03 13:11:15 | [maml_trainer] epoch #221 | Saving snapshot... 2025-04-03 13:11:39 | [maml_trainer] epoch #221 | Saved 2025-04-03 13:11:39 | [maml_trainer] epoch #221 | Time 84977.61 s 2025-04-03 13:11:39 | [maml_trainer] epoch #221 | EpochTime 387.48 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.3647 Average/AverageReturn -175.206 Average/Iteration 221 Average/MaxReturn -153.468 Average/MinReturn -246.988 Average/NumEpisodes 80 Average/StdReturn 20.3203 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3509 GaussianMLPPolicy/KLAfter 0.00183577 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.9344e-06 GaussianMLPPolicy/LossBefore -1.50502e-09 GaussianMLPPolicy/dLoss -6.93591e-06 Iteration 221 MetaTest/Average/AverageDiscountedReturn -169.64 MetaTest/Average/AverageReturn -169.64 MetaTest/Average/Iteration 221 MetaTest/Average/MaxReturn -155.77 MetaTest/Average/MinReturn -224.335 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.4929 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.64 MetaTest/__unnamed_task__/AverageReturn -169.64 MetaTest/__unnamed_task__/Iteration 221 MetaTest/__unnamed_task__/MaxReturn -155.77 MetaTest/__unnamed_task__/MinReturn -224.335 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.4929 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.104e+06 __unnamed_task__/AverageDiscountedReturn -73.3647 __unnamed_task__/AverageReturn -175.206 __unnamed_task__/Iteration 221 __unnamed_task__/MaxReturn -153.468 __unnamed_task__/MinReturn -246.988 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.3203 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 13:16:32 | [maml_trainer] epoch #222 | Sampling for adapation and meta-testing... 2025-04-03 13:17:46 | [maml_trainer] epoch #222 | Finished meta-testing... 2025-04-03 13:17:46 | [maml_trainer] epoch #222 | Saving snapshot... 2025-04-03 13:18:08 | [maml_trainer] epoch #222 | Saved 2025-04-03 13:18:08 | [maml_trainer] epoch #222 | Time 85366.99 s 2025-04-03 13:18:08 | [maml_trainer] epoch #222 | EpochTime 389.38 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.7508 Average/AverageReturn -171.214 Average/Iteration 222 Average/MaxReturn -148.711 Average/MinReturn -231.155 Average/NumEpisodes 80 Average/StdReturn 14.8429 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3442 GaussianMLPPolicy/KLAfter 0.00214662 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.00843e-05 GaussianMLPPolicy/LossBefore -1.90735e-09 GaussianMLPPolicy/dLoss -2.00862e-05 Iteration 222 MetaTest/Average/AverageDiscountedReturn -176.95 MetaTest/Average/AverageReturn -176.95 MetaTest/Average/Iteration 222 MetaTest/Average/MaxReturn -156.496 MetaTest/Average/MinReturn -232.68 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.6845 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.95 MetaTest/__unnamed_task__/AverageReturn -176.95 MetaTest/__unnamed_task__/Iteration 222 MetaTest/__unnamed_task__/MaxReturn -156.496 MetaTest/__unnamed_task__/MinReturn -232.68 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.6845 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.136e+06 __unnamed_task__/AverageDiscountedReturn -71.7508 __unnamed_task__/AverageReturn -171.214 __unnamed_task__/Iteration 222 __unnamed_task__/MaxReturn -148.711 __unnamed_task__/MinReturn -231.155 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 14.8429 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 13:23:00 | [maml_trainer] epoch #223 | Sampling for adapation and meta-testing... 2025-04-03 13:24:13 | [maml_trainer] epoch #223 | Finished meta-testing... 2025-04-03 13:24:13 | [maml_trainer] epoch #223 | Saving snapshot... 2025-04-03 13:24:37 | [maml_trainer] epoch #223 | Saved 2025-04-03 13:24:37 | [maml_trainer] epoch #223 | Time 85755.82 s 2025-04-03 13:24:37 | [maml_trainer] epoch #223 | EpochTime 388.83 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.1056 Average/AverageReturn -175.886 Average/Iteration 223 Average/MaxReturn -152.11 Average/MinReturn -263.464 Average/NumEpisodes 80 Average/StdReturn 20.915 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.339 GaussianMLPPolicy/KLAfter 0.00277496 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.99052e-05 GaussianMLPPolicy/LossBefore 4.08292e-09 GaussianMLPPolicy/dLoss 1.99092e-05 Iteration 223 MetaTest/Average/AverageDiscountedReturn -173.86 MetaTest/Average/AverageReturn -173.86 MetaTest/Average/Iteration 223 MetaTest/Average/MaxReturn -159.121 MetaTest/Average/MinReturn -230.83 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.5878 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.86 MetaTest/__unnamed_task__/AverageReturn -173.86 MetaTest/__unnamed_task__/Iteration 223 MetaTest/__unnamed_task__/MaxReturn -159.121 MetaTest/__unnamed_task__/MinReturn -230.83 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.5878 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.168e+06 __unnamed_task__/AverageDiscountedReturn -74.1056 __unnamed_task__/AverageReturn -175.886 __unnamed_task__/Iteration 223 __unnamed_task__/MaxReturn -152.11 __unnamed_task__/MinReturn -263.464 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.915 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 13:29:28 | [maml_trainer] epoch #224 | Sampling for adapation and meta-testing... 2025-04-03 13:30:41 | [maml_trainer] epoch #224 | Finished meta-testing... 2025-04-03 13:30:41 | [maml_trainer] epoch #224 | Saving snapshot... 2025-04-03 13:31:05 | [maml_trainer] epoch #224 | Saved 2025-04-03 13:31:05 | [maml_trainer] epoch #224 | Time 86143.19 s 2025-04-03 13:31:05 | [maml_trainer] epoch #224 | EpochTime 387.37 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.2242 Average/AverageReturn -174.776 Average/Iteration 224 Average/MaxReturn -155.21 Average/MinReturn -239.02 Average/NumEpisodes 80 Average/StdReturn 18.5954 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3337 GaussianMLPPolicy/KLAfter 0.0028601 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.88246e-05 GaussianMLPPolicy/LossBefore -1.49012e-11 GaussianMLPPolicy/dLoss 5.88246e-05 Iteration 224 MetaTest/Average/AverageDiscountedReturn -174.079 MetaTest/Average/AverageReturn -174.079 MetaTest/Average/Iteration 224 MetaTest/Average/MaxReturn -158.602 MetaTest/Average/MinReturn -234.779 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.8696 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.079 MetaTest/__unnamed_task__/AverageReturn -174.079 MetaTest/__unnamed_task__/Iteration 224 MetaTest/__unnamed_task__/MaxReturn -158.602 MetaTest/__unnamed_task__/MinReturn -234.779 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.8696 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.2e+06 __unnamed_task__/AverageDiscountedReturn -73.2242 __unnamed_task__/AverageReturn -174.776 __unnamed_task__/Iteration 224 __unnamed_task__/MaxReturn -155.21 __unnamed_task__/MinReturn -239.02 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.5954 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 13:35:58 | [maml_trainer] epoch #225 | Sampling for adapation and meta-testing... 2025-04-03 13:37:11 | [maml_trainer] epoch #225 | Finished meta-testing... 2025-04-03 13:37:11 | [maml_trainer] epoch #225 | Saving snapshot... 2025-04-03 13:37:34 | [maml_trainer] epoch #225 | Saved 2025-04-03 13:37:34 | [maml_trainer] epoch #225 | Time 86532.63 s 2025-04-03 13:37:34 | [maml_trainer] epoch #225 | EpochTime 389.43 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.8777 Average/AverageReturn -173.732 Average/Iteration 225 Average/MaxReturn -154.451 Average/MinReturn -241.81 Average/NumEpisodes 80 Average/StdReturn 18.3725 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3284 GaussianMLPPolicy/KLAfter 0.00291636 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.67923e-06 GaussianMLPPolicy/LossBefore -4.67896e-09 GaussianMLPPolicy/dLoss -9.68391e-06 Iteration 225 MetaTest/Average/AverageDiscountedReturn -174.853 MetaTest/Average/AverageReturn -174.853 MetaTest/Average/Iteration 225 MetaTest/Average/MaxReturn -163.843 MetaTest/Average/MinReturn -252.713 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.5198 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.853 MetaTest/__unnamed_task__/AverageReturn -174.853 MetaTest/__unnamed_task__/Iteration 225 MetaTest/__unnamed_task__/MaxReturn -163.843 MetaTest/__unnamed_task__/MinReturn -252.713 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.5198 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.232e+06 __unnamed_task__/AverageDiscountedReturn -72.8777 __unnamed_task__/AverageReturn -173.732 __unnamed_task__/Iteration 225 __unnamed_task__/MaxReturn -154.451 __unnamed_task__/MinReturn -241.81 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.3725 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 13:42:24 | [maml_trainer] epoch #226 | Sampling for adapation and meta-testing... 2025-04-03 13:43:39 | [maml_trainer] epoch #226 | Finished meta-testing... 2025-04-03 13:43:39 | [maml_trainer] epoch #226 | Saving snapshot... 2025-04-03 13:44:01 | [maml_trainer] epoch #226 | Saved 2025-04-03 13:44:01 | [maml_trainer] epoch #226 | Time 86920.06 s 2025-04-03 13:44:01 | [maml_trainer] epoch #226 | EpochTime 387.43 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.9026 Average/AverageReturn -176.686 Average/Iteration 226 Average/MaxReturn -153.361 Average/MinReturn -242.372 Average/NumEpisodes 80 Average/StdReturn 20.0364 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3263 GaussianMLPPolicy/KLAfter 0.00282891 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.78665e-05 GaussianMLPPolicy/LossBefore -4.72367e-09 GaussianMLPPolicy/dLoss 3.78618e-05 Iteration 226 MetaTest/Average/AverageDiscountedReturn -175.572 MetaTest/Average/AverageReturn -175.572 MetaTest/Average/Iteration 226 MetaTest/Average/MaxReturn -154.337 MetaTest/Average/MinReturn -244.831 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.026 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.572 MetaTest/__unnamed_task__/AverageReturn -175.572 MetaTest/__unnamed_task__/Iteration 226 MetaTest/__unnamed_task__/MaxReturn -154.337 MetaTest/__unnamed_task__/MinReturn -244.831 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.026 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.264e+06 __unnamed_task__/AverageDiscountedReturn -73.9026 __unnamed_task__/AverageReturn -176.686 __unnamed_task__/Iteration 226 __unnamed_task__/MaxReturn -153.361 __unnamed_task__/MinReturn -242.372 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.0364 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 13:48:54 | [maml_trainer] epoch #227 | Sampling for adapation and meta-testing... 2025-04-03 13:50:07 | [maml_trainer] epoch #227 | Finished meta-testing... 2025-04-03 13:50:07 | [maml_trainer] epoch #227 | Saving snapshot... 2025-04-03 13:50:31 | [maml_trainer] epoch #227 | Saved 2025-04-03 13:50:31 | [maml_trainer] epoch #227 | Time 87309.14 s 2025-04-03 13:50:31 | [maml_trainer] epoch #227 | EpochTime 389.08 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.6709 Average/AverageReturn -172.932 Average/Iteration 227 Average/MaxReturn -150.345 Average/MinReturn -248.16 Average/NumEpisodes 80 Average/StdReturn 17.5832 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3257 GaussianMLPPolicy/KLAfter 0.00313983 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.49548e-05 GaussianMLPPolicy/LossBefore -3.7849e-09 GaussianMLPPolicy/dLoss -1.49585e-05 Iteration 227 MetaTest/Average/AverageDiscountedReturn -174.88 MetaTest/Average/AverageReturn -174.88 MetaTest/Average/Iteration 227 MetaTest/Average/MaxReturn -152.435 MetaTest/Average/MinReturn -239.815 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.7036 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.88 MetaTest/__unnamed_task__/AverageReturn -174.88 MetaTest/__unnamed_task__/Iteration 227 MetaTest/__unnamed_task__/MaxReturn -152.435 MetaTest/__unnamed_task__/MinReturn -239.815 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.7036 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.296e+06 __unnamed_task__/AverageDiscountedReturn -72.6709 __unnamed_task__/AverageReturn -172.932 __unnamed_task__/Iteration 227 __unnamed_task__/MaxReturn -150.345 __unnamed_task__/MinReturn -248.16 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.5832 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 13:55:21 | [maml_trainer] epoch #228 | Sampling for adapation and meta-testing... 2025-04-03 13:56:34 | [maml_trainer] epoch #228 | Finished meta-testing... 2025-04-03 13:56:34 | [maml_trainer] epoch #228 | Saving snapshot... 2025-04-03 13:56:58 | [maml_trainer] epoch #228 | Saved 2025-04-03 13:56:58 | [maml_trainer] epoch #228 | Time 87696.31 s 2025-04-03 13:56:58 | [maml_trainer] epoch #228 | EpochTime 387.17 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.3584 Average/AverageReturn -177.078 Average/Iteration 228 Average/MaxReturn -152.438 Average/MinReturn -247.431 Average/NumEpisodes 80 Average/StdReturn 23.6942 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3272 GaussianMLPPolicy/KLAfter 0.00366544 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.56327e-05 GaussianMLPPolicy/LossBefore -1.19209e-10 GaussianMLPPolicy/dLoss 4.56326e-05 Iteration 228 MetaTest/Average/AverageDiscountedReturn -176.74 MetaTest/Average/AverageReturn -176.74 MetaTest/Average/Iteration 228 MetaTest/Average/MaxReturn -160.645 MetaTest/Average/MinReturn -230.892 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.1693 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.74 MetaTest/__unnamed_task__/AverageReturn -176.74 MetaTest/__unnamed_task__/Iteration 228 MetaTest/__unnamed_task__/MaxReturn -160.645 MetaTest/__unnamed_task__/MinReturn -230.892 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.1693 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.328e+06 __unnamed_task__/AverageDiscountedReturn -74.3584 __unnamed_task__/AverageReturn -177.078 __unnamed_task__/Iteration 228 __unnamed_task__/MaxReturn -152.438 __unnamed_task__/MinReturn -247.431 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.6942 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 14:01:49 | [maml_trainer] epoch #229 | Sampling for adapation and meta-testing... 2025-04-03 14:03:02 | [maml_trainer] epoch #229 | Finished meta-testing... 2025-04-03 14:03:02 | [maml_trainer] epoch #229 | Saving snapshot... 2025-04-03 14:03:25 | [maml_trainer] epoch #229 | Saved 2025-04-03 14:03:25 | [maml_trainer] epoch #229 | Time 88083.97 s 2025-04-03 14:03:25 | [maml_trainer] epoch #229 | EpochTime 387.65 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.4418 Average/AverageReturn -172.285 Average/Iteration 229 Average/MaxReturn -149.832 Average/MinReturn -233.526 Average/NumEpisodes 80 Average/StdReturn 15.1597 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3258 GaussianMLPPolicy/KLAfter 0.00343934 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.69951e-05 GaussianMLPPolicy/LossBefore -6.10948e-10 GaussianMLPPolicy/dLoss 1.69945e-05 Iteration 229 MetaTest/Average/AverageDiscountedReturn -168.851 MetaTest/Average/AverageReturn -168.851 MetaTest/Average/Iteration 229 MetaTest/Average/MaxReturn -156.354 MetaTest/Average/MinReturn -187.479 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.64961 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.851 MetaTest/__unnamed_task__/AverageReturn -168.851 MetaTest/__unnamed_task__/Iteration 229 MetaTest/__unnamed_task__/MaxReturn -156.354 MetaTest/__unnamed_task__/MinReturn -187.479 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.64961 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.36e+06 __unnamed_task__/AverageDiscountedReturn -72.4418 __unnamed_task__/AverageReturn -172.285 __unnamed_task__/Iteration 229 __unnamed_task__/MaxReturn -149.832 __unnamed_task__/MinReturn -233.526 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.1597 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 14:08:20 | [maml_trainer] epoch #230 | Sampling for adapation and meta-testing... 2025-04-03 14:09:32 | [maml_trainer] epoch #230 | Finished meta-testing... 2025-04-03 14:09:32 | [maml_trainer] epoch #230 | Saving snapshot... 2025-04-03 14:09:54 | [maml_trainer] epoch #230 | Saved 2025-04-03 14:09:54 | [maml_trainer] epoch #230 | Time 88473.00 s 2025-04-03 14:09:54 | [maml_trainer] epoch #230 | EpochTime 389.02 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.5475 Average/AverageReturn -170.539 Average/Iteration 230 Average/MaxReturn -151.639 Average/MinReturn -251.412 Average/NumEpisodes 80 Average/StdReturn 17.4188 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3235 GaussianMLPPolicy/KLAfter 0.00360288 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.68155e-05 GaussianMLPPolicy/LossBefore 4.64916e-09 GaussianMLPPolicy/dLoss -2.68109e-05 Iteration 230 MetaTest/Average/AverageDiscountedReturn -172.705 MetaTest/Average/AverageReturn -172.705 MetaTest/Average/Iteration 230 MetaTest/Average/MaxReturn -158.338 MetaTest/Average/MinReturn -234.222 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.3703 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.705 MetaTest/__unnamed_task__/AverageReturn -172.705 MetaTest/__unnamed_task__/Iteration 230 MetaTest/__unnamed_task__/MaxReturn -158.338 MetaTest/__unnamed_task__/MinReturn -234.222 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.3703 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.392e+06 __unnamed_task__/AverageDiscountedReturn -71.5475 __unnamed_task__/AverageReturn -170.539 __unnamed_task__/Iteration 230 __unnamed_task__/MaxReturn -151.639 __unnamed_task__/MinReturn -251.412 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.4188 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 14:14:45 | [maml_trainer] epoch #231 | Sampling for adapation and meta-testing... 2025-04-03 14:15:58 | [maml_trainer] epoch #231 | Finished meta-testing... 2025-04-03 14:15:58 | [maml_trainer] epoch #231 | Saving snapshot... 2025-04-03 14:16:22 | [maml_trainer] epoch #231 | Saved 2025-04-03 14:16:22 | [maml_trainer] epoch #231 | Time 88860.38 s 2025-04-03 14:16:22 | [maml_trainer] epoch #231 | EpochTime 387.38 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -76.3136 Average/AverageReturn -176.918 Average/Iteration 231 Average/MaxReturn -151.545 Average/MinReturn -495.598 Average/NumEpisodes 80 Average/StdReturn 41.4748 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3216 GaussianMLPPolicy/KLAfter 0.00377302 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.32374e-05 GaussianMLPPolicy/LossBefore 2.563e-09 GaussianMLPPolicy/dLoss -2.32348e-05 Iteration 231 MetaTest/Average/AverageDiscountedReturn -177.173 MetaTest/Average/AverageReturn -177.173 MetaTest/Average/Iteration 231 MetaTest/Average/MaxReturn -158.942 MetaTest/Average/MinReturn -233.555 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.638 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.173 MetaTest/__unnamed_task__/AverageReturn -177.173 MetaTest/__unnamed_task__/Iteration 231 MetaTest/__unnamed_task__/MaxReturn -158.942 MetaTest/__unnamed_task__/MinReturn -233.555 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.638 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.424e+06 __unnamed_task__/AverageDiscountedReturn -76.3136 __unnamed_task__/AverageReturn -176.918 __unnamed_task__/Iteration 231 __unnamed_task__/MaxReturn -151.545 __unnamed_task__/MinReturn -495.598 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 41.4748 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 14:21:14 | [maml_trainer] epoch #232 | Sampling for adapation and meta-testing... 2025-04-03 14:22:26 | [maml_trainer] epoch #232 | Finished meta-testing... 2025-04-03 14:22:26 | [maml_trainer] epoch #232 | Saving snapshot... 2025-04-03 14:22:50 | [maml_trainer] epoch #232 | Saved 2025-04-03 14:22:50 | [maml_trainer] epoch #232 | Time 89248.39 s 2025-04-03 14:22:50 | [maml_trainer] epoch #232 | EpochTime 388.01 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.258 Average/AverageReturn -171.733 Average/Iteration 232 Average/MaxReturn -150.365 Average/MinReturn -235.025 Average/NumEpisodes 80 Average/StdReturn 20.4245 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3219 GaussianMLPPolicy/KLAfter 0.00396605 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.25653e-05 GaussianMLPPolicy/LossBefore 1.11759e-09 GaussianMLPPolicy/dLoss 4.25664e-05 Iteration 232 MetaTest/Average/AverageDiscountedReturn -173.749 MetaTest/Average/AverageReturn -173.749 MetaTest/Average/Iteration 232 MetaTest/Average/MaxReturn -158.557 MetaTest/Average/MinReturn -233.338 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.1875 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.749 MetaTest/__unnamed_task__/AverageReturn -173.749 MetaTest/__unnamed_task__/Iteration 232 MetaTest/__unnamed_task__/MaxReturn -158.557 MetaTest/__unnamed_task__/MinReturn -233.338 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.1875 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.456e+06 __unnamed_task__/AverageDiscountedReturn -72.258 __unnamed_task__/AverageReturn -171.733 __unnamed_task__/Iteration 232 __unnamed_task__/MaxReturn -150.365 __unnamed_task__/MinReturn -235.025 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.4245 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 14:27:39 | [maml_trainer] epoch #233 | Sampling for adapation and meta-testing... 2025-04-03 14:28:51 | [maml_trainer] epoch #233 | Finished meta-testing... 2025-04-03 14:28:51 | [maml_trainer] epoch #233 | Saving snapshot... 2025-04-03 14:29:16 | [maml_trainer] epoch #233 | Saved 2025-04-03 14:29:16 | [maml_trainer] epoch #233 | Time 89634.14 s 2025-04-03 14:29:16 | [maml_trainer] epoch #233 | EpochTime 385.75 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.6425 Average/AverageReturn -169.749 Average/Iteration 233 Average/MaxReturn -146.185 Average/MinReturn -256.08 Average/NumEpisodes 80 Average/StdReturn 19.7564 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3205 GaussianMLPPolicy/KLAfter 0.00396996 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.85632e-06 GaussianMLPPolicy/LossBefore 1.02073e-08 GaussianMLPPolicy/dLoss -6.84611e-06 Iteration 233 MetaTest/Average/AverageDiscountedReturn -169.047 MetaTest/Average/AverageReturn -169.047 MetaTest/Average/Iteration 233 MetaTest/Average/MaxReturn -153.62 MetaTest/Average/MinReturn -232.417 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.3343 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.047 MetaTest/__unnamed_task__/AverageReturn -169.047 MetaTest/__unnamed_task__/Iteration 233 MetaTest/__unnamed_task__/MaxReturn -153.62 MetaTest/__unnamed_task__/MinReturn -232.417 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.3343 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.488e+06 __unnamed_task__/AverageDiscountedReturn -71.6425 __unnamed_task__/AverageReturn -169.749 __unnamed_task__/Iteration 233 __unnamed_task__/MaxReturn -146.185 __unnamed_task__/MinReturn -256.08 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.7564 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 14:34:07 | [maml_trainer] epoch #234 | Sampling for adapation and meta-testing... 2025-04-03 14:35:20 | [maml_trainer] epoch #234 | Finished meta-testing... 2025-04-03 14:35:20 | [maml_trainer] epoch #234 | Saving snapshot... 2025-04-03 14:35:42 | [maml_trainer] epoch #234 | Saved 2025-04-03 14:35:42 | [maml_trainer] epoch #234 | Time 90020.57 s 2025-04-03 14:35:42 | [maml_trainer] epoch #234 | EpochTime 386.43 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.8691 Average/AverageReturn -169.32 Average/Iteration 234 Average/MaxReturn -147.427 Average/MinReturn -253.868 Average/NumEpisodes 80 Average/StdReturn 22.3561 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3193 GaussianMLPPolicy/KLAfter 0.00345346 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.27129e-05 GaussianMLPPolicy/LossBefore -2.87592e-09 GaussianMLPPolicy/dLoss -1.27157e-05 Iteration 234 MetaTest/Average/AverageDiscountedReturn -167.382 MetaTest/Average/AverageReturn -167.382 MetaTest/Average/Iteration 234 MetaTest/Average/MaxReturn -150.631 MetaTest/Average/MinReturn -226.255 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.1281 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.382 MetaTest/__unnamed_task__/AverageReturn -167.382 MetaTest/__unnamed_task__/Iteration 234 MetaTest/__unnamed_task__/MaxReturn -150.631 MetaTest/__unnamed_task__/MinReturn -226.255 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.1281 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.52e+06 __unnamed_task__/AverageDiscountedReturn -71.8691 __unnamed_task__/AverageReturn -169.32 __unnamed_task__/Iteration 234 __unnamed_task__/MaxReturn -147.427 __unnamed_task__/MinReturn -253.868 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.3561 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 14:40:31 | [maml_trainer] epoch #235 | Sampling for adapation and meta-testing... 2025-04-03 14:41:43 | [maml_trainer] epoch #235 | Finished meta-testing... 2025-04-03 14:41:43 | [maml_trainer] epoch #235 | Saving snapshot... 2025-04-03 14:42:06 | [maml_trainer] epoch #235 | Saved 2025-04-03 14:42:06 | [maml_trainer] epoch #235 | Time 90404.67 s 2025-04-03 14:42:06 | [maml_trainer] epoch #235 | EpochTime 384.09 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.2531 Average/AverageReturn -170.849 Average/Iteration 235 Average/MaxReturn -145.154 Average/MinReturn -256.953 Average/NumEpisodes 80 Average/StdReturn 22.7961 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3179 GaussianMLPPolicy/KLAfter 0.00325416 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.85759e-05 GaussianMLPPolicy/LossBefore -1.07288e-09 GaussianMLPPolicy/dLoss 1.85749e-05 Iteration 235 MetaTest/Average/AverageDiscountedReturn -165.578 MetaTest/Average/AverageReturn -165.578 MetaTest/Average/Iteration 235 MetaTest/Average/MaxReturn -147.046 MetaTest/Average/MinReturn -220.563 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.543 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.578 MetaTest/__unnamed_task__/AverageReturn -165.578 MetaTest/__unnamed_task__/Iteration 235 MetaTest/__unnamed_task__/MaxReturn -147.046 MetaTest/__unnamed_task__/MinReturn -220.563 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.543 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.552e+06 __unnamed_task__/AverageDiscountedReturn -72.2531 __unnamed_task__/AverageReturn -170.849 __unnamed_task__/Iteration 235 __unnamed_task__/MaxReturn -145.154 __unnamed_task__/MinReturn -256.953 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.7961 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 14:46:57 | [maml_trainer] epoch #236 | Sampling for adapation and meta-testing... 2025-04-03 14:48:09 | [maml_trainer] epoch #236 | Finished meta-testing... 2025-04-03 14:48:09 | [maml_trainer] epoch #236 | Saving snapshot... 2025-04-03 14:48:33 | [maml_trainer] epoch #236 | Saved 2025-04-03 14:48:33 | [maml_trainer] epoch #236 | Time 90791.61 s 2025-04-03 14:48:33 | [maml_trainer] epoch #236 | EpochTime 386.93 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.7802 Average/AverageReturn -169.58 Average/Iteration 236 Average/MaxReturn -145.058 Average/MinReturn -240.828 Average/NumEpisodes 80 Average/StdReturn 18.4851 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3155 GaussianMLPPolicy/KLAfter 0.00241183 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.82128e-06 GaussianMLPPolicy/LossBefore 3.42727e-09 GaussianMLPPolicy/dLoss 2.82471e-06 Iteration 236 MetaTest/Average/AverageDiscountedReturn -166.701 MetaTest/Average/AverageReturn -166.701 MetaTest/Average/Iteration 236 MetaTest/Average/MaxReturn -144.174 MetaTest/Average/MinReturn -229.622 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.5946 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.701 MetaTest/__unnamed_task__/AverageReturn -166.701 MetaTest/__unnamed_task__/Iteration 236 MetaTest/__unnamed_task__/MaxReturn -144.174 MetaTest/__unnamed_task__/MinReturn -229.622 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.5946 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.584e+06 __unnamed_task__/AverageDiscountedReturn -71.7802 __unnamed_task__/AverageReturn -169.58 __unnamed_task__/Iteration 236 __unnamed_task__/MaxReturn -145.058 __unnamed_task__/MinReturn -240.828 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 18.4851 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 14:53:21 | [maml_trainer] epoch #237 | Sampling for adapation and meta-testing... 2025-04-03 14:54:33 | [maml_trainer] epoch #237 | Finished meta-testing... 2025-04-03 14:54:33 | [maml_trainer] epoch #237 | Saving snapshot... 2025-04-03 14:54:56 | [maml_trainer] epoch #237 | Saved 2025-04-03 14:54:56 | [maml_trainer] epoch #237 | Time 91174.91 s 2025-04-03 14:54:56 | [maml_trainer] epoch #237 | EpochTime 383.30 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.4242 Average/AverageReturn -170.481 Average/Iteration 237 Average/MaxReturn -143.505 Average/MinReturn -256.615 Average/NumEpisodes 80 Average/StdReturn 24.098 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3111 GaussianMLPPolicy/KLAfter 0.00282974 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.39621e-05 GaussianMLPPolicy/LossBefore 4.00841e-09 GaussianMLPPolicy/dLoss -2.39581e-05 Iteration 237 MetaTest/Average/AverageDiscountedReturn -161.654 MetaTest/Average/AverageReturn -161.654 MetaTest/Average/Iteration 237 MetaTest/Average/MaxReturn -138.414 MetaTest/Average/MinReturn -242.669 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.7517 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -161.654 MetaTest/__unnamed_task__/AverageReturn -161.654 MetaTest/__unnamed_task__/Iteration 237 MetaTest/__unnamed_task__/MaxReturn -138.414 MetaTest/__unnamed_task__/MinReturn -242.669 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.7517 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.616e+06 __unnamed_task__/AverageDiscountedReturn -72.4242 __unnamed_task__/AverageReturn -170.481 __unnamed_task__/Iteration 237 __unnamed_task__/MaxReturn -143.505 __unnamed_task__/MinReturn -256.615 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.098 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 14:59:44 | [maml_trainer] epoch #238 | Sampling for adapation and meta-testing... 2025-04-03 15:00:57 | [maml_trainer] epoch #238 | Finished meta-testing... 2025-04-03 15:00:57 | [maml_trainer] epoch #238 | Saving snapshot... 2025-04-03 15:01:19 | [maml_trainer] epoch #238 | Saved 2025-04-03 15:01:19 | [maml_trainer] epoch #238 | Time 91557.58 s 2025-04-03 15:01:19 | [maml_trainer] epoch #238 | EpochTime 382.66 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.1961 Average/AverageReturn -164.767 Average/Iteration 238 Average/MaxReturn -138.926 Average/MinReturn -235.32 Average/NumEpisodes 80 Average/StdReturn 17.6332 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3047 GaussianMLPPolicy/KLAfter 0.00292259 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.3436e-05 GaussianMLPPolicy/LossBefore 3.9041e-09 GaussianMLPPolicy/dLoss 3.34399e-05 Iteration 238 MetaTest/Average/AverageDiscountedReturn -170.476 MetaTest/Average/AverageReturn -170.476 MetaTest/Average/Iteration 238 MetaTest/Average/MaxReturn -146 MetaTest/Average/MinReturn -226.078 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.9717 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.476 MetaTest/__unnamed_task__/AverageReturn -170.476 MetaTest/__unnamed_task__/Iteration 238 MetaTest/__unnamed_task__/MaxReturn -146 MetaTest/__unnamed_task__/MinReturn -226.078 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.9717 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.648e+06 __unnamed_task__/AverageDiscountedReturn -70.1961 __unnamed_task__/AverageReturn -164.767 __unnamed_task__/Iteration 238 __unnamed_task__/MaxReturn -138.926 __unnamed_task__/MinReturn -235.32 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.6332 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 15:06:08 | [maml_trainer] epoch #239 | Sampling for adapation and meta-testing... 2025-04-03 15:07:21 | [maml_trainer] epoch #239 | Finished meta-testing... 2025-04-03 15:07:21 | [maml_trainer] epoch #239 | Saving snapshot... 2025-04-03 15:07:44 | [maml_trainer] epoch #239 | Saved 2025-04-03 15:07:44 | [maml_trainer] epoch #239 | Time 91942.19 s 2025-04-03 15:07:44 | [maml_trainer] epoch #239 | EpochTime 384.61 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.3069 Average/AverageReturn -165.474 Average/Iteration 239 Average/MaxReturn -144.45 Average/MinReturn -224.729 Average/NumEpisodes 80 Average/StdReturn 15.792 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2968 GaussianMLPPolicy/KLAfter 0.00374209 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.11405e-06 GaussianMLPPolicy/LossBefore -3.8147e-09 GaussianMLPPolicy/dLoss -7.11787e-06 Iteration 239 MetaTest/Average/AverageDiscountedReturn -160.267 MetaTest/Average/AverageReturn -160.267 MetaTest/Average/Iteration 239 MetaTest/Average/MaxReturn -146.795 MetaTest/Average/MinReturn -222.206 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.5696 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -160.267 MetaTest/__unnamed_task__/AverageReturn -160.267 MetaTest/__unnamed_task__/Iteration 239 MetaTest/__unnamed_task__/MaxReturn -146.795 MetaTest/__unnamed_task__/MinReturn -222.206 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.5696 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.68e+06 __unnamed_task__/AverageDiscountedReturn -70.3069 __unnamed_task__/AverageReturn -165.474 __unnamed_task__/Iteration 239 __unnamed_task__/MaxReturn -144.45 __unnamed_task__/MinReturn -224.729 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.792 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 15:12:37 | [maml_trainer] epoch #240 | Sampling for adapation and meta-testing... 2025-04-03 15:13:48 | [maml_trainer] epoch #240 | Finished meta-testing... 2025-04-03 15:13:48 | [maml_trainer] epoch #240 | Saving snapshot... 2025-04-03 15:14:12 | [maml_trainer] epoch #240 | Saved 2025-04-03 15:14:12 | [maml_trainer] epoch #240 | Time 92330.20 s 2025-04-03 15:14:12 | [maml_trainer] epoch #240 | EpochTime 388.01 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.8024 Average/AverageReturn -171.844 Average/Iteration 240 Average/MaxReturn -142.889 Average/MinReturn -237.602 Average/NumEpisodes 80 Average/StdReturn 23.7115 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.289 GaussianMLPPolicy/KLAfter 0.00360214 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.97449e-06 GaussianMLPPolicy/LossBefore 4.48525e-09 GaussianMLPPolicy/dLoss -1.97001e-06 Iteration 240 MetaTest/Average/AverageDiscountedReturn -159.9 MetaTest/Average/AverageReturn -159.9 MetaTest/Average/Iteration 240 MetaTest/Average/MaxReturn -143.219 MetaTest/Average/MinReturn -239.471 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.0745 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -159.9 MetaTest/__unnamed_task__/AverageReturn -159.9 MetaTest/__unnamed_task__/Iteration 240 MetaTest/__unnamed_task__/MaxReturn -143.219 MetaTest/__unnamed_task__/MinReturn -239.471 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.0745 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.712e+06 __unnamed_task__/AverageDiscountedReturn -72.8024 __unnamed_task__/AverageReturn -171.844 __unnamed_task__/Iteration 240 __unnamed_task__/MaxReturn -142.889 __unnamed_task__/MinReturn -237.602 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.7115 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 15:18:58 | [maml_trainer] epoch #241 | Sampling for adapation and meta-testing... 2025-04-03 15:20:12 | [maml_trainer] epoch #241 | Finished meta-testing... 2025-04-03 15:20:12 | [maml_trainer] epoch #241 | Saving snapshot... 2025-04-03 15:20:35 | [maml_trainer] epoch #241 | Saved 2025-04-03 15:20:35 | [maml_trainer] epoch #241 | Time 92713.49 s 2025-04-03 15:20:35 | [maml_trainer] epoch #241 | EpochTime 383.28 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.9834 Average/AverageReturn -167.306 Average/Iteration 241 Average/MaxReturn -145.258 Average/MinReturn -236.584 Average/NumEpisodes 80 Average/StdReturn 20.5891 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2807 GaussianMLPPolicy/KLAfter 0.00359582 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.9819e-05 GaussianMLPPolicy/LossBefore 8.62777e-09 GaussianMLPPolicy/dLoss -2.98103e-05 Iteration 241 MetaTest/Average/AverageDiscountedReturn -173.137 MetaTest/Average/AverageReturn -173.137 MetaTest/Average/Iteration 241 MetaTest/Average/MaxReturn -153.215 MetaTest/Average/MinReturn -253.276 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.1407 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.137 MetaTest/__unnamed_task__/AverageReturn -173.137 MetaTest/__unnamed_task__/Iteration 241 MetaTest/__unnamed_task__/MaxReturn -153.215 MetaTest/__unnamed_task__/MinReturn -253.276 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.1407 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.744e+06 __unnamed_task__/AverageDiscountedReturn -70.9834 __unnamed_task__/AverageReturn -167.306 __unnamed_task__/Iteration 241 __unnamed_task__/MaxReturn -145.258 __unnamed_task__/MinReturn -236.584 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.5891 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 15:25:27 | [maml_trainer] epoch #242 | Sampling for adapation and meta-testing... 2025-04-03 15:26:39 | [maml_trainer] epoch #242 | Finished meta-testing... 2025-04-03 15:26:39 | [maml_trainer] epoch #242 | Saving snapshot... 2025-04-03 15:27:03 | [maml_trainer] epoch #242 | Saved 2025-04-03 15:27:03 | [maml_trainer] epoch #242 | Time 93101.36 s 2025-04-03 15:27:03 | [maml_trainer] epoch #242 | EpochTime 387.87 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.1017 Average/AverageReturn -167.002 Average/Iteration 242 Average/MaxReturn -146.12 Average/MinReturn -239.508 Average/NumEpisodes 80 Average/StdReturn 21.4314 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.276 GaussianMLPPolicy/KLAfter 0.00359399 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.2475e-05 GaussianMLPPolicy/LossBefore -1.93715e-09 GaussianMLPPolicy/dLoss 1.2473e-05 Iteration 242 MetaTest/Average/AverageDiscountedReturn -164.529 MetaTest/Average/AverageReturn -164.529 MetaTest/Average/Iteration 242 MetaTest/Average/MaxReturn -144.368 MetaTest/Average/MinReturn -253.131 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.3531 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.529 MetaTest/__unnamed_task__/AverageReturn -164.529 MetaTest/__unnamed_task__/Iteration 242 MetaTest/__unnamed_task__/MaxReturn -144.368 MetaTest/__unnamed_task__/MinReturn -253.131 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.3531 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.776e+06 __unnamed_task__/AverageDiscountedReturn -71.1017 __unnamed_task__/AverageReturn -167.002 __unnamed_task__/Iteration 242 __unnamed_task__/MaxReturn -146.12 __unnamed_task__/MinReturn -239.508 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.4314 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 15:31:55 | [maml_trainer] epoch #243 | Sampling for adapation and meta-testing... 2025-04-03 15:33:09 | [maml_trainer] epoch #243 | Finished meta-testing... 2025-04-03 15:33:09 | [maml_trainer] epoch #243 | Saving snapshot... 2025-04-03 15:33:31 | [maml_trainer] epoch #243 | Saved 2025-04-03 15:33:31 | [maml_trainer] epoch #243 | Time 93489.87 s 2025-04-03 15:33:31 | [maml_trainer] epoch #243 | EpochTime 388.51 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -69.2092 Average/AverageReturn -161.934 Average/Iteration 243 Average/MaxReturn -141.09 Average/MinReturn -237.197 Average/NumEpisodes 80 Average/StdReturn 17.3409 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2727 GaussianMLPPolicy/KLAfter 0.00401826 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.43224e-05 GaussianMLPPolicy/LossBefore 7.86781e-09 GaussianMLPPolicy/dLoss -6.43145e-05 Iteration 243 MetaTest/Average/AverageDiscountedReturn -161.075 MetaTest/Average/AverageReturn -161.075 MetaTest/Average/Iteration 243 MetaTest/Average/MaxReturn -140.73 MetaTest/Average/MinReturn -228.774 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.011 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -161.075 MetaTest/__unnamed_task__/AverageReturn -161.075 MetaTest/__unnamed_task__/Iteration 243 MetaTest/__unnamed_task__/MaxReturn -140.73 MetaTest/__unnamed_task__/MinReturn -228.774 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.011 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.808e+06 __unnamed_task__/AverageDiscountedReturn -69.2092 __unnamed_task__/AverageReturn -161.934 __unnamed_task__/Iteration 243 __unnamed_task__/MaxReturn -141.09 __unnamed_task__/MinReturn -237.197 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.3409 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 15:38:23 | [maml_trainer] epoch #244 | Sampling for adapation and meta-testing... 2025-04-03 15:39:35 | [maml_trainer] epoch #244 | Finished meta-testing... 2025-04-03 15:39:35 | [maml_trainer] epoch #244 | Saving snapshot... 2025-04-03 15:39:58 | [maml_trainer] epoch #244 | Saved 2025-04-03 15:39:58 | [maml_trainer] epoch #244 | Time 93877.01 s 2025-04-03 15:39:58 | [maml_trainer] epoch #244 | EpochTime 387.14 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.034 Average/AverageReturn -164.603 Average/Iteration 244 Average/MaxReturn -140.375 Average/MinReturn -224.769 Average/NumEpisodes 80 Average/StdReturn 15.5308 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2711 GaussianMLPPolicy/KLAfter 0.00356923 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.65552e-05 GaussianMLPPolicy/LossBefore 3.18885e-09 GaussianMLPPolicy/dLoss -1.6552e-05 Iteration 244 MetaTest/Average/AverageDiscountedReturn -163.753 MetaTest/Average/AverageReturn -163.753 MetaTest/Average/Iteration 244 MetaTest/Average/MaxReturn -147.493 MetaTest/Average/MinReturn -203.534 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.1775 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -163.753 MetaTest/__unnamed_task__/AverageReturn -163.753 MetaTest/__unnamed_task__/Iteration 244 MetaTest/__unnamed_task__/MaxReturn -147.493 MetaTest/__unnamed_task__/MinReturn -203.534 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.1775 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.84e+06 __unnamed_task__/AverageDiscountedReturn -70.034 __unnamed_task__/AverageReturn -164.603 __unnamed_task__/Iteration 244 __unnamed_task__/MaxReturn -140.375 __unnamed_task__/MinReturn -224.769 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.5308 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 15:44:52 | [maml_trainer] epoch #245 | Sampling for adapation and meta-testing... 2025-04-03 15:46:04 | [maml_trainer] epoch #245 | Finished meta-testing... 2025-04-03 15:46:04 | [maml_trainer] epoch #245 | Saving snapshot... 2025-04-03 15:46:27 | [maml_trainer] epoch #245 | Saved 2025-04-03 15:46:27 | [maml_trainer] epoch #245 | Time 94265.39 s 2025-04-03 15:46:27 | [maml_trainer] epoch #245 | EpochTime 388.38 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.7577 Average/AverageReturn -171.308 Average/Iteration 245 Average/MaxReturn -141.952 Average/MinReturn -243.676 Average/NumEpisodes 80 Average/StdReturn 25.7794 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2706 GaussianMLPPolicy/KLAfter 0.0035214 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.96544e-05 GaussianMLPPolicy/LossBefore -2.25008e-09 GaussianMLPPolicy/dLoss -5.96566e-05 Iteration 245 MetaTest/Average/AverageDiscountedReturn -167.984 MetaTest/Average/AverageReturn -167.984 MetaTest/Average/Iteration 245 MetaTest/Average/MaxReturn -148.179 MetaTest/Average/MinReturn -230.882 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.6638 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.984 MetaTest/__unnamed_task__/AverageReturn -167.984 MetaTest/__unnamed_task__/Iteration 245 MetaTest/__unnamed_task__/MaxReturn -148.179 MetaTest/__unnamed_task__/MinReturn -230.882 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.6638 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.872e+06 __unnamed_task__/AverageDiscountedReturn -72.7577 __unnamed_task__/AverageReturn -171.308 __unnamed_task__/Iteration 245 __unnamed_task__/MaxReturn -141.952 __unnamed_task__/MinReturn -243.676 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 25.7794 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 15:51:17 | [maml_trainer] epoch #246 | Sampling for adapation and meta-testing... 2025-04-03 15:52:29 | [maml_trainer] epoch #246 | Finished meta-testing... 2025-04-03 15:52:29 | [maml_trainer] epoch #246 | Saving snapshot... 2025-04-03 15:52:53 | [maml_trainer] epoch #246 | Saved 2025-04-03 15:52:53 | [maml_trainer] epoch #246 | Time 94651.56 s 2025-04-03 15:52:53 | [maml_trainer] epoch #246 | EpochTime 386.17 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.4081 Average/AverageReturn -167.584 Average/Iteration 246 Average/MaxReturn -141.513 Average/MinReturn -231.955 Average/NumEpisodes 80 Average/StdReturn 21.1195 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2702 GaussianMLPPolicy/KLAfter 0.00374237 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.92507e-05 GaussianMLPPolicy/LossBefore 2.90573e-09 GaussianMLPPolicy/dLoss -1.92478e-05 Iteration 246 MetaTest/Average/AverageDiscountedReturn -175.43 MetaTest/Average/AverageReturn -175.43 MetaTest/Average/Iteration 246 MetaTest/Average/MaxReturn -146.17 MetaTest/Average/MinReturn -236.124 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 31.7999 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -175.43 MetaTest/__unnamed_task__/AverageReturn -175.43 MetaTest/__unnamed_task__/Iteration 246 MetaTest/__unnamed_task__/MaxReturn -146.17 MetaTest/__unnamed_task__/MinReturn -236.124 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 31.7999 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.904e+06 __unnamed_task__/AverageDiscountedReturn -71.4081 __unnamed_task__/AverageReturn -167.584 __unnamed_task__/Iteration 246 __unnamed_task__/MaxReturn -141.513 __unnamed_task__/MinReturn -231.955 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.1195 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 15:57:43 | [maml_trainer] epoch #247 | Sampling for adapation and meta-testing... 2025-04-03 15:58:55 | [maml_trainer] epoch #247 | Finished meta-testing... 2025-04-03 15:58:55 | [maml_trainer] epoch #247 | Saving snapshot... 2025-04-03 15:59:17 | [maml_trainer] epoch #247 | Saved 2025-04-03 15:59:17 | [maml_trainer] epoch #247 | Time 95035.44 s 2025-04-03 15:59:17 | [maml_trainer] epoch #247 | EpochTime 383.87 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.7907 Average/AverageReturn -166.736 Average/Iteration 247 Average/MaxReturn -144.333 Average/MinReturn -236.071 Average/NumEpisodes 80 Average/StdReturn 20.135 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.27 GaussianMLPPolicy/KLAfter 0.00395351 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.13558e-05 GaussianMLPPolicy/LossBefore 5.06639e-10 GaussianMLPPolicy/dLoss -5.13553e-05 Iteration 247 MetaTest/Average/AverageDiscountedReturn -167.241 MetaTest/Average/AverageReturn -167.241 MetaTest/Average/Iteration 247 MetaTest/Average/MaxReturn -141.765 MetaTest/Average/MinReturn -236.798 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.5418 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.241 MetaTest/__unnamed_task__/AverageReturn -167.241 MetaTest/__unnamed_task__/Iteration 247 MetaTest/__unnamed_task__/MaxReturn -141.765 MetaTest/__unnamed_task__/MinReturn -236.798 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.5418 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.936e+06 __unnamed_task__/AverageDiscountedReturn -70.7907 __unnamed_task__/AverageReturn -166.736 __unnamed_task__/Iteration 247 __unnamed_task__/MaxReturn -144.333 __unnamed_task__/MinReturn -236.071 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.135 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 16:04:06 | [maml_trainer] epoch #248 | Sampling for adapation and meta-testing... 2025-04-03 16:05:17 | [maml_trainer] epoch #248 | Finished meta-testing... 2025-04-03 16:05:17 | [maml_trainer] epoch #248 | Saving snapshot... 2025-04-03 16:05:40 | [maml_trainer] epoch #248 | Saved 2025-04-03 16:05:40 | [maml_trainer] epoch #248 | Time 95418.82 s 2025-04-03 16:05:40 | [maml_trainer] epoch #248 | EpochTime 383.38 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -69.5952 Average/AverageReturn -162.106 Average/Iteration 248 Average/MaxReturn -142.119 Average/MinReturn -226.637 Average/NumEpisodes 80 Average/StdReturn 15.0095 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2707 GaussianMLPPolicy/KLAfter 0.00292049 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.05066e-05 GaussianMLPPolicy/LossBefore -2.6077e-09 GaussianMLPPolicy/dLoss -2.05092e-05 Iteration 248 MetaTest/Average/AverageDiscountedReturn -164.859 MetaTest/Average/AverageReturn -164.859 MetaTest/Average/Iteration 248 MetaTest/Average/MaxReturn -145.481 MetaTest/Average/MinReturn -229.692 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.6562 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.859 MetaTest/__unnamed_task__/AverageReturn -164.859 MetaTest/__unnamed_task__/Iteration 248 MetaTest/__unnamed_task__/MaxReturn -145.481 MetaTest/__unnamed_task__/MinReturn -229.692 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.6562 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.968e+06 __unnamed_task__/AverageDiscountedReturn -69.5952 __unnamed_task__/AverageReturn -162.106 __unnamed_task__/Iteration 248 __unnamed_task__/MaxReturn -142.119 __unnamed_task__/MinReturn -226.637 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 15.0095 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 16:10:30 | [maml_trainer] epoch #249 | Sampling for adapation and meta-testing... 2025-04-03 16:11:43 | [maml_trainer] epoch #249 | Finished meta-testing... 2025-04-03 16:11:43 | [maml_trainer] epoch #249 | Saving snapshot... 2025-04-03 16:12:06 | [maml_trainer] epoch #249 | Saved 2025-04-03 16:12:06 | [maml_trainer] epoch #249 | Time 95804.83 s 2025-04-03 16:12:06 | [maml_trainer] epoch #249 | EpochTime 386.00 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.6638 Average/AverageReturn -167.827 Average/Iteration 249 Average/MaxReturn -146.449 Average/MinReturn -244.603 Average/NumEpisodes 80 Average/StdReturn 23.2453 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2734 GaussianMLPPolicy/KLAfter 0.00304354 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.25151e-06 GaussianMLPPolicy/LossBefore -4.20213e-09 GaussianMLPPolicy/dLoss -6.25572e-06 Iteration 249 MetaTest/Average/AverageDiscountedReturn -161.297 MetaTest/Average/AverageReturn -161.297 MetaTest/Average/Iteration 249 MetaTest/Average/MaxReturn -144.858 MetaTest/Average/MinReturn -235.158 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.5653 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -161.297 MetaTest/__unnamed_task__/AverageReturn -161.297 MetaTest/__unnamed_task__/Iteration 249 MetaTest/__unnamed_task__/MaxReturn -144.858 MetaTest/__unnamed_task__/MinReturn -235.158 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.5653 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8e+06 __unnamed_task__/AverageDiscountedReturn -71.6638 __unnamed_task__/AverageReturn -167.827 __unnamed_task__/Iteration 249 __unnamed_task__/MaxReturn -146.449 __unnamed_task__/MinReturn -244.603 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.2453 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 16:16:57 | [maml_trainer] epoch #250 | Sampling for adapation and meta-testing... 2025-04-03 16:18:10 | [maml_trainer] epoch #250 | Finished meta-testing... 2025-04-03 16:18:10 | [maml_trainer] epoch #250 | Saving snapshot... 2025-04-03 16:18:33 | [maml_trainer] epoch #250 | Saved 2025-04-03 16:18:33 | [maml_trainer] epoch #250 | Time 96191.76 s 2025-04-03 16:18:33 | [maml_trainer] epoch #250 | EpochTime 386.93 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.475 Average/AverageReturn -166.948 Average/Iteration 250 Average/MaxReturn -142.263 Average/MinReturn -230.902 Average/NumEpisodes 80 Average/StdReturn 24.5209 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2752 GaussianMLPPolicy/KLAfter 0.00361342 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.12381e-05 GaussianMLPPolicy/LossBefore 3.01003e-09 GaussianMLPPolicy/dLoss -5.12351e-05 Iteration 250 MetaTest/Average/AverageDiscountedReturn -165.079 MetaTest/Average/AverageReturn -165.079 MetaTest/Average/Iteration 250 MetaTest/Average/MaxReturn -146.313 MetaTest/Average/MinReturn -248.935 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.7343 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.079 MetaTest/__unnamed_task__/AverageReturn -165.079 MetaTest/__unnamed_task__/Iteration 250 MetaTest/__unnamed_task__/MaxReturn -146.313 MetaTest/__unnamed_task__/MinReturn -248.935 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.7343 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.032e+06 __unnamed_task__/AverageDiscountedReturn -71.475 __unnamed_task__/AverageReturn -166.948 __unnamed_task__/Iteration 250 __unnamed_task__/MaxReturn -142.263 __unnamed_task__/MinReturn -230.902 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.5209 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 16:23:23 | [maml_trainer] epoch #251 | Sampling for adapation and meta-testing... 2025-04-03 16:24:35 | [maml_trainer] epoch #251 | Finished meta-testing... 2025-04-03 16:24:35 | [maml_trainer] epoch #251 | Saving snapshot... 2025-04-03 16:24:57 | [maml_trainer] epoch #251 | Saved 2025-04-03 16:24:57 | [maml_trainer] epoch #251 | Time 96575.70 s 2025-04-03 16:24:57 | [maml_trainer] epoch #251 | EpochTime 383.93 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.5872 Average/AverageReturn -168.958 Average/Iteration 251 Average/MaxReturn -143.602 Average/MinReturn -265.978 Average/NumEpisodes 80 Average/StdReturn 25.0989 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2768 GaussianMLPPolicy/KLAfter 0.00299027 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.43036e-05 GaussianMLPPolicy/LossBefore 1.08778e-09 GaussianMLPPolicy/dLoss 3.43047e-05 Iteration 251 MetaTest/Average/AverageDiscountedReturn -161.242 MetaTest/Average/AverageReturn -161.242 MetaTest/Average/Iteration 251 MetaTest/Average/MaxReturn -140.749 MetaTest/Average/MinReturn -230.873 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.1174 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -161.242 MetaTest/__unnamed_task__/AverageReturn -161.242 MetaTest/__unnamed_task__/Iteration 251 MetaTest/__unnamed_task__/MaxReturn -140.749 MetaTest/__unnamed_task__/MinReturn -230.873 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.1174 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.064e+06 __unnamed_task__/AverageDiscountedReturn -72.5872 __unnamed_task__/AverageReturn -168.958 __unnamed_task__/Iteration 251 __unnamed_task__/MaxReturn -143.602 __unnamed_task__/MinReturn -265.978 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 25.0989 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 16:29:45 | [maml_trainer] epoch #252 | Sampling for adapation and meta-testing... 2025-04-03 16:30:58 | [maml_trainer] epoch #252 | Finished meta-testing... 2025-04-03 16:30:58 | [maml_trainer] epoch #252 | Saving snapshot... 2025-04-03 16:31:23 | [maml_trainer] epoch #252 | Saved 2025-04-03 16:31:23 | [maml_trainer] epoch #252 | Time 96961.77 s 2025-04-03 16:31:23 | [maml_trainer] epoch #252 | EpochTime 386.07 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.0512 Average/AverageReturn -162.919 Average/Iteration 252 Average/MaxReturn -143.387 Average/MinReturn -250.321 Average/NumEpisodes 80 Average/StdReturn 22.4906 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2798 GaussianMLPPolicy/KLAfter 0.00328374 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.82929e-05 GaussianMLPPolicy/LossBefore -4.60446e-09 GaussianMLPPolicy/dLoss 5.82882e-05 Iteration 252 MetaTest/Average/AverageDiscountedReturn -162.608 MetaTest/Average/AverageReturn -162.608 MetaTest/Average/Iteration 252 MetaTest/Average/MaxReturn -141.049 MetaTest/Average/MinReturn -227.9 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.5601 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -162.608 MetaTest/__unnamed_task__/AverageReturn -162.608 MetaTest/__unnamed_task__/Iteration 252 MetaTest/__unnamed_task__/MaxReturn -141.049 MetaTest/__unnamed_task__/MinReturn -227.9 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.5601 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.096e+06 __unnamed_task__/AverageDiscountedReturn -70.0512 __unnamed_task__/AverageReturn -162.919 __unnamed_task__/Iteration 252 __unnamed_task__/MaxReturn -143.387 __unnamed_task__/MinReturn -250.321 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.4906 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 16:36:17 | [maml_trainer] epoch #253 | Sampling for adapation and meta-testing... 2025-04-03 16:37:31 | [maml_trainer] epoch #253 | Finished meta-testing... 2025-04-03 16:37:31 | [maml_trainer] epoch #253 | Saving snapshot... 2025-04-03 16:37:56 | [maml_trainer] epoch #253 | Saved 2025-04-03 16:37:56 | [maml_trainer] epoch #253 | Time 97354.64 s 2025-04-03 16:37:56 | [maml_trainer] epoch #253 | EpochTime 392.87 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.7001 Average/AverageReturn -167.508 Average/Iteration 253 Average/MaxReturn -142.527 Average/MinReturn -291.942 Average/NumEpisodes 80 Average/StdReturn 25.3366 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2857 GaussianMLPPolicy/KLAfter 0.00282539 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.46068e-05 GaussianMLPPolicy/LossBefore 3.8147e-09 GaussianMLPPolicy/dLoss 1.46106e-05 Iteration 253 MetaTest/Average/AverageDiscountedReturn -178.678 MetaTest/Average/AverageReturn -178.678 MetaTest/Average/Iteration 253 MetaTest/Average/MaxReturn -146.952 MetaTest/Average/MinReturn -251.94 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 35.4619 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -178.678 MetaTest/__unnamed_task__/AverageReturn -178.678 MetaTest/__unnamed_task__/Iteration 253 MetaTest/__unnamed_task__/MaxReturn -146.952 MetaTest/__unnamed_task__/MinReturn -251.94 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 35.4619 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.128e+06 __unnamed_task__/AverageDiscountedReturn -71.7001 __unnamed_task__/AverageReturn -167.508 __unnamed_task__/Iteration 253 __unnamed_task__/MaxReturn -142.527 __unnamed_task__/MinReturn -291.942 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 25.3366 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 16:42:50 | [maml_trainer] epoch #254 | Sampling for adapation and meta-testing... 2025-04-03 16:44:02 | [maml_trainer] epoch #254 | Finished meta-testing... 2025-04-03 16:44:02 | [maml_trainer] epoch #254 | Saving snapshot... 2025-04-03 16:44:26 | [maml_trainer] epoch #254 | Saved 2025-04-03 16:44:26 | [maml_trainer] epoch #254 | Time 97744.76 s 2025-04-03 16:44:26 | [maml_trainer] epoch #254 | EpochTime 390.11 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.543 Average/AverageReturn -166.507 Average/Iteration 254 Average/MaxReturn -145.2 Average/MinReturn -262.238 Average/NumEpisodes 80 Average/StdReturn 24.1483 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2921 GaussianMLPPolicy/KLAfter 0.0037379 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.85901e-05 GaussianMLPPolicy/LossBefore -1.16825e-08 GaussianMLPPolicy/dLoss -2.86018e-05 Iteration 254 MetaTest/Average/AverageDiscountedReturn -165.341 MetaTest/Average/AverageReturn -165.341 MetaTest/Average/Iteration 254 MetaTest/Average/MaxReturn -139.865 MetaTest/Average/MinReturn -227.406 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.5914 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -165.341 MetaTest/__unnamed_task__/AverageReturn -165.341 MetaTest/__unnamed_task__/Iteration 254 MetaTest/__unnamed_task__/MaxReturn -139.865 MetaTest/__unnamed_task__/MinReturn -227.406 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.5914 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.16e+06 __unnamed_task__/AverageDiscountedReturn -71.543 __unnamed_task__/AverageReturn -166.507 __unnamed_task__/Iteration 254 __unnamed_task__/MaxReturn -145.2 __unnamed_task__/MinReturn -262.238 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.1483 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 16:49:22 | [maml_trainer] epoch #255 | Sampling for adapation and meta-testing... 2025-04-03 16:50:35 | [maml_trainer] epoch #255 | Finished meta-testing... 2025-04-03 16:50:35 | [maml_trainer] epoch #255 | Saving snapshot... 2025-04-03 16:50:57 | [maml_trainer] epoch #255 | Saved 2025-04-03 16:50:57 | [maml_trainer] epoch #255 | Time 98135.70 s 2025-04-03 16:50:57 | [maml_trainer] epoch #255 | EpochTime 390.94 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.0608 Average/AverageReturn -169.704 Average/Iteration 255 Average/MaxReturn -143.616 Average/MinReturn -233.59 Average/NumEpisodes 80 Average/StdReturn 22.39 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.2968 GaussianMLPPolicy/KLAfter 0.00285155 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.41344e-05 GaussianMLPPolicy/LossBefore 6.27339e-09 GaussianMLPPolicy/dLoss -3.41281e-05 Iteration 255 MetaTest/Average/AverageDiscountedReturn -164.463 MetaTest/Average/AverageReturn -164.463 MetaTest/Average/Iteration 255 MetaTest/Average/MaxReturn -148.153 MetaTest/Average/MinReturn -214.272 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.4582 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.463 MetaTest/__unnamed_task__/AverageReturn -164.463 MetaTest/__unnamed_task__/Iteration 255 MetaTest/__unnamed_task__/MaxReturn -148.153 MetaTest/__unnamed_task__/MinReturn -214.272 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.4582 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.192e+06 __unnamed_task__/AverageDiscountedReturn -72.0608 __unnamed_task__/AverageReturn -169.704 __unnamed_task__/Iteration 255 __unnamed_task__/MaxReturn -143.616 __unnamed_task__/MinReturn -233.59 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.39 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 16:55:47 | [maml_trainer] epoch #256 | Sampling for adapation and meta-testing... 2025-04-03 16:56:59 | [maml_trainer] epoch #256 | Finished meta-testing... 2025-04-03 16:56:59 | [maml_trainer] epoch #256 | Saving snapshot... 2025-04-03 16:57:21 | [maml_trainer] epoch #256 | Saved 2025-04-03 16:57:21 | [maml_trainer] epoch #256 | Time 98520.11 s 2025-04-03 16:57:21 | [maml_trainer] epoch #256 | EpochTime 384.41 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.7815 Average/AverageReturn -168.814 Average/Iteration 256 Average/MaxReturn -126.342 Average/MinReturn -238.847 Average/NumEpisodes 80 Average/StdReturn 25.1841 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3016 GaussianMLPPolicy/KLAfter 0.00298244 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.8035e-05 GaussianMLPPolicy/LossBefore 5.33462e-09 GaussianMLPPolicy/dLoss -1.80296e-05 Iteration 256 MetaTest/Average/AverageDiscountedReturn -163.577 MetaTest/Average/AverageReturn -163.577 MetaTest/Average/Iteration 256 MetaTest/Average/MaxReturn -146.023 MetaTest/Average/MinReturn -184.667 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.3719 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -163.577 MetaTest/__unnamed_task__/AverageReturn -163.577 MetaTest/__unnamed_task__/Iteration 256 MetaTest/__unnamed_task__/MaxReturn -146.023 MetaTest/__unnamed_task__/MinReturn -184.667 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.3719 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.224e+06 __unnamed_task__/AverageDiscountedReturn -71.7815 __unnamed_task__/AverageReturn -168.814 __unnamed_task__/Iteration 256 __unnamed_task__/MaxReturn -126.342 __unnamed_task__/MinReturn -238.847 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 25.1841 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 17:02:08 | [maml_trainer] epoch #257 | Sampling for adapation and meta-testing... 2025-04-03 17:03:22 | [maml_trainer] epoch #257 | Finished meta-testing... 2025-04-03 17:03:22 | [maml_trainer] epoch #257 | Saving snapshot... 2025-04-03 17:03:46 | [maml_trainer] epoch #257 | Saved 2025-04-03 17:03:46 | [maml_trainer] epoch #257 | Time 98904.88 s 2025-04-03 17:03:46 | [maml_trainer] epoch #257 | EpochTime 384.77 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.2752 Average/AverageReturn -169.786 Average/Iteration 257 Average/MaxReturn -145.819 Average/MinReturn -243.259 Average/NumEpisodes 80 Average/StdReturn 24.8469 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3058 GaussianMLPPolicy/KLAfter 0.00304664 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.19351e-06 GaussianMLPPolicy/LossBefore 4.42564e-09 GaussianMLPPolicy/dLoss 1.19793e-06 Iteration 257 MetaTest/Average/AverageDiscountedReturn -169.003 MetaTest/Average/AverageReturn -169.003 MetaTest/Average/Iteration 257 MetaTest/Average/MaxReturn -143.056 MetaTest/Average/MinReturn -236.225 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 27.8232 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.003 MetaTest/__unnamed_task__/AverageReturn -169.003 MetaTest/__unnamed_task__/Iteration 257 MetaTest/__unnamed_task__/MaxReturn -143.056 MetaTest/__unnamed_task__/MinReturn -236.225 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 27.8232 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.256e+06 __unnamed_task__/AverageDiscountedReturn -72.2752 __unnamed_task__/AverageReturn -169.786 __unnamed_task__/Iteration 257 __unnamed_task__/MaxReturn -145.819 __unnamed_task__/MinReturn -243.259 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.8469 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 17:08:39 | [maml_trainer] epoch #258 | Sampling for adapation and meta-testing... 2025-04-03 17:09:53 | [maml_trainer] epoch #258 | Finished meta-testing... 2025-04-03 17:09:53 | [maml_trainer] epoch #258 | Saving snapshot... 2025-04-03 17:10:17 | [maml_trainer] epoch #258 | Saved 2025-04-03 17:10:17 | [maml_trainer] epoch #258 | Time 99295.72 s 2025-04-03 17:10:17 | [maml_trainer] epoch #258 | EpochTime 390.84 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.5602 Average/AverageReturn -167.181 Average/Iteration 258 Average/MaxReturn -138.238 Average/MinReturn -255.074 Average/NumEpisodes 80 Average/StdReturn 26.3244 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3102 GaussianMLPPolicy/KLAfter 0.00334873 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.30046e-05 GaussianMLPPolicy/LossBefore 7.59959e-10 GaussianMLPPolicy/dLoss 1.30054e-05 Iteration 258 MetaTest/Average/AverageDiscountedReturn -164.695 MetaTest/Average/AverageReturn -164.695 MetaTest/Average/Iteration 258 MetaTest/Average/MaxReturn -148.562 MetaTest/Average/MinReturn -209.183 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.9499 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -164.695 MetaTest/__unnamed_task__/AverageReturn -164.695 MetaTest/__unnamed_task__/Iteration 258 MetaTest/__unnamed_task__/MaxReturn -148.562 MetaTest/__unnamed_task__/MinReturn -209.183 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.9499 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.288e+06 __unnamed_task__/AverageDiscountedReturn -71.5602 __unnamed_task__/AverageReturn -167.181 __unnamed_task__/Iteration 258 __unnamed_task__/MaxReturn -138.238 __unnamed_task__/MinReturn -255.074 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 26.3244 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 17:15:11 | [maml_trainer] epoch #259 | Sampling for adapation and meta-testing... 2025-04-03 17:16:23 | [maml_trainer] epoch #259 | Finished meta-testing... 2025-04-03 17:16:23 | [maml_trainer] epoch #259 | Saving snapshot... 2025-04-03 17:16:46 | [maml_trainer] epoch #259 | Saved 2025-04-03 17:16:46 | [maml_trainer] epoch #259 | Time 99685.10 s 2025-04-03 17:16:46 | [maml_trainer] epoch #259 | EpochTime 389.38 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.4209 Average/AverageReturn -164.9 Average/Iteration 259 Average/MaxReturn -141.13 Average/MinReturn -249.769 Average/NumEpisodes 80 Average/StdReturn 20.3554 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3134 GaussianMLPPolicy/KLAfter 0.00196528 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.82319e-05 GaussianMLPPolicy/LossBefore 2.87592e-09 GaussianMLPPolicy/dLoss -1.8229e-05 Iteration 259 MetaTest/Average/AverageDiscountedReturn -176.118 MetaTest/Average/AverageReturn -176.118 MetaTest/Average/Iteration 259 MetaTest/Average/MaxReturn -147.76 MetaTest/Average/MinReturn -241.389 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 32.679 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.118 MetaTest/__unnamed_task__/AverageReturn -176.118 MetaTest/__unnamed_task__/Iteration 259 MetaTest/__unnamed_task__/MaxReturn -147.76 MetaTest/__unnamed_task__/MinReturn -241.389 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 32.679 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.32e+06 __unnamed_task__/AverageDiscountedReturn -70.4209 __unnamed_task__/AverageReturn -164.9 __unnamed_task__/Iteration 259 __unnamed_task__/MaxReturn -141.13 __unnamed_task__/MinReturn -249.769 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.3554 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 17:21:39 | [maml_trainer] epoch #260 | Sampling for adapation and meta-testing... 2025-04-03 17:22:51 | [maml_trainer] epoch #260 | Finished meta-testing... 2025-04-03 17:22:51 | [maml_trainer] epoch #260 | Saving snapshot... 2025-04-03 17:23:13 | [maml_trainer] epoch #260 | Saved 2025-04-03 17:23:13 | [maml_trainer] epoch #260 | Time 100071.88 s 2025-04-03 17:23:13 | [maml_trainer] epoch #260 | EpochTime 386.77 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.6544 Average/AverageReturn -169.917 Average/Iteration 260 Average/MaxReturn -145.49 Average/MinReturn -286.815 Average/NumEpisodes 80 Average/StdReturn 24.7724 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3165 GaussianMLPPolicy/KLAfter 0.00340722 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.68721e-05 GaussianMLPPolicy/LossBefore 5.43892e-09 GaussianMLPPolicy/dLoss 1.68775e-05 Iteration 260 MetaTest/Average/AverageDiscountedReturn -168.238 MetaTest/Average/AverageReturn -168.238 MetaTest/Average/Iteration 260 MetaTest/Average/MaxReturn -145.552 MetaTest/Average/MinReturn -238.159 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.4964 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.238 MetaTest/__unnamed_task__/AverageReturn -168.238 MetaTest/__unnamed_task__/Iteration 260 MetaTest/__unnamed_task__/MaxReturn -145.552 MetaTest/__unnamed_task__/MinReturn -238.159 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.4964 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.352e+06 __unnamed_task__/AverageDiscountedReturn -72.6544 __unnamed_task__/AverageReturn -169.917 __unnamed_task__/Iteration 260 __unnamed_task__/MaxReturn -145.49 __unnamed_task__/MinReturn -286.815 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.7724 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 17:28:06 | [maml_trainer] epoch #261 | Sampling for adapation and meta-testing... 2025-04-03 17:29:19 | [maml_trainer] epoch #261 | Finished meta-testing... 2025-04-03 17:29:19 | [maml_trainer] epoch #261 | Saving snapshot... 2025-04-03 17:29:43 | [maml_trainer] epoch #261 | Saved 2025-04-03 17:29:43 | [maml_trainer] epoch #261 | Time 100461.28 s 2025-04-03 17:29:43 | [maml_trainer] epoch #261 | EpochTime 389.39 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.9597 Average/AverageReturn -167.488 Average/Iteration 261 Average/MaxReturn -142.637 Average/MinReturn -308.889 Average/NumEpisodes 80 Average/StdReturn 25.6273 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3186 GaussianMLPPolicy/KLAfter 0.00243566 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.29048e-05 GaussianMLPPolicy/LossBefore 3.33786e-09 GaussianMLPPolicy/dLoss -3.29015e-05 Iteration 261 MetaTest/Average/AverageDiscountedReturn -167.564 MetaTest/Average/AverageReturn -167.564 MetaTest/Average/Iteration 261 MetaTest/Average/MaxReturn -148.04 MetaTest/Average/MinReturn -234.655 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.6744 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.564 MetaTest/__unnamed_task__/AverageReturn -167.564 MetaTest/__unnamed_task__/Iteration 261 MetaTest/__unnamed_task__/MaxReturn -148.04 MetaTest/__unnamed_task__/MinReturn -234.655 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.6744 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.384e+06 __unnamed_task__/AverageDiscountedReturn -70.9597 __unnamed_task__/AverageReturn -167.488 __unnamed_task__/Iteration 261 __unnamed_task__/MaxReturn -142.637 __unnamed_task__/MinReturn -308.889 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 25.6273 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 17:34:35 | [maml_trainer] epoch #262 | Sampling for adapation and meta-testing... 2025-04-03 17:35:48 | [maml_trainer] epoch #262 | Finished meta-testing... 2025-04-03 17:35:48 | [maml_trainer] epoch #262 | Saving snapshot... 2025-04-03 17:36:12 | [maml_trainer] epoch #262 | Saved 2025-04-03 17:36:12 | [maml_trainer] epoch #262 | Time 100850.21 s 2025-04-03 17:36:12 | [maml_trainer] epoch #262 | EpochTime 388.93 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.6814 Average/AverageReturn -169.123 Average/Iteration 262 Average/MaxReturn -141.713 Average/MinReturn -281.505 Average/NumEpisodes 80 Average/StdReturn 26.2425 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3206 GaussianMLPPolicy/KLAfter 0.00302939 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.39259e-05 GaussianMLPPolicy/LossBefore -4.30644e-09 GaussianMLPPolicy/dLoss -2.39302e-05 Iteration 262 MetaTest/Average/AverageDiscountedReturn -163.639 MetaTest/Average/AverageReturn -163.639 MetaTest/Average/Iteration 262 MetaTest/Average/MaxReturn -144.517 MetaTest/Average/MinReturn -187.485 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.8931 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -163.639 MetaTest/__unnamed_task__/AverageReturn -163.639 MetaTest/__unnamed_task__/Iteration 262 MetaTest/__unnamed_task__/MaxReturn -144.517 MetaTest/__unnamed_task__/MinReturn -187.485 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.8931 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.416e+06 __unnamed_task__/AverageDiscountedReturn -71.6814 __unnamed_task__/AverageReturn -169.123 __unnamed_task__/Iteration 262 __unnamed_task__/MaxReturn -141.713 __unnamed_task__/MinReturn -281.505 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 26.2425 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 17:41:04 | [maml_trainer] epoch #263 | Sampling for adapation and meta-testing... 2025-04-03 17:42:16 | [maml_trainer] epoch #263 | Finished meta-testing... 2025-04-03 17:42:16 | [maml_trainer] epoch #263 | Saving snapshot... 2025-04-03 17:42:40 | [maml_trainer] epoch #263 | Saved 2025-04-03 17:42:40 | [maml_trainer] epoch #263 | Time 101238.63 s 2025-04-03 17:42:40 | [maml_trainer] epoch #263 | EpochTime 388.42 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.6132 Average/AverageReturn -172.568 Average/Iteration 263 Average/MaxReturn -145.644 Average/MinReturn -259.58 Average/NumEpisodes 80 Average/StdReturn 29.0812 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3221 GaussianMLPPolicy/KLAfter 0.00307506 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.70885e-05 GaussianMLPPolicy/LossBefore 2.98024e-11 GaussianMLPPolicy/dLoss -1.70884e-05 Iteration 263 MetaTest/Average/AverageDiscountedReturn -161.94 MetaTest/Average/AverageReturn -161.94 MetaTest/Average/Iteration 263 MetaTest/Average/MaxReturn -143.445 MetaTest/Average/MinReturn -180.616 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.2205 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -161.94 MetaTest/__unnamed_task__/AverageReturn -161.94 MetaTest/__unnamed_task__/Iteration 263 MetaTest/__unnamed_task__/MaxReturn -143.445 MetaTest/__unnamed_task__/MinReturn -180.616 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.2205 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.448e+06 __unnamed_task__/AverageDiscountedReturn -72.6132 __unnamed_task__/AverageReturn -172.568 __unnamed_task__/Iteration 263 __unnamed_task__/MaxReturn -145.644 __unnamed_task__/MinReturn -259.58 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 29.0812 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 17:47:33 | [maml_trainer] epoch #264 | Sampling for adapation and meta-testing... 2025-04-03 17:48:45 | [maml_trainer] epoch #264 | Finished meta-testing... 2025-04-03 17:48:45 | [maml_trainer] epoch #264 | Saving snapshot... 2025-04-03 17:49:07 | [maml_trainer] epoch #264 | Saved 2025-04-03 17:49:07 | [maml_trainer] epoch #264 | Time 101625.78 s 2025-04-03 17:49:07 | [maml_trainer] epoch #264 | EpochTime 387.15 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -69.3785 Average/AverageReturn -164.791 Average/Iteration 264 Average/MaxReturn -147.803 Average/MinReturn -222.347 Average/NumEpisodes 80 Average/StdReturn 12.7448 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3246 GaussianMLPPolicy/KLAfter 0.00273015 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.15089e-05 GaussianMLPPolicy/LossBefore -6.55651e-10 GaussianMLPPolicy/dLoss 2.15082e-05 Iteration 264 MetaTest/Average/AverageDiscountedReturn -176.06 MetaTest/Average/AverageReturn -176.06 MetaTest/Average/Iteration 264 MetaTest/Average/MaxReturn -149.659 MetaTest/Average/MinReturn -238.434 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.815 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.06 MetaTest/__unnamed_task__/AverageReturn -176.06 MetaTest/__unnamed_task__/Iteration 264 MetaTest/__unnamed_task__/MaxReturn -149.659 MetaTest/__unnamed_task__/MinReturn -238.434 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.815 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.48e+06 __unnamed_task__/AverageDiscountedReturn -69.3785 __unnamed_task__/AverageReturn -164.791 __unnamed_task__/Iteration 264 __unnamed_task__/MaxReturn -147.803 __unnamed_task__/MinReturn -222.347 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 12.7448 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 17:54:00 | [maml_trainer] epoch #265 | Sampling for adapation and meta-testing... 2025-04-03 17:55:13 | [maml_trainer] epoch #265 | Finished meta-testing... 2025-04-03 17:55:13 | [maml_trainer] epoch #265 | Saving snapshot... 2025-04-03 17:55:37 | [maml_trainer] epoch #265 | Saved 2025-04-03 17:55:37 | [maml_trainer] epoch #265 | Time 102015.15 s 2025-04-03 17:55:37 | [maml_trainer] epoch #265 | EpochTime 389.36 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.9679 Average/AverageReturn -168.859 Average/Iteration 265 Average/MaxReturn -140.296 Average/MinReturn -257.869 Average/NumEpisodes 80 Average/StdReturn 21.1185 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3248 GaussianMLPPolicy/KLAfter 0.00280506 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.55294e-05 GaussianMLPPolicy/LossBefore 2.23517e-10 GaussianMLPPolicy/dLoss 2.55296e-05 Iteration 265 MetaTest/Average/AverageDiscountedReturn -169.83 MetaTest/Average/AverageReturn -169.83 MetaTest/Average/Iteration 265 MetaTest/Average/MaxReturn -146.748 MetaTest/Average/MinReturn -223.112 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.5346 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.83 MetaTest/__unnamed_task__/AverageReturn -169.83 MetaTest/__unnamed_task__/Iteration 265 MetaTest/__unnamed_task__/MaxReturn -146.748 MetaTest/__unnamed_task__/MinReturn -223.112 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.5346 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.512e+06 __unnamed_task__/AverageDiscountedReturn -70.9679 __unnamed_task__/AverageReturn -168.859 __unnamed_task__/Iteration 265 __unnamed_task__/MaxReturn -140.296 __unnamed_task__/MinReturn -257.869 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.1185 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 18:00:29 | [maml_trainer] epoch #266 | Sampling for adapation and meta-testing... 2025-04-03 18:01:41 | [maml_trainer] epoch #266 | Finished meta-testing... 2025-04-03 18:01:41 | [maml_trainer] epoch #266 | Saving snapshot... 2025-04-03 18:02:05 | [maml_trainer] epoch #266 | Saved 2025-04-03 18:02:05 | [maml_trainer] epoch #266 | Time 102403.42 s 2025-04-03 18:02:05 | [maml_trainer] epoch #266 | EpochTime 388.26 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.6353 Average/AverageReturn -176.891 Average/Iteration 266 Average/MaxReturn -147.673 Average/MinReturn -266.898 Average/NumEpisodes 80 Average/StdReturn 25.2123 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3263 GaussianMLPPolicy/KLAfter 0.00302588 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.67077e-06 GaussianMLPPolicy/LossBefore -3.8296e-09 GaussianMLPPolicy/dLoss 5.66694e-06 Iteration 266 MetaTest/Average/AverageDiscountedReturn -168.116 MetaTest/Average/AverageReturn -168.116 MetaTest/Average/Iteration 266 MetaTest/Average/MaxReturn -144.851 MetaTest/Average/MinReturn -192.349 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.8843 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.116 MetaTest/__unnamed_task__/AverageReturn -168.116 MetaTest/__unnamed_task__/Iteration 266 MetaTest/__unnamed_task__/MaxReturn -144.851 MetaTest/__unnamed_task__/MinReturn -192.349 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.8843 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.544e+06 __unnamed_task__/AverageDiscountedReturn -73.6353 __unnamed_task__/AverageReturn -176.891 __unnamed_task__/Iteration 266 __unnamed_task__/MaxReturn -147.673 __unnamed_task__/MinReturn -266.898 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 25.2123 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 18:06:56 | [maml_trainer] epoch #267 | Sampling for adapation and meta-testing... 2025-04-03 18:08:08 | [maml_trainer] epoch #267 | Finished meta-testing... 2025-04-03 18:08:08 | [maml_trainer] epoch #267 | Saving snapshot... 2025-04-03 18:08:32 | [maml_trainer] epoch #267 | Saved 2025-04-03 18:08:32 | [maml_trainer] epoch #267 | Time 102790.23 s 2025-04-03 18:08:32 | [maml_trainer] epoch #267 | EpochTime 386.81 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.1168 Average/AverageReturn -169.438 Average/Iteration 267 Average/MaxReturn -145.874 Average/MinReturn -255.853 Average/NumEpisodes 80 Average/StdReturn 23.6953 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3273 GaussianMLPPolicy/KLAfter 0.00237065 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.14151e-06 GaussianMLPPolicy/LossBefore -9.59635e-09 GaussianMLPPolicy/dLoss -2.1511e-06 Iteration 267 MetaTest/Average/AverageDiscountedReturn -167.924 MetaTest/Average/AverageReturn -167.924 MetaTest/Average/Iteration 267 MetaTest/Average/MaxReturn -144.137 MetaTest/Average/MinReturn -237.894 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.7976 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.924 MetaTest/__unnamed_task__/AverageReturn -167.924 MetaTest/__unnamed_task__/Iteration 267 MetaTest/__unnamed_task__/MaxReturn -144.137 MetaTest/__unnamed_task__/MinReturn -237.894 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.7976 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.576e+06 __unnamed_task__/AverageDiscountedReturn -71.1168 __unnamed_task__/AverageReturn -169.438 __unnamed_task__/Iteration 267 __unnamed_task__/MaxReturn -145.874 __unnamed_task__/MinReturn -255.853 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.6953 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 18:13:22 | [maml_trainer] epoch #268 | Sampling for adapation and meta-testing... 2025-04-03 18:14:36 | [maml_trainer] epoch #268 | Finished meta-testing... 2025-04-03 18:14:36 | [maml_trainer] epoch #268 | Saving snapshot... 2025-04-03 18:14:58 | [maml_trainer] epoch #268 | Saved 2025-04-03 18:14:58 | [maml_trainer] epoch #268 | Time 103176.97 s 2025-04-03 18:14:58 | [maml_trainer] epoch #268 | EpochTime 386.73 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.3354 Average/AverageReturn -174.085 Average/Iteration 268 Average/MaxReturn -146.866 Average/MinReturn -247.71 Average/NumEpisodes 80 Average/StdReturn 24.0561 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3278 GaussianMLPPolicy/KLAfter 0.00195391 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.02356e-06 GaussianMLPPolicy/LossBefore 2.5779e-09 GaussianMLPPolicy/dLoss 1.02614e-06 Iteration 268 MetaTest/Average/AverageDiscountedReturn -167.433 MetaTest/Average/AverageReturn -167.433 MetaTest/Average/Iteration 268 MetaTest/Average/MaxReturn -143.993 MetaTest/Average/MinReturn -236.416 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.9635 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.433 MetaTest/__unnamed_task__/AverageReturn -167.433 MetaTest/__unnamed_task__/Iteration 268 MetaTest/__unnamed_task__/MaxReturn -143.993 MetaTest/__unnamed_task__/MinReturn -236.416 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.9635 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.608e+06 __unnamed_task__/AverageDiscountedReturn -72.3354 __unnamed_task__/AverageReturn -174.085 __unnamed_task__/Iteration 268 __unnamed_task__/MaxReturn -146.866 __unnamed_task__/MinReturn -247.71 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.0561 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 18:19:51 | [maml_trainer] epoch #269 | Sampling for adapation and meta-testing... 2025-04-03 18:21:04 | [maml_trainer] epoch #269 | Finished meta-testing... 2025-04-03 18:21:04 | [maml_trainer] epoch #269 | Saving snapshot... 2025-04-03 18:21:27 | [maml_trainer] epoch #269 | Saved 2025-04-03 18:21:27 | [maml_trainer] epoch #269 | Time 103565.72 s 2025-04-03 18:21:27 | [maml_trainer] epoch #269 | EpochTime 388.75 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.3159 Average/AverageReturn -170.833 Average/Iteration 269 Average/MaxReturn -140.835 Average/MinReturn -254.195 Average/NumEpisodes 80 Average/StdReturn 21.471 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3279 GaussianMLPPolicy/KLAfter 0.00232042 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.30993e-05 GaussianMLPPolicy/LossBefore -4.26173e-09 GaussianMLPPolicy/dLoss -1.31036e-05 Iteration 269 MetaTest/Average/AverageDiscountedReturn -174.477 MetaTest/Average/AverageReturn -174.477 MetaTest/Average/Iteration 269 MetaTest/Average/MaxReturn -152.903 MetaTest/Average/MinReturn -248.501 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 27.1958 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.477 MetaTest/__unnamed_task__/AverageReturn -174.477 MetaTest/__unnamed_task__/Iteration 269 MetaTest/__unnamed_task__/MaxReturn -152.903 MetaTest/__unnamed_task__/MinReturn -248.501 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 27.1958 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.64e+06 __unnamed_task__/AverageDiscountedReturn -71.3159 __unnamed_task__/AverageReturn -170.833 __unnamed_task__/Iteration 269 __unnamed_task__/MaxReturn -140.835 __unnamed_task__/MinReturn -254.195 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.471 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 18:26:20 | [maml_trainer] epoch #270 | Sampling for adapation and meta-testing... 2025-04-03 18:27:33 | [maml_trainer] epoch #270 | Finished meta-testing... 2025-04-03 18:27:33 | [maml_trainer] epoch #270 | Saving snapshot... 2025-04-03 18:27:56 | [maml_trainer] epoch #270 | Saved 2025-04-03 18:27:56 | [maml_trainer] epoch #270 | Time 103954.89 s 2025-04-03 18:27:56 | [maml_trainer] epoch #270 | EpochTime 389.16 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.5753 Average/AverageReturn -174.158 Average/Iteration 270 Average/MaxReturn -141.814 Average/MinReturn -253.399 Average/NumEpisodes 80 Average/StdReturn 23.0556 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3284 GaussianMLPPolicy/KLAfter 0.00154983 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.20944e-06 GaussianMLPPolicy/LossBefore 3.91901e-09 GaussianMLPPolicy/dLoss 1.21336e-06 Iteration 270 MetaTest/Average/AverageDiscountedReturn -177.121 MetaTest/Average/AverageReturn -177.121 MetaTest/Average/Iteration 270 MetaTest/Average/MaxReturn -147.601 MetaTest/Average/MinReturn -273.117 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 33.7103 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.121 MetaTest/__unnamed_task__/AverageReturn -177.121 MetaTest/__unnamed_task__/Iteration 270 MetaTest/__unnamed_task__/MaxReturn -147.601 MetaTest/__unnamed_task__/MinReturn -273.117 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 33.7103 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.672e+06 __unnamed_task__/AverageDiscountedReturn -72.5753 __unnamed_task__/AverageReturn -174.158 __unnamed_task__/Iteration 270 __unnamed_task__/MaxReturn -141.814 __unnamed_task__/MinReturn -253.399 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.0556 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 18:32:48 | [maml_trainer] epoch #271 | Sampling for adapation and meta-testing... 2025-04-03 18:34:01 | [maml_trainer] epoch #271 | Finished meta-testing... 2025-04-03 18:34:01 | [maml_trainer] epoch #271 | Saving snapshot... 2025-04-03 18:34:25 | [maml_trainer] epoch #271 | Saved 2025-04-03 18:34:25 | [maml_trainer] epoch #271 | Time 104343.76 s 2025-04-03 18:34:25 | [maml_trainer] epoch #271 | EpochTime 388.87 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.4005 Average/AverageReturn -173.52 Average/Iteration 271 Average/MaxReturn -144.669 Average/MinReturn -252.43 Average/NumEpisodes 80 Average/StdReturn 24.6608 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3298 GaussianMLPPolicy/KLAfter 0.00140666 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.1213e-05 GaussianMLPPolicy/LossBefore -4.72367e-09 GaussianMLPPolicy/dLoss 1.12083e-05 Iteration 271 MetaTest/Average/AverageDiscountedReturn -177.056 MetaTest/Average/AverageReturn -177.056 MetaTest/Average/Iteration 271 MetaTest/Average/MaxReturn -145.909 MetaTest/Average/MinReturn -253.749 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 28.06 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.056 MetaTest/__unnamed_task__/AverageReturn -177.056 MetaTest/__unnamed_task__/Iteration 271 MetaTest/__unnamed_task__/MaxReturn -145.909 MetaTest/__unnamed_task__/MinReturn -253.749 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 28.06 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.704e+06 __unnamed_task__/AverageDiscountedReturn -72.4005 __unnamed_task__/AverageReturn -173.52 __unnamed_task__/Iteration 271 __unnamed_task__/MaxReturn -144.669 __unnamed_task__/MinReturn -252.43 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.6608 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 18:39:17 | [maml_trainer] epoch #272 | Sampling for adapation and meta-testing... 2025-04-03 18:40:29 | [maml_trainer] epoch #272 | Finished meta-testing... 2025-04-03 18:40:29 | [maml_trainer] epoch #272 | Saving snapshot... 2025-04-03 18:40:53 | [maml_trainer] epoch #272 | Saved 2025-04-03 18:40:53 | [maml_trainer] epoch #272 | Time 104731.69 s 2025-04-03 18:40:53 | [maml_trainer] epoch #272 | EpochTime 387.93 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.1729 Average/AverageReturn -175.133 Average/Iteration 272 Average/MaxReturn -149.818 Average/MinReturn -255.434 Average/NumEpisodes 80 Average/StdReturn 23.2497 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3327 GaussianMLPPolicy/KLAfter 0.0013076 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.04699e-05 GaussianMLPPolicy/LossBefore 3.48687e-09 GaussianMLPPolicy/dLoss 2.04734e-05 Iteration 272 MetaTest/Average/AverageDiscountedReturn -167.241 MetaTest/Average/AverageReturn -167.241 MetaTest/Average/Iteration 272 MetaTest/Average/MaxReturn -148.582 MetaTest/Average/MinReturn -188.748 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.5223 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.241 MetaTest/__unnamed_task__/AverageReturn -167.241 MetaTest/__unnamed_task__/Iteration 272 MetaTest/__unnamed_task__/MaxReturn -148.582 MetaTest/__unnamed_task__/MinReturn -188.748 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.5223 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.736e+06 __unnamed_task__/AverageDiscountedReturn -73.1729 __unnamed_task__/AverageReturn -175.133 __unnamed_task__/Iteration 272 __unnamed_task__/MaxReturn -149.818 __unnamed_task__/MinReturn -255.434 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 23.2497 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 18:45:47 | [maml_trainer] epoch #273 | Sampling for adapation and meta-testing... 2025-04-03 18:47:00 | [maml_trainer] epoch #273 | Finished meta-testing... 2025-04-03 18:47:00 | [maml_trainer] epoch #273 | Saving snapshot... 2025-04-03 18:47:23 | [maml_trainer] epoch #273 | Saved 2025-04-03 18:47:23 | [maml_trainer] epoch #273 | Time 105121.34 s 2025-04-03 18:47:23 | [maml_trainer] epoch #273 | EpochTime 389.64 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.5017 Average/AverageReturn -173.839 Average/Iteration 273 Average/MaxReturn -146.49 Average/MinReturn -251.35 Average/NumEpisodes 80 Average/StdReturn 25.408 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3368 GaussianMLPPolicy/KLAfter 0.00129678 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.60382e-06 GaussianMLPPolicy/LossBefore 6.70552e-10 GaussianMLPPolicy/dLoss 6.60449e-06 Iteration 273 MetaTest/Average/AverageDiscountedReturn -172.037 MetaTest/Average/AverageReturn -172.037 MetaTest/Average/Iteration 273 MetaTest/Average/MaxReturn -147.1 MetaTest/Average/MinReturn -253.12 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 28.8316 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.037 MetaTest/__unnamed_task__/AverageReturn -172.037 MetaTest/__unnamed_task__/Iteration 273 MetaTest/__unnamed_task__/MaxReturn -147.1 MetaTest/__unnamed_task__/MinReturn -253.12 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 28.8316 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.768e+06 __unnamed_task__/AverageDiscountedReturn -72.5017 __unnamed_task__/AverageReturn -173.839 __unnamed_task__/Iteration 273 __unnamed_task__/MaxReturn -146.49 __unnamed_task__/MinReturn -251.35 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 25.408 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 18:52:16 | [maml_trainer] epoch #274 | Sampling for adapation and meta-testing... 2025-04-03 18:53:31 | [maml_trainer] epoch #274 | Finished meta-testing... 2025-04-03 18:53:31 | [maml_trainer] epoch #274 | Saving snapshot... 2025-04-03 18:53:55 | [maml_trainer] epoch #274 | Saved 2025-04-03 18:53:55 | [maml_trainer] epoch #274 | Time 105513.31 s 2025-04-03 18:53:55 | [maml_trainer] epoch #274 | EpochTime 391.96 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.6526 Average/AverageReturn -173.318 Average/Iteration 274 Average/MaxReturn -142.638 Average/MinReturn -265.643 Average/NumEpisodes 80 Average/StdReturn 28.6753 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3439 GaussianMLPPolicy/KLAfter 0.00117068 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.42762e-07 GaussianMLPPolicy/LossBefore -2.39909e-09 GaussianMLPPolicy/dLoss -6.45161e-07 Iteration 274 MetaTest/Average/AverageDiscountedReturn -166.732 MetaTest/Average/AverageReturn -166.732 MetaTest/Average/Iteration 274 MetaTest/Average/MaxReturn -148.451 MetaTest/Average/MinReturn -224.128 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.892 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.732 MetaTest/__unnamed_task__/AverageReturn -166.732 MetaTest/__unnamed_task__/Iteration 274 MetaTest/__unnamed_task__/MaxReturn -148.451 MetaTest/__unnamed_task__/MinReturn -224.128 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.892 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.8e+06 __unnamed_task__/AverageDiscountedReturn -72.6526 __unnamed_task__/AverageReturn -173.318 __unnamed_task__/Iteration 274 __unnamed_task__/MaxReturn -142.638 __unnamed_task__/MinReturn -265.643 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 28.6753 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 18:58:47 | [maml_trainer] epoch #275 | Sampling for adapation and meta-testing... 2025-04-03 19:00:00 | [maml_trainer] epoch #275 | Finished meta-testing... 2025-04-03 19:00:00 | [maml_trainer] epoch #275 | Saving snapshot... 2025-04-03 19:00:24 | [maml_trainer] epoch #275 | Saved 2025-04-03 19:00:24 | [maml_trainer] epoch #275 | Time 105902.55 s 2025-04-03 19:00:24 | [maml_trainer] epoch #275 | EpochTime 389.24 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.1926 Average/AverageReturn -172.99 Average/Iteration 275 Average/MaxReturn -146.536 Average/MinReturn -250.675 Average/NumEpisodes 80 Average/StdReturn 24.545 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3515 GaussianMLPPolicy/KLAfter 0.00351081 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.34679e-05 GaussianMLPPolicy/LossBefore 2.68221e-10 GaussianMLPPolicy/dLoss 3.34682e-05 Iteration 275 MetaTest/Average/AverageDiscountedReturn -176.314 MetaTest/Average/AverageReturn -176.314 MetaTest/Average/Iteration 275 MetaTest/Average/MaxReturn -149.488 MetaTest/Average/MinReturn -244.335 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.425 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.314 MetaTest/__unnamed_task__/AverageReturn -176.314 MetaTest/__unnamed_task__/Iteration 275 MetaTest/__unnamed_task__/MaxReturn -149.488 MetaTest/__unnamed_task__/MinReturn -244.335 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.425 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.832e+06 __unnamed_task__/AverageDiscountedReturn -72.1926 __unnamed_task__/AverageReturn -172.99 __unnamed_task__/Iteration 275 __unnamed_task__/MaxReturn -146.536 __unnamed_task__/MinReturn -250.675 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.545 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 19:05:17 | [maml_trainer] epoch #276 | Sampling for adapation and meta-testing... 2025-04-03 19:06:30 | [maml_trainer] epoch #276 | Finished meta-testing... 2025-04-03 19:06:30 | [maml_trainer] epoch #276 | Saving snapshot... 2025-04-03 19:06:52 | [maml_trainer] epoch #276 | Saved 2025-04-03 19:06:52 | [maml_trainer] epoch #276 | Time 106290.86 s 2025-04-03 19:06:52 | [maml_trainer] epoch #276 | EpochTime 388.31 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.1085 Average/AverageReturn -174.607 Average/Iteration 276 Average/MaxReturn -145.371 Average/MinReturn -261.194 Average/NumEpisodes 80 Average/StdReturn 29.5365 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3559 GaussianMLPPolicy/KLAfter 0.00330584 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.68463e-05 GaussianMLPPolicy/LossBefore -3.60608e-09 GaussianMLPPolicy/dLoss 3.68427e-05 Iteration 276 MetaTest/Average/AverageDiscountedReturn -171.318 MetaTest/Average/AverageReturn -171.318 MetaTest/Average/Iteration 276 MetaTest/Average/MaxReturn -154.313 MetaTest/Average/MinReturn -237.916 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.4162 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.318 MetaTest/__unnamed_task__/AverageReturn -171.318 MetaTest/__unnamed_task__/Iteration 276 MetaTest/__unnamed_task__/MaxReturn -154.313 MetaTest/__unnamed_task__/MinReturn -237.916 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.4162 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.864e+06 __unnamed_task__/AverageDiscountedReturn -73.1085 __unnamed_task__/AverageReturn -174.607 __unnamed_task__/Iteration 276 __unnamed_task__/MaxReturn -145.371 __unnamed_task__/MinReturn -261.194 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 29.5365 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 19:11:25 | [maml_trainer] epoch #277 | Sampling for adapation and meta-testing... 2025-04-03 19:12:32 | [maml_trainer] epoch #277 | Finished meta-testing... 2025-04-03 19:12:32 | [maml_trainer] epoch #277 | Saving snapshot... 2025-04-03 19:12:54 | [maml_trainer] epoch #277 | Saved 2025-04-03 19:12:54 | [maml_trainer] epoch #277 | Time 106652.15 s 2025-04-03 19:12:54 | [maml_trainer] epoch #277 | EpochTime 361.28 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.7793 Average/AverageReturn -168.249 Average/Iteration 277 Average/MaxReturn -145.65 Average/MinReturn -259.136 Average/NumEpisodes 80 Average/StdReturn 24.6257 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3594 GaussianMLPPolicy/KLAfter 0.00279448 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.46429e-05 GaussianMLPPolicy/LossBefore -9.37283e-09 GaussianMLPPolicy/dLoss 1.46336e-05 Iteration 277 MetaTest/Average/AverageDiscountedReturn -172.549 MetaTest/Average/AverageReturn -172.549 MetaTest/Average/Iteration 277 MetaTest/Average/MaxReturn -143.597 MetaTest/Average/MinReturn -257.159 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.0402 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.549 MetaTest/__unnamed_task__/AverageReturn -172.549 MetaTest/__unnamed_task__/Iteration 277 MetaTest/__unnamed_task__/MaxReturn -143.597 MetaTest/__unnamed_task__/MinReturn -257.159 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.0402 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.896e+06 __unnamed_task__/AverageDiscountedReturn -70.7793 __unnamed_task__/AverageReturn -168.249 __unnamed_task__/Iteration 277 __unnamed_task__/MaxReturn -145.65 __unnamed_task__/MinReturn -259.136 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.6257 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 19:17:32 | [maml_trainer] epoch #278 | Sampling for adapation and meta-testing... 2025-04-03 19:18:42 | [maml_trainer] epoch #278 | Finished meta-testing... 2025-04-03 19:18:42 | [maml_trainer] epoch #278 | Saving snapshot... 2025-04-03 19:19:05 | [maml_trainer] epoch #278 | Saved 2025-04-03 19:19:05 | [maml_trainer] epoch #278 | Time 107023.37 s 2025-04-03 19:19:05 | [maml_trainer] epoch #278 | EpochTime 371.22 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.3262 Average/AverageReturn -169.514 Average/Iteration 278 Average/MaxReturn -143.165 Average/MinReturn -264.681 Average/NumEpisodes 80 Average/StdReturn 26.475 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3599 GaussianMLPPolicy/KLAfter 0.00295095 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.63744e-05 GaussianMLPPolicy/LossBefore -5.51343e-10 GaussianMLPPolicy/dLoss -3.6375e-05 Iteration 278 MetaTest/Average/AverageDiscountedReturn -178.203 MetaTest/Average/AverageReturn -178.203 MetaTest/Average/Iteration 278 MetaTest/Average/MaxReturn -147.003 MetaTest/Average/MinReturn -271.268 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 36.3991 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -178.203 MetaTest/__unnamed_task__/AverageReturn -178.203 MetaTest/__unnamed_task__/Iteration 278 MetaTest/__unnamed_task__/MaxReturn -147.003 MetaTest/__unnamed_task__/MinReturn -271.268 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 36.3991 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.928e+06 __unnamed_task__/AverageDiscountedReturn -71.3262 __unnamed_task__/AverageReturn -169.514 __unnamed_task__/Iteration 278 __unnamed_task__/MaxReturn -143.165 __unnamed_task__/MinReturn -264.681 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 26.475 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 19:23:40 | [maml_trainer] epoch #279 | Sampling for adapation and meta-testing... 2025-04-03 19:24:49 | [maml_trainer] epoch #279 | Finished meta-testing... 2025-04-03 19:24:49 | [maml_trainer] epoch #279 | Saving snapshot... 2025-04-03 19:25:11 | [maml_trainer] epoch #279 | Saved 2025-04-03 19:25:11 | [maml_trainer] epoch #279 | Time 107389.74 s 2025-04-03 19:25:11 | [maml_trainer] epoch #279 | EpochTime 366.36 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.7698 Average/AverageReturn -176.631 Average/Iteration 279 Average/MaxReturn -144.74 Average/MinReturn -248.577 Average/NumEpisodes 80 Average/StdReturn 29.4498 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3604 GaussianMLPPolicy/KLAfter 0.00268586 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.70269e-05 GaussianMLPPolicy/LossBefore 2.22027e-09 GaussianMLPPolicy/dLoss 4.70291e-05 Iteration 279 MetaTest/Average/AverageDiscountedReturn -178.953 MetaTest/Average/AverageReturn -178.953 MetaTest/Average/Iteration 279 MetaTest/Average/MaxReturn -151.157 MetaTest/Average/MinReturn -247.039 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.4187 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -178.953 MetaTest/__unnamed_task__/AverageReturn -178.953 MetaTest/__unnamed_task__/Iteration 279 MetaTest/__unnamed_task__/MaxReturn -151.157 MetaTest/__unnamed_task__/MinReturn -247.039 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.4187 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.96e+06 __unnamed_task__/AverageDiscountedReturn -73.7698 __unnamed_task__/AverageReturn -176.631 __unnamed_task__/Iteration 279 __unnamed_task__/MaxReturn -144.74 __unnamed_task__/MinReturn -248.577 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 29.4498 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 19:29:48 | [maml_trainer] epoch #280 | Sampling for adapation and meta-testing... 2025-04-03 19:30:56 | [maml_trainer] epoch #280 | Finished meta-testing... 2025-04-03 19:30:56 | [maml_trainer] epoch #280 | Saving snapshot... 2025-04-03 19:31:18 | [maml_trainer] epoch #280 | Saved 2025-04-03 19:31:18 | [maml_trainer] epoch #280 | Time 107756.71 s 2025-04-03 19:31:18 | [maml_trainer] epoch #280 | EpochTime 366.97 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.3315 Average/AverageReturn -173.356 Average/Iteration 280 Average/MaxReturn -143.848 Average/MinReturn -334.18 Average/NumEpisodes 80 Average/StdReturn 30.7005 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3601 GaussianMLPPolicy/KLAfter 0.00202791 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.46742e-06 GaussianMLPPolicy/LossBefore -1.04308e-10 GaussianMLPPolicy/dLoss 1.46732e-06 Iteration 280 MetaTest/Average/AverageDiscountedReturn -170.271 MetaTest/Average/AverageReturn -170.271 MetaTest/Average/Iteration 280 MetaTest/Average/MaxReturn -151.054 MetaTest/Average/MinReturn -242.084 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.3568 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -170.271 MetaTest/__unnamed_task__/AverageReturn -170.271 MetaTest/__unnamed_task__/Iteration 280 MetaTest/__unnamed_task__/MaxReturn -151.054 MetaTest/__unnamed_task__/MinReturn -242.084 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.3568 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.992e+06 __unnamed_task__/AverageDiscountedReturn -73.3315 __unnamed_task__/AverageReturn -173.356 __unnamed_task__/Iteration 280 __unnamed_task__/MaxReturn -143.848 __unnamed_task__/MinReturn -334.18 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 30.7005 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 19:35:51 | [maml_trainer] epoch #281 | Sampling for adapation and meta-testing... 2025-04-03 19:36:59 | [maml_trainer] epoch #281 | Finished meta-testing... 2025-04-03 19:36:59 | [maml_trainer] epoch #281 | Saving snapshot... 2025-04-03 19:37:21 | [maml_trainer] epoch #281 | Saved 2025-04-03 19:37:21 | [maml_trainer] epoch #281 | Time 108119.39 s 2025-04-03 19:37:21 | [maml_trainer] epoch #281 | EpochTime 362.67 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.7812 Average/AverageReturn -178.196 Average/Iteration 281 Average/MaxReturn -145.362 Average/MinReturn -268.609 Average/NumEpisodes 80 Average/StdReturn 33.9731 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3603 GaussianMLPPolicy/KLAfter 0.00236851 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.88277e-05 GaussianMLPPolicy/LossBefore 4.44055e-09 GaussianMLPPolicy/dLoss -1.88232e-05 Iteration 281 MetaTest/Average/AverageDiscountedReturn -172.534 MetaTest/Average/AverageReturn -172.534 MetaTest/Average/Iteration 281 MetaTest/Average/MaxReturn -151.014 MetaTest/Average/MinReturn -242.149 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.3767 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -172.534 MetaTest/__unnamed_task__/AverageReturn -172.534 MetaTest/__unnamed_task__/Iteration 281 MetaTest/__unnamed_task__/MaxReturn -151.014 MetaTest/__unnamed_task__/MinReturn -242.149 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.3767 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.024e+06 __unnamed_task__/AverageDiscountedReturn -74.7812 __unnamed_task__/AverageReturn -178.196 __unnamed_task__/Iteration 281 __unnamed_task__/MaxReturn -145.362 __unnamed_task__/MinReturn -268.609 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 33.9731 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 19:41:59 | [maml_trainer] epoch #282 | Sampling for adapation and meta-testing... 2025-04-03 19:43:12 | [maml_trainer] epoch #282 | Finished meta-testing... 2025-04-03 19:43:12 | [maml_trainer] epoch #282 | Saving snapshot... 2025-04-03 19:43:36 | [maml_trainer] epoch #282 | Saved 2025-04-03 19:43:36 | [maml_trainer] epoch #282 | Time 108494.79 s 2025-04-03 19:43:36 | [maml_trainer] epoch #282 | EpochTime 375.40 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.2435 Average/AverageReturn -172.927 Average/Iteration 282 Average/MaxReturn -147.222 Average/MinReturn -259.251 Average/NumEpisodes 80 Average/StdReturn 27.7328 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3612 GaussianMLPPolicy/KLAfter 0.00165245 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.30056e-06 GaussianMLPPolicy/LossBefore -3.75509e-09 GaussianMLPPolicy/dLoss 7.2968e-06 Iteration 282 MetaTest/Average/AverageDiscountedReturn -168.067 MetaTest/Average/AverageReturn -168.067 MetaTest/Average/Iteration 282 MetaTest/Average/MaxReturn -144.988 MetaTest/Average/MinReturn -244.043 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.5915 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.067 MetaTest/__unnamed_task__/AverageReturn -168.067 MetaTest/__unnamed_task__/Iteration 282 MetaTest/__unnamed_task__/MaxReturn -144.988 MetaTest/__unnamed_task__/MinReturn -244.043 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.5915 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.056e+06 __unnamed_task__/AverageDiscountedReturn -72.2435 __unnamed_task__/AverageReturn -172.927 __unnamed_task__/Iteration 282 __unnamed_task__/MaxReturn -147.222 __unnamed_task__/MinReturn -259.251 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 27.7328 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 19:48:31 | [maml_trainer] epoch #283 | Sampling for adapation and meta-testing... 2025-04-03 19:49:45 | [maml_trainer] epoch #283 | Finished meta-testing... 2025-04-03 19:49:45 | [maml_trainer] epoch #283 | Saving snapshot... 2025-04-03 19:50:10 | [maml_trainer] epoch #283 | Saved 2025-04-03 19:50:10 | [maml_trainer] epoch #283 | Time 108888.14 s 2025-04-03 19:50:10 | [maml_trainer] epoch #283 | EpochTime 393.35 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.8265 Average/AverageReturn -169.988 Average/Iteration 283 Average/MaxReturn -144.965 Average/MinReturn -268.038 Average/NumEpisodes 80 Average/StdReturn 24.9588 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3631 GaussianMLPPolicy/KLAfter 0.0015496 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.14619e-05 GaussianMLPPolicy/LossBefore -1.51992e-09 GaussianMLPPolicy/dLoss -1.14635e-05 Iteration 283 MetaTest/Average/AverageDiscountedReturn -177.336 MetaTest/Average/AverageReturn -177.336 MetaTest/Average/Iteration 283 MetaTest/Average/MaxReturn -148.977 MetaTest/Average/MinReturn -251.481 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 28.4492 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.336 MetaTest/__unnamed_task__/AverageReturn -177.336 MetaTest/__unnamed_task__/Iteration 283 MetaTest/__unnamed_task__/MaxReturn -148.977 MetaTest/__unnamed_task__/MinReturn -251.481 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 28.4492 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.088e+06 __unnamed_task__/AverageDiscountedReturn -71.8265 __unnamed_task__/AverageReturn -169.988 __unnamed_task__/Iteration 283 __unnamed_task__/MaxReturn -144.965 __unnamed_task__/MinReturn -268.038 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 24.9588 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 19:55:05 | [maml_trainer] epoch #284 | Sampling for adapation and meta-testing... 2025-04-03 19:56:26 | [maml_trainer] epoch #284 | Finished meta-testing... 2025-04-03 19:56:26 | [maml_trainer] epoch #284 | Saving snapshot... 2025-04-03 19:56:51 | [maml_trainer] epoch #284 | Saved 2025-04-03 19:56:51 | [maml_trainer] epoch #284 | Time 109289.13 s 2025-04-03 19:56:51 | [maml_trainer] epoch #284 | EpochTime 400.98 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.5054 Average/AverageReturn -166.904 Average/Iteration 284 Average/MaxReturn -143.589 Average/MinReturn -259.306 Average/NumEpisodes 80 Average/StdReturn 20.6068 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3652 GaussianMLPPolicy/KLAfter 0.00154954 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.39075e-05 GaussianMLPPolicy/LossBefore -5.69224e-09 GaussianMLPPolicy/dLoss -1.39132e-05 Iteration 284 MetaTest/Average/AverageDiscountedReturn -182.78 MetaTest/Average/AverageReturn -182.78 MetaTest/Average/Iteration 284 MetaTest/Average/MaxReturn -144.616 MetaTest/Average/MinReturn -256.286 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 39.3907 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -182.78 MetaTest/__unnamed_task__/AverageReturn -182.78 MetaTest/__unnamed_task__/Iteration 284 MetaTest/__unnamed_task__/MaxReturn -144.616 MetaTest/__unnamed_task__/MinReturn -256.286 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 39.3907 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.12e+06 __unnamed_task__/AverageDiscountedReturn -70.5054 __unnamed_task__/AverageReturn -166.904 __unnamed_task__/Iteration 284 __unnamed_task__/MaxReturn -143.589 __unnamed_task__/MinReturn -259.306 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 20.6068 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 20:01:51 | [maml_trainer] epoch #285 | Sampling for adapation and meta-testing... 2025-04-03 20:03:05 | [maml_trainer] epoch #285 | Finished meta-testing... 2025-04-03 20:03:05 | [maml_trainer] epoch #285 | Saving snapshot... 2025-04-03 20:03:28 | [maml_trainer] epoch #285 | Saved 2025-04-03 20:03:28 | [maml_trainer] epoch #285 | Time 109686.47 s 2025-04-03 20:03:28 | [maml_trainer] epoch #285 | EpochTime 397.33 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.4481 Average/AverageReturn -172.292 Average/Iteration 285 Average/MaxReturn -142.21 Average/MinReturn -263.507 Average/NumEpisodes 80 Average/StdReturn 22.9056 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.368 GaussianMLPPolicy/KLAfter 0.00175447 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.09851e-05 GaussianMLPPolicy/LossBefore 3.65078e-09 GaussianMLPPolicy/dLoss -5.09815e-05 Iteration 285 MetaTest/Average/AverageDiscountedReturn -178.718 MetaTest/Average/AverageReturn -178.718 MetaTest/Average/Iteration 285 MetaTest/Average/MaxReturn -153.753 MetaTest/Average/MinReturn -255.305 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 29.4639 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -178.718 MetaTest/__unnamed_task__/AverageReturn -178.718 MetaTest/__unnamed_task__/Iteration 285 MetaTest/__unnamed_task__/MaxReturn -153.753 MetaTest/__unnamed_task__/MinReturn -255.305 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 29.4639 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.152e+06 __unnamed_task__/AverageDiscountedReturn -72.4481 __unnamed_task__/AverageReturn -172.292 __unnamed_task__/Iteration 285 __unnamed_task__/MaxReturn -142.21 __unnamed_task__/MinReturn -263.507 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.9056 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 20:08:21 | [maml_trainer] epoch #286 | Sampling for adapation and meta-testing... 2025-04-03 20:09:35 | [maml_trainer] epoch #286 | Finished meta-testing... 2025-04-03 20:09:35 | [maml_trainer] epoch #286 | Saving snapshot... 2025-04-03 20:10:00 | [maml_trainer] epoch #286 | Saved 2025-04-03 20:10:00 | [maml_trainer] epoch #286 | Time 110078.28 s 2025-04-03 20:10:00 | [maml_trainer] epoch #286 | EpochTime 391.81 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.6425 Average/AverageReturn -167.395 Average/Iteration 286 Average/MaxReturn -147.78 Average/MinReturn -250.303 Average/NumEpisodes 80 Average/StdReturn 17.2638 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3707 GaussianMLPPolicy/KLAfter 0.00153312 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.12745e-05 GaussianMLPPolicy/LossBefore 3.68059e-09 GaussianMLPPolicy/dLoss -1.12708e-05 Iteration 286 MetaTest/Average/AverageDiscountedReturn -177.339 MetaTest/Average/AverageReturn -177.339 MetaTest/Average/Iteration 286 MetaTest/Average/MaxReturn -152.469 MetaTest/Average/MinReturn -251.969 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 29.3044 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -177.339 MetaTest/__unnamed_task__/AverageReturn -177.339 MetaTest/__unnamed_task__/Iteration 286 MetaTest/__unnamed_task__/MaxReturn -152.469 MetaTest/__unnamed_task__/MinReturn -251.969 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 29.3044 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.184e+06 __unnamed_task__/AverageDiscountedReturn -70.6425 __unnamed_task__/AverageReturn -167.395 __unnamed_task__/Iteration 286 __unnamed_task__/MaxReturn -147.78 __unnamed_task__/MinReturn -250.303 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 17.2638 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 20:14:50 | [maml_trainer] epoch #287 | Sampling for adapation and meta-testing... 2025-04-03 20:16:00 | [maml_trainer] epoch #287 | Finished meta-testing... 2025-04-03 20:16:00 | [maml_trainer] epoch #287 | Saving snapshot... 2025-04-03 20:16:23 | [maml_trainer] epoch #287 | Saved 2025-04-03 20:16:23 | [maml_trainer] epoch #287 | Time 110461.43 s 2025-04-03 20:16:23 | [maml_trainer] epoch #287 | EpochTime 383.14 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.8151 Average/AverageReturn -175.074 Average/Iteration 287 Average/MaxReturn -141.055 Average/MinReturn -258.669 Average/NumEpisodes 80 Average/StdReturn 21.4646 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.372 GaussianMLPPolicy/KLAfter 0.00144233 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.00368e-06 GaussianMLPPolicy/LossBefore 1.2517e-09 GaussianMLPPolicy/dLoss -9.00243e-06 Iteration 287 MetaTest/Average/AverageDiscountedReturn -167.264 MetaTest/Average/AverageReturn -167.264 MetaTest/Average/Iteration 287 MetaTest/Average/MaxReturn -150.639 MetaTest/Average/MinReturn -215.142 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.7561 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -167.264 MetaTest/__unnamed_task__/AverageReturn -167.264 MetaTest/__unnamed_task__/Iteration 287 MetaTest/__unnamed_task__/MaxReturn -150.639 MetaTest/__unnamed_task__/MinReturn -215.142 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.7561 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.216e+06 __unnamed_task__/AverageDiscountedReturn -73.8151 __unnamed_task__/AverageReturn -175.074 __unnamed_task__/Iteration 287 __unnamed_task__/MaxReturn -141.055 __unnamed_task__/MinReturn -258.669 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.4646 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 20:21:31 | [maml_trainer] epoch #288 | Sampling for adapation and meta-testing... 2025-04-03 20:22:40 | [maml_trainer] epoch #288 | Finished meta-testing... 2025-04-03 20:22:40 | [maml_trainer] epoch #288 | Saving snapshot... 2025-04-03 20:23:03 | [maml_trainer] epoch #288 | Saved 2025-04-03 20:23:03 | [maml_trainer] epoch #288 | Time 110861.32 s 2025-04-03 20:23:03 | [maml_trainer] epoch #288 | EpochTime 399.88 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.6726 Average/AverageReturn -172.616 Average/Iteration 288 Average/MaxReturn -144.362 Average/MinReturn -265.938 Average/NumEpisodes 80 Average/StdReturn 26.0597 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3724 GaussianMLPPolicy/KLAfter 0.00139169 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.87796e-05 GaussianMLPPolicy/LossBefore 1.13249e-09 GaussianMLPPolicy/dLoss 2.87807e-05 Iteration 288 MetaTest/Average/AverageDiscountedReturn -179.111 MetaTest/Average/AverageReturn -179.111 MetaTest/Average/Iteration 288 MetaTest/Average/MaxReturn -152.639 MetaTest/Average/MinReturn -237.278 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 28.5954 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -179.111 MetaTest/__unnamed_task__/AverageReturn -179.111 MetaTest/__unnamed_task__/Iteration 288 MetaTest/__unnamed_task__/MaxReturn -152.639 MetaTest/__unnamed_task__/MinReturn -237.278 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 28.5954 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.248e+06 __unnamed_task__/AverageDiscountedReturn -72.6726 __unnamed_task__/AverageReturn -172.616 __unnamed_task__/Iteration 288 __unnamed_task__/MaxReturn -144.362 __unnamed_task__/MinReturn -265.938 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 26.0597 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 20:27:40 | [maml_trainer] epoch #289 | Sampling for adapation and meta-testing... 2025-04-03 20:28:50 | [maml_trainer] epoch #289 | Finished meta-testing... 2025-04-03 20:28:50 | [maml_trainer] epoch #289 | Saving snapshot... 2025-04-03 20:29:11 | [maml_trainer] epoch #289 | Saved 2025-04-03 20:29:11 | [maml_trainer] epoch #289 | Time 111229.64 s 2025-04-03 20:29:11 | [maml_trainer] epoch #289 | EpochTime 368.32 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.8265 Average/AverageReturn -176.324 Average/Iteration 289 Average/MaxReturn -149.393 Average/MinReturn -248.863 Average/NumEpisodes 80 Average/StdReturn 28.5598 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3732 GaussianMLPPolicy/KLAfter 0.00183943 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.31479e-05 GaussianMLPPolicy/LossBefore 2.5481e-09 GaussianMLPPolicy/dLoss -1.31454e-05 Iteration 289 MetaTest/Average/AverageDiscountedReturn -181.41 MetaTest/Average/AverageReturn -181.41 MetaTest/Average/Iteration 289 MetaTest/Average/MaxReturn -152.661 MetaTest/Average/MinReturn -252.129 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 29.4646 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -181.41 MetaTest/__unnamed_task__/AverageReturn -181.41 MetaTest/__unnamed_task__/Iteration 289 MetaTest/__unnamed_task__/MaxReturn -152.661 MetaTest/__unnamed_task__/MinReturn -252.129 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 29.4646 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.28e+06 __unnamed_task__/AverageDiscountedReturn -73.8265 __unnamed_task__/AverageReturn -176.324 __unnamed_task__/Iteration 289 __unnamed_task__/MaxReturn -149.393 __unnamed_task__/MinReturn -248.863 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 28.5598 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 20:33:54 | [maml_trainer] epoch #290 | Sampling for adapation and meta-testing... 2025-04-03 20:35:08 | [maml_trainer] epoch #290 | Finished meta-testing... 2025-04-03 20:35:08 | [maml_trainer] epoch #290 | Saving snapshot... 2025-04-03 20:35:29 | [maml_trainer] epoch #290 | Saved 2025-04-03 20:35:29 | [maml_trainer] epoch #290 | Time 111607.81 s 2025-04-03 20:35:29 | [maml_trainer] epoch #290 | EpochTime 378.17 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.9601 Average/AverageReturn -173.198 Average/Iteration 290 Average/MaxReturn -144.687 Average/MinReturn -270.644 Average/NumEpisodes 80 Average/StdReturn 29.4108 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3726 GaussianMLPPolicy/KLAfter 0.00178566 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.98344e-06 GaussianMLPPolicy/LossBefore 3.48687e-09 GaussianMLPPolicy/dLoss -5.97996e-06 Iteration 290 MetaTest/Average/AverageDiscountedReturn -174.074 MetaTest/Average/AverageReturn -174.074 MetaTest/Average/Iteration 290 MetaTest/Average/MaxReturn -151.467 MetaTest/Average/MinReturn -243.599 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.4034 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.074 MetaTest/__unnamed_task__/AverageReturn -174.074 MetaTest/__unnamed_task__/Iteration 290 MetaTest/__unnamed_task__/MaxReturn -151.467 MetaTest/__unnamed_task__/MinReturn -243.599 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.4034 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.312e+06 __unnamed_task__/AverageDiscountedReturn -72.9601 __unnamed_task__/AverageReturn -173.198 __unnamed_task__/Iteration 290 __unnamed_task__/MaxReturn -144.687 __unnamed_task__/MinReturn -270.644 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 29.4108 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 20:40:09 | [maml_trainer] epoch #291 | Sampling for adapation and meta-testing... 2025-04-03 20:41:20 | [maml_trainer] epoch #291 | Finished meta-testing... 2025-04-03 20:41:20 | [maml_trainer] epoch #291 | Saving snapshot... 2025-04-03 20:41:43 | [maml_trainer] epoch #291 | Saved 2025-04-03 20:41:43 | [maml_trainer] epoch #291 | Time 111982.08 s 2025-04-03 20:41:43 | [maml_trainer] epoch #291 | EpochTime 374.26 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -75.1696 Average/AverageReturn -178.957 Average/Iteration 291 Average/MaxReturn -147.159 Average/MinReturn -259.195 Average/NumEpisodes 80 Average/StdReturn 30.2531 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3717 GaussianMLPPolicy/KLAfter 0.00148154 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.5184e-05 GaussianMLPPolicy/LossBefore -2.68221e-10 GaussianMLPPolicy/dLoss 1.51838e-05 Iteration 291 MetaTest/Average/AverageDiscountedReturn -171.666 MetaTest/Average/AverageReturn -171.666 MetaTest/Average/Iteration 291 MetaTest/Average/MaxReturn -149.081 MetaTest/Average/MinReturn -274.752 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.5837 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -171.666 MetaTest/__unnamed_task__/AverageReturn -171.666 MetaTest/__unnamed_task__/Iteration 291 MetaTest/__unnamed_task__/MaxReturn -149.081 MetaTest/__unnamed_task__/MinReturn -274.752 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.5837 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.344e+06 __unnamed_task__/AverageDiscountedReturn -75.1696 __unnamed_task__/AverageReturn -178.957 __unnamed_task__/Iteration 291 __unnamed_task__/MaxReturn -147.159 __unnamed_task__/MinReturn -259.195 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 30.2531 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 20:46:31 | [maml_trainer] epoch #292 | Sampling for adapation and meta-testing... 2025-04-03 20:47:40 | [maml_trainer] epoch #292 | Finished meta-testing... 2025-04-03 20:47:40 | [maml_trainer] epoch #292 | Saving snapshot... 2025-04-03 20:48:03 | [maml_trainer] epoch #292 | Saved 2025-04-03 20:48:03 | [maml_trainer] epoch #292 | Time 112361.64 s 2025-04-03 20:48:03 | [maml_trainer] epoch #292 | EpochTime 379.56 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.3178 Average/AverageReturn -171.623 Average/Iteration 292 Average/MaxReturn -148.548 Average/MinReturn -251.052 Average/NumEpisodes 80 Average/StdReturn 21.6162 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3692 GaussianMLPPolicy/KLAfter 0.00192854 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.36399e-05 GaussianMLPPolicy/LossBefore 1.00732e-08 GaussianMLPPolicy/dLoss 1.365e-05 Iteration 292 MetaTest/Average/AverageDiscountedReturn -187.631 MetaTest/Average/AverageReturn -187.631 MetaTest/Average/Iteration 292 MetaTest/Average/MaxReturn -147.157 MetaTest/Average/MinReturn -284.213 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 39.0996 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -187.631 MetaTest/__unnamed_task__/AverageReturn -187.631 MetaTest/__unnamed_task__/Iteration 292 MetaTest/__unnamed_task__/MaxReturn -147.157 MetaTest/__unnamed_task__/MinReturn -284.213 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 39.0996 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.376e+06 __unnamed_task__/AverageDiscountedReturn -72.3178 __unnamed_task__/AverageReturn -171.623 __unnamed_task__/Iteration 292 __unnamed_task__/MaxReturn -148.548 __unnamed_task__/MinReturn -251.052 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.6162 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 20:52:53 | [maml_trainer] epoch #293 | Sampling for adapation and meta-testing... 2025-04-03 20:54:05 | [maml_trainer] epoch #293 | Finished meta-testing... 2025-04-03 20:54:05 | [maml_trainer] epoch #293 | Saving snapshot... 2025-04-03 20:54:29 | [maml_trainer] epoch #293 | Saved 2025-04-03 20:54:29 | [maml_trainer] epoch #293 | Time 112747.95 s 2025-04-03 20:54:29 | [maml_trainer] epoch #293 | EpochTime 386.31 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -74.1925 Average/AverageReturn -177.327 Average/Iteration 293 Average/MaxReturn -143.385 Average/MinReturn -255.553 Average/NumEpisodes 80 Average/StdReturn 30.1141 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3662 GaussianMLPPolicy/KLAfter 0.00225784 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.57549e-05 GaussianMLPPolicy/LossBefore 8.44896e-09 GaussianMLPPolicy/dLoss 4.57633e-05 Iteration 293 MetaTest/Average/AverageDiscountedReturn -169.514 MetaTest/Average/AverageReturn -169.514 MetaTest/Average/Iteration 293 MetaTest/Average/MaxReturn -147.023 MetaTest/Average/MinReturn -234.796 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.6942 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.514 MetaTest/__unnamed_task__/AverageReturn -169.514 MetaTest/__unnamed_task__/Iteration 293 MetaTest/__unnamed_task__/MaxReturn -147.023 MetaTest/__unnamed_task__/MinReturn -234.796 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.6942 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.408e+06 __unnamed_task__/AverageDiscountedReturn -74.1925 __unnamed_task__/AverageReturn -177.327 __unnamed_task__/Iteration 293 __unnamed_task__/MaxReturn -143.385 __unnamed_task__/MinReturn -255.553 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 30.1141 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 20:59:12 | [maml_trainer] epoch #294 | Sampling for adapation and meta-testing... 2025-04-03 21:00:22 | [maml_trainer] epoch #294 | Finished meta-testing... 2025-04-03 21:00:22 | [maml_trainer] epoch #294 | Saving snapshot... 2025-04-03 21:00:44 | [maml_trainer] epoch #294 | Saved 2025-04-03 21:00:44 | [maml_trainer] epoch #294 | Time 113122.38 s 2025-04-03 21:00:44 | [maml_trainer] epoch #294 | EpochTime 374.42 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -72.1632 Average/AverageReturn -171.178 Average/Iteration 294 Average/MaxReturn -144.086 Average/MinReturn -245.256 Average/NumEpisodes 80 Average/StdReturn 22.8647 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3641 GaussianMLPPolicy/KLAfter 0.00147158 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.12132e-05 GaussianMLPPolicy/LossBefore -6.10948e-09 GaussianMLPPolicy/dLoss -3.12193e-05 Iteration 294 MetaTest/Average/AverageDiscountedReturn -169.536 MetaTest/Average/AverageReturn -169.536 MetaTest/Average/Iteration 294 MetaTest/Average/MaxReturn -152.112 MetaTest/Average/MinReturn -228.25 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.9397 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -169.536 MetaTest/__unnamed_task__/AverageReturn -169.536 MetaTest/__unnamed_task__/Iteration 294 MetaTest/__unnamed_task__/MaxReturn -152.112 MetaTest/__unnamed_task__/MinReturn -228.25 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.9397 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.44e+06 __unnamed_task__/AverageDiscountedReturn -72.1632 __unnamed_task__/AverageReturn -171.178 __unnamed_task__/Iteration 294 __unnamed_task__/MaxReturn -144.086 __unnamed_task__/MinReturn -245.256 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 22.8647 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 21:05:27 | [maml_trainer] epoch #295 | Sampling for adapation and meta-testing... 2025-04-03 21:06:40 | [maml_trainer] epoch #295 | Finished meta-testing... 2025-04-03 21:06:40 | [maml_trainer] epoch #295 | Saving snapshot... 2025-04-03 21:07:04 | [maml_trainer] epoch #295 | Saved 2025-04-03 21:07:04 | [maml_trainer] epoch #295 | Time 113502.37 s 2025-04-03 21:07:04 | [maml_trainer] epoch #295 | EpochTime 379.99 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -75.4522 Average/AverageReturn -181.286 Average/Iteration 295 Average/MaxReturn -141.611 Average/MinReturn -273.381 Average/NumEpisodes 80 Average/StdReturn 31.85 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.362 GaussianMLPPolicy/KLAfter 0.00228395 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.1421e-06 GaussianMLPPolicy/LossBefore 5.96046e-09 GaussianMLPPolicy/dLoss -1.13614e-06 Iteration 295 MetaTest/Average/AverageDiscountedReturn -176.069 MetaTest/Average/AverageReturn -176.069 MetaTest/Average/Iteration 295 MetaTest/Average/MaxReturn -146.699 MetaTest/Average/MinReturn -234.511 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.5037 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -176.069 MetaTest/__unnamed_task__/AverageReturn -176.069 MetaTest/__unnamed_task__/Iteration 295 MetaTest/__unnamed_task__/MaxReturn -146.699 MetaTest/__unnamed_task__/MinReturn -234.511 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.5037 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.472e+06 __unnamed_task__/AverageDiscountedReturn -75.4522 __unnamed_task__/AverageReturn -181.286 __unnamed_task__/Iteration 295 __unnamed_task__/MaxReturn -141.611 __unnamed_task__/MinReturn -273.381 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 31.85 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 21:11:54 | [maml_trainer] epoch #296 | Sampling for adapation and meta-testing... 2025-04-03 21:13:05 | [maml_trainer] epoch #296 | Finished meta-testing... 2025-04-03 21:13:05 | [maml_trainer] epoch #296 | Saving snapshot... 2025-04-03 21:13:27 | [maml_trainer] epoch #296 | Saved 2025-04-03 21:13:27 | [maml_trainer] epoch #296 | Time 113886.00 s 2025-04-03 21:13:27 | [maml_trainer] epoch #296 | EpochTime 383.63 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.191 Average/AverageReturn -168.701 Average/Iteration 296 Average/MaxReturn -133.586 Average/MinReturn -237.8 Average/NumEpisodes 80 Average/StdReturn 19.4691 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3598 GaussianMLPPolicy/KLAfter 0.00333436 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.0586e-05 GaussianMLPPolicy/LossBefore -3.8743e-09 GaussianMLPPolicy/dLoss 2.05821e-05 Iteration 296 MetaTest/Average/AverageDiscountedReturn -161.099 MetaTest/Average/AverageReturn -161.099 MetaTest/Average/Iteration 296 MetaTest/Average/MaxReturn -144.712 MetaTest/Average/MinReturn -197.575 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.7881 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -161.099 MetaTest/__unnamed_task__/AverageReturn -161.099 MetaTest/__unnamed_task__/Iteration 296 MetaTest/__unnamed_task__/MaxReturn -144.712 MetaTest/__unnamed_task__/MinReturn -197.575 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.7881 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.504e+06 __unnamed_task__/AverageDiscountedReturn -71.191 __unnamed_task__/AverageReturn -168.701 __unnamed_task__/Iteration 296 __unnamed_task__/MaxReturn -133.586 __unnamed_task__/MinReturn -237.8 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.4691 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 21:17:59 | [maml_trainer] epoch #297 | Sampling for adapation and meta-testing... 2025-04-03 21:19:08 | [maml_trainer] epoch #297 | Finished meta-testing... 2025-04-03 21:19:08 | [maml_trainer] epoch #297 | Saving snapshot... 2025-04-03 21:19:31 | [maml_trainer] epoch #297 | Saved 2025-04-03 21:19:31 | [maml_trainer] epoch #297 | Time 114249.64 s 2025-04-03 21:19:31 | [maml_trainer] epoch #297 | EpochTime 363.63 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -71.7137 Average/AverageReturn -169.813 Average/Iteration 297 Average/MaxReturn -148.2 Average/MinReturn -248.355 Average/NumEpisodes 80 Average/StdReturn 21.3602 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3578 GaussianMLPPolicy/KLAfter 0.0033978 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.0634e-05 GaussianMLPPolicy/LossBefore -7.40588e-09 GaussianMLPPolicy/dLoss -3.06414e-05 Iteration 297 MetaTest/Average/AverageDiscountedReturn -173.239 MetaTest/Average/AverageReturn -173.239 MetaTest/Average/Iteration 297 MetaTest/Average/MaxReturn -149.417 MetaTest/Average/MinReturn -197.427 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.4173 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -173.239 MetaTest/__unnamed_task__/AverageReturn -173.239 MetaTest/__unnamed_task__/Iteration 297 MetaTest/__unnamed_task__/MaxReturn -149.417 MetaTest/__unnamed_task__/MinReturn -197.427 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.4173 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.536e+06 __unnamed_task__/AverageDiscountedReturn -71.7137 __unnamed_task__/AverageReturn -169.813 __unnamed_task__/Iteration 297 __unnamed_task__/MaxReturn -148.2 __unnamed_task__/MinReturn -248.355 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 21.3602 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 21:24:59 | [maml_trainer] epoch #298 | Sampling for adapation and meta-testing... 2025-04-03 21:26:08 | [maml_trainer] epoch #298 | Finished meta-testing... 2025-04-03 21:26:08 | [maml_trainer] epoch #298 | Saving snapshot... 2025-04-03 21:26:29 | [maml_trainer] epoch #298 | Saved 2025-04-03 21:26:29 | [maml_trainer] epoch #298 | Time 114667.84 s 2025-04-03 21:26:29 | [maml_trainer] epoch #298 | EpochTime 418.20 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -70.2542 Average/AverageReturn -166.447 Average/Iteration 298 Average/MaxReturn -144.305 Average/MinReturn -242.4 Average/NumEpisodes 80 Average/StdReturn 19.7533 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3568 GaussianMLPPolicy/KLAfter 0.0039289 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.65908e-05 GaussianMLPPolicy/LossBefore 2.5332e-10 GaussianMLPPolicy/dLoss -2.65905e-05 Iteration 298 MetaTest/Average/AverageDiscountedReturn -166.681 MetaTest/Average/AverageReturn -166.681 MetaTest/Average/Iteration 298 MetaTest/Average/MaxReturn -145.206 MetaTest/Average/MinReturn -246.858 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.8889 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -166.681 MetaTest/__unnamed_task__/AverageReturn -166.681 MetaTest/__unnamed_task__/Iteration 298 MetaTest/__unnamed_task__/MaxReturn -145.206 MetaTest/__unnamed_task__/MinReturn -246.858 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.8889 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.568e+06 __unnamed_task__/AverageDiscountedReturn -70.2542 __unnamed_task__/AverageReturn -166.447 __unnamed_task__/Iteration 298 __unnamed_task__/MaxReturn -144.305 __unnamed_task__/MinReturn -242.4 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 19.7533 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-03 21:31:04 | [maml_trainer] epoch #299 | Sampling for adapation and meta-testing... 2025-04-03 21:32:12 | [maml_trainer] epoch #299 | Finished meta-testing... 2025-04-03 21:32:12 | [maml_trainer] epoch #299 | Saving snapshot... 2025-04-03 21:32:34 | [maml_trainer] epoch #299 | Saved 2025-04-03 21:32:34 | [maml_trainer] epoch #299 | Time 115032.69 s 2025-04-03 21:32:34 | [maml_trainer] epoch #299 | EpochTime 364.84 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -73.0962 Average/AverageReturn -173.621 Average/Iteration 299 Average/MaxReturn -142.596 Average/MinReturn -246.929 Average/NumEpisodes 80 Average/StdReturn 25.9552 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 19.3556 GaussianMLPPolicy/KLAfter 0.00389229 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.883e-06 GaussianMLPPolicy/LossBefore 3.42727e-09 GaussianMLPPolicy/dLoss -7.87957e-06 Iteration 299 MetaTest/Average/AverageDiscountedReturn -174.034 MetaTest/Average/AverageReturn -174.034 MetaTest/Average/Iteration 299 MetaTest/Average/MaxReturn -142.113 MetaTest/Average/MinReturn -239.768 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 30.6841 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -174.034 MetaTest/__unnamed_task__/AverageReturn -174.034 MetaTest/__unnamed_task__/Iteration 299 MetaTest/__unnamed_task__/MaxReturn -142.113 MetaTest/__unnamed_task__/MinReturn -239.768 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 30.6841 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.6e+06 __unnamed_task__/AverageDiscountedReturn -73.0962 __unnamed_task__/AverageReturn -173.621 __unnamed_task__/Iteration 299 __unnamed_task__/MaxReturn -142.596 __unnamed_task__/MinReturn -246.929 __unnamed_task__/NumEpisodes 80 __unnamed_task__/StdReturn 25.9552 __unnamed_task__/TerminationRate 0 ------------------------------------------------- --------------