2025-04-03 16:31:12 | [maml_trainer] Logging to /home/h2khalil/MetaRL-Assistive-Robotics/data/local/experiment/maml_trainer_3 2025-04-03 16:39:16 | [maml_trainer] Obtaining samples... 2025-04-03 17:02:25 | [maml_trainer] epoch #0 | Sampling for adapation and meta-testing... 2025-04-03 17:06:20 | [maml_trainer] epoch #0 | Finished meta-testing... 2025-04-03 17:06:20 | [maml_trainer] epoch #0 | Saving snapshot... 2025-04-03 17:06:38 | [maml_trainer] epoch #0 | Saved 2025-04-03 17:06:38 | [maml_trainer] epoch #0 | Time 1642.92 s 2025-04-03 17:06:38 | [maml_trainer] epoch #0 | EpochTime 1642.92 s ------------------------------------------------- --------------- Average/AverageDiscountedReturn -82.2053 Average/AverageReturn -193.763 Average/Iteration 0 Average/MaxReturn -134.335 Average/MinReturn -217.6 Average/NumEpisodes 120 Average/StdReturn 18.2797 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.92566 GaussianMLPPolicy/KLAfter 0.0297345 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.1981e-05 GaussianMLPPolicy/LossBefore -9.63608e-10 GaussianMLPPolicy/dLoss -8.1982e-05 Iteration 0 MetaTest/Average/AverageDiscountedReturn -179.135 MetaTest/Average/AverageReturn -179.135 MetaTest/Average/Iteration 0 MetaTest/Average/MaxReturn -137.176 MetaTest/Average/MinReturn -216.652 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.8925 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -179.135 MetaTest/__unnamed_task__/AverageReturn -179.135 MetaTest/__unnamed_task__/Iteration 0 MetaTest/__unnamed_task__/MaxReturn -137.176 MetaTest/__unnamed_task__/MinReturn -216.652 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.8925 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 48000 __unnamed_task__/AverageDiscountedReturn -82.2053 __unnamed_task__/AverageReturn -193.763 __unnamed_task__/Iteration 0 __unnamed_task__/MaxReturn -134.335 __unnamed_task__/MinReturn -217.6 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 18.2797 __unnamed_task__/TerminationRate 0 ------------------------------------------------- --------------- 2025-04-03 17:29:52 | [maml_trainer] epoch #1 | Sampling for adapation and meta-testing... 2025-04-03 17:33:42 | [maml_trainer] epoch #1 | Finished meta-testing... 2025-04-03 17:33:42 | [maml_trainer] epoch #1 | Saving snapshot... 2025-04-03 17:34:02 | [maml_trainer] epoch #1 | Saved 2025-04-03 17:34:02 | [maml_trainer] epoch #1 | Time 3286.21 s 2025-04-03 17:34:02 | [maml_trainer] epoch #1 | EpochTime 1643.29 s ------------------------------------------------- --------------- Average/AverageDiscountedReturn -78.4917 Average/AverageReturn -184.439 Average/Iteration 1 Average/MaxReturn -128.929 Average/MinReturn -221.723 Average/NumEpisodes 120 Average/StdReturn 25.6009 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.92805 GaussianMLPPolicy/KLAfter 0.0168477 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.67706e-06 GaussianMLPPolicy/LossBefore 3.0299e-09 GaussianMLPPolicy/dLoss 3.68009e-06 Iteration 1 MetaTest/Average/AverageDiscountedReturn -183.157 MetaTest/Average/AverageReturn -183.157 MetaTest/Average/Iteration 1 MetaTest/Average/MaxReturn -146.68 MetaTest/Average/MinReturn -220.859 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 21.4197 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -183.157 MetaTest/__unnamed_task__/AverageReturn -183.157 MetaTest/__unnamed_task__/Iteration 1 MetaTest/__unnamed_task__/MaxReturn -146.68 MetaTest/__unnamed_task__/MinReturn -220.859 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 21.4197 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 96000 __unnamed_task__/AverageDiscountedReturn -78.4917 __unnamed_task__/AverageReturn -184.439 __unnamed_task__/Iteration 1 __unnamed_task__/MaxReturn -128.929 __unnamed_task__/MinReturn -221.723 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 25.6009 __unnamed_task__/TerminationRate 0 ------------------------------------------------- --------------- 2025-04-03 17:57:10 | [maml_trainer] epoch #2 | Sampling for adapation and meta-testing... 2025-04-03 18:01:01 | [maml_trainer] epoch #2 | Finished meta-testing... 2025-04-03 18:01:01 | [maml_trainer] epoch #2 | Saving snapshot... 2025-04-03 18:01:22 | [maml_trainer] epoch #2 | Saved 2025-04-03 18:01:22 | [maml_trainer] epoch #2 | Time 4926.26 s 2025-04-03 18:01:22 | [maml_trainer] epoch #2 | EpochTime 1640.05 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -73.3937 Average/AverageReturn -172.945 Average/Iteration 2 Average/MaxReturn -126.256 Average/MinReturn -230.744 Average/NumEpisodes 120 Average/StdReturn 26.519 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.93248 GaussianMLPPolicy/KLAfter 0.0111545 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.0001372 GaussianMLPPolicy/LossBefore -7.2519e-09 GaussianMLPPolicy/dLoss 0.000137193 Iteration 2 MetaTest/Average/AverageDiscountedReturn -159.761 MetaTest/Average/AverageReturn -159.761 MetaTest/Average/Iteration 2 MetaTest/Average/MaxReturn -133.559 MetaTest/Average/MinReturn -215.737 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.5506 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -159.761 MetaTest/__unnamed_task__/AverageReturn -159.761 MetaTest/__unnamed_task__/Iteration 2 MetaTest/__unnamed_task__/MaxReturn -133.559 MetaTest/__unnamed_task__/MinReturn -215.737 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.5506 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 144000 __unnamed_task__/AverageDiscountedReturn -73.3937 __unnamed_task__/AverageReturn -172.945 __unnamed_task__/Iteration 2 __unnamed_task__/MaxReturn -126.256 __unnamed_task__/MinReturn -230.744 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 26.519 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 18:24:39 | [maml_trainer] epoch #3 | Sampling for adapation and meta-testing... 2025-04-03 18:28:31 | [maml_trainer] epoch #3 | Finished meta-testing... 2025-04-03 18:28:31 | [maml_trainer] epoch #3 | Saving snapshot... 2025-04-03 18:28:51 | [maml_trainer] epoch #3 | Saved 2025-04-03 18:28:51 | [maml_trainer] epoch #3 | Time 6575.80 s 2025-04-03 18:28:51 | [maml_trainer] epoch #3 | EpochTime 1649.54 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -70.2883 Average/AverageReturn -165.004 Average/Iteration 3 Average/MaxReturn -131.759 Average/MinReturn -218.736 Average/NumEpisodes 120 Average/StdReturn 22.0294 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.93532 GaussianMLPPolicy/KLAfter 0.00980512 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.78498e-05 GaussianMLPPolicy/LossBefore 1.15236e-09 GaussianMLPPolicy/dLoss 7.78509e-05 Iteration 3 MetaTest/Average/AverageDiscountedReturn -155.667 MetaTest/Average/AverageReturn -155.667 MetaTest/Average/Iteration 3 MetaTest/Average/MaxReturn -134.895 MetaTest/Average/MinReturn -207.028 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.1626 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -155.667 MetaTest/__unnamed_task__/AverageReturn -155.667 MetaTest/__unnamed_task__/Iteration 3 MetaTest/__unnamed_task__/MaxReturn -134.895 MetaTest/__unnamed_task__/MinReturn -207.028 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.1626 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 192000 __unnamed_task__/AverageDiscountedReturn -70.2883 __unnamed_task__/AverageReturn -165.004 __unnamed_task__/Iteration 3 __unnamed_task__/MaxReturn -131.759 __unnamed_task__/MinReturn -218.736 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 22.0294 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 18:52:07 | [maml_trainer] epoch #4 | Sampling for adapation and meta-testing... 2025-04-03 18:56:00 | [maml_trainer] epoch #4 | Finished meta-testing... 2025-04-03 18:56:00 | [maml_trainer] epoch #4 | Saving snapshot... 2025-04-03 18:56:21 | [maml_trainer] epoch #4 | Saved 2025-04-03 18:56:21 | [maml_trainer] epoch #4 | Time 8225.39 s 2025-04-03 18:56:21 | [maml_trainer] epoch #4 | EpochTime 1649.58 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -66.3017 Average/AverageReturn -155.735 Average/Iteration 4 Average/MaxReturn -123.512 Average/MinReturn -222.567 Average/NumEpisodes 120 Average/StdReturn 17.4132 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.93762 GaussianMLPPolicy/KLAfter 0.00974523 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.5226e-05 GaussianMLPPolicy/LossBefore 6.25849e-09 GaussianMLPPolicy/dLoss 6.52322e-05 Iteration 4 MetaTest/Average/AverageDiscountedReturn -148.552 MetaTest/Average/AverageReturn -148.552 MetaTest/Average/Iteration 4 MetaTest/Average/MaxReturn -133.266 MetaTest/Average/MinReturn -195.425 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.1364 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -148.552 MetaTest/__unnamed_task__/AverageReturn -148.552 MetaTest/__unnamed_task__/Iteration 4 MetaTest/__unnamed_task__/MaxReturn -133.266 MetaTest/__unnamed_task__/MinReturn -195.425 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.1364 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 240000 __unnamed_task__/AverageDiscountedReturn -66.3017 __unnamed_task__/AverageReturn -155.735 __unnamed_task__/Iteration 4 __unnamed_task__/MaxReturn -123.512 __unnamed_task__/MinReturn -222.567 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 17.4132 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 19:19:02 | [maml_trainer] epoch #5 | Sampling for adapation and meta-testing... 2025-04-03 19:22:41 | [maml_trainer] epoch #5 | Finished meta-testing... 2025-04-03 19:22:41 | [maml_trainer] epoch #5 | Saving snapshot... 2025-04-03 19:23:00 | [maml_trainer] epoch #5 | Saved 2025-04-03 19:23:00 | [maml_trainer] epoch #5 | Time 9824.86 s 2025-04-03 19:23:00 | [maml_trainer] epoch #5 | EpochTime 1599.47 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -63.4067 Average/AverageReturn -148.828 Average/Iteration 5 Average/MaxReturn -129.488 Average/MinReturn -186.101 Average/NumEpisodes 120 Average/StdReturn 9.23365 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94014 GaussianMLPPolicy/KLAfter 0.00489618 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.17414e-05 GaussianMLPPolicy/LossBefore -6.39757e-09 GaussianMLPPolicy/dLoss 5.1735e-05 Iteration 5 MetaTest/Average/AverageDiscountedReturn -144.55 MetaTest/Average/AverageReturn -144.55 MetaTest/Average/Iteration 5 MetaTest/Average/MaxReturn -126.715 MetaTest/Average/MinReturn -209.422 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.524 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -144.55 MetaTest/__unnamed_task__/AverageReturn -144.55 MetaTest/__unnamed_task__/Iteration 5 MetaTest/__unnamed_task__/MaxReturn -126.715 MetaTest/__unnamed_task__/MinReturn -209.422 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.524 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 288000 __unnamed_task__/AverageDiscountedReturn -63.4067 __unnamed_task__/AverageReturn -148.828 __unnamed_task__/Iteration 5 __unnamed_task__/MaxReturn -129.488 __unnamed_task__/MinReturn -186.101 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.23365 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 19:45:08 | [maml_trainer] epoch #6 | Sampling for adapation and meta-testing... 2025-04-03 19:49:06 | [maml_trainer] epoch #6 | Finished meta-testing... 2025-04-03 19:49:06 | [maml_trainer] epoch #6 | Saving snapshot... 2025-04-03 19:49:26 | [maml_trainer] epoch #6 | Saved 2025-04-03 19:49:26 | [maml_trainer] epoch #6 | Time 11410.93 s 2025-04-03 19:49:26 | [maml_trainer] epoch #6 | EpochTime 1586.06 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -61.965 Average/AverageReturn -145.442 Average/Iteration 6 Average/MaxReturn -125.238 Average/MinReturn -220.577 Average/NumEpisodes 120 Average/StdReturn 12.3678 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94429 GaussianMLPPolicy/KLAfter 0.00382896 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.01783e-05 GaussianMLPPolicy/LossBefore 4.43061e-09 GaussianMLPPolicy/dLoss -4.01738e-05 Iteration 6 MetaTest/Average/AverageDiscountedReturn -145.659 MetaTest/Average/AverageReturn -145.659 MetaTest/Average/Iteration 6 MetaTest/Average/MaxReturn -132.179 MetaTest/Average/MinReturn -169.705 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.14661 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -145.659 MetaTest/__unnamed_task__/AverageReturn -145.659 MetaTest/__unnamed_task__/Iteration 6 MetaTest/__unnamed_task__/MaxReturn -132.179 MetaTest/__unnamed_task__/MinReturn -169.705 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.14661 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 336000 __unnamed_task__/AverageDiscountedReturn -61.965 __unnamed_task__/AverageReturn -145.442 __unnamed_task__/Iteration 6 __unnamed_task__/MaxReturn -125.238 __unnamed_task__/MinReturn -220.577 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.3678 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 20:13:20 | [maml_trainer] epoch #7 | Sampling for adapation and meta-testing... 2025-04-03 20:17:03 | [maml_trainer] epoch #7 | Finished meta-testing... 2025-04-03 20:17:03 | [maml_trainer] epoch #7 | Saving snapshot... 2025-04-03 20:17:23 | [maml_trainer] epoch #7 | Saved 2025-04-03 20:17:23 | [maml_trainer] epoch #7 | Time 13087.38 s 2025-04-03 20:17:23 | [maml_trainer] epoch #7 | EpochTime 1676.45 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -61.8576 Average/AverageReturn -144.795 Average/Iteration 7 Average/MaxReturn -122.64 Average/MinReturn -206.512 Average/NumEpisodes 120 Average/StdReturn 11.5804 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94718 GaussianMLPPolicy/KLAfter 0.00578938 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.91971e-06 GaussianMLPPolicy/LossBefore -1.20004e-08 GaussianMLPPolicy/dLoss 4.90771e-06 Iteration 7 MetaTest/Average/AverageDiscountedReturn -144.293 MetaTest/Average/AverageReturn -144.293 MetaTest/Average/Iteration 7 MetaTest/Average/MaxReturn -130.101 MetaTest/Average/MinReturn -156.358 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.62275 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -144.293 MetaTest/__unnamed_task__/AverageReturn -144.293 MetaTest/__unnamed_task__/Iteration 7 MetaTest/__unnamed_task__/MaxReturn -130.101 MetaTest/__unnamed_task__/MinReturn -156.358 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.62275 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 384000 __unnamed_task__/AverageDiscountedReturn -61.8576 __unnamed_task__/AverageReturn -144.795 __unnamed_task__/Iteration 7 __unnamed_task__/MaxReturn -122.64 __unnamed_task__/MinReturn -206.512 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.5804 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 20:40:26 | [maml_trainer] epoch #8 | Sampling for adapation and meta-testing... 2025-04-03 20:44:18 | [maml_trainer] epoch #8 | Finished meta-testing... 2025-04-03 20:44:18 | [maml_trainer] epoch #8 | Saving snapshot... 2025-04-03 20:44:39 | [maml_trainer] epoch #8 | Saved 2025-04-03 20:44:39 | [maml_trainer] epoch #8 | Time 14723.39 s 2025-04-03 20:44:39 | [maml_trainer] epoch #8 | EpochTime 1636.00 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -60.2078 Average/AverageReturn -140.792 Average/Iteration 8 Average/MaxReturn -123.458 Average/MinReturn -159.832 Average/NumEpisodes 120 Average/StdReturn 8.11926 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94711 GaussianMLPPolicy/KLAfter 0.00472086 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000102256 GaussianMLPPolicy/LossBefore 2.16564e-09 GaussianMLPPolicy/dLoss 0.000102258 Iteration 8 MetaTest/Average/AverageDiscountedReturn -138.268 MetaTest/Average/AverageReturn -138.268 MetaTest/Average/Iteration 8 MetaTest/Average/MaxReturn -130.562 MetaTest/Average/MinReturn -159.357 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.40614 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -138.268 MetaTest/__unnamed_task__/AverageReturn -138.268 MetaTest/__unnamed_task__/Iteration 8 MetaTest/__unnamed_task__/MaxReturn -130.562 MetaTest/__unnamed_task__/MinReturn -159.357 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.40614 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 432000 __unnamed_task__/AverageDiscountedReturn -60.2078 __unnamed_task__/AverageReturn -140.792 __unnamed_task__/Iteration 8 __unnamed_task__/MaxReturn -123.458 __unnamed_task__/MinReturn -159.832 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.11926 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 21:07:38 | [maml_trainer] epoch #9 | Sampling for adapation and meta-testing... 2025-04-03 21:11:35 | [maml_trainer] epoch #9 | Finished meta-testing... 2025-04-03 21:11:35 | [maml_trainer] epoch #9 | Saving snapshot... 2025-04-03 21:11:54 | [maml_trainer] epoch #9 | Saved 2025-04-03 21:11:54 | [maml_trainer] epoch #9 | Time 16358.88 s 2025-04-03 21:11:54 | [maml_trainer] epoch #9 | EpochTime 1635.49 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -59.3589 Average/AverageReturn -138.663 Average/Iteration 9 Average/MaxReturn -122.16 Average/MinReturn -168.294 Average/NumEpisodes 120 Average/StdReturn 8.32631 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94788 GaussianMLPPolicy/KLAfter 0.00520743 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.14686e-06 GaussianMLPPolicy/LossBefore 5.64257e-09 GaussianMLPPolicy/dLoss 5.1525e-06 Iteration 9 MetaTest/Average/AverageDiscountedReturn -136.915 MetaTest/Average/AverageReturn -136.915 MetaTest/Average/Iteration 9 MetaTest/Average/MaxReturn -122.67 MetaTest/Average/MinReturn -156.111 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.23241 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -136.915 MetaTest/__unnamed_task__/AverageReturn -136.915 MetaTest/__unnamed_task__/Iteration 9 MetaTest/__unnamed_task__/MaxReturn -122.67 MetaTest/__unnamed_task__/MinReturn -156.111 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.23241 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 480000 __unnamed_task__/AverageDiscountedReturn -59.3589 __unnamed_task__/AverageReturn -138.663 __unnamed_task__/Iteration 9 __unnamed_task__/MaxReturn -122.16 __unnamed_task__/MinReturn -168.294 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.32631 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 21:34:58 | [maml_trainer] epoch #10 | Sampling for adapation and meta-testing... 2025-04-03 21:38:36 | [maml_trainer] epoch #10 | Finished meta-testing... 2025-04-03 21:38:36 | [maml_trainer] epoch #10 | Saving snapshot... 2025-04-03 21:38:55 | [maml_trainer] epoch #10 | Saved 2025-04-03 21:38:55 | [maml_trainer] epoch #10 | Time 17979.21 s 2025-04-03 21:38:55 | [maml_trainer] epoch #10 | EpochTime 1620.33 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -59.5652 Average/AverageReturn -139.267 Average/Iteration 10 Average/MaxReturn -116.88 Average/MinReturn -160.964 Average/NumEpisodes 120 Average/StdReturn 8.29386 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94782 GaussianMLPPolicy/KLAfter 0.00495302 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000104325 GaussianMLPPolicy/LossBefore 1.6888e-09 GaussianMLPPolicy/dLoss 0.000104327 Iteration 10 MetaTest/Average/AverageDiscountedReturn -135.115 MetaTest/Average/AverageReturn -135.115 MetaTest/Average/Iteration 10 MetaTest/Average/MaxReturn -125.062 MetaTest/Average/MinReturn -146.583 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.29427 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -135.115 MetaTest/__unnamed_task__/AverageReturn -135.115 MetaTest/__unnamed_task__/Iteration 10 MetaTest/__unnamed_task__/MaxReturn -125.062 MetaTest/__unnamed_task__/MinReturn -146.583 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.29427 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 528000 __unnamed_task__/AverageDiscountedReturn -59.5652 __unnamed_task__/AverageReturn -139.267 __unnamed_task__/Iteration 10 __unnamed_task__/MaxReturn -116.88 __unnamed_task__/MinReturn -160.964 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.29386 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 22:00:41 | [maml_trainer] epoch #11 | Sampling for adapation and meta-testing... 2025-04-03 22:04:16 | [maml_trainer] epoch #11 | Finished meta-testing... 2025-04-03 22:04:16 | [maml_trainer] epoch #11 | Saving snapshot... 2025-04-03 22:04:35 | [maml_trainer] epoch #11 | Saved 2025-04-03 22:04:35 | [maml_trainer] epoch #11 | Time 19519.04 s 2025-04-03 22:04:35 | [maml_trainer] epoch #11 | EpochTime 1539.82 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -58.8037 Average/AverageReturn -136.933 Average/Iteration 11 Average/MaxReturn -123.062 Average/MinReturn -154.384 Average/NumEpisodes 120 Average/StdReturn 6.91497 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94898 GaussianMLPPolicy/KLAfter 0.00643462 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.26917e-05 GaussianMLPPolicy/LossBefore 5.98033e-09 GaussianMLPPolicy/dLoss 3.26977e-05 Iteration 11 MetaTest/Average/AverageDiscountedReturn -137.298 MetaTest/Average/AverageReturn -137.298 MetaTest/Average/Iteration 11 MetaTest/Average/MaxReturn -123.181 MetaTest/Average/MinReturn -151.064 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.15146 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -137.298 MetaTest/__unnamed_task__/AverageReturn -137.298 MetaTest/__unnamed_task__/Iteration 11 MetaTest/__unnamed_task__/MaxReturn -123.181 MetaTest/__unnamed_task__/MinReturn -151.064 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.15146 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 576000 __unnamed_task__/AverageDiscountedReturn -58.8037 __unnamed_task__/AverageReturn -136.933 __unnamed_task__/Iteration 11 __unnamed_task__/MaxReturn -123.062 __unnamed_task__/MinReturn -154.384 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.91497 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 22:27:43 | [maml_trainer] epoch #12 | Sampling for adapation and meta-testing... 2025-04-03 22:31:49 | [maml_trainer] epoch #12 | Finished meta-testing... 2025-04-03 22:31:49 | [maml_trainer] epoch #12 | Saving snapshot... 2025-04-03 22:32:10 | [maml_trainer] epoch #12 | Saved 2025-04-03 22:32:10 | [maml_trainer] epoch #12 | Time 21174.19 s 2025-04-03 22:32:10 | [maml_trainer] epoch #12 | EpochTime 1655.15 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -58.7409 Average/AverageReturn -136.808 Average/Iteration 12 Average/MaxReturn -118.86 Average/MinReturn -160.008 Average/NumEpisodes 120 Average/StdReturn 7.67521 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95082 GaussianMLPPolicy/KLAfter 0.00604509 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.11096e-05 GaussianMLPPolicy/LossBefore 7.17243e-09 GaussianMLPPolicy/dLoss 3.11167e-05 Iteration 12 MetaTest/Average/AverageDiscountedReturn -128.304 MetaTest/Average/AverageReturn -128.304 MetaTest/Average/Iteration 12 MetaTest/Average/MaxReturn -117.034 MetaTest/Average/MinReturn -154.988 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.77891 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -128.304 MetaTest/__unnamed_task__/AverageReturn -128.304 MetaTest/__unnamed_task__/Iteration 12 MetaTest/__unnamed_task__/MaxReturn -117.034 MetaTest/__unnamed_task__/MinReturn -154.988 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.77891 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 624000 __unnamed_task__/AverageDiscountedReturn -58.7409 __unnamed_task__/AverageReturn -136.808 __unnamed_task__/Iteration 12 __unnamed_task__/MaxReturn -118.86 __unnamed_task__/MinReturn -160.008 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.67521 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 22:54:49 | [maml_trainer] epoch #13 | Sampling for adapation and meta-testing... 2025-04-03 22:58:46 | [maml_trainer] epoch #13 | Finished meta-testing... 2025-04-03 22:58:46 | [maml_trainer] epoch #13 | Saving snapshot... 2025-04-03 22:59:06 | [maml_trainer] epoch #13 | Saved 2025-04-03 22:59:06 | [maml_trainer] epoch #13 | Time 22790.72 s 2025-04-03 22:59:06 | [maml_trainer] epoch #13 | EpochTime 1616.53 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -57.2712 Average/AverageReturn -132.688 Average/Iteration 13 Average/MaxReturn -110.178 Average/MinReturn -153.897 Average/NumEpisodes 120 Average/StdReturn 8.37591 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95336 GaussianMLPPolicy/KLAfter 0.00391486 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.95175e-05 GaussianMLPPolicy/LossBefore 4.37101e-10 GaussianMLPPolicy/dLoss 4.95179e-05 Iteration 13 MetaTest/Average/AverageDiscountedReturn -131.901 MetaTest/Average/AverageReturn -131.901 MetaTest/Average/Iteration 13 MetaTest/Average/MaxReturn -118.047 MetaTest/Average/MinReturn -150.287 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.05101 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -131.901 MetaTest/__unnamed_task__/AverageReturn -131.901 MetaTest/__unnamed_task__/Iteration 13 MetaTest/__unnamed_task__/MaxReturn -118.047 MetaTest/__unnamed_task__/MinReturn -150.287 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.05101 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 672000 __unnamed_task__/AverageDiscountedReturn -57.2712 __unnamed_task__/AverageReturn -132.688 __unnamed_task__/Iteration 13 __unnamed_task__/MaxReturn -110.178 __unnamed_task__/MinReturn -153.897 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.37591 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 23:22:25 | [maml_trainer] epoch #14 | Sampling for adapation and meta-testing... 2025-04-03 23:26:19 | [maml_trainer] epoch #14 | Finished meta-testing... 2025-04-03 23:26:19 | [maml_trainer] epoch #14 | Saving snapshot... 2025-04-03 23:26:40 | [maml_trainer] epoch #14 | Saved 2025-04-03 23:26:40 | [maml_trainer] epoch #14 | Time 24444.45 s 2025-04-03 23:26:40 | [maml_trainer] epoch #14 | EpochTime 1653.72 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -56.2572 Average/AverageReturn -129.545 Average/Iteration 14 Average/MaxReturn -112.896 Average/MinReturn -149.027 Average/NumEpisodes 120 Average/StdReturn 7.53097 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95491 GaussianMLPPolicy/KLAfter 0.0057979 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.56015e-05 GaussianMLPPolicy/LossBefore 5.86112e-09 GaussianMLPPolicy/dLoss 7.56073e-05 Iteration 14 MetaTest/Average/AverageDiscountedReturn -131.692 MetaTest/Average/AverageReturn -131.692 MetaTest/Average/Iteration 14 MetaTest/Average/MaxReturn -118.392 MetaTest/Average/MinReturn -148.562 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.77233 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -131.692 MetaTest/__unnamed_task__/AverageReturn -131.692 MetaTest/__unnamed_task__/Iteration 14 MetaTest/__unnamed_task__/MaxReturn -118.392 MetaTest/__unnamed_task__/MinReturn -148.562 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.77233 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 720000 __unnamed_task__/AverageDiscountedReturn -56.2572 __unnamed_task__/AverageReturn -129.545 __unnamed_task__/Iteration 14 __unnamed_task__/MaxReturn -112.896 __unnamed_task__/MinReturn -149.027 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.53097 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-03 23:50:32 | [maml_trainer] epoch #15 | Sampling for adapation and meta-testing... 2025-04-03 23:54:29 | [maml_trainer] epoch #15 | Finished meta-testing... 2025-04-03 23:54:29 | [maml_trainer] epoch #15 | Saving snapshot... 2025-04-03 23:54:49 | [maml_trainer] epoch #15 | Saved 2025-04-03 23:54:49 | [maml_trainer] epoch #15 | Time 26133.78 s 2025-04-03 23:54:49 | [maml_trainer] epoch #15 | EpochTime 1689.32 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -56.5967 Average/AverageReturn -130.133 Average/Iteration 15 Average/MaxReturn -112.862 Average/MinReturn -146.542 Average/NumEpisodes 120 Average/StdReturn 7.637 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95664 GaussianMLPPolicy/KLAfter 0.00825869 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.98916e-05 GaussianMLPPolicy/LossBefore 1.15236e-08 GaussianMLPPolicy/dLoss 5.99031e-05 Iteration 15 MetaTest/Average/AverageDiscountedReturn -126.612 MetaTest/Average/AverageReturn -126.612 MetaTest/Average/Iteration 15 MetaTest/Average/MaxReturn -116.913 MetaTest/Average/MinReturn -137.11 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.37274 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -126.612 MetaTest/__unnamed_task__/AverageReturn -126.612 MetaTest/__unnamed_task__/Iteration 15 MetaTest/__unnamed_task__/MaxReturn -116.913 MetaTest/__unnamed_task__/MinReturn -137.11 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.37274 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 768000 __unnamed_task__/AverageDiscountedReturn -56.5967 __unnamed_task__/AverageReturn -130.133 __unnamed_task__/Iteration 15 __unnamed_task__/MaxReturn -112.862 __unnamed_task__/MinReturn -146.542 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.637 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-04 00:18:22 | [maml_trainer] epoch #16 | Sampling for adapation and meta-testing... 2025-04-04 00:22:18 | [maml_trainer] epoch #16 | Finished meta-testing... 2025-04-04 00:22:18 | [maml_trainer] epoch #16 | Saving snapshot... 2025-04-04 00:22:39 | [maml_trainer] epoch #16 | Saved 2025-04-04 00:22:39 | [maml_trainer] epoch #16 | Time 27803.28 s 2025-04-04 00:22:39 | [maml_trainer] epoch #16 | EpochTime 1669.50 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -55.1648 Average/AverageReturn -125.952 Average/Iteration 16 Average/MaxReturn -105.804 Average/MinReturn -143.543 Average/NumEpisodes 120 Average/StdReturn 8.06455 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95812 GaussianMLPPolicy/KLAfter 0.011384 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.5789e-06 GaussianMLPPolicy/LossBefore -5.28495e-09 GaussianMLPPolicy/dLoss 9.57362e-06 Iteration 16 MetaTest/Average/AverageDiscountedReturn -124.015 MetaTest/Average/AverageReturn -124.015 MetaTest/Average/Iteration 16 MetaTest/Average/MaxReturn -116.438 MetaTest/Average/MinReturn -143.03 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.23648 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -124.015 MetaTest/__unnamed_task__/AverageReturn -124.015 MetaTest/__unnamed_task__/Iteration 16 MetaTest/__unnamed_task__/MaxReturn -116.438 MetaTest/__unnamed_task__/MinReturn -143.03 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.23648 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 816000 __unnamed_task__/AverageDiscountedReturn -55.1648 __unnamed_task__/AverageReturn -125.952 __unnamed_task__/Iteration 16 __unnamed_task__/MaxReturn -105.804 __unnamed_task__/MinReturn -143.543 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.06455 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-04 00:46:15 | [maml_trainer] epoch #17 | Sampling for adapation and meta-testing... 2025-04-04 00:50:13 | [maml_trainer] epoch #17 | Finished meta-testing... 2025-04-04 00:50:13 | [maml_trainer] epoch #17 | Saving snapshot... 2025-04-04 00:50:33 | [maml_trainer] epoch #17 | Saved 2025-04-04 00:50:33 | [maml_trainer] epoch #17 | Time 29477.62 s 2025-04-04 00:50:33 | [maml_trainer] epoch #17 | EpochTime 1674.34 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -54.7048 Average/AverageReturn -124.192 Average/Iteration 17 Average/MaxReturn -102.592 Average/MinReturn -147.264 Average/NumEpisodes 120 Average/StdReturn 9.56627 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96001 GaussianMLPPolicy/KLAfter 0.0113182 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.70992e-05 GaussianMLPPolicy/LossBefore -8.72215e-09 GaussianMLPPolicy/dLoss 4.70905e-05 Iteration 17 MetaTest/Average/AverageDiscountedReturn -118.769 MetaTest/Average/AverageReturn -118.769 MetaTest/Average/Iteration 17 MetaTest/Average/MaxReturn -105.953 MetaTest/Average/MinReturn -137.455 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.61785 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -118.769 MetaTest/__unnamed_task__/AverageReturn -118.769 MetaTest/__unnamed_task__/Iteration 17 MetaTest/__unnamed_task__/MaxReturn -105.953 MetaTest/__unnamed_task__/MinReturn -137.455 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.61785 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 864000 __unnamed_task__/AverageDiscountedReturn -54.7048 __unnamed_task__/AverageReturn -124.192 __unnamed_task__/Iteration 17 __unnamed_task__/MaxReturn -102.592 __unnamed_task__/MinReturn -147.264 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.56627 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-04 01:14:12 | [maml_trainer] epoch #18 | Sampling for adapation and meta-testing... 2025-04-04 01:18:07 | [maml_trainer] epoch #18 | Finished meta-testing... 2025-04-04 01:18:07 | [maml_trainer] epoch #18 | Saving snapshot... 2025-04-04 01:18:28 | [maml_trainer] epoch #18 | Saved 2025-04-04 01:18:28 | [maml_trainer] epoch #18 | Time 31152.13 s 2025-04-04 01:18:28 | [maml_trainer] epoch #18 | EpochTime 1674.50 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -53.4122 Average/AverageReturn -120.279 Average/Iteration 18 Average/MaxReturn -100.466 Average/MinReturn -145.292 Average/NumEpisodes 120 Average/StdReturn 8.5785 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95999 GaussianMLPPolicy/KLAfter 0.0129157 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.02627e-05 GaussianMLPPolicy/LossBefore 4.39088e-09 GaussianMLPPolicy/dLoss 5.02671e-05 Iteration 18 MetaTest/Average/AverageDiscountedReturn -116.231 MetaTest/Average/AverageReturn -116.231 MetaTest/Average/Iteration 18 MetaTest/Average/MaxReturn -106.749 MetaTest/Average/MinReturn -128.354 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.88189 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -116.231 MetaTest/__unnamed_task__/AverageReturn -116.231 MetaTest/__unnamed_task__/Iteration 18 MetaTest/__unnamed_task__/MaxReturn -106.749 MetaTest/__unnamed_task__/MinReturn -128.354 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.88189 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 912000 __unnamed_task__/AverageDiscountedReturn -53.4122 __unnamed_task__/AverageReturn -120.279 __unnamed_task__/Iteration 18 __unnamed_task__/MaxReturn -100.466 __unnamed_task__/MinReturn -145.292 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.5785 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-04 01:40:39 | [maml_trainer] epoch #19 | Sampling for adapation and meta-testing... 2025-04-04 01:44:23 | [maml_trainer] epoch #19 | Finished meta-testing... 2025-04-04 01:44:23 | [maml_trainer] epoch #19 | Saving snapshot... 2025-04-04 01:44:43 | [maml_trainer] epoch #19 | Saved 2025-04-04 01:44:43 | [maml_trainer] epoch #19 | Time 32727.24 s 2025-04-04 01:44:43 | [maml_trainer] epoch #19 | EpochTime 1575.11 s ------------------------------------------------- ---------------- Average/AverageDiscountedReturn -51.3934 Average/AverageReturn -114.451 Average/Iteration 19 Average/MaxReturn -96.3453 Average/MinReturn -137.922 Average/NumEpisodes 120 Average/StdReturn 8.79287 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96059 GaussianMLPPolicy/KLAfter 0.0120949 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.37757e-06 GaussianMLPPolicy/LossBefore 1.47025e-09 GaussianMLPPolicy/dLoss 5.37904e-06 Iteration 19 MetaTest/Average/AverageDiscountedReturn -112.474 MetaTest/Average/AverageReturn -112.474 MetaTest/Average/Iteration 19 MetaTest/Average/MaxReturn -101.272 MetaTest/Average/MinReturn -133.748 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.9087 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -112.474 MetaTest/__unnamed_task__/AverageReturn -112.474 MetaTest/__unnamed_task__/Iteration 19 MetaTest/__unnamed_task__/MaxReturn -101.272 MetaTest/__unnamed_task__/MinReturn -133.748 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.9087 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 960000 __unnamed_task__/AverageDiscountedReturn -51.3934 __unnamed_task__/AverageReturn -114.451 __unnamed_task__/Iteration 19 __unnamed_task__/MaxReturn -96.3453 __unnamed_task__/MinReturn -137.922 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.79287 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ---------------- 2025-04-04 02:06:55 | [maml_trainer] epoch #20 | Sampling for adapation and meta-testing... 2025-04-04 02:10:36 | [maml_trainer] epoch #20 | Finished meta-testing... 2025-04-04 02:10:36 | [maml_trainer] epoch #20 | Saving snapshot... 2025-04-04 02:10:56 | [maml_trainer] epoch #20 | Saved 2025-04-04 02:10:56 | [maml_trainer] epoch #20 | Time 34300.06 s 2025-04-04 02:10:56 | [maml_trainer] epoch #20 | EpochTime 1572.81 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -50.0141 Average/AverageReturn -110.339 Average/Iteration 20 Average/MaxReturn -91.891 Average/MinReturn -133.976 Average/NumEpisodes 120 Average/StdReturn 7.75056 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96143 GaussianMLPPolicy/KLAfter 0.00985724 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.86122e-06 GaussianMLPPolicy/LossBefore 1.16825e-08 GaussianMLPPolicy/dLoss 2.8729e-06 Iteration 20 MetaTest/Average/AverageDiscountedReturn -107.424 MetaTest/Average/AverageReturn -107.424 MetaTest/Average/Iteration 20 MetaTest/Average/MaxReturn -93.3441 MetaTest/Average/MinReturn -124.559 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.45655 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -107.424 MetaTest/__unnamed_task__/AverageReturn -107.424 MetaTest/__unnamed_task__/Iteration 20 MetaTest/__unnamed_task__/MaxReturn -93.3441 MetaTest/__unnamed_task__/MinReturn -124.559 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.45655 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.008e+06 __unnamed_task__/AverageDiscountedReturn -50.0141 __unnamed_task__/AverageReturn -110.339 __unnamed_task__/Iteration 20 __unnamed_task__/MaxReturn -91.891 __unnamed_task__/MinReturn -133.976 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.75056 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 02:33:06 | [maml_trainer] epoch #21 | Sampling for adapation and meta-testing... 2025-04-04 02:36:47 | [maml_trainer] epoch #21 | Finished meta-testing... 2025-04-04 02:36:47 | [maml_trainer] epoch #21 | Saving snapshot... 2025-04-04 02:37:06 | [maml_trainer] epoch #21 | Saved 2025-04-04 02:37:06 | [maml_trainer] epoch #21 | Time 35870.69 s 2025-04-04 02:37:06 | [maml_trainer] epoch #21 | EpochTime 1570.63 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -49.3972 Average/AverageReturn -107.91 Average/Iteration 21 Average/MaxReturn -89.7106 Average/MinReturn -130.812 Average/NumEpisodes 120 Average/StdReturn 8.06753 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96162 GaussianMLPPolicy/KLAfter 0.00856512 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.11969e-05 GaussianMLPPolicy/LossBefore -2.28484e-09 GaussianMLPPolicy/dLoss 9.11947e-05 Iteration 21 MetaTest/Average/AverageDiscountedReturn -101.914 MetaTest/Average/AverageReturn -101.914 MetaTest/Average/Iteration 21 MetaTest/Average/MaxReturn -88.898 MetaTest/Average/MinReturn -115.002 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.0148 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.914 MetaTest/__unnamed_task__/AverageReturn -101.914 MetaTest/__unnamed_task__/Iteration 21 MetaTest/__unnamed_task__/MaxReturn -88.898 MetaTest/__unnamed_task__/MinReturn -115.002 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.0148 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.056e+06 __unnamed_task__/AverageDiscountedReturn -49.3972 __unnamed_task__/AverageReturn -107.91 __unnamed_task__/Iteration 21 __unnamed_task__/MaxReturn -89.7106 __unnamed_task__/MinReturn -130.812 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.06753 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 02:58:50 | [maml_trainer] epoch #22 | Sampling for adapation and meta-testing... 2025-04-04 03:02:30 | [maml_trainer] epoch #22 | Finished meta-testing... 2025-04-04 03:02:30 | [maml_trainer] epoch #22 | Saving snapshot... 2025-04-04 03:02:49 | [maml_trainer] epoch #22 | Saved 2025-04-04 03:02:49 | [maml_trainer] epoch #22 | Time 37413.40 s 2025-04-04 03:02:49 | [maml_trainer] epoch #22 | EpochTime 1542.71 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -48.0902 Average/AverageReturn -104.152 Average/Iteration 22 Average/MaxReturn -80.4207 Average/MinReturn -125.246 Average/NumEpisodes 120 Average/StdReturn 8.5268 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96169 GaussianMLPPolicy/KLAfter 0.00901658 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.62834e-07 GaussianMLPPolicy/LossBefore -1.29938e-08 GaussianMLPPolicy/dLoss -3.75828e-07 Iteration 22 MetaTest/Average/AverageDiscountedReturn -103.354 MetaTest/Average/AverageReturn -103.354 MetaTest/Average/Iteration 22 MetaTest/Average/MaxReturn -92.2119 MetaTest/Average/MinReturn -115.833 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.73109 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -103.354 MetaTest/__unnamed_task__/AverageReturn -103.354 MetaTest/__unnamed_task__/Iteration 22 MetaTest/__unnamed_task__/MaxReturn -92.2119 MetaTest/__unnamed_task__/MinReturn -115.833 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.73109 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.104e+06 __unnamed_task__/AverageDiscountedReturn -48.0902 __unnamed_task__/AverageReturn -104.152 __unnamed_task__/Iteration 22 __unnamed_task__/MaxReturn -80.4207 __unnamed_task__/MinReturn -125.246 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.5268 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 03:24:48 | [maml_trainer] epoch #23 | Sampling for adapation and meta-testing... 2025-04-04 03:28:29 | [maml_trainer] epoch #23 | Finished meta-testing... 2025-04-04 03:28:29 | [maml_trainer] epoch #23 | Saving snapshot... 2025-04-04 03:28:48 | [maml_trainer] epoch #23 | Saved 2025-04-04 03:28:48 | [maml_trainer] epoch #23 | Time 38972.25 s 2025-04-04 03:28:48 | [maml_trainer] epoch #23 | EpochTime 1558.85 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -47.6611 Average/AverageReturn -102.507 Average/Iteration 23 Average/MaxReturn -86.4267 Average/MinReturn -125.076 Average/NumEpisodes 120 Average/StdReturn 8.14207 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96063 GaussianMLPPolicy/KLAfter 0.00978113 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.88531e-05 GaussianMLPPolicy/LossBefore 3.69549e-09 GaussianMLPPolicy/dLoss 9.88568e-05 Iteration 23 MetaTest/Average/AverageDiscountedReturn -99.5005 MetaTest/Average/AverageReturn -99.5005 MetaTest/Average/Iteration 23 MetaTest/Average/MaxReturn -85.3564 MetaTest/Average/MinReturn -120.559 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.94608 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -99.5005 MetaTest/__unnamed_task__/AverageReturn -99.5005 MetaTest/__unnamed_task__/Iteration 23 MetaTest/__unnamed_task__/MaxReturn -85.3564 MetaTest/__unnamed_task__/MinReturn -120.559 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.94608 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.152e+06 __unnamed_task__/AverageDiscountedReturn -47.6611 __unnamed_task__/AverageReturn -102.507 __unnamed_task__/Iteration 23 __unnamed_task__/MaxReturn -86.4267 __unnamed_task__/MinReturn -125.076 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.14207 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 03:50:27 | [maml_trainer] epoch #24 | Sampling for adapation and meta-testing... 2025-04-04 03:54:06 | [maml_trainer] epoch #24 | Finished meta-testing... 2025-04-04 03:54:06 | [maml_trainer] epoch #24 | Saving snapshot... 2025-04-04 03:54:25 | [maml_trainer] epoch #24 | Saved 2025-04-04 03:54:25 | [maml_trainer] epoch #24 | Time 40509.37 s 2025-04-04 03:54:25 | [maml_trainer] epoch #24 | EpochTime 1537.12 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -46.3213 Average/AverageReturn -98.9785 Average/Iteration 24 Average/MaxReturn -75 Average/MinReturn -123.25 Average/NumEpisodes 120 Average/StdReturn 8.16332 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95844 GaussianMLPPolicy/KLAfter 0.00689651 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.58248e-05 GaussianMLPPolicy/LossBefore -4.76837e-09 GaussianMLPPolicy/dLoss 6.582e-05 Iteration 24 MetaTest/Average/AverageDiscountedReturn -97.6783 MetaTest/Average/AverageReturn -97.6783 MetaTest/Average/Iteration 24 MetaTest/Average/MaxReturn -83.1939 MetaTest/Average/MinReturn -113.379 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.24557 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.6783 MetaTest/__unnamed_task__/AverageReturn -97.6783 MetaTest/__unnamed_task__/Iteration 24 MetaTest/__unnamed_task__/MaxReturn -83.1939 MetaTest/__unnamed_task__/MinReturn -113.379 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.24557 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2e+06 __unnamed_task__/AverageDiscountedReturn -46.3213 __unnamed_task__/AverageReturn -98.9785 __unnamed_task__/Iteration 24 __unnamed_task__/MaxReturn -75 __unnamed_task__/MinReturn -123.25 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.16332 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 04:16:18 | [maml_trainer] epoch #25 | Sampling for adapation and meta-testing... 2025-04-04 04:19:57 | [maml_trainer] epoch #25 | Finished meta-testing... 2025-04-04 04:19:57 | [maml_trainer] epoch #25 | Saving snapshot... 2025-04-04 04:20:17 | [maml_trainer] epoch #25 | Saved 2025-04-04 04:20:17 | [maml_trainer] epoch #25 | Time 42061.66 s 2025-04-04 04:20:17 | [maml_trainer] epoch #25 | EpochTime 1552.29 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -45.6381 Average/AverageReturn -97.0585 Average/Iteration 25 Average/MaxReturn -81.381 Average/MinReturn -117.359 Average/NumEpisodes 120 Average/StdReturn 7.45153 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95759 GaussianMLPPolicy/KLAfter 0.00591015 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.26537e-05 GaussianMLPPolicy/LossBefore 1.19209e-10 GaussianMLPPolicy/dLoss 7.26538e-05 Iteration 25 MetaTest/Average/AverageDiscountedReturn -94.4554 MetaTest/Average/AverageReturn -94.4554 MetaTest/Average/Iteration 25 MetaTest/Average/MaxReturn -79.8159 MetaTest/Average/MinReturn -111.48 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.54998 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.4554 MetaTest/__unnamed_task__/AverageReturn -94.4554 MetaTest/__unnamed_task__/Iteration 25 MetaTest/__unnamed_task__/MaxReturn -79.8159 MetaTest/__unnamed_task__/MinReturn -111.48 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.54998 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.248e+06 __unnamed_task__/AverageDiscountedReturn -45.6381 __unnamed_task__/AverageReturn -97.0585 __unnamed_task__/Iteration 25 __unnamed_task__/MaxReturn -81.381 __unnamed_task__/MinReturn -117.359 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.45153 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 04:42:11 | [maml_trainer] epoch #26 | Sampling for adapation and meta-testing... 2025-04-04 04:45:52 | [maml_trainer] epoch #26 | Finished meta-testing... 2025-04-04 04:45:52 | [maml_trainer] epoch #26 | Saving snapshot... 2025-04-04 04:46:11 | [maml_trainer] epoch #26 | Saved 2025-04-04 04:46:11 | [maml_trainer] epoch #26 | Time 43615.76 s 2025-04-04 04:46:11 | [maml_trainer] epoch #26 | EpochTime 1554.09 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -44.2009 Average/AverageReturn -93.2869 Average/Iteration 26 Average/MaxReturn -76.9273 Average/MinReturn -110.985 Average/NumEpisodes 120 Average/StdReturn 7.73727 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95664 GaussianMLPPolicy/KLAfter 0.00882355 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.1777e-05 GaussianMLPPolicy/LossBefore 4.80811e-09 GaussianMLPPolicy/dLoss 9.17818e-05 Iteration 26 MetaTest/Average/AverageDiscountedReturn -92.4372 MetaTest/Average/AverageReturn -92.4372 MetaTest/Average/Iteration 26 MetaTest/Average/MaxReturn -77.5005 MetaTest/Average/MinReturn -104.185 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.55209 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.4372 MetaTest/__unnamed_task__/AverageReturn -92.4372 MetaTest/__unnamed_task__/Iteration 26 MetaTest/__unnamed_task__/MaxReturn -77.5005 MetaTest/__unnamed_task__/MinReturn -104.185 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.55209 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.296e+06 __unnamed_task__/AverageDiscountedReturn -44.2009 __unnamed_task__/AverageReturn -93.2869 __unnamed_task__/Iteration 26 __unnamed_task__/MaxReturn -76.9273 __unnamed_task__/MinReturn -110.985 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.73727 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 05:08:20 | [maml_trainer] epoch #27 | Sampling for adapation and meta-testing... 2025-04-04 05:12:00 | [maml_trainer] epoch #27 | Finished meta-testing... 2025-04-04 05:12:00 | [maml_trainer] epoch #27 | Saving snapshot... 2025-04-04 05:12:20 | [maml_trainer] epoch #27 | Saved 2025-04-04 05:12:20 | [maml_trainer] epoch #27 | Time 45184.23 s 2025-04-04 05:12:20 | [maml_trainer] epoch #27 | EpochTime 1568.47 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -44.1012 Average/AverageReturn -92.8233 Average/Iteration 27 Average/MaxReturn -68.4292 Average/MinReturn -115.748 Average/NumEpisodes 120 Average/StdReturn 8.0963 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95656 GaussianMLPPolicy/KLAfter 0.00802317 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.77399e-05 GaussianMLPPolicy/LossBefore 9.29832e-09 GaussianMLPPolicy/dLoss -2.77306e-05 Iteration 27 MetaTest/Average/AverageDiscountedReturn -92.0104 MetaTest/Average/AverageReturn -92.0104 MetaTest/Average/Iteration 27 MetaTest/Average/MaxReturn -73.732 MetaTest/Average/MinReturn -105.975 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.55389 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.0104 MetaTest/__unnamed_task__/AverageReturn -92.0104 MetaTest/__unnamed_task__/Iteration 27 MetaTest/__unnamed_task__/MaxReturn -73.732 MetaTest/__unnamed_task__/MinReturn -105.975 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.55389 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.344e+06 __unnamed_task__/AverageDiscountedReturn -44.1012 __unnamed_task__/AverageReturn -92.8233 __unnamed_task__/Iteration 27 __unnamed_task__/MaxReturn -68.4292 __unnamed_task__/MinReturn -115.748 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.0963 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 05:34:22 | [maml_trainer] epoch #28 | Sampling for adapation and meta-testing... 2025-04-04 05:38:01 | [maml_trainer] epoch #28 | Finished meta-testing... 2025-04-04 05:38:01 | [maml_trainer] epoch #28 | Saving snapshot... 2025-04-04 05:38:20 | [maml_trainer] epoch #28 | Saved 2025-04-04 05:38:20 | [maml_trainer] epoch #28 | Time 46744.28 s 2025-04-04 05:38:20 | [maml_trainer] epoch #28 | EpochTime 1560.05 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -42.6438 Average/AverageReturn -89.2431 Average/Iteration 28 Average/MaxReturn -67.3316 Average/MinReturn -109.917 Average/NumEpisodes 120 Average/StdReturn 8.56009 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95648 GaussianMLPPolicy/KLAfter 0.00765783 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.50815e-05 GaussianMLPPolicy/LossBefore 2.98023e-09 GaussianMLPPolicy/dLoss 5.50845e-05 Iteration 28 MetaTest/Average/AverageDiscountedReturn -89.1382 MetaTest/Average/AverageReturn -89.1382 MetaTest/Average/Iteration 28 MetaTest/Average/MaxReturn -78.5266 MetaTest/Average/MinReturn -99.7064 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.78137 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -89.1382 MetaTest/__unnamed_task__/AverageReturn -89.1382 MetaTest/__unnamed_task__/Iteration 28 MetaTest/__unnamed_task__/MaxReturn -78.5266 MetaTest/__unnamed_task__/MinReturn -99.7064 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.78137 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.392e+06 __unnamed_task__/AverageDiscountedReturn -42.6438 __unnamed_task__/AverageReturn -89.2431 __unnamed_task__/Iteration 28 __unnamed_task__/MaxReturn -67.3316 __unnamed_task__/MinReturn -109.917 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.56009 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 06:00:13 | [maml_trainer] epoch #29 | Sampling for adapation and meta-testing... 2025-04-04 06:03:55 | [maml_trainer] epoch #29 | Finished meta-testing... 2025-04-04 06:03:55 | [maml_trainer] epoch #29 | Saving snapshot... 2025-04-04 06:04:15 | [maml_trainer] epoch #29 | Saved 2025-04-04 06:04:15 | [maml_trainer] epoch #29 | Time 48299.58 s 2025-04-04 06:04:15 | [maml_trainer] epoch #29 | EpochTime 1555.30 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -41.9964 Average/AverageReturn -87.1991 Average/Iteration 29 Average/MaxReturn -66.646 Average/MinReturn -114.347 Average/NumEpisodes 120 Average/StdReturn 8.71402 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95682 GaussianMLPPolicy/KLAfter 0.00871886 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000174274 GaussianMLPPolicy/LossBefore 6.75519e-10 GaussianMLPPolicy/dLoss 0.000174275 Iteration 29 MetaTest/Average/AverageDiscountedReturn -83.9129 MetaTest/Average/AverageReturn -83.9129 MetaTest/Average/Iteration 29 MetaTest/Average/MaxReturn -59.8647 MetaTest/Average/MinReturn -106.127 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.79928 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -83.9129 MetaTest/__unnamed_task__/AverageReturn -83.9129 MetaTest/__unnamed_task__/Iteration 29 MetaTest/__unnamed_task__/MaxReturn -59.8647 MetaTest/__unnamed_task__/MinReturn -106.127 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.79928 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.44e+06 __unnamed_task__/AverageDiscountedReturn -41.9964 __unnamed_task__/AverageReturn -87.1991 __unnamed_task__/Iteration 29 __unnamed_task__/MaxReturn -66.646 __unnamed_task__/MinReturn -114.347 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.71402 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 06:26:45 | [maml_trainer] epoch #30 | Sampling for adapation and meta-testing... 2025-04-04 06:30:30 | [maml_trainer] epoch #30 | Finished meta-testing... 2025-04-04 06:30:30 | [maml_trainer] epoch #30 | Saving snapshot... 2025-04-04 06:30:49 | [maml_trainer] epoch #30 | Saved 2025-04-04 06:30:49 | [maml_trainer] epoch #30 | Time 49893.91 s 2025-04-04 06:30:49 | [maml_trainer] epoch #30 | EpochTime 1594.33 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -41.3333 Average/AverageReturn -85.2132 Average/Iteration 30 Average/MaxReturn -64.4476 Average/MinReturn -105.606 Average/NumEpisodes 120 Average/StdReturn 8.9988 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95642 GaussianMLPPolicy/KLAfter 0.00406935 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.62731e-05 GaussianMLPPolicy/LossBefore 2.00272e-08 GaussianMLPPolicy/dLoss 6.62931e-05 Iteration 30 MetaTest/Average/AverageDiscountedReturn -84.3896 MetaTest/Average/AverageReturn -84.3896 MetaTest/Average/Iteration 30 MetaTest/Average/MaxReturn -69.9504 MetaTest/Average/MinReturn -107.841 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.6824 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -84.3896 MetaTest/__unnamed_task__/AverageReturn -84.3896 MetaTest/__unnamed_task__/Iteration 30 MetaTest/__unnamed_task__/MaxReturn -69.9504 MetaTest/__unnamed_task__/MinReturn -107.841 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.6824 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.488e+06 __unnamed_task__/AverageDiscountedReturn -41.3333 __unnamed_task__/AverageReturn -85.2132 __unnamed_task__/Iteration 30 __unnamed_task__/MaxReturn -64.4476 __unnamed_task__/MinReturn -105.606 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.9988 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 06:53:11 | [maml_trainer] epoch #31 | Sampling for adapation and meta-testing... 2025-04-04 06:56:55 | [maml_trainer] epoch #31 | Finished meta-testing... 2025-04-04 06:56:55 | [maml_trainer] epoch #31 | Saving snapshot... 2025-04-04 06:57:14 | [maml_trainer] epoch #31 | Saved 2025-04-04 06:57:14 | [maml_trainer] epoch #31 | Time 51478.91 s 2025-04-04 06:57:14 | [maml_trainer] epoch #31 | EpochTime 1585.00 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -40.2717 Average/AverageReturn -82.7033 Average/Iteration 31 Average/MaxReturn -64.6415 Average/MinReturn -103.064 Average/NumEpisodes 120 Average/StdReturn 7.61241 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95682 GaussianMLPPolicy/KLAfter 0.00656332 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.86726e-05 GaussianMLPPolicy/LossBefore 4.92732e-09 GaussianMLPPolicy/dLoss 4.86775e-05 Iteration 31 MetaTest/Average/AverageDiscountedReturn -84.5883 MetaTest/Average/AverageReturn -84.5883 MetaTest/Average/Iteration 31 MetaTest/Average/MaxReturn -71.4005 MetaTest/Average/MinReturn -101.525 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.922 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -84.5883 MetaTest/__unnamed_task__/AverageReturn -84.5883 MetaTest/__unnamed_task__/Iteration 31 MetaTest/__unnamed_task__/MaxReturn -71.4005 MetaTest/__unnamed_task__/MinReturn -101.525 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.922 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.536e+06 __unnamed_task__/AverageDiscountedReturn -40.2717 __unnamed_task__/AverageReturn -82.7033 __unnamed_task__/Iteration 31 __unnamed_task__/MaxReturn -64.6415 __unnamed_task__/MinReturn -103.064 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.61241 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 07:19:47 | [maml_trainer] epoch #32 | Sampling for adapation and meta-testing... 2025-04-04 07:23:34 | [maml_trainer] epoch #32 | Finished meta-testing... 2025-04-04 07:23:34 | [maml_trainer] epoch #32 | Saving snapshot... 2025-04-04 07:23:53 | [maml_trainer] epoch #32 | Saved 2025-04-04 07:23:53 | [maml_trainer] epoch #32 | Time 53077.55 s 2025-04-04 07:23:53 | [maml_trainer] epoch #32 | EpochTime 1598.63 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -39.9499 Average/AverageReturn -81.6193 Average/Iteration 32 Average/MaxReturn -62.7162 Average/MinReturn -102.906 Average/NumEpisodes 120 Average/StdReturn 8.34765 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95716 GaussianMLPPolicy/KLAfter 0.00322622 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.41827e-05 GaussianMLPPolicy/LossBefore -3.21865e-09 GaussianMLPPolicy/dLoss 6.41795e-05 Iteration 32 MetaTest/Average/AverageDiscountedReturn -79.8778 MetaTest/Average/AverageReturn -79.8778 MetaTest/Average/Iteration 32 MetaTest/Average/MaxReturn -62.1972 MetaTest/Average/MinReturn -102.935 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.5407 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -79.8778 MetaTest/__unnamed_task__/AverageReturn -79.8778 MetaTest/__unnamed_task__/Iteration 32 MetaTest/__unnamed_task__/MaxReturn -62.1972 MetaTest/__unnamed_task__/MinReturn -102.935 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.5407 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.584e+06 __unnamed_task__/AverageDiscountedReturn -39.9499 __unnamed_task__/AverageReturn -81.6193 __unnamed_task__/Iteration 32 __unnamed_task__/MaxReturn -62.7162 __unnamed_task__/MinReturn -102.906 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.34765 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 07:46:13 | [maml_trainer] epoch #33 | Sampling for adapation and meta-testing... 2025-04-04 07:50:01 | [maml_trainer] epoch #33 | Finished meta-testing... 2025-04-04 07:50:01 | [maml_trainer] epoch #33 | Saving snapshot... 2025-04-04 07:50:20 | [maml_trainer] epoch #33 | Saved 2025-04-04 07:50:20 | [maml_trainer] epoch #33 | Time 54664.72 s 2025-04-04 07:50:20 | [maml_trainer] epoch #33 | EpochTime 1587.16 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -39.2009 Average/AverageReturn -80.0689 Average/Iteration 33 Average/MaxReturn -54.9197 Average/MinReturn -107.625 Average/NumEpisodes 120 Average/StdReturn 9.51811 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95612 GaussianMLPPolicy/KLAfter 0.00538882 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.85316e-05 GaussianMLPPolicy/LossBefore 6.35783e-09 GaussianMLPPolicy/dLoss 7.8538e-05 Iteration 33 MetaTest/Average/AverageDiscountedReturn -78.429 MetaTest/Average/AverageReturn -78.429 MetaTest/Average/Iteration 33 MetaTest/Average/MaxReturn -58.9209 MetaTest/Average/MinReturn -90.7865 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.2176 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -78.429 MetaTest/__unnamed_task__/AverageReturn -78.429 MetaTest/__unnamed_task__/Iteration 33 MetaTest/__unnamed_task__/MaxReturn -58.9209 MetaTest/__unnamed_task__/MinReturn -90.7865 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.2176 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.632e+06 __unnamed_task__/AverageDiscountedReturn -39.2009 __unnamed_task__/AverageReturn -80.0689 __unnamed_task__/Iteration 33 __unnamed_task__/MaxReturn -54.9197 __unnamed_task__/MinReturn -107.625 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.51811 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 08:12:46 | [maml_trainer] epoch #34 | Sampling for adapation and meta-testing... 2025-04-04 08:16:33 | [maml_trainer] epoch #34 | Finished meta-testing... 2025-04-04 08:16:33 | [maml_trainer] epoch #34 | Saving snapshot... 2025-04-04 08:16:53 | [maml_trainer] epoch #34 | Saved 2025-04-04 08:16:53 | [maml_trainer] epoch #34 | Time 56256.98 s 2025-04-04 08:16:53 | [maml_trainer] epoch #34 | EpochTime 1592.26 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -38.6068 Average/AverageReturn -78.6658 Average/Iteration 34 Average/MaxReturn -59.3901 Average/MinReturn -105.74 Average/NumEpisodes 120 Average/StdReturn 9.40517 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95645 GaussianMLPPolicy/KLAfter 0.00682468 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.89031e-05 GaussianMLPPolicy/LossBefore 4.80811e-09 GaussianMLPPolicy/dLoss -5.88982e-05 Iteration 34 MetaTest/Average/AverageDiscountedReturn -76.903 MetaTest/Average/AverageReturn -76.903 MetaTest/Average/Iteration 34 MetaTest/Average/MaxReturn -61.7765 MetaTest/Average/MinReturn -99.8302 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.13914 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -76.903 MetaTest/__unnamed_task__/AverageReturn -76.903 MetaTest/__unnamed_task__/Iteration 34 MetaTest/__unnamed_task__/MaxReturn -61.7765 MetaTest/__unnamed_task__/MinReturn -99.8302 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.13914 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.68e+06 __unnamed_task__/AverageDiscountedReturn -38.6068 __unnamed_task__/AverageReturn -78.6658 __unnamed_task__/Iteration 34 __unnamed_task__/MaxReturn -59.3901 __unnamed_task__/MinReturn -105.74 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.40517 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 08:39:50 | [maml_trainer] epoch #35 | Sampling for adapation and meta-testing... 2025-04-04 08:43:40 | [maml_trainer] epoch #35 | Finished meta-testing... 2025-04-04 08:43:40 | [maml_trainer] epoch #35 | Saving snapshot... 2025-04-04 08:44:00 | [maml_trainer] epoch #35 | Saved 2025-04-04 08:44:00 | [maml_trainer] epoch #35 | Time 57884.40 s 2025-04-04 08:44:00 | [maml_trainer] epoch #35 | EpochTime 1627.41 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -38.063 Average/AverageReturn -77.1499 Average/Iteration 35 Average/MaxReturn -59.0097 Average/MinReturn -97.9927 Average/NumEpisodes 120 Average/StdReturn 8.21979 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95703 GaussianMLPPolicy/KLAfter 0.00651828 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.70069e-05 GaussianMLPPolicy/LossBefore 9.17912e-09 GaussianMLPPolicy/dLoss 2.70161e-05 Iteration 35 MetaTest/Average/AverageDiscountedReturn -79.0295 MetaTest/Average/AverageReturn -79.0295 MetaTest/Average/Iteration 35 MetaTest/Average/MaxReturn -58.6314 MetaTest/Average/MinReturn -97.3986 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.47268 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -79.0295 MetaTest/__unnamed_task__/AverageReturn -79.0295 MetaTest/__unnamed_task__/Iteration 35 MetaTest/__unnamed_task__/MaxReturn -58.6314 MetaTest/__unnamed_task__/MinReturn -97.3986 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.47268 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.728e+06 __unnamed_task__/AverageDiscountedReturn -38.063 __unnamed_task__/AverageReturn -77.1499 __unnamed_task__/Iteration 35 __unnamed_task__/MaxReturn -59.0097 __unnamed_task__/MinReturn -97.9927 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.21979 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-04 09:07:10 | [maml_trainer] epoch #36 | Sampling for adapation and meta-testing... 2025-04-04 09:11:00 | [maml_trainer] epoch #36 | Finished meta-testing... 2025-04-04 09:11:00 | [maml_trainer] epoch #36 | Saving snapshot... 2025-04-04 09:11:19 | [maml_trainer] epoch #36 | Saved 2025-04-04 09:11:19 | [maml_trainer] epoch #36 | Time 59523.46 s 2025-04-04 09:11:19 | [maml_trainer] epoch #36 | EpochTime 1639.06 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -37.4035 Average/AverageReturn -75.1504 Average/Iteration 36 Average/MaxReturn -55.0235 Average/MinReturn -97.1303 Average/NumEpisodes 120 Average/StdReturn 8.49267 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.9578 GaussianMLPPolicy/KLAfter 0.00653371 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000135147 GaussianMLPPolicy/LossBefore -5.08626e-09 GaussianMLPPolicy/dLoss 0.000135142 Iteration 36 MetaTest/Average/AverageDiscountedReturn -74.6331 MetaTest/Average/AverageReturn -74.6331 MetaTest/Average/Iteration 36 MetaTest/Average/MaxReturn -59.3095 MetaTest/Average/MinReturn -91.572 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.4263 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -74.6331 MetaTest/__unnamed_task__/AverageReturn -74.6331 MetaTest/__unnamed_task__/Iteration 36 MetaTest/__unnamed_task__/MaxReturn -59.3095 MetaTest/__unnamed_task__/MinReturn -91.572 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.4263 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.776e+06 __unnamed_task__/AverageDiscountedReturn -37.4035 __unnamed_task__/AverageReturn -75.1504 __unnamed_task__/Iteration 36 __unnamed_task__/MaxReturn -55.0235 __unnamed_task__/MinReturn -97.1303 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.49267 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-04 09:34:13 | [maml_trainer] epoch #37 | Sampling for adapation and meta-testing... 2025-04-04 09:38:00 | [maml_trainer] epoch #37 | Finished meta-testing... 2025-04-04 09:38:00 | [maml_trainer] epoch #37 | Saving snapshot... 2025-04-04 09:38:19 | [maml_trainer] epoch #37 | Saved 2025-04-04 09:38:19 | [maml_trainer] epoch #37 | Time 61143.74 s 2025-04-04 09:38:19 | [maml_trainer] epoch #37 | EpochTime 1620.28 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -36.713 Average/AverageReturn -74.3926 Average/Iteration 37 Average/MaxReturn -57.8871 Average/MinReturn -99.0695 Average/NumEpisodes 120 Average/StdReturn 8.21299 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95776 GaussianMLPPolicy/KLAfter 0.00383585 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000131952 GaussianMLPPolicy/LossBefore -2.74181e-09 GaussianMLPPolicy/dLoss -0.000131955 Iteration 37 MetaTest/Average/AverageDiscountedReturn -76.7123 MetaTest/Average/AverageReturn -76.7123 MetaTest/Average/Iteration 37 MetaTest/Average/MaxReturn -63.0083 MetaTest/Average/MinReturn -94.2631 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.47775 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -76.7123 MetaTest/__unnamed_task__/AverageReturn -76.7123 MetaTest/__unnamed_task__/Iteration 37 MetaTest/__unnamed_task__/MaxReturn -63.0083 MetaTest/__unnamed_task__/MinReturn -94.2631 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.47775 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.824e+06 __unnamed_task__/AverageDiscountedReturn -36.713 __unnamed_task__/AverageReturn -74.3926 __unnamed_task__/Iteration 37 __unnamed_task__/MaxReturn -57.8871 __unnamed_task__/MinReturn -99.0695 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.21299 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-04 10:01:08 | [maml_trainer] epoch #38 | Sampling for adapation and meta-testing... 2025-04-04 10:04:56 | [maml_trainer] epoch #38 | Finished meta-testing... 2025-04-04 10:04:56 | [maml_trainer] epoch #38 | Saving snapshot... 2025-04-04 10:05:16 | [maml_trainer] epoch #38 | Saved 2025-04-04 10:05:16 | [maml_trainer] epoch #38 | Time 62760.53 s 2025-04-04 10:05:16 | [maml_trainer] epoch #38 | EpochTime 1616.78 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -36.5022 Average/AverageReturn -73.4496 Average/Iteration 38 Average/MaxReturn -58.1056 Average/MinReturn -96.0145 Average/NumEpisodes 120 Average/StdReturn 7.77252 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95539 GaussianMLPPolicy/KLAfter 0.00389101 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.53233e-05 GaussianMLPPolicy/LossBefore 2.1855e-09 GaussianMLPPolicy/dLoss -2.53211e-05 Iteration 38 MetaTest/Average/AverageDiscountedReturn -71.0726 MetaTest/Average/AverageReturn -71.0726 MetaTest/Average/Iteration 38 MetaTest/Average/MaxReturn -56.8097 MetaTest/Average/MinReturn -86.2047 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.54505 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -71.0726 MetaTest/__unnamed_task__/AverageReturn -71.0726 MetaTest/__unnamed_task__/Iteration 38 MetaTest/__unnamed_task__/MaxReturn -56.8097 MetaTest/__unnamed_task__/MinReturn -86.2047 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.54505 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.872e+06 __unnamed_task__/AverageDiscountedReturn -36.5022 __unnamed_task__/AverageReturn -73.4496 __unnamed_task__/Iteration 38 __unnamed_task__/MaxReturn -58.1056 __unnamed_task__/MinReturn -96.0145 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.77252 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-04 10:28:22 | [maml_trainer] epoch #39 | Sampling for adapation and meta-testing... 2025-04-04 10:32:10 | [maml_trainer] epoch #39 | Finished meta-testing... 2025-04-04 10:32:10 | [maml_trainer] epoch #39 | Saving snapshot... 2025-04-04 10:32:29 | [maml_trainer] epoch #39 | Saved 2025-04-04 10:32:29 | [maml_trainer] epoch #39 | Time 64393.83 s 2025-04-04 10:32:29 | [maml_trainer] epoch #39 | EpochTime 1633.30 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -36.934 Average/AverageReturn -74.8312 Average/Iteration 39 Average/MaxReturn -54.712 Average/MinReturn -100.583 Average/NumEpisodes 120 Average/StdReturn 9.56084 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95321 GaussianMLPPolicy/KLAfter 0.00183818 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.02884e-05 GaussianMLPPolicy/LossBefore 9.93411e-10 GaussianMLPPolicy/dLoss 2.02894e-05 Iteration 39 MetaTest/Average/AverageDiscountedReturn -77.3482 MetaTest/Average/AverageReturn -77.3482 MetaTest/Average/Iteration 39 MetaTest/Average/MaxReturn -61.032 MetaTest/Average/MinReturn -94.896 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.5234 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -77.3482 MetaTest/__unnamed_task__/AverageReturn -77.3482 MetaTest/__unnamed_task__/Iteration 39 MetaTest/__unnamed_task__/MaxReturn -61.032 MetaTest/__unnamed_task__/MinReturn -94.896 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.5234 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.92e+06 __unnamed_task__/AverageDiscountedReturn -36.934 __unnamed_task__/AverageReturn -74.8312 __unnamed_task__/Iteration 39 __unnamed_task__/MaxReturn -54.712 __unnamed_task__/MinReturn -100.583 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.56084 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 10:55:37 | [maml_trainer] epoch #40 | Sampling for adapation and meta-testing... 2025-04-04 10:59:28 | [maml_trainer] epoch #40 | Finished meta-testing... 2025-04-04 10:59:28 | [maml_trainer] epoch #40 | Saving snapshot... 2025-04-04 10:59:48 | [maml_trainer] epoch #40 | Saved 2025-04-04 10:59:48 | [maml_trainer] epoch #40 | Time 66032.27 s 2025-04-04 10:59:48 | [maml_trainer] epoch #40 | EpochTime 1638.43 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -37.0681 Average/AverageReturn -75.2762 Average/Iteration 40 Average/MaxReturn -57.8028 Average/MinReturn -105.55 Average/NumEpisodes 120 Average/StdReturn 9.24602 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95169 GaussianMLPPolicy/KLAfter 0.00170484 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.5121e-05 GaussianMLPPolicy/LossBefore 2.30471e-09 GaussianMLPPolicy/dLoss 3.51233e-05 Iteration 40 MetaTest/Average/AverageDiscountedReturn -80.1382 MetaTest/Average/AverageReturn -80.1382 MetaTest/Average/Iteration 40 MetaTest/Average/MaxReturn -62.6461 MetaTest/Average/MinReturn -104.53 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.80883 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -80.1382 MetaTest/__unnamed_task__/AverageReturn -80.1382 MetaTest/__unnamed_task__/Iteration 40 MetaTest/__unnamed_task__/MaxReturn -62.6461 MetaTest/__unnamed_task__/MinReturn -104.53 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.80883 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.968e+06 __unnamed_task__/AverageDiscountedReturn -37.0681 __unnamed_task__/AverageReturn -75.2762 __unnamed_task__/Iteration 40 __unnamed_task__/MaxReturn -57.8028 __unnamed_task__/MinReturn -105.55 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.24602 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 11:22:49 | [maml_trainer] epoch #41 | Sampling for adapation and meta-testing... 2025-04-04 11:26:39 | [maml_trainer] epoch #41 | Finished meta-testing... 2025-04-04 11:26:39 | [maml_trainer] epoch #41 | Saving snapshot... 2025-04-04 11:26:59 | [maml_trainer] epoch #41 | Saved 2025-04-04 11:26:59 | [maml_trainer] epoch #41 | Time 67662.99 s 2025-04-04 11:26:59 | [maml_trainer] epoch #41 | EpochTime 1630.72 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -36.4298 Average/AverageReturn -74.6512 Average/Iteration 41 Average/MaxReturn -53.6053 Average/MinReturn -103.544 Average/NumEpisodes 120 Average/StdReturn 10.7455 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95177 GaussianMLPPolicy/KLAfter 0.00128986 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.05066e-05 GaussianMLPPolicy/LossBefore 1.86761e-09 GaussianMLPPolicy/dLoss -3.05047e-05 Iteration 41 MetaTest/Average/AverageDiscountedReturn -70.1681 MetaTest/Average/AverageReturn -70.1681 MetaTest/Average/Iteration 41 MetaTest/Average/MaxReturn -56.0195 MetaTest/Average/MinReturn -106.836 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.3204 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -70.1681 MetaTest/__unnamed_task__/AverageReturn -70.1681 MetaTest/__unnamed_task__/Iteration 41 MetaTest/__unnamed_task__/MaxReturn -56.0195 MetaTest/__unnamed_task__/MinReturn -106.836 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.3204 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.016e+06 __unnamed_task__/AverageDiscountedReturn -36.4298 __unnamed_task__/AverageReturn -74.6512 __unnamed_task__/Iteration 41 __unnamed_task__/MaxReturn -53.6053 __unnamed_task__/MinReturn -103.544 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.7455 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 11:50:01 | [maml_trainer] epoch #42 | Sampling for adapation and meta-testing... 2025-04-04 11:53:52 | [maml_trainer] epoch #42 | Finished meta-testing... 2025-04-04 11:53:52 | [maml_trainer] epoch #42 | Saving snapshot... 2025-04-04 11:54:12 | [maml_trainer] epoch #42 | Saved 2025-04-04 11:54:12 | [maml_trainer] epoch #42 | Time 69296.49 s 2025-04-04 11:54:12 | [maml_trainer] epoch #42 | EpochTime 1633.50 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -36.696 Average/AverageReturn -74.9699 Average/Iteration 42 Average/MaxReturn -55.5582 Average/MinReturn -98.5279 Average/NumEpisodes 120 Average/StdReturn 9.66568 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95059 GaussianMLPPolicy/KLAfter 0.00171648 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.80605e-06 GaussianMLPPolicy/LossBefore -1.64906e-08 GaussianMLPPolicy/dLoss -5.82254e-06 Iteration 42 MetaTest/Average/AverageDiscountedReturn -73.799 MetaTest/Average/AverageReturn -73.799 MetaTest/Average/Iteration 42 MetaTest/Average/MaxReturn -58.7446 MetaTest/Average/MinReturn -105.728 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.904 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -73.799 MetaTest/__unnamed_task__/AverageReturn -73.799 MetaTest/__unnamed_task__/Iteration 42 MetaTest/__unnamed_task__/MaxReturn -58.7446 MetaTest/__unnamed_task__/MinReturn -105.728 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.904 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.064e+06 __unnamed_task__/AverageDiscountedReturn -36.696 __unnamed_task__/AverageReturn -74.9699 __unnamed_task__/Iteration 42 __unnamed_task__/MaxReturn -55.5582 __unnamed_task__/MinReturn -98.5279 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.66568 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 12:17:18 | [maml_trainer] epoch #43 | Sampling for adapation and meta-testing... 2025-04-04 12:21:11 | [maml_trainer] epoch #43 | Finished meta-testing... 2025-04-04 12:21:11 | [maml_trainer] epoch #43 | Saving snapshot... 2025-04-04 12:21:31 | [maml_trainer] epoch #43 | Saved 2025-04-04 12:21:31 | [maml_trainer] epoch #43 | Time 70935.57 s 2025-04-04 12:21:31 | [maml_trainer] epoch #43 | EpochTime 1639.08 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -35.9761 Average/AverageReturn -73.1482 Average/Iteration 43 Average/MaxReturn -56.8896 Average/MinReturn -97.5414 Average/NumEpisodes 120 Average/StdReturn 9.60402 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95003 GaussianMLPPolicy/KLAfter 0.00193456 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.47054e-06 GaussianMLPPolicy/LossBefore 9.45727e-09 GaussianMLPPolicy/dLoss 3.48e-06 Iteration 43 MetaTest/Average/AverageDiscountedReturn -70.6185 MetaTest/Average/AverageReturn -70.6185 MetaTest/Average/Iteration 43 MetaTest/Average/MaxReturn -53.923 MetaTest/Average/MinReturn -93.0957 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.6587 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -70.6185 MetaTest/__unnamed_task__/AverageReturn -70.6185 MetaTest/__unnamed_task__/Iteration 43 MetaTest/__unnamed_task__/MaxReturn -53.923 MetaTest/__unnamed_task__/MinReturn -93.0957 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.6587 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.112e+06 __unnamed_task__/AverageDiscountedReturn -35.9761 __unnamed_task__/AverageReturn -73.1482 __unnamed_task__/Iteration 43 __unnamed_task__/MaxReturn -56.8896 __unnamed_task__/MinReturn -97.5414 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.60402 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-04 12:44:29 | [maml_trainer] epoch #44 | Sampling for adapation and meta-testing... 2025-04-04 12:48:22 | [maml_trainer] epoch #44 | Finished meta-testing... 2025-04-04 12:48:22 | [maml_trainer] epoch #44 | Saving snapshot... 2025-04-04 12:48:42 | [maml_trainer] epoch #44 | Saved 2025-04-04 12:48:42 | [maml_trainer] epoch #44 | Time 72566.12 s 2025-04-04 12:48:42 | [maml_trainer] epoch #44 | EpochTime 1630.54 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -36.2323 Average/AverageReturn -73.7171 Average/Iteration 44 Average/MaxReturn -53.7007 Average/MinReturn -98.203 Average/NumEpisodes 120 Average/StdReturn 9.89788 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94971 GaussianMLPPolicy/KLAfter 0.00241179 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.47952e-06 GaussianMLPPolicy/LossBefore 1.07288e-08 GaussianMLPPolicy/dLoss -3.46879e-06 Iteration 44 MetaTest/Average/AverageDiscountedReturn -71.4342 MetaTest/Average/AverageReturn -71.4342 MetaTest/Average/Iteration 44 MetaTest/Average/MaxReturn -59.2715 MetaTest/Average/MinReturn -101.065 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.8327 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -71.4342 MetaTest/__unnamed_task__/AverageReturn -71.4342 MetaTest/__unnamed_task__/Iteration 44 MetaTest/__unnamed_task__/MaxReturn -59.2715 MetaTest/__unnamed_task__/MinReturn -101.065 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.8327 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.16e+06 __unnamed_task__/AverageDiscountedReturn -36.2323 __unnamed_task__/AverageReturn -73.7171 __unnamed_task__/Iteration 44 __unnamed_task__/MaxReturn -53.7007 __unnamed_task__/MinReturn -98.203 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.89788 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 13:12:10 | [maml_trainer] epoch #45 | Sampling for adapation and meta-testing... 2025-04-04 13:16:00 | [maml_trainer] epoch #45 | Finished meta-testing... 2025-04-04 13:16:00 | [maml_trainer] epoch #45 | Saving snapshot... 2025-04-04 13:16:20 | [maml_trainer] epoch #45 | Saved 2025-04-04 13:16:20 | [maml_trainer] epoch #45 | Time 74224.00 s 2025-04-04 13:16:20 | [maml_trainer] epoch #45 | EpochTime 1657.88 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -36.079 Average/AverageReturn -73.4313 Average/Iteration 45 Average/MaxReturn -54.8981 Average/MinReturn -103.529 Average/NumEpisodes 120 Average/StdReturn 10.3505 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94852 GaussianMLPPolicy/KLAfter 0.00277888 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.34211e-05 GaussianMLPPolicy/LossBefore 6.35783e-10 GaussianMLPPolicy/dLoss -5.34204e-05 Iteration 45 MetaTest/Average/AverageDiscountedReturn -72.3886 MetaTest/Average/AverageReturn -72.3886 MetaTest/Average/Iteration 45 MetaTest/Average/MaxReturn -58.1897 MetaTest/Average/MinReturn -90.204 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.73098 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -72.3886 MetaTest/__unnamed_task__/AverageReturn -72.3886 MetaTest/__unnamed_task__/Iteration 45 MetaTest/__unnamed_task__/MaxReturn -58.1897 MetaTest/__unnamed_task__/MinReturn -90.204 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.73098 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.208e+06 __unnamed_task__/AverageDiscountedReturn -36.079 __unnamed_task__/AverageReturn -73.4313 __unnamed_task__/Iteration 45 __unnamed_task__/MaxReturn -54.8981 __unnamed_task__/MinReturn -103.529 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.3505 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 13:39:57 | [maml_trainer] epoch #46 | Sampling for adapation and meta-testing... 2025-04-04 13:43:50 | [maml_trainer] epoch #46 | Finished meta-testing... 2025-04-04 13:43:50 | [maml_trainer] epoch #46 | Saving snapshot... 2025-04-04 13:44:09 | [maml_trainer] epoch #46 | Saved 2025-04-04 13:44:09 | [maml_trainer] epoch #46 | Time 75893.91 s 2025-04-04 13:44:09 | [maml_trainer] epoch #46 | EpochTime 1669.91 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -35.5808 Average/AverageReturn -72.3932 Average/Iteration 46 Average/MaxReturn -56.2675 Average/MinReturn -113.119 Average/NumEpisodes 120 Average/StdReturn 10.415 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94718 GaussianMLPPolicy/KLAfter 0.00133236 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.77545e-05 GaussianMLPPolicy/LossBefore -1.56164e-08 GaussianMLPPolicy/dLoss 3.77389e-05 Iteration 46 MetaTest/Average/AverageDiscountedReturn -75.7235 MetaTest/Average/AverageReturn -75.7235 MetaTest/Average/Iteration 46 MetaTest/Average/MaxReturn -56.0302 MetaTest/Average/MinReturn -101.206 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.1313 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -75.7235 MetaTest/__unnamed_task__/AverageReturn -75.7235 MetaTest/__unnamed_task__/Iteration 46 MetaTest/__unnamed_task__/MaxReturn -56.0302 MetaTest/__unnamed_task__/MinReturn -101.206 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.1313 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.256e+06 __unnamed_task__/AverageDiscountedReturn -35.5808 __unnamed_task__/AverageReturn -72.3932 __unnamed_task__/Iteration 46 __unnamed_task__/MaxReturn -56.2675 __unnamed_task__/MinReturn -113.119 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.415 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 14:07:18 | [maml_trainer] epoch #47 | Sampling for adapation and meta-testing... 2025-04-04 14:11:11 | [maml_trainer] epoch #47 | Finished meta-testing... 2025-04-04 14:11:11 | [maml_trainer] epoch #47 | Saving snapshot... 2025-04-04 14:11:31 | [maml_trainer] epoch #47 | Saved 2025-04-04 14:11:31 | [maml_trainer] epoch #47 | Time 77535.32 s 2025-04-04 14:11:31 | [maml_trainer] epoch #47 | EpochTime 1641.41 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -36.2716 Average/AverageReturn -74.8553 Average/Iteration 47 Average/MaxReturn -56.9895 Average/MinReturn -107.34 Average/NumEpisodes 120 Average/StdReturn 11.3824 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.9457 GaussianMLPPolicy/KLAfter 0.00150252 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.88057e-05 GaussianMLPPolicy/LossBefore -5.40415e-09 GaussianMLPPolicy/dLoss -9.88111e-05 Iteration 47 MetaTest/Average/AverageDiscountedReturn -71.2412 MetaTest/Average/AverageReturn -71.2412 MetaTest/Average/Iteration 47 MetaTest/Average/MaxReturn -52.5486 MetaTest/Average/MinReturn -94.137 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.3096 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -71.2412 MetaTest/__unnamed_task__/AverageReturn -71.2412 MetaTest/__unnamed_task__/Iteration 47 MetaTest/__unnamed_task__/MaxReturn -52.5486 MetaTest/__unnamed_task__/MinReturn -94.137 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.3096 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.304e+06 __unnamed_task__/AverageDiscountedReturn -36.2716 __unnamed_task__/AverageReturn -74.8553 __unnamed_task__/Iteration 47 __unnamed_task__/MaxReturn -56.9895 __unnamed_task__/MinReturn -107.34 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.3824 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 14:34:49 | [maml_trainer] epoch #48 | Sampling for adapation and meta-testing... 2025-04-04 14:38:41 | [maml_trainer] epoch #48 | Finished meta-testing... 2025-04-04 14:38:41 | [maml_trainer] epoch #48 | Saving snapshot... 2025-04-04 14:39:00 | [maml_trainer] epoch #48 | Saved 2025-04-04 14:39:00 | [maml_trainer] epoch #48 | Time 79184.78 s 2025-04-04 14:39:00 | [maml_trainer] epoch #48 | EpochTime 1649.45 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -35.8446 Average/AverageReturn -73.7913 Average/Iteration 48 Average/MaxReturn -53.4425 Average/MinReturn -99.0771 Average/NumEpisodes 120 Average/StdReturn 10.5379 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94423 GaussianMLPPolicy/KLAfter 0.00155773 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.22221e-05 GaussianMLPPolicy/LossBefore 4.92732e-09 GaussianMLPPolicy/dLoss -2.22172e-05 Iteration 48 MetaTest/Average/AverageDiscountedReturn -69.1756 MetaTest/Average/AverageReturn -69.1756 MetaTest/Average/Iteration 48 MetaTest/Average/MaxReturn -52.7117 MetaTest/Average/MinReturn -98.2236 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.5162 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -69.1756 MetaTest/__unnamed_task__/AverageReturn -69.1756 MetaTest/__unnamed_task__/Iteration 48 MetaTest/__unnamed_task__/MaxReturn -52.7117 MetaTest/__unnamed_task__/MinReturn -98.2236 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.5162 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.352e+06 __unnamed_task__/AverageDiscountedReturn -35.8446 __unnamed_task__/AverageReturn -73.7913 __unnamed_task__/Iteration 48 __unnamed_task__/MaxReturn -53.4425 __unnamed_task__/MinReturn -99.0771 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.5379 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-04 15:02:04 | [maml_trainer] epoch #49 | Sampling for adapation and meta-testing... 2025-04-04 15:05:58 | [maml_trainer] epoch #49 | Finished meta-testing... 2025-04-04 15:05:58 | [maml_trainer] epoch #49 | Saving snapshot... 2025-04-04 15:06:18 | [maml_trainer] epoch #49 | Saved 2025-04-04 15:06:18 | [maml_trainer] epoch #49 | Time 80822.73 s 2025-04-04 15:06:18 | [maml_trainer] epoch #49 | EpochTime 1637.95 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -35.7876 Average/AverageReturn -73.1591 Average/Iteration 49 Average/MaxReturn -56.6736 Average/MinReturn -103.059 Average/NumEpisodes 120 Average/StdReturn 10.5127 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94541 GaussianMLPPolicy/KLAfter 0.00207737 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.96533e-05 GaussianMLPPolicy/LossBefore -3.85443e-09 GaussianMLPPolicy/dLoss 3.96495e-05 Iteration 49 MetaTest/Average/AverageDiscountedReturn -73.6875 MetaTest/Average/AverageReturn -73.6875 MetaTest/Average/Iteration 49 MetaTest/Average/MaxReturn -60.243 MetaTest/Average/MinReturn -95.0189 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.66312 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -73.6875 MetaTest/__unnamed_task__/AverageReturn -73.6875 MetaTest/__unnamed_task__/Iteration 49 MetaTest/__unnamed_task__/MaxReturn -60.243 MetaTest/__unnamed_task__/MinReturn -95.0189 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.66312 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.4e+06 __unnamed_task__/AverageDiscountedReturn -35.7876 __unnamed_task__/AverageReturn -73.1591 __unnamed_task__/Iteration 49 __unnamed_task__/MaxReturn -56.6736 __unnamed_task__/MinReturn -103.059 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.5127 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 15:29:47 | [maml_trainer] epoch #50 | Sampling for adapation and meta-testing... 2025-04-04 15:33:41 | [maml_trainer] epoch #50 | Finished meta-testing... 2025-04-04 15:33:41 | [maml_trainer] epoch #50 | Saving snapshot... 2025-04-04 15:34:01 | [maml_trainer] epoch #50 | Saved 2025-04-04 15:34:01 | [maml_trainer] epoch #50 | Time 82485.94 s 2025-04-04 15:34:01 | [maml_trainer] epoch #50 | EpochTime 1663.20 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -36.0038 Average/AverageReturn -74.0011 Average/Iteration 50 Average/MaxReturn -54.3492 Average/MinReturn -95.4378 Average/NumEpisodes 120 Average/StdReturn 10.149 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94679 GaussianMLPPolicy/KLAfter 0.00362502 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.94505e-05 GaussianMLPPolicy/LossBefore -2.22524e-09 GaussianMLPPolicy/dLoss 9.94482e-05 Iteration 50 MetaTest/Average/AverageDiscountedReturn -69.5808 MetaTest/Average/AverageReturn -69.5808 MetaTest/Average/Iteration 50 MetaTest/Average/MaxReturn -53.5694 MetaTest/Average/MinReturn -85.6434 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.16393 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -69.5808 MetaTest/__unnamed_task__/AverageReturn -69.5808 MetaTest/__unnamed_task__/Iteration 50 MetaTest/__unnamed_task__/MaxReturn -53.5694 MetaTest/__unnamed_task__/MinReturn -85.6434 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.16393 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.448e+06 __unnamed_task__/AverageDiscountedReturn -36.0038 __unnamed_task__/AverageReturn -74.0011 __unnamed_task__/Iteration 50 __unnamed_task__/MaxReturn -54.3492 __unnamed_task__/MinReturn -95.4378 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.149 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-04 15:57:35 | [maml_trainer] epoch #51 | Sampling for adapation and meta-testing... 2025-04-04 16:01:29 | [maml_trainer] epoch #51 | Finished meta-testing... 2025-04-04 16:01:29 | [maml_trainer] epoch #51 | Saving snapshot... 2025-04-04 16:01:49 | [maml_trainer] epoch #51 | Saved 2025-04-04 16:01:49 | [maml_trainer] epoch #51 | Time 84153.30 s 2025-04-04 16:01:49 | [maml_trainer] epoch #51 | EpochTime 1667.35 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -35.6681 Average/AverageReturn -72.4079 Average/Iteration 51 Average/MaxReturn -52.4892 Average/MinReturn -99.8819 Average/NumEpisodes 120 Average/StdReturn 10.329 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94924 GaussianMLPPolicy/KLAfter 0.00425464 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.52394e-05 GaussianMLPPolicy/LossBefore 1.27554e-08 GaussianMLPPolicy/dLoss 8.52522e-05 Iteration 51 MetaTest/Average/AverageDiscountedReturn -73.0213 MetaTest/Average/AverageReturn -73.0213 MetaTest/Average/Iteration 51 MetaTest/Average/MaxReturn -57.0488 MetaTest/Average/MinReturn -94.0957 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.1165 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -73.0213 MetaTest/__unnamed_task__/AverageReturn -73.0213 MetaTest/__unnamed_task__/Iteration 51 MetaTest/__unnamed_task__/MaxReturn -57.0488 MetaTest/__unnamed_task__/MinReturn -94.0957 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.1165 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.496e+06 __unnamed_task__/AverageDiscountedReturn -35.6681 __unnamed_task__/AverageReturn -72.4079 __unnamed_task__/Iteration 51 __unnamed_task__/MaxReturn -52.4892 __unnamed_task__/MinReturn -99.8819 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.329 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-04 16:24:58 | [maml_trainer] epoch #52 | Sampling for adapation and meta-testing... 2025-04-04 16:28:50 | [maml_trainer] epoch #52 | Finished meta-testing... 2025-04-04 16:28:50 | [maml_trainer] epoch #52 | Saving snapshot... 2025-04-04 16:29:11 | [maml_trainer] epoch #52 | Saved 2025-04-04 16:29:11 | [maml_trainer] epoch #52 | Time 85795.00 s 2025-04-04 16:29:11 | [maml_trainer] epoch #52 | EpochTime 1641.70 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -35.2794 Average/AverageReturn -72.0024 Average/Iteration 52 Average/MaxReturn -52.1485 Average/MinReturn -100.378 Average/NumEpisodes 120 Average/StdReturn 11.1225 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95205 GaussianMLPPolicy/KLAfter 0.00437394 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.21149e-05 GaussianMLPPolicy/LossBefore -1.00136e-08 GaussianMLPPolicy/dLoss 2.21049e-05 Iteration 52 MetaTest/Average/AverageDiscountedReturn -71.6818 MetaTest/Average/AverageReturn -71.6818 MetaTest/Average/Iteration 52 MetaTest/Average/MaxReturn -55.5237 MetaTest/Average/MinReturn -85.7311 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.19347 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -71.6818 MetaTest/__unnamed_task__/AverageReturn -71.6818 MetaTest/__unnamed_task__/Iteration 52 MetaTest/__unnamed_task__/MaxReturn -55.5237 MetaTest/__unnamed_task__/MinReturn -85.7311 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.19347 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.544e+06 __unnamed_task__/AverageDiscountedReturn -35.2794 __unnamed_task__/AverageReturn -72.0024 __unnamed_task__/Iteration 52 __unnamed_task__/MaxReturn -52.1485 __unnamed_task__/MinReturn -100.378 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.1225 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 16:52:36 | [maml_trainer] epoch #53 | Sampling for adapation and meta-testing... 2025-04-04 16:56:30 | [maml_trainer] epoch #53 | Finished meta-testing... 2025-04-04 16:56:30 | [maml_trainer] epoch #53 | Saving snapshot... 2025-04-04 16:56:50 | [maml_trainer] epoch #53 | Saved 2025-04-04 16:56:50 | [maml_trainer] epoch #53 | Time 87454.58 s 2025-04-04 16:56:50 | [maml_trainer] epoch #53 | EpochTime 1659.57 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -34.6968 Average/AverageReturn -70.2331 Average/Iteration 53 Average/MaxReturn -50.5958 Average/MinReturn -101.527 Average/NumEpisodes 120 Average/StdReturn 10.907 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95642 GaussianMLPPolicy/KLAfter 0.00761887 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.00017468 GaussianMLPPolicy/LossBefore -7.98702e-09 GaussianMLPPolicy/dLoss 0.000174672 Iteration 53 MetaTest/Average/AverageDiscountedReturn -72.1521 MetaTest/Average/AverageReturn -72.1521 MetaTest/Average/Iteration 53 MetaTest/Average/MaxReturn -55.2811 MetaTest/Average/MinReturn -100.468 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.2806 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -72.1521 MetaTest/__unnamed_task__/AverageReturn -72.1521 MetaTest/__unnamed_task__/Iteration 53 MetaTest/__unnamed_task__/MaxReturn -55.2811 MetaTest/__unnamed_task__/MinReturn -100.468 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.2806 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.592e+06 __unnamed_task__/AverageDiscountedReturn -34.6968 __unnamed_task__/AverageReturn -70.2331 __unnamed_task__/Iteration 53 __unnamed_task__/MaxReturn -50.5958 __unnamed_task__/MinReturn -101.527 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.907 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 17:20:19 | [maml_trainer] epoch #54 | Sampling for adapation and meta-testing... 2025-04-04 17:24:12 | [maml_trainer] epoch #54 | Finished meta-testing... 2025-04-04 17:24:12 | [maml_trainer] epoch #54 | Saving snapshot... 2025-04-04 17:24:31 | [maml_trainer] epoch #54 | Saved 2025-04-04 17:24:31 | [maml_trainer] epoch #54 | Time 89115.96 s 2025-04-04 17:24:31 | [maml_trainer] epoch #54 | EpochTime 1661.37 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -35.1745 Average/AverageReturn -71.45 Average/Iteration 54 Average/MaxReturn -53.9973 Average/MinReturn -108.566 Average/NumEpisodes 120 Average/StdReturn 11.175 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96083 GaussianMLPPolicy/KLAfter 0.00769316 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.92302e-05 GaussianMLPPolicy/LossBefore 8.0665e-09 GaussianMLPPolicy/dLoss -3.92221e-05 Iteration 54 MetaTest/Average/AverageDiscountedReturn -77.3461 MetaTest/Average/AverageReturn -77.3461 MetaTest/Average/Iteration 54 MetaTest/Average/MaxReturn -59.8536 MetaTest/Average/MinReturn -87.9344 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.50901 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -77.3461 MetaTest/__unnamed_task__/AverageReturn -77.3461 MetaTest/__unnamed_task__/Iteration 54 MetaTest/__unnamed_task__/MaxReturn -59.8536 MetaTest/__unnamed_task__/MinReturn -87.9344 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.50901 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.64e+06 __unnamed_task__/AverageDiscountedReturn -35.1745 __unnamed_task__/AverageReturn -71.45 __unnamed_task__/Iteration 54 __unnamed_task__/MaxReturn -53.9973 __unnamed_task__/MinReturn -108.566 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.175 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 17:47:42 | [maml_trainer] epoch #55 | Sampling for adapation and meta-testing... 2025-04-04 17:51:35 | [maml_trainer] epoch #55 | Finished meta-testing... 2025-04-04 17:51:35 | [maml_trainer] epoch #55 | Saving snapshot... 2025-04-04 17:51:54 | [maml_trainer] epoch #55 | Saved 2025-04-04 17:51:54 | [maml_trainer] epoch #55 | Time 90758.88 s 2025-04-04 17:51:54 | [maml_trainer] epoch #55 | EpochTime 1642.92 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -34.2941 Average/AverageReturn -68.4049 Average/Iteration 55 Average/MaxReturn -50.3214 Average/MinReturn -99.4283 Average/NumEpisodes 120 Average/StdReturn 10.4176 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96561 GaussianMLPPolicy/KLAfter 0.00579663 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000196719 GaussianMLPPolicy/LossBefore -1.13646e-08 GaussianMLPPolicy/dLoss -0.00019673 Iteration 55 MetaTest/Average/AverageDiscountedReturn -73.3874 MetaTest/Average/AverageReturn -73.3874 MetaTest/Average/Iteration 55 MetaTest/Average/MaxReturn -51.6261 MetaTest/Average/MinReturn -127.245 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.1422 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -73.3874 MetaTest/__unnamed_task__/AverageReturn -73.3874 MetaTest/__unnamed_task__/Iteration 55 MetaTest/__unnamed_task__/MaxReturn -51.6261 MetaTest/__unnamed_task__/MinReturn -127.245 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.1422 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.688e+06 __unnamed_task__/AverageDiscountedReturn -34.2941 __unnamed_task__/AverageReturn -68.4049 __unnamed_task__/Iteration 55 __unnamed_task__/MaxReturn -50.3214 __unnamed_task__/MinReturn -99.4283 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.4176 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 18:15:46 | [maml_trainer] epoch #56 | Sampling for adapation and meta-testing... 2025-04-04 18:19:46 | [maml_trainer] epoch #56 | Finished meta-testing... 2025-04-04 18:19:46 | [maml_trainer] epoch #56 | Saving snapshot... 2025-04-04 18:20:06 | [maml_trainer] epoch #56 | Saved 2025-04-04 18:20:06 | [maml_trainer] epoch #56 | Time 92450.02 s 2025-04-04 18:20:06 | [maml_trainer] epoch #56 | EpochTime 1691.14 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -34.6212 Average/AverageReturn -70.0492 Average/Iteration 56 Average/MaxReturn -52.3515 Average/MinReturn -125.999 Average/NumEpisodes 120 Average/StdReturn 12.5242 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.97087 GaussianMLPPolicy/KLAfter 0.005551 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.69825e-05 GaussianMLPPolicy/LossBefore 1.73251e-08 GaussianMLPPolicy/dLoss 2.69998e-05 Iteration 56 MetaTest/Average/AverageDiscountedReturn -69.8162 MetaTest/Average/AverageReturn -69.8162 MetaTest/Average/Iteration 56 MetaTest/Average/MaxReturn -51.7318 MetaTest/Average/MinReturn -88.2777 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.3392 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -69.8162 MetaTest/__unnamed_task__/AverageReturn -69.8162 MetaTest/__unnamed_task__/Iteration 56 MetaTest/__unnamed_task__/MaxReturn -51.7318 MetaTest/__unnamed_task__/MinReturn -88.2777 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.3392 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.736e+06 __unnamed_task__/AverageDiscountedReturn -34.6212 __unnamed_task__/AverageReturn -70.0492 __unnamed_task__/Iteration 56 __unnamed_task__/MaxReturn -52.3515 __unnamed_task__/MinReturn -125.999 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.5242 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 18:43:35 | [maml_trainer] epoch #57 | Sampling for adapation and meta-testing... 2025-04-04 18:47:27 | [maml_trainer] epoch #57 | Finished meta-testing... 2025-04-04 18:47:27 | [maml_trainer] epoch #57 | Saving snapshot... 2025-04-04 18:47:47 | [maml_trainer] epoch #57 | Saved 2025-04-04 18:47:47 | [maml_trainer] epoch #57 | Time 94111.06 s 2025-04-04 18:47:47 | [maml_trainer] epoch #57 | EpochTime 1661.03 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -35.1296 Average/AverageReturn -71.9918 Average/Iteration 57 Average/MaxReturn -48.91 Average/MinReturn -136.921 Average/NumEpisodes 120 Average/StdReturn 14.3633 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.97518 GaussianMLPPolicy/KLAfter 0.00532968 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.72001e-05 GaussianMLPPolicy/LossBefore -2.06629e-09 GaussianMLPPolicy/dLoss 3.71981e-05 Iteration 57 MetaTest/Average/AverageDiscountedReturn -68.5407 MetaTest/Average/AverageReturn -68.5407 MetaTest/Average/Iteration 57 MetaTest/Average/MaxReturn -50.7192 MetaTest/Average/MinReturn -157.52 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.0076 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -68.5407 MetaTest/__unnamed_task__/AverageReturn -68.5407 MetaTest/__unnamed_task__/Iteration 57 MetaTest/__unnamed_task__/MaxReturn -50.7192 MetaTest/__unnamed_task__/MinReturn -157.52 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.0076 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.784e+06 __unnamed_task__/AverageDiscountedReturn -35.1296 __unnamed_task__/AverageReturn -71.9918 __unnamed_task__/Iteration 57 __unnamed_task__/MaxReturn -48.91 __unnamed_task__/MinReturn -136.921 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.3633 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 19:11:54 | [maml_trainer] epoch #58 | Sampling for adapation and meta-testing... 2025-04-04 19:15:53 | [maml_trainer] epoch #58 | Finished meta-testing... 2025-04-04 19:15:53 | [maml_trainer] epoch #58 | Saving snapshot... 2025-04-04 19:16:13 | [maml_trainer] epoch #58 | Saved 2025-04-04 19:16:13 | [maml_trainer] epoch #58 | Time 95817.81 s 2025-04-04 19:16:13 | [maml_trainer] epoch #58 | EpochTime 1706.75 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -33.8416 Average/AverageReturn -68.2187 Average/Iteration 58 Average/MaxReturn -47.9124 Average/MinReturn -150.706 Average/NumEpisodes 120 Average/StdReturn 15.3394 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.97898 GaussianMLPPolicy/KLAfter 0.00438835 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.60257e-05 GaussianMLPPolicy/LossBefore 9.85464e-09 GaussianMLPPolicy/dLoss -6.60158e-05 Iteration 58 MetaTest/Average/AverageDiscountedReturn -66.873 MetaTest/Average/AverageReturn -66.873 MetaTest/Average/Iteration 58 MetaTest/Average/MaxReturn -46.0704 MetaTest/Average/MinReturn -133.441 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.8488 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -66.873 MetaTest/__unnamed_task__/AverageReturn -66.873 MetaTest/__unnamed_task__/Iteration 58 MetaTest/__unnamed_task__/MaxReturn -46.0704 MetaTest/__unnamed_task__/MinReturn -133.441 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.8488 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.832e+06 __unnamed_task__/AverageDiscountedReturn -33.8416 __unnamed_task__/AverageReturn -68.2187 __unnamed_task__/Iteration 58 __unnamed_task__/MaxReturn -47.9124 __unnamed_task__/MinReturn -150.706 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 15.3394 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 19:39:45 | [maml_trainer] epoch #59 | Sampling for adapation and meta-testing... 2025-04-04 19:43:39 | [maml_trainer] epoch #59 | Finished meta-testing... 2025-04-04 19:43:39 | [maml_trainer] epoch #59 | Saving snapshot... 2025-04-04 19:43:59 | [maml_trainer] epoch #59 | Saved 2025-04-04 19:43:59 | [maml_trainer] epoch #59 | Time 97483.36 s 2025-04-04 19:43:59 | [maml_trainer] epoch #59 | EpochTime 1665.54 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -34.1732 Average/AverageReturn -69.6874 Average/Iteration 59 Average/MaxReturn -49.2629 Average/MinReturn -144.466 Average/NumEpisodes 120 Average/StdReturn 17.8696 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.98203 GaussianMLPPolicy/KLAfter 0.00541235 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.44214e-05 GaussianMLPPolicy/LossBefore 8.78175e-09 GaussianMLPPolicy/dLoss -2.44126e-05 Iteration 59 MetaTest/Average/AverageDiscountedReturn -65.5487 MetaTest/Average/AverageReturn -65.5487 MetaTest/Average/Iteration 59 MetaTest/Average/MaxReturn -50.7083 MetaTest/Average/MinReturn -112.809 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.8204 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -65.5487 MetaTest/__unnamed_task__/AverageReturn -65.5487 MetaTest/__unnamed_task__/Iteration 59 MetaTest/__unnamed_task__/MaxReturn -50.7083 MetaTest/__unnamed_task__/MinReturn -112.809 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.8204 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.88e+06 __unnamed_task__/AverageDiscountedReturn -34.1732 __unnamed_task__/AverageReturn -69.6874 __unnamed_task__/Iteration 59 __unnamed_task__/MaxReturn -49.2629 __unnamed_task__/MinReturn -144.466 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 17.8696 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 20:07:36 | [maml_trainer] epoch #60 | Sampling for adapation and meta-testing... 2025-04-04 20:11:31 | [maml_trainer] epoch #60 | Finished meta-testing... 2025-04-04 20:11:31 | [maml_trainer] epoch #60 | Saving snapshot... 2025-04-04 20:11:51 | [maml_trainer] epoch #60 | Saved 2025-04-04 20:11:51 | [maml_trainer] epoch #60 | Time 99155.58 s 2025-04-04 20:11:51 | [maml_trainer] epoch #60 | EpochTime 1672.22 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -33.6438 Average/AverageReturn -66.9869 Average/Iteration 60 Average/MaxReturn -48.1345 Average/MinReturn -128.144 Average/NumEpisodes 120 Average/StdReturn 14.0339 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.98544 GaussianMLPPolicy/KLAfter 0.00572111 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.71357e-05 GaussianMLPPolicy/LossBefore 1.14044e-08 GaussianMLPPolicy/dLoss 4.71471e-05 Iteration 60 MetaTest/Average/AverageDiscountedReturn -74.3002 MetaTest/Average/AverageReturn -74.3002 MetaTest/Average/Iteration 60 MetaTest/Average/MaxReturn -49.107 MetaTest/Average/MinReturn -147.486 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.1454 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -74.3002 MetaTest/__unnamed_task__/AverageReturn -74.3002 MetaTest/__unnamed_task__/Iteration 60 MetaTest/__unnamed_task__/MaxReturn -49.107 MetaTest/__unnamed_task__/MinReturn -147.486 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.1454 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.928e+06 __unnamed_task__/AverageDiscountedReturn -33.6438 __unnamed_task__/AverageReturn -66.9869 __unnamed_task__/Iteration 60 __unnamed_task__/MaxReturn -48.1345 __unnamed_task__/MinReturn -128.144 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.0339 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 20:35:25 | [maml_trainer] epoch #61 | Sampling for adapation and meta-testing... 2025-04-04 20:39:19 | [maml_trainer] epoch #61 | Finished meta-testing... 2025-04-04 20:39:19 | [maml_trainer] epoch #61 | Saving snapshot... 2025-04-04 20:39:39 | [maml_trainer] epoch #61 | Saved 2025-04-04 20:39:39 | [maml_trainer] epoch #61 | Time 100823.31 s 2025-04-04 20:39:39 | [maml_trainer] epoch #61 | EpochTime 1667.72 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -33.9739 Average/AverageReturn -68.4003 Average/Iteration 61 Average/MaxReturn -50.6182 Average/MinReturn -154.961 Average/NumEpisodes 120 Average/StdReturn 17.6178 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.98834 GaussianMLPPolicy/KLAfter 0.00617085 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.26415e-05 GaussianMLPPolicy/LossBefore 3.23852e-09 GaussianMLPPolicy/dLoss 6.26447e-05 Iteration 61 MetaTest/Average/AverageDiscountedReturn -71.6684 MetaTest/Average/AverageReturn -71.6684 MetaTest/Average/Iteration 61 MetaTest/Average/MaxReturn -46.0098 MetaTest/Average/MinReturn -148.054 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.2163 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -71.6684 MetaTest/__unnamed_task__/AverageReturn -71.6684 MetaTest/__unnamed_task__/Iteration 61 MetaTest/__unnamed_task__/MaxReturn -46.0098 MetaTest/__unnamed_task__/MinReturn -148.054 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.2163 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.976e+06 __unnamed_task__/AverageDiscountedReturn -33.9739 __unnamed_task__/AverageReturn -68.4003 __unnamed_task__/Iteration 61 __unnamed_task__/MaxReturn -50.6182 __unnamed_task__/MinReturn -154.961 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 17.6178 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 21:03:20 | [maml_trainer] epoch #62 | Sampling for adapation and meta-testing... 2025-04-04 21:07:16 | [maml_trainer] epoch #62 | Finished meta-testing... 2025-04-04 21:07:16 | [maml_trainer] epoch #62 | Saving snapshot... 2025-04-04 21:07:37 | [maml_trainer] epoch #62 | Saved 2025-04-04 21:07:37 | [maml_trainer] epoch #62 | Time 102501.03 s 2025-04-04 21:07:37 | [maml_trainer] epoch #62 | EpochTime 1677.72 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -34.2308 Average/AverageReturn -67.5738 Average/Iteration 62 Average/MaxReturn -48.646 Average/MinReturn -137.368 Average/NumEpisodes 120 Average/StdReturn 16.241 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.99146 GaussianMLPPolicy/KLAfter 0.00690271 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.7777e-06 GaussianMLPPolicy/LossBefore 2.78155e-09 GaussianMLPPolicy/dLoss -5.77492e-06 Iteration 62 MetaTest/Average/AverageDiscountedReturn -66.4695 MetaTest/Average/AverageReturn -66.4695 MetaTest/Average/Iteration 62 MetaTest/Average/MaxReturn -47.247 MetaTest/Average/MinReturn -110.701 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.293 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -66.4695 MetaTest/__unnamed_task__/AverageReturn -66.4695 MetaTest/__unnamed_task__/Iteration 62 MetaTest/__unnamed_task__/MaxReturn -47.247 MetaTest/__unnamed_task__/MinReturn -110.701 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.293 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.024e+06 __unnamed_task__/AverageDiscountedReturn -34.2308 __unnamed_task__/AverageReturn -67.5738 __unnamed_task__/Iteration 62 __unnamed_task__/MaxReturn -48.646 __unnamed_task__/MinReturn -137.368 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 16.241 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 21:31:25 | [maml_trainer] epoch #63 | Sampling for adapation and meta-testing... 2025-04-04 21:35:21 | [maml_trainer] epoch #63 | Finished meta-testing... 2025-04-04 21:35:21 | [maml_trainer] epoch #63 | Saving snapshot... 2025-04-04 21:35:42 | [maml_trainer] epoch #63 | Saved 2025-04-04 21:35:42 | [maml_trainer] epoch #63 | Time 104186.00 s 2025-04-04 21:35:42 | [maml_trainer] epoch #63 | EpochTime 1684.97 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -33.1882 Average/AverageReturn -63.0262 Average/Iteration 63 Average/MaxReturn -48.5005 Average/MinReturn -108.673 Average/NumEpisodes 120 Average/StdReturn 9.81466 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.99412 GaussianMLPPolicy/KLAfter 0.00584469 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.75662e-05 GaussianMLPPolicy/LossBefore -5.48363e-09 GaussianMLPPolicy/dLoss 1.75607e-05 Iteration 63 MetaTest/Average/AverageDiscountedReturn -60.4493 MetaTest/Average/AverageReturn -60.4493 MetaTest/Average/Iteration 63 MetaTest/Average/MaxReturn -50.3962 MetaTest/Average/MinReturn -74.8365 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.99921 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -60.4493 MetaTest/__unnamed_task__/AverageReturn -60.4493 MetaTest/__unnamed_task__/Iteration 63 MetaTest/__unnamed_task__/MaxReturn -50.3962 MetaTest/__unnamed_task__/MinReturn -74.8365 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.99921 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.072e+06 __unnamed_task__/AverageDiscountedReturn -33.1882 __unnamed_task__/AverageReturn -63.0262 __unnamed_task__/Iteration 63 __unnamed_task__/MaxReturn -48.5005 __unnamed_task__/MinReturn -108.673 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.81466 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 21:59:28 | [maml_trainer] epoch #64 | Sampling for adapation and meta-testing... 2025-04-04 22:03:22 | [maml_trainer] epoch #64 | Finished meta-testing... 2025-04-04 22:03:22 | [maml_trainer] epoch #64 | Saving snapshot... 2025-04-04 22:03:42 | [maml_trainer] epoch #64 | Saved 2025-04-04 22:03:42 | [maml_trainer] epoch #64 | Time 105866.16 s 2025-04-04 22:03:42 | [maml_trainer] epoch #64 | EpochTime 1680.16 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -33.4542 Average/AverageReturn -64.4139 Average/Iteration 64 Average/MaxReturn -50.1815 Average/MinReturn -156.718 Average/NumEpisodes 120 Average/StdReturn 15.5578 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.99703 GaussianMLPPolicy/KLAfter 0.0066887 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.83245e-05 GaussianMLPPolicy/LossBefore 1.09275e-08 GaussianMLPPolicy/dLoss 2.83354e-05 Iteration 64 MetaTest/Average/AverageDiscountedReturn -60.9685 MetaTest/Average/AverageReturn -60.9685 MetaTest/Average/Iteration 64 MetaTest/Average/MaxReturn -50.2794 MetaTest/Average/MinReturn -69.4478 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.18559 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -60.9685 MetaTest/__unnamed_task__/AverageReturn -60.9685 MetaTest/__unnamed_task__/Iteration 64 MetaTest/__unnamed_task__/MaxReturn -50.2794 MetaTest/__unnamed_task__/MinReturn -69.4478 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.18559 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.12e+06 __unnamed_task__/AverageDiscountedReturn -33.4542 __unnamed_task__/AverageReturn -64.4139 __unnamed_task__/Iteration 64 __unnamed_task__/MaxReturn -50.1815 __unnamed_task__/MinReturn -156.718 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 15.5578 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 22:27:08 | [maml_trainer] epoch #65 | Sampling for adapation and meta-testing... 2025-04-04 22:31:01 | [maml_trainer] epoch #65 | Finished meta-testing... 2025-04-04 22:31:01 | [maml_trainer] epoch #65 | Saving snapshot... 2025-04-04 22:31:21 | [maml_trainer] epoch #65 | Saved 2025-04-04 22:31:21 | [maml_trainer] epoch #65 | Time 107525.89 s 2025-04-04 22:31:21 | [maml_trainer] epoch #65 | EpochTime 1659.72 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.9394 Average/AverageReturn -62.1037 Average/Iteration 65 Average/MaxReturn -45.7031 Average/MinReturn -157.685 Average/NumEpisodes 120 Average/StdReturn 12.0661 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.99837 GaussianMLPPolicy/KLAfter 0.00748525 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.6652e-05 GaussianMLPPolicy/LossBefore -3.13918e-09 GaussianMLPPolicy/dLoss 8.66489e-05 Iteration 65 MetaTest/Average/AverageDiscountedReturn -59.2136 MetaTest/Average/AverageReturn -59.2136 MetaTest/Average/Iteration 65 MetaTest/Average/MaxReturn -49.3458 MetaTest/Average/MinReturn -71.11 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.28226 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -59.2136 MetaTest/__unnamed_task__/AverageReturn -59.2136 MetaTest/__unnamed_task__/Iteration 65 MetaTest/__unnamed_task__/MaxReturn -49.3458 MetaTest/__unnamed_task__/MinReturn -71.11 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.28226 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.168e+06 __unnamed_task__/AverageDiscountedReturn -32.9394 __unnamed_task__/AverageReturn -62.1037 __unnamed_task__/Iteration 65 __unnamed_task__/MaxReturn -45.7031 __unnamed_task__/MinReturn -157.685 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.0661 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 22:54:41 | [maml_trainer] epoch #66 | Sampling for adapation and meta-testing... 2025-04-04 22:58:33 | [maml_trainer] epoch #66 | Finished meta-testing... 2025-04-04 22:58:34 | [maml_trainer] epoch #66 | Saving snapshot... 2025-04-04 22:58:54 | [maml_trainer] epoch #66 | Saved 2025-04-04 22:58:54 | [maml_trainer] epoch #66 | Time 109178.06 s 2025-04-04 22:58:54 | [maml_trainer] epoch #66 | EpochTime 1652.17 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.6559 Average/AverageReturn -61.5584 Average/Iteration 66 Average/MaxReturn -47.222 Average/MinReturn -131.475 Average/NumEpisodes 120 Average/StdReturn 13.788 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.99925 GaussianMLPPolicy/KLAfter 0.00683781 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.41906e-05 GaussianMLPPolicy/LossBefore 9.41753e-09 GaussianMLPPolicy/dLoss -8.41812e-05 Iteration 66 MetaTest/Average/AverageDiscountedReturn -57.1593 MetaTest/Average/AverageReturn -57.1593 MetaTest/Average/Iteration 66 MetaTest/Average/MaxReturn -47.7196 MetaTest/Average/MinReturn -68.4743 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.48636 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -57.1593 MetaTest/__unnamed_task__/AverageReturn -57.1593 MetaTest/__unnamed_task__/Iteration 66 MetaTest/__unnamed_task__/MaxReturn -47.7196 MetaTest/__unnamed_task__/MinReturn -68.4743 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.48636 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.216e+06 __unnamed_task__/AverageDiscountedReturn -32.6559 __unnamed_task__/AverageReturn -61.5584 __unnamed_task__/Iteration 66 __unnamed_task__/MaxReturn -47.222 __unnamed_task__/MinReturn -131.475 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 13.788 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-04 23:21:51 | [maml_trainer] epoch #67 | Sampling for adapation and meta-testing... 2025-04-04 23:25:45 | [maml_trainer] epoch #67 | Finished meta-testing... 2025-04-04 23:25:45 | [maml_trainer] epoch #67 | Saving snapshot... 2025-04-04 23:26:06 | [maml_trainer] epoch #67 | Saved 2025-04-04 23:26:06 | [maml_trainer] epoch #67 | Time 110810.35 s 2025-04-04 23:26:06 | [maml_trainer] epoch #67 | EpochTime 1632.28 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -32.3946 Average/AverageReturn -58.8171 Average/Iteration 67 Average/MaxReturn -47.1557 Average/MinReturn -82.5453 Average/NumEpisodes 120 Average/StdReturn 5.77513 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.99892 GaussianMLPPolicy/KLAfter 0.00683179 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000102886 GaussianMLPPolicy/LossBefore 4.76837e-09 GaussianMLPPolicy/dLoss 0.000102891 Iteration 67 MetaTest/Average/AverageDiscountedReturn -57.8278 MetaTest/Average/AverageReturn -57.8278 MetaTest/Average/Iteration 67 MetaTest/Average/MaxReturn -48.8225 MetaTest/Average/MinReturn -67.5294 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.55107 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -57.8278 MetaTest/__unnamed_task__/AverageReturn -57.8278 MetaTest/__unnamed_task__/Iteration 67 MetaTest/__unnamed_task__/MaxReturn -48.8225 MetaTest/__unnamed_task__/MinReturn -67.5294 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.55107 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.264e+06 __unnamed_task__/AverageDiscountedReturn -32.3946 __unnamed_task__/AverageReturn -58.8171 __unnamed_task__/Iteration 67 __unnamed_task__/MaxReturn -47.1557 __unnamed_task__/MinReturn -82.5453 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.77513 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-04 23:49:23 | [maml_trainer] epoch #68 | Sampling for adapation and meta-testing... 2025-04-04 23:53:17 | [maml_trainer] epoch #68 | Finished meta-testing... 2025-04-04 23:53:17 | [maml_trainer] epoch #68 | Saving snapshot... 2025-04-04 23:53:37 | [maml_trainer] epoch #68 | Saved 2025-04-04 23:53:37 | [maml_trainer] epoch #68 | Time 112461.82 s 2025-04-04 23:53:37 | [maml_trainer] epoch #68 | EpochTime 1651.46 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -32.3726 Average/AverageReturn -58.5267 Average/Iteration 68 Average/MaxReturn -47.0963 Average/MinReturn -80.6368 Average/NumEpisodes 120 Average/StdReturn 5.87898 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.99826 GaussianMLPPolicy/KLAfter 0.00595331 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.37019e-05 GaussianMLPPolicy/LossBefore 1.33912e-08 GaussianMLPPolicy/dLoss 1.37153e-05 Iteration 68 MetaTest/Average/AverageDiscountedReturn -57.6583 MetaTest/Average/AverageReturn -57.6583 MetaTest/Average/Iteration 68 MetaTest/Average/MaxReturn -49.5115 MetaTest/Average/MinReturn -88.6595 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.02781 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -57.6583 MetaTest/__unnamed_task__/AverageReturn -57.6583 MetaTest/__unnamed_task__/Iteration 68 MetaTest/__unnamed_task__/MaxReturn -49.5115 MetaTest/__unnamed_task__/MinReturn -88.6595 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.02781 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.312e+06 __unnamed_task__/AverageDiscountedReturn -32.3726 __unnamed_task__/AverageReturn -58.5267 __unnamed_task__/Iteration 68 __unnamed_task__/MaxReturn -47.0963 __unnamed_task__/MinReturn -80.6368 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.87898 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 00:16:58 | [maml_trainer] epoch #69 | Sampling for adapation and meta-testing... 2025-04-05 00:20:49 | [maml_trainer] epoch #69 | Finished meta-testing... 2025-04-05 00:20:49 | [maml_trainer] epoch #69 | Saving snapshot... 2025-04-05 00:21:09 | [maml_trainer] epoch #69 | Saved 2025-04-05 00:21:09 | [maml_trainer] epoch #69 | Time 114113.54 s 2025-04-05 00:21:09 | [maml_trainer] epoch #69 | EpochTime 1651.72 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -32.3983 Average/AverageReturn -58.4798 Average/Iteration 69 Average/MaxReturn -47.4579 Average/MinReturn -74.4689 Average/NumEpisodes 120 Average/StdReturn 5.46807 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.99622 GaussianMLPPolicy/KLAfter 0.00645062 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.81e-05 GaussianMLPPolicy/LossBefore 2.14577e-09 GaussianMLPPolicy/dLoss -1.80978e-05 Iteration 69 MetaTest/Average/AverageDiscountedReturn -56.5389 MetaTest/Average/AverageReturn -56.5389 MetaTest/Average/Iteration 69 MetaTest/Average/MaxReturn -49.9342 MetaTest/Average/MinReturn -65.6988 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.82455 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -56.5389 MetaTest/__unnamed_task__/AverageReturn -56.5389 MetaTest/__unnamed_task__/Iteration 69 MetaTest/__unnamed_task__/MaxReturn -49.9342 MetaTest/__unnamed_task__/MinReturn -65.6988 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.82455 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.36e+06 __unnamed_task__/AverageDiscountedReturn -32.3983 __unnamed_task__/AverageReturn -58.4798 __unnamed_task__/Iteration 69 __unnamed_task__/MaxReturn -47.4579 __unnamed_task__/MinReturn -74.4689 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.46807 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 00:44:06 | [maml_trainer] epoch #70 | Sampling for adapation and meta-testing... 2025-04-05 00:48:02 | [maml_trainer] epoch #70 | Finished meta-testing... 2025-04-05 00:48:02 | [maml_trainer] epoch #70 | Saving snapshot... 2025-04-05 00:48:23 | [maml_trainer] epoch #70 | Saved 2025-04-05 00:48:23 | [maml_trainer] epoch #70 | Time 115747.15 s 2025-04-05 00:48:23 | [maml_trainer] epoch #70 | EpochTime 1633.61 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -32.2276 Average/AverageReturn -58.0794 Average/Iteration 70 Average/MaxReturn -47.3674 Average/MinReturn -76.3788 Average/NumEpisodes 120 Average/StdReturn 5.69181 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.99262 GaussianMLPPolicy/KLAfter 0.00811791 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.00014378 GaussianMLPPolicy/LossBefore -1.54972e-09 GaussianMLPPolicy/dLoss -0.000143782 Iteration 70 MetaTest/Average/AverageDiscountedReturn -57.9636 MetaTest/Average/AverageReturn -57.9636 MetaTest/Average/Iteration 70 MetaTest/Average/MaxReturn -46.0649 MetaTest/Average/MinReturn -80.1261 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.61944 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -57.9636 MetaTest/__unnamed_task__/AverageReturn -57.9636 MetaTest/__unnamed_task__/Iteration 70 MetaTest/__unnamed_task__/MaxReturn -46.0649 MetaTest/__unnamed_task__/MinReturn -80.1261 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.61944 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.408e+06 __unnamed_task__/AverageDiscountedReturn -32.2276 __unnamed_task__/AverageReturn -58.0794 __unnamed_task__/Iteration 70 __unnamed_task__/MaxReturn -47.3674 __unnamed_task__/MinReturn -76.3788 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.69181 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 01:11:52 | [maml_trainer] epoch #71 | Sampling for adapation and meta-testing... 2025-04-05 01:15:40 | [maml_trainer] epoch #71 | Finished meta-testing... 2025-04-05 01:15:40 | [maml_trainer] epoch #71 | Saving snapshot... 2025-04-05 01:16:00 | [maml_trainer] epoch #71 | Saved 2025-04-05 01:16:00 | [maml_trainer] epoch #71 | Time 117404.48 s 2025-04-05 01:16:00 | [maml_trainer] epoch #71 | EpochTime 1657.33 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -32.3809 Average/AverageReturn -58.6185 Average/Iteration 71 Average/MaxReturn -48.1933 Average/MinReturn -78.7347 Average/NumEpisodes 120 Average/StdReturn 5.84311 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.98813 GaussianMLPPolicy/KLAfter 0.007888 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.0076e-05 GaussianMLPPolicy/LossBefore 1.24375e-08 GaussianMLPPolicy/dLoss 8.00885e-05 Iteration 71 MetaTest/Average/AverageDiscountedReturn -59.6236 MetaTest/Average/AverageReturn -59.6236 MetaTest/Average/Iteration 71 MetaTest/Average/MaxReturn -49.5389 MetaTest/Average/MinReturn -72.4505 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.50315 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -59.6236 MetaTest/__unnamed_task__/AverageReturn -59.6236 MetaTest/__unnamed_task__/Iteration 71 MetaTest/__unnamed_task__/MaxReturn -49.5389 MetaTest/__unnamed_task__/MinReturn -72.4505 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.50315 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.456e+06 __unnamed_task__/AverageDiscountedReturn -32.3809 __unnamed_task__/AverageReturn -58.6185 __unnamed_task__/Iteration 71 __unnamed_task__/MaxReturn -48.1933 __unnamed_task__/MinReturn -78.7347 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.84311 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 01:39:13 | [maml_trainer] epoch #72 | Sampling for adapation and meta-testing... 2025-04-05 01:43:05 | [maml_trainer] epoch #72 | Finished meta-testing... 2025-04-05 01:43:05 | [maml_trainer] epoch #72 | Saving snapshot... 2025-04-05 01:43:25 | [maml_trainer] epoch #72 | Saved 2025-04-05 01:43:25 | [maml_trainer] epoch #72 | Time 119049.89 s 2025-04-05 01:43:25 | [maml_trainer] epoch #72 | EpochTime 1645.40 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -32.6999 Average/AverageReturn -59.7331 Average/Iteration 72 Average/MaxReturn -48.0436 Average/MinReturn -87.3308 Average/NumEpisodes 120 Average/StdReturn 7.2699 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.98419 GaussianMLPPolicy/KLAfter 0.00680742 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.50123e-05 GaussianMLPPolicy/LossBefore -2.66234e-09 GaussianMLPPolicy/dLoss 1.50096e-05 Iteration 72 MetaTest/Average/AverageDiscountedReturn -56.1916 MetaTest/Average/AverageReturn -56.1916 MetaTest/Average/Iteration 72 MetaTest/Average/MaxReturn -48.5814 MetaTest/Average/MinReturn -75.8151 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.91383 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -56.1916 MetaTest/__unnamed_task__/AverageReturn -56.1916 MetaTest/__unnamed_task__/Iteration 72 MetaTest/__unnamed_task__/MaxReturn -48.5814 MetaTest/__unnamed_task__/MinReturn -75.8151 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.91383 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.504e+06 __unnamed_task__/AverageDiscountedReturn -32.6999 __unnamed_task__/AverageReturn -59.7331 __unnamed_task__/Iteration 72 __unnamed_task__/MaxReturn -48.0436 __unnamed_task__/MinReturn -87.3308 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.2699 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 02:06:39 | [maml_trainer] epoch #73 | Sampling for adapation and meta-testing... 2025-04-05 02:10:29 | [maml_trainer] epoch #73 | Finished meta-testing... 2025-04-05 02:10:29 | [maml_trainer] epoch #73 | Saving snapshot... 2025-04-05 02:10:49 | [maml_trainer] epoch #73 | Saved 2025-04-05 02:10:49 | [maml_trainer] epoch #73 | Time 120693.72 s 2025-04-05 02:10:49 | [maml_trainer] epoch #73 | EpochTime 1643.83 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -31.9527 Average/AverageReturn -57.8923 Average/Iteration 73 Average/MaxReturn -46.8038 Average/MinReturn -81.1373 Average/NumEpisodes 120 Average/StdReturn 6.93702 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.9802 GaussianMLPPolicy/KLAfter 0.00916397 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000172868 GaussianMLPPolicy/LossBefore -4.05312e-09 GaussianMLPPolicy/dLoss 0.000172864 Iteration 73 MetaTest/Average/AverageDiscountedReturn -62.6487 MetaTest/Average/AverageReturn -62.6487 MetaTest/Average/Iteration 73 MetaTest/Average/MaxReturn -51.4459 MetaTest/Average/MinReturn -93.4157 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.04842 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -62.6487 MetaTest/__unnamed_task__/AverageReturn -62.6487 MetaTest/__unnamed_task__/Iteration 73 MetaTest/__unnamed_task__/MaxReturn -51.4459 MetaTest/__unnamed_task__/MinReturn -93.4157 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.04842 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.552e+06 __unnamed_task__/AverageDiscountedReturn -31.9527 __unnamed_task__/AverageReturn -57.8923 __unnamed_task__/Iteration 73 __unnamed_task__/MaxReturn -46.8038 __unnamed_task__/MinReturn -81.1373 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.93702 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 02:33:54 | [maml_trainer] epoch #74 | Sampling for adapation and meta-testing... 2025-04-05 02:37:41 | [maml_trainer] epoch #74 | Finished meta-testing... 2025-04-05 02:37:41 | [maml_trainer] epoch #74 | Saving snapshot... 2025-04-05 02:38:01 | [maml_trainer] epoch #74 | Saved 2025-04-05 02:38:01 | [maml_trainer] epoch #74 | Time 122325.95 s 2025-04-05 02:38:01 | [maml_trainer] epoch #74 | EpochTime 1632.23 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.11 Average/AverageReturn -59.021 Average/Iteration 74 Average/MaxReturn -44.4808 Average/MinReturn -147.59 Average/NumEpisodes 120 Average/StdReturn 10.6454 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.97728 GaussianMLPPolicy/KLAfter 0.0081299 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.19652e-05 GaussianMLPPolicy/LossBefore -4.60943e-09 GaussianMLPPolicy/dLoss 8.19606e-05 Iteration 74 MetaTest/Average/AverageDiscountedReturn -56.6359 MetaTest/Average/AverageReturn -56.6359 MetaTest/Average/Iteration 74 MetaTest/Average/MaxReturn -47.596 MetaTest/Average/MinReturn -65.3359 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.99441 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -56.6359 MetaTest/__unnamed_task__/AverageReturn -56.6359 MetaTest/__unnamed_task__/Iteration 74 MetaTest/__unnamed_task__/MaxReturn -47.596 MetaTest/__unnamed_task__/MinReturn -65.3359 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.99441 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.6e+06 __unnamed_task__/AverageDiscountedReturn -32.11 __unnamed_task__/AverageReturn -59.021 __unnamed_task__/Iteration 74 __unnamed_task__/MaxReturn -44.4808 __unnamed_task__/MinReturn -147.59 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.6454 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 03:01:07 | [maml_trainer] epoch #75 | Sampling for adapation and meta-testing... 2025-04-05 03:04:59 | [maml_trainer] epoch #75 | Finished meta-testing... 2025-04-05 03:04:59 | [maml_trainer] epoch #75 | Saving snapshot... 2025-04-05 03:05:19 | [maml_trainer] epoch #75 | Saved 2025-04-05 03:05:19 | [maml_trainer] epoch #75 | Time 123963.85 s 2025-04-05 03:05:19 | [maml_trainer] epoch #75 | EpochTime 1637.89 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.3605 Average/AverageReturn -59.8418 Average/Iteration 75 Average/MaxReturn -46.1727 Average/MinReturn -126.267 Average/NumEpisodes 120 Average/StdReturn 10.8108 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.97521 GaussianMLPPolicy/KLAfter 0.00648716 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.08444e-06 GaussianMLPPolicy/LossBefore -8.38439e-09 GaussianMLPPolicy/dLoss 5.07605e-06 Iteration 75 MetaTest/Average/AverageDiscountedReturn -53.9219 MetaTest/Average/AverageReturn -53.9219 MetaTest/Average/Iteration 75 MetaTest/Average/MaxReturn -42.9947 MetaTest/Average/MinReturn -76.4795 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.60454 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.9219 MetaTest/__unnamed_task__/AverageReturn -53.9219 MetaTest/__unnamed_task__/Iteration 75 MetaTest/__unnamed_task__/MaxReturn -42.9947 MetaTest/__unnamed_task__/MinReturn -76.4795 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.60454 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.648e+06 __unnamed_task__/AverageDiscountedReturn -32.3605 __unnamed_task__/AverageReturn -59.8418 __unnamed_task__/Iteration 75 __unnamed_task__/MaxReturn -46.1727 __unnamed_task__/MinReturn -126.267 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.8108 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 03:28:37 | [maml_trainer] epoch #76 | Sampling for adapation and meta-testing... 2025-04-05 03:32:29 | [maml_trainer] epoch #76 | Finished meta-testing... 2025-04-05 03:32:29 | [maml_trainer] epoch #76 | Saving snapshot... 2025-04-05 03:32:49 | [maml_trainer] epoch #76 | Saved 2025-04-05 03:32:49 | [maml_trainer] epoch #76 | Time 125613.74 s 2025-04-05 03:32:49 | [maml_trainer] epoch #76 | EpochTime 1649.89 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -31.4404 Average/AverageReturn -57.1847 Average/Iteration 76 Average/MaxReturn -46.4346 Average/MinReturn -86.6627 Average/NumEpisodes 120 Average/StdReturn 6.99649 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.97216 GaussianMLPPolicy/KLAfter 0.00489162 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.64641e-05 GaussianMLPPolicy/LossBefore -3.69549e-09 GaussianMLPPolicy/dLoss 4.64604e-05 Iteration 76 MetaTest/Average/AverageDiscountedReturn -55.1882 MetaTest/Average/AverageReturn -55.1882 MetaTest/Average/Iteration 76 MetaTest/Average/MaxReturn -46.5544 MetaTest/Average/MinReturn -74.1244 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.10401 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.1882 MetaTest/__unnamed_task__/AverageReturn -55.1882 MetaTest/__unnamed_task__/Iteration 76 MetaTest/__unnamed_task__/MaxReturn -46.5544 MetaTest/__unnamed_task__/MinReturn -74.1244 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.10401 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.696e+06 __unnamed_task__/AverageDiscountedReturn -31.4404 __unnamed_task__/AverageReturn -57.1847 __unnamed_task__/Iteration 76 __unnamed_task__/MaxReturn -46.4346 __unnamed_task__/MinReturn -86.6627 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.99649 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 03:56:05 | [maml_trainer] epoch #77 | Sampling for adapation and meta-testing... 2025-04-05 04:00:00 | [maml_trainer] epoch #77 | Finished meta-testing... 2025-04-05 04:00:00 | [maml_trainer] epoch #77 | Saving snapshot... 2025-04-05 04:00:20 | [maml_trainer] epoch #77 | Saved 2025-04-05 04:00:20 | [maml_trainer] epoch #77 | Time 127264.63 s 2025-04-05 04:00:20 | [maml_trainer] epoch #77 | EpochTime 1650.88 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -31.4366 Average/AverageReturn -57.8687 Average/Iteration 77 Average/MaxReturn -44.1332 Average/MinReturn -110.901 Average/NumEpisodes 120 Average/StdReturn 9.08424 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.97038 GaussianMLPPolicy/KLAfter 0.00534654 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.33461e-05 GaussianMLPPolicy/LossBefore -1.00533e-08 GaussianMLPPolicy/dLoss -3.33562e-05 Iteration 77 MetaTest/Average/AverageDiscountedReturn -59.2099 MetaTest/Average/AverageReturn -59.2099 MetaTest/Average/Iteration 77 MetaTest/Average/MaxReturn -46.6451 MetaTest/Average/MinReturn -79.7074 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.14225 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -59.2099 MetaTest/__unnamed_task__/AverageReturn -59.2099 MetaTest/__unnamed_task__/Iteration 77 MetaTest/__unnamed_task__/MaxReturn -46.6451 MetaTest/__unnamed_task__/MinReturn -79.7074 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.14225 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.744e+06 __unnamed_task__/AverageDiscountedReturn -31.4366 __unnamed_task__/AverageReturn -57.8687 __unnamed_task__/Iteration 77 __unnamed_task__/MaxReturn -44.1332 __unnamed_task__/MinReturn -110.901 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.08424 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 04:23:33 | [maml_trainer] epoch #78 | Sampling for adapation and meta-testing... 2025-04-05 04:27:23 | [maml_trainer] epoch #78 | Finished meta-testing... 2025-04-05 04:27:23 | [maml_trainer] epoch #78 | Saving snapshot... 2025-04-05 04:27:44 | [maml_trainer] epoch #78 | Saved 2025-04-05 04:27:44 | [maml_trainer] epoch #78 | Time 128908.82 s 2025-04-05 04:27:44 | [maml_trainer] epoch #78 | EpochTime 1644.18 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -31.5132 Average/AverageReturn -58.043 Average/Iteration 78 Average/MaxReturn -45.7811 Average/MinReturn -106.196 Average/NumEpisodes 120 Average/StdReturn 9.97133 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.9691 GaussianMLPPolicy/KLAfter 0.0048728 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000121232 GaussianMLPPolicy/LossBefore -1.11262e-09 GaussianMLPPolicy/dLoss -0.000121233 Iteration 78 MetaTest/Average/AverageDiscountedReturn -60.8125 MetaTest/Average/AverageReturn -60.8125 MetaTest/Average/Iteration 78 MetaTest/Average/MaxReturn -47.0598 MetaTest/Average/MinReturn -77.716 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.551 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -60.8125 MetaTest/__unnamed_task__/AverageReturn -60.8125 MetaTest/__unnamed_task__/Iteration 78 MetaTest/__unnamed_task__/MaxReturn -47.0598 MetaTest/__unnamed_task__/MinReturn -77.716 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.551 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.792e+06 __unnamed_task__/AverageDiscountedReturn -31.5132 __unnamed_task__/AverageReturn -58.043 __unnamed_task__/Iteration 78 __unnamed_task__/MaxReturn -45.7811 __unnamed_task__/MinReturn -106.196 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.97133 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 04:51:06 | [maml_trainer] epoch #79 | Sampling for adapation and meta-testing... 2025-04-05 04:54:53 | [maml_trainer] epoch #79 | Finished meta-testing... 2025-04-05 04:54:53 | [maml_trainer] epoch #79 | Saving snapshot... 2025-04-05 04:55:13 | [maml_trainer] epoch #79 | Saved 2025-04-05 04:55:13 | [maml_trainer] epoch #79 | Time 130557.68 s 2025-04-05 04:55:13 | [maml_trainer] epoch #79 | EpochTime 1648.86 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -31.5618 Average/AverageReturn -58.9887 Average/Iteration 79 Average/MaxReturn -43.5847 Average/MinReturn -83.9473 Average/NumEpisodes 120 Average/StdReturn 8.95949 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96829 GaussianMLPPolicy/KLAfter 0.00440186 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.0479e-05 GaussianMLPPolicy/LossBefore -3.09944e-09 GaussianMLPPolicy/dLoss 8.04759e-05 Iteration 79 MetaTest/Average/AverageDiscountedReturn -61.61 MetaTest/Average/AverageReturn -61.61 MetaTest/Average/Iteration 79 MetaTest/Average/MaxReturn -46.1126 MetaTest/Average/MinReturn -77.4507 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.22353 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -61.61 MetaTest/__unnamed_task__/AverageReturn -61.61 MetaTest/__unnamed_task__/Iteration 79 MetaTest/__unnamed_task__/MaxReturn -46.1126 MetaTest/__unnamed_task__/MinReturn -77.4507 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.22353 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.84e+06 __unnamed_task__/AverageDiscountedReturn -31.5618 __unnamed_task__/AverageReturn -58.9887 __unnamed_task__/Iteration 79 __unnamed_task__/MaxReturn -43.5847 __unnamed_task__/MinReturn -83.9473 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.95949 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 05:18:08 | [maml_trainer] epoch #80 | Sampling for adapation and meta-testing... 2025-04-05 05:22:04 | [maml_trainer] epoch #80 | Finished meta-testing... 2025-04-05 05:22:04 | [maml_trainer] epoch #80 | Saving snapshot... 2025-04-05 05:22:25 | [maml_trainer] epoch #80 | Saved 2025-04-05 05:22:25 | [maml_trainer] epoch #80 | Time 132189.18 s 2025-04-05 05:22:25 | [maml_trainer] epoch #80 | EpochTime 1631.50 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.2219 Average/AverageReturn -61.9006 Average/Iteration 80 Average/MaxReturn -46.1213 Average/MinReturn -141.717 Average/NumEpisodes 120 Average/StdReturn 12.0617 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96768 GaussianMLPPolicy/KLAfter 0.00356178 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.47273e-05 GaussianMLPPolicy/LossBefore -1.19209e-09 GaussianMLPPolicy/dLoss -1.47285e-05 Iteration 80 MetaTest/Average/AverageDiscountedReturn -70.7409 MetaTest/Average/AverageReturn -70.7409 MetaTest/Average/Iteration 80 MetaTest/Average/MaxReturn -49.554 MetaTest/Average/MinReturn -168.838 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 28.7082 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -70.7409 MetaTest/__unnamed_task__/AverageReturn -70.7409 MetaTest/__unnamed_task__/Iteration 80 MetaTest/__unnamed_task__/MaxReturn -49.554 MetaTest/__unnamed_task__/MinReturn -168.838 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 28.7082 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.888e+06 __unnamed_task__/AverageDiscountedReturn -32.2219 __unnamed_task__/AverageReturn -61.9006 __unnamed_task__/Iteration 80 __unnamed_task__/MaxReturn -46.1213 __unnamed_task__/MinReturn -141.717 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.0617 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 05:45:28 | [maml_trainer] epoch #81 | Sampling for adapation and meta-testing... 2025-04-05 05:49:19 | [maml_trainer] epoch #81 | Finished meta-testing... 2025-04-05 05:49:19 | [maml_trainer] epoch #81 | Saving snapshot... 2025-04-05 05:49:40 | [maml_trainer] epoch #81 | Saved 2025-04-05 05:49:40 | [maml_trainer] epoch #81 | Time 133824.11 s 2025-04-05 05:49:40 | [maml_trainer] epoch #81 | EpochTime 1634.93 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.1801 Average/AverageReturn -62.0036 Average/Iteration 81 Average/MaxReturn -45.4871 Average/MinReturn -132.866 Average/NumEpisodes 120 Average/StdReturn 11.6518 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96698 GaussianMLPPolicy/KLAfter 0.0051359 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.11683e-05 GaussianMLPPolicy/LossBefore 7.54992e-09 GaussianMLPPolicy/dLoss 4.11758e-05 Iteration 81 MetaTest/Average/AverageDiscountedReturn -60.4813 MetaTest/Average/AverageReturn -60.4813 MetaTest/Average/Iteration 81 MetaTest/Average/MaxReturn -47.2209 MetaTest/Average/MinReturn -80.477 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.29384 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -60.4813 MetaTest/__unnamed_task__/AverageReturn -60.4813 MetaTest/__unnamed_task__/Iteration 81 MetaTest/__unnamed_task__/MaxReturn -47.2209 MetaTest/__unnamed_task__/MinReturn -80.477 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.29384 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.936e+06 __unnamed_task__/AverageDiscountedReturn -32.1801 __unnamed_task__/AverageReturn -62.0036 __unnamed_task__/Iteration 81 __unnamed_task__/MaxReturn -45.4871 __unnamed_task__/MinReturn -132.866 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.6518 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 06:12:56 | [maml_trainer] epoch #82 | Sampling for adapation and meta-testing... 2025-04-05 06:16:48 | [maml_trainer] epoch #82 | Finished meta-testing... 2025-04-05 06:16:48 | [maml_trainer] epoch #82 | Saving snapshot... 2025-04-05 06:17:09 | [maml_trainer] epoch #82 | Saved 2025-04-05 06:17:09 | [maml_trainer] epoch #82 | Time 135473.14 s 2025-04-05 06:17:09 | [maml_trainer] epoch #82 | EpochTime 1649.03 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.2624 Average/AverageReturn -63.2878 Average/Iteration 82 Average/MaxReturn -43.1829 Average/MinReturn -200.007 Average/NumEpisodes 120 Average/StdReturn 17.4658 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96537 GaussianMLPPolicy/KLAfter 0.00317222 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.65565e-05 GaussianMLPPolicy/LossBefore 1.39475e-08 GaussianMLPPolicy/dLoss 8.65705e-05 Iteration 82 MetaTest/Average/AverageDiscountedReturn -59.7759 MetaTest/Average/AverageReturn -59.7759 MetaTest/Average/Iteration 82 MetaTest/Average/MaxReturn -46.4403 MetaTest/Average/MinReturn -80.7 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.116 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -59.7759 MetaTest/__unnamed_task__/AverageReturn -59.7759 MetaTest/__unnamed_task__/Iteration 82 MetaTest/__unnamed_task__/MaxReturn -46.4403 MetaTest/__unnamed_task__/MinReturn -80.7 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.116 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 3.984e+06 __unnamed_task__/AverageDiscountedReturn -32.2624 __unnamed_task__/AverageReturn -63.2878 __unnamed_task__/Iteration 82 __unnamed_task__/MaxReturn -43.1829 __unnamed_task__/MinReturn -200.007 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 17.4658 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 06:40:18 | [maml_trainer] epoch #83 | Sampling for adapation and meta-testing... 2025-04-05 06:44:05 | [maml_trainer] epoch #83 | Finished meta-testing... 2025-04-05 06:44:05 | [maml_trainer] epoch #83 | Saving snapshot... 2025-04-05 06:44:26 | [maml_trainer] epoch #83 | Saved 2025-04-05 06:44:26 | [maml_trainer] epoch #83 | Time 137110.32 s 2025-04-05 06:44:26 | [maml_trainer] epoch #83 | EpochTime 1637.17 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.3925 Average/AverageReturn -63.3221 Average/Iteration 83 Average/MaxReturn -44.7495 Average/MinReturn -138.36 Average/NumEpisodes 120 Average/StdReturn 14.2104 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96405 GaussianMLPPolicy/KLAfter 0.00412848 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.68309e-05 GaussianMLPPolicy/LossBefore -3.97364e-10 GaussianMLPPolicy/dLoss 9.68305e-05 Iteration 83 MetaTest/Average/AverageDiscountedReturn -64.4062 MetaTest/Average/AverageReturn -64.4062 MetaTest/Average/Iteration 83 MetaTest/Average/MaxReturn -44.5491 MetaTest/Average/MinReturn -153.627 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.4197 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -64.4062 MetaTest/__unnamed_task__/AverageReturn -64.4062 MetaTest/__unnamed_task__/Iteration 83 MetaTest/__unnamed_task__/MaxReturn -44.5491 MetaTest/__unnamed_task__/MinReturn -153.627 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.4197 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.032e+06 __unnamed_task__/AverageDiscountedReturn -32.3925 __unnamed_task__/AverageReturn -63.3221 __unnamed_task__/Iteration 83 __unnamed_task__/MaxReturn -44.7495 __unnamed_task__/MinReturn -138.36 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.2104 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 07:07:38 | [maml_trainer] epoch #84 | Sampling for adapation and meta-testing... 2025-04-05 07:11:33 | [maml_trainer] epoch #84 | Finished meta-testing... 2025-04-05 07:11:33 | [maml_trainer] epoch #84 | Saving snapshot... 2025-04-05 07:11:55 | [maml_trainer] epoch #84 | Saved 2025-04-05 07:11:55 | [maml_trainer] epoch #84 | Time 138758.99 s 2025-04-05 07:11:55 | [maml_trainer] epoch #84 | EpochTime 1648.67 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -31.1109 Average/AverageReturn -60.337 Average/Iteration 84 Average/MaxReturn -43.5316 Average/MinReturn -172.526 Average/NumEpisodes 120 Average/StdReturn 16.5557 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96438 GaussianMLPPolicy/KLAfter 0.00359852 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.89702e-05 GaussianMLPPolicy/LossBefore -1.11262e-09 GaussianMLPPolicy/dLoss -2.89714e-05 Iteration 84 MetaTest/Average/AverageDiscountedReturn -60.0777 MetaTest/Average/AverageReturn -60.0777 MetaTest/Average/Iteration 84 MetaTest/Average/MaxReturn -48.4434 MetaTest/Average/MinReturn -90.6847 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.6443 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -60.0777 MetaTest/__unnamed_task__/AverageReturn -60.0777 MetaTest/__unnamed_task__/Iteration 84 MetaTest/__unnamed_task__/MaxReturn -48.4434 MetaTest/__unnamed_task__/MinReturn -90.6847 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.6443 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.08e+06 __unnamed_task__/AverageDiscountedReturn -31.1109 __unnamed_task__/AverageReturn -60.337 __unnamed_task__/Iteration 84 __unnamed_task__/MaxReturn -43.5316 __unnamed_task__/MinReturn -172.526 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 16.5557 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 07:35:19 | [maml_trainer] epoch #85 | Sampling for adapation and meta-testing... 2025-04-05 07:39:09 | [maml_trainer] epoch #85 | Finished meta-testing... 2025-04-05 07:39:09 | [maml_trainer] epoch #85 | Saving snapshot... 2025-04-05 07:39:29 | [maml_trainer] epoch #85 | Saved 2025-04-05 07:39:29 | [maml_trainer] epoch #85 | Time 140413.68 s 2025-04-05 07:39:29 | [maml_trainer] epoch #85 | EpochTime 1654.68 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -31.218 Average/AverageReturn -61.2313 Average/Iteration 85 Average/MaxReturn -44.7326 Average/MinReturn -175.881 Average/NumEpisodes 120 Average/StdReturn 19.1219 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96594 GaussianMLPPolicy/KLAfter 0.00276423 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.10314e-05 GaussianMLPPolicy/LossBefore -5.86112e-09 GaussianMLPPolicy/dLoss 2.10256e-05 Iteration 85 MetaTest/Average/AverageDiscountedReturn -64.678 MetaTest/Average/AverageReturn -64.678 MetaTest/Average/Iteration 85 MetaTest/Average/MaxReturn -45.6668 MetaTest/Average/MinReturn -189.979 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 30.2242 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -64.678 MetaTest/__unnamed_task__/AverageReturn -64.678 MetaTest/__unnamed_task__/Iteration 85 MetaTest/__unnamed_task__/MaxReturn -45.6668 MetaTest/__unnamed_task__/MinReturn -189.979 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 30.2242 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.128e+06 __unnamed_task__/AverageDiscountedReturn -31.218 __unnamed_task__/AverageReturn -61.2313 __unnamed_task__/Iteration 85 __unnamed_task__/MaxReturn -44.7326 __unnamed_task__/MinReturn -175.881 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 19.1219 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 08:02:44 | [maml_trainer] epoch #86 | Sampling for adapation and meta-testing... 2025-04-05 08:06:39 | [maml_trainer] epoch #86 | Finished meta-testing... 2025-04-05 08:06:39 | [maml_trainer] epoch #86 | Saving snapshot... 2025-04-05 08:07:00 | [maml_trainer] epoch #86 | Saved 2025-04-05 08:07:00 | [maml_trainer] epoch #86 | Time 142064.10 s 2025-04-05 08:07:00 | [maml_trainer] epoch #86 | EpochTime 1650.42 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -30.4549 Average/AverageReturn -57.8577 Average/Iteration 86 Average/MaxReturn -43.7126 Average/MinReturn -108.535 Average/NumEpisodes 120 Average/StdReturn 10.1488 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96649 GaussianMLPPolicy/KLAfter 0.00285404 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.00010535 GaussianMLPPolicy/LossBefore 1.56959e-08 GaussianMLPPolicy/dLoss -0.000105334 Iteration 86 MetaTest/Average/AverageDiscountedReturn -60.9536 MetaTest/Average/AverageReturn -60.9536 MetaTest/Average/Iteration 86 MetaTest/Average/MaxReturn -46.8809 MetaTest/Average/MinReturn -111.45 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.0858 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -60.9536 MetaTest/__unnamed_task__/AverageReturn -60.9536 MetaTest/__unnamed_task__/Iteration 86 MetaTest/__unnamed_task__/MaxReturn -46.8809 MetaTest/__unnamed_task__/MinReturn -111.45 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.0858 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.176e+06 __unnamed_task__/AverageDiscountedReturn -30.4549 __unnamed_task__/AverageReturn -57.8577 __unnamed_task__/Iteration 86 __unnamed_task__/MaxReturn -43.7126 __unnamed_task__/MinReturn -108.535 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.1488 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 08:30:26 | [maml_trainer] epoch #87 | Sampling for adapation and meta-testing... 2025-04-05 08:34:21 | [maml_trainer] epoch #87 | Finished meta-testing... 2025-04-05 08:34:21 | [maml_trainer] epoch #87 | Saving snapshot... 2025-04-05 08:34:41 | [maml_trainer] epoch #87 | Saved 2025-04-05 08:34:41 | [maml_trainer] epoch #87 | Time 143725.93 s 2025-04-05 08:34:41 | [maml_trainer] epoch #87 | EpochTime 1661.84 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -30.6752 Average/AverageReturn -59.3497 Average/Iteration 87 Average/MaxReturn -42.4099 Average/MinReturn -137.675 Average/NumEpisodes 120 Average/StdReturn 13.4154 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96587 GaussianMLPPolicy/KLAfter 0.00259497 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.59603e-05 GaussianMLPPolicy/LossBefore 7.70887e-09 GaussianMLPPolicy/dLoss 5.5968e-05 Iteration 87 MetaTest/Average/AverageDiscountedReturn -57.1425 MetaTest/Average/AverageReturn -57.1425 MetaTest/Average/Iteration 87 MetaTest/Average/MaxReturn -45.8172 MetaTest/Average/MinReturn -86.2133 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.8958 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -57.1425 MetaTest/__unnamed_task__/AverageReturn -57.1425 MetaTest/__unnamed_task__/Iteration 87 MetaTest/__unnamed_task__/MaxReturn -45.8172 MetaTest/__unnamed_task__/MinReturn -86.2133 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.8958 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.224e+06 __unnamed_task__/AverageDiscountedReturn -30.6752 __unnamed_task__/AverageReturn -59.3497 __unnamed_task__/Iteration 87 __unnamed_task__/MaxReturn -42.4099 __unnamed_task__/MinReturn -137.675 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 13.4154 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 08:57:50 | [maml_trainer] epoch #88 | Sampling for adapation and meta-testing... 2025-04-05 09:01:40 | [maml_trainer] epoch #88 | Finished meta-testing... 2025-04-05 09:01:40 | [maml_trainer] epoch #88 | Saving snapshot... 2025-04-05 09:02:01 | [maml_trainer] epoch #88 | Saved 2025-04-05 09:02:01 | [maml_trainer] epoch #88 | Time 145365.33 s 2025-04-05 09:02:01 | [maml_trainer] epoch #88 | EpochTime 1639.39 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -31.0802 Average/AverageReturn -63.3815 Average/Iteration 88 Average/MaxReturn -42.0779 Average/MinReturn -193.346 Average/NumEpisodes 120 Average/StdReturn 26.5486 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96613 GaussianMLPPolicy/KLAfter 0.00247862 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.37373e-05 GaussianMLPPolicy/LossBefore -2.70208e-09 GaussianMLPPolicy/dLoss 2.37346e-05 Iteration 88 MetaTest/Average/AverageDiscountedReturn -63.7654 MetaTest/Average/AverageReturn -63.7654 MetaTest/Average/Iteration 88 MetaTest/Average/MaxReturn -47.0283 MetaTest/Average/MinReturn -164.196 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.6234 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -63.7654 MetaTest/__unnamed_task__/AverageReturn -63.7654 MetaTest/__unnamed_task__/Iteration 88 MetaTest/__unnamed_task__/MaxReturn -47.0283 MetaTest/__unnamed_task__/MinReturn -164.196 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.6234 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.272e+06 __unnamed_task__/AverageDiscountedReturn -31.0802 __unnamed_task__/AverageReturn -63.3815 __unnamed_task__/Iteration 88 __unnamed_task__/MaxReturn -42.0779 __unnamed_task__/MinReturn -193.346 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 26.5486 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 09:25:11 | [maml_trainer] epoch #89 | Sampling for adapation and meta-testing... 2025-04-05 09:29:03 | [maml_trainer] epoch #89 | Finished meta-testing... 2025-04-05 09:29:03 | [maml_trainer] epoch #89 | Saving snapshot... 2025-04-05 09:29:24 | [maml_trainer] epoch #89 | Saved 2025-04-05 09:29:24 | [maml_trainer] epoch #89 | Time 147008.24 s 2025-04-05 09:29:24 | [maml_trainer] epoch #89 | EpochTime 1642.91 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.6101 Average/AverageReturn -58.3364 Average/Iteration 89 Average/MaxReturn -42.9804 Average/MinReturn -190.57 Average/NumEpisodes 120 Average/StdReturn 24.5937 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96451 GaussianMLPPolicy/KLAfter 0.00302948 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.7102e-05 GaussianMLPPolicy/LossBefore -3.50674e-09 GaussianMLPPolicy/dLoss 3.70985e-05 Iteration 89 MetaTest/Average/AverageDiscountedReturn -70.5178 MetaTest/Average/AverageReturn -70.5178 MetaTest/Average/Iteration 89 MetaTest/Average/MaxReturn -46.3977 MetaTest/Average/MinReturn -189.238 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 39.4415 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -70.5178 MetaTest/__unnamed_task__/AverageReturn -70.5178 MetaTest/__unnamed_task__/Iteration 89 MetaTest/__unnamed_task__/MaxReturn -46.3977 MetaTest/__unnamed_task__/MinReturn -189.238 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 39.4415 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.32e+06 __unnamed_task__/AverageDiscountedReturn -29.6101 __unnamed_task__/AverageReturn -58.3364 __unnamed_task__/Iteration 89 __unnamed_task__/MaxReturn -42.9804 __unnamed_task__/MinReturn -190.57 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 24.5937 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 09:52:53 | [maml_trainer] epoch #90 | Sampling for adapation and meta-testing... 2025-04-05 09:56:49 | [maml_trainer] epoch #90 | Finished meta-testing... 2025-04-05 09:56:49 | [maml_trainer] epoch #90 | Saving snapshot... 2025-04-05 09:57:11 | [maml_trainer] epoch #90 | Saved 2025-04-05 09:57:11 | [maml_trainer] epoch #90 | Time 148675.20 s 2025-04-05 09:57:11 | [maml_trainer] epoch #90 | EpochTime 1666.95 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.8822 Average/AverageReturn -59.5636 Average/Iteration 90 Average/MaxReturn -42.4041 Average/MinReturn -180.245 Average/NumEpisodes 120 Average/StdReturn 23.6192 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96298 GaussianMLPPolicy/KLAfter 0.00485447 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.81109e-05 GaussianMLPPolicy/LossBefore 4.09285e-09 GaussianMLPPolicy/dLoss 1.8115e-05 Iteration 90 MetaTest/Average/AverageDiscountedReturn -50.3863 MetaTest/Average/AverageReturn -50.3863 MetaTest/Average/Iteration 90 MetaTest/Average/MaxReturn -40.4488 MetaTest/Average/MinReturn -66.5881 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.8584 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.3863 MetaTest/__unnamed_task__/AverageReturn -50.3863 MetaTest/__unnamed_task__/Iteration 90 MetaTest/__unnamed_task__/MaxReturn -40.4488 MetaTest/__unnamed_task__/MinReturn -66.5881 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.8584 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.368e+06 __unnamed_task__/AverageDiscountedReturn -29.8822 __unnamed_task__/AverageReturn -59.5636 __unnamed_task__/Iteration 90 __unnamed_task__/MaxReturn -42.4041 __unnamed_task__/MinReturn -180.245 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 23.6192 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 10:21:11 | [maml_trainer] epoch #91 | Sampling for adapation and meta-testing... 2025-04-05 10:25:06 | [maml_trainer] epoch #91 | Finished meta-testing... 2025-04-05 10:25:06 | [maml_trainer] epoch #91 | Saving snapshot... 2025-04-05 10:25:27 | [maml_trainer] epoch #91 | Saved 2025-04-05 10:25:27 | [maml_trainer] epoch #91 | Time 150371.48 s 2025-04-05 10:25:27 | [maml_trainer] epoch #91 | EpochTime 1696.28 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.6358 Average/AverageReturn -57.6889 Average/Iteration 91 Average/MaxReturn -41.064 Average/MinReturn -171.374 Average/NumEpisodes 120 Average/StdReturn 20.5468 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96158 GaussianMLPPolicy/KLAfter 0.00399884 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.80113e-05 GaussianMLPPolicy/LossBefore -3.27826e-09 GaussianMLPPolicy/dLoss 3.8008e-05 Iteration 91 MetaTest/Average/AverageDiscountedReturn -58.4129 MetaTest/Average/AverageReturn -58.4129 MetaTest/Average/Iteration 91 MetaTest/Average/MaxReturn -42.5019 MetaTest/Average/MinReturn -182.189 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 29.5125 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -58.4129 MetaTest/__unnamed_task__/AverageReturn -58.4129 MetaTest/__unnamed_task__/Iteration 91 MetaTest/__unnamed_task__/MaxReturn -42.5019 MetaTest/__unnamed_task__/MinReturn -182.189 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 29.5125 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.416e+06 __unnamed_task__/AverageDiscountedReturn -29.6358 __unnamed_task__/AverageReturn -57.6889 __unnamed_task__/Iteration 91 __unnamed_task__/MaxReturn -41.064 __unnamed_task__/MinReturn -171.374 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 20.5468 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 10:48:56 | [maml_trainer] epoch #92 | Sampling for adapation and meta-testing... 2025-04-05 10:52:49 | [maml_trainer] epoch #92 | Finished meta-testing... 2025-04-05 10:52:49 | [maml_trainer] epoch #92 | Saving snapshot... 2025-04-05 10:53:10 | [maml_trainer] epoch #92 | Saved 2025-04-05 10:53:10 | [maml_trainer] epoch #92 | Time 152034.19 s 2025-04-05 10:53:10 | [maml_trainer] epoch #92 | EpochTime 1662.71 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.1623 Average/AverageReturn -56.9068 Average/Iteration 92 Average/MaxReturn -41.7085 Average/MinReturn -178.415 Average/NumEpisodes 120 Average/StdReturn 22.0849 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96133 GaussianMLPPolicy/KLAfter 0.00440087 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.23922e-05 GaussianMLPPolicy/LossBefore -3.27826e-09 GaussianMLPPolicy/dLoss -1.23954e-05 Iteration 92 MetaTest/Average/AverageDiscountedReturn -55.6519 MetaTest/Average/AverageReturn -55.6519 MetaTest/Average/Iteration 92 MetaTest/Average/MaxReturn -43.0697 MetaTest/Average/MinReturn -88.4887 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.2443 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.6519 MetaTest/__unnamed_task__/AverageReturn -55.6519 MetaTest/__unnamed_task__/Iteration 92 MetaTest/__unnamed_task__/MaxReturn -43.0697 MetaTest/__unnamed_task__/MinReturn -88.4887 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.2443 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.464e+06 __unnamed_task__/AverageDiscountedReturn -29.1623 __unnamed_task__/AverageReturn -56.9068 __unnamed_task__/Iteration 92 __unnamed_task__/MaxReturn -41.7085 __unnamed_task__/MinReturn -178.415 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 22.0849 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 11:16:30 | [maml_trainer] epoch #93 | Sampling for adapation and meta-testing... 2025-04-05 11:20:26 | [maml_trainer] epoch #93 | Finished meta-testing... 2025-04-05 11:20:26 | [maml_trainer] epoch #93 | Saving snapshot... 2025-04-05 11:20:47 | [maml_trainer] epoch #93 | Saved 2025-04-05 11:20:47 | [maml_trainer] epoch #93 | Time 153691.55 s 2025-04-05 11:20:47 | [maml_trainer] epoch #93 | EpochTime 1657.36 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.4969 Average/AverageReturn -53.2934 Average/Iteration 93 Average/MaxReturn -41.7825 Average/MinReturn -94.8963 Average/NumEpisodes 120 Average/StdReturn 8.98511 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.96036 GaussianMLPPolicy/KLAfter 0.00247976 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.21772e-05 GaussianMLPPolicy/LossBefore 2.74181e-09 GaussianMLPPolicy/dLoss -2.21744e-05 Iteration 93 MetaTest/Average/AverageDiscountedReturn -55.3694 MetaTest/Average/AverageReturn -55.3694 MetaTest/Average/Iteration 93 MetaTest/Average/MaxReturn -46.6118 MetaTest/Average/MinReturn -135.994 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.9397 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.3694 MetaTest/__unnamed_task__/AverageReturn -55.3694 MetaTest/__unnamed_task__/Iteration 93 MetaTest/__unnamed_task__/MaxReturn -46.6118 MetaTest/__unnamed_task__/MinReturn -135.994 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.9397 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.512e+06 __unnamed_task__/AverageDiscountedReturn -28.4969 __unnamed_task__/AverageReturn -53.2934 __unnamed_task__/Iteration 93 __unnamed_task__/MaxReturn -41.7825 __unnamed_task__/MinReturn -94.8963 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.98511 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 11:44:22 | [maml_trainer] epoch #94 | Sampling for adapation and meta-testing... 2025-04-05 11:48:17 | [maml_trainer] epoch #94 | Finished meta-testing... 2025-04-05 11:48:17 | [maml_trainer] epoch #94 | Saving snapshot... 2025-04-05 11:48:38 | [maml_trainer] epoch #94 | Saved 2025-04-05 11:48:38 | [maml_trainer] epoch #94 | Time 155362.62 s 2025-04-05 11:48:38 | [maml_trainer] epoch #94 | EpochTime 1671.06 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.8227 Average/AverageReturn -54.5293 Average/Iteration 94 Average/MaxReturn -43.1441 Average/MinReturn -144.361 Average/NumEpisodes 120 Average/StdReturn 12.5177 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95917 GaussianMLPPolicy/KLAfter 0.00254408 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.97066e-05 GaussianMLPPolicy/LossBefore 2.78155e-09 GaussianMLPPolicy/dLoss 3.97094e-05 Iteration 94 MetaTest/Average/AverageDiscountedReturn -56.2704 MetaTest/Average/AverageReturn -56.2704 MetaTest/Average/Iteration 94 MetaTest/Average/MaxReturn -47.3517 MetaTest/Average/MinReturn -117.499 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.9112 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -56.2704 MetaTest/__unnamed_task__/AverageReturn -56.2704 MetaTest/__unnamed_task__/Iteration 94 MetaTest/__unnamed_task__/MaxReturn -47.3517 MetaTest/__unnamed_task__/MinReturn -117.499 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.9112 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.56e+06 __unnamed_task__/AverageDiscountedReturn -28.8227 __unnamed_task__/AverageReturn -54.5293 __unnamed_task__/Iteration 94 __unnamed_task__/MaxReturn -43.1441 __unnamed_task__/MinReturn -144.361 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.5177 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 12:12:11 | [maml_trainer] epoch #95 | Sampling for adapation and meta-testing... 2025-04-05 12:16:12 | [maml_trainer] epoch #95 | Finished meta-testing... 2025-04-05 12:16:12 | [maml_trainer] epoch #95 | Saving snapshot... 2025-04-05 12:16:33 | [maml_trainer] epoch #95 | Saved 2025-04-05 12:16:33 | [maml_trainer] epoch #95 | Time 157037.41 s 2025-04-05 12:16:33 | [maml_trainer] epoch #95 | EpochTime 1674.79 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.6141 Average/AverageReturn -53.5099 Average/Iteration 95 Average/MaxReturn -41.1638 Average/MinReturn -125.74 Average/NumEpisodes 120 Average/StdReturn 10.6697 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95821 GaussianMLPPolicy/KLAfter 0.00353217 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.54413e-05 GaussianMLPPolicy/LossBefore 5.126e-09 GaussianMLPPolicy/dLoss 4.54465e-05 Iteration 95 MetaTest/Average/AverageDiscountedReturn -50.2972 MetaTest/Average/AverageReturn -50.2972 MetaTest/Average/Iteration 95 MetaTest/Average/MaxReturn -42.426 MetaTest/Average/MinReturn -65.3995 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.22778 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.2972 MetaTest/__unnamed_task__/AverageReturn -50.2972 MetaTest/__unnamed_task__/Iteration 95 MetaTest/__unnamed_task__/MaxReturn -42.426 MetaTest/__unnamed_task__/MinReturn -65.3995 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.22778 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.608e+06 __unnamed_task__/AverageDiscountedReturn -28.6141 __unnamed_task__/AverageReturn -53.5099 __unnamed_task__/Iteration 95 __unnamed_task__/MaxReturn -41.1638 __unnamed_task__/MinReturn -125.74 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.6697 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 12:41:08 | [maml_trainer] epoch #96 | Sampling for adapation and meta-testing... 2025-04-05 12:45:19 | [maml_trainer] epoch #96 | Finished meta-testing... 2025-04-05 12:45:19 | [maml_trainer] epoch #96 | Saving snapshot... 2025-04-05 12:45:42 | [maml_trainer] epoch #96 | Saved 2025-04-05 12:45:42 | [maml_trainer] epoch #96 | Time 158786.44 s 2025-04-05 12:45:42 | [maml_trainer] epoch #96 | EpochTime 1749.03 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.1625 Average/AverageReturn -53.4405 Average/Iteration 96 Average/MaxReturn -43.3048 Average/MinReturn -157.223 Average/NumEpisodes 120 Average/StdReturn 14.5795 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95758 GaussianMLPPolicy/KLAfter 0.00252138 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000104698 GaussianMLPPolicy/LossBefore 7.2519e-09 GaussianMLPPolicy/dLoss 0.000104706 Iteration 96 MetaTest/Average/AverageDiscountedReturn -57.0998 MetaTest/Average/AverageReturn -57.0998 MetaTest/Average/Iteration 96 MetaTest/Average/MaxReturn -46.0531 MetaTest/Average/MinReturn -118.561 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.276 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -57.0998 MetaTest/__unnamed_task__/AverageReturn -57.0998 MetaTest/__unnamed_task__/Iteration 96 MetaTest/__unnamed_task__/MaxReturn -46.0531 MetaTest/__unnamed_task__/MinReturn -118.561 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.276 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.656e+06 __unnamed_task__/AverageDiscountedReturn -28.1625 __unnamed_task__/AverageReturn -53.4405 __unnamed_task__/Iteration 96 __unnamed_task__/MaxReturn -43.3048 __unnamed_task__/MinReturn -157.223 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.5795 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 13:09:46 | [maml_trainer] epoch #97 | Sampling for adapation and meta-testing... 2025-04-05 13:13:43 | [maml_trainer] epoch #97 | Finished meta-testing... 2025-04-05 13:13:43 | [maml_trainer] epoch #97 | Saving snapshot... 2025-04-05 13:14:04 | [maml_trainer] epoch #97 | Saved 2025-04-05 13:14:04 | [maml_trainer] epoch #97 | Time 160488.21 s 2025-04-05 13:14:04 | [maml_trainer] epoch #97 | EpochTime 1701.77 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.4171 Average/AverageReturn -52.0575 Average/Iteration 97 Average/MaxReturn -43.2805 Average/MinReturn -70.0271 Average/NumEpisodes 120 Average/StdReturn 5.01085 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95779 GaussianMLPPolicy/KLAfter 0.00252363 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.41512e-05 GaussianMLPPolicy/LossBefore 1.02123e-08 GaussianMLPPolicy/dLoss 2.41615e-05 Iteration 97 MetaTest/Average/AverageDiscountedReturn -52.619 MetaTest/Average/AverageReturn -52.619 MetaTest/Average/Iteration 97 MetaTest/Average/MaxReturn -44.4421 MetaTest/Average/MinReturn -65.8042 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.61183 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.619 MetaTest/__unnamed_task__/AverageReturn -52.619 MetaTest/__unnamed_task__/Iteration 97 MetaTest/__unnamed_task__/MaxReturn -44.4421 MetaTest/__unnamed_task__/MinReturn -65.8042 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.61183 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.704e+06 __unnamed_task__/AverageDiscountedReturn -28.4171 __unnamed_task__/AverageReturn -52.0575 __unnamed_task__/Iteration 97 __unnamed_task__/MaxReturn -43.2805 __unnamed_task__/MinReturn -70.0271 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.01085 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 13:37:50 | [maml_trainer] epoch #98 | Sampling for adapation and meta-testing... 2025-04-05 13:41:43 | [maml_trainer] epoch #98 | Finished meta-testing... 2025-04-05 13:41:43 | [maml_trainer] epoch #98 | Saving snapshot... 2025-04-05 13:42:04 | [maml_trainer] epoch #98 | Saved 2025-04-05 13:42:04 | [maml_trainer] epoch #98 | Time 162168.70 s 2025-04-05 13:42:04 | [maml_trainer] epoch #98 | EpochTime 1680.49 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.194 Average/AverageReturn -52.1139 Average/Iteration 98 Average/MaxReturn -42.1884 Average/MinReturn -116.71 Average/NumEpisodes 120 Average/StdReturn 7.47425 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95696 GaussianMLPPolicy/KLAfter 0.00261446 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.78363e-05 GaussianMLPPolicy/LossBefore -1.15633e-08 GaussianMLPPolicy/dLoss 1.78247e-05 Iteration 98 MetaTest/Average/AverageDiscountedReturn -55.3939 MetaTest/Average/AverageReturn -55.3939 MetaTest/Average/Iteration 98 MetaTest/Average/MaxReturn -43.9058 MetaTest/Average/MinReturn -130.889 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.0222 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.3939 MetaTest/__unnamed_task__/AverageReturn -55.3939 MetaTest/__unnamed_task__/Iteration 98 MetaTest/__unnamed_task__/MaxReturn -43.9058 MetaTest/__unnamed_task__/MinReturn -130.889 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.0222 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.752e+06 __unnamed_task__/AverageDiscountedReturn -28.194 __unnamed_task__/AverageReturn -52.1139 __unnamed_task__/Iteration 98 __unnamed_task__/MaxReturn -42.1884 __unnamed_task__/MinReturn -116.71 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.47425 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 14:05:21 | [maml_trainer] epoch #99 | Sampling for adapation and meta-testing... 2025-04-05 14:09:22 | [maml_trainer] epoch #99 | Finished meta-testing... 2025-04-05 14:09:22 | [maml_trainer] epoch #99 | Saving snapshot... 2025-04-05 14:09:43 | [maml_trainer] epoch #99 | Saved 2025-04-05 14:09:43 | [maml_trainer] epoch #99 | Time 163827.21 s 2025-04-05 14:09:43 | [maml_trainer] epoch #99 | EpochTime 1658.50 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.0189 Average/AverageReturn -51.6878 Average/Iteration 99 Average/MaxReturn -42.257 Average/MinReturn -85.9253 Average/NumEpisodes 120 Average/StdReturn 6.03294 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95697 GaussianMLPPolicy/KLAfter 0.0024304 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.85104e-06 GaussianMLPPolicy/LossBefore -1.07288e-08 GaussianMLPPolicy/dLoss 7.84032e-06 Iteration 99 MetaTest/Average/AverageDiscountedReturn -52.6126 MetaTest/Average/AverageReturn -52.6126 MetaTest/Average/Iteration 99 MetaTest/Average/MaxReturn -44.7489 MetaTest/Average/MinReturn -87.4205 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.79591 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6126 MetaTest/__unnamed_task__/AverageReturn -52.6126 MetaTest/__unnamed_task__/Iteration 99 MetaTest/__unnamed_task__/MaxReturn -44.7489 MetaTest/__unnamed_task__/MinReturn -87.4205 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.79591 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.8e+06 __unnamed_task__/AverageDiscountedReturn -28.0189 __unnamed_task__/AverageReturn -51.6878 __unnamed_task__/Iteration 99 __unnamed_task__/MaxReturn -42.257 __unnamed_task__/MinReturn -85.9253 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.03294 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 14:33:06 | [maml_trainer] epoch #100 | Sampling for adapation and meta-testing... 2025-04-05 14:37:00 | [maml_trainer] epoch #100 | Finished meta-testing... 2025-04-05 14:37:00 | [maml_trainer] epoch #100 | Saving snapshot... 2025-04-05 14:37:21 | [maml_trainer] epoch #100 | Saved 2025-04-05 14:37:21 | [maml_trainer] epoch #100 | Time 165485.83 s 2025-04-05 14:37:21 | [maml_trainer] epoch #100 | EpochTime 1658.62 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.8419 Average/AverageReturn -55.609 Average/Iteration 100 Average/MaxReturn -42.3302 Average/MinReturn -179.318 Average/NumEpisodes 120 Average/StdReturn 21.1128 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.95596 GaussianMLPPolicy/KLAfter 0.00154048 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.68168e-05 GaussianMLPPolicy/LossBefore 6.41743e-09 GaussianMLPPolicy/dLoss -2.68103e-05 Iteration 100 MetaTest/Average/AverageDiscountedReturn -53.6682 MetaTest/Average/AverageReturn -53.6682 MetaTest/Average/Iteration 100 MetaTest/Average/MaxReturn -44.0246 MetaTest/Average/MinReturn -77.3252 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.40881 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.6682 MetaTest/__unnamed_task__/AverageReturn -53.6682 MetaTest/__unnamed_task__/Iteration 100 MetaTest/__unnamed_task__/MaxReturn -44.0246 MetaTest/__unnamed_task__/MinReturn -77.3252 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.40881 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.848e+06 __unnamed_task__/AverageDiscountedReturn -28.8419 __unnamed_task__/AverageReturn -55.609 __unnamed_task__/Iteration 100 __unnamed_task__/MaxReturn -42.3302 __unnamed_task__/MinReturn -179.318 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 21.1128 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 15:00:59 | [maml_trainer] epoch #101 | Sampling for adapation and meta-testing... 2025-04-05 15:04:54 | [maml_trainer] epoch #101 | Finished meta-testing... 2025-04-05 15:04:54 | [maml_trainer] epoch #101 | Saving snapshot... 2025-04-05 15:05:15 | [maml_trainer] epoch #101 | Saved 2025-04-05 15:05:15 | [maml_trainer] epoch #101 | Time 167159.51 s 2025-04-05 15:05:15 | [maml_trainer] epoch #101 | EpochTime 1673.68 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.1193 Average/AverageReturn -52.7379 Average/Iteration 101 Average/MaxReturn 261.574 Average/MinReturn -177.699 Average/NumEpisodes 120 Average/StdReturn 34.7779 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.9526 GaussianMLPPolicy/KLAfter 0.00266528 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.1448e-06 GaussianMLPPolicy/LossBefore 9.93411e-10 GaussianMLPPolicy/dLoss 1.1458e-06 Iteration 101 MetaTest/Average/AverageDiscountedReturn -50.6922 MetaTest/Average/AverageReturn -50.6922 MetaTest/Average/Iteration 101 MetaTest/Average/MaxReturn -39.3108 MetaTest/Average/MinReturn -72.2192 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.81403 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.6922 MetaTest/__unnamed_task__/AverageReturn -50.6922 MetaTest/__unnamed_task__/Iteration 101 MetaTest/__unnamed_task__/MaxReturn -39.3108 MetaTest/__unnamed_task__/MinReturn -72.2192 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.81403 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.896e+06 __unnamed_task__/AverageDiscountedReturn -28.1193 __unnamed_task__/AverageReturn -52.7379 __unnamed_task__/Iteration 101 __unnamed_task__/MaxReturn 261.574 __unnamed_task__/MinReturn -177.699 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 34.7779 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 15:28:47 | [maml_trainer] epoch #102 | Sampling for adapation and meta-testing... 2025-04-05 15:32:41 | [maml_trainer] epoch #102 | Finished meta-testing... 2025-04-05 15:32:41 | [maml_trainer] epoch #102 | Saving snapshot... 2025-04-05 15:33:02 | [maml_trainer] epoch #102 | Saved 2025-04-05 15:33:02 | [maml_trainer] epoch #102 | Time 168826.56 s 2025-04-05 15:33:02 | [maml_trainer] epoch #102 | EpochTime 1667.05 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.9285 Average/AverageReturn -55.2858 Average/Iteration 102 Average/MaxReturn -42.3545 Average/MinReturn -164.804 Average/NumEpisodes 120 Average/StdReturn 19.6098 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94872 GaussianMLPPolicy/KLAfter 0.00289561 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.64122e-05 GaussianMLPPolicy/LossBefore 8.42412e-09 GaussianMLPPolicy/dLoss 2.64206e-05 Iteration 102 MetaTest/Average/AverageDiscountedReturn -53.0887 MetaTest/Average/AverageReturn -53.0887 MetaTest/Average/Iteration 102 MetaTest/Average/MaxReturn -43.3693 MetaTest/Average/MinReturn -102.614 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.3653 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.0887 MetaTest/__unnamed_task__/AverageReturn -53.0887 MetaTest/__unnamed_task__/Iteration 102 MetaTest/__unnamed_task__/MaxReturn -43.3693 MetaTest/__unnamed_task__/MinReturn -102.614 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.3653 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.944e+06 __unnamed_task__/AverageDiscountedReturn -28.9285 __unnamed_task__/AverageReturn -55.2858 __unnamed_task__/Iteration 102 __unnamed_task__/MaxReturn -42.3545 __unnamed_task__/MinReturn -164.804 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 19.6098 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 15:56:42 | [maml_trainer] epoch #103 | Sampling for adapation and meta-testing... 2025-04-05 16:00:43 | [maml_trainer] epoch #103 | Finished meta-testing... 2025-04-05 16:00:43 | [maml_trainer] epoch #103 | Saving snapshot... 2025-04-05 16:01:05 | [maml_trainer] epoch #103 | Saved 2025-04-05 16:01:05 | [maml_trainer] epoch #103 | Time 170509.65 s 2025-04-05 16:01:05 | [maml_trainer] epoch #103 | EpochTime 1683.09 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.2038 Average/AverageReturn -51.9189 Average/Iteration 103 Average/MaxReturn -39.4598 Average/MinReturn -108.832 Average/NumEpisodes 120 Average/StdReturn 7.40233 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.946 GaussianMLPPolicy/KLAfter 0.00264905 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.79491e-05 GaussianMLPPolicy/LossBefore -7.82808e-09 GaussianMLPPolicy/dLoss -3.7957e-05 Iteration 103 MetaTest/Average/AverageDiscountedReturn -53.3658 MetaTest/Average/AverageReturn -53.3658 MetaTest/Average/Iteration 103 MetaTest/Average/MaxReturn -44.849 MetaTest/Average/MinReturn -63.2012 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.67582 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.3658 MetaTest/__unnamed_task__/AverageReturn -53.3658 MetaTest/__unnamed_task__/Iteration 103 MetaTest/__unnamed_task__/MaxReturn -44.849 MetaTest/__unnamed_task__/MinReturn -63.2012 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.67582 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4.992e+06 __unnamed_task__/AverageDiscountedReturn -28.2038 __unnamed_task__/AverageReturn -51.9189 __unnamed_task__/Iteration 103 __unnamed_task__/MaxReturn -39.4598 __unnamed_task__/MinReturn -108.832 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.40233 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 16:26:05 | [maml_trainer] epoch #104 | Sampling for adapation and meta-testing... 2025-04-05 16:30:11 | [maml_trainer] epoch #104 | Finished meta-testing... 2025-04-05 16:30:11 | [maml_trainer] epoch #104 | Saving snapshot... 2025-04-05 16:30:34 | [maml_trainer] epoch #104 | Saved 2025-04-05 16:30:34 | [maml_trainer] epoch #104 | Time 172278.06 s 2025-04-05 16:30:34 | [maml_trainer] epoch #104 | EpochTime 1768.41 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.5822 Average/AverageReturn -52.5687 Average/Iteration 104 Average/MaxReturn -42.4986 Average/MinReturn -74.8981 Average/NumEpisodes 120 Average/StdReturn 5.50724 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.9436 GaussianMLPPolicy/KLAfter 0.00194529 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.58121e-05 GaussianMLPPolicy/LossBefore 1.48614e-08 GaussianMLPPolicy/dLoss -7.57972e-05 Iteration 104 MetaTest/Average/AverageDiscountedReturn -51.1678 MetaTest/Average/AverageReturn -51.1678 MetaTest/Average/Iteration 104 MetaTest/Average/MaxReturn -45.126 MetaTest/Average/MinReturn -61.7353 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.19287 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.1678 MetaTest/__unnamed_task__/AverageReturn -51.1678 MetaTest/__unnamed_task__/Iteration 104 MetaTest/__unnamed_task__/MaxReturn -45.126 MetaTest/__unnamed_task__/MinReturn -61.7353 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.19287 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.04e+06 __unnamed_task__/AverageDiscountedReturn -28.5822 __unnamed_task__/AverageReturn -52.5687 __unnamed_task__/Iteration 104 __unnamed_task__/MaxReturn -42.4986 __unnamed_task__/MinReturn -74.8981 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.50724 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 16:55:20 | [maml_trainer] epoch #105 | Sampling for adapation and meta-testing... 2025-04-05 16:59:29 | [maml_trainer] epoch #105 | Finished meta-testing... 2025-04-05 16:59:29 | [maml_trainer] epoch #105 | Saving snapshot... 2025-04-05 16:59:52 | [maml_trainer] epoch #105 | Saved 2025-04-05 16:59:52 | [maml_trainer] epoch #105 | Time 174036.52 s 2025-04-05 16:59:52 | [maml_trainer] epoch #105 | EpochTime 1758.45 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.7281 Average/AverageReturn -53.7593 Average/Iteration 105 Average/MaxReturn -42.3685 Average/MinReturn -166.709 Average/NumEpisodes 120 Average/StdReturn 12.2198 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.94061 GaussianMLPPolicy/KLAfter 0.00114982 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.98474e-05 GaussianMLPPolicy/LossBefore -1.49409e-08 GaussianMLPPolicy/dLoss 2.98325e-05 Iteration 105 MetaTest/Average/AverageDiscountedReturn -51.5374 MetaTest/Average/AverageReturn -51.5374 MetaTest/Average/Iteration 105 MetaTest/Average/MaxReturn -44.8026 MetaTest/Average/MinReturn -60.1001 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.48314 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.5374 MetaTest/__unnamed_task__/AverageReturn -51.5374 MetaTest/__unnamed_task__/Iteration 105 MetaTest/__unnamed_task__/MaxReturn -44.8026 MetaTest/__unnamed_task__/MinReturn -60.1001 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.48314 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.088e+06 __unnamed_task__/AverageDiscountedReturn -28.7281 __unnamed_task__/AverageReturn -53.7593 __unnamed_task__/Iteration 105 __unnamed_task__/MaxReturn -42.3685 __unnamed_task__/MinReturn -166.709 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.2198 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 17:24:42 | [maml_trainer] epoch #106 | Sampling for adapation and meta-testing... 2025-04-05 17:28:54 | [maml_trainer] epoch #106 | Finished meta-testing... 2025-04-05 17:28:54 | [maml_trainer] epoch #106 | Saving snapshot... 2025-04-05 17:29:16 | [maml_trainer] epoch #106 | Saved 2025-04-05 17:29:16 | [maml_trainer] epoch #106 | Time 175800.91 s 2025-04-05 17:29:16 | [maml_trainer] epoch #106 | EpochTime 1764.39 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.7742 Average/AverageReturn -53.5435 Average/Iteration 106 Average/MaxReturn -41.8378 Average/MinReturn -141.789 Average/NumEpisodes 120 Average/StdReturn 10.0697 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.93676 GaussianMLPPolicy/KLAfter 0.00274419 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000101878 GaussianMLPPolicy/LossBefore -4.33127e-09 GaussianMLPPolicy/dLoss 0.000101874 Iteration 106 MetaTest/Average/AverageDiscountedReturn -52.8986 MetaTest/Average/AverageReturn -52.8986 MetaTest/Average/Iteration 106 MetaTest/Average/MaxReturn -46.1241 MetaTest/Average/MinReturn -69.6802 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.07702 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.8986 MetaTest/__unnamed_task__/AverageReturn -52.8986 MetaTest/__unnamed_task__/Iteration 106 MetaTest/__unnamed_task__/MaxReturn -46.1241 MetaTest/__unnamed_task__/MinReturn -69.6802 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.07702 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.136e+06 __unnamed_task__/AverageDiscountedReturn -28.7742 __unnamed_task__/AverageReturn -53.5435 __unnamed_task__/Iteration 106 __unnamed_task__/MaxReturn -41.8378 __unnamed_task__/MinReturn -141.789 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.0697 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-05 17:54:04 | [maml_trainer] epoch #107 | Sampling for adapation and meta-testing... 2025-04-05 17:58:11 | [maml_trainer] epoch #107 | Finished meta-testing... 2025-04-05 17:58:11 | [maml_trainer] epoch #107 | Saving snapshot... 2025-04-05 17:58:34 | [maml_trainer] epoch #107 | Saved 2025-04-05 17:58:34 | [maml_trainer] epoch #107 | Time 177558.42 s 2025-04-05 17:58:34 | [maml_trainer] epoch #107 | EpochTime 1757.51 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.6588 Average/AverageReturn -52.6623 Average/Iteration 107 Average/MaxReturn -41.6545 Average/MinReturn -70.4714 Average/NumEpisodes 120 Average/StdReturn 5.4978 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.93503 GaussianMLPPolicy/KLAfter 0.00175562 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.06459e-06 GaussianMLPPolicy/LossBefore -1.41064e-08 GaussianMLPPolicy/dLoss -8.07869e-06 Iteration 107 MetaTest/Average/AverageDiscountedReturn -52.2063 MetaTest/Average/AverageReturn -52.2063 MetaTest/Average/Iteration 107 MetaTest/Average/MaxReturn -44.5888 MetaTest/Average/MinReturn -65.5914 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.23935 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2063 MetaTest/__unnamed_task__/AverageReturn -52.2063 MetaTest/__unnamed_task__/Iteration 107 MetaTest/__unnamed_task__/MaxReturn -44.5888 MetaTest/__unnamed_task__/MinReturn -65.5914 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.23935 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.184e+06 __unnamed_task__/AverageDiscountedReturn -28.6588 __unnamed_task__/AverageReturn -52.6623 __unnamed_task__/Iteration 107 __unnamed_task__/MaxReturn -41.6545 __unnamed_task__/MinReturn -70.4714 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.4978 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 18:23:21 | [maml_trainer] epoch #108 | Sampling for adapation and meta-testing... 2025-04-05 18:27:32 | [maml_trainer] epoch #108 | Finished meta-testing... 2025-04-05 18:27:32 | [maml_trainer] epoch #108 | Saving snapshot... 2025-04-05 18:27:55 | [maml_trainer] epoch #108 | Saved 2025-04-05 18:27:55 | [maml_trainer] epoch #108 | Time 179319.37 s 2025-04-05 18:27:55 | [maml_trainer] epoch #108 | EpochTime 1760.95 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.3556 Average/AverageReturn -51.8739 Average/Iteration 108 Average/MaxReturn -43.1072 Average/MinReturn -73.4435 Average/NumEpisodes 120 Average/StdReturn 5.15773 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.93403 GaussianMLPPolicy/KLAfter 0.00222565 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.92374e-05 GaussianMLPPolicy/LossBefore -5.5631e-10 GaussianMLPPolicy/dLoss 1.92368e-05 Iteration 108 MetaTest/Average/AverageDiscountedReturn -53.5447 MetaTest/Average/AverageReturn -53.5447 MetaTest/Average/Iteration 108 MetaTest/Average/MaxReturn -48.3854 MetaTest/Average/MinReturn -66.3425 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.31139 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.5447 MetaTest/__unnamed_task__/AverageReturn -53.5447 MetaTest/__unnamed_task__/Iteration 108 MetaTest/__unnamed_task__/MaxReturn -48.3854 MetaTest/__unnamed_task__/MinReturn -66.3425 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.31139 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.232e+06 __unnamed_task__/AverageDiscountedReturn -28.3556 __unnamed_task__/AverageReturn -51.8739 __unnamed_task__/Iteration 108 __unnamed_task__/MaxReturn -43.1072 __unnamed_task__/MinReturn -73.4435 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.15773 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 18:52:38 | [maml_trainer] epoch #109 | Sampling for adapation and meta-testing... 2025-04-05 18:56:45 | [maml_trainer] epoch #109 | Finished meta-testing... 2025-04-05 18:56:45 | [maml_trainer] epoch #109 | Saving snapshot... 2025-04-05 18:57:08 | [maml_trainer] epoch #109 | Saved 2025-04-05 18:57:08 | [maml_trainer] epoch #109 | Time 181072.27 s 2025-04-05 18:57:08 | [maml_trainer] epoch #109 | EpochTime 1752.89 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.8856 Average/AverageReturn -53.2025 Average/Iteration 109 Average/MaxReturn -43.3215 Average/MinReturn -70.5487 Average/NumEpisodes 120 Average/StdReturn 5.39865 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.9325 GaussianMLPPolicy/KLAfter 0.00421949 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.84231e-06 GaussianMLPPolicy/LossBefore 2.02656e-09 GaussianMLPPolicy/dLoss 3.84434e-06 Iteration 109 MetaTest/Average/AverageDiscountedReturn -51.9575 MetaTest/Average/AverageReturn -51.9575 MetaTest/Average/Iteration 109 MetaTest/Average/MaxReturn -43.9584 MetaTest/Average/MinReturn -65.8749 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.60646 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.9575 MetaTest/__unnamed_task__/AverageReturn -51.9575 MetaTest/__unnamed_task__/Iteration 109 MetaTest/__unnamed_task__/MaxReturn -43.9584 MetaTest/__unnamed_task__/MinReturn -65.8749 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.60646 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.28e+06 __unnamed_task__/AverageDiscountedReturn -28.8856 __unnamed_task__/AverageReturn -53.2025 __unnamed_task__/Iteration 109 __unnamed_task__/MaxReturn -43.3215 __unnamed_task__/MinReturn -70.5487 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.39865 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 19:21:59 | [maml_trainer] epoch #110 | Sampling for adapation and meta-testing... 2025-04-05 19:26:12 | [maml_trainer] epoch #110 | Finished meta-testing... 2025-04-05 19:26:12 | [maml_trainer] epoch #110 | Saving snapshot... 2025-04-05 19:26:35 | [maml_trainer] epoch #110 | Saved 2025-04-05 19:26:35 | [maml_trainer] epoch #110 | Time 182839.42 s 2025-04-05 19:26:35 | [maml_trainer] epoch #110 | EpochTime 1767.15 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.6536 Average/AverageReturn -52.5786 Average/Iteration 110 Average/MaxReturn -41.9928 Average/MinReturn -65.0309 Average/NumEpisodes 120 Average/StdReturn 4.21114 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.9317 GaussianMLPPolicy/KLAfter 0.00342693 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.49458e-05 GaussianMLPPolicy/LossBefore -1.58151e-08 GaussianMLPPolicy/dLoss -3.49617e-05 Iteration 110 MetaTest/Average/AverageDiscountedReturn -53.169 MetaTest/Average/AverageReturn -53.169 MetaTest/Average/Iteration 110 MetaTest/Average/MaxReturn -44.7929 MetaTest/Average/MinReturn -65.4943 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.56463 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.169 MetaTest/__unnamed_task__/AverageReturn -53.169 MetaTest/__unnamed_task__/Iteration 110 MetaTest/__unnamed_task__/MaxReturn -44.7929 MetaTest/__unnamed_task__/MinReturn -65.4943 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.56463 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.328e+06 __unnamed_task__/AverageDiscountedReturn -28.6536 __unnamed_task__/AverageReturn -52.5786 __unnamed_task__/Iteration 110 __unnamed_task__/MaxReturn -41.9928 __unnamed_task__/MinReturn -65.0309 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.21114 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 19:51:35 | [maml_trainer] epoch #111 | Sampling for adapation and meta-testing... 2025-04-05 19:55:48 | [maml_trainer] epoch #111 | Finished meta-testing... 2025-04-05 19:55:48 | [maml_trainer] epoch #111 | Saving snapshot... 2025-04-05 19:56:11 | [maml_trainer] epoch #111 | Saved 2025-04-05 19:56:11 | [maml_trainer] epoch #111 | Time 184615.40 s 2025-04-05 19:56:11 | [maml_trainer] epoch #111 | EpochTime 1775.97 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.7541 Average/AverageReturn -52.8121 Average/Iteration 111 Average/MaxReturn -42.9781 Average/MinReturn -66.7746 Average/NumEpisodes 120 Average/StdReturn 4.7869 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.92895 GaussianMLPPolicy/KLAfter 0.00245505 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.11819e-05 GaussianMLPPolicy/LossBefore 1.5378e-08 GaussianMLPPolicy/dLoss -7.11666e-05 Iteration 111 MetaTest/Average/AverageDiscountedReturn -52.5374 MetaTest/Average/AverageReturn -52.5374 MetaTest/Average/Iteration 111 MetaTest/Average/MaxReturn -45.8182 MetaTest/Average/MinReturn -66.2827 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.41541 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.5374 MetaTest/__unnamed_task__/AverageReturn -52.5374 MetaTest/__unnamed_task__/Iteration 111 MetaTest/__unnamed_task__/MaxReturn -45.8182 MetaTest/__unnamed_task__/MinReturn -66.2827 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.41541 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.376e+06 __unnamed_task__/AverageDiscountedReturn -28.7541 __unnamed_task__/AverageReturn -52.8121 __unnamed_task__/Iteration 111 __unnamed_task__/MaxReturn -42.9781 __unnamed_task__/MinReturn -66.7746 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.7869 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 20:21:02 | [maml_trainer] epoch #112 | Sampling for adapation and meta-testing... 2025-04-05 20:25:09 | [maml_trainer] epoch #112 | Finished meta-testing... 2025-04-05 20:25:09 | [maml_trainer] epoch #112 | Saving snapshot... 2025-04-05 20:25:31 | [maml_trainer] epoch #112 | Saved 2025-04-05 20:25:31 | [maml_trainer] epoch #112 | Time 186375.85 s 2025-04-05 20:25:31 | [maml_trainer] epoch #112 | EpochTime 1760.44 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.0605 Average/AverageReturn -53.8654 Average/Iteration 112 Average/MaxReturn -44.8967 Average/MinReturn -75.1636 Average/NumEpisodes 120 Average/StdReturn 5.50645 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.92621 GaussianMLPPolicy/KLAfter 0.0021751 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.23495e-05 GaussianMLPPolicy/LossBefore 1.44641e-08 GaussianMLPPolicy/dLoss 2.2364e-05 Iteration 112 MetaTest/Average/AverageDiscountedReturn -54.2765 MetaTest/Average/AverageReturn -54.2765 MetaTest/Average/Iteration 112 MetaTest/Average/MaxReturn -45.6425 MetaTest/Average/MinReturn -64.2643 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.93218 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.2765 MetaTest/__unnamed_task__/AverageReturn -54.2765 MetaTest/__unnamed_task__/Iteration 112 MetaTest/__unnamed_task__/MaxReturn -45.6425 MetaTest/__unnamed_task__/MinReturn -64.2643 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.93218 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.424e+06 __unnamed_task__/AverageDiscountedReturn -29.0605 __unnamed_task__/AverageReturn -53.8654 __unnamed_task__/Iteration 112 __unnamed_task__/MaxReturn -44.8967 __unnamed_task__/MinReturn -75.1636 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.50645 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 20:50:29 | [maml_trainer] epoch #113 | Sampling for adapation and meta-testing... 2025-04-05 20:54:34 | [maml_trainer] epoch #113 | Finished meta-testing... 2025-04-05 20:54:34 | [maml_trainer] epoch #113 | Saving snapshot... 2025-04-05 20:54:57 | [maml_trainer] epoch #113 | Saved 2025-04-05 20:54:57 | [maml_trainer] epoch #113 | Time 188141.25 s 2025-04-05 20:54:57 | [maml_trainer] epoch #113 | EpochTime 1765.40 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.898 Average/AverageReturn -53.4271 Average/Iteration 113 Average/MaxReturn -43.4533 Average/MinReturn -70.7429 Average/NumEpisodes 120 Average/StdReturn 5.15235 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.92437 GaussianMLPPolicy/KLAfter 0.00299913 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.40273e-05 GaussianMLPPolicy/LossBefore -1.98682e-08 GaussianMLPPolicy/dLoss -2.40472e-05 Iteration 113 MetaTest/Average/AverageDiscountedReturn -51.7198 MetaTest/Average/AverageReturn -51.7198 MetaTest/Average/Iteration 113 MetaTest/Average/MaxReturn -44.9282 MetaTest/Average/MinReturn -62.358 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.44341 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.7198 MetaTest/__unnamed_task__/AverageReturn -51.7198 MetaTest/__unnamed_task__/Iteration 113 MetaTest/__unnamed_task__/MaxReturn -44.9282 MetaTest/__unnamed_task__/MinReturn -62.358 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.44341 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.472e+06 __unnamed_task__/AverageDiscountedReturn -28.898 __unnamed_task__/AverageReturn -53.4271 __unnamed_task__/Iteration 113 __unnamed_task__/MaxReturn -43.4533 __unnamed_task__/MinReturn -70.7429 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.15235 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 21:19:56 | [maml_trainer] epoch #114 | Sampling for adapation and meta-testing... 2025-04-05 21:24:10 | [maml_trainer] epoch #114 | Finished meta-testing... 2025-04-05 21:24:10 | [maml_trainer] epoch #114 | Saving snapshot... 2025-04-05 21:24:33 | [maml_trainer] epoch #114 | Saved 2025-04-05 21:24:33 | [maml_trainer] epoch #114 | Time 189917.52 s 2025-04-05 21:24:33 | [maml_trainer] epoch #114 | EpochTime 1776.26 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.7785 Average/AverageReturn -53.0215 Average/Iteration 114 Average/MaxReturn -43.3184 Average/MinReturn -79.4892 Average/NumEpisodes 120 Average/StdReturn 5.98586 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.92258 GaussianMLPPolicy/KLAfter 0.00310095 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.57114e-05 GaussianMLPPolicy/LossBefore 2.6226e-08 GaussianMLPPolicy/dLoss -5.56852e-05 Iteration 114 MetaTest/Average/AverageDiscountedReturn -53.3862 MetaTest/Average/AverageReturn -53.3862 MetaTest/Average/Iteration 114 MetaTest/Average/MaxReturn -46.3585 MetaTest/Average/MinReturn -64.6373 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.45998 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.3862 MetaTest/__unnamed_task__/AverageReturn -53.3862 MetaTest/__unnamed_task__/Iteration 114 MetaTest/__unnamed_task__/MaxReturn -46.3585 MetaTest/__unnamed_task__/MinReturn -64.6373 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.45998 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.52e+06 __unnamed_task__/AverageDiscountedReturn -28.7785 __unnamed_task__/AverageReturn -53.0215 __unnamed_task__/Iteration 114 __unnamed_task__/MaxReturn -43.3184 __unnamed_task__/MinReturn -79.4892 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.98586 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 21:49:53 | [maml_trainer] epoch #115 | Sampling for adapation and meta-testing... 2025-04-05 21:54:01 | [maml_trainer] epoch #115 | Finished meta-testing... 2025-04-05 21:54:01 | [maml_trainer] epoch #115 | Saving snapshot... 2025-04-05 21:54:24 | [maml_trainer] epoch #115 | Saved 2025-04-05 21:54:24 | [maml_trainer] epoch #115 | Time 191708.81 s 2025-04-05 21:54:24 | [maml_trainer] epoch #115 | EpochTime 1791.30 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.3548 Average/AverageReturn -54.002 Average/Iteration 115 Average/MaxReturn -43.507 Average/MinReturn -77.016 Average/NumEpisodes 120 Average/StdReturn 5.78658 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.92168 GaussianMLPPolicy/KLAfter 0.00492031 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000151641 GaussianMLPPolicy/LossBefore -1.71264e-08 GaussianMLPPolicy/dLoss -0.000151658 Iteration 115 MetaTest/Average/AverageDiscountedReturn -53.3711 MetaTest/Average/AverageReturn -53.3711 MetaTest/Average/Iteration 115 MetaTest/Average/MaxReturn -43.7762 MetaTest/Average/MinReturn -63.603 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.32031 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.3711 MetaTest/__unnamed_task__/AverageReturn -53.3711 MetaTest/__unnamed_task__/Iteration 115 MetaTest/__unnamed_task__/MaxReturn -43.7762 MetaTest/__unnamed_task__/MinReturn -63.603 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.32031 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.568e+06 __unnamed_task__/AverageDiscountedReturn -29.3548 __unnamed_task__/AverageReturn -54.002 __unnamed_task__/Iteration 115 __unnamed_task__/MaxReturn -43.507 __unnamed_task__/MinReturn -77.016 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.78658 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 22:19:18 | [maml_trainer] epoch #116 | Sampling for adapation and meta-testing... 2025-04-05 22:23:27 | [maml_trainer] epoch #116 | Finished meta-testing... 2025-04-05 22:23:27 | [maml_trainer] epoch #116 | Saving snapshot... 2025-04-05 22:23:49 | [maml_trainer] epoch #116 | Saved 2025-04-05 22:23:49 | [maml_trainer] epoch #116 | Time 193473.88 s 2025-04-05 22:23:49 | [maml_trainer] epoch #116 | EpochTime 1765.07 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.6798 Average/AverageReturn -52.651 Average/Iteration 116 Average/MaxReturn -44.4265 Average/MinReturn -68.5021 Average/NumEpisodes 120 Average/StdReturn 5.03753 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.92011 GaussianMLPPolicy/KLAfter 0.00579713 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000203099 GaussianMLPPolicy/LossBefore 5.126e-09 GaussianMLPPolicy/dLoss 0.000203104 Iteration 116 MetaTest/Average/AverageDiscountedReturn -52.8902 MetaTest/Average/AverageReturn -52.8902 MetaTest/Average/Iteration 116 MetaTest/Average/MaxReturn -47.3906 MetaTest/Average/MinReturn -61.4671 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.60679 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.8902 MetaTest/__unnamed_task__/AverageReturn -52.8902 MetaTest/__unnamed_task__/Iteration 116 MetaTest/__unnamed_task__/MaxReturn -47.3906 MetaTest/__unnamed_task__/MinReturn -61.4671 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.60679 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.616e+06 __unnamed_task__/AverageDiscountedReturn -28.6798 __unnamed_task__/AverageReturn -52.651 __unnamed_task__/Iteration 116 __unnamed_task__/MaxReturn -44.4265 __unnamed_task__/MinReturn -68.5021 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.03753 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 22:48:54 | [maml_trainer] epoch #117 | Sampling for adapation and meta-testing... 2025-04-05 22:53:09 | [maml_trainer] epoch #117 | Finished meta-testing... 2025-04-05 22:53:09 | [maml_trainer] epoch #117 | Saving snapshot... 2025-04-05 22:53:32 | [maml_trainer] epoch #117 | Saved 2025-04-05 22:53:32 | [maml_trainer] epoch #117 | Time 195256.09 s 2025-04-05 22:53:32 | [maml_trainer] epoch #117 | EpochTime 1782.20 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.0705 Average/AverageReturn -53.0793 Average/Iteration 117 Average/MaxReturn -44.2464 Average/MinReturn -71.2705 Average/NumEpisodes 120 Average/StdReturn 4.52633 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.91953 GaussianMLPPolicy/KLAfter 0.00552407 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000162094 GaussianMLPPolicy/LossBefore 3.21865e-09 GaussianMLPPolicy/dLoss 0.000162097 Iteration 117 MetaTest/Average/AverageDiscountedReturn -53.2476 MetaTest/Average/AverageReturn -53.2476 MetaTest/Average/Iteration 117 MetaTest/Average/MaxReturn -47.1193 MetaTest/Average/MinReturn -83.801 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.72557 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.2476 MetaTest/__unnamed_task__/AverageReturn -53.2476 MetaTest/__unnamed_task__/Iteration 117 MetaTest/__unnamed_task__/MaxReturn -47.1193 MetaTest/__unnamed_task__/MinReturn -83.801 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.72557 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.664e+06 __unnamed_task__/AverageDiscountedReturn -29.0705 __unnamed_task__/AverageReturn -53.0793 __unnamed_task__/Iteration 117 __unnamed_task__/MaxReturn -44.2464 __unnamed_task__/MinReturn -71.2705 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.52633 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 23:19:01 | [maml_trainer] epoch #118 | Sampling for adapation and meta-testing... 2025-04-05 23:23:17 | [maml_trainer] epoch #118 | Finished meta-testing... 2025-04-05 23:23:17 | [maml_trainer] epoch #118 | Saving snapshot... 2025-04-05 23:23:40 | [maml_trainer] epoch #118 | Saved 2025-04-05 23:23:40 | [maml_trainer] epoch #118 | Time 197064.02 s 2025-04-05 23:23:40 | [maml_trainer] epoch #118 | EpochTime 1807.92 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.5143 Average/AverageReturn -51.8767 Average/Iteration 118 Average/MaxReturn -44.051 Average/MinReturn -70.551 Average/NumEpisodes 120 Average/StdReturn 4.56661 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.9162 GaussianMLPPolicy/KLAfter 0.00296416 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000172579 GaussianMLPPolicy/LossBefore -1.22786e-08 GaussianMLPPolicy/dLoss 0.000172566 Iteration 118 MetaTest/Average/AverageDiscountedReturn -51.6935 MetaTest/Average/AverageReturn -51.6935 MetaTest/Average/Iteration 118 MetaTest/Average/MaxReturn -45.7386 MetaTest/Average/MinReturn -69.3296 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.0934 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6935 MetaTest/__unnamed_task__/AverageReturn -51.6935 MetaTest/__unnamed_task__/Iteration 118 MetaTest/__unnamed_task__/MaxReturn -45.7386 MetaTest/__unnamed_task__/MinReturn -69.3296 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.0934 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.712e+06 __unnamed_task__/AverageDiscountedReturn -28.5143 __unnamed_task__/AverageReturn -51.8767 __unnamed_task__/Iteration 118 __unnamed_task__/MaxReturn -44.051 __unnamed_task__/MinReturn -70.551 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.56661 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-05 23:48:42 | [maml_trainer] epoch #119 | Sampling for adapation and meta-testing... 2025-04-05 23:52:54 | [maml_trainer] epoch #119 | Finished meta-testing... 2025-04-05 23:52:54 | [maml_trainer] epoch #119 | Saving snapshot... 2025-04-05 23:53:16 | [maml_trainer] epoch #119 | Saved 2025-04-05 23:53:16 | [maml_trainer] epoch #119 | Time 198840.84 s 2025-04-05 23:53:16 | [maml_trainer] epoch #119 | EpochTime 1776.82 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.4532 Average/AverageReturn -52.1927 Average/Iteration 119 Average/MaxReturn -43.8255 Average/MinReturn -64.7472 Average/NumEpisodes 120 Average/StdReturn 4.74807 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.91263 GaussianMLPPolicy/KLAfter 0.00329981 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.90919e-05 GaussianMLPPolicy/LossBefore -5.5631e-09 GaussianMLPPolicy/dLoss 6.90863e-05 Iteration 119 MetaTest/Average/AverageDiscountedReturn -51.2957 MetaTest/Average/AverageReturn -51.2957 MetaTest/Average/Iteration 119 MetaTest/Average/MaxReturn -44.7417 MetaTest/Average/MinReturn -60.7461 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.13857 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2957 MetaTest/__unnamed_task__/AverageReturn -51.2957 MetaTest/__unnamed_task__/Iteration 119 MetaTest/__unnamed_task__/MaxReturn -44.7417 MetaTest/__unnamed_task__/MinReturn -60.7461 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.13857 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.76e+06 __unnamed_task__/AverageDiscountedReturn -28.4532 __unnamed_task__/AverageReturn -52.1927 __unnamed_task__/Iteration 119 __unnamed_task__/MaxReturn -43.8255 __unnamed_task__/MinReturn -64.7472 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.74807 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 00:18:46 | [maml_trainer] epoch #120 | Sampling for adapation and meta-testing... 2025-04-06 00:22:57 | [maml_trainer] epoch #120 | Finished meta-testing... 2025-04-06 00:22:57 | [maml_trainer] epoch #120 | Saving snapshot... 2025-04-06 00:23:18 | [maml_trainer] epoch #120 | Saved 2025-04-06 00:23:18 | [maml_trainer] epoch #120 | Time 200642.40 s 2025-04-06 00:23:18 | [maml_trainer] epoch #120 | EpochTime 1801.55 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.9677 Average/AverageReturn -53.003 Average/Iteration 120 Average/MaxReturn -43.5648 Average/MinReturn -72.4551 Average/NumEpisodes 120 Average/StdReturn 5.84648 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.9087 GaussianMLPPolicy/KLAfter 0.00284177 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000106412 GaussianMLPPolicy/LossBefore -3.85443e-09 GaussianMLPPolicy/dLoss 0.000106408 Iteration 120 MetaTest/Average/AverageDiscountedReturn -50.868 MetaTest/Average/AverageReturn -50.868 MetaTest/Average/Iteration 120 MetaTest/Average/MaxReturn -46.8693 MetaTest/Average/MinReturn -62.0798 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.45817 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.868 MetaTest/__unnamed_task__/AverageReturn -50.868 MetaTest/__unnamed_task__/Iteration 120 MetaTest/__unnamed_task__/MaxReturn -46.8693 MetaTest/__unnamed_task__/MinReturn -62.0798 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.45817 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.808e+06 __unnamed_task__/AverageDiscountedReturn -28.9677 __unnamed_task__/AverageReturn -53.003 __unnamed_task__/Iteration 120 __unnamed_task__/MaxReturn -43.5648 __unnamed_task__/MinReturn -72.4551 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.84648 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 00:47:16 | [maml_trainer] epoch #121 | Sampling for adapation and meta-testing... 2025-04-06 00:51:11 | [maml_trainer] epoch #121 | Finished meta-testing... 2025-04-06 00:51:11 | [maml_trainer] epoch #121 | Saving snapshot... 2025-04-06 00:51:32 | [maml_trainer] epoch #121 | Saved 2025-04-06 00:51:32 | [maml_trainer] epoch #121 | Time 202336.45 s 2025-04-06 00:51:32 | [maml_trainer] epoch #121 | EpochTime 1694.05 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.5768 Average/AverageReturn -52.1705 Average/Iteration 121 Average/MaxReturn -43.4795 Average/MinReturn -84.6151 Average/NumEpisodes 120 Average/StdReturn 6.01891 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.90485 GaussianMLPPolicy/KLAfter 0.00192267 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.69504e-05 GaussianMLPPolicy/LossBefore -9.57648e-09 GaussianMLPPolicy/dLoss -2.696e-05 Iteration 121 MetaTest/Average/AverageDiscountedReturn -51.9227 MetaTest/Average/AverageReturn -51.9227 MetaTest/Average/Iteration 121 MetaTest/Average/MaxReturn -44.4324 MetaTest/Average/MinReturn -72.689 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.4859 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.9227 MetaTest/__unnamed_task__/AverageReturn -51.9227 MetaTest/__unnamed_task__/Iteration 121 MetaTest/__unnamed_task__/MaxReturn -44.4324 MetaTest/__unnamed_task__/MinReturn -72.689 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.4859 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.856e+06 __unnamed_task__/AverageDiscountedReturn -28.5768 __unnamed_task__/AverageReturn -52.1705 __unnamed_task__/Iteration 121 __unnamed_task__/MaxReturn -43.4795 __unnamed_task__/MinReturn -84.6151 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.01891 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 01:15:11 | [maml_trainer] epoch #122 | Sampling for adapation and meta-testing... 2025-04-06 01:19:07 | [maml_trainer] epoch #122 | Finished meta-testing... 2025-04-06 01:19:07 | [maml_trainer] epoch #122 | Saving snapshot... 2025-04-06 01:19:28 | [maml_trainer] epoch #122 | Saved 2025-04-06 01:19:28 | [maml_trainer] epoch #122 | Time 204012.66 s 2025-04-06 01:19:28 | [maml_trainer] epoch #122 | EpochTime 1676.21 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.3289 Average/AverageReturn -51.4911 Average/Iteration 122 Average/MaxReturn -42.4051 Average/MinReturn -67.1367 Average/NumEpisodes 120 Average/StdReturn 5.06293 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.90069 GaussianMLPPolicy/KLAfter 0.00209849 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.44951e-05 GaussianMLPPolicy/LossBefore 5.88099e-09 GaussianMLPPolicy/dLoss -2.44892e-05 Iteration 122 MetaTest/Average/AverageDiscountedReturn -52.3903 MetaTest/Average/AverageReturn -52.3903 MetaTest/Average/Iteration 122 MetaTest/Average/MaxReturn -43.4111 MetaTest/Average/MinReturn -74.4081 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.81494 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.3903 MetaTest/__unnamed_task__/AverageReturn -52.3903 MetaTest/__unnamed_task__/Iteration 122 MetaTest/__unnamed_task__/MaxReturn -43.4111 MetaTest/__unnamed_task__/MinReturn -74.4081 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.81494 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.904e+06 __unnamed_task__/AverageDiscountedReturn -28.3289 __unnamed_task__/AverageReturn -51.4911 __unnamed_task__/Iteration 122 __unnamed_task__/MaxReturn -42.4051 __unnamed_task__/MinReturn -67.1367 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.06293 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 01:43:10 | [maml_trainer] epoch #123 | Sampling for adapation and meta-testing... 2025-04-06 01:47:08 | [maml_trainer] epoch #123 | Finished meta-testing... 2025-04-06 01:47:08 | [maml_trainer] epoch #123 | Saving snapshot... 2025-04-06 01:47:29 | [maml_trainer] epoch #123 | Saved 2025-04-06 01:47:29 | [maml_trainer] epoch #123 | Time 205693.38 s 2025-04-06 01:47:29 | [maml_trainer] epoch #123 | EpochTime 1680.71 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.6926 Average/AverageReturn -52.5528 Average/Iteration 123 Average/MaxReturn -42.5225 Average/MinReturn -76.1241 Average/NumEpisodes 120 Average/StdReturn 5.66298 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.8962 GaussianMLPPolicy/KLAfter 0.00164937 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.07604e-05 GaussianMLPPolicy/LossBefore -2.1855e-09 GaussianMLPPolicy/dLoss 4.07582e-05 Iteration 123 MetaTest/Average/AverageDiscountedReturn -52.0395 MetaTest/Average/AverageReturn -52.0395 MetaTest/Average/Iteration 123 MetaTest/Average/MaxReturn -46.2929 MetaTest/Average/MinReturn -58.9905 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.07344 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.0395 MetaTest/__unnamed_task__/AverageReturn -52.0395 MetaTest/__unnamed_task__/Iteration 123 MetaTest/__unnamed_task__/MaxReturn -46.2929 MetaTest/__unnamed_task__/MinReturn -58.9905 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.07344 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 5.952e+06 __unnamed_task__/AverageDiscountedReturn -28.6926 __unnamed_task__/AverageReturn -52.5528 __unnamed_task__/Iteration 123 __unnamed_task__/MaxReturn -42.5225 __unnamed_task__/MinReturn -76.1241 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.66298 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 02:11:43 | [maml_trainer] epoch #124 | Sampling for adapation and meta-testing... 2025-04-06 02:15:41 | [maml_trainer] epoch #124 | Finished meta-testing... 2025-04-06 02:15:41 | [maml_trainer] epoch #124 | Saving snapshot... 2025-04-06 02:16:02 | [maml_trainer] epoch #124 | Saved 2025-04-06 02:16:02 | [maml_trainer] epoch #124 | Time 207406.38 s 2025-04-06 02:16:02 | [maml_trainer] epoch #124 | EpochTime 1713.01 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.0945 Average/AverageReturn -53.3447 Average/Iteration 124 Average/MaxReturn -43.6329 Average/MinReturn -76.0709 Average/NumEpisodes 120 Average/StdReturn 6.25056 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89201 GaussianMLPPolicy/KLAfter 0.0040136 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.25575e-05 GaussianMLPPolicy/LossBefore -3.53654e-09 GaussianMLPPolicy/dLoss -2.25611e-05 Iteration 124 MetaTest/Average/AverageDiscountedReturn -52.2638 MetaTest/Average/AverageReturn -52.2638 MetaTest/Average/Iteration 124 MetaTest/Average/MaxReturn -44.4478 MetaTest/Average/MinReturn -61.0074 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.57224 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2638 MetaTest/__unnamed_task__/AverageReturn -52.2638 MetaTest/__unnamed_task__/Iteration 124 MetaTest/__unnamed_task__/MaxReturn -44.4478 MetaTest/__unnamed_task__/MinReturn -61.0074 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.57224 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6e+06 __unnamed_task__/AverageDiscountedReturn -29.0945 __unnamed_task__/AverageReturn -53.3447 __unnamed_task__/Iteration 124 __unnamed_task__/MaxReturn -43.6329 __unnamed_task__/MinReturn -76.0709 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.25056 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 02:39:56 | [maml_trainer] epoch #125 | Sampling for adapation and meta-testing... 2025-04-06 02:43:52 | [maml_trainer] epoch #125 | Finished meta-testing... 2025-04-06 02:43:52 | [maml_trainer] epoch #125 | Saving snapshot... 2025-04-06 02:44:14 | [maml_trainer] epoch #125 | Saved 2025-04-06 02:44:14 | [maml_trainer] epoch #125 | Time 209098.12 s 2025-04-06 02:44:14 | [maml_trainer] epoch #125 | EpochTime 1691.73 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.8904 Average/AverageReturn -52.62 Average/Iteration 125 Average/MaxReturn -43.582 Average/MinReturn -72.2481 Average/NumEpisodes 120 Average/StdReturn 5.1116 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88925 GaussianMLPPolicy/KLAfter 0.00373943 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.78723e-06 GaussianMLPPolicy/LossBefore 3.65575e-09 GaussianMLPPolicy/dLoss 8.79089e-06 Iteration 125 MetaTest/Average/AverageDiscountedReturn -50.8542 MetaTest/Average/AverageReturn -50.8542 MetaTest/Average/Iteration 125 MetaTest/Average/MaxReturn -45.7151 MetaTest/Average/MinReturn -59.1923 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.82349 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.8542 MetaTest/__unnamed_task__/AverageReturn -50.8542 MetaTest/__unnamed_task__/Iteration 125 MetaTest/__unnamed_task__/MaxReturn -45.7151 MetaTest/__unnamed_task__/MinReturn -59.1923 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.82349 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.048e+06 __unnamed_task__/AverageDiscountedReturn -28.8904 __unnamed_task__/AverageReturn -52.62 __unnamed_task__/Iteration 125 __unnamed_task__/MaxReturn -43.582 __unnamed_task__/MinReturn -72.2481 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.1116 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 03:17:35 | [maml_trainer] epoch #126 | Sampling for adapation and meta-testing... 2025-04-06 03:21:35 | [maml_trainer] epoch #126 | Finished meta-testing... 2025-04-06 03:21:35 | [maml_trainer] epoch #126 | Saving snapshot... 2025-04-06 03:21:56 | [maml_trainer] epoch #126 | Saved 2025-04-06 03:21:56 | [maml_trainer] epoch #126 | Time 211360.92 s 2025-04-06 03:21:56 | [maml_trainer] epoch #126 | EpochTime 2262.80 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.4678 Average/AverageReturn -51.316 Average/Iteration 126 Average/MaxReturn -42.9172 Average/MinReturn -66.6647 Average/NumEpisodes 120 Average/StdReturn 5.04211 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88772 GaussianMLPPolicy/KLAfter 0.00370578 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.15805e-05 GaussianMLPPolicy/LossBefore 1.02123e-08 GaussianMLPPolicy/dLoss -2.15702e-05 Iteration 126 MetaTest/Average/AverageDiscountedReturn -50.9475 MetaTest/Average/AverageReturn -50.9475 MetaTest/Average/Iteration 126 MetaTest/Average/MaxReturn -42.7564 MetaTest/Average/MinReturn -60.053 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.25355 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.9475 MetaTest/__unnamed_task__/AverageReturn -50.9475 MetaTest/__unnamed_task__/Iteration 126 MetaTest/__unnamed_task__/MaxReturn -42.7564 MetaTest/__unnamed_task__/MinReturn -60.053 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.25355 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.096e+06 __unnamed_task__/AverageDiscountedReturn -28.4678 __unnamed_task__/AverageReturn -51.316 __unnamed_task__/Iteration 126 __unnamed_task__/MaxReturn -42.9172 __unnamed_task__/MinReturn -66.6647 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.04211 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 03:45:44 | [maml_trainer] epoch #127 | Sampling for adapation and meta-testing... 2025-04-06 03:49:44 | [maml_trainer] epoch #127 | Finished meta-testing... 2025-04-06 03:49:44 | [maml_trainer] epoch #127 | Saving snapshot... 2025-04-06 03:50:05 | [maml_trainer] epoch #127 | Saved 2025-04-06 03:50:05 | [maml_trainer] epoch #127 | Time 213049.51 s 2025-04-06 03:50:05 | [maml_trainer] epoch #127 | EpochTime 1688.58 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.3878 Average/AverageReturn -53.5573 Average/Iteration 127 Average/MaxReturn -43.469 Average/MinReturn -81.6421 Average/NumEpisodes 120 Average/StdReturn 6.72049 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88698 GaussianMLPPolicy/KLAfter 0.00363361 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000108189 GaussianMLPPolicy/LossBefore 2.22524e-09 GaussianMLPPolicy/dLoss 0.000108191 Iteration 127 MetaTest/Average/AverageDiscountedReturn -54.1332 MetaTest/Average/AverageReturn -54.1332 MetaTest/Average/Iteration 127 MetaTest/Average/MaxReturn -45.5398 MetaTest/Average/MinReturn -125.32 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.7397 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.1332 MetaTest/__unnamed_task__/AverageReturn -54.1332 MetaTest/__unnamed_task__/Iteration 127 MetaTest/__unnamed_task__/MaxReturn -45.5398 MetaTest/__unnamed_task__/MinReturn -125.32 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.7397 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.144e+06 __unnamed_task__/AverageDiscountedReturn -29.3878 __unnamed_task__/AverageReturn -53.5573 __unnamed_task__/Iteration 127 __unnamed_task__/MaxReturn -43.469 __unnamed_task__/MinReturn -81.6421 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.72049 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 04:13:38 | [maml_trainer] epoch #128 | Sampling for adapation and meta-testing... 2025-04-06 04:17:34 | [maml_trainer] epoch #128 | Finished meta-testing... 2025-04-06 04:17:34 | [maml_trainer] epoch #128 | Saving snapshot... 2025-04-06 04:17:55 | [maml_trainer] epoch #128 | Saved 2025-04-06 04:17:55 | [maml_trainer] epoch #128 | Time 214719.86 s 2025-04-06 04:17:55 | [maml_trainer] epoch #128 | EpochTime 1670.35 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.8438 Average/AverageReturn -52.46 Average/Iteration 128 Average/MaxReturn -42.929 Average/MinReturn -77.9564 Average/NumEpisodes 120 Average/StdReturn 7.01241 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88796 GaussianMLPPolicy/KLAfter 0.00581481 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.4963e-05 GaussianMLPPolicy/LossBefore 9.13938e-10 GaussianMLPPolicy/dLoss 2.49639e-05 Iteration 128 MetaTest/Average/AverageDiscountedReturn -52.6662 MetaTest/Average/AverageReturn -52.6662 MetaTest/Average/Iteration 128 MetaTest/Average/MaxReturn -42.3193 MetaTest/Average/MinReturn -76.1263 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.15018 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6662 MetaTest/__unnamed_task__/AverageReturn -52.6662 MetaTest/__unnamed_task__/Iteration 128 MetaTest/__unnamed_task__/MaxReturn -42.3193 MetaTest/__unnamed_task__/MinReturn -76.1263 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.15018 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.192e+06 __unnamed_task__/AverageDiscountedReturn -28.8438 __unnamed_task__/AverageReturn -52.46 __unnamed_task__/Iteration 128 __unnamed_task__/MaxReturn -42.929 __unnamed_task__/MinReturn -77.9564 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.01241 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 04:41:30 | [maml_trainer] epoch #129 | Sampling for adapation and meta-testing... 2025-04-06 04:45:29 | [maml_trainer] epoch #129 | Finished meta-testing... 2025-04-06 04:45:29 | [maml_trainer] epoch #129 | Saving snapshot... 2025-04-06 04:45:50 | [maml_trainer] epoch #129 | Saved 2025-04-06 04:45:50 | [maml_trainer] epoch #129 | Time 216394.02 s 2025-04-06 04:45:50 | [maml_trainer] epoch #129 | EpochTime 1674.15 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.349 Average/AverageReturn -50.8814 Average/Iteration 129 Average/MaxReturn -42.1891 Average/MinReturn -88.7122 Average/NumEpisodes 120 Average/StdReturn 6.6739 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88884 GaussianMLPPolicy/KLAfter 0.00572082 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000205013 GaussianMLPPolicy/LossBefore 1.62919e-09 GaussianMLPPolicy/dLoss -0.000205012 Iteration 129 MetaTest/Average/AverageDiscountedReturn -50.4784 MetaTest/Average/AverageReturn -50.4784 MetaTest/Average/Iteration 129 MetaTest/Average/MaxReturn -44.2467 MetaTest/Average/MinReturn -69.3468 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.58445 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.4784 MetaTest/__unnamed_task__/AverageReturn -50.4784 MetaTest/__unnamed_task__/Iteration 129 MetaTest/__unnamed_task__/MaxReturn -44.2467 MetaTest/__unnamed_task__/MinReturn -69.3468 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.58445 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.24e+06 __unnamed_task__/AverageDiscountedReturn -28.349 __unnamed_task__/AverageReturn -50.8814 __unnamed_task__/Iteration 129 __unnamed_task__/MaxReturn -42.1891 __unnamed_task__/MinReturn -88.7122 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.6739 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 05:09:19 | [maml_trainer] epoch #130 | Sampling for adapation and meta-testing... 2025-04-06 05:13:11 | [maml_trainer] epoch #130 | Finished meta-testing... 2025-04-06 05:13:11 | [maml_trainer] epoch #130 | Saving snapshot... 2025-04-06 05:13:32 | [maml_trainer] epoch #130 | Saved 2025-04-06 05:13:32 | [maml_trainer] epoch #130 | Time 218056.93 s 2025-04-06 05:13:32 | [maml_trainer] epoch #130 | EpochTime 1662.91 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.9318 Average/AverageReturn -52.5828 Average/Iteration 130 Average/MaxReturn -40.5446 Average/MinReturn -104.403 Average/NumEpisodes 120 Average/StdReturn 9.1081 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88833 GaussianMLPPolicy/KLAfter 0.00383478 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.83886e-05 GaussianMLPPolicy/LossBefore 1.4027e-08 GaussianMLPPolicy/dLoss 7.84027e-05 Iteration 130 MetaTest/Average/AverageDiscountedReturn -48.9587 MetaTest/Average/AverageReturn -48.9587 MetaTest/Average/Iteration 130 MetaTest/Average/MaxReturn -41.0706 MetaTest/Average/MinReturn -60.1262 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.50735 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9587 MetaTest/__unnamed_task__/AverageReturn -48.9587 MetaTest/__unnamed_task__/Iteration 130 MetaTest/__unnamed_task__/MaxReturn -41.0706 MetaTest/__unnamed_task__/MinReturn -60.1262 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.50735 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.288e+06 __unnamed_task__/AverageDiscountedReturn -28.9318 __unnamed_task__/AverageReturn -52.5828 __unnamed_task__/Iteration 130 __unnamed_task__/MaxReturn -40.5446 __unnamed_task__/MinReturn -104.403 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.1081 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 05:37:12 | [maml_trainer] epoch #131 | Sampling for adapation and meta-testing... 2025-04-06 05:41:15 | [maml_trainer] epoch #131 | Finished meta-testing... 2025-04-06 05:41:15 | [maml_trainer] epoch #131 | Saving snapshot... 2025-04-06 05:41:36 | [maml_trainer] epoch #131 | Saved 2025-04-06 05:41:36 | [maml_trainer] epoch #131 | Time 219740.81 s 2025-04-06 05:41:36 | [maml_trainer] epoch #131 | EpochTime 1683.87 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.791 Average/AverageReturn -52.2391 Average/Iteration 131 Average/MaxReturn -42.2452 Average/MinReturn -107.358 Average/NumEpisodes 120 Average/StdReturn 9.3302 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88794 GaussianMLPPolicy/KLAfter 0.00310472 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.35227e-05 GaussianMLPPolicy/LossBefore 5.28494e-09 GaussianMLPPolicy/dLoss 6.3528e-05 Iteration 131 MetaTest/Average/AverageDiscountedReturn -53.8318 MetaTest/Average/AverageReturn -53.8318 MetaTest/Average/Iteration 131 MetaTest/Average/MaxReturn -41.1707 MetaTest/Average/MinReturn -84.4594 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.35483 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.8318 MetaTest/__unnamed_task__/AverageReturn -53.8318 MetaTest/__unnamed_task__/Iteration 131 MetaTest/__unnamed_task__/MaxReturn -41.1707 MetaTest/__unnamed_task__/MinReturn -84.4594 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.35483 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.336e+06 __unnamed_task__/AverageDiscountedReturn -28.791 __unnamed_task__/AverageReturn -52.2391 __unnamed_task__/Iteration 131 __unnamed_task__/MaxReturn -42.2452 __unnamed_task__/MinReturn -107.358 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.3302 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 06:05:26 | [maml_trainer] epoch #132 | Sampling for adapation and meta-testing... 2025-04-06 06:09:22 | [maml_trainer] epoch #132 | Finished meta-testing... 2025-04-06 06:09:22 | [maml_trainer] epoch #132 | Saving snapshot... 2025-04-06 06:09:43 | [maml_trainer] epoch #132 | Saved 2025-04-06 06:09:43 | [maml_trainer] epoch #132 | Time 221427.27 s 2025-04-06 06:09:43 | [maml_trainer] epoch #132 | EpochTime 1686.46 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.5316 Average/AverageReturn -56.7547 Average/Iteration 132 Average/MaxReturn -41.3266 Average/MinReturn -150.326 Average/NumEpisodes 120 Average/StdReturn 20.1539 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88789 GaussianMLPPolicy/KLAfter 0.00250488 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.3088e-05 GaussianMLPPolicy/LossBefore -5.5631e-09 GaussianMLPPolicy/dLoss -2.30935e-05 Iteration 132 MetaTest/Average/AverageDiscountedReturn -49.8728 MetaTest/Average/AverageReturn -49.8728 MetaTest/Average/Iteration 132 MetaTest/Average/MaxReturn -41.5658 MetaTest/Average/MinReturn -59.4331 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.01566 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8728 MetaTest/__unnamed_task__/AverageReturn -49.8728 MetaTest/__unnamed_task__/Iteration 132 MetaTest/__unnamed_task__/MaxReturn -41.5658 MetaTest/__unnamed_task__/MinReturn -59.4331 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.01566 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.384e+06 __unnamed_task__/AverageDiscountedReturn -29.5316 __unnamed_task__/AverageReturn -56.7547 __unnamed_task__/Iteration 132 __unnamed_task__/MaxReturn -41.3266 __unnamed_task__/MinReturn -150.326 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 20.1539 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 06:33:30 | [maml_trainer] epoch #133 | Sampling for adapation and meta-testing... 2025-04-06 06:37:24 | [maml_trainer] epoch #133 | Finished meta-testing... 2025-04-06 06:37:24 | [maml_trainer] epoch #133 | Saving snapshot... 2025-04-06 06:37:46 | [maml_trainer] epoch #133 | Saved 2025-04-06 06:37:46 | [maml_trainer] epoch #133 | Time 223110.00 s 2025-04-06 06:37:46 | [maml_trainer] epoch #133 | EpochTime 1682.73 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.6824 Average/AverageReturn -57.2107 Average/Iteration 133 Average/MaxReturn -28.5136 Average/MinReturn -176.403 Average/NumEpisodes 120 Average/StdReturn 24.4825 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88734 GaussianMLPPolicy/KLAfter 0.00364025 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000123101 GaussianMLPPolicy/LossBefore -3.27826e-09 GaussianMLPPolicy/dLoss -0.000123105 Iteration 133 MetaTest/Average/AverageDiscountedReturn -55.7915 MetaTest/Average/AverageReturn -55.7915 MetaTest/Average/Iteration 133 MetaTest/Average/MaxReturn -40.8413 MetaTest/Average/MinReturn -173.51 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 27.5039 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.7915 MetaTest/__unnamed_task__/AverageReturn -55.7915 MetaTest/__unnamed_task__/Iteration 133 MetaTest/__unnamed_task__/MaxReturn -40.8413 MetaTest/__unnamed_task__/MinReturn -173.51 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 27.5039 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.432e+06 __unnamed_task__/AverageDiscountedReturn -29.6824 __unnamed_task__/AverageReturn -57.2107 __unnamed_task__/Iteration 133 __unnamed_task__/MaxReturn -28.5136 __unnamed_task__/MinReturn -176.403 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 24.4825 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 07:01:44 | [maml_trainer] epoch #134 | Sampling for adapation and meta-testing... 2025-04-06 07:05:39 | [maml_trainer] epoch #134 | Finished meta-testing... 2025-04-06 07:05:39 | [maml_trainer] epoch #134 | Saving snapshot... 2025-04-06 07:06:00 | [maml_trainer] epoch #134 | Saved 2025-04-06 07:06:00 | [maml_trainer] epoch #134 | Time 224804.62 s 2025-04-06 07:06:00 | [maml_trainer] epoch #134 | EpochTime 1694.62 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.2732 Average/AverageReturn -55.6752 Average/Iteration 134 Average/MaxReturn -41.0252 Average/MinReturn -169.621 Average/NumEpisodes 120 Average/StdReturn 20.2712 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88678 GaussianMLPPolicy/KLAfter 0.00538287 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.60329e-06 GaussianMLPPolicy/LossBefore 3.53654e-09 GaussianMLPPolicy/dLoss -7.59975e-06 Iteration 134 MetaTest/Average/AverageDiscountedReturn -57.9552 MetaTest/Average/AverageReturn -57.9552 MetaTest/Average/Iteration 134 MetaTest/Average/MaxReturn -45.0538 MetaTest/Average/MinReturn -120.916 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.9562 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -57.9552 MetaTest/__unnamed_task__/AverageReturn -57.9552 MetaTest/__unnamed_task__/Iteration 134 MetaTest/__unnamed_task__/MaxReturn -45.0538 MetaTest/__unnamed_task__/MinReturn -120.916 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.9562 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.48e+06 __unnamed_task__/AverageDiscountedReturn -29.2732 __unnamed_task__/AverageReturn -55.6752 __unnamed_task__/Iteration 134 __unnamed_task__/MaxReturn -41.0252 __unnamed_task__/MinReturn -169.621 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 20.2712 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 07:29:37 | [maml_trainer] epoch #135 | Sampling for adapation and meta-testing... 2025-04-06 07:33:31 | [maml_trainer] epoch #135 | Finished meta-testing... 2025-04-06 07:33:31 | [maml_trainer] epoch #135 | Saving snapshot... 2025-04-06 07:33:52 | [maml_trainer] epoch #135 | Saved 2025-04-06 07:33:52 | [maml_trainer] epoch #135 | Time 226476.20 s 2025-04-06 07:33:52 | [maml_trainer] epoch #135 | EpochTime 1671.57 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.6109 Average/AverageReturn -57.2685 Average/Iteration 135 Average/MaxReturn 234.041 Average/MinReturn -178.707 Average/NumEpisodes 120 Average/StdReturn 37.3713 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88653 GaussianMLPPolicy/KLAfter 0.00431025 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.6709e-05 GaussianMLPPolicy/LossBefore -8.29498e-10 GaussianMLPPolicy/dLoss -1.67098e-05 Iteration 135 MetaTest/Average/AverageDiscountedReturn -56.3143 MetaTest/Average/AverageReturn -56.3143 MetaTest/Average/Iteration 135 MetaTest/Average/MaxReturn -43.2209 MetaTest/Average/MinReturn -137.745 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.0515 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -56.3143 MetaTest/__unnamed_task__/AverageReturn -56.3143 MetaTest/__unnamed_task__/Iteration 135 MetaTest/__unnamed_task__/MaxReturn -43.2209 MetaTest/__unnamed_task__/MinReturn -137.745 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.0515 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.528e+06 __unnamed_task__/AverageDiscountedReturn -29.6109 __unnamed_task__/AverageReturn -57.2685 __unnamed_task__/Iteration 135 __unnamed_task__/MaxReturn 234.041 __unnamed_task__/MinReturn -178.707 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 37.3713 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 07:57:26 | [maml_trainer] epoch #136 | Sampling for adapation and meta-testing... 2025-04-06 08:01:25 | [maml_trainer] epoch #136 | Finished meta-testing... 2025-04-06 08:01:25 | [maml_trainer] epoch #136 | Saving snapshot... 2025-04-06 08:01:47 | [maml_trainer] epoch #136 | Saved 2025-04-06 08:01:47 | [maml_trainer] epoch #136 | Time 228151.04 s 2025-04-06 08:01:47 | [maml_trainer] epoch #136 | EpochTime 1674.84 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -30.3952 Average/AverageReturn -58.7606 Average/Iteration 136 Average/MaxReturn 140.105 Average/MinReturn -180.749 Average/NumEpisodes 120 Average/StdReturn 31.7974 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.8876 GaussianMLPPolicy/KLAfter 0.00267749 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.20986e-05 GaussianMLPPolicy/LossBefore -5.26508e-10 GaussianMLPPolicy/dLoss 1.20981e-05 Iteration 136 MetaTest/Average/AverageDiscountedReturn -45.8903 MetaTest/Average/AverageReturn -45.8903 MetaTest/Average/Iteration 136 MetaTest/Average/MaxReturn 131.726 MetaTest/Average/MinReturn -166.301 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 48.4294 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.8903 MetaTest/__unnamed_task__/AverageReturn -45.8903 MetaTest/__unnamed_task__/Iteration 136 MetaTest/__unnamed_task__/MaxReturn 131.726 MetaTest/__unnamed_task__/MinReturn -166.301 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 48.4294 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.576e+06 __unnamed_task__/AverageDiscountedReturn -30.3952 __unnamed_task__/AverageReturn -58.7606 __unnamed_task__/Iteration 136 __unnamed_task__/MaxReturn 140.105 __unnamed_task__/MinReturn -180.749 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 31.7974 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 08:25:27 | [maml_trainer] epoch #137 | Sampling for adapation and meta-testing... 2025-04-06 08:29:29 | [maml_trainer] epoch #137 | Finished meta-testing... 2025-04-06 08:29:29 | [maml_trainer] epoch #137 | Saving snapshot... 2025-04-06 08:29:50 | [maml_trainer] epoch #137 | Saved 2025-04-06 08:29:50 | [maml_trainer] epoch #137 | Time 229834.56 s 2025-04-06 08:29:50 | [maml_trainer] epoch #137 | EpochTime 1683.52 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.7801 Average/AverageReturn -56.0983 Average/Iteration 137 Average/MaxReturn 22.1 Average/MinReturn -150.718 Average/NumEpisodes 120 Average/StdReturn 22.9984 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88904 GaussianMLPPolicy/KLAfter 0.00289323 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.21982e-06 GaussianMLPPolicy/LossBefore 1.17222e-09 GaussianMLPPolicy/dLoss 3.221e-06 Iteration 137 MetaTest/Average/AverageDiscountedReturn -55.2808 MetaTest/Average/AverageReturn -55.2808 MetaTest/Average/Iteration 137 MetaTest/Average/MaxReturn -37.0179 MetaTest/Average/MinReturn -106.023 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.2516 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.2808 MetaTest/__unnamed_task__/AverageReturn -55.2808 MetaTest/__unnamed_task__/Iteration 137 MetaTest/__unnamed_task__/MaxReturn -37.0179 MetaTest/__unnamed_task__/MinReturn -106.023 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.2516 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.624e+06 __unnamed_task__/AverageDiscountedReturn -29.7801 __unnamed_task__/AverageReturn -56.0983 __unnamed_task__/Iteration 137 __unnamed_task__/MaxReturn 22.1 __unnamed_task__/MinReturn -150.718 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 22.9984 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 08:53:33 | [maml_trainer] epoch #138 | Sampling for adapation and meta-testing... 2025-04-06 08:57:31 | [maml_trainer] epoch #138 | Finished meta-testing... 2025-04-06 08:57:31 | [maml_trainer] epoch #138 | Saving snapshot... 2025-04-06 08:57:52 | [maml_trainer] epoch #138 | Saved 2025-04-06 08:57:52 | [maml_trainer] epoch #138 | Time 231516.64 s 2025-04-06 08:57:52 | [maml_trainer] epoch #138 | EpochTime 1682.07 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -30.0717 Average/AverageReturn -57.4925 Average/Iteration 138 Average/MaxReturn 114.852 Average/MinReturn -164.737 Average/NumEpisodes 120 Average/StdReturn 28.7014 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89107 GaussianMLPPolicy/KLAfter 0.00313304 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.31558e-05 GaussianMLPPolicy/LossBefore -2.45372e-09 GaussianMLPPolicy/dLoss -2.31583e-05 Iteration 138 MetaTest/Average/AverageDiscountedReturn -54.9232 MetaTest/Average/AverageReturn -54.9232 MetaTest/Average/Iteration 138 MetaTest/Average/MaxReturn -42.9758 MetaTest/Average/MinReturn -86.2242 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.0307 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.9232 MetaTest/__unnamed_task__/AverageReturn -54.9232 MetaTest/__unnamed_task__/Iteration 138 MetaTest/__unnamed_task__/MaxReturn -42.9758 MetaTest/__unnamed_task__/MinReturn -86.2242 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.0307 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.672e+06 __unnamed_task__/AverageDiscountedReturn -30.0717 __unnamed_task__/AverageReturn -57.4925 __unnamed_task__/Iteration 138 __unnamed_task__/MaxReturn 114.852 __unnamed_task__/MinReturn -164.737 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 28.7014 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 09:21:42 | [maml_trainer] epoch #139 | Sampling for adapation and meta-testing... 2025-04-06 09:25:41 | [maml_trainer] epoch #139 | Finished meta-testing... 2025-04-06 09:25:41 | [maml_trainer] epoch #139 | Saving snapshot... 2025-04-06 09:26:02 | [maml_trainer] epoch #139 | Saved 2025-04-06 09:26:02 | [maml_trainer] epoch #139 | Time 233206.36 s 2025-04-06 09:26:02 | [maml_trainer] epoch #139 | EpochTime 1689.72 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.9594 Average/AverageReturn -55.9177 Average/Iteration 139 Average/MaxReturn -42.0633 Average/MinReturn -158.054 Average/NumEpisodes 120 Average/StdReturn 15.841 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89405 GaussianMLPPolicy/KLAfter 0.00373776 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.68601e-05 GaussianMLPPolicy/LossBefore 9.35793e-09 GaussianMLPPolicy/dLoss -4.68507e-05 Iteration 139 MetaTest/Average/AverageDiscountedReturn -52.0098 MetaTest/Average/AverageReturn -52.0098 MetaTest/Average/Iteration 139 MetaTest/Average/MaxReturn -43.7705 MetaTest/Average/MinReturn -67.4596 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.78129 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.0098 MetaTest/__unnamed_task__/AverageReturn -52.0098 MetaTest/__unnamed_task__/Iteration 139 MetaTest/__unnamed_task__/MaxReturn -43.7705 MetaTest/__unnamed_task__/MinReturn -67.4596 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.78129 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.72e+06 __unnamed_task__/AverageDiscountedReturn -29.9594 __unnamed_task__/AverageReturn -55.9177 __unnamed_task__/Iteration 139 __unnamed_task__/MaxReturn -42.0633 __unnamed_task__/MinReturn -158.054 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 15.841 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 09:49:54 | [maml_trainer] epoch #140 | Sampling for adapation and meta-testing... 2025-04-06 09:53:54 | [maml_trainer] epoch #140 | Finished meta-testing... 2025-04-06 09:53:54 | [maml_trainer] epoch #140 | Saving snapshot... 2025-04-06 09:54:15 | [maml_trainer] epoch #140 | Saved 2025-04-06 09:54:15 | [maml_trainer] epoch #140 | Time 234899.87 s 2025-04-06 09:54:15 | [maml_trainer] epoch #140 | EpochTime 1693.51 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.9261 Average/AverageReturn -51.4228 Average/Iteration 140 Average/MaxReturn 231.9 Average/MinReturn -162.324 Average/NumEpisodes 120 Average/StdReturn 30.0854 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89457 GaussianMLPPolicy/KLAfter 0.0033877 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.77536e-05 GaussianMLPPolicy/LossBefore -3.13918e-09 GaussianMLPPolicy/dLoss 1.77505e-05 Iteration 140 MetaTest/Average/AverageDiscountedReturn -53.8918 MetaTest/Average/AverageReturn -53.8918 MetaTest/Average/Iteration 140 MetaTest/Average/MaxReturn -44.7785 MetaTest/Average/MinReturn -68.6761 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.0788 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.8918 MetaTest/__unnamed_task__/AverageReturn -53.8918 MetaTest/__unnamed_task__/Iteration 140 MetaTest/__unnamed_task__/MaxReturn -44.7785 MetaTest/__unnamed_task__/MinReturn -68.6761 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.0788 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.768e+06 __unnamed_task__/AverageDiscountedReturn -28.9261 __unnamed_task__/AverageReturn -51.4228 __unnamed_task__/Iteration 140 __unnamed_task__/MaxReturn 231.9 __unnamed_task__/MinReturn -162.324 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 30.0854 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 10:18:06 | [maml_trainer] epoch #141 | Sampling for adapation and meta-testing... 2025-04-06 10:22:01 | [maml_trainer] epoch #141 | Finished meta-testing... 2025-04-06 10:22:01 | [maml_trainer] epoch #141 | Saving snapshot... 2025-04-06 10:22:22 | [maml_trainer] epoch #141 | Saved 2025-04-06 10:22:22 | [maml_trainer] epoch #141 | Time 236586.86 s 2025-04-06 10:22:22 | [maml_trainer] epoch #141 | EpochTime 1686.99 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.2379 Average/AverageReturn -52.0956 Average/Iteration 141 Average/MaxReturn -40.8622 Average/MinReturn -76.5301 Average/NumEpisodes 120 Average/StdReturn 5.99735 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89478 GaussianMLPPolicy/KLAfter 0.00182271 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.65648e-05 GaussianMLPPolicy/LossBefore -1.70867e-09 GaussianMLPPolicy/dLoss -3.65665e-05 Iteration 141 MetaTest/Average/AverageDiscountedReturn -53.7784 MetaTest/Average/AverageReturn -53.7784 MetaTest/Average/Iteration 141 MetaTest/Average/MaxReturn -43.3935 MetaTest/Average/MinReturn -69.8166 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.62944 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.7784 MetaTest/__unnamed_task__/AverageReturn -53.7784 MetaTest/__unnamed_task__/Iteration 141 MetaTest/__unnamed_task__/MaxReturn -43.3935 MetaTest/__unnamed_task__/MinReturn -69.8166 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.62944 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.816e+06 __unnamed_task__/AverageDiscountedReturn -29.2379 __unnamed_task__/AverageReturn -52.0956 __unnamed_task__/Iteration 141 __unnamed_task__/MaxReturn -40.8622 __unnamed_task__/MinReturn -76.5301 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.99735 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 10:46:10 | [maml_trainer] epoch #142 | Sampling for adapation and meta-testing... 2025-04-06 10:50:20 | [maml_trainer] epoch #142 | Finished meta-testing... 2025-04-06 10:50:20 | [maml_trainer] epoch #142 | Saving snapshot... 2025-04-06 10:50:43 | [maml_trainer] epoch #142 | Saved 2025-04-06 10:50:43 | [maml_trainer] epoch #142 | Time 238287.41 s 2025-04-06 10:50:43 | [maml_trainer] epoch #142 | EpochTime 1700.55 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.7505 Average/AverageReturn -52.3682 Average/Iteration 142 Average/MaxReturn 218.358 Average/MinReturn -104.756 Average/NumEpisodes 120 Average/StdReturn 26.3006 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89542 GaussianMLPPolicy/KLAfter 0.00143578 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.33688e-05 GaussianMLPPolicy/LossBefore -1.40071e-09 GaussianMLPPolicy/dLoss 4.33674e-05 Iteration 142 MetaTest/Average/AverageDiscountedReturn -53.5468 MetaTest/Average/AverageReturn -53.5468 MetaTest/Average/Iteration 142 MetaTest/Average/MaxReturn -45.0243 MetaTest/Average/MinReturn -64.6852 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.65446 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.5468 MetaTest/__unnamed_task__/AverageReturn -53.5468 MetaTest/__unnamed_task__/Iteration 142 MetaTest/__unnamed_task__/MaxReturn -45.0243 MetaTest/__unnamed_task__/MinReturn -64.6852 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.65446 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.864e+06 __unnamed_task__/AverageDiscountedReturn -29.7505 __unnamed_task__/AverageReturn -52.3682 __unnamed_task__/Iteration 142 __unnamed_task__/MaxReturn 218.358 __unnamed_task__/MinReturn -104.756 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 26.3006 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 11:15:36 | [maml_trainer] epoch #143 | Sampling for adapation and meta-testing... 2025-04-06 11:19:45 | [maml_trainer] epoch #143 | Finished meta-testing... 2025-04-06 11:19:45 | [maml_trainer] epoch #143 | Saving snapshot... 2025-04-06 11:20:07 | [maml_trainer] epoch #143 | Saved 2025-04-06 11:20:07 | [maml_trainer] epoch #143 | Time 240051.94 s 2025-04-06 11:20:07 | [maml_trainer] epoch #143 | EpochTime 1764.52 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.2891 Average/AverageReturn -51.3183 Average/Iteration 143 Average/MaxReturn 158.153 Average/MinReturn -74.0797 Average/NumEpisodes 120 Average/StdReturn 20.4606 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89533 GaussianMLPPolicy/KLAfter 0.00147648 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.61075e-06 GaussianMLPPolicy/LossBefore 2.38419e-10 GaussianMLPPolicy/dLoss 3.61099e-06 Iteration 143 MetaTest/Average/AverageDiscountedReturn -42.2709 MetaTest/Average/AverageReturn -42.2709 MetaTest/Average/Iteration 143 MetaTest/Average/MaxReturn 206.019 MetaTest/Average/MinReturn -80.0761 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 57.4072 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -42.2709 MetaTest/__unnamed_task__/AverageReturn -42.2709 MetaTest/__unnamed_task__/Iteration 143 MetaTest/__unnamed_task__/MaxReturn 206.019 MetaTest/__unnamed_task__/MinReturn -80.0761 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 57.4072 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.912e+06 __unnamed_task__/AverageDiscountedReturn -29.2891 __unnamed_task__/AverageReturn -51.3183 __unnamed_task__/Iteration 143 __unnamed_task__/MaxReturn 158.153 __unnamed_task__/MinReturn -74.0797 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 20.4606 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 11:45:04 | [maml_trainer] epoch #144 | Sampling for adapation and meta-testing... 2025-04-06 11:49:14 | [maml_trainer] epoch #144 | Finished meta-testing... 2025-04-06 11:49:14 | [maml_trainer] epoch #144 | Saving snapshot... 2025-04-06 11:49:37 | [maml_trainer] epoch #144 | Saved 2025-04-06 11:49:37 | [maml_trainer] epoch #144 | Time 241821.73 s 2025-04-06 11:49:37 | [maml_trainer] epoch #144 | EpochTime 1769.78 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -30.1772 Average/AverageReturn -55.2764 Average/Iteration 144 Average/MaxReturn -43.4226 Average/MinReturn -81.9317 Average/NumEpisodes 120 Average/StdReturn 7.84737 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89504 GaussianMLPPolicy/KLAfter 0.00196751 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.7935e-05 GaussianMLPPolicy/LossBefore -1.54972e-09 GaussianMLPPolicy/dLoss -4.79365e-05 Iteration 144 MetaTest/Average/AverageDiscountedReturn -52.6577 MetaTest/Average/AverageReturn -52.6577 MetaTest/Average/Iteration 144 MetaTest/Average/MaxReturn -44.2471 MetaTest/Average/MinReturn -69.3337 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.43583 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6577 MetaTest/__unnamed_task__/AverageReturn -52.6577 MetaTest/__unnamed_task__/Iteration 144 MetaTest/__unnamed_task__/MaxReturn -44.2471 MetaTest/__unnamed_task__/MinReturn -69.3337 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.43583 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6.96e+06 __unnamed_task__/AverageDiscountedReturn -30.1772 __unnamed_task__/AverageReturn -55.2764 __unnamed_task__/Iteration 144 __unnamed_task__/MaxReturn -43.4226 __unnamed_task__/MinReturn -81.9317 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.84737 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 12:14:21 | [maml_trainer] epoch #145 | Sampling for adapation and meta-testing... 2025-04-06 12:18:32 | [maml_trainer] epoch #145 | Finished meta-testing... 2025-04-06 12:18:32 | [maml_trainer] epoch #145 | Saving snapshot... 2025-04-06 12:18:56 | [maml_trainer] epoch #145 | Saved 2025-04-06 12:18:56 | [maml_trainer] epoch #145 | Time 243580.01 s 2025-04-06 12:18:56 | [maml_trainer] epoch #145 | EpochTime 1758.28 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.7638 Average/AverageReturn -53.4969 Average/Iteration 145 Average/MaxReturn -44.0326 Average/MinReturn -83.5896 Average/NumEpisodes 120 Average/StdReturn 6.54722 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89462 GaussianMLPPolicy/KLAfter 0.00214007 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000100051 GaussianMLPPolicy/LossBefore 2.03848e-08 GaussianMLPPolicy/dLoss -0.000100031 Iteration 145 MetaTest/Average/AverageDiscountedReturn -53.5376 MetaTest/Average/AverageReturn -53.5376 MetaTest/Average/Iteration 145 MetaTest/Average/MaxReturn -44.945 MetaTest/Average/MinReturn -65.1307 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.26743 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.5376 MetaTest/__unnamed_task__/AverageReturn -53.5376 MetaTest/__unnamed_task__/Iteration 145 MetaTest/__unnamed_task__/MaxReturn -44.945 MetaTest/__unnamed_task__/MinReturn -65.1307 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.26743 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.008e+06 __unnamed_task__/AverageDiscountedReturn -29.7638 __unnamed_task__/AverageReturn -53.4969 __unnamed_task__/Iteration 145 __unnamed_task__/MaxReturn -44.0326 __unnamed_task__/MinReturn -83.5896 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.54722 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 12:43:36 | [maml_trainer] epoch #146 | Sampling for adapation and meta-testing... 2025-04-06 12:47:41 | [maml_trainer] epoch #146 | Finished meta-testing... 2025-04-06 12:47:41 | [maml_trainer] epoch #146 | Saving snapshot... 2025-04-06 12:48:04 | [maml_trainer] epoch #146 | Saved 2025-04-06 12:48:04 | [maml_trainer] epoch #146 | Time 245328.43 s 2025-04-06 12:48:04 | [maml_trainer] epoch #146 | EpochTime 1748.41 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.8033 Average/AverageReturn -54.0422 Average/Iteration 146 Average/MaxReturn -40.2827 Average/MinReturn -134.087 Average/NumEpisodes 120 Average/StdReturn 9.69861 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89443 GaussianMLPPolicy/KLAfter 0.00103609 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.51266e-05 GaussianMLPPolicy/LossBefore 3.01997e-09 GaussianMLPPolicy/dLoss 1.51296e-05 Iteration 146 MetaTest/Average/AverageDiscountedReturn -53.0162 MetaTest/Average/AverageReturn -53.0162 MetaTest/Average/Iteration 146 MetaTest/Average/MaxReturn -45.6584 MetaTest/Average/MinReturn -86.8615 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.80968 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.0162 MetaTest/__unnamed_task__/AverageReturn -53.0162 MetaTest/__unnamed_task__/Iteration 146 MetaTest/__unnamed_task__/MaxReturn -45.6584 MetaTest/__unnamed_task__/MinReturn -86.8615 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.80968 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.056e+06 __unnamed_task__/AverageDiscountedReturn -29.8033 __unnamed_task__/AverageReturn -54.0422 __unnamed_task__/Iteration 146 __unnamed_task__/MaxReturn -40.2827 __unnamed_task__/MinReturn -134.087 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.69861 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 13:13:02 | [maml_trainer] epoch #147 | Sampling for adapation and meta-testing... 2025-04-06 13:17:07 | [maml_trainer] epoch #147 | Finished meta-testing... 2025-04-06 13:17:07 | [maml_trainer] epoch #147 | Saving snapshot... 2025-04-06 13:17:31 | [maml_trainer] epoch #147 | Saved 2025-04-06 13:17:31 | [maml_trainer] epoch #147 | Time 247095.05 s 2025-04-06 13:17:31 | [maml_trainer] epoch #147 | EpochTime 1766.62 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.9809 Average/AverageReturn -54.3458 Average/Iteration 147 Average/MaxReturn -42.8057 Average/MinReturn -101.226 Average/NumEpisodes 120 Average/StdReturn 7.77891 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89308 GaussianMLPPolicy/KLAfter 0.00159137 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.37472e-05 GaussianMLPPolicy/LossBefore 1.02917e-08 GaussianMLPPolicy/dLoss 3.37575e-05 Iteration 147 MetaTest/Average/AverageDiscountedReturn -51.2905 MetaTest/Average/AverageReturn -51.2905 MetaTest/Average/Iteration 147 MetaTest/Average/MaxReturn -44.6921 MetaTest/Average/MinReturn -73.5933 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.18277 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2905 MetaTest/__unnamed_task__/AverageReturn -51.2905 MetaTest/__unnamed_task__/Iteration 147 MetaTest/__unnamed_task__/MaxReturn -44.6921 MetaTest/__unnamed_task__/MinReturn -73.5933 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.18277 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.104e+06 __unnamed_task__/AverageDiscountedReturn -29.9809 __unnamed_task__/AverageReturn -54.3458 __unnamed_task__/Iteration 147 __unnamed_task__/MaxReturn -42.8057 __unnamed_task__/MinReturn -101.226 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.77891 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 13:42:20 | [maml_trainer] epoch #148 | Sampling for adapation and meta-testing... 2025-04-06 13:46:27 | [maml_trainer] epoch #148 | Finished meta-testing... 2025-04-06 13:46:27 | [maml_trainer] epoch #148 | Saving snapshot... 2025-04-06 13:46:50 | [maml_trainer] epoch #148 | Saved 2025-04-06 13:46:50 | [maml_trainer] epoch #148 | Time 248854.52 s 2025-04-06 13:46:50 | [maml_trainer] epoch #148 | EpochTime 1759.47 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -30.1289 Average/AverageReturn -54.6637 Average/Iteration 148 Average/MaxReturn -42.2448 Average/MinReturn -83.7794 Average/NumEpisodes 120 Average/StdReturn 7.29097 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.8918 GaussianMLPPolicy/KLAfter 0.00154597 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.18428e-06 GaussianMLPPolicy/LossBefore -1.49012e-08 GaussianMLPPolicy/dLoss -3.19918e-06 Iteration 148 MetaTest/Average/AverageDiscountedReturn -52.3356 MetaTest/Average/AverageReturn -52.3356 MetaTest/Average/Iteration 148 MetaTest/Average/MaxReturn -43.4344 MetaTest/Average/MinReturn -61.9125 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.54887 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.3356 MetaTest/__unnamed_task__/AverageReturn -52.3356 MetaTest/__unnamed_task__/Iteration 148 MetaTest/__unnamed_task__/MaxReturn -43.4344 MetaTest/__unnamed_task__/MinReturn -61.9125 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.54887 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.152e+06 __unnamed_task__/AverageDiscountedReturn -30.1289 __unnamed_task__/AverageReturn -54.6637 __unnamed_task__/Iteration 148 __unnamed_task__/MaxReturn -42.2448 __unnamed_task__/MinReturn -83.7794 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.29097 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 14:11:40 | [maml_trainer] epoch #149 | Sampling for adapation and meta-testing... 2025-04-06 14:15:49 | [maml_trainer] epoch #149 | Finished meta-testing... 2025-04-06 14:15:49 | [maml_trainer] epoch #149 | Saving snapshot... 2025-04-06 14:16:13 | [maml_trainer] epoch #149 | Saved 2025-04-06 14:16:13 | [maml_trainer] epoch #149 | Time 250617.21 s 2025-04-06 14:16:13 | [maml_trainer] epoch #149 | EpochTime 1762.69 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -30.0612 Average/AverageReturn -54.8443 Average/Iteration 149 Average/MaxReturn -43.2767 Average/MinReturn -87.328 Average/NumEpisodes 120 Average/StdReturn 7.80694 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89191 GaussianMLPPolicy/KLAfter 0.00189454 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.5729e-05 GaussianMLPPolicy/LossBefore -1.39078e-09 GaussianMLPPolicy/dLoss -3.57304e-05 Iteration 149 MetaTest/Average/AverageDiscountedReturn -54.8855 MetaTest/Average/AverageReturn -54.8855 MetaTest/Average/Iteration 149 MetaTest/Average/MaxReturn -45.8119 MetaTest/Average/MinReturn -71.4792 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.95569 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.8855 MetaTest/__unnamed_task__/AverageReturn -54.8855 MetaTest/__unnamed_task__/Iteration 149 MetaTest/__unnamed_task__/MaxReturn -45.8119 MetaTest/__unnamed_task__/MinReturn -71.4792 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.95569 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.2e+06 __unnamed_task__/AverageDiscountedReturn -30.0612 __unnamed_task__/AverageReturn -54.8443 __unnamed_task__/Iteration 149 __unnamed_task__/MaxReturn -43.2767 __unnamed_task__/MinReturn -87.328 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.80694 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 14:41:02 | [maml_trainer] epoch #150 | Sampling for adapation and meta-testing... 2025-04-06 14:45:15 | [maml_trainer] epoch #150 | Finished meta-testing... 2025-04-06 14:45:15 | [maml_trainer] epoch #150 | Saving snapshot... 2025-04-06 14:45:38 | [maml_trainer] epoch #150 | Saved 2025-04-06 14:45:38 | [maml_trainer] epoch #150 | Time 252382.15 s 2025-04-06 14:45:38 | [maml_trainer] epoch #150 | EpochTime 1764.93 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.9728 Average/AverageReturn -54.4726 Average/Iteration 150 Average/MaxReturn -41.965 Average/MinReturn -101.738 Average/NumEpisodes 120 Average/StdReturn 8.90933 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89326 GaussianMLPPolicy/KLAfter 0.00193346 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.42881e-05 GaussianMLPPolicy/LossBefore 2.38419e-09 GaussianMLPPolicy/dLoss 8.42905e-05 Iteration 150 MetaTest/Average/AverageDiscountedReturn -52.4319 MetaTest/Average/AverageReturn -52.4319 MetaTest/Average/Iteration 150 MetaTest/Average/MaxReturn -40.8627 MetaTest/Average/MinReturn -120.099 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.1683 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.4319 MetaTest/__unnamed_task__/AverageReturn -52.4319 MetaTest/__unnamed_task__/Iteration 150 MetaTest/__unnamed_task__/MaxReturn -40.8627 MetaTest/__unnamed_task__/MinReturn -120.099 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.1683 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.248e+06 __unnamed_task__/AverageDiscountedReturn -29.9728 __unnamed_task__/AverageReturn -54.4726 __unnamed_task__/Iteration 150 __unnamed_task__/MaxReturn -41.965 __unnamed_task__/MinReturn -101.738 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.90933 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 15:10:29 | [maml_trainer] epoch #151 | Sampling for adapation and meta-testing... 2025-04-06 15:14:36 | [maml_trainer] epoch #151 | Finished meta-testing... 2025-04-06 15:14:36 | [maml_trainer] epoch #151 | Saving snapshot... 2025-04-06 15:15:00 | [maml_trainer] epoch #151 | Saved 2025-04-06 15:15:00 | [maml_trainer] epoch #151 | Time 254144.09 s 2025-04-06 15:15:00 | [maml_trainer] epoch #151 | EpochTime 1761.94 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.7976 Average/AverageReturn -53.9082 Average/Iteration 151 Average/MaxReturn 24.2686 Average/MinReturn -93.6879 Average/NumEpisodes 120 Average/StdReturn 10.8602 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89356 GaussianMLPPolicy/KLAfter 0.00108715 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.99141e-05 GaussianMLPPolicy/LossBefore 1.86761e-09 GaussianMLPPolicy/dLoss -1.99122e-05 Iteration 151 MetaTest/Average/AverageDiscountedReturn -53.4629 MetaTest/Average/AverageReturn -53.4629 MetaTest/Average/Iteration 151 MetaTest/Average/MaxReturn -43.275 MetaTest/Average/MinReturn -69.8149 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.53774 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.4629 MetaTest/__unnamed_task__/AverageReturn -53.4629 MetaTest/__unnamed_task__/Iteration 151 MetaTest/__unnamed_task__/MaxReturn -43.275 MetaTest/__unnamed_task__/MinReturn -69.8149 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.53774 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.296e+06 __unnamed_task__/AverageDiscountedReturn -29.7976 __unnamed_task__/AverageReturn -53.9082 __unnamed_task__/Iteration 151 __unnamed_task__/MaxReturn 24.2686 __unnamed_task__/MinReturn -93.6879 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.8602 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 15:40:00 | [maml_trainer] epoch #152 | Sampling for adapation and meta-testing... 2025-04-06 15:44:09 | [maml_trainer] epoch #152 | Finished meta-testing... 2025-04-06 15:44:09 | [maml_trainer] epoch #152 | Saving snapshot... 2025-04-06 15:44:32 | [maml_trainer] epoch #152 | Saved 2025-04-06 15:44:32 | [maml_trainer] epoch #152 | Time 255916.35 s 2025-04-06 15:44:32 | [maml_trainer] epoch #152 | EpochTime 1772.26 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.9475 Average/AverageReturn -55.4914 Average/Iteration 152 Average/MaxReturn -19.0514 Average/MinReturn -137.894 Average/NumEpisodes 120 Average/StdReturn 13.1645 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.8957 GaussianMLPPolicy/KLAfter 0.002448 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.90951e-05 GaussianMLPPolicy/LossBefore 5.96046e-10 GaussianMLPPolicy/dLoss -2.90945e-05 Iteration 152 MetaTest/Average/AverageDiscountedReturn -51.2971 MetaTest/Average/AverageReturn -51.2971 MetaTest/Average/Iteration 152 MetaTest/Average/MaxReturn -43.5164 MetaTest/Average/MinReturn -60.1193 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.27962 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2971 MetaTest/__unnamed_task__/AverageReturn -51.2971 MetaTest/__unnamed_task__/Iteration 152 MetaTest/__unnamed_task__/MaxReturn -43.5164 MetaTest/__unnamed_task__/MinReturn -60.1193 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.27962 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.344e+06 __unnamed_task__/AverageDiscountedReturn -29.9475 __unnamed_task__/AverageReturn -55.4914 __unnamed_task__/Iteration 152 __unnamed_task__/MaxReturn -19.0514 __unnamed_task__/MinReturn -137.894 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 13.1645 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 16:09:35 | [maml_trainer] epoch #153 | Sampling for adapation and meta-testing... 2025-04-06 16:13:47 | [maml_trainer] epoch #153 | Finished meta-testing... 2025-04-06 16:13:47 | [maml_trainer] epoch #153 | Saving snapshot... 2025-04-06 16:14:10 | [maml_trainer] epoch #153 | Saved 2025-04-06 16:14:10 | [maml_trainer] epoch #153 | Time 257694.17 s 2025-04-06 16:14:10 | [maml_trainer] epoch #153 | EpochTime 1777.82 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.5656 Average/AverageReturn -54.3205 Average/Iteration 153 Average/MaxReturn -41.1859 Average/MinReturn -130.043 Average/NumEpisodes 120 Average/StdReturn 11.8205 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89726 GaussianMLPPolicy/KLAfter 0.00199823 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.73594e-05 GaussianMLPPolicy/LossBefore -3.73522e-09 GaussianMLPPolicy/dLoss -7.73631e-05 Iteration 153 MetaTest/Average/AverageDiscountedReturn -59.6633 MetaTest/Average/AverageReturn -59.6633 MetaTest/Average/Iteration 153 MetaTest/Average/MaxReturn -41.7943 MetaTest/Average/MinReturn -150.556 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.7412 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -59.6633 MetaTest/__unnamed_task__/AverageReturn -59.6633 MetaTest/__unnamed_task__/Iteration 153 MetaTest/__unnamed_task__/MaxReturn -41.7943 MetaTest/__unnamed_task__/MinReturn -150.556 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.7412 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.392e+06 __unnamed_task__/AverageDiscountedReturn -29.5656 __unnamed_task__/AverageReturn -54.3205 __unnamed_task__/Iteration 153 __unnamed_task__/MaxReturn -41.1859 __unnamed_task__/MinReturn -130.043 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.8205 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 16:39:22 | [maml_trainer] epoch #154 | Sampling for adapation and meta-testing... 2025-04-06 16:43:33 | [maml_trainer] epoch #154 | Finished meta-testing... 2025-04-06 16:43:33 | [maml_trainer] epoch #154 | Saving snapshot... 2025-04-06 16:43:56 | [maml_trainer] epoch #154 | Saved 2025-04-06 16:43:56 | [maml_trainer] epoch #154 | Time 259480.03 s 2025-04-06 16:43:56 | [maml_trainer] epoch #154 | EpochTime 1785.85 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.9334 Average/AverageReturn -55.2007 Average/Iteration 154 Average/MaxReturn -41.8064 Average/MinReturn -144.594 Average/NumEpisodes 120 Average/StdReturn 13.066 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89683 GaussianMLPPolicy/KLAfter 0.00161973 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.2803e-05 GaussianMLPPolicy/LossBefore -5.08626e-09 GaussianMLPPolicy/dLoss 2.27979e-05 Iteration 154 MetaTest/Average/AverageDiscountedReturn -57.7769 MetaTest/Average/AverageReturn -57.7769 MetaTest/Average/Iteration 154 MetaTest/Average/MaxReturn -41.6841 MetaTest/Average/MinReturn -112.182 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.5852 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -57.7769 MetaTest/__unnamed_task__/AverageReturn -57.7769 MetaTest/__unnamed_task__/Iteration 154 MetaTest/__unnamed_task__/MaxReturn -41.6841 MetaTest/__unnamed_task__/MinReturn -112.182 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.5852 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.44e+06 __unnamed_task__/AverageDiscountedReturn -29.9334 __unnamed_task__/AverageReturn -55.2007 __unnamed_task__/Iteration 154 __unnamed_task__/MaxReturn -41.8064 __unnamed_task__/MinReturn -144.594 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 13.066 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 17:09:15 | [maml_trainer] epoch #155 | Sampling for adapation and meta-testing... 2025-04-06 17:13:29 | [maml_trainer] epoch #155 | Finished meta-testing... 2025-04-06 17:13:29 | [maml_trainer] epoch #155 | Saving snapshot... 2025-04-06 17:13:53 | [maml_trainer] epoch #155 | Saved 2025-04-06 17:13:53 | [maml_trainer] epoch #155 | Time 261277.29 s 2025-04-06 17:13:53 | [maml_trainer] epoch #155 | EpochTime 1797.25 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.68 Average/AverageReturn -54.4395 Average/Iteration 155 Average/MaxReturn -31.6299 Average/MinReturn -135.771 Average/NumEpisodes 120 Average/StdReturn 11.9795 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89672 GaussianMLPPolicy/KLAfter 0.00135864 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.9565e-05 GaussianMLPPolicy/LossBefore -7.43071e-09 GaussianMLPPolicy/dLoss 4.95576e-05 Iteration 155 MetaTest/Average/AverageDiscountedReturn -54.2959 MetaTest/Average/AverageReturn -54.2959 MetaTest/Average/Iteration 155 MetaTest/Average/MaxReturn -42.9612 MetaTest/Average/MinReturn -82.7055 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.89392 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.2959 MetaTest/__unnamed_task__/AverageReturn -54.2959 MetaTest/__unnamed_task__/Iteration 155 MetaTest/__unnamed_task__/MaxReturn -42.9612 MetaTest/__unnamed_task__/MinReturn -82.7055 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.89392 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.488e+06 __unnamed_task__/AverageDiscountedReturn -29.68 __unnamed_task__/AverageReturn -54.4395 __unnamed_task__/Iteration 155 __unnamed_task__/MaxReturn -31.6299 __unnamed_task__/MinReturn -135.771 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.9795 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 17:38:56 | [maml_trainer] epoch #156 | Sampling for adapation and meta-testing... 2025-04-06 17:43:05 | [maml_trainer] epoch #156 | Finished meta-testing... 2025-04-06 17:43:05 | [maml_trainer] epoch #156 | Saving snapshot... 2025-04-06 17:43:29 | [maml_trainer] epoch #156 | Saved 2025-04-06 17:43:29 | [maml_trainer] epoch #156 | Time 263053.05 s 2025-04-06 17:43:29 | [maml_trainer] epoch #156 | EpochTime 1775.76 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.009 Average/AverageReturn -52.2083 Average/Iteration 156 Average/MaxReturn 1.7885 Average/MinReturn -139.842 Average/NumEpisodes 120 Average/StdReturn 12.5974 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89661 GaussianMLPPolicy/KLAfter 0.0020529 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.92978e-05 GaussianMLPPolicy/LossBefore 6.39757e-09 GaussianMLPPolicy/dLoss 2.93042e-05 Iteration 156 MetaTest/Average/AverageDiscountedReturn -51.6631 MetaTest/Average/AverageReturn -51.6631 MetaTest/Average/Iteration 156 MetaTest/Average/MaxReturn -38.4777 MetaTest/Average/MinReturn -67.0042 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.38126 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6631 MetaTest/__unnamed_task__/AverageReturn -51.6631 MetaTest/__unnamed_task__/Iteration 156 MetaTest/__unnamed_task__/MaxReturn -38.4777 MetaTest/__unnamed_task__/MinReturn -67.0042 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.38126 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.536e+06 __unnamed_task__/AverageDiscountedReturn -29.009 __unnamed_task__/AverageReturn -52.2083 __unnamed_task__/Iteration 156 __unnamed_task__/MaxReturn 1.7885 __unnamed_task__/MinReturn -139.842 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.5974 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 18:08:42 | [maml_trainer] epoch #157 | Sampling for adapation and meta-testing... 2025-04-06 18:12:54 | [maml_trainer] epoch #157 | Finished meta-testing... 2025-04-06 18:12:54 | [maml_trainer] epoch #157 | Saving snapshot... 2025-04-06 18:13:17 | [maml_trainer] epoch #157 | Saved 2025-04-06 18:13:17 | [maml_trainer] epoch #157 | Time 264841.07 s 2025-04-06 18:13:17 | [maml_trainer] epoch #157 | EpochTime 1788.01 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.2642 Average/AverageReturn -53.1274 Average/Iteration 157 Average/MaxReturn -40.9791 Average/MinReturn -100.876 Average/NumEpisodes 120 Average/StdReturn 8.88837 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89662 GaussianMLPPolicy/KLAfter 0.00247779 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.34019e-05 GaussianMLPPolicy/LossBefore 4.29153e-09 GaussianMLPPolicy/dLoss 1.34062e-05 Iteration 157 MetaTest/Average/AverageDiscountedReturn -53.4563 MetaTest/Average/AverageReturn -53.4563 MetaTest/Average/Iteration 157 MetaTest/Average/MaxReturn -43.5865 MetaTest/Average/MinReturn -76.2738 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.2838 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.4563 MetaTest/__unnamed_task__/AverageReturn -53.4563 MetaTest/__unnamed_task__/Iteration 157 MetaTest/__unnamed_task__/MaxReturn -43.5865 MetaTest/__unnamed_task__/MinReturn -76.2738 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.2838 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.584e+06 __unnamed_task__/AverageDiscountedReturn -29.2642 __unnamed_task__/AverageReturn -53.1274 __unnamed_task__/Iteration 157 __unnamed_task__/MaxReturn -40.9791 __unnamed_task__/MinReturn -100.876 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.88837 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 18:38:32 | [maml_trainer] epoch #158 | Sampling for adapation and meta-testing... 2025-04-06 18:42:43 | [maml_trainer] epoch #158 | Finished meta-testing... 2025-04-06 18:42:43 | [maml_trainer] epoch #158 | Saving snapshot... 2025-04-06 18:43:06 | [maml_trainer] epoch #158 | Saved 2025-04-06 18:43:06 | [maml_trainer] epoch #158 | Time 266630.29 s 2025-04-06 18:43:06 | [maml_trainer] epoch #158 | EpochTime 1789.22 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.1147 Average/AverageReturn -52.6239 Average/Iteration 158 Average/MaxReturn 509.617 Average/MinReturn -177.78 Average/NumEpisodes 120 Average/StdReturn 57.332 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89545 GaussianMLPPolicy/KLAfter 0.00347703 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.42438e-06 GaussianMLPPolicy/LossBefore 7.30157e-10 GaussianMLPPolicy/dLoss -6.42365e-06 Iteration 158 MetaTest/Average/AverageDiscountedReturn -51.8264 MetaTest/Average/AverageReturn -51.8264 MetaTest/Average/Iteration 158 MetaTest/Average/MaxReturn -42.8014 MetaTest/Average/MinReturn -70.9208 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.50375 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.8264 MetaTest/__unnamed_task__/AverageReturn -51.8264 MetaTest/__unnamed_task__/Iteration 158 MetaTest/__unnamed_task__/MaxReturn -42.8014 MetaTest/__unnamed_task__/MinReturn -70.9208 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.50375 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.632e+06 __unnamed_task__/AverageDiscountedReturn -29.1147 __unnamed_task__/AverageReturn -52.6239 __unnamed_task__/Iteration 158 __unnamed_task__/MaxReturn 509.617 __unnamed_task__/MinReturn -177.78 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 57.332 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 19:08:15 | [maml_trainer] epoch #159 | Sampling for adapation and meta-testing... 2025-04-06 19:12:27 | [maml_trainer] epoch #159 | Finished meta-testing... 2025-04-06 19:12:27 | [maml_trainer] epoch #159 | Saving snapshot... 2025-04-06 19:12:50 | [maml_trainer] epoch #159 | Saved 2025-04-06 19:12:50 | [maml_trainer] epoch #159 | Time 268414.02 s 2025-04-06 19:12:50 | [maml_trainer] epoch #159 | EpochTime 1783.72 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.4445 Average/AverageReturn -53.944 Average/Iteration 159 Average/MaxReturn -39.3463 Average/MinReturn -104.588 Average/NumEpisodes 120 Average/StdReturn 9.28087 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89297 GaussianMLPPolicy/KLAfter 0.00344776 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.2365e-05 GaussianMLPPolicy/LossBefore -2.78155e-10 GaussianMLPPolicy/dLoss 5.23647e-05 Iteration 159 MetaTest/Average/AverageDiscountedReturn -55.6394 MetaTest/Average/AverageReturn -55.6394 MetaTest/Average/Iteration 159 MetaTest/Average/MaxReturn -43.485 MetaTest/Average/MinReturn -127.339 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.335 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.6394 MetaTest/__unnamed_task__/AverageReturn -55.6394 MetaTest/__unnamed_task__/Iteration 159 MetaTest/__unnamed_task__/MaxReturn -43.485 MetaTest/__unnamed_task__/MinReturn -127.339 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.335 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.68e+06 __unnamed_task__/AverageDiscountedReturn -29.4445 __unnamed_task__/AverageReturn -53.944 __unnamed_task__/Iteration 159 __unnamed_task__/MaxReturn -39.3463 __unnamed_task__/MinReturn -104.588 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.28087 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 19:38:05 | [maml_trainer] epoch #160 | Sampling for adapation and meta-testing... 2025-04-06 19:42:12 | [maml_trainer] epoch #160 | Finished meta-testing... 2025-04-06 19:42:12 | [maml_trainer] epoch #160 | Saving snapshot... 2025-04-06 19:42:35 | [maml_trainer] epoch #160 | Saved 2025-04-06 19:42:35 | [maml_trainer] epoch #160 | Time 270199.62 s 2025-04-06 19:42:35 | [maml_trainer] epoch #160 | EpochTime 1785.60 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.8954 Average/AverageReturn -53.1207 Average/Iteration 160 Average/MaxReturn -41.6086 Average/MinReturn -109.475 Average/NumEpisodes 120 Average/StdReturn 9.91445 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89155 GaussianMLPPolicy/KLAfter 0.00265257 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.81773e-06 GaussianMLPPolicy/LossBefore 1.19209e-10 GaussianMLPPolicy/dLoss -5.81761e-06 Iteration 160 MetaTest/Average/AverageDiscountedReturn -54.7186 MetaTest/Average/AverageReturn -54.7186 MetaTest/Average/Iteration 160 MetaTest/Average/MaxReturn -44.638 MetaTest/Average/MinReturn -106.729 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.8087 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.7186 MetaTest/__unnamed_task__/AverageReturn -54.7186 MetaTest/__unnamed_task__/Iteration 160 MetaTest/__unnamed_task__/MaxReturn -44.638 MetaTest/__unnamed_task__/MinReturn -106.729 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.8087 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.728e+06 __unnamed_task__/AverageDiscountedReturn -28.8954 __unnamed_task__/AverageReturn -53.1207 __unnamed_task__/Iteration 160 __unnamed_task__/MaxReturn -41.6086 __unnamed_task__/MinReturn -109.475 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.91445 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 20:07:55 | [maml_trainer] epoch #161 | Sampling for adapation and meta-testing... 2025-04-06 20:12:07 | [maml_trainer] epoch #161 | Finished meta-testing... 2025-04-06 20:12:07 | [maml_trainer] epoch #161 | Saving snapshot... 2025-04-06 20:12:30 | [maml_trainer] epoch #161 | Saved 2025-04-06 20:12:30 | [maml_trainer] epoch #161 | Time 271994.67 s 2025-04-06 20:12:30 | [maml_trainer] epoch #161 | EpochTime 1795.04 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.3692 Average/AverageReturn -50.0486 Average/Iteration 161 Average/MaxReturn 78.6825 Average/MinReturn -86.4224 Average/NumEpisodes 120 Average/StdReturn 13.8374 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89077 GaussianMLPPolicy/KLAfter 0.00143265 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.50599e-05 GaussianMLPPolicy/LossBefore -2.1855e-09 GaussianMLPPolicy/dLoss 2.50578e-05 Iteration 161 MetaTest/Average/AverageDiscountedReturn -49.3308 MetaTest/Average/AverageReturn -49.3308 MetaTest/Average/Iteration 161 MetaTest/Average/MaxReturn -43.1038 MetaTest/Average/MinReturn -58.5326 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.6073 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.3308 MetaTest/__unnamed_task__/AverageReturn -49.3308 MetaTest/__unnamed_task__/Iteration 161 MetaTest/__unnamed_task__/MaxReturn -43.1038 MetaTest/__unnamed_task__/MinReturn -58.5326 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.6073 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.776e+06 __unnamed_task__/AverageDiscountedReturn -28.3692 __unnamed_task__/AverageReturn -50.0486 __unnamed_task__/Iteration 161 __unnamed_task__/MaxReturn 78.6825 __unnamed_task__/MinReturn -86.4224 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 13.8374 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 20:37:41 | [maml_trainer] epoch #162 | Sampling for adapation and meta-testing... 2025-04-06 20:41:55 | [maml_trainer] epoch #162 | Finished meta-testing... 2025-04-06 20:41:55 | [maml_trainer] epoch #162 | Saving snapshot... 2025-04-06 20:42:18 | [maml_trainer] epoch #162 | Saved 2025-04-06 20:42:18 | [maml_trainer] epoch #162 | Time 273782.69 s 2025-04-06 20:42:18 | [maml_trainer] epoch #162 | EpochTime 1788.02 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.7132 Average/AverageReturn -52.0309 Average/Iteration 162 Average/MaxReturn -41.826 Average/MinReturn -124.176 Average/NumEpisodes 120 Average/StdReturn 9.13809 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.89026 GaussianMLPPolicy/KLAfter 0.000828314 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.1327e-05 GaussianMLPPolicy/LossBefore -4.01338e-09 GaussianMLPPolicy/dLoss 1.1323e-05 Iteration 162 MetaTest/Average/AverageDiscountedReturn -52.2269 MetaTest/Average/AverageReturn -52.2269 MetaTest/Average/Iteration 162 MetaTest/Average/MaxReturn -43.4828 MetaTest/Average/MinReturn -90.317 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.5575 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2269 MetaTest/__unnamed_task__/AverageReturn -52.2269 MetaTest/__unnamed_task__/Iteration 162 MetaTest/__unnamed_task__/MaxReturn -43.4828 MetaTest/__unnamed_task__/MinReturn -90.317 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.5575 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.824e+06 __unnamed_task__/AverageDiscountedReturn -28.7132 __unnamed_task__/AverageReturn -52.0309 __unnamed_task__/Iteration 162 __unnamed_task__/MaxReturn -41.826 __unnamed_task__/MinReturn -124.176 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.13809 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-06 21:07:33 | [maml_trainer] epoch #163 | Sampling for adapation and meta-testing... 2025-04-06 21:11:45 | [maml_trainer] epoch #163 | Finished meta-testing... 2025-04-06 21:11:45 | [maml_trainer] epoch #163 | Saving snapshot... 2025-04-06 21:12:09 | [maml_trainer] epoch #163 | Saved 2025-04-06 21:12:09 | [maml_trainer] epoch #163 | Time 275573.09 s 2025-04-06 21:12:09 | [maml_trainer] epoch #163 | EpochTime 1790.40 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.4339 Average/AverageReturn -51.2563 Average/Iteration 163 Average/MaxReturn -42.7068 Average/MinReturn -90.3291 Average/NumEpisodes 120 Average/StdReturn 6.43503 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88865 GaussianMLPPolicy/KLAfter 0.00101748 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.8251e-06 GaussianMLPPolicy/LossBefore 4.17232e-09 GaussianMLPPolicy/dLoss -8.82093e-06 Iteration 163 MetaTest/Average/AverageDiscountedReturn -52.1758 MetaTest/Average/AverageReturn -52.1758 MetaTest/Average/Iteration 163 MetaTest/Average/MaxReturn -43.2032 MetaTest/Average/MinReturn -81.7468 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.47279 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.1758 MetaTest/__unnamed_task__/AverageReturn -52.1758 MetaTest/__unnamed_task__/Iteration 163 MetaTest/__unnamed_task__/MaxReturn -43.2032 MetaTest/__unnamed_task__/MinReturn -81.7468 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.47279 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.872e+06 __unnamed_task__/AverageDiscountedReturn -28.4339 __unnamed_task__/AverageReturn -51.2563 __unnamed_task__/Iteration 163 __unnamed_task__/MaxReturn -42.7068 __unnamed_task__/MinReturn -90.3291 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.43503 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 21:37:28 | [maml_trainer] epoch #164 | Sampling for adapation and meta-testing... 2025-04-06 21:41:40 | [maml_trainer] epoch #164 | Finished meta-testing... 2025-04-06 21:41:40 | [maml_trainer] epoch #164 | Saving snapshot... 2025-04-06 21:42:03 | [maml_trainer] epoch #164 | Saved 2025-04-06 21:42:03 | [maml_trainer] epoch #164 | Time 277367.76 s 2025-04-06 21:42:03 | [maml_trainer] epoch #164 | EpochTime 1794.66 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.6812 Average/AverageReturn -51.8748 Average/Iteration 164 Average/MaxReturn -39.5472 Average/MinReturn -93.8018 Average/NumEpisodes 120 Average/StdReturn 7.77734 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88776 GaussianMLPPolicy/KLAfter 0.00104438 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.77709e-05 GaussianMLPPolicy/LossBefore -3.41733e-09 GaussianMLPPolicy/dLoss 2.77675e-05 Iteration 164 MetaTest/Average/AverageDiscountedReturn -49.4038 MetaTest/Average/AverageReturn -49.4038 MetaTest/Average/Iteration 164 MetaTest/Average/MaxReturn -44.7006 MetaTest/Average/MinReturn -59.8569 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.28248 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.4038 MetaTest/__unnamed_task__/AverageReturn -49.4038 MetaTest/__unnamed_task__/Iteration 164 MetaTest/__unnamed_task__/MaxReturn -44.7006 MetaTest/__unnamed_task__/MinReturn -59.8569 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.28248 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.92e+06 __unnamed_task__/AverageDiscountedReturn -28.6812 __unnamed_task__/AverageReturn -51.8748 __unnamed_task__/Iteration 164 __unnamed_task__/MaxReturn -39.5472 __unnamed_task__/MinReturn -93.8018 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.77734 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 22:07:36 | [maml_trainer] epoch #165 | Sampling for adapation and meta-testing... 2025-04-06 22:11:49 | [maml_trainer] epoch #165 | Finished meta-testing... 2025-04-06 22:11:49 | [maml_trainer] epoch #165 | Saving snapshot... 2025-04-06 22:12:12 | [maml_trainer] epoch #165 | Saved 2025-04-06 22:12:12 | [maml_trainer] epoch #165 | Time 279176.23 s 2025-04-06 22:12:12 | [maml_trainer] epoch #165 | EpochTime 1808.47 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.4096 Average/AverageReturn -50.8491 Average/Iteration 165 Average/MaxReturn -42.8447 Average/MinReturn -70.5569 Average/NumEpisodes 120 Average/StdReturn 5.25015 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88774 GaussianMLPPolicy/KLAfter 0.00135766 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.26017e-05 GaussianMLPPolicy/LossBefore -2.22524e-09 GaussianMLPPolicy/dLoss 2.25995e-05 Iteration 165 MetaTest/Average/AverageDiscountedReturn -49.5613 MetaTest/Average/AverageReturn -49.5613 MetaTest/Average/Iteration 165 MetaTest/Average/MaxReturn -41.5629 MetaTest/Average/MinReturn -56.2934 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.44545 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5613 MetaTest/__unnamed_task__/AverageReturn -49.5613 MetaTest/__unnamed_task__/Iteration 165 MetaTest/__unnamed_task__/MaxReturn -41.5629 MetaTest/__unnamed_task__/MinReturn -56.2934 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.44545 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 7.968e+06 __unnamed_task__/AverageDiscountedReturn -28.4096 __unnamed_task__/AverageReturn -50.8491 __unnamed_task__/Iteration 165 __unnamed_task__/MaxReturn -42.8447 __unnamed_task__/MinReturn -70.5569 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.25015 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 22:37:24 | [maml_trainer] epoch #166 | Sampling for adapation and meta-testing... 2025-04-06 22:41:37 | [maml_trainer] epoch #166 | Finished meta-testing... 2025-04-06 22:41:37 | [maml_trainer] epoch #166 | Saving snapshot... 2025-04-06 22:42:00 | [maml_trainer] epoch #166 | Saved 2025-04-06 22:42:00 | [maml_trainer] epoch #166 | Time 280964.34 s 2025-04-06 22:42:00 | [maml_trainer] epoch #166 | EpochTime 1788.10 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.3978 Average/AverageReturn -51.2251 Average/Iteration 166 Average/MaxReturn -41.9919 Average/MinReturn -81.4965 Average/NumEpisodes 120 Average/StdReturn 5.98791 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88722 GaussianMLPPolicy/KLAfter 0.00107252 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.52723e-05 GaussianMLPPolicy/LossBefore -1.34707e-08 GaussianMLPPolicy/dLoss -4.52858e-05 Iteration 166 MetaTest/Average/AverageDiscountedReturn -50.5331 MetaTest/Average/AverageReturn -50.5331 MetaTest/Average/Iteration 166 MetaTest/Average/MaxReturn -43.5633 MetaTest/Average/MinReturn -55.647 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.03696 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5331 MetaTest/__unnamed_task__/AverageReturn -50.5331 MetaTest/__unnamed_task__/Iteration 166 MetaTest/__unnamed_task__/MaxReturn -43.5633 MetaTest/__unnamed_task__/MinReturn -55.647 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.03696 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.016e+06 __unnamed_task__/AverageDiscountedReturn -28.3978 __unnamed_task__/AverageReturn -51.2251 __unnamed_task__/Iteration 166 __unnamed_task__/MaxReturn -41.9919 __unnamed_task__/MinReturn -81.4965 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.98791 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 23:07:10 | [maml_trainer] epoch #167 | Sampling for adapation and meta-testing... 2025-04-06 23:11:20 | [maml_trainer] epoch #167 | Finished meta-testing... 2025-04-06 23:11:20 | [maml_trainer] epoch #167 | Saving snapshot... 2025-04-06 23:11:44 | [maml_trainer] epoch #167 | Saved 2025-04-06 23:11:44 | [maml_trainer] epoch #167 | Time 282748.02 s 2025-04-06 23:11:44 | [maml_trainer] epoch #167 | EpochTime 1783.67 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.8953 Average/AverageReturn -49.6875 Average/Iteration 167 Average/MaxReturn 15.8952 Average/MinReturn -68.2804 Average/NumEpisodes 120 Average/StdReturn 8.24116 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88638 GaussianMLPPolicy/KLAfter 0.00275432 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000158284 GaussianMLPPolicy/LossBefore -1.82788e-08 GaussianMLPPolicy/dLoss 0.000158266 Iteration 167 MetaTest/Average/AverageDiscountedReturn -49.217 MetaTest/Average/AverageReturn -49.217 MetaTest/Average/Iteration 167 MetaTest/Average/MaxReturn -39.0323 MetaTest/Average/MinReturn -61.0983 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.6955 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.217 MetaTest/__unnamed_task__/AverageReturn -49.217 MetaTest/__unnamed_task__/Iteration 167 MetaTest/__unnamed_task__/MaxReturn -39.0323 MetaTest/__unnamed_task__/MinReturn -61.0983 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.6955 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.064e+06 __unnamed_task__/AverageDiscountedReturn -27.8953 __unnamed_task__/AverageReturn -49.6875 __unnamed_task__/Iteration 167 __unnamed_task__/MaxReturn 15.8952 __unnamed_task__/MinReturn -68.2804 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.24116 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-06 23:36:56 | [maml_trainer] epoch #168 | Sampling for adapation and meta-testing... 2025-04-06 23:41:09 | [maml_trainer] epoch #168 | Finished meta-testing... 2025-04-06 23:41:09 | [maml_trainer] epoch #168 | Saving snapshot... 2025-04-06 23:41:32 | [maml_trainer] epoch #168 | Saved 2025-04-06 23:41:32 | [maml_trainer] epoch #168 | Time 284536.56 s 2025-04-06 23:41:32 | [maml_trainer] epoch #168 | EpochTime 1788.54 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.2717 Average/AverageReturn -45.0028 Average/Iteration 168 Average/MaxReturn 355.204 Average/MinReturn -108.926 Average/NumEpisodes 120 Average/StdReturn 40.5248 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88489 GaussianMLPPolicy/KLAfter 0.00313708 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.51536e-05 GaussianMLPPolicy/LossBefore -1.02818e-09 GaussianMLPPolicy/dLoss -1.51546e-05 Iteration 168 MetaTest/Average/AverageDiscountedReturn -50.1065 MetaTest/Average/AverageReturn -50.1065 MetaTest/Average/Iteration 168 MetaTest/Average/MaxReturn -40.4539 MetaTest/Average/MinReturn -61.9234 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.28822 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.1065 MetaTest/__unnamed_task__/AverageReturn -50.1065 MetaTest/__unnamed_task__/Iteration 168 MetaTest/__unnamed_task__/MaxReturn -40.4539 MetaTest/__unnamed_task__/MinReturn -61.9234 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.28822 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.112e+06 __unnamed_task__/AverageDiscountedReturn -27.2717 __unnamed_task__/AverageReturn -45.0028 __unnamed_task__/Iteration 168 __unnamed_task__/MaxReturn 355.204 __unnamed_task__/MinReturn -108.926 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 40.5248 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 00:06:49 | [maml_trainer] epoch #169 | Sampling for adapation and meta-testing... 2025-04-07 00:10:55 | [maml_trainer] epoch #169 | Finished meta-testing... 2025-04-07 00:10:55 | [maml_trainer] epoch #169 | Saving snapshot... 2025-04-07 00:11:16 | [maml_trainer] epoch #169 | Saved 2025-04-07 00:11:16 | [maml_trainer] epoch #169 | Time 286320.63 s 2025-04-07 00:11:16 | [maml_trainer] epoch #169 | EpochTime 1784.06 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.1185 Average/AverageReturn -51.4442 Average/Iteration 169 Average/MaxReturn -11.9761 Average/MinReturn -107.447 Average/NumEpisodes 120 Average/StdReturn 11.9823 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88359 GaussianMLPPolicy/KLAfter 0.00387623 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.03897e-05 GaussianMLPPolicy/LossBefore -3.77496e-09 GaussianMLPPolicy/dLoss 7.03859e-05 Iteration 169 MetaTest/Average/AverageDiscountedReturn -49.3207 MetaTest/Average/AverageReturn -49.3207 MetaTest/Average/Iteration 169 MetaTest/Average/MaxReturn -43.2061 MetaTest/Average/MinReturn -57.9725 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.01087 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.3207 MetaTest/__unnamed_task__/AverageReturn -49.3207 MetaTest/__unnamed_task__/Iteration 169 MetaTest/__unnamed_task__/MaxReturn -43.2061 MetaTest/__unnamed_task__/MinReturn -57.9725 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.01087 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.16e+06 __unnamed_task__/AverageDiscountedReturn -28.1185 __unnamed_task__/AverageReturn -51.4442 __unnamed_task__/Iteration 169 __unnamed_task__/MaxReturn -11.9761 __unnamed_task__/MinReturn -107.447 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.9823 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 00:34:50 | [maml_trainer] epoch #170 | Sampling for adapation and meta-testing... 2025-04-07 00:38:50 | [maml_trainer] epoch #170 | Finished meta-testing... 2025-04-07 00:38:50 | [maml_trainer] epoch #170 | Saving snapshot... 2025-04-07 00:39:12 | [maml_trainer] epoch #170 | Saved 2025-04-07 00:39:12 | [maml_trainer] epoch #170 | Time 287996.53 s 2025-04-07 00:39:12 | [maml_trainer] epoch #170 | EpochTime 1675.90 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.2569 Average/AverageReturn -52.5721 Average/Iteration 170 Average/MaxReturn -25.7313 Average/MinReturn -151.247 Average/NumEpisodes 120 Average/StdReturn 15.5111 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88284 GaussianMLPPolicy/KLAfter 0.00231294 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.85812e-05 GaussianMLPPolicy/LossBefore 3.47694e-09 GaussianMLPPolicy/dLoss -3.85777e-05 Iteration 170 MetaTest/Average/AverageDiscountedReturn -50.5576 MetaTest/Average/AverageReturn -50.5576 MetaTest/Average/Iteration 170 MetaTest/Average/MaxReturn -40.7147 MetaTest/Average/MinReturn -79.2781 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.08988 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5576 MetaTest/__unnamed_task__/AverageReturn -50.5576 MetaTest/__unnamed_task__/Iteration 170 MetaTest/__unnamed_task__/MaxReturn -40.7147 MetaTest/__unnamed_task__/MinReturn -79.2781 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.08988 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.208e+06 __unnamed_task__/AverageDiscountedReturn -28.2569 __unnamed_task__/AverageReturn -52.5721 __unnamed_task__/Iteration 170 __unnamed_task__/MaxReturn -25.7313 __unnamed_task__/MinReturn -151.247 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 15.5111 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 01:02:58 | [maml_trainer] epoch #171 | Sampling for adapation and meta-testing... 2025-04-07 01:06:58 | [maml_trainer] epoch #171 | Finished meta-testing... 2025-04-07 01:06:59 | [maml_trainer] epoch #171 | Saving snapshot... 2025-04-07 01:07:20 | [maml_trainer] epoch #171 | Saved 2025-04-07 01:07:20 | [maml_trainer] epoch #171 | Time 289684.58 s 2025-04-07 01:07:20 | [maml_trainer] epoch #171 | EpochTime 1688.05 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.1944 Average/AverageReturn -50.9449 Average/Iteration 171 Average/MaxReturn 273.623 Average/MinReturn -174.181 Average/NumEpisodes 120 Average/StdReturn 39.7076 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88283 GaussianMLPPolicy/KLAfter 0.00134532 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.9859e-05 GaussianMLPPolicy/LossBefore -8.19564e-10 GaussianMLPPolicy/dLoss 1.98582e-05 Iteration 171 MetaTest/Average/AverageDiscountedReturn -51.6719 MetaTest/Average/AverageReturn -51.6719 MetaTest/Average/Iteration 171 MetaTest/Average/MaxReturn -42.5015 MetaTest/Average/MinReturn -65.662 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.61795 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6719 MetaTest/__unnamed_task__/AverageReturn -51.6719 MetaTest/__unnamed_task__/Iteration 171 MetaTest/__unnamed_task__/MaxReturn -42.5015 MetaTest/__unnamed_task__/MinReturn -65.662 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.61795 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.256e+06 __unnamed_task__/AverageDiscountedReturn -28.1944 __unnamed_task__/AverageReturn -50.9449 __unnamed_task__/Iteration 171 __unnamed_task__/MaxReturn 273.623 __unnamed_task__/MinReturn -174.181 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 39.7076 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 01:31:01 | [maml_trainer] epoch #172 | Sampling for adapation and meta-testing... 2025-04-07 01:35:02 | [maml_trainer] epoch #172 | Finished meta-testing... 2025-04-07 01:35:02 | [maml_trainer] epoch #172 | Saving snapshot... 2025-04-07 01:35:24 | [maml_trainer] epoch #172 | Saved 2025-04-07 01:35:24 | [maml_trainer] epoch #172 | Time 291368.60 s 2025-04-07 01:35:24 | [maml_trainer] epoch #172 | EpochTime 1684.02 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.9814 Average/AverageReturn -53.4037 Average/Iteration 172 Average/MaxReturn -39.1743 Average/MinReturn -176.847 Average/NumEpisodes 120 Average/StdReturn 20.3584 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88275 GaussianMLPPolicy/KLAfter 0.0017286 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.27351e-06 GaussianMLPPolicy/LossBefore 2.5034e-09 GaussianMLPPolicy/dLoss -3.271e-06 Iteration 172 MetaTest/Average/AverageDiscountedReturn -54.1463 MetaTest/Average/AverageReturn -54.1463 MetaTest/Average/Iteration 172 MetaTest/Average/MaxReturn -43.6847 MetaTest/Average/MinReturn -87.4727 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.9063 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.1463 MetaTest/__unnamed_task__/AverageReturn -54.1463 MetaTest/__unnamed_task__/Iteration 172 MetaTest/__unnamed_task__/MaxReturn -43.6847 MetaTest/__unnamed_task__/MinReturn -87.4727 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.9063 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.304e+06 __unnamed_task__/AverageDiscountedReturn -27.9814 __unnamed_task__/AverageReturn -53.4037 __unnamed_task__/Iteration 172 __unnamed_task__/MaxReturn -39.1743 __unnamed_task__/MinReturn -176.847 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 20.3584 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 01:59:19 | [maml_trainer] epoch #173 | Sampling for adapation and meta-testing... 2025-04-07 02:03:14 | [maml_trainer] epoch #173 | Finished meta-testing... 2025-04-07 02:03:14 | [maml_trainer] epoch #173 | Saving snapshot... 2025-04-07 02:03:35 | [maml_trainer] epoch #173 | Saved 2025-04-07 02:03:35 | [maml_trainer] epoch #173 | Time 293059.23 s 2025-04-07 02:03:35 | [maml_trainer] epoch #173 | EpochTime 1690.63 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.1233 Average/AverageReturn -56.9754 Average/Iteration 173 Average/MaxReturn -21.7759 Average/MinReturn -178.944 Average/NumEpisodes 120 Average/StdReturn 23.9541 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88277 GaussianMLPPolicy/KLAfter 0.00177074 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.81032e-05 GaussianMLPPolicy/LossBefore 9.93411e-10 GaussianMLPPolicy/dLoss 3.81042e-05 Iteration 173 MetaTest/Average/AverageDiscountedReturn -54.0498 MetaTest/Average/AverageReturn -54.0498 MetaTest/Average/Iteration 173 MetaTest/Average/MaxReturn -16.2336 MetaTest/Average/MinReturn -173.532 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 29.9677 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.0498 MetaTest/__unnamed_task__/AverageReturn -54.0498 MetaTest/__unnamed_task__/Iteration 173 MetaTest/__unnamed_task__/MaxReturn -16.2336 MetaTest/__unnamed_task__/MinReturn -173.532 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 29.9677 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.352e+06 __unnamed_task__/AverageDiscountedReturn -29.1233 __unnamed_task__/AverageReturn -56.9754 __unnamed_task__/Iteration 173 __unnamed_task__/MaxReturn -21.7759 __unnamed_task__/MinReturn -178.944 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 23.9541 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 02:27:14 | [maml_trainer] epoch #174 | Sampling for adapation and meta-testing... 2025-04-07 02:31:18 | [maml_trainer] epoch #174 | Finished meta-testing... 2025-04-07 02:31:18 | [maml_trainer] epoch #174 | Saving snapshot... 2025-04-07 02:31:39 | [maml_trainer] epoch #174 | Saved 2025-04-07 02:31:39 | [maml_trainer] epoch #174 | Time 294743.68 s 2025-04-07 02:31:39 | [maml_trainer] epoch #174 | EpochTime 1684.44 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.2745 Average/AverageReturn -53.3917 Average/Iteration 174 Average/MaxReturn -35.5313 Average/MinReturn -160.129 Average/NumEpisodes 120 Average/StdReturn 17.3355 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88269 GaussianMLPPolicy/KLAfter 0.00205254 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.42372e-05 GaussianMLPPolicy/LossBefore 7.05322e-09 GaussianMLPPolicy/dLoss -4.42302e-05 Iteration 174 MetaTest/Average/AverageDiscountedReturn -49.5531 MetaTest/Average/AverageReturn -49.5531 MetaTest/Average/Iteration 174 MetaTest/Average/MaxReturn -42.2303 MetaTest/Average/MinReturn -64.9637 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.92614 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5531 MetaTest/__unnamed_task__/AverageReturn -49.5531 MetaTest/__unnamed_task__/Iteration 174 MetaTest/__unnamed_task__/MaxReturn -42.2303 MetaTest/__unnamed_task__/MinReturn -64.9637 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.92614 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.4e+06 __unnamed_task__/AverageDiscountedReturn -28.2745 __unnamed_task__/AverageReturn -53.3917 __unnamed_task__/Iteration 174 __unnamed_task__/MaxReturn -35.5313 __unnamed_task__/MinReturn -160.129 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 17.3355 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 02:55:17 | [maml_trainer] epoch #175 | Sampling for adapation and meta-testing... 2025-04-07 02:59:15 | [maml_trainer] epoch #175 | Finished meta-testing... 2025-04-07 02:59:15 | [maml_trainer] epoch #175 | Saving snapshot... 2025-04-07 02:59:37 | [maml_trainer] epoch #175 | Saved 2025-04-07 02:59:37 | [maml_trainer] epoch #175 | Time 296421.10 s 2025-04-07 02:59:37 | [maml_trainer] epoch #175 | EpochTime 1677.42 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.5553 Average/AverageReturn -55.9232 Average/Iteration 175 Average/MaxReturn -39.7624 Average/MinReturn -169.222 Average/NumEpisodes 120 Average/StdReturn 23.2932 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88229 GaussianMLPPolicy/KLAfter 0.00211989 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.2347e-05 GaussianMLPPolicy/LossBefore 1.98683e-11 GaussianMLPPolicy/dLoss 3.23471e-05 Iteration 175 MetaTest/Average/AverageDiscountedReturn -58.5743 MetaTest/Average/AverageReturn -58.5743 MetaTest/Average/Iteration 175 MetaTest/Average/MaxReturn -39.2082 MetaTest/Average/MinReturn -143.108 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 28.755 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -58.5743 MetaTest/__unnamed_task__/AverageReturn -58.5743 MetaTest/__unnamed_task__/Iteration 175 MetaTest/__unnamed_task__/MaxReturn -39.2082 MetaTest/__unnamed_task__/MinReturn -143.108 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 28.755 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.448e+06 __unnamed_task__/AverageDiscountedReturn -28.5553 __unnamed_task__/AverageReturn -55.9232 __unnamed_task__/Iteration 175 __unnamed_task__/MaxReturn -39.7624 __unnamed_task__/MinReturn -169.222 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 23.2932 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 03:23:38 | [maml_trainer] epoch #176 | Sampling for adapation and meta-testing... 2025-04-07 03:27:39 | [maml_trainer] epoch #176 | Finished meta-testing... 2025-04-07 03:27:39 | [maml_trainer] epoch #176 | Saving snapshot... 2025-04-07 03:28:01 | [maml_trainer] epoch #176 | Saved 2025-04-07 03:28:01 | [maml_trainer] epoch #176 | Time 298125.52 s 2025-04-07 03:28:01 | [maml_trainer] epoch #176 | EpochTime 1704.41 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.3029 Average/AverageReturn -49.5938 Average/Iteration 176 Average/MaxReturn -38.7661 Average/MinReturn -95.9797 Average/NumEpisodes 120 Average/StdReturn 7.43963 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88222 GaussianMLPPolicy/KLAfter 0.00214522 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.87041e-05 GaussianMLPPolicy/LossBefore -1.42654e-08 GaussianMLPPolicy/dLoss -7.87184e-05 Iteration 176 MetaTest/Average/AverageDiscountedReturn -52.9837 MetaTest/Average/AverageReturn -52.9837 MetaTest/Average/Iteration 176 MetaTest/Average/MaxReturn -42.1409 MetaTest/Average/MinReturn -88.4789 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.478 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.9837 MetaTest/__unnamed_task__/AverageReturn -52.9837 MetaTest/__unnamed_task__/Iteration 176 MetaTest/__unnamed_task__/MaxReturn -42.1409 MetaTest/__unnamed_task__/MinReturn -88.4789 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.478 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.496e+06 __unnamed_task__/AverageDiscountedReturn -27.3029 __unnamed_task__/AverageReturn -49.5938 __unnamed_task__/Iteration 176 __unnamed_task__/MaxReturn -38.7661 __unnamed_task__/MinReturn -95.9797 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.43963 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 03:51:49 | [maml_trainer] epoch #177 | Sampling for adapation and meta-testing... 2025-04-07 03:55:49 | [maml_trainer] epoch #177 | Finished meta-testing... 2025-04-07 03:55:49 | [maml_trainer] epoch #177 | Saving snapshot... 2025-04-07 03:56:10 | [maml_trainer] epoch #177 | Saved 2025-04-07 03:56:10 | [maml_trainer] epoch #177 | Time 299814.90 s 2025-04-07 03:56:10 | [maml_trainer] epoch #177 | EpochTime 1689.38 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.2065 Average/AverageReturn -49.9451 Average/Iteration 177 Average/MaxReturn -38.942 Average/MinReturn -133.38 Average/NumEpisodes 120 Average/StdReturn 11.7083 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88345 GaussianMLPPolicy/KLAfter 0.00095355 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.46566e-05 GaussianMLPPolicy/LossBefore -5.5631e-09 GaussianMLPPolicy/dLoss 6.4651e-05 Iteration 177 MetaTest/Average/AverageDiscountedReturn -54.1295 MetaTest/Average/AverageReturn -54.1295 MetaTest/Average/Iteration 177 MetaTest/Average/MaxReturn -43.1412 MetaTest/Average/MinReturn -122.128 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.0082 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.1295 MetaTest/__unnamed_task__/AverageReturn -54.1295 MetaTest/__unnamed_task__/Iteration 177 MetaTest/__unnamed_task__/MaxReturn -43.1412 MetaTest/__unnamed_task__/MinReturn -122.128 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.0082 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.544e+06 __unnamed_task__/AverageDiscountedReturn -27.2065 __unnamed_task__/AverageReturn -49.9451 __unnamed_task__/Iteration 177 __unnamed_task__/MaxReturn -38.942 __unnamed_task__/MinReturn -133.38 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.7083 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 04:20:22 | [maml_trainer] epoch #178 | Sampling for adapation and meta-testing... 2025-04-07 04:24:22 | [maml_trainer] epoch #178 | Finished meta-testing... 2025-04-07 04:24:22 | [maml_trainer] epoch #178 | Saving snapshot... 2025-04-07 04:24:43 | [maml_trainer] epoch #178 | Saved 2025-04-07 04:24:43 | [maml_trainer] epoch #178 | Time 301527.82 s 2025-04-07 04:24:43 | [maml_trainer] epoch #178 | EpochTime 1712.91 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.458 Average/AverageReturn -50.1993 Average/Iteration 178 Average/MaxReturn -39.3152 Average/MinReturn -130.173 Average/NumEpisodes 120 Average/StdReturn 9.72753 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.8839 GaussianMLPPolicy/KLAfter 0.00145505 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.02652e-05 GaussianMLPPolicy/LossBefore 6.75519e-10 GaussianMLPPolicy/dLoss -4.02645e-05 Iteration 178 MetaTest/Average/AverageDiscountedReturn -50.3102 MetaTest/Average/AverageReturn -50.3102 MetaTest/Average/Iteration 178 MetaTest/Average/MaxReturn -40.5086 MetaTest/Average/MinReturn -70.8456 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.33982 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.3102 MetaTest/__unnamed_task__/AverageReturn -50.3102 MetaTest/__unnamed_task__/Iteration 178 MetaTest/__unnamed_task__/MaxReturn -40.5086 MetaTest/__unnamed_task__/MinReturn -70.8456 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.33982 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.592e+06 __unnamed_task__/AverageDiscountedReturn -27.458 __unnamed_task__/AverageReturn -50.1993 __unnamed_task__/Iteration 178 __unnamed_task__/MaxReturn -39.3152 __unnamed_task__/MinReturn -130.173 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.72753 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 04:48:55 | [maml_trainer] epoch #179 | Sampling for adapation and meta-testing... 2025-04-07 04:52:54 | [maml_trainer] epoch #179 | Finished meta-testing... 2025-04-07 04:52:54 | [maml_trainer] epoch #179 | Saving snapshot... 2025-04-07 04:53:15 | [maml_trainer] epoch #179 | Saved 2025-04-07 04:53:15 | [maml_trainer] epoch #179 | Time 303239.57 s 2025-04-07 04:53:15 | [maml_trainer] epoch #179 | EpochTime 1711.74 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.7507 Average/AverageReturn -45.3876 Average/Iteration 179 Average/MaxReturn 498.814 Average/MinReturn -99.2032 Average/NumEpisodes 120 Average/StdReturn 50.3695 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88369 GaussianMLPPolicy/KLAfter 0.0021785 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.96145e-05 GaussianMLPPolicy/LossBefore 7.30654e-09 GaussianMLPPolicy/dLoss 4.96218e-05 Iteration 179 MetaTest/Average/AverageDiscountedReturn -55.6735 MetaTest/Average/AverageReturn -55.6735 MetaTest/Average/Iteration 179 MetaTest/Average/MaxReturn -44.2199 MetaTest/Average/MinReturn -176.047 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 27.8312 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.6735 MetaTest/__unnamed_task__/AverageReturn -55.6735 MetaTest/__unnamed_task__/Iteration 179 MetaTest/__unnamed_task__/MaxReturn -44.2199 MetaTest/__unnamed_task__/MinReturn -176.047 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 27.8312 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.64e+06 __unnamed_task__/AverageDiscountedReturn -26.7507 __unnamed_task__/AverageReturn -45.3876 __unnamed_task__/Iteration 179 __unnamed_task__/MaxReturn 498.814 __unnamed_task__/MinReturn -99.2032 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 50.3695 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 05:17:27 | [maml_trainer] epoch #180 | Sampling for adapation and meta-testing... 2025-04-07 05:21:26 | [maml_trainer] epoch #180 | Finished meta-testing... 2025-04-07 05:21:26 | [maml_trainer] epoch #180 | Saving snapshot... 2025-04-07 05:21:47 | [maml_trainer] epoch #180 | Saved 2025-04-07 05:21:47 | [maml_trainer] epoch #180 | Time 304951.54 s 2025-04-07 05:21:47 | [maml_trainer] epoch #180 | EpochTime 1711.97 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.1193 Average/AverageReturn -49.059 Average/Iteration 180 Average/MaxReturn -40.892 Average/MinReturn -89.3168 Average/NumEpisodes 120 Average/StdReturn 6.25805 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88436 GaussianMLPPolicy/KLAfter 0.00132284 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.44293e-05 GaussianMLPPolicy/LossBefore -1.13249e-08 GaussianMLPPolicy/dLoss -2.44406e-05 Iteration 180 MetaTest/Average/AverageDiscountedReturn -48.4498 MetaTest/Average/AverageReturn -48.4498 MetaTest/Average/Iteration 180 MetaTest/Average/MaxReturn -42.7588 MetaTest/Average/MinReturn -66.512 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.11066 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.4498 MetaTest/__unnamed_task__/AverageReturn -48.4498 MetaTest/__unnamed_task__/Iteration 180 MetaTest/__unnamed_task__/MaxReturn -42.7588 MetaTest/__unnamed_task__/MinReturn -66.512 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.11066 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.688e+06 __unnamed_task__/AverageDiscountedReturn -27.1193 __unnamed_task__/AverageReturn -49.059 __unnamed_task__/Iteration 180 __unnamed_task__/MaxReturn -40.892 __unnamed_task__/MinReturn -89.3168 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.25805 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 05:45:39 | [maml_trainer] epoch #181 | Sampling for adapation and meta-testing... 2025-04-07 05:49:37 | [maml_trainer] epoch #181 | Finished meta-testing... 2025-04-07 05:49:37 | [maml_trainer] epoch #181 | Saving snapshot... 2025-04-07 05:49:58 | [maml_trainer] epoch #181 | Saved 2025-04-07 05:49:58 | [maml_trainer] epoch #181 | Time 306642.48 s 2025-04-07 05:49:58 | [maml_trainer] epoch #181 | EpochTime 1690.93 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.4349 Average/AverageReturn -49.9102 Average/Iteration 181 Average/MaxReturn -38.2062 Average/MinReturn -144.599 Average/NumEpisodes 120 Average/StdReturn 10.8765 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88504 GaussianMLPPolicy/KLAfter 0.00170528 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.71667e-05 GaussianMLPPolicy/LossBefore -1.23978e-08 GaussianMLPPolicy/dLoss 6.71543e-05 Iteration 181 MetaTest/Average/AverageDiscountedReturn -61.0889 MetaTest/Average/AverageReturn -61.0889 MetaTest/Average/Iteration 181 MetaTest/Average/MaxReturn -39.6333 MetaTest/Average/MinReturn -151.795 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 30.3366 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -61.0889 MetaTest/__unnamed_task__/AverageReturn -61.0889 MetaTest/__unnamed_task__/Iteration 181 MetaTest/__unnamed_task__/MaxReturn -39.6333 MetaTest/__unnamed_task__/MinReturn -151.795 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 30.3366 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.736e+06 __unnamed_task__/AverageDiscountedReturn -27.4349 __unnamed_task__/AverageReturn -49.9102 __unnamed_task__/Iteration 181 __unnamed_task__/MaxReturn -38.2062 __unnamed_task__/MinReturn -144.599 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.8765 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 06:13:42 | [maml_trainer] epoch #182 | Sampling for adapation and meta-testing... 2025-04-07 06:17:40 | [maml_trainer] epoch #182 | Finished meta-testing... 2025-04-07 06:17:40 | [maml_trainer] epoch #182 | Saving snapshot... 2025-04-07 06:18:01 | [maml_trainer] epoch #182 | Saved 2025-04-07 06:18:01 | [maml_trainer] epoch #182 | Time 308325.22 s 2025-04-07 06:18:01 | [maml_trainer] epoch #182 | EpochTime 1682.74 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.2474 Average/AverageReturn -49.1748 Average/Iteration 182 Average/MaxReturn -41.1177 Average/MinReturn -70.4861 Average/NumEpisodes 120 Average/StdReturn 5.44592 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88528 GaussianMLPPolicy/KLAfter 0.00173274 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.35161e-06 GaussianMLPPolicy/LossBefore 7.15256e-09 GaussianMLPPolicy/dLoss 3.35876e-06 Iteration 182 MetaTest/Average/AverageDiscountedReturn -51.5908 MetaTest/Average/AverageReturn -51.5908 MetaTest/Average/Iteration 182 MetaTest/Average/MaxReturn -43.1335 MetaTest/Average/MinReturn -62.6053 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.79998 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.5908 MetaTest/__unnamed_task__/AverageReturn -51.5908 MetaTest/__unnamed_task__/Iteration 182 MetaTest/__unnamed_task__/MaxReturn -43.1335 MetaTest/__unnamed_task__/MinReturn -62.6053 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.79998 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.784e+06 __unnamed_task__/AverageDiscountedReturn -27.2474 __unnamed_task__/AverageReturn -49.1748 __unnamed_task__/Iteration 182 __unnamed_task__/MaxReturn -41.1177 __unnamed_task__/MinReturn -70.4861 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.44592 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 06:42:05 | [maml_trainer] epoch #183 | Sampling for adapation and meta-testing... 2025-04-07 06:46:08 | [maml_trainer] epoch #183 | Finished meta-testing... 2025-04-07 06:46:08 | [maml_trainer] epoch #183 | Saving snapshot... 2025-04-07 06:46:29 | [maml_trainer] epoch #183 | Saved 2025-04-07 06:46:29 | [maml_trainer] epoch #183 | Time 310033.29 s 2025-04-07 06:46:29 | [maml_trainer] epoch #183 | EpochTime 1708.07 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.6977 Average/AverageReturn -50.3764 Average/Iteration 183 Average/MaxReturn -39.9212 Average/MinReturn -77.6768 Average/NumEpisodes 120 Average/StdReturn 6.07879 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88432 GaussianMLPPolicy/KLAfter 0.00221216 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.70467e-05 GaussianMLPPolicy/LossBefore 9.02017e-09 GaussianMLPPolicy/dLoss 6.70557e-05 Iteration 183 MetaTest/Average/AverageDiscountedReturn -50.5177 MetaTest/Average/AverageReturn -50.5177 MetaTest/Average/Iteration 183 MetaTest/Average/MaxReturn -43.1634 MetaTest/Average/MinReturn -64.8364 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.36867 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5177 MetaTest/__unnamed_task__/AverageReturn -50.5177 MetaTest/__unnamed_task__/Iteration 183 MetaTest/__unnamed_task__/MaxReturn -43.1634 MetaTest/__unnamed_task__/MinReturn -64.8364 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.36867 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.832e+06 __unnamed_task__/AverageDiscountedReturn -27.6977 __unnamed_task__/AverageReturn -50.3764 __unnamed_task__/Iteration 183 __unnamed_task__/MaxReturn -39.9212 __unnamed_task__/MinReturn -77.6768 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.07879 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 07:10:41 | [maml_trainer] epoch #184 | Sampling for adapation and meta-testing... 2025-04-07 07:14:41 | [maml_trainer] epoch #184 | Finished meta-testing... 2025-04-07 07:14:41 | [maml_trainer] epoch #184 | Saving snapshot... 2025-04-07 07:15:02 | [maml_trainer] epoch #184 | Saved 2025-04-07 07:15:02 | [maml_trainer] epoch #184 | Time 311746.44 s 2025-04-07 07:15:02 | [maml_trainer] epoch #184 | EpochTime 1713.15 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.6413 Average/AverageReturn -50.3122 Average/Iteration 184 Average/MaxReturn -42.5313 Average/MinReturn -66.1257 Average/NumEpisodes 120 Average/StdReturn 5.03394 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.88151 GaussianMLPPolicy/KLAfter 0.00117574 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.4811e-05 GaussianMLPPolicy/LossBefore 3.3776e-09 GaussianMLPPolicy/dLoss -2.48076e-05 Iteration 184 MetaTest/Average/AverageDiscountedReturn -51.5448 MetaTest/Average/AverageReturn -51.5448 MetaTest/Average/Iteration 184 MetaTest/Average/MaxReturn -44.4458 MetaTest/Average/MinReturn -65.8046 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.97126 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.5448 MetaTest/__unnamed_task__/AverageReturn -51.5448 MetaTest/__unnamed_task__/Iteration 184 MetaTest/__unnamed_task__/MaxReturn -44.4458 MetaTest/__unnamed_task__/MinReturn -65.8046 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.97126 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.88e+06 __unnamed_task__/AverageDiscountedReturn -27.6413 __unnamed_task__/AverageReturn -50.3122 __unnamed_task__/Iteration 184 __unnamed_task__/MaxReturn -42.5313 __unnamed_task__/MinReturn -66.1257 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.03394 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 07:39:17 | [maml_trainer] epoch #185 | Sampling for adapation and meta-testing... 2025-04-07 07:43:19 | [maml_trainer] epoch #185 | Finished meta-testing... 2025-04-07 07:43:19 | [maml_trainer] epoch #185 | Saving snapshot... 2025-04-07 07:43:39 | [maml_trainer] epoch #185 | Saved 2025-04-07 07:43:39 | [maml_trainer] epoch #185 | Time 313463.84 s 2025-04-07 07:43:39 | [maml_trainer] epoch #185 | EpochTime 1717.40 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.7723 Average/AverageReturn -50.7196 Average/Iteration 185 Average/MaxReturn -41.712 Average/MinReturn -70.955 Average/NumEpisodes 120 Average/StdReturn 5.86679 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.8767 GaussianMLPPolicy/KLAfter 0.00139659 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.33665e-05 GaussianMLPPolicy/LossBefore -1.20401e-08 GaussianMLPPolicy/dLoss 1.33545e-05 Iteration 185 MetaTest/Average/AverageDiscountedReturn -50.9746 MetaTest/Average/AverageReturn -50.9746 MetaTest/Average/Iteration 185 MetaTest/Average/MaxReturn -43.3642 MetaTest/Average/MinReturn -61.0086 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.00824 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.9746 MetaTest/__unnamed_task__/AverageReturn -50.9746 MetaTest/__unnamed_task__/Iteration 185 MetaTest/__unnamed_task__/MaxReturn -43.3642 MetaTest/__unnamed_task__/MinReturn -61.0086 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.00824 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.928e+06 __unnamed_task__/AverageDiscountedReturn -27.7723 __unnamed_task__/AverageReturn -50.7196 __unnamed_task__/Iteration 185 __unnamed_task__/MaxReturn -41.712 __unnamed_task__/MinReturn -70.955 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.86679 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 08:07:50 | [maml_trainer] epoch #186 | Sampling for adapation and meta-testing... 2025-04-07 08:11:48 | [maml_trainer] epoch #186 | Finished meta-testing... 2025-04-07 08:11:48 | [maml_trainer] epoch #186 | Saving snapshot... 2025-04-07 08:12:09 | [maml_trainer] epoch #186 | Saved 2025-04-07 08:12:09 | [maml_trainer] epoch #186 | Time 315173.48 s 2025-04-07 08:12:09 | [maml_trainer] epoch #186 | EpochTime 1709.64 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.9677 Average/AverageReturn -51.2916 Average/Iteration 186 Average/MaxReturn -40.6604 Average/MinReturn -75.8067 Average/NumEpisodes 120 Average/StdReturn 5.95813 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.87338 GaussianMLPPolicy/KLAfter 0.0013074 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.63821e-05 GaussianMLPPolicy/LossBefore 1.59343e-08 GaussianMLPPolicy/dLoss 2.63981e-05 Iteration 186 MetaTest/Average/AverageDiscountedReturn -54.7658 MetaTest/Average/AverageReturn -54.7658 MetaTest/Average/Iteration 186 MetaTest/Average/MaxReturn -43.4017 MetaTest/Average/MinReturn -96.1089 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.6323 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.7658 MetaTest/__unnamed_task__/AverageReturn -54.7658 MetaTest/__unnamed_task__/Iteration 186 MetaTest/__unnamed_task__/MaxReturn -43.4017 MetaTest/__unnamed_task__/MinReturn -96.1089 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.6323 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8.976e+06 __unnamed_task__/AverageDiscountedReturn -27.9677 __unnamed_task__/AverageReturn -51.2916 __unnamed_task__/Iteration 186 __unnamed_task__/MaxReturn -40.6604 __unnamed_task__/MinReturn -75.8067 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.95813 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 08:36:15 | [maml_trainer] epoch #187 | Sampling for adapation and meta-testing... 2025-04-07 08:40:16 | [maml_trainer] epoch #187 | Finished meta-testing... 2025-04-07 08:40:16 | [maml_trainer] epoch #187 | Saving snapshot... 2025-04-07 08:40:35 | [maml_trainer] epoch #187 | Saved 2025-04-07 08:40:35 | [maml_trainer] epoch #187 | Time 316879.92 s 2025-04-07 08:40:35 | [maml_trainer] epoch #187 | EpochTime 1706.44 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.1865 Average/AverageReturn -51.8656 Average/Iteration 187 Average/MaxReturn -42.7827 Average/MinReturn -68.8682 Average/NumEpisodes 120 Average/StdReturn 5.37175 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.86942 GaussianMLPPolicy/KLAfter 0.00208942 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.99424e-06 GaussianMLPPolicy/LossBefore -1.07288e-09 GaussianMLPPolicy/dLoss -5.99531e-06 Iteration 187 MetaTest/Average/AverageDiscountedReturn -51.6632 MetaTest/Average/AverageReturn -51.6632 MetaTest/Average/Iteration 187 MetaTest/Average/MaxReturn -45.8759 MetaTest/Average/MinReturn -64.2561 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.28418 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6632 MetaTest/__unnamed_task__/AverageReturn -51.6632 MetaTest/__unnamed_task__/Iteration 187 MetaTest/__unnamed_task__/MaxReturn -45.8759 MetaTest/__unnamed_task__/MinReturn -64.2561 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.28418 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.024e+06 __unnamed_task__/AverageDiscountedReturn -28.1865 __unnamed_task__/AverageReturn -51.8656 __unnamed_task__/Iteration 187 __unnamed_task__/MaxReturn -42.7827 __unnamed_task__/MinReturn -68.8682 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.37175 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 09:04:30 | [maml_trainer] epoch #188 | Sampling for adapation and meta-testing... 2025-04-07 09:08:31 | [maml_trainer] epoch #188 | Finished meta-testing... 2025-04-07 09:08:31 | [maml_trainer] epoch #188 | Saving snapshot... 2025-04-07 09:08:52 | [maml_trainer] epoch #188 | Saved 2025-04-07 09:08:52 | [maml_trainer] epoch #188 | Time 318576.82 s 2025-04-07 09:08:52 | [maml_trainer] epoch #188 | EpochTime 1696.89 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.8087 Average/AverageReturn -51.0128 Average/Iteration 188 Average/MaxReturn -40.6187 Average/MinReturn -92.8194 Average/NumEpisodes 120 Average/StdReturn 6.93975 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.86592 GaussianMLPPolicy/KLAfter 0.00316045 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.5413e-05 GaussianMLPPolicy/LossBefore -2.26498e-09 GaussianMLPPolicy/dLoss 2.54108e-05 Iteration 188 MetaTest/Average/AverageDiscountedReturn -55.5372 MetaTest/Average/AverageReturn -55.5372 MetaTest/Average/Iteration 188 MetaTest/Average/MaxReturn -43.3031 MetaTest/Average/MinReturn -78.2202 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.48342 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.5372 MetaTest/__unnamed_task__/AverageReturn -55.5372 MetaTest/__unnamed_task__/Iteration 188 MetaTest/__unnamed_task__/MaxReturn -43.3031 MetaTest/__unnamed_task__/MinReturn -78.2202 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.48342 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.072e+06 __unnamed_task__/AverageDiscountedReturn -27.8087 __unnamed_task__/AverageReturn -51.0128 __unnamed_task__/Iteration 188 __unnamed_task__/MaxReturn -40.6187 __unnamed_task__/MinReturn -92.8194 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.93975 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 09:32:41 | [maml_trainer] epoch #189 | Sampling for adapation and meta-testing... 2025-04-07 09:36:38 | [maml_trainer] epoch #189 | Finished meta-testing... 2025-04-07 09:36:38 | [maml_trainer] epoch #189 | Saving snapshot... 2025-04-07 09:36:58 | [maml_trainer] epoch #189 | Saved 2025-04-07 09:36:58 | [maml_trainer] epoch #189 | Time 320262.93 s 2025-04-07 09:36:58 | [maml_trainer] epoch #189 | EpochTime 1686.11 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.0669 Average/AverageReturn -51.1385 Average/Iteration 189 Average/MaxReturn -43.1279 Average/MinReturn -71.5291 Average/NumEpisodes 120 Average/StdReturn 4.79666 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.86127 GaussianMLPPolicy/KLAfter 0.00228214 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.99456e-05 GaussianMLPPolicy/LossBefore -7.35124e-09 GaussianMLPPolicy/dLoss -3.9953e-05 Iteration 189 MetaTest/Average/AverageDiscountedReturn -49.8685 MetaTest/Average/AverageReturn -49.8685 MetaTest/Average/Iteration 189 MetaTest/Average/MaxReturn -44.4102 MetaTest/Average/MinReturn -61.8812 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.13516 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8685 MetaTest/__unnamed_task__/AverageReturn -49.8685 MetaTest/__unnamed_task__/Iteration 189 MetaTest/__unnamed_task__/MaxReturn -44.4102 MetaTest/__unnamed_task__/MinReturn -61.8812 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.13516 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.12e+06 __unnamed_task__/AverageDiscountedReturn -28.0669 __unnamed_task__/AverageReturn -51.1385 __unnamed_task__/Iteration 189 __unnamed_task__/MaxReturn -43.1279 __unnamed_task__/MinReturn -71.5291 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.79666 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 10:00:54 | [maml_trainer] epoch #190 | Sampling for adapation and meta-testing... 2025-04-07 10:04:50 | [maml_trainer] epoch #190 | Finished meta-testing... 2025-04-07 10:04:50 | [maml_trainer] epoch #190 | Saving snapshot... 2025-04-07 10:05:11 | [maml_trainer] epoch #190 | Saved 2025-04-07 10:05:11 | [maml_trainer] epoch #190 | Time 321955.61 s 2025-04-07 10:05:11 | [maml_trainer] epoch #190 | EpochTime 1692.68 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.2081 Average/AverageReturn -51.9656 Average/Iteration 190 Average/MaxReturn -43.1978 Average/MinReturn -78.6175 Average/NumEpisodes 120 Average/StdReturn 5.93177 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.85651 GaussianMLPPolicy/KLAfter 0.00337287 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.81791e-06 GaussianMLPPolicy/LossBefore 1.90735e-09 GaussianMLPPolicy/dLoss 2.81982e-06 Iteration 190 MetaTest/Average/AverageDiscountedReturn -51.3012 MetaTest/Average/AverageReturn -51.3012 MetaTest/Average/Iteration 190 MetaTest/Average/MaxReturn -44.0593 MetaTest/Average/MinReturn -64.8261 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.54341 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.3012 MetaTest/__unnamed_task__/AverageReturn -51.3012 MetaTest/__unnamed_task__/Iteration 190 MetaTest/__unnamed_task__/MaxReturn -44.0593 MetaTest/__unnamed_task__/MinReturn -64.8261 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.54341 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.168e+06 __unnamed_task__/AverageDiscountedReturn -28.2081 __unnamed_task__/AverageReturn -51.9656 __unnamed_task__/Iteration 190 __unnamed_task__/MaxReturn -43.1978 __unnamed_task__/MinReturn -78.6175 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.93177 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 10:28:41 | [maml_trainer] epoch #191 | Sampling for adapation and meta-testing... 2025-04-07 10:32:36 | [maml_trainer] epoch #191 | Finished meta-testing... 2025-04-07 10:32:36 | [maml_trainer] epoch #191 | Saving snapshot... 2025-04-07 10:32:57 | [maml_trainer] epoch #191 | Saved 2025-04-07 10:32:57 | [maml_trainer] epoch #191 | Time 323621.45 s 2025-04-07 10:32:57 | [maml_trainer] epoch #191 | EpochTime 1665.83 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.0916 Average/AverageReturn -51.0378 Average/Iteration 191 Average/MaxReturn -43.1106 Average/MinReturn -71.3202 Average/NumEpisodes 120 Average/StdReturn 5.38777 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.85223 GaussianMLPPolicy/KLAfter 0.00273034 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000144697 GaussianMLPPolicy/LossBefore -1.07686e-08 GaussianMLPPolicy/dLoss -0.000144707 Iteration 191 MetaTest/Average/AverageDiscountedReturn -51.5788 MetaTest/Average/AverageReturn -51.5788 MetaTest/Average/Iteration 191 MetaTest/Average/MaxReturn -43.4679 MetaTest/Average/MinReturn -71.0218 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.24369 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.5788 MetaTest/__unnamed_task__/AverageReturn -51.5788 MetaTest/__unnamed_task__/Iteration 191 MetaTest/__unnamed_task__/MaxReturn -43.4679 MetaTest/__unnamed_task__/MinReturn -71.0218 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.24369 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.216e+06 __unnamed_task__/AverageDiscountedReturn -28.0916 __unnamed_task__/AverageReturn -51.0378 __unnamed_task__/Iteration 191 __unnamed_task__/MaxReturn -43.1106 __unnamed_task__/MinReturn -71.3202 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.38777 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 10:56:22 | [maml_trainer] epoch #192 | Sampling for adapation and meta-testing... 2025-04-07 11:00:17 | [maml_trainer] epoch #192 | Finished meta-testing... 2025-04-07 11:00:17 | [maml_trainer] epoch #192 | Saving snapshot... 2025-04-07 11:00:37 | [maml_trainer] epoch #192 | Saved 2025-04-07 11:00:37 | [maml_trainer] epoch #192 | Time 325281.68 s 2025-04-07 11:00:37 | [maml_trainer] epoch #192 | EpochTime 1660.22 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.955 Average/AverageReturn -53.795 Average/Iteration 192 Average/MaxReturn -44.0459 Average/MinReturn -92.3731 Average/NumEpisodes 120 Average/StdReturn 7.60594 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84878 GaussianMLPPolicy/KLAfter 0.00389809 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.13634e-06 GaussianMLPPolicy/LossBefore 1.27554e-08 GaussianMLPPolicy/dLoss -7.12359e-06 Iteration 192 MetaTest/Average/AverageDiscountedReturn -57.4926 MetaTest/Average/AverageReturn -57.4926 MetaTest/Average/Iteration 192 MetaTest/Average/MaxReturn -47.45 MetaTest/Average/MinReturn -78.7805 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.74221 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -57.4926 MetaTest/__unnamed_task__/AverageReturn -57.4926 MetaTest/__unnamed_task__/Iteration 192 MetaTest/__unnamed_task__/MaxReturn -47.45 MetaTest/__unnamed_task__/MinReturn -78.7805 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.74221 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.264e+06 __unnamed_task__/AverageDiscountedReturn -28.955 __unnamed_task__/AverageReturn -53.795 __unnamed_task__/Iteration 192 __unnamed_task__/MaxReturn -44.0459 __unnamed_task__/MinReturn -92.3731 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.60594 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 11:24:26 | [maml_trainer] epoch #193 | Sampling for adapation and meta-testing... 2025-04-07 11:28:22 | [maml_trainer] epoch #193 | Finished meta-testing... 2025-04-07 11:28:22 | [maml_trainer] epoch #193 | Saving snapshot... 2025-04-07 11:28:43 | [maml_trainer] epoch #193 | Saved 2025-04-07 11:28:43 | [maml_trainer] epoch #193 | Time 326967.13 s 2025-04-07 11:28:43 | [maml_trainer] epoch #193 | EpochTime 1685.45 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.8075 Average/AverageReturn -52.7665 Average/Iteration 193 Average/MaxReturn -41.5578 Average/MinReturn -86.8922 Average/NumEpisodes 120 Average/StdReturn 7.40849 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84651 GaussianMLPPolicy/KLAfter 0.00412446 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000230391 GaussianMLPPolicy/LossBefore -9.85463e-09 GaussianMLPPolicy/dLoss 0.000230381 Iteration 193 MetaTest/Average/AverageDiscountedReturn -52.7811 MetaTest/Average/AverageReturn -52.7811 MetaTest/Average/Iteration 193 MetaTest/Average/MaxReturn -45.8525 MetaTest/Average/MinReturn -75.63 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.98761 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.7811 MetaTest/__unnamed_task__/AverageReturn -52.7811 MetaTest/__unnamed_task__/Iteration 193 MetaTest/__unnamed_task__/MaxReturn -45.8525 MetaTest/__unnamed_task__/MinReturn -75.63 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.98761 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.312e+06 __unnamed_task__/AverageDiscountedReturn -28.8075 __unnamed_task__/AverageReturn -52.7665 __unnamed_task__/Iteration 193 __unnamed_task__/MaxReturn -41.5578 __unnamed_task__/MinReturn -86.8922 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.40849 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 11:52:20 | [maml_trainer] epoch #194 | Sampling for adapation and meta-testing... 2025-04-07 11:56:21 | [maml_trainer] epoch #194 | Finished meta-testing... 2025-04-07 11:56:21 | [maml_trainer] epoch #194 | Saving snapshot... 2025-04-07 11:56:43 | [maml_trainer] epoch #194 | Saved 2025-04-07 11:56:43 | [maml_trainer] epoch #194 | Time 328647.79 s 2025-04-07 11:56:43 | [maml_trainer] epoch #194 | EpochTime 1680.65 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.7539 Average/AverageReturn -53.138 Average/Iteration 194 Average/MaxReturn -43.1875 Average/MinReturn -110.267 Average/NumEpisodes 120 Average/StdReturn 8.541 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84512 GaussianMLPPolicy/KLAfter 0.00386002 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.75022e-05 GaussianMLPPolicy/LossBefore -2.14577e-09 GaussianMLPPolicy/dLoss 6.75e-05 Iteration 194 MetaTest/Average/AverageDiscountedReturn -51.0582 MetaTest/Average/AverageReturn -51.0582 MetaTest/Average/Iteration 194 MetaTest/Average/MaxReturn -45.8465 MetaTest/Average/MinReturn -59.707 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.85687 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.0582 MetaTest/__unnamed_task__/AverageReturn -51.0582 MetaTest/__unnamed_task__/Iteration 194 MetaTest/__unnamed_task__/MaxReturn -45.8465 MetaTest/__unnamed_task__/MinReturn -59.707 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.85687 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.36e+06 __unnamed_task__/AverageDiscountedReturn -28.7539 __unnamed_task__/AverageReturn -53.138 __unnamed_task__/Iteration 194 __unnamed_task__/MaxReturn -43.1875 __unnamed_task__/MinReturn -110.267 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.541 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 12:21:41 | [maml_trainer] epoch #195 | Sampling for adapation and meta-testing... 2025-04-07 12:25:52 | [maml_trainer] epoch #195 | Finished meta-testing... 2025-04-07 12:25:52 | [maml_trainer] epoch #195 | Saving snapshot... 2025-04-07 12:26:14 | [maml_trainer] epoch #195 | Saved 2025-04-07 12:26:14 | [maml_trainer] epoch #195 | Time 330418.21 s 2025-04-07 12:26:14 | [maml_trainer] epoch #195 | EpochTime 1770.42 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.9134 Average/AverageReturn -53.4756 Average/Iteration 195 Average/MaxReturn -43.6285 Average/MinReturn -72.2803 Average/NumEpisodes 120 Average/StdReturn 6.08137 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84452 GaussianMLPPolicy/KLAfter 0.00291569 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.35984e-05 GaussianMLPPolicy/LossBefore 2.88089e-08 GaussianMLPPolicy/dLoss -7.35696e-05 Iteration 195 MetaTest/Average/AverageDiscountedReturn -52.6972 MetaTest/Average/AverageReturn -52.6972 MetaTest/Average/Iteration 195 MetaTest/Average/MaxReturn -47.1704 MetaTest/Average/MinReturn -71.794 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.43168 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6972 MetaTest/__unnamed_task__/AverageReturn -52.6972 MetaTest/__unnamed_task__/Iteration 195 MetaTest/__unnamed_task__/MaxReturn -47.1704 MetaTest/__unnamed_task__/MinReturn -71.794 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.43168 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.408e+06 __unnamed_task__/AverageDiscountedReturn -28.9134 __unnamed_task__/AverageReturn -53.4756 __unnamed_task__/Iteration 195 __unnamed_task__/MaxReturn -43.6285 __unnamed_task__/MinReturn -72.2803 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.08137 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 12:51:02 | [maml_trainer] epoch #196 | Sampling for adapation and meta-testing... 2025-04-07 12:55:09 | [maml_trainer] epoch #196 | Finished meta-testing... 2025-04-07 12:55:09 | [maml_trainer] epoch #196 | Saving snapshot... 2025-04-07 12:55:31 | [maml_trainer] epoch #196 | Saved 2025-04-07 12:55:31 | [maml_trainer] epoch #196 | Time 332175.53 s 2025-04-07 12:55:31 | [maml_trainer] epoch #196 | EpochTime 1757.32 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.708 Average/AverageReturn -52.6249 Average/Iteration 196 Average/MaxReturn -43.7213 Average/MinReturn -69.3713 Average/NumEpisodes 120 Average/StdReturn 5.70168 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84444 GaussianMLPPolicy/KLAfter 0.00165577 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.41152e-05 GaussianMLPPolicy/LossBefore -2.66234e-09 GaussianMLPPolicy/dLoss 3.41125e-05 Iteration 196 MetaTest/Average/AverageDiscountedReturn -52.5016 MetaTest/Average/AverageReturn -52.5016 MetaTest/Average/Iteration 196 MetaTest/Average/MaxReturn -47.2407 MetaTest/Average/MinReturn -67.4335 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.88921 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.5016 MetaTest/__unnamed_task__/AverageReturn -52.5016 MetaTest/__unnamed_task__/Iteration 196 MetaTest/__unnamed_task__/MaxReturn -47.2407 MetaTest/__unnamed_task__/MinReturn -67.4335 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.88921 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.456e+06 __unnamed_task__/AverageDiscountedReturn -28.708 __unnamed_task__/AverageReturn -52.6249 __unnamed_task__/Iteration 196 __unnamed_task__/MaxReturn -43.7213 __unnamed_task__/MinReturn -69.3713 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.70168 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 13:20:46 | [maml_trainer] epoch #197 | Sampling for adapation and meta-testing... 2025-04-07 13:24:51 | [maml_trainer] epoch #197 | Finished meta-testing... 2025-04-07 13:24:51 | [maml_trainer] epoch #197 | Saving snapshot... 2025-04-07 13:25:13 | [maml_trainer] epoch #197 | Saved 2025-04-07 13:25:13 | [maml_trainer] epoch #197 | Time 333957.22 s 2025-04-07 13:25:13 | [maml_trainer] epoch #197 | EpochTime 1781.69 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.2378 Average/AverageReturn -53.6216 Average/Iteration 197 Average/MaxReturn -43.8425 Average/MinReturn -86.6697 Average/NumEpisodes 120 Average/StdReturn 7.01038 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.8435 GaussianMLPPolicy/KLAfter 0.00279883 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000152728 GaussianMLPPolicy/LossBefore 1.35104e-08 GaussianMLPPolicy/dLoss 0.000152742 Iteration 197 MetaTest/Average/AverageDiscountedReturn -51.6581 MetaTest/Average/AverageReturn -51.6581 MetaTest/Average/Iteration 197 MetaTest/Average/MaxReturn -46.5357 MetaTest/Average/MinReturn -64.3894 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.60494 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6581 MetaTest/__unnamed_task__/AverageReturn -51.6581 MetaTest/__unnamed_task__/Iteration 197 MetaTest/__unnamed_task__/MaxReturn -46.5357 MetaTest/__unnamed_task__/MinReturn -64.3894 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.60494 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.504e+06 __unnamed_task__/AverageDiscountedReturn -29.2378 __unnamed_task__/AverageReturn -53.6216 __unnamed_task__/Iteration 197 __unnamed_task__/MaxReturn -43.8425 __unnamed_task__/MinReturn -86.6697 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.01038 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 13:50:24 | [maml_trainer] epoch #198 | Sampling for adapation and meta-testing... 2025-04-07 13:54:34 | [maml_trainer] epoch #198 | Finished meta-testing... 2025-04-07 13:54:34 | [maml_trainer] epoch #198 | Saving snapshot... 2025-04-07 13:54:56 | [maml_trainer] epoch #198 | Saved 2025-04-07 13:54:56 | [maml_trainer] epoch #198 | Time 335740.00 s 2025-04-07 13:54:56 | [maml_trainer] epoch #198 | EpochTime 1782.77 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.8711 Average/AverageReturn -52.2828 Average/Iteration 198 Average/MaxReturn -43.4149 Average/MinReturn -75.7644 Average/NumEpisodes 120 Average/StdReturn 5.88396 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84305 GaussianMLPPolicy/KLAfter 0.00346998 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.16445e-05 GaussianMLPPolicy/LossBefore 2.9405e-09 GaussianMLPPolicy/dLoss -4.16416e-05 Iteration 198 MetaTest/Average/AverageDiscountedReturn -50.1976 MetaTest/Average/AverageReturn -50.1976 MetaTest/Average/Iteration 198 MetaTest/Average/MaxReturn -42.2746 MetaTest/Average/MinReturn -62.2885 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.65553 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.1976 MetaTest/__unnamed_task__/AverageReturn -50.1976 MetaTest/__unnamed_task__/Iteration 198 MetaTest/__unnamed_task__/MaxReturn -42.2746 MetaTest/__unnamed_task__/MinReturn -62.2885 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.65553 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.552e+06 __unnamed_task__/AverageDiscountedReturn -28.8711 __unnamed_task__/AverageReturn -52.2828 __unnamed_task__/Iteration 198 __unnamed_task__/MaxReturn -43.4149 __unnamed_task__/MinReturn -75.7644 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.88396 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 14:20:03 | [maml_trainer] epoch #199 | Sampling for adapation and meta-testing... 2025-04-07 14:24:18 | [maml_trainer] epoch #199 | Finished meta-testing... 2025-04-07 14:24:18 | [maml_trainer] epoch #199 | Saving snapshot... 2025-04-07 14:24:41 | [maml_trainer] epoch #199 | Saved 2025-04-07 14:24:41 | [maml_trainer] epoch #199 | Time 337525.52 s 2025-04-07 14:24:41 | [maml_trainer] epoch #199 | EpochTime 1785.52 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.4649 Average/AverageReturn -51.2174 Average/Iteration 199 Average/MaxReturn -44.2051 Average/MinReturn -71.4766 Average/NumEpisodes 120 Average/StdReturn 4.68839 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84241 GaussianMLPPolicy/KLAfter 0.00257656 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.48129e-05 GaussianMLPPolicy/LossBefore 2.07822e-08 GaussianMLPPolicy/dLoss 3.48337e-05 Iteration 199 MetaTest/Average/AverageDiscountedReturn -50.3631 MetaTest/Average/AverageReturn -50.3631 MetaTest/Average/Iteration 199 MetaTest/Average/MaxReturn -45.2166 MetaTest/Average/MinReturn -58.7806 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.39858 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.3631 MetaTest/__unnamed_task__/AverageReturn -50.3631 MetaTest/__unnamed_task__/Iteration 199 MetaTest/__unnamed_task__/MaxReturn -45.2166 MetaTest/__unnamed_task__/MinReturn -58.7806 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.39858 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.6e+06 __unnamed_task__/AverageDiscountedReturn -28.4649 __unnamed_task__/AverageReturn -51.2174 __unnamed_task__/Iteration 199 __unnamed_task__/MaxReturn -44.2051 __unnamed_task__/MinReturn -71.4766 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.68839 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 14:48:31 | [maml_trainer] epoch #200 | Sampling for adapation and meta-testing... 2025-04-07 14:52:41 | [maml_trainer] epoch #200 | Finished meta-testing... 2025-04-07 14:52:41 | [maml_trainer] epoch #200 | Saving snapshot... 2025-04-07 14:53:04 | [maml_trainer] epoch #200 | Saved 2025-04-07 14:53:04 | [maml_trainer] epoch #200 | Time 339228.15 s 2025-04-07 14:53:04 | [maml_trainer] epoch #200 | EpochTime 1702.63 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.7733 Average/AverageReturn -51.7313 Average/Iteration 200 Average/MaxReturn -43.9309 Average/MinReturn -78.585 Average/NumEpisodes 120 Average/StdReturn 5.77722 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84221 GaussianMLPPolicy/KLAfter 0.00325249 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.75635e-05 GaussianMLPPolicy/LossBefore 9.02017e-09 GaussianMLPPolicy/dLoss -5.75545e-05 Iteration 200 MetaTest/Average/AverageDiscountedReturn -50.0916 MetaTest/Average/AverageReturn -50.0916 MetaTest/Average/Iteration 200 MetaTest/Average/MaxReturn -43.6046 MetaTest/Average/MinReturn -58.5125 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.38803 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0916 MetaTest/__unnamed_task__/AverageReturn -50.0916 MetaTest/__unnamed_task__/Iteration 200 MetaTest/__unnamed_task__/MaxReturn -43.6046 MetaTest/__unnamed_task__/MinReturn -58.5125 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.38803 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.648e+06 __unnamed_task__/AverageDiscountedReturn -28.7733 __unnamed_task__/AverageReturn -51.7313 __unnamed_task__/Iteration 200 __unnamed_task__/MaxReturn -43.9309 __unnamed_task__/MinReturn -78.585 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.77722 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 15:18:12 | [maml_trainer] epoch #201 | Sampling for adapation and meta-testing... 2025-04-07 15:22:27 | [maml_trainer] epoch #201 | Finished meta-testing... 2025-04-07 15:22:27 | [maml_trainer] epoch #201 | Saving snapshot... 2025-04-07 15:22:49 | [maml_trainer] epoch #201 | Saved 2025-04-07 15:22:49 | [maml_trainer] epoch #201 | Time 341013.83 s 2025-04-07 15:22:49 | [maml_trainer] epoch #201 | EpochTime 1785.67 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.4034 Average/AverageReturn -50.5016 Average/Iteration 201 Average/MaxReturn -39.8666 Average/MinReturn -73.9659 Average/NumEpisodes 120 Average/StdReturn 5.64538 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84258 GaussianMLPPolicy/KLAfter 0.00603439 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.19229e-05 GaussianMLPPolicy/LossBefore 1.00136e-08 GaussianMLPPolicy/dLoss -8.19129e-05 Iteration 201 MetaTest/Average/AverageDiscountedReturn -52.5593 MetaTest/Average/AverageReturn -52.5593 MetaTest/Average/Iteration 201 MetaTest/Average/MaxReturn -43.049 MetaTest/Average/MinReturn -98.379 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.8629 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.5593 MetaTest/__unnamed_task__/AverageReturn -52.5593 MetaTest/__unnamed_task__/Iteration 201 MetaTest/__unnamed_task__/MaxReturn -43.049 MetaTest/__unnamed_task__/MinReturn -98.379 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.8629 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.696e+06 __unnamed_task__/AverageDiscountedReturn -28.4034 __unnamed_task__/AverageReturn -50.5016 __unnamed_task__/Iteration 201 __unnamed_task__/MaxReturn -39.8666 __unnamed_task__/MinReturn -73.9659 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.64538 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-07 15:47:38 | [maml_trainer] epoch #202 | Sampling for adapation and meta-testing... 2025-04-07 15:51:40 | [maml_trainer] epoch #202 | Finished meta-testing... 2025-04-07 15:51:40 | [maml_trainer] epoch #202 | Saving snapshot... 2025-04-07 15:52:01 | [maml_trainer] epoch #202 | Saved 2025-04-07 15:52:01 | [maml_trainer] epoch #202 | Time 342765.00 s 2025-04-07 15:52:01 | [maml_trainer] epoch #202 | EpochTime 1751.17 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.5901 Average/AverageReturn -50.4816 Average/Iteration 202 Average/MaxReturn -40.679 Average/MinReturn -73.326 Average/NumEpisodes 120 Average/StdReturn 5.8776 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84311 GaussianMLPPolicy/KLAfter 0.0069974 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.0756e-05 GaussianMLPPolicy/LossBefore -7.39098e-09 GaussianMLPPolicy/dLoss -9.07634e-05 Iteration 202 MetaTest/Average/AverageDiscountedReturn -54.4466 MetaTest/Average/AverageReturn -54.4466 MetaTest/Average/Iteration 202 MetaTest/Average/MaxReturn -41.6056 MetaTest/Average/MinReturn -149.778 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.5056 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.4466 MetaTest/__unnamed_task__/AverageReturn -54.4466 MetaTest/__unnamed_task__/Iteration 202 MetaTest/__unnamed_task__/MaxReturn -41.6056 MetaTest/__unnamed_task__/MinReturn -149.778 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.5056 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.744e+06 __unnamed_task__/AverageDiscountedReturn -28.5901 __unnamed_task__/AverageReturn -50.4816 __unnamed_task__/Iteration 202 __unnamed_task__/MaxReturn -40.679 __unnamed_task__/MinReturn -73.326 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.8776 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 16:16:00 | [maml_trainer] epoch #203 | Sampling for adapation and meta-testing... 2025-04-07 16:20:07 | [maml_trainer] epoch #203 | Finished meta-testing... 2025-04-07 16:20:07 | [maml_trainer] epoch #203 | Saving snapshot... 2025-04-07 16:20:31 | [maml_trainer] epoch #203 | Saved 2025-04-07 16:20:31 | [maml_trainer] epoch #203 | Time 344475.11 s 2025-04-07 16:20:31 | [maml_trainer] epoch #203 | EpochTime 1710.11 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.7345 Average/AverageReturn -52.3534 Average/Iteration 203 Average/MaxReturn -40.2094 Average/MinReturn -104.987 Average/NumEpisodes 120 Average/StdReturn 11.8147 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84418 GaussianMLPPolicy/KLAfter 0.00638604 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.77153e-05 GaussianMLPPolicy/LossBefore -1.98682e-10 GaussianMLPPolicy/dLoss -9.77155e-05 Iteration 203 MetaTest/Average/AverageDiscountedReturn -56.632 MetaTest/Average/AverageReturn -56.632 MetaTest/Average/Iteration 203 MetaTest/Average/MaxReturn -44.9284 MetaTest/Average/MinReturn -105.314 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.0431 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -56.632 MetaTest/__unnamed_task__/AverageReturn -56.632 MetaTest/__unnamed_task__/Iteration 203 MetaTest/__unnamed_task__/MaxReturn -44.9284 MetaTest/__unnamed_task__/MinReturn -105.314 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.0431 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.792e+06 __unnamed_task__/AverageDiscountedReturn -28.7345 __unnamed_task__/AverageReturn -52.3534 __unnamed_task__/Iteration 203 __unnamed_task__/MaxReturn -40.2094 __unnamed_task__/MinReturn -104.987 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.8147 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 16:45:23 | [maml_trainer] epoch #204 | Sampling for adapation and meta-testing... 2025-04-07 16:49:31 | [maml_trainer] epoch #204 | Finished meta-testing... 2025-04-07 16:49:31 | [maml_trainer] epoch #204 | Saving snapshot... 2025-04-07 16:49:53 | [maml_trainer] epoch #204 | Saved 2025-04-07 16:49:53 | [maml_trainer] epoch #204 | Time 346237.71 s 2025-04-07 16:49:53 | [maml_trainer] epoch #204 | EpochTime 1762.59 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.9258 Average/AverageReturn -53.8705 Average/Iteration 204 Average/MaxReturn -34.9389 Average/MinReturn -153.081 Average/NumEpisodes 120 Average/StdReturn 18.6297 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84431 GaussianMLPPolicy/KLAfter 0.00464661 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000104802 GaussianMLPPolicy/LossBefore 3.23852e-09 GaussianMLPPolicy/dLoss -0.000104799 Iteration 204 MetaTest/Average/AverageDiscountedReturn -58.3702 MetaTest/Average/AverageReturn -58.3702 MetaTest/Average/Iteration 204 MetaTest/Average/MaxReturn -43.312 MetaTest/Average/MinReturn -147.969 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.1452 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -58.3702 MetaTest/__unnamed_task__/AverageReturn -58.3702 MetaTest/__unnamed_task__/Iteration 204 MetaTest/__unnamed_task__/MaxReturn -43.312 MetaTest/__unnamed_task__/MinReturn -147.969 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.1452 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.84e+06 __unnamed_task__/AverageDiscountedReturn -28.9258 __unnamed_task__/AverageReturn -53.8705 __unnamed_task__/Iteration 204 __unnamed_task__/MaxReturn -34.9389 __unnamed_task__/MinReturn -153.081 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 18.6297 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 17:14:38 | [maml_trainer] epoch #205 | Sampling for adapation and meta-testing... 2025-04-07 17:18:43 | [maml_trainer] epoch #205 | Finished meta-testing... 2025-04-07 17:18:43 | [maml_trainer] epoch #205 | Saving snapshot... 2025-04-07 17:19:06 | [maml_trainer] epoch #205 | Saved 2025-04-07 17:19:06 | [maml_trainer] epoch #205 | Time 347990.30 s 2025-04-07 17:19:06 | [maml_trainer] epoch #205 | EpochTime 1752.58 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -30.7543 Average/AverageReturn -63.1041 Average/Iteration 205 Average/MaxReturn 12.5963 Average/MinReturn -175.178 Average/NumEpisodes 120 Average/StdReturn 30.0155 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84501 GaussianMLPPolicy/KLAfter 0.00437147 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.40709e-06 GaussianMLPPolicy/LossBefore -4.40081e-09 GaussianMLPPolicy/dLoss -9.41149e-06 Iteration 205 MetaTest/Average/AverageDiscountedReturn -64.8932 MetaTest/Average/AverageReturn -64.8932 MetaTest/Average/Iteration 205 MetaTest/Average/MaxReturn -31.3497 MetaTest/Average/MinReturn -143.977 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 28.2172 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -64.8932 MetaTest/__unnamed_task__/AverageReturn -64.8932 MetaTest/__unnamed_task__/Iteration 205 MetaTest/__unnamed_task__/MaxReturn -31.3497 MetaTest/__unnamed_task__/MinReturn -143.977 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 28.2172 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.888e+06 __unnamed_task__/AverageDiscountedReturn -30.7543 __unnamed_task__/AverageReturn -63.1041 __unnamed_task__/Iteration 205 __unnamed_task__/MaxReturn 12.5963 __unnamed_task__/MinReturn -175.178 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 30.0155 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 17:43:21 | [maml_trainer] epoch #206 | Sampling for adapation and meta-testing... 2025-04-07 17:47:29 | [maml_trainer] epoch #206 | Finished meta-testing... 2025-04-07 17:47:29 | [maml_trainer] epoch #206 | Saving snapshot... 2025-04-07 17:47:52 | [maml_trainer] epoch #206 | Saved 2025-04-07 17:47:52 | [maml_trainer] epoch #206 | Time 349715.98 s 2025-04-07 17:47:52 | [maml_trainer] epoch #206 | EpochTime 1725.68 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -30.9171 Average/AverageReturn -62.1634 Average/Iteration 206 Average/MaxReturn 84.0455 Average/MinReturn -174.2 Average/NumEpisodes 120 Average/StdReturn 33.5225 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84563 GaussianMLPPolicy/KLAfter 0.00341457 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.08045e-05 GaussianMLPPolicy/LossBefore -1.50998e-09 GaussianMLPPolicy/dLoss 2.0803e-05 Iteration 206 MetaTest/Average/AverageDiscountedReturn -57.8641 MetaTest/Average/AverageReturn -57.8641 MetaTest/Average/Iteration 206 MetaTest/Average/MaxReturn 371.518 MetaTest/Average/MinReturn -180.633 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 107.68 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -57.8641 MetaTest/__unnamed_task__/AverageReturn -57.8641 MetaTest/__unnamed_task__/Iteration 206 MetaTest/__unnamed_task__/MaxReturn 371.518 MetaTest/__unnamed_task__/MinReturn -180.633 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 107.68 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.936e+06 __unnamed_task__/AverageDiscountedReturn -30.9171 __unnamed_task__/AverageReturn -62.1634 __unnamed_task__/Iteration 206 __unnamed_task__/MaxReturn 84.0455 __unnamed_task__/MinReturn -174.2 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 33.5225 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 18:12:50 | [maml_trainer] epoch #207 | Sampling for adapation and meta-testing... 2025-04-07 18:16:56 | [maml_trainer] epoch #207 | Finished meta-testing... 2025-04-07 18:16:56 | [maml_trainer] epoch #207 | Saving snapshot... 2025-04-07 18:17:18 | [maml_trainer] epoch #207 | Saved 2025-04-07 18:17:18 | [maml_trainer] epoch #207 | Time 351482.72 s 2025-04-07 18:17:18 | [maml_trainer] epoch #207 | EpochTime 1766.74 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -30.3912 Average/AverageReturn -60.2943 Average/Iteration 207 Average/MaxReturn 232.215 Average/MinReturn -175.85 Average/NumEpisodes 120 Average/StdReturn 42.0688 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84591 GaussianMLPPolicy/KLAfter 0.00239983 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.36323e-05 GaussianMLPPolicy/LossBefore -1.66893e-09 GaussianMLPPolicy/dLoss -2.3634e-05 Iteration 207 MetaTest/Average/AverageDiscountedReturn -64.8905 MetaTest/Average/AverageReturn -64.8905 MetaTest/Average/Iteration 207 MetaTest/Average/MaxReturn 119.631 MetaTest/Average/MinReturn -159.838 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 56.5676 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -64.8905 MetaTest/__unnamed_task__/AverageReturn -64.8905 MetaTest/__unnamed_task__/Iteration 207 MetaTest/__unnamed_task__/MaxReturn 119.631 MetaTest/__unnamed_task__/MinReturn -159.838 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 56.5676 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 9.984e+06 __unnamed_task__/AverageDiscountedReturn -30.3912 __unnamed_task__/AverageReturn -60.2943 __unnamed_task__/Iteration 207 __unnamed_task__/MaxReturn 232.215 __unnamed_task__/MinReturn -175.85 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 42.0688 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 18:41:49 | [maml_trainer] epoch #208 | Sampling for adapation and meta-testing... 2025-04-07 18:45:53 | [maml_trainer] epoch #208 | Finished meta-testing... 2025-04-07 18:45:53 | [maml_trainer] epoch #208 | Saving snapshot... 2025-04-07 18:46:17 | [maml_trainer] epoch #208 | Saved 2025-04-07 18:46:17 | [maml_trainer] epoch #208 | Time 353221.65 s 2025-04-07 18:46:17 | [maml_trainer] epoch #208 | EpochTime 1738.93 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -31.4553 Average/AverageReturn -68.4601 Average/Iteration 208 Average/MaxReturn 215.376 Average/MinReturn -180.868 Average/NumEpisodes 120 Average/StdReturn 44.6869 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84563 GaussianMLPPolicy/KLAfter 0.00163253 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.16279e-06 GaussianMLPPolicy/LossBefore -7.35124e-10 GaussianMLPPolicy/dLoss 3.16206e-06 Iteration 208 MetaTest/Average/AverageDiscountedReturn -58.0191 MetaTest/Average/AverageReturn -58.0191 MetaTest/Average/Iteration 208 MetaTest/Average/MaxReturn -41.3967 MetaTest/Average/MinReturn -106.859 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.8699 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -58.0191 MetaTest/__unnamed_task__/AverageReturn -58.0191 MetaTest/__unnamed_task__/Iteration 208 MetaTest/__unnamed_task__/MaxReturn -41.3967 MetaTest/__unnamed_task__/MinReturn -106.859 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.8699 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0032e+07 __unnamed_task__/AverageDiscountedReturn -31.4553 __unnamed_task__/AverageReturn -68.4601 __unnamed_task__/Iteration 208 __unnamed_task__/MaxReturn 215.376 __unnamed_task__/MinReturn -180.868 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 44.6869 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 19:10:24 | [maml_trainer] epoch #209 | Sampling for adapation and meta-testing... 2025-04-07 19:14:39 | [maml_trainer] epoch #209 | Finished meta-testing... 2025-04-07 19:14:39 | [maml_trainer] epoch #209 | Saving snapshot... 2025-04-07 19:15:02 | [maml_trainer] epoch #209 | Saved 2025-04-07 19:15:02 | [maml_trainer] epoch #209 | Time 354946.68 s 2025-04-07 19:15:02 | [maml_trainer] epoch #209 | EpochTime 1725.02 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.8208 Average/AverageReturn -74.7122 Average/Iteration 209 Average/MaxReturn 218.915 Average/MinReturn -173.699 Average/NumEpisodes 120 Average/StdReturn 47.2449 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84543 GaussianMLPPolicy/KLAfter 0.0012949 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.73223e-05 GaussianMLPPolicy/LossBefore -4.56969e-10 GaussianMLPPolicy/dLoss -1.73227e-05 Iteration 209 MetaTest/Average/AverageDiscountedReturn -74.381 MetaTest/Average/AverageReturn -74.381 MetaTest/Average/Iteration 209 MetaTest/Average/MaxReturn -42.6604 MetaTest/Average/MinReturn -162.096 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 33.7873 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -74.381 MetaTest/__unnamed_task__/AverageReturn -74.381 MetaTest/__unnamed_task__/Iteration 209 MetaTest/__unnamed_task__/MaxReturn -42.6604 MetaTest/__unnamed_task__/MinReturn -162.096 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 33.7873 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.008e+07 __unnamed_task__/AverageDiscountedReturn -32.8208 __unnamed_task__/AverageReturn -74.7122 __unnamed_task__/Iteration 209 __unnamed_task__/MaxReturn 218.915 __unnamed_task__/MinReturn -173.699 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 47.2449 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 19:39:38 | [maml_trainer] epoch #210 | Sampling for adapation and meta-testing... 2025-04-07 19:43:42 | [maml_trainer] epoch #210 | Finished meta-testing... 2025-04-07 19:43:42 | [maml_trainer] epoch #210 | Saving snapshot... 2025-04-07 19:44:05 | [maml_trainer] epoch #210 | Saved 2025-04-07 19:44:05 | [maml_trainer] epoch #210 | Time 356689.80 s 2025-04-07 19:44:05 | [maml_trainer] epoch #210 | EpochTime 1743.12 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.3886 Average/AverageReturn -70.5966 Average/Iteration 210 Average/MaxReturn 223.232 Average/MinReturn -182.51 Average/NumEpisodes 120 Average/StdReturn 53.543 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84523 GaussianMLPPolicy/KLAfter 0.00105162 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.83337e-06 GaussianMLPPolicy/LossBefore 4.91738e-10 GaussianMLPPolicy/dLoss 6.83387e-06 Iteration 210 MetaTest/Average/AverageDiscountedReturn -67.1593 MetaTest/Average/AverageReturn -67.1593 MetaTest/Average/Iteration 210 MetaTest/Average/MaxReturn -32.9171 MetaTest/Average/MinReturn -178.309 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 37.7217 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -67.1593 MetaTest/__unnamed_task__/AverageReturn -67.1593 MetaTest/__unnamed_task__/Iteration 210 MetaTest/__unnamed_task__/MaxReturn -32.9171 MetaTest/__unnamed_task__/MinReturn -178.309 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 37.7217 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0128e+07 __unnamed_task__/AverageDiscountedReturn -32.3886 __unnamed_task__/AverageReturn -70.5966 __unnamed_task__/Iteration 210 __unnamed_task__/MaxReturn 223.232 __unnamed_task__/MinReturn -182.51 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 53.543 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 20:08:30 | [maml_trainer] epoch #211 | Sampling for adapation and meta-testing... 2025-04-07 20:12:33 | [maml_trainer] epoch #211 | Finished meta-testing... 2025-04-07 20:12:33 | [maml_trainer] epoch #211 | Saving snapshot... 2025-04-07 20:12:56 | [maml_trainer] epoch #211 | Saved 2025-04-07 20:12:56 | [maml_trainer] epoch #211 | Time 358420.47 s 2025-04-07 20:12:56 | [maml_trainer] epoch #211 | EpochTime 1730.67 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -33.7375 Average/AverageReturn -78.9459 Average/Iteration 211 Average/MaxReturn 173.776 Average/MinReturn -180.041 Average/NumEpisodes 120 Average/StdReturn 50.1509 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84491 GaussianMLPPolicy/KLAfter 0.0010367 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.41262e-05 GaussianMLPPolicy/LossBefore -1.45038e-09 GaussianMLPPolicy/dLoss -1.41277e-05 Iteration 211 MetaTest/Average/AverageDiscountedReturn -91.1597 MetaTest/Average/AverageReturn -91.1597 MetaTest/Average/Iteration 211 MetaTest/Average/MaxReturn 66.2809 MetaTest/Average/MinReturn -170.223 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 55.9736 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.1597 MetaTest/__unnamed_task__/AverageReturn -91.1597 MetaTest/__unnamed_task__/Iteration 211 MetaTest/__unnamed_task__/MaxReturn 66.2809 MetaTest/__unnamed_task__/MinReturn -170.223 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 55.9736 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0176e+07 __unnamed_task__/AverageDiscountedReturn -33.7375 __unnamed_task__/AverageReturn -78.9459 __unnamed_task__/Iteration 211 __unnamed_task__/MaxReturn 173.776 __unnamed_task__/MinReturn -180.041 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 50.1509 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 20:36:07 | [maml_trainer] epoch #212 | Sampling for adapation and meta-testing... 2025-04-07 20:39:56 | [maml_trainer] epoch #212 | Finished meta-testing... 2025-04-07 20:39:56 | [maml_trainer] epoch #212 | Saving snapshot... 2025-04-07 20:40:17 | [maml_trainer] epoch #212 | Saved 2025-04-07 20:40:17 | [maml_trainer] epoch #212 | Time 360061.93 s 2025-04-07 20:40:17 | [maml_trainer] epoch #212 | EpochTime 1641.45 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -34.8363 Average/AverageReturn -85.3861 Average/Iteration 212 Average/MaxReturn 122.283 Average/MinReturn -180.755 Average/NumEpisodes 120 Average/StdReturn 50.4011 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84461 GaussianMLPPolicy/KLAfter 0.00124222 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.28514e-08 GaussianMLPPolicy/LossBefore 4.78327e-09 GaussianMLPPolicy/dLoss -6.80682e-08 Iteration 212 MetaTest/Average/AverageDiscountedReturn -97.9295 MetaTest/Average/AverageReturn -97.9295 MetaTest/Average/Iteration 212 MetaTest/Average/MaxReturn 149.776 MetaTest/Average/MinReturn -179.291 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 73.8397 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.9295 MetaTest/__unnamed_task__/AverageReturn -97.9295 MetaTest/__unnamed_task__/Iteration 212 MetaTest/__unnamed_task__/MaxReturn 149.776 MetaTest/__unnamed_task__/MinReturn -179.291 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 73.8397 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0224e+07 __unnamed_task__/AverageDiscountedReturn -34.8363 __unnamed_task__/AverageReturn -85.3861 __unnamed_task__/Iteration 212 __unnamed_task__/MaxReturn 122.283 __unnamed_task__/MinReturn -180.755 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 50.4011 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 21:03:15 | [maml_trainer] epoch #213 | Sampling for adapation and meta-testing... 2025-04-07 21:07:13 | [maml_trainer] epoch #213 | Finished meta-testing... 2025-04-07 21:07:13 | [maml_trainer] epoch #213 | Saving snapshot... 2025-04-07 21:07:36 | [maml_trainer] epoch #213 | Saved 2025-04-07 21:07:36 | [maml_trainer] epoch #213 | Time 361699.97 s 2025-04-07 21:07:36 | [maml_trainer] epoch #213 | EpochTime 1638.03 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -33.3081 Average/AverageReturn -75.0408 Average/Iteration 213 Average/MaxReturn 569.6 Average/MinReturn -181.438 Average/NumEpisodes 120 Average/StdReturn 87.6944 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84459 GaussianMLPPolicy/KLAfter 0.000831107 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.176e-05 GaussianMLPPolicy/LossBefore 6.33299e-10 GaussianMLPPolicy/dLoss -1.17594e-05 Iteration 213 MetaTest/Average/AverageDiscountedReturn -43.0997 MetaTest/Average/AverageReturn -43.0997 MetaTest/Average/Iteration 213 MetaTest/Average/MaxReturn 452.598 MetaTest/Average/MinReturn -149.423 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 117.463 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -43.0997 MetaTest/__unnamed_task__/AverageReturn -43.0997 MetaTest/__unnamed_task__/Iteration 213 MetaTest/__unnamed_task__/MaxReturn 452.598 MetaTest/__unnamed_task__/MinReturn -149.423 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 117.463 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0272e+07 __unnamed_task__/AverageDiscountedReturn -33.3081 __unnamed_task__/AverageReturn -75.0408 __unnamed_task__/Iteration 213 __unnamed_task__/MaxReturn 569.6 __unnamed_task__/MinReturn -181.438 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 87.6944 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 21:31:54 | [maml_trainer] epoch #214 | Sampling for adapation and meta-testing... 2025-04-07 21:35:55 | [maml_trainer] epoch #214 | Finished meta-testing... 2025-04-07 21:35:55 | [maml_trainer] epoch #214 | Saving snapshot... 2025-04-07 21:36:18 | [maml_trainer] epoch #214 | Saved 2025-04-07 21:36:18 | [maml_trainer] epoch #214 | Time 363422.13 s 2025-04-07 21:36:18 | [maml_trainer] epoch #214 | EpochTime 1722.16 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -34.3772 Average/AverageReturn -81.2388 Average/Iteration 214 Average/MaxReturn -4.30994 Average/MinReturn -191.39 Average/NumEpisodes 120 Average/StdReturn 43.875 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84482 GaussianMLPPolicy/KLAfter 0.000731566 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.16916e-07 GaussianMLPPolicy/LossBefore 1.00831e-09 GaussianMLPPolicy/dLoss 2.17925e-07 Iteration 214 MetaTest/Average/AverageDiscountedReturn -60.453 MetaTest/Average/AverageReturn -60.453 MetaTest/Average/Iteration 214 MetaTest/Average/MaxReturn 153.183 MetaTest/Average/MinReturn -166.283 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 58.5578 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -60.453 MetaTest/__unnamed_task__/AverageReturn -60.453 MetaTest/__unnamed_task__/Iteration 214 MetaTest/__unnamed_task__/MaxReturn 153.183 MetaTest/__unnamed_task__/MinReturn -166.283 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 58.5578 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.032e+07 __unnamed_task__/AverageDiscountedReturn -34.3772 __unnamed_task__/AverageReturn -81.2388 __unnamed_task__/Iteration 214 __unnamed_task__/MaxReturn -4.30994 __unnamed_task__/MinReturn -191.39 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 43.875 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 22:00:27 | [maml_trainer] epoch #215 | Sampling for adapation and meta-testing... 2025-04-07 22:04:32 | [maml_trainer] epoch #215 | Finished meta-testing... 2025-04-07 22:04:32 | [maml_trainer] epoch #215 | Saving snapshot... 2025-04-07 22:04:54 | [maml_trainer] epoch #215 | Saved 2025-04-07 22:04:54 | [maml_trainer] epoch #215 | Time 365138.90 s 2025-04-07 22:04:54 | [maml_trainer] epoch #215 | EpochTime 1716.76 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -34.6551 Average/AverageReturn -81.4791 Average/Iteration 215 Average/MaxReturn 37.8585 Average/MinReturn -184.33 Average/NumEpisodes 120 Average/StdReturn 48.1979 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84481 GaussianMLPPolicy/KLAfter 0.000498075 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.27544e-07 GaussianMLPPolicy/LossBefore -1.04308e-10 GaussianMLPPolicy/dLoss -4.27648e-07 Iteration 215 MetaTest/Average/AverageDiscountedReturn -93.6792 MetaTest/Average/AverageReturn -93.6792 MetaTest/Average/Iteration 215 MetaTest/Average/MaxReturn -24.6998 MetaTest/Average/MinReturn -180.452 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 53.3053 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.6792 MetaTest/__unnamed_task__/AverageReturn -93.6792 MetaTest/__unnamed_task__/Iteration 215 MetaTest/__unnamed_task__/MaxReturn -24.6998 MetaTest/__unnamed_task__/MinReturn -180.452 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 53.3053 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0368e+07 __unnamed_task__/AverageDiscountedReturn -34.6551 __unnamed_task__/AverageReturn -81.4791 __unnamed_task__/Iteration 215 __unnamed_task__/MaxReturn 37.8585 __unnamed_task__/MinReturn -184.33 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 48.1979 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 22:29:15 | [maml_trainer] epoch #216 | Sampling for adapation and meta-testing... 2025-04-07 22:33:20 | [maml_trainer] epoch #216 | Finished meta-testing... 2025-04-07 22:33:20 | [maml_trainer] epoch #216 | Saving snapshot... 2025-04-07 22:33:42 | [maml_trainer] epoch #216 | Saved 2025-04-07 22:33:42 | [maml_trainer] epoch #216 | Time 366866.72 s 2025-04-07 22:33:42 | [maml_trainer] epoch #216 | EpochTime 1727.82 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.5424 Average/AverageReturn -67.1759 Average/Iteration 216 Average/MaxReturn 291.717 Average/MinReturn -181.919 Average/NumEpisodes 120 Average/StdReturn 55.9835 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84498 GaussianMLPPolicy/KLAfter 0.000365958 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.29539e-06 GaussianMLPPolicy/LossBefore 1.81546e-09 GaussianMLPPolicy/dLoss 3.29721e-06 Iteration 216 MetaTest/Average/AverageDiscountedReturn -88.5721 MetaTest/Average/AverageReturn -88.5721 MetaTest/Average/Iteration 216 MetaTest/Average/MaxReturn -44.0768 MetaTest/Average/MinReturn -174.636 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 48.4091 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.5721 MetaTest/__unnamed_task__/AverageReturn -88.5721 MetaTest/__unnamed_task__/Iteration 216 MetaTest/__unnamed_task__/MaxReturn -44.0768 MetaTest/__unnamed_task__/MinReturn -174.636 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 48.4091 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0416e+07 __unnamed_task__/AverageDiscountedReturn -32.5424 __unnamed_task__/AverageReturn -67.1759 __unnamed_task__/Iteration 216 __unnamed_task__/MaxReturn 291.717 __unnamed_task__/MinReturn -181.919 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 55.9835 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 22:57:53 | [maml_trainer] epoch #217 | Sampling for adapation and meta-testing... 2025-04-07 23:01:55 | [maml_trainer] epoch #217 | Finished meta-testing... 2025-04-07 23:01:55 | [maml_trainer] epoch #217 | Saving snapshot... 2025-04-07 23:02:18 | [maml_trainer] epoch #217 | Saved 2025-04-07 23:02:18 | [maml_trainer] epoch #217 | Time 368582.31 s 2025-04-07 23:02:18 | [maml_trainer] epoch #217 | EpochTime 1715.60 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.473 Average/AverageReturn -67.2906 Average/Iteration 217 Average/MaxReturn 18.3245 Average/MinReturn -184.548 Average/NumEpisodes 120 Average/StdReturn 37.518 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84508 GaussianMLPPolicy/KLAfter 0.000567962 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.8983e-05 GaussianMLPPolicy/LossBefore -2.6226e-09 GaussianMLPPolicy/dLoss 2.89804e-05 Iteration 217 MetaTest/Average/AverageDiscountedReturn -67.767 MetaTest/Average/AverageReturn -67.767 MetaTest/Average/Iteration 217 MetaTest/Average/MaxReturn -42.6176 MetaTest/Average/MinReturn -173.924 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 36.6993 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -67.767 MetaTest/__unnamed_task__/AverageReturn -67.767 MetaTest/__unnamed_task__/Iteration 217 MetaTest/__unnamed_task__/MaxReturn -42.6176 MetaTest/__unnamed_task__/MinReturn -173.924 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 36.6993 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0464e+07 __unnamed_task__/AverageDiscountedReturn -32.473 __unnamed_task__/AverageReturn -67.2906 __unnamed_task__/Iteration 217 __unnamed_task__/MaxReturn 18.3245 __unnamed_task__/MinReturn -184.548 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 37.518 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 23:26:15 | [maml_trainer] epoch #218 | Sampling for adapation and meta-testing... 2025-04-07 23:30:14 | [maml_trainer] epoch #218 | Finished meta-testing... 2025-04-07 23:30:14 | [maml_trainer] epoch #218 | Saving snapshot... 2025-04-07 23:30:36 | [maml_trainer] epoch #218 | Saved 2025-04-07 23:30:36 | [maml_trainer] epoch #218 | Time 370280.37 s 2025-04-07 23:30:36 | [maml_trainer] epoch #218 | EpochTime 1698.05 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -33.4158 Average/AverageReturn -72.4132 Average/Iteration 218 Average/MaxReturn 145.952 Average/MinReturn -179.46 Average/NumEpisodes 120 Average/StdReturn 42.7261 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84605 GaussianMLPPolicy/KLAfter 0.000798306 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.48678e-05 GaussianMLPPolicy/LossBefore -5.46376e-10 GaussianMLPPolicy/dLoss 2.48673e-05 Iteration 218 MetaTest/Average/AverageDiscountedReturn -74.2311 MetaTest/Average/AverageReturn -74.2311 MetaTest/Average/Iteration 218 MetaTest/Average/MaxReturn -44.8012 MetaTest/Average/MinReturn -174.742 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 37.7341 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -74.2311 MetaTest/__unnamed_task__/AverageReturn -74.2311 MetaTest/__unnamed_task__/Iteration 218 MetaTest/__unnamed_task__/MaxReturn -44.8012 MetaTest/__unnamed_task__/MinReturn -174.742 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 37.7341 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0512e+07 __unnamed_task__/AverageDiscountedReturn -33.4158 __unnamed_task__/AverageReturn -72.4132 __unnamed_task__/Iteration 218 __unnamed_task__/MaxReturn 145.952 __unnamed_task__/MinReturn -179.46 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 42.7261 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-07 23:54:47 | [maml_trainer] epoch #219 | Sampling for adapation and meta-testing... 2025-04-07 23:58:57 | [maml_trainer] epoch #219 | Finished meta-testing... 2025-04-07 23:58:57 | [maml_trainer] epoch #219 | Saving snapshot... 2025-04-07 23:59:19 | [maml_trainer] epoch #219 | Saved 2025-04-07 23:59:19 | [maml_trainer] epoch #219 | Time 372003.53 s 2025-04-07 23:59:19 | [maml_trainer] epoch #219 | EpochTime 1723.16 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -32.4852 Average/AverageReturn -64.9872 Average/Iteration 219 Average/MaxReturn -44.8111 Average/MinReturn -179.797 Average/NumEpisodes 120 Average/StdReturn 29.6405 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84658 GaussianMLPPolicy/KLAfter 0.000834515 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.251e-05 GaussianMLPPolicy/LossBefore -2.54313e-09 GaussianMLPPolicy/dLoss 8.25074e-05 Iteration 219 MetaTest/Average/AverageDiscountedReturn -56.4674 MetaTest/Average/AverageReturn -56.4674 MetaTest/Average/Iteration 219 MetaTest/Average/MaxReturn -42.8188 MetaTest/Average/MinReturn -103.84 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.3131 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -56.4674 MetaTest/__unnamed_task__/AverageReturn -56.4674 MetaTest/__unnamed_task__/Iteration 219 MetaTest/__unnamed_task__/MaxReturn -42.8188 MetaTest/__unnamed_task__/MinReturn -103.84 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.3131 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.056e+07 __unnamed_task__/AverageDiscountedReturn -32.4852 __unnamed_task__/AverageReturn -64.9872 __unnamed_task__/Iteration 219 __unnamed_task__/MaxReturn -44.8111 __unnamed_task__/MinReturn -179.797 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 29.6405 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-08 00:23:41 | [maml_trainer] epoch #220 | Sampling for adapation and meta-testing... 2025-04-08 00:27:46 | [maml_trainer] epoch #220 | Finished meta-testing... 2025-04-08 00:27:46 | [maml_trainer] epoch #220 | Saving snapshot... 2025-04-08 00:28:10 | [maml_trainer] epoch #220 | Saved 2025-04-08 00:28:10 | [maml_trainer] epoch #220 | Time 373734.03 s 2025-04-08 00:28:10 | [maml_trainer] epoch #220 | EpochTime 1730.50 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -31.7954 Average/AverageReturn -61.0628 Average/Iteration 220 Average/MaxReturn -43.5615 Average/MinReturn -186.096 Average/NumEpisodes 120 Average/StdReturn 25.5624 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84708 GaussianMLPPolicy/KLAfter 0.00143132 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.23607e-05 GaussianMLPPolicy/LossBefore -2.58287e-09 GaussianMLPPolicy/dLoss 8.23582e-05 Iteration 220 MetaTest/Average/AverageDiscountedReturn -56.8087 MetaTest/Average/AverageReturn -56.8087 MetaTest/Average/Iteration 220 MetaTest/Average/MaxReturn -43.2111 MetaTest/Average/MinReturn -94.2869 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.3983 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -56.8087 MetaTest/__unnamed_task__/AverageReturn -56.8087 MetaTest/__unnamed_task__/Iteration 220 MetaTest/__unnamed_task__/MaxReturn -43.2111 MetaTest/__unnamed_task__/MinReturn -94.2869 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.3983 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0608e+07 __unnamed_task__/AverageDiscountedReturn -31.7954 __unnamed_task__/AverageReturn -61.0628 __unnamed_task__/Iteration 220 __unnamed_task__/MaxReturn -43.5615 __unnamed_task__/MinReturn -186.096 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 25.5624 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-08 00:52:34 | [maml_trainer] epoch #221 | Sampling for adapation and meta-testing... 2025-04-08 00:56:36 | [maml_trainer] epoch #221 | Finished meta-testing... 2025-04-08 00:56:36 | [maml_trainer] epoch #221 | Saving snapshot... 2025-04-08 00:56:59 | [maml_trainer] epoch #221 | Saved 2025-04-08 00:56:59 | [maml_trainer] epoch #221 | Time 375463.57 s 2025-04-08 00:56:59 | [maml_trainer] epoch #221 | EpochTime 1729.53 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -31.43 Average/AverageReturn -58.261 Average/Iteration 221 Average/MaxReturn -42.4764 Average/MinReturn -155.169 Average/NumEpisodes 120 Average/StdReturn 17.357 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84713 GaussianMLPPolicy/KLAfter 0.00170075 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.95687e-05 GaussianMLPPolicy/LossBefore -3.57628e-09 GaussianMLPPolicy/dLoss 6.95651e-05 Iteration 221 MetaTest/Average/AverageDiscountedReturn -52.8031 MetaTest/Average/AverageReturn -52.8031 MetaTest/Average/Iteration 221 MetaTest/Average/MaxReturn -43.4718 MetaTest/Average/MinReturn -72.3841 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.72631 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.8031 MetaTest/__unnamed_task__/AverageReturn -52.8031 MetaTest/__unnamed_task__/Iteration 221 MetaTest/__unnamed_task__/MaxReturn -43.4718 MetaTest/__unnamed_task__/MinReturn -72.3841 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.72631 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0656e+07 __unnamed_task__/AverageDiscountedReturn -31.43 __unnamed_task__/AverageReturn -58.261 __unnamed_task__/Iteration 221 __unnamed_task__/MaxReturn -42.4764 __unnamed_task__/MinReturn -155.169 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 17.357 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-08 01:20:47 | [maml_trainer] epoch #222 | Sampling for adapation and meta-testing... 2025-04-08 01:24:37 | [maml_trainer] epoch #222 | Finished meta-testing... 2025-04-08 01:24:37 | [maml_trainer] epoch #222 | Saving snapshot... 2025-04-08 01:24:59 | [maml_trainer] epoch #222 | Saved 2025-04-08 01:24:59 | [maml_trainer] epoch #222 | Time 377143.06 s 2025-04-08 01:24:59 | [maml_trainer] epoch #222 | EpochTime 1679.49 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -30.9878 Average/AverageReturn -56.3621 Average/Iteration 222 Average/MaxReturn -41.8165 Average/MinReturn -178.657 Average/NumEpisodes 120 Average/StdReturn 16.4418 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84735 GaussianMLPPolicy/KLAfter 0.00153284 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.8072e-05 GaussianMLPPolicy/LossBefore 6.39757e-09 GaussianMLPPolicy/dLoss 4.80784e-05 Iteration 222 MetaTest/Average/AverageDiscountedReturn -53.6769 MetaTest/Average/AverageReturn -53.6769 MetaTest/Average/Iteration 222 MetaTest/Average/MaxReturn -48.1442 MetaTest/Average/MinReturn -70.0109 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.98105 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.6769 MetaTest/__unnamed_task__/AverageReturn -53.6769 MetaTest/__unnamed_task__/Iteration 222 MetaTest/__unnamed_task__/MaxReturn -48.1442 MetaTest/__unnamed_task__/MinReturn -70.0109 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.98105 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0704e+07 __unnamed_task__/AverageDiscountedReturn -30.9878 __unnamed_task__/AverageReturn -56.3621 __unnamed_task__/Iteration 222 __unnamed_task__/MaxReturn -41.8165 __unnamed_task__/MinReturn -178.657 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 16.4418 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-08 02:14:07 | [maml_trainer] epoch #223 | Sampling for adapation and meta-testing... 2025-04-08 02:17:56 | [maml_trainer] epoch #223 | Finished meta-testing... 2025-04-08 02:17:56 | [maml_trainer] epoch #223 | Saving snapshot... 2025-04-08 02:18:18 | [maml_trainer] epoch #223 | Saved 2025-04-08 02:18:18 | [maml_trainer] epoch #223 | Time 380342.31 s 2025-04-08 02:18:18 | [maml_trainer] epoch #223 | EpochTime 3199.24 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -30.8355 Average/AverageReturn -54.4175 Average/Iteration 223 Average/MaxReturn -44.2098 Average/MinReturn -78.9861 Average/NumEpisodes 120 Average/StdReturn 5.27974 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84747 GaussianMLPPolicy/KLAfter 0.0020266 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.64764e-05 GaussianMLPPolicy/LossBefore 7.11282e-09 GaussianMLPPolicy/dLoss 4.64835e-05 Iteration 223 MetaTest/Average/AverageDiscountedReturn -54.1243 MetaTest/Average/AverageReturn -54.1243 MetaTest/Average/Iteration 223 MetaTest/Average/MaxReturn -45.607 MetaTest/Average/MinReturn -67.4636 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.31771 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.1243 MetaTest/__unnamed_task__/AverageReturn -54.1243 MetaTest/__unnamed_task__/Iteration 223 MetaTest/__unnamed_task__/MaxReturn -45.607 MetaTest/__unnamed_task__/MinReturn -67.4636 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.31771 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0752e+07 __unnamed_task__/AverageDiscountedReturn -30.8355 __unnamed_task__/AverageReturn -54.4175 __unnamed_task__/Iteration 223 __unnamed_task__/MaxReturn -44.2098 __unnamed_task__/MinReturn -78.9861 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.27974 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 02:41:23 | [maml_trainer] epoch #224 | Sampling for adapation and meta-testing... 2025-04-08 02:45:16 | [maml_trainer] epoch #224 | Finished meta-testing... 2025-04-08 02:45:16 | [maml_trainer] epoch #224 | Saving snapshot... 2025-04-08 02:45:38 | [maml_trainer] epoch #224 | Saved 2025-04-08 02:45:38 | [maml_trainer] epoch #224 | Time 381982.57 s 2025-04-08 02:45:38 | [maml_trainer] epoch #224 | EpochTime 1640.26 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -30.8542 Average/AverageReturn -54.602 Average/Iteration 224 Average/MaxReturn -44.7515 Average/MinReturn -67.2628 Average/NumEpisodes 120 Average/StdReturn 4.60167 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84811 GaussianMLPPolicy/KLAfter 0.001775 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.17248e-05 GaussianMLPPolicy/LossBefore 1.83185e-08 GaussianMLPPolicy/dLoss 3.17432e-05 Iteration 224 MetaTest/Average/AverageDiscountedReturn -54.2125 MetaTest/Average/AverageReturn -54.2125 MetaTest/Average/Iteration 224 MetaTest/Average/MaxReturn -45.9705 MetaTest/Average/MinReturn -65.2442 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.88956 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.2125 MetaTest/__unnamed_task__/AverageReturn -54.2125 MetaTest/__unnamed_task__/Iteration 224 MetaTest/__unnamed_task__/MaxReturn -45.9705 MetaTest/__unnamed_task__/MinReturn -65.2442 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.88956 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.08e+07 __unnamed_task__/AverageDiscountedReturn -30.8542 __unnamed_task__/AverageReturn -54.602 __unnamed_task__/Iteration 224 __unnamed_task__/MaxReturn -44.7515 __unnamed_task__/MinReturn -67.2628 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.60167 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 03:09:06 | [maml_trainer] epoch #225 | Sampling for adapation and meta-testing... 2025-04-08 03:12:57 | [maml_trainer] epoch #225 | Finished meta-testing... 2025-04-08 03:12:57 | [maml_trainer] epoch #225 | Saving snapshot... 2025-04-08 03:13:18 | [maml_trainer] epoch #225 | Saved 2025-04-08 03:13:18 | [maml_trainer] epoch #225 | Time 383642.32 s 2025-04-08 03:13:18 | [maml_trainer] epoch #225 | EpochTime 1659.75 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -30.4771 Average/AverageReturn -54.116 Average/Iteration 225 Average/MaxReturn -43.3829 Average/MinReturn -74.4891 Average/NumEpisodes 120 Average/StdReturn 5.38262 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84938 GaussianMLPPolicy/KLAfter 0.00148067 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.39287e-05 GaussianMLPPolicy/LossBefore 5.126e-09 GaussianMLPPolicy/dLoss -4.39236e-05 Iteration 225 MetaTest/Average/AverageDiscountedReturn -52.2795 MetaTest/Average/AverageReturn -52.2795 MetaTest/Average/Iteration 225 MetaTest/Average/MaxReturn -43.4853 MetaTest/Average/MinReturn -62.5078 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.91932 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2795 MetaTest/__unnamed_task__/AverageReturn -52.2795 MetaTest/__unnamed_task__/Iteration 225 MetaTest/__unnamed_task__/MaxReturn -43.4853 MetaTest/__unnamed_task__/MinReturn -62.5078 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.91932 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0848e+07 __unnamed_task__/AverageDiscountedReturn -30.4771 __unnamed_task__/AverageReturn -54.116 __unnamed_task__/Iteration 225 __unnamed_task__/MaxReturn -43.3829 __unnamed_task__/MinReturn -74.4891 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.38262 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 03:36:16 | [maml_trainer] epoch #226 | Sampling for adapation and meta-testing... 2025-04-08 03:40:05 | [maml_trainer] epoch #226 | Finished meta-testing... 2025-04-08 03:40:05 | [maml_trainer] epoch #226 | Saving snapshot... 2025-04-08 03:40:26 | [maml_trainer] epoch #226 | Saved 2025-04-08 03:40:26 | [maml_trainer] epoch #226 | Time 385270.56 s 2025-04-08 03:40:26 | [maml_trainer] epoch #226 | EpochTime 1628.23 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -30.5747 Average/AverageReturn -54.1625 Average/Iteration 226 Average/MaxReturn -44.3123 Average/MinReturn -67.5701 Average/NumEpisodes 120 Average/StdReturn 5.18402 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84932 GaussianMLPPolicy/KLAfter 0.000547848 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.49244e-05 GaussianMLPPolicy/LossBefore 1.20799e-08 GaussianMLPPolicy/dLoss -4.49123e-05 Iteration 226 MetaTest/Average/AverageDiscountedReturn -53.8645 MetaTest/Average/AverageReturn -53.8645 MetaTest/Average/Iteration 226 MetaTest/Average/MaxReturn -49.6632 MetaTest/Average/MinReturn -61.2228 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.49717 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.8645 MetaTest/__unnamed_task__/AverageReturn -53.8645 MetaTest/__unnamed_task__/Iteration 226 MetaTest/__unnamed_task__/MaxReturn -49.6632 MetaTest/__unnamed_task__/MinReturn -61.2228 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.49717 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0896e+07 __unnamed_task__/AverageDiscountedReturn -30.5747 __unnamed_task__/AverageReturn -54.1625 __unnamed_task__/Iteration 226 __unnamed_task__/MaxReturn -44.3123 __unnamed_task__/MinReturn -67.5701 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.18402 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 04:03:13 | [maml_trainer] epoch #227 | Sampling for adapation and meta-testing... 2025-04-08 04:07:05 | [maml_trainer] epoch #227 | Finished meta-testing... 2025-04-08 04:07:05 | [maml_trainer] epoch #227 | Saving snapshot... 2025-04-08 04:07:27 | [maml_trainer] epoch #227 | Saved 2025-04-08 04:07:27 | [maml_trainer] epoch #227 | Time 386891.42 s 2025-04-08 04:07:27 | [maml_trainer] epoch #227 | EpochTime 1620.86 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -30.5354 Average/AverageReturn -54.4566 Average/Iteration 227 Average/MaxReturn -44.6645 Average/MinReturn -71.6315 Average/NumEpisodes 120 Average/StdReturn 5.0443 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84819 GaussianMLPPolicy/KLAfter 0.00102144 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.22712e-06 GaussianMLPPolicy/LossBefore 6.39757e-09 GaussianMLPPolicy/dLoss -4.22072e-06 Iteration 227 MetaTest/Average/AverageDiscountedReturn -52.3155 MetaTest/Average/AverageReturn -52.3155 MetaTest/Average/Iteration 227 MetaTest/Average/MaxReturn -47.1095 MetaTest/Average/MinReturn -58.8453 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.75793 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.3155 MetaTest/__unnamed_task__/AverageReturn -52.3155 MetaTest/__unnamed_task__/Iteration 227 MetaTest/__unnamed_task__/MaxReturn -47.1095 MetaTest/__unnamed_task__/MinReturn -58.8453 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.75793 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0944e+07 __unnamed_task__/AverageDiscountedReturn -30.5354 __unnamed_task__/AverageReturn -54.4566 __unnamed_task__/Iteration 227 __unnamed_task__/MaxReturn -44.6645 __unnamed_task__/MinReturn -71.6315 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.0443 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 04:30:26 | [maml_trainer] epoch #228 | Sampling for adapation and meta-testing... 2025-04-08 04:34:13 | [maml_trainer] epoch #228 | Finished meta-testing... 2025-04-08 04:34:13 | [maml_trainer] epoch #228 | Saving snapshot... 2025-04-08 04:34:34 | [maml_trainer] epoch #228 | Saved 2025-04-08 04:34:34 | [maml_trainer] epoch #228 | Time 388518.76 s 2025-04-08 04:34:34 | [maml_trainer] epoch #228 | EpochTime 1627.33 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -30.4646 Average/AverageReturn -54.5988 Average/Iteration 228 Average/MaxReturn -45.3556 Average/MinReturn -72.4068 Average/NumEpisodes 120 Average/StdReturn 5.49055 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84847 GaussianMLPPolicy/KLAfter 0.000902898 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.65983e-05 GaussianMLPPolicy/LossBefore -1.00931e-08 GaussianMLPPolicy/dLoss -1.66084e-05 Iteration 228 MetaTest/Average/AverageDiscountedReturn -54.5802 MetaTest/Average/AverageReturn -54.5802 MetaTest/Average/Iteration 228 MetaTest/Average/MaxReturn -47.191 MetaTest/Average/MinReturn -72.0911 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.90902 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.5802 MetaTest/__unnamed_task__/AverageReturn -54.5802 MetaTest/__unnamed_task__/Iteration 228 MetaTest/__unnamed_task__/MaxReturn -47.191 MetaTest/__unnamed_task__/MinReturn -72.0911 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.90902 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.0992e+07 __unnamed_task__/AverageDiscountedReturn -30.4646 __unnamed_task__/AverageReturn -54.5988 __unnamed_task__/Iteration 228 __unnamed_task__/MaxReturn -45.3556 __unnamed_task__/MinReturn -72.4068 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.49055 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 04:57:20 | [maml_trainer] epoch #229 | Sampling for adapation and meta-testing... 2025-04-08 05:01:13 | [maml_trainer] epoch #229 | Finished meta-testing... 2025-04-08 05:01:13 | [maml_trainer] epoch #229 | Saving snapshot... 2025-04-08 05:01:35 | [maml_trainer] epoch #229 | Saved 2025-04-08 05:01:35 | [maml_trainer] epoch #229 | Time 390139.26 s 2025-04-08 05:01:35 | [maml_trainer] epoch #229 | EpochTime 1620.50 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.9718 Average/AverageReturn -53.353 Average/Iteration 229 Average/MaxReturn -43.8429 Average/MinReturn -74.3876 Average/NumEpisodes 120 Average/StdReturn 5.39783 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84665 GaussianMLPPolicy/KLAfter 0.00192779 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.16907e-06 GaussianMLPPolicy/LossBefore 8.38439e-09 GaussianMLPPolicy/dLoss 4.17745e-06 Iteration 229 MetaTest/Average/AverageDiscountedReturn -54.0312 MetaTest/Average/AverageReturn -54.0312 MetaTest/Average/Iteration 229 MetaTest/Average/MaxReturn -46.9553 MetaTest/Average/MinReturn -75.817 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.48531 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.0312 MetaTest/__unnamed_task__/AverageReturn -54.0312 MetaTest/__unnamed_task__/Iteration 229 MetaTest/__unnamed_task__/MaxReturn -46.9553 MetaTest/__unnamed_task__/MinReturn -75.817 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.48531 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.104e+07 __unnamed_task__/AverageDiscountedReturn -29.9718 __unnamed_task__/AverageReturn -53.353 __unnamed_task__/Iteration 229 __unnamed_task__/MaxReturn -43.8429 __unnamed_task__/MinReturn -74.3876 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.39783 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 05:24:49 | [maml_trainer] epoch #230 | Sampling for adapation and meta-testing... 2025-04-08 05:28:41 | [maml_trainer] epoch #230 | Finished meta-testing... 2025-04-08 05:28:41 | [maml_trainer] epoch #230 | Saving snapshot... 2025-04-08 05:29:03 | [maml_trainer] epoch #230 | Saved 2025-04-08 05:29:03 | [maml_trainer] epoch #230 | Time 391787.19 s 2025-04-08 05:29:03 | [maml_trainer] epoch #230 | EpochTime 1647.92 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -30.0965 Average/AverageReturn -53.4324 Average/Iteration 230 Average/MaxReturn -44.1763 Average/MinReturn -70.0169 Average/NumEpisodes 120 Average/StdReturn 5.3604 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84393 GaussianMLPPolicy/KLAfter 0.00178547 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.73275e-05 GaussianMLPPolicy/LossBefore 4.29153e-09 GaussianMLPPolicy/dLoss 1.73318e-05 Iteration 230 MetaTest/Average/AverageDiscountedReturn -51.0995 MetaTest/Average/AverageReturn -51.0995 MetaTest/Average/Iteration 230 MetaTest/Average/MaxReturn -45.0423 MetaTest/Average/MinReturn -63.549 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.26865 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.0995 MetaTest/__unnamed_task__/AverageReturn -51.0995 MetaTest/__unnamed_task__/Iteration 230 MetaTest/__unnamed_task__/MaxReturn -45.0423 MetaTest/__unnamed_task__/MinReturn -63.549 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.26865 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1088e+07 __unnamed_task__/AverageDiscountedReturn -30.0965 __unnamed_task__/AverageReturn -53.4324 __unnamed_task__/Iteration 230 __unnamed_task__/MaxReturn -44.1763 __unnamed_task__/MinReturn -70.0169 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.3604 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 05:51:54 | [maml_trainer] epoch #231 | Sampling for adapation and meta-testing... 2025-04-08 05:55:46 | [maml_trainer] epoch #231 | Finished meta-testing... 2025-04-08 05:55:46 | [maml_trainer] epoch #231 | Saving snapshot... 2025-04-08 05:56:08 | [maml_trainer] epoch #231 | Saved 2025-04-08 05:56:08 | [maml_trainer] epoch #231 | Time 393411.98 s 2025-04-08 05:56:08 | [maml_trainer] epoch #231 | EpochTime 1624.79 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.8013 Average/AverageReturn -52.6333 Average/Iteration 231 Average/MaxReturn -44.1102 Average/MinReturn -64.6575 Average/NumEpisodes 120 Average/StdReturn 4.14468 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84149 GaussianMLPPolicy/KLAfter 0.00245707 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.23451e-05 GaussianMLPPolicy/LossBefore -5.126e-09 GaussianMLPPolicy/dLoss -7.23502e-05 Iteration 231 MetaTest/Average/AverageDiscountedReturn -52.0377 MetaTest/Average/AverageReturn -52.0377 MetaTest/Average/Iteration 231 MetaTest/Average/MaxReturn -45.8797 MetaTest/Average/MinReturn -57.7637 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 2.8609 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.0377 MetaTest/__unnamed_task__/AverageReturn -52.0377 MetaTest/__unnamed_task__/Iteration 231 MetaTest/__unnamed_task__/MaxReturn -45.8797 MetaTest/__unnamed_task__/MinReturn -57.7637 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 2.8609 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1136e+07 __unnamed_task__/AverageDiscountedReturn -29.8013 __unnamed_task__/AverageReturn -52.6333 __unnamed_task__/Iteration 231 __unnamed_task__/MaxReturn -44.1102 __unnamed_task__/MinReturn -64.6575 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.14468 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 06:19:14 | [maml_trainer] epoch #232 | Sampling for adapation and meta-testing... 2025-04-08 06:23:08 | [maml_trainer] epoch #232 | Finished meta-testing... 2025-04-08 06:23:08 | [maml_trainer] epoch #232 | Saving snapshot... 2025-04-08 06:23:30 | [maml_trainer] epoch #232 | Saved 2025-04-08 06:23:30 | [maml_trainer] epoch #232 | Time 395054.71 s 2025-04-08 06:23:30 | [maml_trainer] epoch #232 | EpochTime 1642.73 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.2189 Average/AverageReturn -51.2649 Average/Iteration 232 Average/MaxReturn -42.1524 Average/MinReturn -71.2547 Average/NumEpisodes 120 Average/StdReturn 4.42689 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.83825 GaussianMLPPolicy/KLAfter 0.00310522 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.39582e-05 GaussianMLPPolicy/LossBefore -1.50998e-08 GaussianMLPPolicy/dLoss 4.39431e-05 Iteration 232 MetaTest/Average/AverageDiscountedReturn -50.961 MetaTest/Average/AverageReturn -50.961 MetaTest/Average/Iteration 232 MetaTest/Average/MaxReturn -45.5579 MetaTest/Average/MinReturn -56.9673 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.25829 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.961 MetaTest/__unnamed_task__/AverageReturn -50.961 MetaTest/__unnamed_task__/Iteration 232 MetaTest/__unnamed_task__/MaxReturn -45.5579 MetaTest/__unnamed_task__/MinReturn -56.9673 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.25829 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1184e+07 __unnamed_task__/AverageDiscountedReturn -29.2189 __unnamed_task__/AverageReturn -51.2649 __unnamed_task__/Iteration 232 __unnamed_task__/MaxReturn -42.1524 __unnamed_task__/MinReturn -71.2547 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.42689 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 06:47:02 | [maml_trainer] epoch #233 | Sampling for adapation and meta-testing... 2025-04-08 06:50:56 | [maml_trainer] epoch #233 | Finished meta-testing... 2025-04-08 06:50:56 | [maml_trainer] epoch #233 | Saving snapshot... 2025-04-08 06:51:18 | [maml_trainer] epoch #233 | Saved 2025-04-08 06:51:18 | [maml_trainer] epoch #233 | Time 396722.24 s 2025-04-08 06:51:18 | [maml_trainer] epoch #233 | EpochTime 1667.52 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.5677 Average/AverageReturn -52.0624 Average/Iteration 233 Average/MaxReturn -44.7506 Average/MinReturn -66.7195 Average/NumEpisodes 120 Average/StdReturn 4.4741 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.83534 GaussianMLPPolicy/KLAfter 0.00260178 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000113778 GaussianMLPPolicy/LossBefore 8.98043e-09 GaussianMLPPolicy/dLoss 0.000113787 Iteration 233 MetaTest/Average/AverageDiscountedReturn -50.3319 MetaTest/Average/AverageReturn -50.3319 MetaTest/Average/Iteration 233 MetaTest/Average/MaxReturn -45.8276 MetaTest/Average/MinReturn -53.5706 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 2.11325 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.3319 MetaTest/__unnamed_task__/AverageReturn -50.3319 MetaTest/__unnamed_task__/Iteration 233 MetaTest/__unnamed_task__/MaxReturn -45.8276 MetaTest/__unnamed_task__/MinReturn -53.5706 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 2.11325 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1232e+07 __unnamed_task__/AverageDiscountedReturn -29.5677 __unnamed_task__/AverageReturn -52.0624 __unnamed_task__/Iteration 233 __unnamed_task__/MaxReturn -44.7506 __unnamed_task__/MinReturn -66.7195 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.4741 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 07:14:25 | [maml_trainer] epoch #234 | Sampling for adapation and meta-testing... 2025-04-08 07:18:25 | [maml_trainer] epoch #234 | Finished meta-testing... 2025-04-08 07:18:25 | [maml_trainer] epoch #234 | Saving snapshot... 2025-04-08 07:18:47 | [maml_trainer] epoch #234 | Saved 2025-04-08 07:18:47 | [maml_trainer] epoch #234 | Time 398371.26 s 2025-04-08 07:18:47 | [maml_trainer] epoch #234 | EpochTime 1649.02 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.0446 Average/AverageReturn -51.354 Average/Iteration 234 Average/MaxReturn -41.0632 Average/MinReturn -72.6134 Average/NumEpisodes 120 Average/StdReturn 5.19536 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.83269 GaussianMLPPolicy/KLAfter 0.00324489 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000104221 GaussianMLPPolicy/LossBefore 1.39078e-09 GaussianMLPPolicy/dLoss -0.000104219 Iteration 234 MetaTest/Average/AverageDiscountedReturn -50.2024 MetaTest/Average/AverageReturn -50.2024 MetaTest/Average/Iteration 234 MetaTest/Average/MaxReturn -42.4582 MetaTest/Average/MinReturn -59.5724 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.60811 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.2024 MetaTest/__unnamed_task__/AverageReturn -50.2024 MetaTest/__unnamed_task__/Iteration 234 MetaTest/__unnamed_task__/MaxReturn -42.4582 MetaTest/__unnamed_task__/MinReturn -59.5724 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.60811 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.128e+07 __unnamed_task__/AverageDiscountedReturn -29.0446 __unnamed_task__/AverageReturn -51.354 __unnamed_task__/Iteration 234 __unnamed_task__/MaxReturn -41.0632 __unnamed_task__/MinReturn -72.6134 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.19536 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 07:42:29 | [maml_trainer] epoch #235 | Sampling for adapation and meta-testing... 2025-04-08 07:46:21 | [maml_trainer] epoch #235 | Finished meta-testing... 2025-04-08 07:46:21 | [maml_trainer] epoch #235 | Saving snapshot... 2025-04-08 07:46:42 | [maml_trainer] epoch #235 | Saved 2025-04-08 07:46:42 | [maml_trainer] epoch #235 | Time 400046.80 s 2025-04-08 07:46:42 | [maml_trainer] epoch #235 | EpochTime 1675.54 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.2365 Average/AverageReturn -51.9828 Average/Iteration 235 Average/MaxReturn -42.4261 Average/MinReturn -68.2036 Average/NumEpisodes 120 Average/StdReturn 4.69304 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.82896 GaussianMLPPolicy/KLAfter 0.00395181 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000156514 GaussianMLPPolicy/LossBefore 6.15915e-09 GaussianMLPPolicy/dLoss -0.000156507 Iteration 235 MetaTest/Average/AverageDiscountedReturn -50.7603 MetaTest/Average/AverageReturn -50.7603 MetaTest/Average/Iteration 235 MetaTest/Average/MaxReturn -42.5149 MetaTest/Average/MinReturn -69.5694 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.87698 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.7603 MetaTest/__unnamed_task__/AverageReturn -50.7603 MetaTest/__unnamed_task__/Iteration 235 MetaTest/__unnamed_task__/MaxReturn -42.5149 MetaTest/__unnamed_task__/MinReturn -69.5694 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.87698 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1328e+07 __unnamed_task__/AverageDiscountedReturn -29.2365 __unnamed_task__/AverageReturn -51.9828 __unnamed_task__/Iteration 235 __unnamed_task__/MaxReturn -42.4261 __unnamed_task__/MinReturn -68.2036 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.69304 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 08:10:09 | [maml_trainer] epoch #236 | Sampling for adapation and meta-testing... 2025-04-08 08:14:04 | [maml_trainer] epoch #236 | Finished meta-testing... 2025-04-08 08:14:04 | [maml_trainer] epoch #236 | Saving snapshot... 2025-04-08 08:14:25 | [maml_trainer] epoch #236 | Saved 2025-04-08 08:14:25 | [maml_trainer] epoch #236 | Time 401709.90 s 2025-04-08 08:14:25 | [maml_trainer] epoch #236 | EpochTime 1663.09 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.5871 Average/AverageReturn -50.7911 Average/Iteration 236 Average/MaxReturn -40.5226 Average/MinReturn -71.4503 Average/NumEpisodes 120 Average/StdReturn 5.55317 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.82669 GaussianMLPPolicy/KLAfter 0.00274492 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.59901e-05 GaussianMLPPolicy/LossBefore 1.3272e-08 GaussianMLPPolicy/dLoss -1.59768e-05 Iteration 236 MetaTest/Average/AverageDiscountedReturn -49.7591 MetaTest/Average/AverageReturn -49.7591 MetaTest/Average/Iteration 236 MetaTest/Average/MaxReturn -41.9622 MetaTest/Average/MinReturn -61.8325 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.11553 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.7591 MetaTest/__unnamed_task__/AverageReturn -49.7591 MetaTest/__unnamed_task__/Iteration 236 MetaTest/__unnamed_task__/MaxReturn -41.9622 MetaTest/__unnamed_task__/MinReturn -61.8325 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.11553 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1376e+07 __unnamed_task__/AverageDiscountedReturn -28.5871 __unnamed_task__/AverageReturn -50.7911 __unnamed_task__/Iteration 236 __unnamed_task__/MaxReturn -40.5226 __unnamed_task__/MinReturn -71.4503 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.55317 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 08:37:41 | [maml_trainer] epoch #237 | Sampling for adapation and meta-testing... 2025-04-08 08:41:36 | [maml_trainer] epoch #237 | Finished meta-testing... 2025-04-08 08:41:36 | [maml_trainer] epoch #237 | Saving snapshot... 2025-04-08 08:41:58 | [maml_trainer] epoch #237 | Saved 2025-04-08 08:41:58 | [maml_trainer] epoch #237 | Time 403361.99 s 2025-04-08 08:41:58 | [maml_trainer] epoch #237 | EpochTime 1652.09 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.9405 Average/AverageReturn -50.6949 Average/Iteration 237 Average/MaxReturn 204.397 Average/MinReturn -69.5446 Average/NumEpisodes 120 Average/StdReturn 24.0232 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.82337 GaussianMLPPolicy/KLAfter 0.00297702 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.12971e-05 GaussianMLPPolicy/LossBefore -7.15256e-10 GaussianMLPPolicy/dLoss 4.12964e-05 Iteration 237 MetaTest/Average/AverageDiscountedReturn -51.091 MetaTest/Average/AverageReturn -51.091 MetaTest/Average/Iteration 237 MetaTest/Average/MaxReturn -44.9536 MetaTest/Average/MinReturn -58.9656 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.47283 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.091 MetaTest/__unnamed_task__/AverageReturn -51.091 MetaTest/__unnamed_task__/Iteration 237 MetaTest/__unnamed_task__/MaxReturn -44.9536 MetaTest/__unnamed_task__/MinReturn -58.9656 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.47283 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1424e+07 __unnamed_task__/AverageDiscountedReturn -28.9405 __unnamed_task__/AverageReturn -50.6949 __unnamed_task__/Iteration 237 __unnamed_task__/MaxReturn 204.397 __unnamed_task__/MinReturn -69.5446 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 24.0232 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 09:05:31 | [maml_trainer] epoch #238 | Sampling for adapation and meta-testing... 2025-04-08 09:09:28 | [maml_trainer] epoch #238 | Finished meta-testing... 2025-04-08 09:09:28 | [maml_trainer] epoch #238 | Saving snapshot... 2025-04-08 09:09:50 | [maml_trainer] epoch #238 | Saved 2025-04-08 09:09:50 | [maml_trainer] epoch #238 | Time 405034.50 s 2025-04-08 09:09:50 | [maml_trainer] epoch #238 | EpochTime 1672.50 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.9844 Average/AverageReturn -52.7487 Average/Iteration 238 Average/MaxReturn -40.236 Average/MinReturn -133.06 Average/NumEpisodes 120 Average/StdReturn 10.1212 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81901 GaussianMLPPolicy/KLAfter 0.00194427 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.7522e-05 GaussianMLPPolicy/LossBefore -3.97364e-11 GaussianMLPPolicy/dLoss -8.7522e-05 Iteration 238 MetaTest/Average/AverageDiscountedReturn -52.9153 MetaTest/Average/AverageReturn -52.9153 MetaTest/Average/Iteration 238 MetaTest/Average/MaxReturn -44.6373 MetaTest/Average/MinReturn -64.6056 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.06248 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.9153 MetaTest/__unnamed_task__/AverageReturn -52.9153 MetaTest/__unnamed_task__/Iteration 238 MetaTest/__unnamed_task__/MaxReturn -44.6373 MetaTest/__unnamed_task__/MinReturn -64.6056 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.06248 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1472e+07 __unnamed_task__/AverageDiscountedReturn -28.9844 __unnamed_task__/AverageReturn -52.7487 __unnamed_task__/Iteration 238 __unnamed_task__/MaxReturn -40.236 __unnamed_task__/MinReturn -133.06 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.1212 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-08 09:33:27 | [maml_trainer] epoch #239 | Sampling for adapation and meta-testing... 2025-04-08 09:37:21 | [maml_trainer] epoch #239 | Finished meta-testing... 2025-04-08 09:37:21 | [maml_trainer] epoch #239 | Saving snapshot... 2025-04-08 09:37:43 | [maml_trainer] epoch #239 | Saved 2025-04-08 09:37:43 | [maml_trainer] epoch #239 | Time 406707.44 s 2025-04-08 09:37:43 | [maml_trainer] epoch #239 | EpochTime 1672.94 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -29.0641 Average/AverageReturn -52.5882 Average/Iteration 239 Average/MaxReturn -42.5082 Average/MinReturn -70.5259 Average/NumEpisodes 120 Average/StdReturn 6.15243 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81607 GaussianMLPPolicy/KLAfter 0.0012625 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.50259e-05 GaussianMLPPolicy/LossBefore 8.74201e-10 GaussianMLPPolicy/dLoss 6.50268e-05 Iteration 239 MetaTest/Average/AverageDiscountedReturn -50.8816 MetaTest/Average/AverageReturn -50.8816 MetaTest/Average/Iteration 239 MetaTest/Average/MaxReturn -41.6194 MetaTest/Average/MinReturn -59.7724 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.22666 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.8816 MetaTest/__unnamed_task__/AverageReturn -50.8816 MetaTest/__unnamed_task__/Iteration 239 MetaTest/__unnamed_task__/MaxReturn -41.6194 MetaTest/__unnamed_task__/MinReturn -59.7724 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.22666 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.152e+07 __unnamed_task__/AverageDiscountedReturn -29.0641 __unnamed_task__/AverageReturn -52.5882 __unnamed_task__/Iteration 239 __unnamed_task__/MaxReturn -42.5082 __unnamed_task__/MinReturn -70.5259 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.15243 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 10:01:15 | [maml_trainer] epoch #240 | Sampling for adapation and meta-testing... 2025-04-08 10:05:20 | [maml_trainer] epoch #240 | Finished meta-testing... 2025-04-08 10:05:20 | [maml_trainer] epoch #240 | Saving snapshot... 2025-04-08 10:05:43 | [maml_trainer] epoch #240 | Saved 2025-04-08 10:05:43 | [maml_trainer] epoch #240 | Time 408387.95 s 2025-04-08 10:05:43 | [maml_trainer] epoch #240 | EpochTime 1680.51 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -29.2563 Average/AverageReturn -53.8642 Average/Iteration 240 Average/MaxReturn -41.6887 Average/MinReturn -173.623 Average/NumEpisodes 120 Average/StdReturn 13.1301 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81342 GaussianMLPPolicy/KLAfter 0.00177441 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.99203e-06 GaussianMLPPolicy/LossBefore 1.49012e-09 GaussianMLPPolicy/dLoss -4.99054e-06 Iteration 240 MetaTest/Average/AverageDiscountedReturn -50.5434 MetaTest/Average/AverageReturn -50.5434 MetaTest/Average/Iteration 240 MetaTest/Average/MaxReturn -42.0598 MetaTest/Average/MinReturn -61.4803 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.61384 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5434 MetaTest/__unnamed_task__/AverageReturn -50.5434 MetaTest/__unnamed_task__/Iteration 240 MetaTest/__unnamed_task__/MaxReturn -42.0598 MetaTest/__unnamed_task__/MinReturn -61.4803 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.61384 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1568e+07 __unnamed_task__/AverageDiscountedReturn -29.2563 __unnamed_task__/AverageReturn -53.8642 __unnamed_task__/Iteration 240 __unnamed_task__/MaxReturn -41.6887 __unnamed_task__/MinReturn -173.623 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 13.1301 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-08 10:30:27 | [maml_trainer] epoch #241 | Sampling for adapation and meta-testing... 2025-04-08 10:34:36 | [maml_trainer] epoch #241 | Finished meta-testing... 2025-04-08 10:34:36 | [maml_trainer] epoch #241 | Saving snapshot... 2025-04-08 10:35:00 | [maml_trainer] epoch #241 | Saved 2025-04-08 10:35:00 | [maml_trainer] epoch #241 | Time 410144.38 s 2025-04-08 10:35:00 | [maml_trainer] epoch #241 | EpochTime 1756.42 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.3258 Average/AverageReturn -50.5161 Average/Iteration 241 Average/MaxReturn -42.0889 Average/MinReturn -69.8231 Average/NumEpisodes 120 Average/StdReturn 5.23293 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81152 GaussianMLPPolicy/KLAfter 0.00129788 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.37611e-07 GaussianMLPPolicy/LossBefore 8.82149e-09 GaussianMLPPolicy/dLoss -6.28789e-07 Iteration 241 MetaTest/Average/AverageDiscountedReturn -52.6926 MetaTest/Average/AverageReturn -52.6926 MetaTest/Average/Iteration 241 MetaTest/Average/MaxReturn -42.9669 MetaTest/Average/MinReturn -70.8061 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.52521 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6926 MetaTest/__unnamed_task__/AverageReturn -52.6926 MetaTest/__unnamed_task__/Iteration 241 MetaTest/__unnamed_task__/MaxReturn -42.9669 MetaTest/__unnamed_task__/MinReturn -70.8061 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.52521 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1616e+07 __unnamed_task__/AverageDiscountedReturn -28.3258 __unnamed_task__/AverageReturn -50.5161 __unnamed_task__/Iteration 241 __unnamed_task__/MaxReturn -42.0889 __unnamed_task__/MinReturn -69.8231 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.23293 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 10:59:40 | [maml_trainer] epoch #242 | Sampling for adapation and meta-testing... 2025-04-08 11:03:45 | [maml_trainer] epoch #242 | Finished meta-testing... 2025-04-08 11:03:45 | [maml_trainer] epoch #242 | Saving snapshot... 2025-04-08 11:04:09 | [maml_trainer] epoch #242 | Saved 2025-04-08 11:04:09 | [maml_trainer] epoch #242 | Time 411893.37 s 2025-04-08 11:04:09 | [maml_trainer] epoch #242 | EpochTime 1748.98 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.758 Average/AverageReturn -51.9033 Average/Iteration 242 Average/MaxReturn -42.0154 Average/MinReturn -67.6078 Average/NumEpisodes 120 Average/StdReturn 5.72807 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81028 GaussianMLPPolicy/KLAfter 0.000995313 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.43395e-05 GaussianMLPPolicy/LossBefore -6.19888e-09 GaussianMLPPolicy/dLoss 1.43333e-05 Iteration 242 MetaTest/Average/AverageDiscountedReturn -52.6808 MetaTest/Average/AverageReturn -52.6808 MetaTest/Average/Iteration 242 MetaTest/Average/MaxReturn -45.9137 MetaTest/Average/MinReturn -70.3188 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.49793 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6808 MetaTest/__unnamed_task__/AverageReturn -52.6808 MetaTest/__unnamed_task__/Iteration 242 MetaTest/__unnamed_task__/MaxReturn -45.9137 MetaTest/__unnamed_task__/MinReturn -70.3188 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.49793 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1664e+07 __unnamed_task__/AverageDiscountedReturn -28.758 __unnamed_task__/AverageReturn -51.9033 __unnamed_task__/Iteration 242 __unnamed_task__/MaxReturn -42.0154 __unnamed_task__/MinReturn -67.6078 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.72807 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 11:29:01 | [maml_trainer] epoch #243 | Sampling for adapation and meta-testing... 2025-04-08 11:33:13 | [maml_trainer] epoch #243 | Finished meta-testing... 2025-04-08 11:33:13 | [maml_trainer] epoch #243 | Saving snapshot... 2025-04-08 11:33:37 | [maml_trainer] epoch #243 | Saved 2025-04-08 11:33:37 | [maml_trainer] epoch #243 | Time 413661.20 s 2025-04-08 11:33:37 | [maml_trainer] epoch #243 | EpochTime 1767.83 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.6457 Average/AverageReturn -51.5362 Average/Iteration 243 Average/MaxReturn -42.4751 Average/MinReturn -68.3209 Average/NumEpisodes 120 Average/StdReturn 5.03247 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.8102 GaussianMLPPolicy/KLAfter 0.00114557 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.36318e-05 GaussianMLPPolicy/LossBefore 5.32468e-09 GaussianMLPPolicy/dLoss 3.36371e-05 Iteration 243 MetaTest/Average/AverageDiscountedReturn -52.2185 MetaTest/Average/AverageReturn -52.2185 MetaTest/Average/Iteration 243 MetaTest/Average/MaxReturn -44.519 MetaTest/Average/MinReturn -62.0051 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.97425 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2185 MetaTest/__unnamed_task__/AverageReturn -52.2185 MetaTest/__unnamed_task__/Iteration 243 MetaTest/__unnamed_task__/MaxReturn -44.519 MetaTest/__unnamed_task__/MinReturn -62.0051 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.97425 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1712e+07 __unnamed_task__/AverageDiscountedReturn -28.6457 __unnamed_task__/AverageReturn -51.5362 __unnamed_task__/Iteration 243 __unnamed_task__/MaxReturn -42.4751 __unnamed_task__/MinReturn -68.3209 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.03247 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 11:58:26 | [maml_trainer] epoch #244 | Sampling for adapation and meta-testing... 2025-04-08 12:02:27 | [maml_trainer] epoch #244 | Finished meta-testing... 2025-04-08 12:02:27 | [maml_trainer] epoch #244 | Saving snapshot... 2025-04-08 12:02:50 | [maml_trainer] epoch #244 | Saved 2025-04-08 12:02:50 | [maml_trainer] epoch #244 | Time 415414.47 s 2025-04-08 12:02:50 | [maml_trainer] epoch #244 | EpochTime 1753.26 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.5324 Average/AverageReturn -51.3588 Average/Iteration 244 Average/MaxReturn -42.8646 Average/MinReturn -71.0507 Average/NumEpisodes 120 Average/StdReturn 4.51158 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81066 GaussianMLPPolicy/KLAfter 0.00183725 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.30579e-05 GaussianMLPPolicy/LossBefore 1.95901e-08 GaussianMLPPolicy/dLoss 9.30775e-05 Iteration 244 MetaTest/Average/AverageDiscountedReturn -52.6962 MetaTest/Average/AverageReturn -52.6962 MetaTest/Average/Iteration 244 MetaTest/Average/MaxReturn -44.9474 MetaTest/Average/MinReturn -72.5132 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.65362 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6962 MetaTest/__unnamed_task__/AverageReturn -52.6962 MetaTest/__unnamed_task__/Iteration 244 MetaTest/__unnamed_task__/MaxReturn -44.9474 MetaTest/__unnamed_task__/MinReturn -72.5132 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.65362 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.176e+07 __unnamed_task__/AverageDiscountedReturn -28.5324 __unnamed_task__/AverageReturn -51.3588 __unnamed_task__/Iteration 244 __unnamed_task__/MaxReturn -42.8646 __unnamed_task__/MinReturn -71.0507 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.51158 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 12:27:40 | [maml_trainer] epoch #245 | Sampling for adapation and meta-testing... 2025-04-08 12:31:49 | [maml_trainer] epoch #245 | Finished meta-testing... 2025-04-08 12:31:49 | [maml_trainer] epoch #245 | Saving snapshot... 2025-04-08 12:32:12 | [maml_trainer] epoch #245 | Saved 2025-04-08 12:32:12 | [maml_trainer] epoch #245 | Time 417176.79 s 2025-04-08 12:32:12 | [maml_trainer] epoch #245 | EpochTime 1762.31 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.8971 Average/AverageReturn -51.8676 Average/Iteration 245 Average/MaxReturn -42.8434 Average/MinReturn -66.3916 Average/NumEpisodes 120 Average/StdReturn 4.83858 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81103 GaussianMLPPolicy/KLAfter 0.00217185 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.96368e-05 GaussianMLPPolicy/LossBefore -1.73648e-08 GaussianMLPPolicy/dLoss -6.96541e-05 Iteration 245 MetaTest/Average/AverageDiscountedReturn -53.0855 MetaTest/Average/AverageReturn -53.0855 MetaTest/Average/Iteration 245 MetaTest/Average/MaxReturn -45.4076 MetaTest/Average/MinReturn -68.2465 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.27092 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.0855 MetaTest/__unnamed_task__/AverageReturn -53.0855 MetaTest/__unnamed_task__/Iteration 245 MetaTest/__unnamed_task__/MaxReturn -45.4076 MetaTest/__unnamed_task__/MinReturn -68.2465 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.27092 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1808e+07 __unnamed_task__/AverageDiscountedReturn -28.8971 __unnamed_task__/AverageReturn -51.8676 __unnamed_task__/Iteration 245 __unnamed_task__/MaxReturn -42.8434 __unnamed_task__/MinReturn -66.3916 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.83858 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 12:56:44 | [maml_trainer] epoch #246 | Sampling for adapation and meta-testing... 2025-04-08 13:00:48 | [maml_trainer] epoch #246 | Finished meta-testing... 2025-04-08 13:00:48 | [maml_trainer] epoch #246 | Saving snapshot... 2025-04-08 13:01:11 | [maml_trainer] epoch #246 | Saved 2025-04-08 13:01:12 | [maml_trainer] epoch #246 | Time 418915.96 s 2025-04-08 13:01:12 | [maml_trainer] epoch #246 | EpochTime 1739.17 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.8496 Average/AverageReturn -51.9471 Average/Iteration 246 Average/MaxReturn -42.644 Average/MinReturn -70.591 Average/NumEpisodes 120 Average/StdReturn 4.87934 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81204 GaussianMLPPolicy/KLAfter 0.00139245 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.37056e-05 GaussianMLPPolicy/LossBefore 9.57648e-09 GaussianMLPPolicy/dLoss 6.37152e-05 Iteration 246 MetaTest/Average/AverageDiscountedReturn -51.8971 MetaTest/Average/AverageReturn -51.8971 MetaTest/Average/Iteration 246 MetaTest/Average/MaxReturn -45.6898 MetaTest/Average/MinReturn -61.1031 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.54753 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.8971 MetaTest/__unnamed_task__/AverageReturn -51.8971 MetaTest/__unnamed_task__/Iteration 246 MetaTest/__unnamed_task__/MaxReturn -45.6898 MetaTest/__unnamed_task__/MinReturn -61.1031 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.54753 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1856e+07 __unnamed_task__/AverageDiscountedReturn -28.8496 __unnamed_task__/AverageReturn -51.9471 __unnamed_task__/Iteration 246 __unnamed_task__/MaxReturn -42.644 __unnamed_task__/MinReturn -70.591 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.87934 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 13:25:51 | [maml_trainer] epoch #247 | Sampling for adapation and meta-testing... 2025-04-08 13:30:01 | [maml_trainer] epoch #247 | Finished meta-testing... 2025-04-08 13:30:01 | [maml_trainer] epoch #247 | Saving snapshot... 2025-04-08 13:30:25 | [maml_trainer] epoch #247 | Saved 2025-04-08 13:30:25 | [maml_trainer] epoch #247 | Time 420669.11 s 2025-04-08 13:30:25 | [maml_trainer] epoch #247 | EpochTime 1753.14 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.3966 Average/AverageReturn -51.0771 Average/Iteration 247 Average/MaxReturn -42.5162 Average/MinReturn -67.771 Average/NumEpisodes 120 Average/StdReturn 4.70585 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81331 GaussianMLPPolicy/KLAfter 0.00169087 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.37875e-05 GaussianMLPPolicy/LossBefore 3.53654e-09 GaussianMLPPolicy/dLoss 2.3791e-05 Iteration 247 MetaTest/Average/AverageDiscountedReturn -51.1159 MetaTest/Average/AverageReturn -51.1159 MetaTest/Average/Iteration 247 MetaTest/Average/MaxReturn -43.8615 MetaTest/Average/MinReturn -60.7264 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.02631 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.1159 MetaTest/__unnamed_task__/AverageReturn -51.1159 MetaTest/__unnamed_task__/Iteration 247 MetaTest/__unnamed_task__/MaxReturn -43.8615 MetaTest/__unnamed_task__/MinReturn -60.7264 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.02631 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1904e+07 __unnamed_task__/AverageDiscountedReturn -28.3966 __unnamed_task__/AverageReturn -51.0771 __unnamed_task__/Iteration 247 __unnamed_task__/MaxReturn -42.5162 __unnamed_task__/MinReturn -67.771 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.70585 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 13:54:47 | [maml_trainer] epoch #248 | Sampling for adapation and meta-testing... 2025-04-08 13:58:53 | [maml_trainer] epoch #248 | Finished meta-testing... 2025-04-08 13:58:53 | [maml_trainer] epoch #248 | Saving snapshot... 2025-04-08 13:59:17 | [maml_trainer] epoch #248 | Saved 2025-04-08 13:59:17 | [maml_trainer] epoch #248 | Time 422401.25 s 2025-04-08 13:59:17 | [maml_trainer] epoch #248 | EpochTime 1732.14 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.2892 Average/AverageReturn -50.7719 Average/Iteration 248 Average/MaxReturn -44.4334 Average/MinReturn -66.0031 Average/NumEpisodes 120 Average/StdReturn 4.52102 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81435 GaussianMLPPolicy/KLAfter 0.001917 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.64176e-05 GaussianMLPPolicy/LossBefore -4.17232e-09 GaussianMLPPolicy/dLoss -4.64217e-05 Iteration 248 MetaTest/Average/AverageDiscountedReturn -51.3849 MetaTest/Average/AverageReturn -51.3849 MetaTest/Average/Iteration 248 MetaTest/Average/MaxReturn -41.2253 MetaTest/Average/MinReturn -60.8753 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.00403 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.3849 MetaTest/__unnamed_task__/AverageReturn -51.3849 MetaTest/__unnamed_task__/Iteration 248 MetaTest/__unnamed_task__/MaxReturn -41.2253 MetaTest/__unnamed_task__/MinReturn -60.8753 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.00403 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.1952e+07 __unnamed_task__/AverageDiscountedReturn -28.2892 __unnamed_task__/AverageReturn -50.7719 __unnamed_task__/Iteration 248 __unnamed_task__/MaxReturn -44.4334 __unnamed_task__/MinReturn -66.0031 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.52102 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 14:24:14 | [maml_trainer] epoch #249 | Sampling for adapation and meta-testing... 2025-04-08 14:28:21 | [maml_trainer] epoch #249 | Finished meta-testing... 2025-04-08 14:28:21 | [maml_trainer] epoch #249 | Saving snapshot... 2025-04-08 14:28:44 | [maml_trainer] epoch #249 | Saved 2025-04-08 14:28:44 | [maml_trainer] epoch #249 | Time 424168.50 s 2025-04-08 14:28:44 | [maml_trainer] epoch #249 | EpochTime 1767.24 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.4008 Average/AverageReturn -51.3808 Average/Iteration 249 Average/MaxReturn -42.0878 Average/MinReturn -74.4523 Average/NumEpisodes 120 Average/StdReturn 5.21937 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81527 GaussianMLPPolicy/KLAfter 0.00274183 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.02061e-05 GaussianMLPPolicy/LossBefore -3.29812e-09 GaussianMLPPolicy/dLoss -6.02094e-05 Iteration 249 MetaTest/Average/AverageDiscountedReturn -50.9708 MetaTest/Average/AverageReturn -50.9708 MetaTest/Average/Iteration 249 MetaTest/Average/MaxReturn -43.8587 MetaTest/Average/MinReturn -64.4352 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.9183 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.9708 MetaTest/__unnamed_task__/AverageReturn -50.9708 MetaTest/__unnamed_task__/Iteration 249 MetaTest/__unnamed_task__/MaxReturn -43.8587 MetaTest/__unnamed_task__/MinReturn -64.4352 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.9183 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2e+07 __unnamed_task__/AverageDiscountedReturn -28.4008 __unnamed_task__/AverageReturn -51.3808 __unnamed_task__/Iteration 249 __unnamed_task__/MaxReturn -42.0878 __unnamed_task__/MinReturn -74.4523 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.21937 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 14:53:33 | [maml_trainer] epoch #250 | Sampling for adapation and meta-testing... 2025-04-08 14:57:41 | [maml_trainer] epoch #250 | Finished meta-testing... 2025-04-08 14:57:41 | [maml_trainer] epoch #250 | Saving snapshot... 2025-04-08 14:58:04 | [maml_trainer] epoch #250 | Saved 2025-04-08 14:58:04 | [maml_trainer] epoch #250 | Time 425928.62 s 2025-04-08 14:58:04 | [maml_trainer] epoch #250 | EpochTime 1760.12 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.6213 Average/AverageReturn -51.8056 Average/Iteration 250 Average/MaxReturn -42.6204 Average/MinReturn -69.1461 Average/NumEpisodes 120 Average/StdReturn 5.65102 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81622 GaussianMLPPolicy/KLAfter 0.000972581 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.49136e-05 GaussianMLPPolicy/LossBefore -1.0252e-08 GaussianMLPPolicy/dLoss 1.49033e-05 Iteration 250 MetaTest/Average/AverageDiscountedReturn -50.5035 MetaTest/Average/AverageReturn -50.5035 MetaTest/Average/Iteration 250 MetaTest/Average/MaxReturn -43.6657 MetaTest/Average/MinReturn -64.7145 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.37656 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5035 MetaTest/__unnamed_task__/AverageReturn -50.5035 MetaTest/__unnamed_task__/Iteration 250 MetaTest/__unnamed_task__/MaxReturn -43.6657 MetaTest/__unnamed_task__/MinReturn -64.7145 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.37656 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2048e+07 __unnamed_task__/AverageDiscountedReturn -28.6213 __unnamed_task__/AverageReturn -51.8056 __unnamed_task__/Iteration 250 __unnamed_task__/MaxReturn -42.6204 __unnamed_task__/MinReturn -69.1461 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.65102 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 15:22:58 | [maml_trainer] epoch #251 | Sampling for adapation and meta-testing... 2025-04-08 15:27:08 | [maml_trainer] epoch #251 | Finished meta-testing... 2025-04-08 15:27:08 | [maml_trainer] epoch #251 | Saving snapshot... 2025-04-08 15:27:32 | [maml_trainer] epoch #251 | Saved 2025-04-08 15:27:32 | [maml_trainer] epoch #251 | Time 427696.10 s 2025-04-08 15:27:32 | [maml_trainer] epoch #251 | EpochTime 1767.48 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.3626 Average/AverageReturn -51.3339 Average/Iteration 251 Average/MaxReturn -40.8979 Average/MinReturn -65.9368 Average/NumEpisodes 120 Average/StdReturn 4.42577 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81686 GaussianMLPPolicy/KLAfter 0.000680749 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.97689e-05 GaussianMLPPolicy/LossBefore -6.15915e-09 GaussianMLPPolicy/dLoss 7.97627e-05 Iteration 251 MetaTest/Average/AverageDiscountedReturn -51.7466 MetaTest/Average/AverageReturn -51.7466 MetaTest/Average/Iteration 251 MetaTest/Average/MaxReturn -42.3409 MetaTest/Average/MinReturn -68.7625 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.69011 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.7466 MetaTest/__unnamed_task__/AverageReturn -51.7466 MetaTest/__unnamed_task__/Iteration 251 MetaTest/__unnamed_task__/MaxReturn -42.3409 MetaTest/__unnamed_task__/MinReturn -68.7625 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.69011 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2096e+07 __unnamed_task__/AverageDiscountedReturn -28.3626 __unnamed_task__/AverageReturn -51.3339 __unnamed_task__/Iteration 251 __unnamed_task__/MaxReturn -40.8979 __unnamed_task__/MinReturn -65.9368 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.42577 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 15:51:30 | [maml_trainer] epoch #252 | Sampling for adapation and meta-testing... 2025-04-08 15:55:22 | [maml_trainer] epoch #252 | Finished meta-testing... 2025-04-08 15:55:22 | [maml_trainer] epoch #252 | Saving snapshot... 2025-04-08 15:55:44 | [maml_trainer] epoch #252 | Saved 2025-04-08 15:55:44 | [maml_trainer] epoch #252 | Time 429388.29 s 2025-04-08 15:55:44 | [maml_trainer] epoch #252 | EpochTime 1692.19 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.2482 Average/AverageReturn -50.9791 Average/Iteration 252 Average/MaxReturn -42.3311 Average/MinReturn -67.2909 Average/NumEpisodes 120 Average/StdReturn 5.00657 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81715 GaussianMLPPolicy/KLAfter 0.00144024 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.90339e-05 GaussianMLPPolicy/LossBefore -8.74202e-10 GaussianMLPPolicy/dLoss 3.9033e-05 Iteration 252 MetaTest/Average/AverageDiscountedReturn -52.2337 MetaTest/Average/AverageReturn -52.2337 MetaTest/Average/Iteration 252 MetaTest/Average/MaxReturn -43.4874 MetaTest/Average/MinReturn -65.9009 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.60654 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2337 MetaTest/__unnamed_task__/AverageReturn -52.2337 MetaTest/__unnamed_task__/Iteration 252 MetaTest/__unnamed_task__/MaxReturn -43.4874 MetaTest/__unnamed_task__/MinReturn -65.9009 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.60654 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2144e+07 __unnamed_task__/AverageDiscountedReturn -28.2482 __unnamed_task__/AverageReturn -50.9791 __unnamed_task__/Iteration 252 __unnamed_task__/MaxReturn -42.3311 __unnamed_task__/MinReturn -67.2909 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.00657 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 16:18:53 | [maml_trainer] epoch #253 | Sampling for adapation and meta-testing... 2025-04-08 16:22:48 | [maml_trainer] epoch #253 | Finished meta-testing... 2025-04-08 16:22:48 | [maml_trainer] epoch #253 | Saving snapshot... 2025-04-08 16:23:10 | [maml_trainer] epoch #253 | Saved 2025-04-08 16:23:10 | [maml_trainer] epoch #253 | Time 431034.44 s 2025-04-08 16:23:10 | [maml_trainer] epoch #253 | EpochTime 1646.15 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.1791 Average/AverageReturn -51.0506 Average/Iteration 253 Average/MaxReturn -40.1196 Average/MinReturn -71.9114 Average/NumEpisodes 120 Average/StdReturn 5.65183 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81644 GaussianMLPPolicy/KLAfter 0.00213596 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.24239e-05 GaussianMLPPolicy/LossBefore -4.21206e-09 GaussianMLPPolicy/dLoss -2.24282e-05 Iteration 253 MetaTest/Average/AverageDiscountedReturn -51.9997 MetaTest/Average/AverageReturn -51.9997 MetaTest/Average/Iteration 253 MetaTest/Average/MaxReturn -42.577 MetaTest/Average/MinReturn -64.6295 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.60955 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.9997 MetaTest/__unnamed_task__/AverageReturn -51.9997 MetaTest/__unnamed_task__/Iteration 253 MetaTest/__unnamed_task__/MaxReturn -42.577 MetaTest/__unnamed_task__/MinReturn -64.6295 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.60955 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2192e+07 __unnamed_task__/AverageDiscountedReturn -28.1791 __unnamed_task__/AverageReturn -51.0506 __unnamed_task__/Iteration 253 __unnamed_task__/MaxReturn -40.1196 __unnamed_task__/MinReturn -71.9114 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.65183 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 16:46:27 | [maml_trainer] epoch #254 | Sampling for adapation and meta-testing... 2025-04-08 16:50:21 | [maml_trainer] epoch #254 | Finished meta-testing... 2025-04-08 16:50:21 | [maml_trainer] epoch #254 | Saving snapshot... 2025-04-08 16:50:43 | [maml_trainer] epoch #254 | Saved 2025-04-08 16:50:43 | [maml_trainer] epoch #254 | Time 432687.65 s 2025-04-08 16:50:43 | [maml_trainer] epoch #254 | EpochTime 1653.21 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.0026 Average/AverageReturn -49.8377 Average/Iteration 254 Average/MaxReturn -40.3218 Average/MinReturn -63.0763 Average/NumEpisodes 120 Average/StdReturn 4.43879 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81587 GaussianMLPPolicy/KLAfter 0.00239185 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.75177e-05 GaussianMLPPolicy/LossBefore -4.64916e-09 GaussianMLPPolicy/dLoss -8.75223e-05 Iteration 254 MetaTest/Average/AverageDiscountedReturn -51.037 MetaTest/Average/AverageReturn -51.037 MetaTest/Average/Iteration 254 MetaTest/Average/MaxReturn -43.8149 MetaTest/Average/MinReturn -64.1023 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.07655 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.037 MetaTest/__unnamed_task__/AverageReturn -51.037 MetaTest/__unnamed_task__/Iteration 254 MetaTest/__unnamed_task__/MaxReturn -43.8149 MetaTest/__unnamed_task__/MinReturn -64.1023 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.07655 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.224e+07 __unnamed_task__/AverageDiscountedReturn -28.0026 __unnamed_task__/AverageReturn -49.8377 __unnamed_task__/Iteration 254 __unnamed_task__/MaxReturn -40.3218 __unnamed_task__/MinReturn -63.0763 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.43879 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 17:14:06 | [maml_trainer] epoch #255 | Sampling for adapation and meta-testing... 2025-04-08 17:18:00 | [maml_trainer] epoch #255 | Finished meta-testing... 2025-04-08 17:18:00 | [maml_trainer] epoch #255 | Saving snapshot... 2025-04-08 17:18:22 | [maml_trainer] epoch #255 | Saved 2025-04-08 17:18:22 | [maml_trainer] epoch #255 | Time 434346.65 s 2025-04-08 17:18:22 | [maml_trainer] epoch #255 | EpochTime 1659.00 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.2086 Average/AverageReturn -50.9134 Average/Iteration 255 Average/MaxReturn -40.158 Average/MinReturn -66.3933 Average/NumEpisodes 120 Average/StdReturn 4.88822 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81489 GaussianMLPPolicy/KLAfter 0.00383516 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.66121e-05 GaussianMLPPolicy/LossBefore -1.75238e-08 GaussianMLPPolicy/dLoss -3.66296e-05 Iteration 255 MetaTest/Average/AverageDiscountedReturn -50.3645 MetaTest/Average/AverageReturn -50.3645 MetaTest/Average/Iteration 255 MetaTest/Average/MaxReturn -42.6142 MetaTest/Average/MinReturn -68.0418 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.34433 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.3645 MetaTest/__unnamed_task__/AverageReturn -50.3645 MetaTest/__unnamed_task__/Iteration 255 MetaTest/__unnamed_task__/MaxReturn -42.6142 MetaTest/__unnamed_task__/MinReturn -68.0418 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.34433 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2288e+07 __unnamed_task__/AverageDiscountedReturn -28.2086 __unnamed_task__/AverageReturn -50.9134 __unnamed_task__/Iteration 255 __unnamed_task__/MaxReturn -40.158 __unnamed_task__/MinReturn -66.3933 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.88822 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 17:41:40 | [maml_trainer] epoch #256 | Sampling for adapation and meta-testing... 2025-04-08 17:45:33 | [maml_trainer] epoch #256 | Finished meta-testing... 2025-04-08 17:45:33 | [maml_trainer] epoch #256 | Saving snapshot... 2025-04-08 17:45:55 | [maml_trainer] epoch #256 | Saved 2025-04-08 17:45:55 | [maml_trainer] epoch #256 | Time 435998.98 s 2025-04-08 17:45:55 | [maml_trainer] epoch #256 | EpochTime 1652.32 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.285 Average/AverageReturn -50.8003 Average/Iteration 256 Average/MaxReturn -39.7366 Average/MinReturn -67.6818 Average/NumEpisodes 120 Average/StdReturn 5.52824 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81488 GaussianMLPPolicy/KLAfter 0.00335379 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.50828e-05 GaussianMLPPolicy/LossBefore -1.05699e-08 GaussianMLPPolicy/dLoss 6.50723e-05 Iteration 256 MetaTest/Average/AverageDiscountedReturn -51.6202 MetaTest/Average/AverageReturn -51.6202 MetaTest/Average/Iteration 256 MetaTest/Average/MaxReturn -44.2387 MetaTest/Average/MinReturn -70.7647 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.09588 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6202 MetaTest/__unnamed_task__/AverageReturn -51.6202 MetaTest/__unnamed_task__/Iteration 256 MetaTest/__unnamed_task__/MaxReturn -44.2387 MetaTest/__unnamed_task__/MinReturn -70.7647 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.09588 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2336e+07 __unnamed_task__/AverageDiscountedReturn -28.285 __unnamed_task__/AverageReturn -50.8003 __unnamed_task__/Iteration 256 __unnamed_task__/MaxReturn -39.7366 __unnamed_task__/MinReturn -67.6818 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.52824 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 18:09:04 | [maml_trainer] epoch #257 | Sampling for adapation and meta-testing... 2025-04-08 18:12:55 | [maml_trainer] epoch #257 | Finished meta-testing... 2025-04-08 18:12:55 | [maml_trainer] epoch #257 | Saving snapshot... 2025-04-08 18:13:17 | [maml_trainer] epoch #257 | Saved 2025-04-08 18:13:17 | [maml_trainer] epoch #257 | Time 437641.38 s 2025-04-08 18:13:17 | [maml_trainer] epoch #257 | EpochTime 1642.40 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.1218 Average/AverageReturn -50.2638 Average/Iteration 257 Average/MaxReturn -40.3363 Average/MinReturn -64.8603 Average/NumEpisodes 120 Average/StdReturn 4.62723 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81479 GaussianMLPPolicy/KLAfter 0.00318882 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000135177 GaussianMLPPolicy/LossBefore -7.39098e-09 GaussianMLPPolicy/dLoss 0.00013517 Iteration 257 MetaTest/Average/AverageDiscountedReturn -51.4133 MetaTest/Average/AverageReturn -51.4133 MetaTest/Average/Iteration 257 MetaTest/Average/MaxReturn -42.9964 MetaTest/Average/MinReturn -62.1273 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.12732 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.4133 MetaTest/__unnamed_task__/AverageReturn -51.4133 MetaTest/__unnamed_task__/Iteration 257 MetaTest/__unnamed_task__/MaxReturn -42.9964 MetaTest/__unnamed_task__/MinReturn -62.1273 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.12732 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2384e+07 __unnamed_task__/AverageDiscountedReturn -28.1218 __unnamed_task__/AverageReturn -50.2638 __unnamed_task__/Iteration 257 __unnamed_task__/MaxReturn -40.3363 __unnamed_task__/MinReturn -64.8603 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.62723 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 18:36:30 | [maml_trainer] epoch #258 | Sampling for adapation and meta-testing... 2025-04-08 18:40:18 | [maml_trainer] epoch #258 | Finished meta-testing... 2025-04-08 18:40:18 | [maml_trainer] epoch #258 | Saving snapshot... 2025-04-08 18:40:39 | [maml_trainer] epoch #258 | Saved 2025-04-08 18:40:39 | [maml_trainer] epoch #258 | Time 439283.75 s 2025-04-08 18:40:39 | [maml_trainer] epoch #258 | EpochTime 1642.36 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.3657 Average/AverageReturn -50.6694 Average/Iteration 258 Average/MaxReturn -40.0581 Average/MinReturn -67.4942 Average/NumEpisodes 120 Average/StdReturn 4.88521 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81517 GaussianMLPPolicy/KLAfter 0.00363227 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.3953e-05 GaussianMLPPolicy/LossBefore 6.35783e-10 GaussianMLPPolicy/dLoss 3.39536e-05 Iteration 258 MetaTest/Average/AverageDiscountedReturn -51.6575 MetaTest/Average/AverageReturn -51.6575 MetaTest/Average/Iteration 258 MetaTest/Average/MaxReturn -45.3498 MetaTest/Average/MinReturn -67.2337 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.0089 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6575 MetaTest/__unnamed_task__/AverageReturn -51.6575 MetaTest/__unnamed_task__/Iteration 258 MetaTest/__unnamed_task__/MaxReturn -45.3498 MetaTest/__unnamed_task__/MinReturn -67.2337 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.0089 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2432e+07 __unnamed_task__/AverageDiscountedReturn -28.3657 __unnamed_task__/AverageReturn -50.6694 __unnamed_task__/Iteration 258 __unnamed_task__/MaxReturn -40.0581 __unnamed_task__/MinReturn -67.4942 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.88521 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 19:03:31 | [maml_trainer] epoch #259 | Sampling for adapation and meta-testing... 2025-04-08 19:07:27 | [maml_trainer] epoch #259 | Finished meta-testing... 2025-04-08 19:07:27 | [maml_trainer] epoch #259 | Saving snapshot... 2025-04-08 19:07:49 | [maml_trainer] epoch #259 | Saved 2025-04-08 19:07:49 | [maml_trainer] epoch #259 | Time 440913.83 s 2025-04-08 19:07:49 | [maml_trainer] epoch #259 | EpochTime 1630.08 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.2566 Average/AverageReturn -49.8135 Average/Iteration 259 Average/MaxReturn -41.822 Average/MinReturn -64.2976 Average/NumEpisodes 120 Average/StdReturn 4.27646 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81488 GaussianMLPPolicy/KLAfter 0.00406883 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.75102e-05 GaussianMLPPolicy/LossBefore -5.44389e-09 GaussianMLPPolicy/dLoss 3.75048e-05 Iteration 259 MetaTest/Average/AverageDiscountedReturn -49.5193 MetaTest/Average/AverageReturn -49.5193 MetaTest/Average/Iteration 259 MetaTest/Average/MaxReturn -43.1162 MetaTest/Average/MinReturn -56.9616 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.75225 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5193 MetaTest/__unnamed_task__/AverageReturn -49.5193 MetaTest/__unnamed_task__/Iteration 259 MetaTest/__unnamed_task__/MaxReturn -43.1162 MetaTest/__unnamed_task__/MinReturn -56.9616 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.75225 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.248e+07 __unnamed_task__/AverageDiscountedReturn -28.2566 __unnamed_task__/AverageReturn -49.8135 __unnamed_task__/Iteration 259 __unnamed_task__/MaxReturn -41.822 __unnamed_task__/MinReturn -64.2976 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.27646 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 19:31:06 | [maml_trainer] epoch #260 | Sampling for adapation and meta-testing... 2025-04-08 19:34:56 | [maml_trainer] epoch #260 | Finished meta-testing... 2025-04-08 19:34:56 | [maml_trainer] epoch #260 | Saving snapshot... 2025-04-08 19:35:18 | [maml_trainer] epoch #260 | Saved 2025-04-08 19:35:18 | [maml_trainer] epoch #260 | Time 442562.63 s 2025-04-08 19:35:18 | [maml_trainer] epoch #260 | EpochTime 1648.80 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.3168 Average/AverageReturn -50.3246 Average/Iteration 260 Average/MaxReturn -42.7115 Average/MinReturn -62.9219 Average/NumEpisodes 120 Average/StdReturn 4.42751 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81442 GaussianMLPPolicy/KLAfter 0.00546237 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.08459e-05 GaussianMLPPolicy/LossBefore -6.27836e-09 GaussianMLPPolicy/dLoss -8.08522e-05 Iteration 260 MetaTest/Average/AverageDiscountedReturn -49.9169 MetaTest/Average/AverageReturn -49.9169 MetaTest/Average/Iteration 260 MetaTest/Average/MaxReturn -42.0238 MetaTest/Average/MinReturn -61.4052 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.31004 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.9169 MetaTest/__unnamed_task__/AverageReturn -49.9169 MetaTest/__unnamed_task__/Iteration 260 MetaTest/__unnamed_task__/MaxReturn -42.0238 MetaTest/__unnamed_task__/MinReturn -61.4052 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.31004 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2528e+07 __unnamed_task__/AverageDiscountedReturn -28.3168 __unnamed_task__/AverageReturn -50.3246 __unnamed_task__/Iteration 260 __unnamed_task__/MaxReturn -42.7115 __unnamed_task__/MinReturn -62.9219 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.42751 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 19:58:15 | [maml_trainer] epoch #261 | Sampling for adapation and meta-testing... 2025-04-08 20:02:28 | [maml_trainer] epoch #261 | Finished meta-testing... 2025-04-08 20:02:28 | [maml_trainer] epoch #261 | Saving snapshot... 2025-04-08 20:02:50 | [maml_trainer] epoch #261 | Saved 2025-04-08 20:02:50 | [maml_trainer] epoch #261 | Time 444214.02 s 2025-04-08 20:02:50 | [maml_trainer] epoch #261 | EpochTime 1651.38 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.5295 Average/AverageReturn -50.6051 Average/Iteration 261 Average/MaxReturn -42.2108 Average/MinReturn -67.4751 Average/NumEpisodes 120 Average/StdReturn 5.19148 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81442 GaussianMLPPolicy/KLAfter 0.00561886 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000115875 GaussianMLPPolicy/LossBefore 4.05312e-09 GaussianMLPPolicy/dLoss -0.000115871 Iteration 261 MetaTest/Average/AverageDiscountedReturn -50.4645 MetaTest/Average/AverageReturn -50.4645 MetaTest/Average/Iteration 261 MetaTest/Average/MaxReturn -41.8569 MetaTest/Average/MinReturn -63.9215 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.35423 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.4645 MetaTest/__unnamed_task__/AverageReturn -50.4645 MetaTest/__unnamed_task__/Iteration 261 MetaTest/__unnamed_task__/MaxReturn -41.8569 MetaTest/__unnamed_task__/MinReturn -63.9215 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.35423 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2576e+07 __unnamed_task__/AverageDiscountedReturn -28.5295 __unnamed_task__/AverageReturn -50.6051 __unnamed_task__/Iteration 261 __unnamed_task__/MaxReturn -42.2108 __unnamed_task__/MinReturn -67.4751 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.19148 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 20:26:22 | [maml_trainer] epoch #262 | Sampling for adapation and meta-testing... 2025-04-08 20:30:15 | [maml_trainer] epoch #262 | Finished meta-testing... 2025-04-08 20:30:15 | [maml_trainer] epoch #262 | Saving snapshot... 2025-04-08 20:30:37 | [maml_trainer] epoch #262 | Saved 2025-04-08 20:30:37 | [maml_trainer] epoch #262 | Time 445881.20 s 2025-04-08 20:30:37 | [maml_trainer] epoch #262 | EpochTime 1667.18 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.6233 Average/AverageReturn -50.6235 Average/Iteration 262 Average/MaxReturn -41.2696 Average/MinReturn -66.6731 Average/NumEpisodes 120 Average/StdReturn 4.69136 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.8137 GaussianMLPPolicy/KLAfter 0.00399682 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000133093 GaussianMLPPolicy/LossBefore 1.3113e-09 GaussianMLPPolicy/dLoss 0.000133095 Iteration 262 MetaTest/Average/AverageDiscountedReturn -50.0577 MetaTest/Average/AverageReturn -50.0577 MetaTest/Average/Iteration 262 MetaTest/Average/MaxReturn -42.8142 MetaTest/Average/MinReturn -58.2205 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.17255 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0577 MetaTest/__unnamed_task__/AverageReturn -50.0577 MetaTest/__unnamed_task__/Iteration 262 MetaTest/__unnamed_task__/MaxReturn -42.8142 MetaTest/__unnamed_task__/MinReturn -58.2205 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.17255 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2624e+07 __unnamed_task__/AverageDiscountedReturn -28.6233 __unnamed_task__/AverageReturn -50.6235 __unnamed_task__/Iteration 262 __unnamed_task__/MaxReturn -41.2696 __unnamed_task__/MinReturn -66.6731 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.69136 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 20:53:25 | [maml_trainer] epoch #263 | Sampling for adapation and meta-testing... 2025-04-08 20:57:18 | [maml_trainer] epoch #263 | Finished meta-testing... 2025-04-08 20:57:18 | [maml_trainer] epoch #263 | Saving snapshot... 2025-04-08 20:57:40 | [maml_trainer] epoch #263 | Saved 2025-04-08 20:57:40 | [maml_trainer] epoch #263 | Time 447504.91 s 2025-04-08 20:57:40 | [maml_trainer] epoch #263 | EpochTime 1623.70 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.9747 Average/AverageReturn -50.955 Average/Iteration 263 Average/MaxReturn -43.0239 Average/MinReturn -63.9216 Average/NumEpisodes 120 Average/StdReturn 4.16828 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81297 GaussianMLPPolicy/KLAfter 0.00191469 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.17538e-05 GaussianMLPPolicy/LossBefore -2.10603e-09 GaussianMLPPolicy/dLoss 2.17517e-05 Iteration 263 MetaTest/Average/AverageDiscountedReturn -51.5658 MetaTest/Average/AverageReturn -51.5658 MetaTest/Average/Iteration 263 MetaTest/Average/MaxReturn -44.5571 MetaTest/Average/MinReturn -65.2779 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.17703 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.5658 MetaTest/__unnamed_task__/AverageReturn -51.5658 MetaTest/__unnamed_task__/Iteration 263 MetaTest/__unnamed_task__/MaxReturn -44.5571 MetaTest/__unnamed_task__/MinReturn -65.2779 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.17703 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2672e+07 __unnamed_task__/AverageDiscountedReturn -28.9747 __unnamed_task__/AverageReturn -50.955 __unnamed_task__/Iteration 263 __unnamed_task__/MaxReturn -43.0239 __unnamed_task__/MinReturn -63.9216 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.16828 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 21:20:33 | [maml_trainer] epoch #264 | Sampling for adapation and meta-testing... 2025-04-08 21:24:21 | [maml_trainer] epoch #264 | Finished meta-testing... 2025-04-08 21:24:21 | [maml_trainer] epoch #264 | Saving snapshot... 2025-04-08 21:24:43 | [maml_trainer] epoch #264 | Saved 2025-04-08 21:24:43 | [maml_trainer] epoch #264 | Time 449127.26 s 2025-04-08 21:24:43 | [maml_trainer] epoch #264 | EpochTime 1622.35 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.5979 Average/AverageReturn -50.1359 Average/Iteration 264 Average/MaxReturn -42.5487 Average/MinReturn -68.4266 Average/NumEpisodes 120 Average/StdReturn 4.70996 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81281 GaussianMLPPolicy/KLAfter 0.00122223 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.53975e-05 GaussianMLPPolicy/LossBefore -2.86102e-09 GaussianMLPPolicy/dLoss -4.54003e-05 Iteration 264 MetaTest/Average/AverageDiscountedReturn -47.8891 MetaTest/Average/AverageReturn -47.8891 MetaTest/Average/Iteration 264 MetaTest/Average/MaxReturn -40.8007 MetaTest/Average/MinReturn -55.9981 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.15222 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.8891 MetaTest/__unnamed_task__/AverageReturn -47.8891 MetaTest/__unnamed_task__/Iteration 264 MetaTest/__unnamed_task__/MaxReturn -40.8007 MetaTest/__unnamed_task__/MinReturn -55.9981 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.15222 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.272e+07 __unnamed_task__/AverageDiscountedReturn -28.5979 __unnamed_task__/AverageReturn -50.1359 __unnamed_task__/Iteration 264 __unnamed_task__/MaxReturn -42.5487 __unnamed_task__/MinReturn -68.4266 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.70996 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 21:47:45 | [maml_trainer] epoch #265 | Sampling for adapation and meta-testing... 2025-04-08 21:51:39 | [maml_trainer] epoch #265 | Finished meta-testing... 2025-04-08 21:51:39 | [maml_trainer] epoch #265 | Saving snapshot... 2025-04-08 21:52:01 | [maml_trainer] epoch #265 | Saved 2025-04-08 21:52:01 | [maml_trainer] epoch #265 | Time 450765.21 s 2025-04-08 21:52:01 | [maml_trainer] epoch #265 | EpochTime 1637.94 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.7174 Average/AverageReturn -50.3977 Average/Iteration 265 Average/MaxReturn -41.5667 Average/MinReturn -69.3327 Average/NumEpisodes 120 Average/StdReturn 4.60206 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81243 GaussianMLPPolicy/KLAfter 0.00170024 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.59944e-05 GaussianMLPPolicy/LossBefore -1.89145e-08 GaussianMLPPolicy/dLoss 5.59755e-05 Iteration 265 MetaTest/Average/AverageDiscountedReturn -48.1581 MetaTest/Average/AverageReturn -48.1581 MetaTest/Average/Iteration 265 MetaTest/Average/MaxReturn -42.1243 MetaTest/Average/MinReturn -73.304 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.48338 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1581 MetaTest/__unnamed_task__/AverageReturn -48.1581 MetaTest/__unnamed_task__/Iteration 265 MetaTest/__unnamed_task__/MaxReturn -42.1243 MetaTest/__unnamed_task__/MinReturn -73.304 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.48338 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2768e+07 __unnamed_task__/AverageDiscountedReturn -28.7174 __unnamed_task__/AverageReturn -50.3977 __unnamed_task__/Iteration 265 __unnamed_task__/MaxReturn -41.5667 __unnamed_task__/MinReturn -69.3327 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.60206 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 22:15:02 | [maml_trainer] epoch #266 | Sampling for adapation and meta-testing... 2025-04-08 22:18:59 | [maml_trainer] epoch #266 | Finished meta-testing... 2025-04-08 22:18:59 | [maml_trainer] epoch #266 | Saving snapshot... 2025-04-08 22:19:21 | [maml_trainer] epoch #266 | Saved 2025-04-08 22:19:21 | [maml_trainer] epoch #266 | Time 452405.35 s 2025-04-08 22:19:21 | [maml_trainer] epoch #266 | EpochTime 1640.13 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.4518 Average/AverageReturn -50.0153 Average/Iteration 266 Average/MaxReturn -39.3597 Average/MinReturn -71.7083 Average/NumEpisodes 120 Average/StdReturn 5.83994 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81314 GaussianMLPPolicy/KLAfter 0.000977382 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.22264e-05 GaussianMLPPolicy/LossBefore -2.82129e-09 GaussianMLPPolicy/dLoss -3.22292e-05 Iteration 266 MetaTest/Average/AverageDiscountedReturn -50.0735 MetaTest/Average/AverageReturn -50.0735 MetaTest/Average/Iteration 266 MetaTest/Average/MaxReturn -41.5898 MetaTest/Average/MinReturn -61.9289 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.15052 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0735 MetaTest/__unnamed_task__/AverageReturn -50.0735 MetaTest/__unnamed_task__/Iteration 266 MetaTest/__unnamed_task__/MaxReturn -41.5898 MetaTest/__unnamed_task__/MinReturn -61.9289 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.15052 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2816e+07 __unnamed_task__/AverageDiscountedReturn -28.4518 __unnamed_task__/AverageReturn -50.0153 __unnamed_task__/Iteration 266 __unnamed_task__/MaxReturn -39.3597 __unnamed_task__/MinReturn -71.7083 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.83994 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 22:42:47 | [maml_trainer] epoch #267 | Sampling for adapation and meta-testing... 2025-04-08 22:46:35 | [maml_trainer] epoch #267 | Finished meta-testing... 2025-04-08 22:46:35 | [maml_trainer] epoch #267 | Saving snapshot... 2025-04-08 22:46:57 | [maml_trainer] epoch #267 | Saved 2025-04-08 22:46:57 | [maml_trainer] epoch #267 | Time 454061.26 s 2025-04-08 22:46:57 | [maml_trainer] epoch #267 | EpochTime 1655.91 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.9627 Average/AverageReturn -50.6296 Average/Iteration 267 Average/MaxReturn -43.4026 Average/MinReturn -72.7114 Average/NumEpisodes 120 Average/StdReturn 5.05788 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81473 GaussianMLPPolicy/KLAfter 0.00255857 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.94301e-06 GaussianMLPPolicy/LossBefore 1.35104e-09 GaussianMLPPolicy/dLoss 3.94436e-06 Iteration 267 MetaTest/Average/AverageDiscountedReturn -51.7591 MetaTest/Average/AverageReturn -51.7591 MetaTest/Average/Iteration 267 MetaTest/Average/MaxReturn -45.287 MetaTest/Average/MinReturn -67.4758 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.02884 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.7591 MetaTest/__unnamed_task__/AverageReturn -51.7591 MetaTest/__unnamed_task__/Iteration 267 MetaTest/__unnamed_task__/MaxReturn -45.287 MetaTest/__unnamed_task__/MinReturn -67.4758 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.02884 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2864e+07 __unnamed_task__/AverageDiscountedReturn -28.9627 __unnamed_task__/AverageReturn -50.6296 __unnamed_task__/Iteration 267 __unnamed_task__/MaxReturn -43.4026 __unnamed_task__/MinReturn -72.7114 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.05788 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 23:09:46 | [maml_trainer] epoch #268 | Sampling for adapation and meta-testing... 2025-04-08 23:13:36 | [maml_trainer] epoch #268 | Finished meta-testing... 2025-04-08 23:13:36 | [maml_trainer] epoch #268 | Saving snapshot... 2025-04-08 23:13:58 | [maml_trainer] epoch #268 | Saved 2025-04-08 23:13:58 | [maml_trainer] epoch #268 | Time 455682.31 s 2025-04-08 23:13:58 | [maml_trainer] epoch #268 | EpochTime 1621.04 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.7266 Average/AverageReturn -50.4016 Average/Iteration 268 Average/MaxReturn -41.8801 Average/MinReturn -73.5191 Average/NumEpisodes 120 Average/StdReturn 5.52221 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81628 GaussianMLPPolicy/KLAfter 0.0025366 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.46283e-05 GaussianMLPPolicy/LossBefore -1.8239e-08 GaussianMLPPolicy/dLoss 2.46101e-05 Iteration 268 MetaTest/Average/AverageDiscountedReturn -49.7121 MetaTest/Average/AverageReturn -49.7121 MetaTest/Average/Iteration 268 MetaTest/Average/MaxReturn -44.1861 MetaTest/Average/MinReturn -70.9612 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.02533 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.7121 MetaTest/__unnamed_task__/AverageReturn -49.7121 MetaTest/__unnamed_task__/Iteration 268 MetaTest/__unnamed_task__/MaxReturn -44.1861 MetaTest/__unnamed_task__/MinReturn -70.9612 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.02533 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.2912e+07 __unnamed_task__/AverageDiscountedReturn -28.7266 __unnamed_task__/AverageReturn -50.4016 __unnamed_task__/Iteration 268 __unnamed_task__/MaxReturn -41.8801 __unnamed_task__/MinReturn -73.5191 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.52221 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-08 23:37:13 | [maml_trainer] epoch #269 | Sampling for adapation and meta-testing... 2025-04-08 23:41:11 | [maml_trainer] epoch #269 | Finished meta-testing... 2025-04-08 23:41:11 | [maml_trainer] epoch #269 | Saving snapshot... 2025-04-08 23:41:34 | [maml_trainer] epoch #269 | Saved 2025-04-08 23:41:34 | [maml_trainer] epoch #269 | Time 457338.64 s 2025-04-08 23:41:34 | [maml_trainer] epoch #269 | EpochTime 1656.32 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.5478 Average/AverageReturn -50.1196 Average/Iteration 269 Average/MaxReturn -37.5275 Average/MinReturn -100.751 Average/NumEpisodes 120 Average/StdReturn 6.78303 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81831 GaussianMLPPolicy/KLAfter 0.00267246 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.82946e-05 GaussianMLPPolicy/LossBefore 6.75519e-09 GaussianMLPPolicy/dLoss 6.83014e-05 Iteration 269 MetaTest/Average/AverageDiscountedReturn -51.6289 MetaTest/Average/AverageReturn -51.6289 MetaTest/Average/Iteration 269 MetaTest/Average/MaxReturn -42.5531 MetaTest/Average/MinReturn -71.4088 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.19751 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6289 MetaTest/__unnamed_task__/AverageReturn -51.6289 MetaTest/__unnamed_task__/Iteration 269 MetaTest/__unnamed_task__/MaxReturn -42.5531 MetaTest/__unnamed_task__/MinReturn -71.4088 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.19751 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.296e+07 __unnamed_task__/AverageDiscountedReturn -28.5478 __unnamed_task__/AverageReturn -50.1196 __unnamed_task__/Iteration 269 __unnamed_task__/MaxReturn -37.5275 __unnamed_task__/MinReturn -100.751 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.78303 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 00:06:06 | [maml_trainer] epoch #270 | Sampling for adapation and meta-testing... 2025-04-09 00:10:20 | [maml_trainer] epoch #270 | Finished meta-testing... 2025-04-09 00:10:20 | [maml_trainer] epoch #270 | Saving snapshot... 2025-04-09 00:10:45 | [maml_trainer] epoch #270 | Saved 2025-04-09 00:10:45 | [maml_trainer] epoch #270 | Time 459089.19 s 2025-04-09 00:10:45 | [maml_trainer] epoch #270 | EpochTime 1750.55 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.2185 Average/AverageReturn -49.2743 Average/Iteration 270 Average/MaxReturn -40.6208 Average/MinReturn -64.9349 Average/NumEpisodes 120 Average/StdReturn 4.54364 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.82019 GaussianMLPPolicy/KLAfter 0.00277032 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.36063e-05 GaussianMLPPolicy/LossBefore -1.13646e-08 GaussianMLPPolicy/dLoss -1.36177e-05 Iteration 270 MetaTest/Average/AverageDiscountedReturn -54.4593 MetaTest/Average/AverageReturn -54.4593 MetaTest/Average/Iteration 270 MetaTest/Average/MaxReturn -41.7308 MetaTest/Average/MinReturn -98.8439 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.7289 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.4593 MetaTest/__unnamed_task__/AverageReturn -54.4593 MetaTest/__unnamed_task__/Iteration 270 MetaTest/__unnamed_task__/MaxReturn -41.7308 MetaTest/__unnamed_task__/MinReturn -98.8439 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.7289 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3008e+07 __unnamed_task__/AverageDiscountedReturn -28.2185 __unnamed_task__/AverageReturn -49.2743 __unnamed_task__/Iteration 270 __unnamed_task__/MaxReturn -40.6208 __unnamed_task__/MinReturn -64.9349 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.54364 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 00:34:29 | [maml_trainer] epoch #271 | Sampling for adapation and meta-testing... 2025-04-09 00:38:31 | [maml_trainer] epoch #271 | Finished meta-testing... 2025-04-09 00:38:31 | [maml_trainer] epoch #271 | Saving snapshot... 2025-04-09 00:38:54 | [maml_trainer] epoch #271 | Saved 2025-04-09 00:38:54 | [maml_trainer] epoch #271 | Time 460778.44 s 2025-04-09 00:38:54 | [maml_trainer] epoch #271 | EpochTime 1689.25 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.0938 Average/AverageReturn -49.407 Average/Iteration 271 Average/MaxReturn -39.8487 Average/MinReturn -81.4531 Average/NumEpisodes 120 Average/StdReturn 5.37421 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.82306 GaussianMLPPolicy/KLAfter 0.00299575 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.51523e-05 GaussianMLPPolicy/LossBefore 4.88758e-09 GaussianMLPPolicy/dLoss -8.51474e-05 Iteration 271 MetaTest/Average/AverageDiscountedReturn -51.2202 MetaTest/Average/AverageReturn -51.2202 MetaTest/Average/Iteration 271 MetaTest/Average/MaxReturn -41.3839 MetaTest/Average/MinReturn -76.1015 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.68051 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2202 MetaTest/__unnamed_task__/AverageReturn -51.2202 MetaTest/__unnamed_task__/Iteration 271 MetaTest/__unnamed_task__/MaxReturn -41.3839 MetaTest/__unnamed_task__/MinReturn -76.1015 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.68051 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3056e+07 __unnamed_task__/AverageDiscountedReturn -28.0938 __unnamed_task__/AverageReturn -49.407 __unnamed_task__/Iteration 271 __unnamed_task__/MaxReturn -39.8487 __unnamed_task__/MinReturn -81.4531 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.37421 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 01:03:34 | [maml_trainer] epoch #272 | Sampling for adapation and meta-testing... 2025-04-09 01:07:41 | [maml_trainer] epoch #272 | Finished meta-testing... 2025-04-09 01:07:41 | [maml_trainer] epoch #272 | Saving snapshot... 2025-04-09 01:08:05 | [maml_trainer] epoch #272 | Saved 2025-04-09 01:08:05 | [maml_trainer] epoch #272 | Time 462529.81 s 2025-04-09 01:08:05 | [maml_trainer] epoch #272 | EpochTime 1751.36 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.4613 Average/AverageReturn -50.4857 Average/Iteration 272 Average/MaxReturn -40.6689 Average/MinReturn -114.347 Average/NumEpisodes 120 Average/StdReturn 8.57467 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.82628 GaussianMLPPolicy/KLAfter 0.00256264 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.30399e-05 GaussianMLPPolicy/LossBefore -8.0665e-09 GaussianMLPPolicy/dLoss -5.3048e-05 Iteration 272 MetaTest/Average/AverageDiscountedReturn -48.8007 MetaTest/Average/AverageReturn -48.8007 MetaTest/Average/Iteration 272 MetaTest/Average/MaxReturn -39.7879 MetaTest/Average/MinReturn -63.2806 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.28178 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.8007 MetaTest/__unnamed_task__/AverageReturn -48.8007 MetaTest/__unnamed_task__/Iteration 272 MetaTest/__unnamed_task__/MaxReturn -39.7879 MetaTest/__unnamed_task__/MinReturn -63.2806 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.28178 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3104e+07 __unnamed_task__/AverageDiscountedReturn -28.4613 __unnamed_task__/AverageReturn -50.4857 __unnamed_task__/Iteration 272 __unnamed_task__/MaxReturn -40.6689 __unnamed_task__/MinReturn -114.347 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.57467 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 01:32:35 | [maml_trainer] epoch #273 | Sampling for adapation and meta-testing... 2025-04-09 01:36:38 | [maml_trainer] epoch #273 | Finished meta-testing... 2025-04-09 01:36:38 | [maml_trainer] epoch #273 | Saving snapshot... 2025-04-09 01:37:02 | [maml_trainer] epoch #273 | Saved 2025-04-09 01:37:02 | [maml_trainer] epoch #273 | Time 464266.33 s 2025-04-09 01:37:02 | [maml_trainer] epoch #273 | EpochTime 1736.52 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.2669 Average/AverageReturn -49.642 Average/Iteration 273 Average/MaxReturn -40.6593 Average/MinReturn -67.3233 Average/NumEpisodes 120 Average/StdReturn 4.92566 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.82942 GaussianMLPPolicy/KLAfter 0.00292418 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.77065e-05 GaussianMLPPolicy/LossBefore -1.06494e-08 GaussianMLPPolicy/dLoss 1.76959e-05 Iteration 273 MetaTest/Average/AverageDiscountedReturn -47.4458 MetaTest/Average/AverageReturn -47.4458 MetaTest/Average/Iteration 273 MetaTest/Average/MaxReturn -41.3833 MetaTest/Average/MinReturn -56.0826 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.13223 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4458 MetaTest/__unnamed_task__/AverageReturn -47.4458 MetaTest/__unnamed_task__/Iteration 273 MetaTest/__unnamed_task__/MaxReturn -41.3833 MetaTest/__unnamed_task__/MinReturn -56.0826 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.13223 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3152e+07 __unnamed_task__/AverageDiscountedReturn -28.2669 __unnamed_task__/AverageReturn -49.642 __unnamed_task__/Iteration 273 __unnamed_task__/MaxReturn -40.6593 __unnamed_task__/MinReturn -67.3233 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.92566 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 02:01:46 | [maml_trainer] epoch #274 | Sampling for adapation and meta-testing... 2025-04-09 02:05:53 | [maml_trainer] epoch #274 | Finished meta-testing... 2025-04-09 02:05:53 | [maml_trainer] epoch #274 | Saving snapshot... 2025-04-09 02:06:17 | [maml_trainer] epoch #274 | Saved 2025-04-09 02:06:17 | [maml_trainer] epoch #274 | Time 466020.99 s 2025-04-09 02:06:17 | [maml_trainer] epoch #274 | EpochTime 1754.66 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.9853 Average/AverageReturn -49.4955 Average/Iteration 274 Average/MaxReturn -39.0308 Average/MinReturn -76.9814 Average/NumEpisodes 120 Average/StdReturn 6.02259 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.83177 GaussianMLPPolicy/KLAfter 0.0019978 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.44412e-05 GaussianMLPPolicy/LossBefore 3.77496e-09 GaussianMLPPolicy/dLoss 5.4445e-05 Iteration 274 MetaTest/Average/AverageDiscountedReturn -49.8404 MetaTest/Average/AverageReturn -49.8404 MetaTest/Average/Iteration 274 MetaTest/Average/MaxReturn -41.9535 MetaTest/Average/MinReturn -67.8896 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.4591 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8404 MetaTest/__unnamed_task__/AverageReturn -49.8404 MetaTest/__unnamed_task__/Iteration 274 MetaTest/__unnamed_task__/MaxReturn -41.9535 MetaTest/__unnamed_task__/MinReturn -67.8896 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.4591 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.32e+07 __unnamed_task__/AverageDiscountedReturn -27.9853 __unnamed_task__/AverageReturn -49.4955 __unnamed_task__/Iteration 274 __unnamed_task__/MaxReturn -39.0308 __unnamed_task__/MinReturn -76.9814 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.02259 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 02:31:01 | [maml_trainer] epoch #275 | Sampling for adapation and meta-testing... 2025-04-09 02:35:09 | [maml_trainer] epoch #275 | Finished meta-testing... 2025-04-09 02:35:09 | [maml_trainer] epoch #275 | Saving snapshot... 2025-04-09 02:35:33 | [maml_trainer] epoch #275 | Saved 2025-04-09 02:35:33 | [maml_trainer] epoch #275 | Time 467777.45 s 2025-04-09 02:35:33 | [maml_trainer] epoch #275 | EpochTime 1756.46 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.6669 Average/AverageReturn -48.741 Average/Iteration 275 Average/MaxReturn -40.6618 Average/MinReturn -67.3038 Average/NumEpisodes 120 Average/StdReturn 4.74014 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.83372 GaussianMLPPolicy/KLAfter 0.00197046 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.0001426 GaussianMLPPolicy/LossBefore -3.73522e-09 GaussianMLPPolicy/dLoss 0.000142597 Iteration 275 MetaTest/Average/AverageDiscountedReturn -48.7942 MetaTest/Average/AverageReturn -48.7942 MetaTest/Average/Iteration 275 MetaTest/Average/MaxReturn -41.8104 MetaTest/Average/MinReturn -55.8639 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.36093 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.7942 MetaTest/__unnamed_task__/AverageReturn -48.7942 MetaTest/__unnamed_task__/Iteration 275 MetaTest/__unnamed_task__/MaxReturn -41.8104 MetaTest/__unnamed_task__/MinReturn -55.8639 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.36093 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3248e+07 __unnamed_task__/AverageDiscountedReturn -27.6669 __unnamed_task__/AverageReturn -48.741 __unnamed_task__/Iteration 275 __unnamed_task__/MaxReturn -40.6618 __unnamed_task__/MinReturn -67.3038 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.74014 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 03:00:07 | [maml_trainer] epoch #276 | Sampling for adapation and meta-testing... 2025-04-09 03:04:16 | [maml_trainer] epoch #276 | Finished meta-testing... 2025-04-09 03:04:16 | [maml_trainer] epoch #276 | Saving snapshot... 2025-04-09 03:04:39 | [maml_trainer] epoch #276 | Saved 2025-04-09 03:04:39 | [maml_trainer] epoch #276 | Time 469523.90 s 2025-04-09 03:04:39 | [maml_trainer] epoch #276 | EpochTime 1746.44 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.3744 Average/AverageReturn -48.1684 Average/Iteration 276 Average/MaxReturn -39.8668 Average/MinReturn -66.3583 Average/NumEpisodes 120 Average/StdReturn 4.51664 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.83575 GaussianMLPPolicy/KLAfter 0.00262957 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000212673 GaussianMLPPolicy/LossBefore 4.13259e-09 GaussianMLPPolicy/dLoss -0.000212669 Iteration 276 MetaTest/Average/AverageDiscountedReturn -49.1689 MetaTest/Average/AverageReturn -49.1689 MetaTest/Average/Iteration 276 MetaTest/Average/MaxReturn -21.3024 MetaTest/Average/MinReturn -66.3441 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.58445 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.1689 MetaTest/__unnamed_task__/AverageReturn -49.1689 MetaTest/__unnamed_task__/Iteration 276 MetaTest/__unnamed_task__/MaxReturn -21.3024 MetaTest/__unnamed_task__/MinReturn -66.3441 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.58445 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3296e+07 __unnamed_task__/AverageDiscountedReturn -27.3744 __unnamed_task__/AverageReturn -48.1684 __unnamed_task__/Iteration 276 __unnamed_task__/MaxReturn -39.8668 __unnamed_task__/MinReturn -66.3583 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.51664 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 03:29:22 | [maml_trainer] epoch #277 | Sampling for adapation and meta-testing... 2025-04-09 03:33:30 | [maml_trainer] epoch #277 | Finished meta-testing... 2025-04-09 03:33:30 | [maml_trainer] epoch #277 | Saving snapshot... 2025-04-09 03:33:54 | [maml_trainer] epoch #277 | Saved 2025-04-09 03:33:54 | [maml_trainer] epoch #277 | Time 471278.76 s 2025-04-09 03:33:54 | [maml_trainer] epoch #277 | EpochTime 1754.86 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.6337 Average/AverageReturn -49.0864 Average/Iteration 277 Average/MaxReturn -38.5068 Average/MinReturn -64.8973 Average/NumEpisodes 120 Average/StdReturn 5.54763 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.83725 GaussianMLPPolicy/KLAfter 0.00331177 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000101932 GaussianMLPPolicy/LossBefore -7.35124e-09 GaussianMLPPolicy/dLoss -0.00010194 Iteration 277 MetaTest/Average/AverageDiscountedReturn -52.3787 MetaTest/Average/AverageReturn -52.3787 MetaTest/Average/Iteration 277 MetaTest/Average/MaxReturn -41.566 MetaTest/Average/MinReturn -92.0921 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.6209 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.3787 MetaTest/__unnamed_task__/AverageReturn -52.3787 MetaTest/__unnamed_task__/Iteration 277 MetaTest/__unnamed_task__/MaxReturn -41.566 MetaTest/__unnamed_task__/MinReturn -92.0921 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.6209 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3344e+07 __unnamed_task__/AverageDiscountedReturn -27.6337 __unnamed_task__/AverageReturn -49.0864 __unnamed_task__/Iteration 277 __unnamed_task__/MaxReturn -38.5068 __unnamed_task__/MinReturn -64.8973 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.54763 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 03:58:42 | [maml_trainer] epoch #278 | Sampling for adapation and meta-testing... 2025-04-09 04:02:51 | [maml_trainer] epoch #278 | Finished meta-testing... 2025-04-09 04:02:51 | [maml_trainer] epoch #278 | Saving snapshot... 2025-04-09 04:03:15 | [maml_trainer] epoch #278 | Saved 2025-04-09 04:03:15 | [maml_trainer] epoch #278 | Time 473039.05 s 2025-04-09 04:03:15 | [maml_trainer] epoch #278 | EpochTime 1760.29 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.424 Average/AverageReturn -49.2935 Average/Iteration 278 Average/MaxReturn -38.9248 Average/MinReturn -114.021 Average/NumEpisodes 120 Average/StdReturn 8.67271 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.83877 GaussianMLPPolicy/KLAfter 0.00242004 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.63e-07 GaussianMLPPolicy/LossBefore -1.95503e-08 GaussianMLPPolicy/dLoss 1.43449e-07 Iteration 278 MetaTest/Average/AverageDiscountedReturn -54.5271 MetaTest/Average/AverageReturn -54.5271 MetaTest/Average/Iteration 278 MetaTest/Average/MaxReturn -42.1816 MetaTest/Average/MinReturn -98.578 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.6559 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.5271 MetaTest/__unnamed_task__/AverageReturn -54.5271 MetaTest/__unnamed_task__/Iteration 278 MetaTest/__unnamed_task__/MaxReturn -42.1816 MetaTest/__unnamed_task__/MinReturn -98.578 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.6559 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3392e+07 __unnamed_task__/AverageDiscountedReturn -27.424 __unnamed_task__/AverageReturn -49.2935 __unnamed_task__/Iteration 278 __unnamed_task__/MaxReturn -38.9248 __unnamed_task__/MinReturn -114.021 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.67271 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 04:28:01 | [maml_trainer] epoch #279 | Sampling for adapation and meta-testing... 2025-04-09 04:32:09 | [maml_trainer] epoch #279 | Finished meta-testing... 2025-04-09 04:32:09 | [maml_trainer] epoch #279 | Saving snapshot... 2025-04-09 04:32:33 | [maml_trainer] epoch #279 | Saved 2025-04-09 04:32:33 | [maml_trainer] epoch #279 | Time 474797.86 s 2025-04-09 04:32:33 | [maml_trainer] epoch #279 | EpochTime 1758.81 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.3237 Average/AverageReturn -48.7237 Average/Iteration 279 Average/MaxReturn 152.609 Average/MinReturn -170.53 Average/NumEpisodes 120 Average/StdReturn 30.6231 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.83968 GaussianMLPPolicy/KLAfter 0.00297534 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.06895e-05 GaussianMLPPolicy/LossBefore -1.81794e-09 GaussianMLPPolicy/dLoss 4.06877e-05 Iteration 279 MetaTest/Average/AverageDiscountedReturn -61.6429 MetaTest/Average/AverageReturn -61.6429 MetaTest/Average/Iteration 279 MetaTest/Average/MaxReturn -44.1243 MetaTest/Average/MinReturn -153.438 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.3329 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -61.6429 MetaTest/__unnamed_task__/AverageReturn -61.6429 MetaTest/__unnamed_task__/Iteration 279 MetaTest/__unnamed_task__/MaxReturn -44.1243 MetaTest/__unnamed_task__/MinReturn -153.438 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.3329 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.344e+07 __unnamed_task__/AverageDiscountedReturn -27.3237 __unnamed_task__/AverageReturn -48.7237 __unnamed_task__/Iteration 279 __unnamed_task__/MaxReturn 152.609 __unnamed_task__/MinReturn -170.53 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 30.6231 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 04:57:13 | [maml_trainer] epoch #280 | Sampling for adapation and meta-testing... 2025-04-09 05:01:21 | [maml_trainer] epoch #280 | Finished meta-testing... 2025-04-09 05:01:21 | [maml_trainer] epoch #280 | Saving snapshot... 2025-04-09 05:01:45 | [maml_trainer] epoch #280 | Saved 2025-04-09 05:01:45 | [maml_trainer] epoch #280 | Time 476549.33 s 2025-04-09 05:01:45 | [maml_trainer] epoch #280 | EpochTime 1751.46 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.4006 Average/AverageReturn -50.4869 Average/Iteration 280 Average/MaxReturn -32.6479 Average/MinReturn -172.711 Average/NumEpisodes 120 Average/StdReturn 16.5795 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84033 GaussianMLPPolicy/KLAfter 0.00205126 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.45333e-06 GaussianMLPPolicy/LossBefore 6.77506e-09 GaussianMLPPolicy/dLoss 6.46011e-06 Iteration 280 MetaTest/Average/AverageDiscountedReturn -49.959 MetaTest/Average/AverageReturn -49.959 MetaTest/Average/Iteration 280 MetaTest/Average/MaxReturn -40.0369 MetaTest/Average/MinReturn -69.5839 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.77003 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.959 MetaTest/__unnamed_task__/AverageReturn -49.959 MetaTest/__unnamed_task__/Iteration 280 MetaTest/__unnamed_task__/MaxReturn -40.0369 MetaTest/__unnamed_task__/MinReturn -69.5839 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.77003 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3488e+07 __unnamed_task__/AverageDiscountedReturn -27.4006 __unnamed_task__/AverageReturn -50.4869 __unnamed_task__/Iteration 280 __unnamed_task__/MaxReturn -32.6479 __unnamed_task__/MinReturn -172.711 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 16.5795 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 05:26:46 | [maml_trainer] epoch #281 | Sampling for adapation and meta-testing... 2025-04-09 05:30:54 | [maml_trainer] epoch #281 | Finished meta-testing... 2025-04-09 05:30:54 | [maml_trainer] epoch #281 | Saving snapshot... 2025-04-09 05:31:18 | [maml_trainer] epoch #281 | Saved 2025-04-09 05:31:18 | [maml_trainer] epoch #281 | Time 478322.06 s 2025-04-09 05:31:18 | [maml_trainer] epoch #281 | EpochTime 1772.72 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.6919 Average/AverageReturn -52.208 Average/Iteration 281 Average/MaxReturn -37.6851 Average/MinReturn -139.59 Average/NumEpisodes 120 Average/StdReturn 14.8945 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.842 GaussianMLPPolicy/KLAfter 0.000762792 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.20295e-05 GaussianMLPPolicy/LossBefore 1.15236e-09 GaussianMLPPolicy/dLoss -1.20283e-05 Iteration 281 MetaTest/Average/AverageDiscountedReturn -49.5727 MetaTest/Average/AverageReturn -49.5727 MetaTest/Average/Iteration 281 MetaTest/Average/MaxReturn -39.4861 MetaTest/Average/MinReturn -78.1038 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.29383 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5727 MetaTest/__unnamed_task__/AverageReturn -49.5727 MetaTest/__unnamed_task__/Iteration 281 MetaTest/__unnamed_task__/MaxReturn -39.4861 MetaTest/__unnamed_task__/MinReturn -78.1038 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.29383 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3536e+07 __unnamed_task__/AverageDiscountedReturn -27.6919 __unnamed_task__/AverageReturn -52.208 __unnamed_task__/Iteration 281 __unnamed_task__/MaxReturn -37.6851 __unnamed_task__/MinReturn -139.59 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.8945 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 05:56:03 | [maml_trainer] epoch #282 | Sampling for adapation and meta-testing... 2025-04-09 06:00:11 | [maml_trainer] epoch #282 | Finished meta-testing... 2025-04-09 06:00:11 | [maml_trainer] epoch #282 | Saving snapshot... 2025-04-09 06:00:35 | [maml_trainer] epoch #282 | Saved 2025-04-09 06:00:35 | [maml_trainer] epoch #282 | Time 480079.03 s 2025-04-09 06:00:35 | [maml_trainer] epoch #282 | EpochTime 1756.97 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.0888 Average/AverageReturn -53.07 Average/Iteration 282 Average/MaxReturn -39.8601 Average/MinReturn -161.478 Average/NumEpisodes 120 Average/StdReturn 16.0315 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84298 GaussianMLPPolicy/KLAfter 0.00115119 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.47356e-05 GaussianMLPPolicy/LossBefore -3.17891e-10 GaussianMLPPolicy/dLoss 2.47353e-05 Iteration 282 MetaTest/Average/AverageDiscountedReturn -48.9273 MetaTest/Average/AverageReturn -48.9273 MetaTest/Average/Iteration 282 MetaTest/Average/MaxReturn -41.2956 MetaTest/Average/MinReturn -71.7271 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.75402 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9273 MetaTest/__unnamed_task__/AverageReturn -48.9273 MetaTest/__unnamed_task__/Iteration 282 MetaTest/__unnamed_task__/MaxReturn -41.2956 MetaTest/__unnamed_task__/MinReturn -71.7271 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.75402 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3584e+07 __unnamed_task__/AverageDiscountedReturn -28.0888 __unnamed_task__/AverageReturn -53.07 __unnamed_task__/Iteration 282 __unnamed_task__/MaxReturn -39.8601 __unnamed_task__/MinReturn -161.478 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 16.0315 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 06:25:18 | [maml_trainer] epoch #283 | Sampling for adapation and meta-testing... 2025-04-09 06:29:23 | [maml_trainer] epoch #283 | Finished meta-testing... 2025-04-09 06:29:23 | [maml_trainer] epoch #283 | Saving snapshot... 2025-04-09 06:29:46 | [maml_trainer] epoch #283 | Saved 2025-04-09 06:29:46 | [maml_trainer] epoch #283 | Time 481830.92 s 2025-04-09 06:29:46 | [maml_trainer] epoch #283 | EpochTime 1751.88 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.2197 Average/AverageReturn -48.7057 Average/Iteration 283 Average/MaxReturn -37.8917 Average/MinReturn -93.0199 Average/NumEpisodes 120 Average/StdReturn 6.47548 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84334 GaussianMLPPolicy/KLAfter 0.000902342 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.005e-05 GaussianMLPPolicy/LossBefore -7.3115e-09 GaussianMLPPolicy/dLoss -6.00573e-05 Iteration 283 MetaTest/Average/AverageDiscountedReturn -53.994 MetaTest/Average/AverageReturn -53.994 MetaTest/Average/Iteration 283 MetaTest/Average/MaxReturn -39.8354 MetaTest/Average/MinReturn -164.762 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.0334 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.994 MetaTest/__unnamed_task__/AverageReturn -53.994 MetaTest/__unnamed_task__/Iteration 283 MetaTest/__unnamed_task__/MaxReturn -39.8354 MetaTest/__unnamed_task__/MinReturn -164.762 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.0334 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3632e+07 __unnamed_task__/AverageDiscountedReturn -27.2197 __unnamed_task__/AverageReturn -48.7057 __unnamed_task__/Iteration 283 __unnamed_task__/MaxReturn -37.8917 __unnamed_task__/MinReturn -93.0199 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.47548 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 06:54:36 | [maml_trainer] epoch #284 | Sampling for adapation and meta-testing... 2025-04-09 06:58:44 | [maml_trainer] epoch #284 | Finished meta-testing... 2025-04-09 06:58:44 | [maml_trainer] epoch #284 | Saving snapshot... 2025-04-09 06:59:08 | [maml_trainer] epoch #284 | Saved 2025-04-09 06:59:08 | [maml_trainer] epoch #284 | Time 483592.12 s 2025-04-09 06:59:08 | [maml_trainer] epoch #284 | EpochTime 1761.20 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.2562 Average/AverageReturn -49.3392 Average/Iteration 284 Average/MaxReturn -40.6804 Average/MinReturn -125.351 Average/NumEpisodes 120 Average/StdReturn 9.22924 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84422 GaussianMLPPolicy/KLAfter 0.00117181 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.2106e-05 GaussianMLPPolicy/LossBefore -2.38419e-09 GaussianMLPPolicy/dLoss 1.21036e-05 Iteration 284 MetaTest/Average/AverageDiscountedReturn -54.9511 MetaTest/Average/AverageReturn -54.9511 MetaTest/Average/Iteration 284 MetaTest/Average/MaxReturn -41.8783 MetaTest/Average/MinReturn -157.794 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.0959 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.9511 MetaTest/__unnamed_task__/AverageReturn -54.9511 MetaTest/__unnamed_task__/Iteration 284 MetaTest/__unnamed_task__/MaxReturn -41.8783 MetaTest/__unnamed_task__/MinReturn -157.794 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.0959 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.368e+07 __unnamed_task__/AverageDiscountedReturn -27.2562 __unnamed_task__/AverageReturn -49.3392 __unnamed_task__/Iteration 284 __unnamed_task__/MaxReturn -40.6804 __unnamed_task__/MinReturn -125.351 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.22924 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 07:23:58 | [maml_trainer] epoch #285 | Sampling for adapation and meta-testing... 2025-04-09 07:28:08 | [maml_trainer] epoch #285 | Finished meta-testing... 2025-04-09 07:28:08 | [maml_trainer] epoch #285 | Saving snapshot... 2025-04-09 07:28:32 | [maml_trainer] epoch #285 | Saved 2025-04-09 07:28:32 | [maml_trainer] epoch #285 | Time 485356.61 s 2025-04-09 07:28:32 | [maml_trainer] epoch #285 | EpochTime 1764.49 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.656 Average/AverageReturn -50.1084 Average/Iteration 285 Average/MaxReturn -39.9202 Average/MinReturn -93.6819 Average/NumEpisodes 120 Average/StdReturn 7.15493 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84486 GaussianMLPPolicy/KLAfter 0.000480827 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.10755e-05 GaussianMLPPolicy/LossBefore -5.16574e-09 GaussianMLPPolicy/dLoss 2.10704e-05 Iteration 285 MetaTest/Average/AverageDiscountedReturn -49.1741 MetaTest/Average/AverageReturn -49.1741 MetaTest/Average/Iteration 285 MetaTest/Average/MaxReturn -41.9384 MetaTest/Average/MinReturn -66.4693 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.19832 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.1741 MetaTest/__unnamed_task__/AverageReturn -49.1741 MetaTest/__unnamed_task__/Iteration 285 MetaTest/__unnamed_task__/MaxReturn -41.9384 MetaTest/__unnamed_task__/MinReturn -66.4693 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.19832 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3728e+07 __unnamed_task__/AverageDiscountedReturn -27.656 __unnamed_task__/AverageReturn -50.1084 __unnamed_task__/Iteration 285 __unnamed_task__/MaxReturn -39.9202 __unnamed_task__/MinReturn -93.6819 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.15493 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 07:53:23 | [maml_trainer] epoch #286 | Sampling for adapation and meta-testing... 2025-04-09 07:57:31 | [maml_trainer] epoch #286 | Finished meta-testing... 2025-04-09 07:57:31 | [maml_trainer] epoch #286 | Saving snapshot... 2025-04-09 07:57:55 | [maml_trainer] epoch #286 | Saved 2025-04-09 07:57:55 | [maml_trainer] epoch #286 | Time 487119.04 s 2025-04-09 07:57:55 | [maml_trainer] epoch #286 | EpochTime 1762.43 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.4658 Average/AverageReturn -49.0478 Average/Iteration 286 Average/MaxReturn -38.5596 Average/MinReturn -84.1677 Average/NumEpisodes 120 Average/StdReturn 6.23412 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84592 GaussianMLPPolicy/KLAfter 0.0018605 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.02779e-07 GaussianMLPPolicy/LossBefore 4.88758e-09 GaussianMLPPolicy/dLoss -6.97891e-07 Iteration 286 MetaTest/Average/AverageDiscountedReturn -53.4291 MetaTest/Average/AverageReturn -53.4291 MetaTest/Average/Iteration 286 MetaTest/Average/MaxReturn -41.6058 MetaTest/Average/MinReturn -146.921 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.0642 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.4291 MetaTest/__unnamed_task__/AverageReturn -53.4291 MetaTest/__unnamed_task__/Iteration 286 MetaTest/__unnamed_task__/MaxReturn -41.6058 MetaTest/__unnamed_task__/MinReturn -146.921 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.0642 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3776e+07 __unnamed_task__/AverageDiscountedReturn -27.4658 __unnamed_task__/AverageReturn -49.0478 __unnamed_task__/Iteration 286 __unnamed_task__/MaxReturn -38.5596 __unnamed_task__/MinReturn -84.1677 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.23412 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 08:22:43 | [maml_trainer] epoch #287 | Sampling for adapation and meta-testing... 2025-04-09 08:26:53 | [maml_trainer] epoch #287 | Finished meta-testing... 2025-04-09 08:26:53 | [maml_trainer] epoch #287 | Saving snapshot... 2025-04-09 08:27:17 | [maml_trainer] epoch #287 | Saved 2025-04-09 08:27:17 | [maml_trainer] epoch #287 | Time 488881.42 s 2025-04-09 08:27:17 | [maml_trainer] epoch #287 | EpochTime 1762.37 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.4829 Average/AverageReturn -49.7213 Average/Iteration 287 Average/MaxReturn -39.285 Average/MinReturn -88.0941 Average/NumEpisodes 120 Average/StdReturn 6.92731 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84657 GaussianMLPPolicy/KLAfter 0.00157238 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.53728e-05 GaussianMLPPolicy/LossBefore 4.56969e-09 GaussianMLPPolicy/dLoss 6.53774e-05 Iteration 287 MetaTest/Average/AverageDiscountedReturn -31.3637 MetaTest/Average/AverageReturn -31.3637 MetaTest/Average/Iteration 287 MetaTest/Average/MaxReturn 313.418 MetaTest/Average/MinReturn -69.6087 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 79.3604 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -31.3637 MetaTest/__unnamed_task__/AverageReturn -31.3637 MetaTest/__unnamed_task__/Iteration 287 MetaTest/__unnamed_task__/MaxReturn 313.418 MetaTest/__unnamed_task__/MinReturn -69.6087 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 79.3604 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3824e+07 __unnamed_task__/AverageDiscountedReturn -27.4829 __unnamed_task__/AverageReturn -49.7213 __unnamed_task__/Iteration 287 __unnamed_task__/MaxReturn -39.285 __unnamed_task__/MinReturn -88.0941 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.92731 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 08:52:01 | [maml_trainer] epoch #288 | Sampling for adapation and meta-testing... 2025-04-09 08:56:10 | [maml_trainer] epoch #288 | Finished meta-testing... 2025-04-09 08:56:10 | [maml_trainer] epoch #288 | Saving snapshot... 2025-04-09 08:56:33 | [maml_trainer] epoch #288 | Saved 2025-04-09 08:56:33 | [maml_trainer] epoch #288 | Time 490637.84 s 2025-04-09 08:56:33 | [maml_trainer] epoch #288 | EpochTime 1756.42 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.2883 Average/AverageReturn -48.6802 Average/Iteration 288 Average/MaxReturn -38.8967 Average/MinReturn -70.9829 Average/NumEpisodes 120 Average/StdReturn 5.1151 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84763 GaussianMLPPolicy/KLAfter 0.000705939 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.97368e-05 GaussianMLPPolicy/LossBefore -4.41074e-09 GaussianMLPPolicy/dLoss 1.97324e-05 Iteration 288 MetaTest/Average/AverageDiscountedReturn -49.3488 MetaTest/Average/AverageReturn -49.3488 MetaTest/Average/Iteration 288 MetaTest/Average/MaxReturn -41.2212 MetaTest/Average/MinReturn -64.1248 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.67222 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.3488 MetaTest/__unnamed_task__/AverageReturn -49.3488 MetaTest/__unnamed_task__/Iteration 288 MetaTest/__unnamed_task__/MaxReturn -41.2212 MetaTest/__unnamed_task__/MinReturn -64.1248 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.67222 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3872e+07 __unnamed_task__/AverageDiscountedReturn -27.2883 __unnamed_task__/AverageReturn -48.6802 __unnamed_task__/Iteration 288 __unnamed_task__/MaxReturn -38.8967 __unnamed_task__/MinReturn -70.9829 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.1151 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 09:21:13 | [maml_trainer] epoch #289 | Sampling for adapation and meta-testing... 2025-04-09 09:25:21 | [maml_trainer] epoch #289 | Finished meta-testing... 2025-04-09 09:25:21 | [maml_trainer] epoch #289 | Saving snapshot... 2025-04-09 09:25:45 | [maml_trainer] epoch #289 | Saved 2025-04-09 09:25:45 | [maml_trainer] epoch #289 | Time 492389.94 s 2025-04-09 09:25:45 | [maml_trainer] epoch #289 | EpochTime 1752.10 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.349 Average/AverageReturn -48.4652 Average/Iteration 289 Average/MaxReturn -39.1301 Average/MinReturn -69.9492 Average/NumEpisodes 120 Average/StdReturn 4.94534 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84709 GaussianMLPPolicy/KLAfter 0.000723787 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.35118e-05 GaussianMLPPolicy/LossBefore 7.23203e-09 GaussianMLPPolicy/dLoss -2.35046e-05 Iteration 289 MetaTest/Average/AverageDiscountedReturn -48.9327 MetaTest/Average/AverageReturn -48.9327 MetaTest/Average/Iteration 289 MetaTest/Average/MaxReturn -41.9294 MetaTest/Average/MinReturn -62.9215 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.04952 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9327 MetaTest/__unnamed_task__/AverageReturn -48.9327 MetaTest/__unnamed_task__/Iteration 289 MetaTest/__unnamed_task__/MaxReturn -41.9294 MetaTest/__unnamed_task__/MinReturn -62.9215 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.04952 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.392e+07 __unnamed_task__/AverageDiscountedReturn -27.349 __unnamed_task__/AverageReturn -48.4652 __unnamed_task__/Iteration 289 __unnamed_task__/MaxReturn -39.1301 __unnamed_task__/MinReturn -69.9492 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.94534 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 09:50:41 | [maml_trainer] epoch #290 | Sampling for adapation and meta-testing... 2025-04-09 09:54:45 | [maml_trainer] epoch #290 | Finished meta-testing... 2025-04-09 09:54:45 | [maml_trainer] epoch #290 | Saving snapshot... 2025-04-09 09:55:09 | [maml_trainer] epoch #290 | Saved 2025-04-09 09:55:09 | [maml_trainer] epoch #290 | Time 494153.09 s 2025-04-09 09:55:09 | [maml_trainer] epoch #290 | EpochTime 1763.15 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.5587 Average/AverageReturn -48.9164 Average/Iteration 290 Average/MaxReturn -39.458 Average/MinReturn -75.9641 Average/NumEpisodes 120 Average/StdReturn 5.34426 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84744 GaussianMLPPolicy/KLAfter 0.0008764 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.21229e-05 GaussianMLPPolicy/LossBefore -5.44389e-09 GaussianMLPPolicy/dLoss 2.21175e-05 Iteration 290 MetaTest/Average/AverageDiscountedReturn -49.0783 MetaTest/Average/AverageReturn -49.0783 MetaTest/Average/Iteration 290 MetaTest/Average/MaxReturn -41.4701 MetaTest/Average/MinReturn -58.0019 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.81865 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.0783 MetaTest/__unnamed_task__/AverageReturn -49.0783 MetaTest/__unnamed_task__/Iteration 290 MetaTest/__unnamed_task__/MaxReturn -41.4701 MetaTest/__unnamed_task__/MinReturn -58.0019 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.81865 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.3968e+07 __unnamed_task__/AverageDiscountedReturn -27.5587 __unnamed_task__/AverageReturn -48.9164 __unnamed_task__/Iteration 290 __unnamed_task__/MaxReturn -39.458 __unnamed_task__/MinReturn -75.9641 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.34426 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 10:20:01 | [maml_trainer] epoch #291 | Sampling for adapation and meta-testing... 2025-04-09 10:24:10 | [maml_trainer] epoch #291 | Finished meta-testing... 2025-04-09 10:24:10 | [maml_trainer] epoch #291 | Saving snapshot... 2025-04-09 10:24:32 | [maml_trainer] epoch #291 | Saved 2025-04-09 10:24:32 | [maml_trainer] epoch #291 | Time 495916.84 s 2025-04-09 10:24:32 | [maml_trainer] epoch #291 | EpochTime 1763.74 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.127 Average/AverageReturn -48.4691 Average/Iteration 291 Average/MaxReturn -39.5616 Average/MinReturn -94.3705 Average/NumEpisodes 120 Average/StdReturn 6.14701 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84723 GaussianMLPPolicy/KLAfter 0.00115406 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.14162e-06 GaussianMLPPolicy/LossBefore -6.71546e-09 GaussianMLPPolicy/dLoss 5.1349e-06 Iteration 291 MetaTest/Average/AverageDiscountedReturn -50.2765 MetaTest/Average/AverageReturn -50.2765 MetaTest/Average/Iteration 291 MetaTest/Average/MaxReturn -43.9955 MetaTest/Average/MinReturn -61.29 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.62471 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.2765 MetaTest/__unnamed_task__/AverageReturn -50.2765 MetaTest/__unnamed_task__/Iteration 291 MetaTest/__unnamed_task__/MaxReturn -43.9955 MetaTest/__unnamed_task__/MinReturn -61.29 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.62471 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4016e+07 __unnamed_task__/AverageDiscountedReturn -27.127 __unnamed_task__/AverageReturn -48.4691 __unnamed_task__/Iteration 291 __unnamed_task__/MaxReturn -39.5616 __unnamed_task__/MinReturn -94.3705 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.14701 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 10:49:11 | [maml_trainer] epoch #292 | Sampling for adapation and meta-testing... 2025-04-09 10:53:20 | [maml_trainer] epoch #292 | Finished meta-testing... 2025-04-09 10:53:20 | [maml_trainer] epoch #292 | Saving snapshot... 2025-04-09 10:53:44 | [maml_trainer] epoch #292 | Saved 2025-04-09 10:53:44 | [maml_trainer] epoch #292 | Time 497668.85 s 2025-04-09 10:53:44 | [maml_trainer] epoch #292 | EpochTime 1752.01 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.4992 Average/AverageReturn -49.0204 Average/Iteration 292 Average/MaxReturn -41.2151 Average/MinReturn -65.4878 Average/NumEpisodes 120 Average/StdReturn 5.31237 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84703 GaussianMLPPolicy/KLAfter 0.00102341 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.04341e-05 GaussianMLPPolicy/LossBefore -6.07967e-09 GaussianMLPPolicy/dLoss -3.04401e-05 Iteration 292 MetaTest/Average/AverageDiscountedReturn -49.039 MetaTest/Average/AverageReturn -49.039 MetaTest/Average/Iteration 292 MetaTest/Average/MaxReturn -40.0913 MetaTest/Average/MinReturn -65.3579 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.47538 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.039 MetaTest/__unnamed_task__/AverageReturn -49.039 MetaTest/__unnamed_task__/Iteration 292 MetaTest/__unnamed_task__/MaxReturn -40.0913 MetaTest/__unnamed_task__/MinReturn -65.3579 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.47538 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4064e+07 __unnamed_task__/AverageDiscountedReturn -27.4992 __unnamed_task__/AverageReturn -49.0204 __unnamed_task__/Iteration 292 __unnamed_task__/MaxReturn -41.2151 __unnamed_task__/MinReturn -65.4878 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.31237 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 11:18:15 | [maml_trainer] epoch #293 | Sampling for adapation and meta-testing... 2025-04-09 11:22:21 | [maml_trainer] epoch #293 | Finished meta-testing... 2025-04-09 11:22:21 | [maml_trainer] epoch #293 | Saving snapshot... 2025-04-09 11:22:44 | [maml_trainer] epoch #293 | Saved 2025-04-09 11:22:44 | [maml_trainer] epoch #293 | Time 499408.61 s 2025-04-09 11:22:44 | [maml_trainer] epoch #293 | EpochTime 1739.75 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.2754 Average/AverageReturn -49.5307 Average/Iteration 293 Average/MaxReturn -40.7706 Average/MinReturn -172.508 Average/NumEpisodes 120 Average/StdReturn 12.2557 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84702 GaussianMLPPolicy/KLAfter 0.000815953 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.02136e-05 GaussianMLPPolicy/LossBefore -5.72205e-09 GaussianMLPPolicy/dLoss 4.02079e-05 Iteration 293 MetaTest/Average/AverageDiscountedReturn -51.2676 MetaTest/Average/AverageReturn -51.2676 MetaTest/Average/Iteration 293 MetaTest/Average/MaxReturn -43.5892 MetaTest/Average/MinReturn -64.7348 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.44633 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2676 MetaTest/__unnamed_task__/AverageReturn -51.2676 MetaTest/__unnamed_task__/Iteration 293 MetaTest/__unnamed_task__/MaxReturn -43.5892 MetaTest/__unnamed_task__/MinReturn -64.7348 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.44633 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4112e+07 __unnamed_task__/AverageDiscountedReturn -27.2754 __unnamed_task__/AverageReturn -49.5307 __unnamed_task__/Iteration 293 __unnamed_task__/MaxReturn -40.7706 __unnamed_task__/MinReturn -172.508 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.2557 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 11:47:40 | [maml_trainer] epoch #294 | Sampling for adapation and meta-testing... 2025-04-09 11:51:55 | [maml_trainer] epoch #294 | Finished meta-testing... 2025-04-09 11:51:55 | [maml_trainer] epoch #294 | Saving snapshot... 2025-04-09 11:52:18 | [maml_trainer] epoch #294 | Saved 2025-04-09 11:52:18 | [maml_trainer] epoch #294 | Time 501181.97 s 2025-04-09 11:52:18 | [maml_trainer] epoch #294 | EpochTime 1773.35 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.6121 Average/AverageReturn -49.8579 Average/Iteration 294 Average/MaxReturn -40.3695 Average/MinReturn -69.3989 Average/NumEpisodes 120 Average/StdReturn 5.90292 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84722 GaussianMLPPolicy/KLAfter 0.00116165 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.94859e-05 GaussianMLPPolicy/LossBefore -2.04643e-08 GaussianMLPPolicy/dLoss -3.95064e-05 Iteration 294 MetaTest/Average/AverageDiscountedReturn -48.2488 MetaTest/Average/AverageReturn -48.2488 MetaTest/Average/Iteration 294 MetaTest/Average/MaxReturn -41.839 MetaTest/Average/MinReturn -61.1988 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.64504 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.2488 MetaTest/__unnamed_task__/AverageReturn -48.2488 MetaTest/__unnamed_task__/Iteration 294 MetaTest/__unnamed_task__/MaxReturn -41.839 MetaTest/__unnamed_task__/MinReturn -61.1988 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.64504 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.416e+07 __unnamed_task__/AverageDiscountedReturn -27.6121 __unnamed_task__/AverageReturn -49.8579 __unnamed_task__/Iteration 294 __unnamed_task__/MaxReturn -40.3695 __unnamed_task__/MinReturn -69.3989 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.90292 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 12:16:45 | [maml_trainer] epoch #295 | Sampling for adapation and meta-testing... 2025-04-09 12:20:50 | [maml_trainer] epoch #295 | Finished meta-testing... 2025-04-09 12:20:50 | [maml_trainer] epoch #295 | Saving snapshot... 2025-04-09 12:21:12 | [maml_trainer] epoch #295 | Saved 2025-04-09 12:21:12 | [maml_trainer] epoch #295 | Time 502916.01 s 2025-04-09 12:21:12 | [maml_trainer] epoch #295 | EpochTime 1734.04 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.5042 Average/AverageReturn -50.5934 Average/Iteration 295 Average/MaxReturn -39.3843 Average/MinReturn -126.272 Average/NumEpisodes 120 Average/StdReturn 9.44996 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.8471 GaussianMLPPolicy/KLAfter 0.00175551 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.86884e-06 GaussianMLPPolicy/LossBefore -7.94729e-10 GaussianMLPPolicy/dLoss -1.86964e-06 Iteration 295 MetaTest/Average/AverageDiscountedReturn -45.4909 MetaTest/Average/AverageReturn -45.4909 MetaTest/Average/Iteration 295 MetaTest/Average/MaxReturn -40.1536 MetaTest/Average/MinReturn -50.5906 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 2.92968 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.4909 MetaTest/__unnamed_task__/AverageReturn -45.4909 MetaTest/__unnamed_task__/Iteration 295 MetaTest/__unnamed_task__/MaxReturn -40.1536 MetaTest/__unnamed_task__/MinReturn -50.5906 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 2.92968 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4208e+07 __unnamed_task__/AverageDiscountedReturn -27.5042 __unnamed_task__/AverageReturn -50.5934 __unnamed_task__/Iteration 295 __unnamed_task__/MaxReturn -39.3843 __unnamed_task__/MinReturn -126.272 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.44996 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 12:45:55 | [maml_trainer] epoch #296 | Sampling for adapation and meta-testing... 2025-04-09 12:50:08 | [maml_trainer] epoch #296 | Finished meta-testing... 2025-04-09 12:50:08 | [maml_trainer] epoch #296 | Saving snapshot... 2025-04-09 12:50:31 | [maml_trainer] epoch #296 | Saved 2025-04-09 12:50:31 | [maml_trainer] epoch #296 | Time 504675.35 s 2025-04-09 12:50:31 | [maml_trainer] epoch #296 | EpochTime 1759.33 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.2516 Average/AverageReturn -49.6713 Average/Iteration 296 Average/MaxReturn -39.2384 Average/MinReturn -113.654 Average/NumEpisodes 120 Average/StdReturn 8.27973 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84663 GaussianMLPPolicy/KLAfter 0.00328026 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.76853e-05 GaussianMLPPolicy/LossBefore 1.53383e-08 GaussianMLPPolicy/dLoss 8.77007e-05 Iteration 296 MetaTest/Average/AverageDiscountedReturn -51.7015 MetaTest/Average/AverageReturn -51.7015 MetaTest/Average/Iteration 296 MetaTest/Average/MaxReturn -42.783 MetaTest/Average/MinReturn -72.6487 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.14165 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.7015 MetaTest/__unnamed_task__/AverageReturn -51.7015 MetaTest/__unnamed_task__/Iteration 296 MetaTest/__unnamed_task__/MaxReturn -42.783 MetaTest/__unnamed_task__/MinReturn -72.6487 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.14165 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4256e+07 __unnamed_task__/AverageDiscountedReturn -27.2516 __unnamed_task__/AverageReturn -49.6713 __unnamed_task__/Iteration 296 __unnamed_task__/MaxReturn -39.2384 __unnamed_task__/MinReturn -113.654 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.27973 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 13:15:03 | [maml_trainer] epoch #297 | Sampling for adapation and meta-testing... 2025-04-09 13:19:01 | [maml_trainer] epoch #297 | Finished meta-testing... 2025-04-09 13:19:01 | [maml_trainer] epoch #297 | Saving snapshot... 2025-04-09 13:19:21 | [maml_trainer] epoch #297 | Saved 2025-04-09 13:19:21 | [maml_trainer] epoch #297 | Time 506405.93 s 2025-04-09 13:19:21 | [maml_trainer] epoch #297 | EpochTime 1730.58 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.6231 Average/AverageReturn -50.3713 Average/Iteration 297 Average/MaxReturn -39.8247 Average/MinReturn -72.188 Average/NumEpisodes 120 Average/StdReturn 6.66166 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84547 GaussianMLPPolicy/KLAfter 0.00188862 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.7503e-05 GaussianMLPPolicy/LossBefore 1.51793e-08 GaussianMLPPolicy/dLoss -4.74879e-05 Iteration 297 MetaTest/Average/AverageDiscountedReturn -48.2738 MetaTest/Average/AverageReturn -48.2738 MetaTest/Average/Iteration 297 MetaTest/Average/MaxReturn -38.3258 MetaTest/Average/MinReturn -72.5338 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.90826 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.2738 MetaTest/__unnamed_task__/AverageReturn -48.2738 MetaTest/__unnamed_task__/Iteration 297 MetaTest/__unnamed_task__/MaxReturn -38.3258 MetaTest/__unnamed_task__/MinReturn -72.5338 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.90826 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4304e+07 __unnamed_task__/AverageDiscountedReturn -27.6231 __unnamed_task__/AverageReturn -50.3713 __unnamed_task__/Iteration 297 __unnamed_task__/MaxReturn -39.8247 __unnamed_task__/MinReturn -72.188 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.66166 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 13:43:19 | [maml_trainer] epoch #298 | Sampling for adapation and meta-testing... 2025-04-09 13:47:10 | [maml_trainer] epoch #298 | Finished meta-testing... 2025-04-09 13:47:10 | [maml_trainer] epoch #298 | Saving snapshot... 2025-04-09 13:47:31 | [maml_trainer] epoch #298 | Saved 2025-04-09 13:47:31 | [maml_trainer] epoch #298 | Time 508095.52 s 2025-04-09 13:47:31 | [maml_trainer] epoch #298 | EpochTime 1689.58 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.295 Average/AverageReturn -49.1143 Average/Iteration 298 Average/MaxReturn -39.9629 Average/MinReturn -74.0346 Average/NumEpisodes 120 Average/StdReturn 6.09844 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84549 GaussianMLPPolicy/KLAfter 0.00115314 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.32421e-05 GaussianMLPPolicy/LossBefore 1.42256e-08 GaussianMLPPolicy/dLoss 4.32563e-05 Iteration 298 MetaTest/Average/AverageDiscountedReturn -47.6657 MetaTest/Average/AverageReturn -47.6657 MetaTest/Average/Iteration 298 MetaTest/Average/MaxReturn -38.097 MetaTest/Average/MinReturn -59.6643 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.54947 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.6657 MetaTest/__unnamed_task__/AverageReturn -47.6657 MetaTest/__unnamed_task__/Iteration 298 MetaTest/__unnamed_task__/MaxReturn -38.097 MetaTest/__unnamed_task__/MinReturn -59.6643 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.54947 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4352e+07 __unnamed_task__/AverageDiscountedReturn -27.295 __unnamed_task__/AverageReturn -49.1143 __unnamed_task__/Iteration 298 __unnamed_task__/MaxReturn -39.9629 __unnamed_task__/MinReturn -74.0346 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.09844 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 14:10:59 | [maml_trainer] epoch #299 | Sampling for adapation and meta-testing... 2025-04-09 14:14:52 | [maml_trainer] epoch #299 | Finished meta-testing... 2025-04-09 14:14:52 | [maml_trainer] epoch #299 | Saving snapshot... 2025-04-09 14:15:13 | [maml_trainer] epoch #299 | Saved 2025-04-09 14:15:13 | [maml_trainer] epoch #299 | Time 509757.53 s 2025-04-09 14:15:13 | [maml_trainer] epoch #299 | EpochTime 1662.01 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.6847 Average/AverageReturn -50.2265 Average/Iteration 299 Average/MaxReturn -39.3224 Average/MinReturn -70.4965 Average/NumEpisodes 120 Average/StdReturn 5.96782 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84422 GaussianMLPPolicy/KLAfter 0.00156841 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.24486e-06 GaussianMLPPolicy/LossBefore 5.84126e-09 GaussianMLPPolicy/dLoss 1.2507e-06 Iteration 299 MetaTest/Average/AverageDiscountedReturn -50.6979 MetaTest/Average/AverageReturn -50.6979 MetaTest/Average/Iteration 299 MetaTest/Average/MaxReturn -43.5031 MetaTest/Average/MinReturn -62.9053 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.63054 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.6979 MetaTest/__unnamed_task__/AverageReturn -50.6979 MetaTest/__unnamed_task__/Iteration 299 MetaTest/__unnamed_task__/MaxReturn -43.5031 MetaTest/__unnamed_task__/MinReturn -62.9053 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.63054 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.44e+07 __unnamed_task__/AverageDiscountedReturn -27.6847 __unnamed_task__/AverageReturn -50.2265 __unnamed_task__/Iteration 299 __unnamed_task__/MaxReturn -39.3224 __unnamed_task__/MinReturn -70.4965 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.96782 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 14:38:36 | [maml_trainer] epoch #300 | Sampling for adapation and meta-testing... 2025-04-09 14:42:31 | [maml_trainer] epoch #300 | Finished meta-testing... 2025-04-09 14:42:31 | [maml_trainer] epoch #300 | Saving snapshot... 2025-04-09 14:42:52 | [maml_trainer] epoch #300 | Saved 2025-04-09 14:42:52 | [maml_trainer] epoch #300 | Time 511416.01 s 2025-04-09 14:42:52 | [maml_trainer] epoch #300 | EpochTime 1658.48 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.3556 Average/AverageReturn -49.2573 Average/Iteration 300 Average/MaxReturn -38.3259 Average/MinReturn -75.2044 Average/NumEpisodes 120 Average/StdReturn 5.81219 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84355 GaussianMLPPolicy/KLAfter 0.00123328 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.68387e-05 GaussianMLPPolicy/LossBefore 1.61727e-08 GaussianMLPPolicy/dLoss 2.68548e-05 Iteration 300 MetaTest/Average/AverageDiscountedReturn -48.9058 MetaTest/Average/AverageReturn -48.9058 MetaTest/Average/Iteration 300 MetaTest/Average/MaxReturn -41.6639 MetaTest/Average/MinReturn -65.6491 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.89462 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9058 MetaTest/__unnamed_task__/AverageReturn -48.9058 MetaTest/__unnamed_task__/Iteration 300 MetaTest/__unnamed_task__/MaxReturn -41.6639 MetaTest/__unnamed_task__/MinReturn -65.6491 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.89462 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4448e+07 __unnamed_task__/AverageDiscountedReturn -27.3556 __unnamed_task__/AverageReturn -49.2573 __unnamed_task__/Iteration 300 __unnamed_task__/MaxReturn -38.3259 __unnamed_task__/MinReturn -75.2044 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.81219 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 15:06:12 | [maml_trainer] epoch #301 | Sampling for adapation and meta-testing... 2025-04-09 15:10:06 | [maml_trainer] epoch #301 | Finished meta-testing... 2025-04-09 15:10:06 | [maml_trainer] epoch #301 | Saving snapshot... 2025-04-09 15:10:27 | [maml_trainer] epoch #301 | Saved 2025-04-09 15:10:27 | [maml_trainer] epoch #301 | Time 513071.30 s 2025-04-09 15:10:27 | [maml_trainer] epoch #301 | EpochTime 1655.29 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.4661 Average/AverageReturn -49.6923 Average/Iteration 301 Average/MaxReturn -40.3277 Average/MinReturn -84.606 Average/NumEpisodes 120 Average/StdReturn 7.71979 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84343 GaussianMLPPolicy/KLAfter 0.00176131 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.45148e-05 GaussianMLPPolicy/LossBefore -4.84784e-09 GaussianMLPPolicy/dLoss -5.45196e-05 Iteration 301 MetaTest/Average/AverageDiscountedReturn -47.4397 MetaTest/Average/AverageReturn -47.4397 MetaTest/Average/Iteration 301 MetaTest/Average/MaxReturn -39.6059 MetaTest/Average/MinReturn -61.9059 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.78599 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4397 MetaTest/__unnamed_task__/AverageReturn -47.4397 MetaTest/__unnamed_task__/Iteration 301 MetaTest/__unnamed_task__/MaxReturn -39.6059 MetaTest/__unnamed_task__/MinReturn -61.9059 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.78599 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4496e+07 __unnamed_task__/AverageDiscountedReturn -27.4661 __unnamed_task__/AverageReturn -49.6923 __unnamed_task__/Iteration 301 __unnamed_task__/MaxReturn -40.3277 __unnamed_task__/MinReturn -84.606 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.71979 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 15:33:54 | [maml_trainer] epoch #302 | Sampling for adapation and meta-testing... 2025-04-09 15:37:48 | [maml_trainer] epoch #302 | Finished meta-testing... 2025-04-09 15:37:48 | [maml_trainer] epoch #302 | Saving snapshot... 2025-04-09 15:38:10 | [maml_trainer] epoch #302 | Saved 2025-04-09 15:38:10 | [maml_trainer] epoch #302 | Time 514734.50 s 2025-04-09 15:38:10 | [maml_trainer] epoch #302 | EpochTime 1663.19 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.3138 Average/AverageReturn -49.4382 Average/Iteration 302 Average/MaxReturn -40.6835 Average/MinReturn -112.395 Average/NumEpisodes 120 Average/StdReturn 8.37214 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.84023 GaussianMLPPolicy/KLAfter 0.00384613 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.33737e-05 GaussianMLPPolicy/LossBefore 5.08626e-09 GaussianMLPPolicy/dLoss 2.33788e-05 Iteration 302 MetaTest/Average/AverageDiscountedReturn -49.6437 MetaTest/Average/AverageReturn -49.6437 MetaTest/Average/Iteration 302 MetaTest/Average/MaxReturn -42.3981 MetaTest/Average/MinReturn -58.9913 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.01655 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.6437 MetaTest/__unnamed_task__/AverageReturn -49.6437 MetaTest/__unnamed_task__/Iteration 302 MetaTest/__unnamed_task__/MaxReturn -42.3981 MetaTest/__unnamed_task__/MinReturn -58.9913 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.01655 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4544e+07 __unnamed_task__/AverageDiscountedReturn -27.3138 __unnamed_task__/AverageReturn -49.4382 __unnamed_task__/Iteration 302 __unnamed_task__/MaxReturn -40.6835 __unnamed_task__/MinReturn -112.395 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.37214 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 16:01:40 | [maml_trainer] epoch #303 | Sampling for adapation and meta-testing... 2025-04-09 16:05:39 | [maml_trainer] epoch #303 | Finished meta-testing... 2025-04-09 16:05:39 | [maml_trainer] epoch #303 | Saving snapshot... 2025-04-09 16:06:00 | [maml_trainer] epoch #303 | Saved 2025-04-09 16:06:00 | [maml_trainer] epoch #303 | Time 516404.49 s 2025-04-09 16:06:00 | [maml_trainer] epoch #303 | EpochTime 1669.99 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.6435 Average/AverageReturn -50.0157 Average/Iteration 303 Average/MaxReturn -35.2054 Average/MinReturn -172.974 Average/NumEpisodes 120 Average/StdReturn 12.5192 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.83751 GaussianMLPPolicy/KLAfter 0.00561018 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.88774e-05 GaussianMLPPolicy/LossBefore 8.0665e-09 GaussianMLPPolicy/dLoss 1.88855e-05 Iteration 303 MetaTest/Average/AverageDiscountedReturn -49.103 MetaTest/Average/AverageReturn -49.103 MetaTest/Average/Iteration 303 MetaTest/Average/MaxReturn -43.2332 MetaTest/Average/MinReturn -56.9792 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.70519 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.103 MetaTest/__unnamed_task__/AverageReturn -49.103 MetaTest/__unnamed_task__/Iteration 303 MetaTest/__unnamed_task__/MaxReturn -43.2332 MetaTest/__unnamed_task__/MinReturn -56.9792 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.70519 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4592e+07 __unnamed_task__/AverageDiscountedReturn -27.6435 __unnamed_task__/AverageReturn -50.0157 __unnamed_task__/Iteration 303 __unnamed_task__/MaxReturn -35.2054 __unnamed_task__/MinReturn -172.974 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.5192 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 16:29:24 | [maml_trainer] epoch #304 | Sampling for adapation and meta-testing... 2025-04-09 16:33:16 | [maml_trainer] epoch #304 | Finished meta-testing... 2025-04-09 16:33:16 | [maml_trainer] epoch #304 | Saving snapshot... 2025-04-09 16:33:37 | [maml_trainer] epoch #304 | Saved 2025-04-09 16:33:37 | [maml_trainer] epoch #304 | Time 518061.86 s 2025-04-09 16:33:37 | [maml_trainer] epoch #304 | EpochTime 1657.37 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.4735 Average/AverageReturn -50.0475 Average/Iteration 304 Average/MaxReturn -37.9322 Average/MinReturn -148.979 Average/NumEpisodes 120 Average/StdReturn 11.5478 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.8335 GaussianMLPPolicy/KLAfter 0.00588801 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.58181e-05 GaussianMLPPolicy/LossBefore -1.37488e-08 GaussianMLPPolicy/dLoss -3.58318e-05 Iteration 304 MetaTest/Average/AverageDiscountedReturn -48.1274 MetaTest/Average/AverageReturn -48.1274 MetaTest/Average/Iteration 304 MetaTest/Average/MaxReturn -40.96 MetaTest/Average/MinReturn -64.5883 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.01947 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1274 MetaTest/__unnamed_task__/AverageReturn -48.1274 MetaTest/__unnamed_task__/Iteration 304 MetaTest/__unnamed_task__/MaxReturn -40.96 MetaTest/__unnamed_task__/MinReturn -64.5883 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.01947 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.464e+07 __unnamed_task__/AverageDiscountedReturn -27.4735 __unnamed_task__/AverageReturn -50.0475 __unnamed_task__/Iteration 304 __unnamed_task__/MaxReturn -37.9322 __unnamed_task__/MinReturn -148.979 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.5478 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 16:56:45 | [maml_trainer] epoch #305 | Sampling for adapation and meta-testing... 2025-04-09 17:00:37 | [maml_trainer] epoch #305 | Finished meta-testing... 2025-04-09 17:00:37 | [maml_trainer] epoch #305 | Saving snapshot... 2025-04-09 17:00:57 | [maml_trainer] epoch #305 | Saved 2025-04-09 17:00:57 | [maml_trainer] epoch #305 | Time 519701.67 s 2025-04-09 17:00:57 | [maml_trainer] epoch #305 | EpochTime 1639.80 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.541 Average/AverageReturn -49.2156 Average/Iteration 305 Average/MaxReturn -38.6683 Average/MinReturn -93.3203 Average/NumEpisodes 120 Average/StdReturn 6.71797 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.83035 GaussianMLPPolicy/KLAfter 0.00349265 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.34735e-05 GaussianMLPPolicy/LossBefore -4.13259e-09 GaussianMLPPolicy/dLoss -3.34776e-05 Iteration 305 MetaTest/Average/AverageDiscountedReturn -49.327 MetaTest/Average/AverageReturn -49.327 MetaTest/Average/Iteration 305 MetaTest/Average/MaxReturn -42.9457 MetaTest/Average/MinReturn -61.3962 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.78991 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.327 MetaTest/__unnamed_task__/AverageReturn -49.327 MetaTest/__unnamed_task__/Iteration 305 MetaTest/__unnamed_task__/MaxReturn -42.9457 MetaTest/__unnamed_task__/MinReturn -61.3962 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.78991 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4688e+07 __unnamed_task__/AverageDiscountedReturn -27.541 __unnamed_task__/AverageReturn -49.2156 __unnamed_task__/Iteration 305 __unnamed_task__/MaxReturn -38.6683 __unnamed_task__/MinReturn -93.3203 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.71797 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 17:24:11 | [maml_trainer] epoch #306 | Sampling for adapation and meta-testing... 2025-04-09 17:28:05 | [maml_trainer] epoch #306 | Finished meta-testing... 2025-04-09 17:28:05 | [maml_trainer] epoch #306 | Saving snapshot... 2025-04-09 17:28:26 | [maml_trainer] epoch #306 | Saved 2025-04-09 17:28:26 | [maml_trainer] epoch #306 | Time 521350.41 s 2025-04-09 17:28:26 | [maml_trainer] epoch #306 | EpochTime 1648.74 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.4808 Average/AverageReturn -48.6592 Average/Iteration 306 Average/MaxReturn -37.898 Average/MinReturn -61.8893 Average/NumEpisodes 120 Average/StdReturn 4.6246 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.82694 GaussianMLPPolicy/KLAfter 0.00278436 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.0318e-05 GaussianMLPPolicy/LossBefore -7.23203e-09 GaussianMLPPolicy/dLoss 3.03108e-05 Iteration 306 MetaTest/Average/AverageDiscountedReturn -51.3009 MetaTest/Average/AverageReturn -51.3009 MetaTest/Average/Iteration 306 MetaTest/Average/MaxReturn -43.872 MetaTest/Average/MinReturn -78.0513 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.23548 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.3009 MetaTest/__unnamed_task__/AverageReturn -51.3009 MetaTest/__unnamed_task__/Iteration 306 MetaTest/__unnamed_task__/MaxReturn -43.872 MetaTest/__unnamed_task__/MinReturn -78.0513 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.23548 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4736e+07 __unnamed_task__/AverageDiscountedReturn -27.4808 __unnamed_task__/AverageReturn -48.6592 __unnamed_task__/Iteration 306 __unnamed_task__/MaxReturn -37.898 __unnamed_task__/MinReturn -61.8893 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.6246 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 17:51:52 | [maml_trainer] epoch #307 | Sampling for adapation and meta-testing... 2025-04-09 17:55:40 | [maml_trainer] epoch #307 | Finished meta-testing... 2025-04-09 17:55:40 | [maml_trainer] epoch #307 | Saving snapshot... 2025-04-09 17:56:02 | [maml_trainer] epoch #307 | Saved 2025-04-09 17:56:02 | [maml_trainer] epoch #307 | Time 523006.25 s 2025-04-09 17:56:02 | [maml_trainer] epoch #307 | EpochTime 1655.83 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.909 Average/AverageReturn -49.5095 Average/Iteration 307 Average/MaxReturn -39.5722 Average/MinReturn -118.274 Average/NumEpisodes 120 Average/StdReturn 7.87854 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.82512 GaussianMLPPolicy/KLAfter 0.00400317 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.24943e-05 GaussianMLPPolicy/LossBefore -5.5631e-10 GaussianMLPPolicy/dLoss 4.24937e-05 Iteration 307 MetaTest/Average/AverageDiscountedReturn -47.8663 MetaTest/Average/AverageReturn -47.8663 MetaTest/Average/Iteration 307 MetaTest/Average/MaxReturn -40.6978 MetaTest/Average/MinReturn -57.6033 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.87443 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.8663 MetaTest/__unnamed_task__/AverageReturn -47.8663 MetaTest/__unnamed_task__/Iteration 307 MetaTest/__unnamed_task__/MaxReturn -40.6978 MetaTest/__unnamed_task__/MinReturn -57.6033 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.87443 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4784e+07 __unnamed_task__/AverageDiscountedReturn -27.909 __unnamed_task__/AverageReturn -49.5095 __unnamed_task__/Iteration 307 __unnamed_task__/MaxReturn -39.5722 __unnamed_task__/MinReturn -118.274 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.87854 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 18:19:36 | [maml_trainer] epoch #308 | Sampling for adapation and meta-testing... 2025-04-09 18:23:29 | [maml_trainer] epoch #308 | Finished meta-testing... 2025-04-09 18:23:29 | [maml_trainer] epoch #308 | Saving snapshot... 2025-04-09 18:23:51 | [maml_trainer] epoch #308 | Saved 2025-04-09 18:23:51 | [maml_trainer] epoch #308 | Time 524674.98 s 2025-04-09 18:23:51 | [maml_trainer] epoch #308 | EpochTime 1668.73 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.8167 Average/AverageReturn -49.8063 Average/Iteration 308 Average/MaxReturn -40.1189 Average/MinReturn -76.2302 Average/NumEpisodes 120 Average/StdReturn 6.05789 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.82389 GaussianMLPPolicy/KLAfter 0.00389338 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.6718e-05 GaussianMLPPolicy/LossBefore 1.72059e-08 GaussianMLPPolicy/dLoss 1.67352e-05 Iteration 308 MetaTest/Average/AverageDiscountedReturn -46.5333 MetaTest/Average/AverageReturn -46.5333 MetaTest/Average/Iteration 308 MetaTest/Average/MaxReturn -41.0288 MetaTest/Average/MinReturn -51.9707 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.22733 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.5333 MetaTest/__unnamed_task__/AverageReturn -46.5333 MetaTest/__unnamed_task__/Iteration 308 MetaTest/__unnamed_task__/MaxReturn -41.0288 MetaTest/__unnamed_task__/MinReturn -51.9707 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.22733 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4832e+07 __unnamed_task__/AverageDiscountedReturn -27.8167 __unnamed_task__/AverageReturn -49.8063 __unnamed_task__/Iteration 308 __unnamed_task__/MaxReturn -40.1189 __unnamed_task__/MinReturn -76.2302 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.05789 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 18:47:11 | [maml_trainer] epoch #309 | Sampling for adapation and meta-testing... 2025-04-09 18:51:00 | [maml_trainer] epoch #309 | Finished meta-testing... 2025-04-09 18:51:00 | [maml_trainer] epoch #309 | Saving snapshot... 2025-04-09 18:51:21 | [maml_trainer] epoch #309 | Saved 2025-04-09 18:51:21 | [maml_trainer] epoch #309 | Time 526325.00 s 2025-04-09 18:51:21 | [maml_trainer] epoch #309 | EpochTime 1650.01 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.773 Average/AverageReturn -48.6486 Average/Iteration 309 Average/MaxReturn -39.6957 Average/MinReturn -65.9791 Average/NumEpisodes 120 Average/StdReturn 4.87028 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.82256 GaussianMLPPolicy/KLAfter 0.00348301 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000135588 GaussianMLPPolicy/LossBefore -4.41074e-09 GaussianMLPPolicy/dLoss -0.000135592 Iteration 309 MetaTest/Average/AverageDiscountedReturn -46.901 MetaTest/Average/AverageReturn -46.901 MetaTest/Average/Iteration 309 MetaTest/Average/MaxReturn -41.5719 MetaTest/Average/MinReturn -54.7417 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.52704 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.901 MetaTest/__unnamed_task__/AverageReturn -46.901 MetaTest/__unnamed_task__/Iteration 309 MetaTest/__unnamed_task__/MaxReturn -41.5719 MetaTest/__unnamed_task__/MinReturn -54.7417 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.52704 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.488e+07 __unnamed_task__/AverageDiscountedReturn -27.773 __unnamed_task__/AverageReturn -48.6486 __unnamed_task__/Iteration 309 __unnamed_task__/MaxReturn -39.6957 __unnamed_task__/MinReturn -65.9791 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.87028 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 19:14:19 | [maml_trainer] epoch #310 | Sampling for adapation and meta-testing... 2025-04-09 19:18:09 | [maml_trainer] epoch #310 | Finished meta-testing... 2025-04-09 19:18:09 | [maml_trainer] epoch #310 | Saving snapshot... 2025-04-09 19:18:29 | [maml_trainer] epoch #310 | Saved 2025-04-09 19:18:29 | [maml_trainer] epoch #310 | Time 527953.67 s 2025-04-09 19:18:29 | [maml_trainer] epoch #310 | EpochTime 1628.67 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.9675 Average/AverageReturn -48.9213 Average/Iteration 310 Average/MaxReturn -28.3573 Average/MinReturn -69.1885 Average/NumEpisodes 120 Average/StdReturn 5.68002 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.8197 GaussianMLPPolicy/KLAfter 0.00133294 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.49466e-06 GaussianMLPPolicy/LossBefore 1.02917e-08 GaussianMLPPolicy/dLoss -3.48437e-06 Iteration 310 MetaTest/Average/AverageDiscountedReturn -48.1356 MetaTest/Average/AverageReturn -48.1356 MetaTest/Average/Iteration 310 MetaTest/Average/MaxReturn -40.8584 MetaTest/Average/MinReturn -62.1198 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.52934 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1356 MetaTest/__unnamed_task__/AverageReturn -48.1356 MetaTest/__unnamed_task__/Iteration 310 MetaTest/__unnamed_task__/MaxReturn -40.8584 MetaTest/__unnamed_task__/MinReturn -62.1198 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.52934 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4928e+07 __unnamed_task__/AverageDiscountedReturn -27.9675 __unnamed_task__/AverageReturn -48.9213 __unnamed_task__/Iteration 310 __unnamed_task__/MaxReturn -28.3573 __unnamed_task__/MinReturn -69.1885 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.68002 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 19:41:23 | [maml_trainer] epoch #311 | Sampling for adapation and meta-testing... 2025-04-09 19:45:11 | [maml_trainer] epoch #311 | Finished meta-testing... 2025-04-09 19:45:11 | [maml_trainer] epoch #311 | Saving snapshot... 2025-04-09 19:45:32 | [maml_trainer] epoch #311 | Saved 2025-04-09 19:45:32 | [maml_trainer] epoch #311 | Time 529576.42 s 2025-04-09 19:45:32 | [maml_trainer] epoch #311 | EpochTime 1622.74 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.8155 Average/AverageReturn -48.7036 Average/Iteration 311 Average/MaxReturn -40.8717 Average/MinReturn -82.5289 Average/NumEpisodes 120 Average/StdReturn 5.40684 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81716 GaussianMLPPolicy/KLAfter 0.00135241 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.73656e-05 GaussianMLPPolicy/LossBefore -9.97384e-09 GaussianMLPPolicy/dLoss -3.73755e-05 Iteration 311 MetaTest/Average/AverageDiscountedReturn -48.4168 MetaTest/Average/AverageReturn -48.4168 MetaTest/Average/Iteration 311 MetaTest/Average/MaxReturn -41.7705 MetaTest/Average/MinReturn -60.7484 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.11815 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.4168 MetaTest/__unnamed_task__/AverageReturn -48.4168 MetaTest/__unnamed_task__/Iteration 311 MetaTest/__unnamed_task__/MaxReturn -41.7705 MetaTest/__unnamed_task__/MinReturn -60.7484 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.11815 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.4976e+07 __unnamed_task__/AverageDiscountedReturn -27.8155 __unnamed_task__/AverageReturn -48.7036 __unnamed_task__/Iteration 311 __unnamed_task__/MaxReturn -40.8717 __unnamed_task__/MinReturn -82.5289 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.40684 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 20:08:40 | [maml_trainer] epoch #312 | Sampling for adapation and meta-testing... 2025-04-09 20:12:33 | [maml_trainer] epoch #312 | Finished meta-testing... 2025-04-09 20:12:33 | [maml_trainer] epoch #312 | Saving snapshot... 2025-04-09 20:12:53 | [maml_trainer] epoch #312 | Saved 2025-04-09 20:12:53 | [maml_trainer] epoch #312 | Time 531217.76 s 2025-04-09 20:12:53 | [maml_trainer] epoch #312 | EpochTime 1641.34 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.166 Average/AverageReturn -49.4382 Average/Iteration 312 Average/MaxReturn -39.0396 Average/MinReturn -78.5957 Average/NumEpisodes 120 Average/StdReturn 5.12367 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81458 GaussianMLPPolicy/KLAfter 0.00115265 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.1744e-05 GaussianMLPPolicy/LossBefore -3.13918e-09 GaussianMLPPolicy/dLoss 6.17409e-05 Iteration 312 MetaTest/Average/AverageDiscountedReturn -48.9259 MetaTest/Average/AverageReturn -48.9259 MetaTest/Average/Iteration 312 MetaTest/Average/MaxReturn -39.6444 MetaTest/Average/MinReturn -61.2597 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.18456 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9259 MetaTest/__unnamed_task__/AverageReturn -48.9259 MetaTest/__unnamed_task__/Iteration 312 MetaTest/__unnamed_task__/MaxReturn -39.6444 MetaTest/__unnamed_task__/MinReturn -61.2597 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.18456 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5024e+07 __unnamed_task__/AverageDiscountedReturn -28.166 __unnamed_task__/AverageReturn -49.4382 __unnamed_task__/Iteration 312 __unnamed_task__/MaxReturn -39.0396 __unnamed_task__/MinReturn -78.5957 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.12367 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 20:35:52 | [maml_trainer] epoch #313 | Sampling for adapation and meta-testing... 2025-04-09 20:39:41 | [maml_trainer] epoch #313 | Finished meta-testing... 2025-04-09 20:39:41 | [maml_trainer] epoch #313 | Saving snapshot... 2025-04-09 20:40:01 | [maml_trainer] epoch #313 | Saved 2025-04-09 20:40:01 | [maml_trainer] epoch #313 | Time 532845.78 s 2025-04-09 20:40:01 | [maml_trainer] epoch #313 | EpochTime 1628.01 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.6974 Average/AverageReturn -48.5032 Average/Iteration 313 Average/MaxReturn -39.1361 Average/MinReturn -64.4651 Average/NumEpisodes 120 Average/StdReturn 4.73379 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.81215 GaussianMLPPolicy/KLAfter 0.0011516 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.43742e-05 GaussianMLPPolicy/LossBefore -5.32468e-09 GaussianMLPPolicy/dLoss 1.43689e-05 Iteration 313 MetaTest/Average/AverageDiscountedReturn -50.1114 MetaTest/Average/AverageReturn -50.1114 MetaTest/Average/Iteration 313 MetaTest/Average/MaxReturn -42.1314 MetaTest/Average/MinReturn -61.7244 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.71427 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.1114 MetaTest/__unnamed_task__/AverageReturn -50.1114 MetaTest/__unnamed_task__/Iteration 313 MetaTest/__unnamed_task__/MaxReturn -42.1314 MetaTest/__unnamed_task__/MinReturn -61.7244 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.71427 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5072e+07 __unnamed_task__/AverageDiscountedReturn -27.6974 __unnamed_task__/AverageReturn -48.5032 __unnamed_task__/Iteration 313 __unnamed_task__/MaxReturn -39.1361 __unnamed_task__/MinReturn -64.4651 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.73379 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 21:02:52 | [maml_trainer] epoch #314 | Sampling for adapation and meta-testing... 2025-04-09 21:06:48 | [maml_trainer] epoch #314 | Finished meta-testing... 2025-04-09 21:06:48 | [maml_trainer] epoch #314 | Saving snapshot... 2025-04-09 21:07:10 | [maml_trainer] epoch #314 | Saved 2025-04-09 21:07:10 | [maml_trainer] epoch #314 | Time 534473.98 s 2025-04-09 21:07:10 | [maml_trainer] epoch #314 | EpochTime 1628.20 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.5821 Average/AverageReturn -48.5143 Average/Iteration 314 Average/MaxReturn -40.5111 Average/MinReturn -60.6104 Average/NumEpisodes 120 Average/StdReturn 4.30856 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.80983 GaussianMLPPolicy/KLAfter 0.00122925 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000116118 GaussianMLPPolicy/LossBefore 1.10467e-08 GaussianMLPPolicy/dLoss 0.000116129 Iteration 314 MetaTest/Average/AverageDiscountedReturn -48.7797 MetaTest/Average/AverageReturn -48.7797 MetaTest/Average/Iteration 314 MetaTest/Average/MaxReturn -39.9255 MetaTest/Average/MinReturn -58.1924 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.66646 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.7797 MetaTest/__unnamed_task__/AverageReturn -48.7797 MetaTest/__unnamed_task__/Iteration 314 MetaTest/__unnamed_task__/MaxReturn -39.9255 MetaTest/__unnamed_task__/MinReturn -58.1924 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.66646 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.512e+07 __unnamed_task__/AverageDiscountedReturn -27.5821 __unnamed_task__/AverageReturn -48.5143 __unnamed_task__/Iteration 314 __unnamed_task__/MaxReturn -40.5111 __unnamed_task__/MinReturn -60.6104 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.30856 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 21:30:25 | [maml_trainer] epoch #315 | Sampling for adapation and meta-testing... 2025-04-09 21:34:18 | [maml_trainer] epoch #315 | Finished meta-testing... 2025-04-09 21:34:18 | [maml_trainer] epoch #315 | Saving snapshot... 2025-04-09 21:34:40 | [maml_trainer] epoch #315 | Saved 2025-04-09 21:34:40 | [maml_trainer] epoch #315 | Time 536124.83 s 2025-04-09 21:34:40 | [maml_trainer] epoch #315 | EpochTime 1650.85 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.4121 Average/AverageReturn -50.5 Average/Iteration 315 Average/MaxReturn -40.5755 Average/MinReturn -101.82 Average/NumEpisodes 120 Average/StdReturn 8.57065 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.80692 GaussianMLPPolicy/KLAfter 0.000818868 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.00618e-05 GaussianMLPPolicy/LossBefore 7.82808e-09 GaussianMLPPolicy/dLoss 4.00696e-05 Iteration 315 MetaTest/Average/AverageDiscountedReturn -46.9649 MetaTest/Average/AverageReturn -46.9649 MetaTest/Average/Iteration 315 MetaTest/Average/MaxReturn -40.1447 MetaTest/Average/MinReturn -59.7469 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.6597 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.9649 MetaTest/__unnamed_task__/AverageReturn -46.9649 MetaTest/__unnamed_task__/Iteration 315 MetaTest/__unnamed_task__/MaxReturn -40.1447 MetaTest/__unnamed_task__/MinReturn -59.7469 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.6597 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5168e+07 __unnamed_task__/AverageDiscountedReturn -28.4121 __unnamed_task__/AverageReturn -50.5 __unnamed_task__/Iteration 315 __unnamed_task__/MaxReturn -40.5755 __unnamed_task__/MinReturn -101.82 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.57065 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 21:57:57 | [maml_trainer] epoch #316 | Sampling for adapation and meta-testing... 2025-04-09 22:01:49 | [maml_trainer] epoch #316 | Finished meta-testing... 2025-04-09 22:01:49 | [maml_trainer] epoch #316 | Saving snapshot... 2025-04-09 22:02:10 | [maml_trainer] epoch #316 | Saved 2025-04-09 22:02:10 | [maml_trainer] epoch #316 | Time 537774.87 s 2025-04-09 22:02:10 | [maml_trainer] epoch #316 | EpochTime 1650.04 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.9429 Average/AverageReturn -49.0744 Average/Iteration 316 Average/MaxReturn -19.9619 Average/MinReturn -66.6264 Average/NumEpisodes 120 Average/StdReturn 5.33786 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.80458 GaussianMLPPolicy/KLAfter 0.000614073 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.06728e-06 GaussianMLPPolicy/LossBefore -6.95387e-09 GaussianMLPPolicy/dLoss 7.06033e-06 Iteration 316 MetaTest/Average/AverageDiscountedReturn -48.1477 MetaTest/Average/AverageReturn -48.1477 MetaTest/Average/Iteration 316 MetaTest/Average/MaxReturn -43.5424 MetaTest/Average/MinReturn -55.9286 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.74069 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1477 MetaTest/__unnamed_task__/AverageReturn -48.1477 MetaTest/__unnamed_task__/Iteration 316 MetaTest/__unnamed_task__/MaxReturn -43.5424 MetaTest/__unnamed_task__/MinReturn -55.9286 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.74069 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5216e+07 __unnamed_task__/AverageDiscountedReturn -27.9429 __unnamed_task__/AverageReturn -49.0744 __unnamed_task__/Iteration 316 __unnamed_task__/MaxReturn -19.9619 __unnamed_task__/MinReturn -66.6264 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.33786 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 22:25:27 | [maml_trainer] epoch #317 | Sampling for adapation and meta-testing... 2025-04-09 22:29:18 | [maml_trainer] epoch #317 | Finished meta-testing... 2025-04-09 22:29:18 | [maml_trainer] epoch #317 | Saving snapshot... 2025-04-09 22:29:40 | [maml_trainer] epoch #317 | Saved 2025-04-09 22:29:40 | [maml_trainer] epoch #317 | Time 539424.42 s 2025-04-09 22:29:40 | [maml_trainer] epoch #317 | EpochTime 1649.54 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.2763 Average/AverageReturn -50.4668 Average/Iteration 317 Average/MaxReturn -40.4743 Average/MinReturn -104.348 Average/NumEpisodes 120 Average/StdReturn 8.11673 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.80352 GaussianMLPPolicy/KLAfter 0.00192482 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.05457e-06 GaussianMLPPolicy/LossBefore 5.96046e-10 GaussianMLPPolicy/dLoss -2.05398e-06 Iteration 317 MetaTest/Average/AverageDiscountedReturn -49.9519 MetaTest/Average/AverageReturn -49.9519 MetaTest/Average/Iteration 317 MetaTest/Average/MaxReturn -41.888 MetaTest/Average/MinReturn -66.2888 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.0156 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.9519 MetaTest/__unnamed_task__/AverageReturn -49.9519 MetaTest/__unnamed_task__/Iteration 317 MetaTest/__unnamed_task__/MaxReturn -41.888 MetaTest/__unnamed_task__/MinReturn -66.2888 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.0156 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5264e+07 __unnamed_task__/AverageDiscountedReturn -28.2763 __unnamed_task__/AverageReturn -50.4668 __unnamed_task__/Iteration 317 __unnamed_task__/MaxReturn -40.4743 __unnamed_task__/MinReturn -104.348 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.11673 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-09 22:52:35 | [maml_trainer] epoch #318 | Sampling for adapation and meta-testing... 2025-04-09 22:56:26 | [maml_trainer] epoch #318 | Finished meta-testing... 2025-04-09 22:56:26 | [maml_trainer] epoch #318 | Saving snapshot... 2025-04-09 22:56:48 | [maml_trainer] epoch #318 | Saved 2025-04-09 22:56:48 | [maml_trainer] epoch #318 | Time 541051.98 s 2025-04-09 22:56:48 | [maml_trainer] epoch #318 | EpochTime 1627.56 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.3098 Average/AverageReturn -49.6881 Average/Iteration 318 Average/MaxReturn -41.5239 Average/MinReturn -66.5557 Average/NumEpisodes 120 Average/StdReturn 5.66451 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.80054 GaussianMLPPolicy/KLAfter 0.00142553 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.48565e-05 GaussianMLPPolicy/LossBefore 1.03315e-09 GaussianMLPPolicy/dLoss -4.48554e-05 Iteration 318 MetaTest/Average/AverageDiscountedReturn -47.3771 MetaTest/Average/AverageReturn -47.3771 MetaTest/Average/Iteration 318 MetaTest/Average/MaxReturn -23.7403 MetaTest/Average/MinReturn -59.3939 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.38295 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.3771 MetaTest/__unnamed_task__/AverageReturn -47.3771 MetaTest/__unnamed_task__/Iteration 318 MetaTest/__unnamed_task__/MaxReturn -23.7403 MetaTest/__unnamed_task__/MinReturn -59.3939 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.38295 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5312e+07 __unnamed_task__/AverageDiscountedReturn -28.3098 __unnamed_task__/AverageReturn -49.6881 __unnamed_task__/Iteration 318 __unnamed_task__/MaxReturn -41.5239 __unnamed_task__/MinReturn -66.5557 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.66451 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 23:19:51 | [maml_trainer] epoch #319 | Sampling for adapation and meta-testing... 2025-04-09 23:23:42 | [maml_trainer] epoch #319 | Finished meta-testing... 2025-04-09 23:23:42 | [maml_trainer] epoch #319 | Saving snapshot... 2025-04-09 23:24:03 | [maml_trainer] epoch #319 | Saved 2025-04-09 23:24:03 | [maml_trainer] epoch #319 | Time 542687.67 s 2025-04-09 23:24:03 | [maml_trainer] epoch #319 | EpochTime 1635.69 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.1834 Average/AverageReturn -49.2963 Average/Iteration 319 Average/MaxReturn -40.0543 Average/MinReturn -64.6422 Average/NumEpisodes 120 Average/StdReturn 4.69928 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.79704 GaussianMLPPolicy/KLAfter 0.00118412 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.40821e-05 GaussianMLPPolicy/LossBefore 8.22544e-09 GaussianMLPPolicy/dLoss 1.40903e-05 Iteration 319 MetaTest/Average/AverageDiscountedReturn -48.4965 MetaTest/Average/AverageReturn -48.4965 MetaTest/Average/Iteration 319 MetaTest/Average/MaxReturn -43.0421 MetaTest/Average/MinReturn -60.7143 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.82871 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.4965 MetaTest/__unnamed_task__/AverageReturn -48.4965 MetaTest/__unnamed_task__/Iteration 319 MetaTest/__unnamed_task__/MaxReturn -43.0421 MetaTest/__unnamed_task__/MinReturn -60.7143 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.82871 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.536e+07 __unnamed_task__/AverageDiscountedReturn -28.1834 __unnamed_task__/AverageReturn -49.2963 __unnamed_task__/Iteration 319 __unnamed_task__/MaxReturn -40.0543 __unnamed_task__/MinReturn -64.6422 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.69928 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-09 23:47:20 | [maml_trainer] epoch #320 | Sampling for adapation and meta-testing... 2025-04-09 23:51:08 | [maml_trainer] epoch #320 | Finished meta-testing... 2025-04-09 23:51:08 | [maml_trainer] epoch #320 | Saving snapshot... 2025-04-09 23:51:28 | [maml_trainer] epoch #320 | Saved 2025-04-09 23:51:28 | [maml_trainer] epoch #320 | Time 544332.83 s 2025-04-09 23:51:28 | [maml_trainer] epoch #320 | EpochTime 1645.15 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.5541 Average/AverageReturn -50.4466 Average/Iteration 320 Average/MaxReturn -41.9554 Average/MinReturn -108.378 Average/NumEpisodes 120 Average/StdReturn 7.24352 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.79413 GaussianMLPPolicy/KLAfter 0.00141039 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.25041e-05 GaussianMLPPolicy/LossBefore 1.98682e-09 GaussianMLPPolicy/dLoss 3.25061e-05 Iteration 320 MetaTest/Average/AverageDiscountedReturn -50.5686 MetaTest/Average/AverageReturn -50.5686 MetaTest/Average/Iteration 320 MetaTest/Average/MaxReturn -43.7113 MetaTest/Average/MinReturn -64.0862 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.1625 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5686 MetaTest/__unnamed_task__/AverageReturn -50.5686 MetaTest/__unnamed_task__/Iteration 320 MetaTest/__unnamed_task__/MaxReturn -43.7113 MetaTest/__unnamed_task__/MinReturn -64.0862 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.1625 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5408e+07 __unnamed_task__/AverageDiscountedReturn -28.5541 __unnamed_task__/AverageReturn -50.4466 __unnamed_task__/Iteration 320 __unnamed_task__/MaxReturn -41.9554 __unnamed_task__/MinReturn -108.378 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.24352 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 00:14:39 | [maml_trainer] epoch #321 | Sampling for adapation and meta-testing... 2025-04-10 00:18:31 | [maml_trainer] epoch #321 | Finished meta-testing... 2025-04-10 00:18:31 | [maml_trainer] epoch #321 | Saving snapshot... 2025-04-10 00:18:52 | [maml_trainer] epoch #321 | Saved 2025-04-10 00:18:52 | [maml_trainer] epoch #321 | Time 545976.25 s 2025-04-10 00:18:52 | [maml_trainer] epoch #321 | EpochTime 1643.41 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.9938 Average/AverageReturn -48.6746 Average/Iteration 321 Average/MaxReturn -39.8114 Average/MinReturn -73.2399 Average/NumEpisodes 120 Average/StdReturn 5.21137 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.79191 GaussianMLPPolicy/KLAfter 0.00137778 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.85831e-05 GaussianMLPPolicy/LossBefore 1.12057e-08 GaussianMLPPolicy/dLoss -4.85719e-05 Iteration 321 MetaTest/Average/AverageDiscountedReturn -49.3972 MetaTest/Average/AverageReturn -49.3972 MetaTest/Average/Iteration 321 MetaTest/Average/MaxReturn -40.4729 MetaTest/Average/MinReturn -60.0459 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.78592 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.3972 MetaTest/__unnamed_task__/AverageReturn -49.3972 MetaTest/__unnamed_task__/Iteration 321 MetaTest/__unnamed_task__/MaxReturn -40.4729 MetaTest/__unnamed_task__/MinReturn -60.0459 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.78592 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5456e+07 __unnamed_task__/AverageDiscountedReturn -27.9938 __unnamed_task__/AverageReturn -48.6746 __unnamed_task__/Iteration 321 __unnamed_task__/MaxReturn -39.8114 __unnamed_task__/MinReturn -73.2399 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.21137 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 00:41:49 | [maml_trainer] epoch #322 | Sampling for adapation and meta-testing... 2025-04-10 00:45:36 | [maml_trainer] epoch #322 | Finished meta-testing... 2025-04-10 00:45:36 | [maml_trainer] epoch #322 | Saving snapshot... 2025-04-10 00:45:58 | [maml_trainer] epoch #322 | Saved 2025-04-10 00:45:58 | [maml_trainer] epoch #322 | Time 547602.56 s 2025-04-10 00:45:58 | [maml_trainer] epoch #322 | EpochTime 1626.31 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.9568 Average/AverageReturn -51.1436 Average/Iteration 322 Average/MaxReturn -40.9545 Average/MinReturn -79.3995 Average/NumEpisodes 120 Average/StdReturn 6.73153 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.79014 GaussianMLPPolicy/KLAfter 0.000991551 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.45834e-05 GaussianMLPPolicy/LossBefore -4.88758e-09 GaussianMLPPolicy/dLoss -8.45883e-05 Iteration 322 MetaTest/Average/AverageDiscountedReturn -57.1051 MetaTest/Average/AverageReturn -57.1051 MetaTest/Average/Iteration 322 MetaTest/Average/MaxReturn -40.8436 MetaTest/Average/MinReturn -157.831 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.917 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -57.1051 MetaTest/__unnamed_task__/AverageReturn -57.1051 MetaTest/__unnamed_task__/Iteration 322 MetaTest/__unnamed_task__/MaxReturn -40.8436 MetaTest/__unnamed_task__/MinReturn -157.831 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.917 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5504e+07 __unnamed_task__/AverageDiscountedReturn -28.9568 __unnamed_task__/AverageReturn -51.1436 __unnamed_task__/Iteration 322 __unnamed_task__/MaxReturn -40.9545 __unnamed_task__/MinReturn -79.3995 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.73153 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 01:08:48 | [maml_trainer] epoch #323 | Sampling for adapation and meta-testing... 2025-04-10 01:12:39 | [maml_trainer] epoch #323 | Finished meta-testing... 2025-04-10 01:12:39 | [maml_trainer] epoch #323 | Saving snapshot... 2025-04-10 01:13:01 | [maml_trainer] epoch #323 | Saved 2025-04-10 01:13:01 | [maml_trainer] epoch #323 | Time 549225.18 s 2025-04-10 01:13:01 | [maml_trainer] epoch #323 | EpochTime 1622.61 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.5042 Average/AverageReturn -50.1699 Average/Iteration 323 Average/MaxReturn -39.1193 Average/MinReturn -86.5068 Average/NumEpisodes 120 Average/StdReturn 5.98316 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.78795 GaussianMLPPolicy/KLAfter 0.000823584 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.21056e-05 GaussianMLPPolicy/LossBefore 1.3868e-08 GaussianMLPPolicy/dLoss 3.21194e-05 Iteration 323 MetaTest/Average/AverageDiscountedReturn -55.1664 MetaTest/Average/AverageReturn -55.1664 MetaTest/Average/Iteration 323 MetaTest/Average/MaxReturn -41.0702 MetaTest/Average/MinReturn -164.471 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.5671 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.1664 MetaTest/__unnamed_task__/AverageReturn -55.1664 MetaTest/__unnamed_task__/Iteration 323 MetaTest/__unnamed_task__/MaxReturn -41.0702 MetaTest/__unnamed_task__/MinReturn -164.471 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.5671 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5552e+07 __unnamed_task__/AverageDiscountedReturn -28.5042 __unnamed_task__/AverageReturn -50.1699 __unnamed_task__/Iteration 323 __unnamed_task__/MaxReturn -39.1193 __unnamed_task__/MinReturn -86.5068 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.98316 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 01:36:09 | [maml_trainer] epoch #324 | Sampling for adapation and meta-testing... 2025-04-10 01:39:57 | [maml_trainer] epoch #324 | Finished meta-testing... 2025-04-10 01:39:57 | [maml_trainer] epoch #324 | Saving snapshot... 2025-04-10 01:40:19 | [maml_trainer] epoch #324 | Saved 2025-04-10 01:40:19 | [maml_trainer] epoch #324 | Time 550863.14 s 2025-04-10 01:40:19 | [maml_trainer] epoch #324 | EpochTime 1637.96 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.8588 Average/AverageReturn -50.7787 Average/Iteration 324 Average/MaxReturn -40.904 Average/MinReturn -82.363 Average/NumEpisodes 120 Average/StdReturn 6.25395 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.78732 GaussianMLPPolicy/KLAfter 0.00114626 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.00042e-05 GaussianMLPPolicy/LossBefore -3.69549e-09 GaussianMLPPolicy/dLoss 9.00005e-05 Iteration 324 MetaTest/Average/AverageDiscountedReturn -49.8347 MetaTest/Average/AverageReturn -49.8347 MetaTest/Average/Iteration 324 MetaTest/Average/MaxReturn -43.1957 MetaTest/Average/MinReturn -69.8567 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.59161 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8347 MetaTest/__unnamed_task__/AverageReturn -49.8347 MetaTest/__unnamed_task__/Iteration 324 MetaTest/__unnamed_task__/MaxReturn -43.1957 MetaTest/__unnamed_task__/MinReturn -69.8567 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.59161 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.56e+07 __unnamed_task__/AverageDiscountedReturn -28.8588 __unnamed_task__/AverageReturn -50.7787 __unnamed_task__/Iteration 324 __unnamed_task__/MaxReturn -40.904 __unnamed_task__/MinReturn -82.363 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.25395 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 02:03:21 | [maml_trainer] epoch #325 | Sampling for adapation and meta-testing... 2025-04-10 02:07:15 | [maml_trainer] epoch #325 | Finished meta-testing... 2025-04-10 02:07:15 | [maml_trainer] epoch #325 | Saving snapshot... 2025-04-10 02:07:37 | [maml_trainer] epoch #325 | Saved 2025-04-10 02:07:37 | [maml_trainer] epoch #325 | Time 552501.64 s 2025-04-10 02:07:37 | [maml_trainer] epoch #325 | EpochTime 1638.50 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.0843 Average/AverageReturn -48.7862 Average/Iteration 325 Average/MaxReturn -40.0531 Average/MinReturn -65.0957 Average/NumEpisodes 120 Average/StdReturn 4.69157 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.78759 GaussianMLPPolicy/KLAfter 0.00270296 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.74927e-05 GaussianMLPPolicy/LossBefore -1.11659e-08 GaussianMLPPolicy/dLoss -6.75039e-05 Iteration 325 MetaTest/Average/AverageDiscountedReturn -50.8461 MetaTest/Average/AverageReturn -50.8461 MetaTest/Average/Iteration 325 MetaTest/Average/MaxReturn -42.4328 MetaTest/Average/MinReturn -59.6953 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.38259 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.8461 MetaTest/__unnamed_task__/AverageReturn -50.8461 MetaTest/__unnamed_task__/Iteration 325 MetaTest/__unnamed_task__/MaxReturn -42.4328 MetaTest/__unnamed_task__/MinReturn -59.6953 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.38259 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5648e+07 __unnamed_task__/AverageDiscountedReturn -28.0843 __unnamed_task__/AverageReturn -48.7862 __unnamed_task__/Iteration 325 __unnamed_task__/MaxReturn -40.0531 __unnamed_task__/MinReturn -65.0957 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.69157 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 02:31:05 | [maml_trainer] epoch #326 | Sampling for adapation and meta-testing... 2025-04-10 02:34:57 | [maml_trainer] epoch #326 | Finished meta-testing... 2025-04-10 02:34:57 | [maml_trainer] epoch #326 | Saving snapshot... 2025-04-10 02:35:19 | [maml_trainer] epoch #326 | Saved 2025-04-10 02:35:19 | [maml_trainer] epoch #326 | Time 554163.84 s 2025-04-10 02:35:19 | [maml_trainer] epoch #326 | EpochTime 1662.19 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -28.4548 Average/AverageReturn -50.6804 Average/Iteration 326 Average/MaxReturn -40.2213 Average/MinReturn -123.592 Average/NumEpisodes 120 Average/StdReturn 8.68516 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.78873 GaussianMLPPolicy/KLAfter 0.00223398 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.49662e-05 GaussianMLPPolicy/LossBefore -5.80152e-09 GaussianMLPPolicy/dLoss 4.49604e-05 Iteration 326 MetaTest/Average/AverageDiscountedReturn -50.0578 MetaTest/Average/AverageReturn -50.0578 MetaTest/Average/Iteration 326 MetaTest/Average/MaxReturn -42.5623 MetaTest/Average/MinReturn -58.6447 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.62377 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0578 MetaTest/__unnamed_task__/AverageReturn -50.0578 MetaTest/__unnamed_task__/Iteration 326 MetaTest/__unnamed_task__/MaxReturn -42.5623 MetaTest/__unnamed_task__/MinReturn -58.6447 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.62377 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5696e+07 __unnamed_task__/AverageDiscountedReturn -28.4548 __unnamed_task__/AverageReturn -50.6804 __unnamed_task__/Iteration 326 __unnamed_task__/MaxReturn -40.2213 __unnamed_task__/MinReturn -123.592 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.68516 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 02:58:28 | [maml_trainer] epoch #327 | Sampling for adapation and meta-testing... 2025-04-10 03:02:19 | [maml_trainer] epoch #327 | Finished meta-testing... 2025-04-10 03:02:19 | [maml_trainer] epoch #327 | Saving snapshot... 2025-04-10 03:02:41 | [maml_trainer] epoch #327 | Saved 2025-04-10 03:02:41 | [maml_trainer] epoch #327 | Time 555805.14 s 2025-04-10 03:02:41 | [maml_trainer] epoch #327 | EpochTime 1641.30 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.4046 Average/AverageReturn -49.8677 Average/Iteration 327 Average/MaxReturn -41.7436 Average/MinReturn -74.4111 Average/NumEpisodes 120 Average/StdReturn 5.93408 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.78988 GaussianMLPPolicy/KLAfter 0.00193486 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.1155e-05 GaussianMLPPolicy/LossBefore 8.30491e-09 GaussianMLPPolicy/dLoss -2.11467e-05 Iteration 327 MetaTest/Average/AverageDiscountedReturn -49.817 MetaTest/Average/AverageReturn -49.817 MetaTest/Average/Iteration 327 MetaTest/Average/MaxReturn -43.9217 MetaTest/Average/MinReturn -57.3454 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.5962 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.817 MetaTest/__unnamed_task__/AverageReturn -49.817 MetaTest/__unnamed_task__/Iteration 327 MetaTest/__unnamed_task__/MaxReturn -43.9217 MetaTest/__unnamed_task__/MinReturn -57.3454 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.5962 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5744e+07 __unnamed_task__/AverageDiscountedReturn -28.4046 __unnamed_task__/AverageReturn -49.8677 __unnamed_task__/Iteration 327 __unnamed_task__/MaxReturn -41.7436 __unnamed_task__/MinReturn -74.4111 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.93408 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 03:53:09 | [maml_trainer] epoch #328 | Sampling for adapation and meta-testing... 2025-04-10 04:02:50 | [maml_trainer] epoch #328 | Finished meta-testing... 2025-04-10 04:02:50 | [maml_trainer] epoch #328 | Saving snapshot... 2025-04-10 04:03:39 | [maml_trainer] epoch #328 | Saved 2025-04-10 04:03:39 | [maml_trainer] epoch #328 | Time 559463.66 s 2025-04-10 04:03:39 | [maml_trainer] epoch #328 | EpochTime 3658.51 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.1596 Average/AverageReturn -49.1912 Average/Iteration 328 Average/MaxReturn -40.5991 Average/MinReturn -65.9819 Average/NumEpisodes 120 Average/StdReturn 5.19057 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.79062 GaussianMLPPolicy/KLAfter 0.00165614 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.52652e-05 GaussianMLPPolicy/LossBefore -5.28494e-09 GaussianMLPPolicy/dLoss 4.52599e-05 Iteration 328 MetaTest/Average/AverageDiscountedReturn -47.8255 MetaTest/Average/AverageReturn -47.8255 MetaTest/Average/Iteration 328 MetaTest/Average/MaxReturn -41.9097 MetaTest/Average/MinReturn -57.8147 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.55548 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.8255 MetaTest/__unnamed_task__/AverageReturn -47.8255 MetaTest/__unnamed_task__/Iteration 328 MetaTest/__unnamed_task__/MaxReturn -41.9097 MetaTest/__unnamed_task__/MinReturn -57.8147 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.55548 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5792e+07 __unnamed_task__/AverageDiscountedReturn -28.1596 __unnamed_task__/AverageReturn -49.1912 __unnamed_task__/Iteration 328 __unnamed_task__/MaxReturn -40.5991 __unnamed_task__/MinReturn -65.9819 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.19057 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 05:00:46 | [maml_trainer] epoch #329 | Sampling for adapation and meta-testing... 2025-04-10 05:09:49 | [maml_trainer] epoch #329 | Finished meta-testing... 2025-04-10 05:09:49 | [maml_trainer] epoch #329 | Saving snapshot... 2025-04-10 05:10:55 | [maml_trainer] epoch #329 | Saved 2025-04-10 05:10:55 | [maml_trainer] epoch #329 | Time 563499.22 s 2025-04-10 05:10:55 | [maml_trainer] epoch #329 | EpochTime 4035.56 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.5295 Average/AverageReturn -50.0785 Average/Iteration 329 Average/MaxReturn -41.1459 Average/MinReturn -68.1184 Average/NumEpisodes 120 Average/StdReturn 5.17596 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.79125 GaussianMLPPolicy/KLAfter 0.00374429 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.10536e-05 GaussianMLPPolicy/LossBefore 3.17891e-09 GaussianMLPPolicy/dLoss 7.10568e-05 Iteration 329 MetaTest/Average/AverageDiscountedReturn -47.2637 MetaTest/Average/AverageReturn -47.2637 MetaTest/Average/Iteration 329 MetaTest/Average/MaxReturn -43.1479 MetaTest/Average/MinReturn -54.2962 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 2.80012 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.2637 MetaTest/__unnamed_task__/AverageReturn -47.2637 MetaTest/__unnamed_task__/Iteration 329 MetaTest/__unnamed_task__/MaxReturn -43.1479 MetaTest/__unnamed_task__/MinReturn -54.2962 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 2.80012 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.584e+07 __unnamed_task__/AverageDiscountedReturn -28.5295 __unnamed_task__/AverageReturn -50.0785 __unnamed_task__/Iteration 329 __unnamed_task__/MaxReturn -41.1459 __unnamed_task__/MinReturn -68.1184 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.17596 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 05:48:04 | [maml_trainer] epoch #330 | Sampling for adapation and meta-testing... 2025-04-10 05:52:46 | [maml_trainer] epoch #330 | Finished meta-testing... 2025-04-10 05:52:46 | [maml_trainer] epoch #330 | Saving snapshot... 2025-04-10 05:53:08 | [maml_trainer] epoch #330 | Saved 2025-04-10 05:53:08 | [maml_trainer] epoch #330 | Time 566031.99 s 2025-04-10 05:53:08 | [maml_trainer] epoch #330 | EpochTime 2532.76 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.1954 Average/AverageReturn -49.2518 Average/Iteration 330 Average/MaxReturn -39.8271 Average/MinReturn -65.9496 Average/NumEpisodes 120 Average/StdReturn 4.4446 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.79126 GaussianMLPPolicy/KLAfter 0.00447978 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.9987e-05 GaussianMLPPolicy/LossBefore -3.61602e-09 GaussianMLPPolicy/dLoss -8.99907e-05 Iteration 330 MetaTest/Average/AverageDiscountedReturn -50.478 MetaTest/Average/AverageReturn -50.478 MetaTest/Average/Iteration 330 MetaTest/Average/MaxReturn -43.7745 MetaTest/Average/MinReturn -63.1525 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.2218 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.478 MetaTest/__unnamed_task__/AverageReturn -50.478 MetaTest/__unnamed_task__/Iteration 330 MetaTest/__unnamed_task__/MaxReturn -43.7745 MetaTest/__unnamed_task__/MinReturn -63.1525 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.2218 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5888e+07 __unnamed_task__/AverageDiscountedReturn -28.1954 __unnamed_task__/AverageReturn -49.2518 __unnamed_task__/Iteration 330 __unnamed_task__/MaxReturn -39.8271 __unnamed_task__/MinReturn -65.9496 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.4446 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 06:16:18 | [maml_trainer] epoch #331 | Sampling for adapation and meta-testing... 2025-04-10 06:20:09 | [maml_trainer] epoch #331 | Finished meta-testing... 2025-04-10 06:20:09 | [maml_trainer] epoch #331 | Saving snapshot... 2025-04-10 06:20:30 | [maml_trainer] epoch #331 | Saved 2025-04-10 06:20:30 | [maml_trainer] epoch #331 | Time 567674.51 s 2025-04-10 06:20:30 | [maml_trainer] epoch #331 | EpochTime 1642.52 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.931 Average/AverageReturn -49.2678 Average/Iteration 331 Average/MaxReturn -42.3299 Average/MinReturn -64.5102 Average/NumEpisodes 120 Average/StdReturn 4.34228 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.79134 GaussianMLPPolicy/KLAfter 0.00569084 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.9758e-05 GaussianMLPPolicy/LossBefore -2.86102e-09 GaussianMLPPolicy/dLoss 4.97551e-05 Iteration 331 MetaTest/Average/AverageDiscountedReturn -48.1913 MetaTest/Average/AverageReturn -48.1913 MetaTest/Average/Iteration 331 MetaTest/Average/MaxReturn -42.6202 MetaTest/Average/MinReturn -55.8029 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.41871 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1913 MetaTest/__unnamed_task__/AverageReturn -48.1913 MetaTest/__unnamed_task__/Iteration 331 MetaTest/__unnamed_task__/MaxReturn -42.6202 MetaTest/__unnamed_task__/MinReturn -55.8029 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.41871 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5936e+07 __unnamed_task__/AverageDiscountedReturn -27.931 __unnamed_task__/AverageReturn -49.2678 __unnamed_task__/Iteration 331 __unnamed_task__/MaxReturn -42.3299 __unnamed_task__/MinReturn -64.5102 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.34228 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 06:43:53 | [maml_trainer] epoch #332 | Sampling for adapation and meta-testing... 2025-04-10 06:47:47 | [maml_trainer] epoch #332 | Finished meta-testing... 2025-04-10 06:47:47 | [maml_trainer] epoch #332 | Saving snapshot... 2025-04-10 06:48:08 | [maml_trainer] epoch #332 | Saved 2025-04-10 06:48:08 | [maml_trainer] epoch #332 | Time 569332.17 s 2025-04-10 06:48:08 | [maml_trainer] epoch #332 | EpochTime 1657.65 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -28.3426 Average/AverageReturn -50.6164 Average/Iteration 332 Average/MaxReturn -43.4737 Average/MinReturn -69.6072 Average/NumEpisodes 120 Average/StdReturn 4.74619 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.7906 GaussianMLPPolicy/KLAfter 0.00453074 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.98009e-05 GaussianMLPPolicy/LossBefore 4.09285e-09 GaussianMLPPolicy/dLoss 6.9805e-05 Iteration 332 MetaTest/Average/AverageDiscountedReturn -51.1091 MetaTest/Average/AverageReturn -51.1091 MetaTest/Average/Iteration 332 MetaTest/Average/MaxReturn -44.34 MetaTest/Average/MinReturn -65.4998 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.47079 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.1091 MetaTest/__unnamed_task__/AverageReturn -51.1091 MetaTest/__unnamed_task__/Iteration 332 MetaTest/__unnamed_task__/MaxReturn -44.34 MetaTest/__unnamed_task__/MinReturn -65.4998 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.47079 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.5984e+07 __unnamed_task__/AverageDiscountedReturn -28.3426 __unnamed_task__/AverageReturn -50.6164 __unnamed_task__/Iteration 332 __unnamed_task__/MaxReturn -43.4737 __unnamed_task__/MinReturn -69.6072 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.74619 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 07:11:27 | [maml_trainer] epoch #333 | Sampling for adapation and meta-testing... 2025-04-10 07:15:19 | [maml_trainer] epoch #333 | Finished meta-testing... 2025-04-10 07:15:19 | [maml_trainer] epoch #333 | Saving snapshot... 2025-04-10 07:15:40 | [maml_trainer] epoch #333 | Saved 2025-04-10 07:15:40 | [maml_trainer] epoch #333 | Time 570984.76 s 2025-04-10 07:15:40 | [maml_trainer] epoch #333 | EpochTime 1652.59 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.9262 Average/AverageReturn -49.3443 Average/Iteration 333 Average/MaxReturn -41.203 Average/MinReturn -63.0138 Average/NumEpisodes 120 Average/StdReturn 4.37436 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.79041 GaussianMLPPolicy/KLAfter 0.00377982 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.88489e-05 GaussianMLPPolicy/LossBefore -2.06629e-09 GaussianMLPPolicy/dLoss -4.8851e-05 Iteration 333 MetaTest/Average/AverageDiscountedReturn -49.8123 MetaTest/Average/AverageReturn -49.8123 MetaTest/Average/Iteration 333 MetaTest/Average/MaxReturn -44.5652 MetaTest/Average/MinReturn -59.6028 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.31855 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8123 MetaTest/__unnamed_task__/AverageReturn -49.8123 MetaTest/__unnamed_task__/Iteration 333 MetaTest/__unnamed_task__/MaxReturn -44.5652 MetaTest/__unnamed_task__/MinReturn -59.6028 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.31855 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6032e+07 __unnamed_task__/AverageDiscountedReturn -27.9262 __unnamed_task__/AverageReturn -49.3443 __unnamed_task__/Iteration 333 __unnamed_task__/MaxReturn -41.203 __unnamed_task__/MinReturn -63.0138 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.37436 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 07:39:08 | [maml_trainer] epoch #334 | Sampling for adapation and meta-testing... 2025-04-10 07:43:02 | [maml_trainer] epoch #334 | Finished meta-testing... 2025-04-10 07:43:02 | [maml_trainer] epoch #334 | Saving snapshot... 2025-04-10 07:43:23 | [maml_trainer] epoch #334 | Saved 2025-04-10 07:43:23 | [maml_trainer] epoch #334 | Time 572647.57 s 2025-04-10 07:43:23 | [maml_trainer] epoch #334 | EpochTime 1662.80 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.822 Average/AverageReturn -49.7049 Average/Iteration 334 Average/MaxReturn -41.9628 Average/MinReturn -67.413 Average/NumEpisodes 120 Average/StdReturn 4.34189 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.78958 GaussianMLPPolicy/KLAfter 0.00260069 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.67725e-05 GaussianMLPPolicy/LossBefore 1.27157e-08 GaussianMLPPolicy/dLoss 7.67852e-05 Iteration 334 MetaTest/Average/AverageDiscountedReturn -47.463 MetaTest/Average/AverageReturn -47.463 MetaTest/Average/Iteration 334 MetaTest/Average/MaxReturn -38.7175 MetaTest/Average/MinReturn -55.3572 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.08291 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.463 MetaTest/__unnamed_task__/AverageReturn -47.463 MetaTest/__unnamed_task__/Iteration 334 MetaTest/__unnamed_task__/MaxReturn -38.7175 MetaTest/__unnamed_task__/MinReturn -55.3572 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.08291 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.608e+07 __unnamed_task__/AverageDiscountedReturn -27.822 __unnamed_task__/AverageReturn -49.7049 __unnamed_task__/Iteration 334 __unnamed_task__/MaxReturn -41.9628 __unnamed_task__/MinReturn -67.413 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.34189 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 08:07:09 | [maml_trainer] epoch #335 | Sampling for adapation and meta-testing... 2025-04-10 08:11:02 | [maml_trainer] epoch #335 | Finished meta-testing... 2025-04-10 08:11:02 | [maml_trainer] epoch #335 | Saving snapshot... 2025-04-10 08:11:23 | [maml_trainer] epoch #335 | Saved 2025-04-10 08:11:23 | [maml_trainer] epoch #335 | Time 574327.04 s 2025-04-10 08:11:23 | [maml_trainer] epoch #335 | EpochTime 1679.47 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.8024 Average/AverageReturn -49.4923 Average/Iteration 335 Average/MaxReturn -42.489 Average/MinReturn -64.1202 Average/NumEpisodes 120 Average/StdReturn 4.13721 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.78875 GaussianMLPPolicy/KLAfter 0.00391874 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.91936e-05 GaussianMLPPolicy/LossBefore -1.85172e-08 GaussianMLPPolicy/dLoss -6.92122e-05 Iteration 335 MetaTest/Average/AverageDiscountedReturn -48.4308 MetaTest/Average/AverageReturn -48.4308 MetaTest/Average/Iteration 335 MetaTest/Average/MaxReturn -40.9707 MetaTest/Average/MinReturn -57.7171 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.27567 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.4308 MetaTest/__unnamed_task__/AverageReturn -48.4308 MetaTest/__unnamed_task__/Iteration 335 MetaTest/__unnamed_task__/MaxReturn -40.9707 MetaTest/__unnamed_task__/MinReturn -57.7171 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.27567 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6128e+07 __unnamed_task__/AverageDiscountedReturn -27.8024 __unnamed_task__/AverageReturn -49.4923 __unnamed_task__/Iteration 335 __unnamed_task__/MaxReturn -42.489 __unnamed_task__/MinReturn -64.1202 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.13721 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 08:34:55 | [maml_trainer] epoch #336 | Sampling for adapation and meta-testing... 2025-04-10 08:38:49 | [maml_trainer] epoch #336 | Finished meta-testing... 2025-04-10 08:38:49 | [maml_trainer] epoch #336 | Saving snapshot... 2025-04-10 08:39:10 | [maml_trainer] epoch #336 | Saved 2025-04-10 08:39:10 | [maml_trainer] epoch #336 | Time 575994.55 s 2025-04-10 08:39:10 | [maml_trainer] epoch #336 | EpochTime 1667.51 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.6179 Average/AverageReturn -49.2039 Average/Iteration 336 Average/MaxReturn -42.3664 Average/MinReturn -63.0145 Average/NumEpisodes 120 Average/StdReturn 4.15857 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.78775 GaussianMLPPolicy/KLAfter 0.00542487 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.41526e-05 GaussianMLPPolicy/LossBefore 1.1007e-08 GaussianMLPPolicy/dLoss 3.41636e-05 Iteration 336 MetaTest/Average/AverageDiscountedReturn -51.2222 MetaTest/Average/AverageReturn -51.2222 MetaTest/Average/Iteration 336 MetaTest/Average/MaxReturn -44.0734 MetaTest/Average/MinReturn -58.471 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.62711 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2222 MetaTest/__unnamed_task__/AverageReturn -51.2222 MetaTest/__unnamed_task__/Iteration 336 MetaTest/__unnamed_task__/MaxReturn -44.0734 MetaTest/__unnamed_task__/MinReturn -58.471 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.62711 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6176e+07 __unnamed_task__/AverageDiscountedReturn -27.6179 __unnamed_task__/AverageReturn -49.2039 __unnamed_task__/Iteration 336 __unnamed_task__/MaxReturn -42.3664 __unnamed_task__/MinReturn -63.0145 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.15857 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 09:02:31 | [maml_trainer] epoch #337 | Sampling for adapation and meta-testing... 2025-04-10 09:06:28 | [maml_trainer] epoch #337 | Finished meta-testing... 2025-04-10 09:06:28 | [maml_trainer] epoch #337 | Saving snapshot... 2025-04-10 09:06:49 | [maml_trainer] epoch #337 | Saved 2025-04-10 09:06:49 | [maml_trainer] epoch #337 | Time 577653.81 s 2025-04-10 09:06:49 | [maml_trainer] epoch #337 | EpochTime 1659.26 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.5145 Average/AverageReturn -48.5155 Average/Iteration 337 Average/MaxReturn -41.0935 Average/MinReturn -68.3906 Average/NumEpisodes 120 Average/StdReturn 4.55022 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.7863 GaussianMLPPolicy/KLAfter 0.00237572 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000101747 GaussianMLPPolicy/LossBefore -3.13918e-09 GaussianMLPPolicy/dLoss 0.000101743 Iteration 337 MetaTest/Average/AverageDiscountedReturn -45.7733 MetaTest/Average/AverageReturn -45.7733 MetaTest/Average/Iteration 337 MetaTest/Average/MaxReturn -40.4649 MetaTest/Average/MinReturn -55.5923 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.79776 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.7733 MetaTest/__unnamed_task__/AverageReturn -45.7733 MetaTest/__unnamed_task__/Iteration 337 MetaTest/__unnamed_task__/MaxReturn -40.4649 MetaTest/__unnamed_task__/MinReturn -55.5923 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.79776 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6224e+07 __unnamed_task__/AverageDiscountedReturn -27.5145 __unnamed_task__/AverageReturn -48.5155 __unnamed_task__/Iteration 337 __unnamed_task__/MaxReturn -41.0935 __unnamed_task__/MinReturn -68.3906 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.55022 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 09:30:30 | [maml_trainer] epoch #338 | Sampling for adapation and meta-testing... 2025-04-10 09:34:22 | [maml_trainer] epoch #338 | Finished meta-testing... 2025-04-10 09:34:22 | [maml_trainer] epoch #338 | Saving snapshot... 2025-04-10 09:34:43 | [maml_trainer] epoch #338 | Saved 2025-04-10 09:34:43 | [maml_trainer] epoch #338 | Time 579327.49 s 2025-04-10 09:34:43 | [maml_trainer] epoch #338 | EpochTime 1673.67 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.8596 Average/AverageReturn -49.571 Average/Iteration 338 Average/MaxReturn -41.5215 Average/MinReturn -91.0577 Average/NumEpisodes 120 Average/StdReturn 6.05628 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.78479 GaussianMLPPolicy/KLAfter 0.0026097 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.65436e-05 GaussianMLPPolicy/LossBefore -5.5631e-09 GaussianMLPPolicy/dLoss -3.65492e-05 Iteration 338 MetaTest/Average/AverageDiscountedReturn -48.1693 MetaTest/Average/AverageReturn -48.1693 MetaTest/Average/Iteration 338 MetaTest/Average/MaxReturn -43.0881 MetaTest/Average/MinReturn -54.6262 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.56521 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1693 MetaTest/__unnamed_task__/AverageReturn -48.1693 MetaTest/__unnamed_task__/Iteration 338 MetaTest/__unnamed_task__/MaxReturn -43.0881 MetaTest/__unnamed_task__/MinReturn -54.6262 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.56521 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6272e+07 __unnamed_task__/AverageDiscountedReturn -27.8596 __unnamed_task__/AverageReturn -49.571 __unnamed_task__/Iteration 338 __unnamed_task__/MaxReturn -41.5215 __unnamed_task__/MinReturn -91.0577 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.05628 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 09:57:57 | [maml_trainer] epoch #339 | Sampling for adapation and meta-testing... 2025-04-10 10:01:51 | [maml_trainer] epoch #339 | Finished meta-testing... 2025-04-10 10:01:51 | [maml_trainer] epoch #339 | Saving snapshot... 2025-04-10 10:02:12 | [maml_trainer] epoch #339 | Saved 2025-04-10 10:02:12 | [maml_trainer] epoch #339 | Time 580976.34 s 2025-04-10 10:02:12 | [maml_trainer] epoch #339 | EpochTime 1648.85 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.2203 Average/AverageReturn -47.7864 Average/Iteration 339 Average/MaxReturn -40.7535 Average/MinReturn -60.7291 Average/NumEpisodes 120 Average/StdReturn 4.40551 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.7828 GaussianMLPPolicy/KLAfter 0.00254717 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.69165e-05 GaussianMLPPolicy/LossBefore 1.0848e-08 GaussianMLPPolicy/dLoss -3.69057e-05 Iteration 339 MetaTest/Average/AverageDiscountedReturn -48.2726 MetaTest/Average/AverageReturn -48.2726 MetaTest/Average/Iteration 339 MetaTest/Average/MaxReturn -42.5993 MetaTest/Average/MinReturn -54.4183 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.86496 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.2726 MetaTest/__unnamed_task__/AverageReturn -48.2726 MetaTest/__unnamed_task__/Iteration 339 MetaTest/__unnamed_task__/MaxReturn -42.5993 MetaTest/__unnamed_task__/MinReturn -54.4183 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.86496 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.632e+07 __unnamed_task__/AverageDiscountedReturn -27.2203 __unnamed_task__/AverageReturn -47.7864 __unnamed_task__/Iteration 339 __unnamed_task__/MaxReturn -40.7535 __unnamed_task__/MinReturn -60.7291 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.40551 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 10:25:45 | [maml_trainer] epoch #340 | Sampling for adapation and meta-testing... 2025-04-10 10:29:42 | [maml_trainer] epoch #340 | Finished meta-testing... 2025-04-10 10:29:42 | [maml_trainer] epoch #340 | Saving snapshot... 2025-04-10 10:30:04 | [maml_trainer] epoch #340 | Saved 2025-04-10 10:30:04 | [maml_trainer] epoch #340 | Time 582648.04 s 2025-04-10 10:30:04 | [maml_trainer] epoch #340 | EpochTime 1671.70 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.1036 Average/AverageReturn -48.1035 Average/Iteration 340 Average/MaxReturn -18.2123 Average/MinReturn -104.007 Average/NumEpisodes 120 Average/StdReturn 7.88071 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.78079 GaussianMLPPolicy/KLAfter 0.00440122 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.4764e-05 GaussianMLPPolicy/LossBefore -5.64257e-09 GaussianMLPPolicy/dLoss 2.47584e-05 Iteration 340 MetaTest/Average/AverageDiscountedReturn -48.204 MetaTest/Average/AverageReturn -48.204 MetaTest/Average/Iteration 340 MetaTest/Average/MaxReturn -41.4605 MetaTest/Average/MinReturn -58.866 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.1114 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.204 MetaTest/__unnamed_task__/AverageReturn -48.204 MetaTest/__unnamed_task__/Iteration 340 MetaTest/__unnamed_task__/MaxReturn -41.4605 MetaTest/__unnamed_task__/MinReturn -58.866 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.1114 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6368e+07 __unnamed_task__/AverageDiscountedReturn -27.1036 __unnamed_task__/AverageReturn -48.1035 __unnamed_task__/Iteration 340 __unnamed_task__/MaxReturn -18.2123 __unnamed_task__/MinReturn -104.007 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.88071 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 10:53:49 | [maml_trainer] epoch #341 | Sampling for adapation and meta-testing... 2025-04-10 10:57:48 | [maml_trainer] epoch #341 | Finished meta-testing... 2025-04-10 10:57:48 | [maml_trainer] epoch #341 | Saving snapshot... 2025-04-10 10:58:10 | [maml_trainer] epoch #341 | Saved 2025-04-10 10:58:10 | [maml_trainer] epoch #341 | Time 584334.01 s 2025-04-10 10:58:10 | [maml_trainer] epoch #341 | EpochTime 1685.96 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.8224 Average/AverageReturn -46.2784 Average/Iteration 341 Average/MaxReturn 260.167 Average/MinReturn -160.594 Average/NumEpisodes 120 Average/StdReturn 30.4718 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77972 GaussianMLPPolicy/KLAfter 0.00314349 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.50273e-05 GaussianMLPPolicy/LossBefore -4.07795e-09 GaussianMLPPolicy/dLoss -1.50314e-05 Iteration 341 MetaTest/Average/AverageDiscountedReturn -46.0123 MetaTest/Average/AverageReturn -46.0123 MetaTest/Average/Iteration 341 MetaTest/Average/MaxReturn -41.5247 MetaTest/Average/MinReturn -52.6271 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.35698 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.0123 MetaTest/__unnamed_task__/AverageReturn -46.0123 MetaTest/__unnamed_task__/Iteration 341 MetaTest/__unnamed_task__/MaxReturn -41.5247 MetaTest/__unnamed_task__/MinReturn -52.6271 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.35698 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6416e+07 __unnamed_task__/AverageDiscountedReturn -26.8224 __unnamed_task__/AverageReturn -46.2784 __unnamed_task__/Iteration 341 __unnamed_task__/MaxReturn 260.167 __unnamed_task__/MinReturn -160.594 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 30.4718 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 11:21:44 | [maml_trainer] epoch #342 | Sampling for adapation and meta-testing... 2025-04-10 11:25:41 | [maml_trainer] epoch #342 | Finished meta-testing... 2025-04-10 11:25:41 | [maml_trainer] epoch #342 | Saving snapshot... 2025-04-10 11:26:03 | [maml_trainer] epoch #342 | Saved 2025-04-10 11:26:03 | [maml_trainer] epoch #342 | Time 586007.93 s 2025-04-10 11:26:03 | [maml_trainer] epoch #342 | EpochTime 1673.92 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.8311 Average/AverageReturn -48.53 Average/Iteration 342 Average/MaxReturn -34.4779 Average/MinReturn -122.396 Average/NumEpisodes 120 Average/StdReturn 11.5824 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77931 GaussianMLPPolicy/KLAfter 0.00334503 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.34233e-05 GaussianMLPPolicy/LossBefore 4.84784e-09 GaussianMLPPolicy/dLoss 8.34281e-05 Iteration 342 MetaTest/Average/AverageDiscountedReturn -56.6738 MetaTest/Average/AverageReturn -56.6738 MetaTest/Average/Iteration 342 MetaTest/Average/MaxReturn -39.0753 MetaTest/Average/MinReturn -168.915 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 35.5374 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -56.6738 MetaTest/__unnamed_task__/AverageReturn -56.6738 MetaTest/__unnamed_task__/Iteration 342 MetaTest/__unnamed_task__/MaxReturn -39.0753 MetaTest/__unnamed_task__/MinReturn -168.915 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 35.5374 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6464e+07 __unnamed_task__/AverageDiscountedReturn -26.8311 __unnamed_task__/AverageReturn -48.53 __unnamed_task__/Iteration 342 __unnamed_task__/MaxReturn -34.4779 __unnamed_task__/MinReturn -122.396 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.5824 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 11:49:55 | [maml_trainer] epoch #343 | Sampling for adapation and meta-testing... 2025-04-10 11:53:53 | [maml_trainer] epoch #343 | Finished meta-testing... 2025-04-10 11:53:53 | [maml_trainer] epoch #343 | Saving snapshot... 2025-04-10 11:54:14 | [maml_trainer] epoch #343 | Saved 2025-04-10 11:54:14 | [maml_trainer] epoch #343 | Time 587698.49 s 2025-04-10 11:54:14 | [maml_trainer] epoch #343 | EpochTime 1690.56 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.3684 Average/AverageReturn -45.3781 Average/Iteration 343 Average/MaxReturn 236.89 Average/MinReturn -92.2394 Average/NumEpisodes 120 Average/StdReturn 26.7517 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77893 GaussianMLPPolicy/KLAfter 0.00340214 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.17932e-05 GaussianMLPPolicy/LossBefore 5.5333e-09 GaussianMLPPolicy/dLoss -5.17877e-05 Iteration 343 MetaTest/Average/AverageDiscountedReturn -45.8721 MetaTest/Average/AverageReturn -45.8721 MetaTest/Average/Iteration 343 MetaTest/Average/MaxReturn -38.3481 MetaTest/Average/MinReturn -57.021 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.07325 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.8721 MetaTest/__unnamed_task__/AverageReturn -45.8721 MetaTest/__unnamed_task__/Iteration 343 MetaTest/__unnamed_task__/MaxReturn -38.3481 MetaTest/__unnamed_task__/MinReturn -57.021 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.07325 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6512e+07 __unnamed_task__/AverageDiscountedReturn -26.3684 __unnamed_task__/AverageReturn -45.3781 __unnamed_task__/Iteration 343 __unnamed_task__/MaxReturn 236.89 __unnamed_task__/MinReturn -92.2394 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 26.7517 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 12:18:06 | [maml_trainer] epoch #344 | Sampling for adapation and meta-testing... 2025-04-10 12:22:01 | [maml_trainer] epoch #344 | Finished meta-testing... 2025-04-10 12:22:01 | [maml_trainer] epoch #344 | Saving snapshot... 2025-04-10 12:22:21 | [maml_trainer] epoch #344 | Saved 2025-04-10 12:22:21 | [maml_trainer] epoch #344 | Time 589385.73 s 2025-04-10 12:22:21 | [maml_trainer] epoch #344 | EpochTime 1687.23 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.8145 Average/AverageReturn -42.8209 Average/Iteration 344 Average/MaxReturn 491.186 Average/MinReturn -85.8103 Average/NumEpisodes 120 Average/StdReturn 49.2876 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77872 GaussianMLPPolicy/KLAfter 0.00323322 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.3822e-05 GaussianMLPPolicy/LossBefore 5.33462e-09 GaussianMLPPolicy/dLoss -4.38166e-05 Iteration 344 MetaTest/Average/AverageDiscountedReturn -55.0689 MetaTest/Average/AverageReturn -55.0689 MetaTest/Average/Iteration 344 MetaTest/Average/MaxReturn -39.3562 MetaTest/Average/MinReturn -135.411 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.8209 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.0689 MetaTest/__unnamed_task__/AverageReturn -55.0689 MetaTest/__unnamed_task__/Iteration 344 MetaTest/__unnamed_task__/MaxReturn -39.3562 MetaTest/__unnamed_task__/MinReturn -135.411 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.8209 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.656e+07 __unnamed_task__/AverageDiscountedReturn -25.8145 __unnamed_task__/AverageReturn -42.8209 __unnamed_task__/Iteration 344 __unnamed_task__/MaxReturn 491.186 __unnamed_task__/MinReturn -85.8103 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 49.2876 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 12:46:11 | [maml_trainer] epoch #345 | Sampling for adapation and meta-testing... 2025-04-10 12:50:11 | [maml_trainer] epoch #345 | Finished meta-testing... 2025-04-10 12:50:11 | [maml_trainer] epoch #345 | Saving snapshot... 2025-04-10 12:50:32 | [maml_trainer] epoch #345 | Saved 2025-04-10 12:50:32 | [maml_trainer] epoch #345 | Time 591076.57 s 2025-04-10 12:50:32 | [maml_trainer] epoch #345 | EpochTime 1690.84 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.9055 Average/AverageReturn -42.0682 Average/Iteration 345 Average/MaxReturn 506.995 Average/MinReturn -156.581 Average/NumEpisodes 120 Average/StdReturn 56.7 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77895 GaussianMLPPolicy/KLAfter 0.002108 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.29349e-06 GaussianMLPPolicy/LossBefore -6.45717e-11 GaussianMLPPolicy/dLoss 3.29342e-06 Iteration 345 MetaTest/Average/AverageDiscountedReturn -17.4364 MetaTest/Average/AverageReturn -17.4364 MetaTest/Average/Iteration 345 MetaTest/Average/MaxReturn 530.547 MetaTest/Average/MinReturn -54.5433 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 125.794 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -17.4364 MetaTest/__unnamed_task__/AverageReturn -17.4364 MetaTest/__unnamed_task__/Iteration 345 MetaTest/__unnamed_task__/MaxReturn 530.547 MetaTest/__unnamed_task__/MinReturn -54.5433 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 125.794 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6608e+07 __unnamed_task__/AverageDiscountedReturn -25.9055 __unnamed_task__/AverageReturn -42.0682 __unnamed_task__/Iteration 345 __unnamed_task__/MaxReturn 506.995 __unnamed_task__/MinReturn -156.581 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 56.7 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 13:14:26 | [maml_trainer] epoch #346 | Sampling for adapation and meta-testing... 2025-04-10 13:18:21 | [maml_trainer] epoch #346 | Finished meta-testing... 2025-04-10 13:18:21 | [maml_trainer] epoch #346 | Saving snapshot... 2025-04-10 13:18:42 | [maml_trainer] epoch #346 | Saved 2025-04-10 13:18:42 | [maml_trainer] epoch #346 | Time 592766.60 s 2025-04-10 13:18:42 | [maml_trainer] epoch #346 | EpochTime 1690.02 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.3529 Average/AverageReturn -51.7625 Average/Iteration 346 Average/MaxReturn 92.2934 Average/MinReturn -175.713 Average/NumEpisodes 120 Average/StdReturn 27.0521 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77941 GaussianMLPPolicy/KLAfter 0.00288958 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.09317e-05 GaussianMLPPolicy/LossBefore 3.47694e-09 GaussianMLPPolicy/dLoss 6.09352e-05 Iteration 346 MetaTest/Average/AverageDiscountedReturn -56.4182 MetaTest/Average/AverageReturn -56.4182 MetaTest/Average/Iteration 346 MetaTest/Average/MaxReturn -39.679 MetaTest/Average/MinReturn -141.64 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 27.3489 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -56.4182 MetaTest/__unnamed_task__/AverageReturn -56.4182 MetaTest/__unnamed_task__/Iteration 346 MetaTest/__unnamed_task__/MaxReturn -39.679 MetaTest/__unnamed_task__/MinReturn -141.64 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 27.3489 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6656e+07 __unnamed_task__/AverageDiscountedReturn -27.3529 __unnamed_task__/AverageReturn -51.7625 __unnamed_task__/Iteration 346 __unnamed_task__/MaxReturn 92.2934 __unnamed_task__/MinReturn -175.713 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 27.0521 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 13:42:28 | [maml_trainer] epoch #347 | Sampling for adapation and meta-testing... 2025-04-10 13:46:30 | [maml_trainer] epoch #347 | Finished meta-testing... 2025-04-10 13:46:30 | [maml_trainer] epoch #347 | Saving snapshot... 2025-04-10 13:46:51 | [maml_trainer] epoch #347 | Saved 2025-04-10 13:46:51 | [maml_trainer] epoch #347 | Time 594455.89 s 2025-04-10 13:46:51 | [maml_trainer] epoch #347 | EpochTime 1689.29 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.6368 Average/AverageReturn -47.7993 Average/Iteration 347 Average/MaxReturn 265.471 Average/MinReturn -171.585 Average/NumEpisodes 120 Average/StdReturn 33.785 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.7795 GaussianMLPPolicy/KLAfter 0.0023891 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.75993e-06 GaussianMLPPolicy/LossBefore -4.91738e-10 GaussianMLPPolicy/dLoss 5.75944e-06 Iteration 347 MetaTest/Average/AverageDiscountedReturn -47.1089 MetaTest/Average/AverageReturn -47.1089 MetaTest/Average/Iteration 347 MetaTest/Average/MaxReturn -37.9657 MetaTest/Average/MinReturn -68.8369 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.69524 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.1089 MetaTest/__unnamed_task__/AverageReturn -47.1089 MetaTest/__unnamed_task__/Iteration 347 MetaTest/__unnamed_task__/MaxReturn -37.9657 MetaTest/__unnamed_task__/MinReturn -68.8369 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.69524 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6704e+07 __unnamed_task__/AverageDiscountedReturn -26.6368 __unnamed_task__/AverageReturn -47.7993 __unnamed_task__/Iteration 347 __unnamed_task__/MaxReturn 265.471 __unnamed_task__/MinReturn -171.585 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 33.785 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 14:10:55 | [maml_trainer] epoch #348 | Sampling for adapation and meta-testing... 2025-04-10 14:14:55 | [maml_trainer] epoch #348 | Finished meta-testing... 2025-04-10 14:14:55 | [maml_trainer] epoch #348 | Saving snapshot... 2025-04-10 14:15:16 | [maml_trainer] epoch #348 | Saved 2025-04-10 14:15:16 | [maml_trainer] epoch #348 | Time 596160.76 s 2025-04-10 14:15:16 | [maml_trainer] epoch #348 | EpochTime 1704.87 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.5447 Average/AverageReturn -48.5559 Average/Iteration 348 Average/MaxReturn -30.7952 Average/MinReturn -83.7109 Average/NumEpisodes 120 Average/StdReturn 8.53471 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77867 GaussianMLPPolicy/KLAfter 0.00140346 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.40921e-06 GaussianMLPPolicy/LossBefore -2.3524e-08 GaussianMLPPolicy/dLoss -1.43274e-06 Iteration 348 MetaTest/Average/AverageDiscountedReturn -58.244 MetaTest/Average/AverageReturn -58.244 MetaTest/Average/Iteration 348 MetaTest/Average/MaxReturn 44.5969 MetaTest/Average/MinReturn -171.857 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 43.8402 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -58.244 MetaTest/__unnamed_task__/AverageReturn -58.244 MetaTest/__unnamed_task__/Iteration 348 MetaTest/__unnamed_task__/MaxReturn 44.5969 MetaTest/__unnamed_task__/MinReturn -171.857 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 43.8402 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6752e+07 __unnamed_task__/AverageDiscountedReturn -26.5447 __unnamed_task__/AverageReturn -48.5559 __unnamed_task__/Iteration 348 __unnamed_task__/MaxReturn -30.7952 __unnamed_task__/MinReturn -83.7109 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.53471 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 14:39:19 | [maml_trainer] epoch #349 | Sampling for adapation and meta-testing... 2025-04-10 14:43:19 | [maml_trainer] epoch #349 | Finished meta-testing... 2025-04-10 14:43:19 | [maml_trainer] epoch #349 | Saving snapshot... 2025-04-10 14:43:40 | [maml_trainer] epoch #349 | Saved 2025-04-10 14:43:40 | [maml_trainer] epoch #349 | Time 597864.19 s 2025-04-10 14:43:40 | [maml_trainer] epoch #349 | EpochTime 1703.42 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.3248 Average/AverageReturn -46.8097 Average/Iteration 349 Average/MaxReturn 554.352 Average/MinReturn -163.407 Average/NumEpisodes 120 Average/StdReturn 59.0897 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77799 GaussianMLPPolicy/KLAfter 0.00144969 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.80586e-05 GaussianMLPPolicy/LossBefore 3.41733e-09 GaussianMLPPolicy/dLoss 2.8062e-05 Iteration 349 MetaTest/Average/AverageDiscountedReturn -47.9453 MetaTest/Average/AverageReturn -47.9453 MetaTest/Average/Iteration 349 MetaTest/Average/MaxReturn -42.88 MetaTest/Average/MinReturn -60.8222 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.92229 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.9453 MetaTest/__unnamed_task__/AverageReturn -47.9453 MetaTest/__unnamed_task__/Iteration 349 MetaTest/__unnamed_task__/MaxReturn -42.88 MetaTest/__unnamed_task__/MinReturn -60.8222 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.92229 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.68e+07 __unnamed_task__/AverageDiscountedReturn -26.3248 __unnamed_task__/AverageReturn -46.8097 __unnamed_task__/Iteration 349 __unnamed_task__/MaxReturn 554.352 __unnamed_task__/MinReturn -163.407 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 59.0897 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 15:07:37 | [maml_trainer] epoch #350 | Sampling for adapation and meta-testing... 2025-04-10 15:11:39 | [maml_trainer] epoch #350 | Finished meta-testing... 2025-04-10 15:11:39 | [maml_trainer] epoch #350 | Saving snapshot... 2025-04-10 15:12:00 | [maml_trainer] epoch #350 | Saved 2025-04-10 15:12:00 | [maml_trainer] epoch #350 | Time 599564.81 s 2025-04-10 15:12:00 | [maml_trainer] epoch #350 | EpochTime 1700.62 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.0338 Average/AverageReturn -45.8953 Average/Iteration 350 Average/MaxReturn 315.648 Average/MinReturn -164.983 Average/NumEpisodes 120 Average/StdReturn 38.3106 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77792 GaussianMLPPolicy/KLAfter 0.00161964 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.26264e-05 GaussianMLPPolicy/LossBefore -2.111e-09 GaussianMLPPolicy/dLoss -2.26285e-05 Iteration 350 MetaTest/Average/AverageDiscountedReturn -46.8206 MetaTest/Average/AverageReturn -46.8206 MetaTest/Average/Iteration 350 MetaTest/Average/MaxReturn -40.1742 MetaTest/Average/MinReturn -54.8733 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.64404 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.8206 MetaTest/__unnamed_task__/AverageReturn -46.8206 MetaTest/__unnamed_task__/Iteration 350 MetaTest/__unnamed_task__/MaxReturn -40.1742 MetaTest/__unnamed_task__/MinReturn -54.8733 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.64404 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6848e+07 __unnamed_task__/AverageDiscountedReturn -26.0338 __unnamed_task__/AverageReturn -45.8953 __unnamed_task__/Iteration 350 __unnamed_task__/MaxReturn 315.648 __unnamed_task__/MinReturn -164.983 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 38.3106 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 15:38:46 | [maml_trainer] epoch #351 | Sampling for adapation and meta-testing... 2025-04-10 15:44:29 | [maml_trainer] epoch #351 | Finished meta-testing... 2025-04-10 15:44:29 | [maml_trainer] epoch #351 | Saving snapshot... 2025-04-10 15:45:17 | [maml_trainer] epoch #351 | Saved 2025-04-10 15:45:17 | [maml_trainer] epoch #351 | Time 601561.62 s 2025-04-10 15:45:17 | [maml_trainer] epoch #351 | EpochTime 1996.80 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.7309 Average/AverageReturn -49.0293 Average/Iteration 351 Average/MaxReturn -11.8491 Average/MinReturn -135.071 Average/NumEpisodes 120 Average/StdReturn 11.9317 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77715 GaussianMLPPolicy/KLAfter 0.00204304 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.84629e-05 GaussianMLPPolicy/LossBefore 5.88099e-09 GaussianMLPPolicy/dLoss 4.84688e-05 Iteration 351 MetaTest/Average/AverageDiscountedReturn -48.2335 MetaTest/Average/AverageReturn -48.2335 MetaTest/Average/Iteration 351 MetaTest/Average/MaxReturn -42.2676 MetaTest/Average/MinReturn -56.6558 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.51737 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.2335 MetaTest/__unnamed_task__/AverageReturn -48.2335 MetaTest/__unnamed_task__/Iteration 351 MetaTest/__unnamed_task__/MaxReturn -42.2676 MetaTest/__unnamed_task__/MinReturn -56.6558 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.51737 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6896e+07 __unnamed_task__/AverageDiscountedReturn -26.7309 __unnamed_task__/AverageReturn -49.0293 __unnamed_task__/Iteration 351 __unnamed_task__/MaxReturn -11.8491 __unnamed_task__/MinReturn -135.071 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.9317 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 17:05:27 | [maml_trainer] epoch #352 | Sampling for adapation and meta-testing... 2025-04-10 17:17:35 | [maml_trainer] epoch #352 | Finished meta-testing... 2025-04-10 17:17:35 | [maml_trainer] epoch #352 | Saving snapshot... 2025-04-10 17:18:57 | [maml_trainer] epoch #352 | Saved 2025-04-10 17:18:57 | [maml_trainer] epoch #352 | Time 607181.49 s 2025-04-10 17:18:57 | [maml_trainer] epoch #352 | EpochTime 5619.86 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.2693 Average/AverageReturn -47.236 Average/Iteration 352 Average/MaxReturn -39.038 Average/MinReturn -69.3008 Average/NumEpisodes 120 Average/StdReturn 4.95033 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77687 GaussianMLPPolicy/KLAfter 0.00235526 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.16452e-06 GaussianMLPPolicy/LossBefore -4.29154e-09 GaussianMLPPolicy/dLoss -2.16881e-06 Iteration 352 MetaTest/Average/AverageDiscountedReturn -47.4036 MetaTest/Average/AverageReturn -47.4036 MetaTest/Average/Iteration 352 MetaTest/Average/MaxReturn -41.8166 MetaTest/Average/MinReturn -64.7987 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.33684 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4036 MetaTest/__unnamed_task__/AverageReturn -47.4036 MetaTest/__unnamed_task__/Iteration 352 MetaTest/__unnamed_task__/MaxReturn -41.8166 MetaTest/__unnamed_task__/MinReturn -64.7987 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.33684 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6944e+07 __unnamed_task__/AverageDiscountedReturn -26.2693 __unnamed_task__/AverageReturn -47.236 __unnamed_task__/Iteration 352 __unnamed_task__/MaxReturn -39.038 __unnamed_task__/MinReturn -69.3008 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.95033 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 18:19:24 | [maml_trainer] epoch #353 | Sampling for adapation and meta-testing... 2025-04-10 18:29:15 | [maml_trainer] epoch #353 | Finished meta-testing... 2025-04-10 18:29:15 | [maml_trainer] epoch #353 | Saving snapshot... 2025-04-10 18:30:12 | [maml_trainer] epoch #353 | Saved 2025-04-10 18:30:12 | [maml_trainer] epoch #353 | Time 611456.96 s 2025-04-10 18:30:12 | [maml_trainer] epoch #353 | EpochTime 4275.45 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.2737 Average/AverageReturn -47.1847 Average/Iteration 353 Average/MaxReturn -40.7602 Average/MinReturn -64.4095 Average/NumEpisodes 120 Average/StdReturn 4.30525 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77606 GaussianMLPPolicy/KLAfter 0.00305461 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.56491e-05 GaussianMLPPolicy/LossBefore -5.00679e-09 GaussianMLPPolicy/dLoss 4.56441e-05 Iteration 353 MetaTest/Average/AverageDiscountedReturn -49.6879 MetaTest/Average/AverageReturn -49.6879 MetaTest/Average/Iteration 353 MetaTest/Average/MaxReturn -41.45 MetaTest/Average/MinReturn -67.3536 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.88937 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.6879 MetaTest/__unnamed_task__/AverageReturn -49.6879 MetaTest/__unnamed_task__/Iteration 353 MetaTest/__unnamed_task__/MaxReturn -41.45 MetaTest/__unnamed_task__/MinReturn -67.3536 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.88937 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.6992e+07 __unnamed_task__/AverageDiscountedReturn -26.2737 __unnamed_task__/AverageReturn -47.1847 __unnamed_task__/Iteration 353 __unnamed_task__/MaxReturn -40.7602 __unnamed_task__/MinReturn -64.4095 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.30525 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 19:02:02 | [maml_trainer] epoch #354 | Sampling for adapation and meta-testing... 2025-04-10 19:06:01 | [maml_trainer] epoch #354 | Finished meta-testing... 2025-04-10 19:06:01 | [maml_trainer] epoch #354 | Saving snapshot... 2025-04-10 19:06:23 | [maml_trainer] epoch #354 | Saved 2025-04-10 19:06:23 | [maml_trainer] epoch #354 | Time 613627.39 s 2025-04-10 19:06:23 | [maml_trainer] epoch #354 | EpochTime 2170.43 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.445 Average/AverageReturn -48.3626 Average/Iteration 354 Average/MaxReturn -38.5825 Average/MinReturn -122.351 Average/NumEpisodes 120 Average/StdReturn 8.52376 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77416 GaussianMLPPolicy/KLAfter 0.00250503 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.23035e-05 GaussianMLPPolicy/LossBefore -6.0002e-09 GaussianMLPPolicy/dLoss 3.22975e-05 Iteration 354 MetaTest/Average/AverageDiscountedReturn -46.662 MetaTest/Average/AverageReturn -46.662 MetaTest/Average/Iteration 354 MetaTest/Average/MaxReturn -40.3315 MetaTest/Average/MinReturn -60.1771 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.7498 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.662 MetaTest/__unnamed_task__/AverageReturn -46.662 MetaTest/__unnamed_task__/Iteration 354 MetaTest/__unnamed_task__/MaxReturn -40.3315 MetaTest/__unnamed_task__/MinReturn -60.1771 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.7498 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.704e+07 __unnamed_task__/AverageDiscountedReturn -26.445 __unnamed_task__/AverageReturn -48.3626 __unnamed_task__/Iteration 354 __unnamed_task__/MaxReturn -38.5825 __unnamed_task__/MinReturn -122.351 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.52376 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 19:30:19 | [maml_trainer] epoch #355 | Sampling for adapation and meta-testing... 2025-04-10 19:34:21 | [maml_trainer] epoch #355 | Finished meta-testing... 2025-04-10 19:34:21 | [maml_trainer] epoch #355 | Saving snapshot... 2025-04-10 19:34:42 | [maml_trainer] epoch #355 | Saved 2025-04-10 19:34:42 | [maml_trainer] epoch #355 | Time 615326.42 s 2025-04-10 19:34:42 | [maml_trainer] epoch #355 | EpochTime 1699.03 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.8392 Average/AverageReturn -48.5163 Average/Iteration 355 Average/MaxReturn -38.2182 Average/MinReturn -65.7578 Average/NumEpisodes 120 Average/StdReturn 4.7003 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.77126 GaussianMLPPolicy/KLAfter 0.00214973 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000112047 GaussianMLPPolicy/LossBefore 1.11262e-08 GaussianMLPPolicy/dLoss -0.000112036 Iteration 355 MetaTest/Average/AverageDiscountedReturn -47.2316 MetaTest/Average/AverageReturn -47.2316 MetaTest/Average/Iteration 355 MetaTest/Average/MaxReturn -40.1521 MetaTest/Average/MinReturn -52.0328 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.23378 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.2316 MetaTest/__unnamed_task__/AverageReturn -47.2316 MetaTest/__unnamed_task__/Iteration 355 MetaTest/__unnamed_task__/MaxReturn -40.1521 MetaTest/__unnamed_task__/MinReturn -52.0328 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.23378 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7088e+07 __unnamed_task__/AverageDiscountedReturn -26.8392 __unnamed_task__/AverageReturn -48.5163 __unnamed_task__/Iteration 355 __unnamed_task__/MaxReturn -38.2182 __unnamed_task__/MinReturn -65.7578 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.7003 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 19:58:53 | [maml_trainer] epoch #356 | Sampling for adapation and meta-testing... 2025-04-10 20:02:55 | [maml_trainer] epoch #356 | Finished meta-testing... 2025-04-10 20:02:55 | [maml_trainer] epoch #356 | Saving snapshot... 2025-04-10 20:03:17 | [maml_trainer] epoch #356 | Saved 2025-04-10 20:03:17 | [maml_trainer] epoch #356 | Time 617041.52 s 2025-04-10 20:03:17 | [maml_trainer] epoch #356 | EpochTime 1715.09 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.4275 Average/AverageReturn -48.1462 Average/Iteration 356 Average/MaxReturn -39.8005 Average/MinReturn -117.836 Average/NumEpisodes 120 Average/StdReturn 7.74874 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.76875 GaussianMLPPolicy/KLAfter 0.00235676 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.74407e-05 GaussianMLPPolicy/LossBefore -1.01725e-08 GaussianMLPPolicy/dLoss 1.74305e-05 Iteration 356 MetaTest/Average/AverageDiscountedReturn -48.1991 MetaTest/Average/AverageReturn -48.1991 MetaTest/Average/Iteration 356 MetaTest/Average/MaxReturn -40.7087 MetaTest/Average/MinReturn -65.1649 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.12006 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1991 MetaTest/__unnamed_task__/AverageReturn -48.1991 MetaTest/__unnamed_task__/Iteration 356 MetaTest/__unnamed_task__/MaxReturn -40.7087 MetaTest/__unnamed_task__/MinReturn -65.1649 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.12006 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7136e+07 __unnamed_task__/AverageDiscountedReturn -26.4275 __unnamed_task__/AverageReturn -48.1462 __unnamed_task__/Iteration 356 __unnamed_task__/MaxReturn -39.8005 __unnamed_task__/MinReturn -117.836 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.74874 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-10 20:27:25 | [maml_trainer] epoch #357 | Sampling for adapation and meta-testing... 2025-04-10 20:31:28 | [maml_trainer] epoch #357 | Finished meta-testing... 2025-04-10 20:31:28 | [maml_trainer] epoch #357 | Saving snapshot... 2025-04-10 20:31:50 | [maml_trainer] epoch #357 | Saved 2025-04-10 20:31:50 | [maml_trainer] epoch #357 | Time 618754.27 s 2025-04-10 20:31:50 | [maml_trainer] epoch #357 | EpochTime 1712.75 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.6459 Average/AverageReturn -48.3248 Average/Iteration 357 Average/MaxReturn -39.2767 Average/MinReturn -61.8611 Average/NumEpisodes 120 Average/StdReturn 4.44233 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.76566 GaussianMLPPolicy/KLAfter 0.00201794 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.31376e-05 GaussianMLPPolicy/LossBefore -6.03994e-09 GaussianMLPPolicy/dLoss -2.31437e-05 Iteration 357 MetaTest/Average/AverageDiscountedReturn -54.1931 MetaTest/Average/AverageReturn -54.1931 MetaTest/Average/Iteration 357 MetaTest/Average/MaxReturn -44.0156 MetaTest/Average/MinReturn -95.1916 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.7912 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.1931 MetaTest/__unnamed_task__/AverageReturn -54.1931 MetaTest/__unnamed_task__/Iteration 357 MetaTest/__unnamed_task__/MaxReturn -44.0156 MetaTest/__unnamed_task__/MinReturn -95.1916 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.7912 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7184e+07 __unnamed_task__/AverageDiscountedReturn -26.6459 __unnamed_task__/AverageReturn -48.3248 __unnamed_task__/Iteration 357 __unnamed_task__/MaxReturn -39.2767 __unnamed_task__/MinReturn -61.8611 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.44233 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 20:55:49 | [maml_trainer] epoch #358 | Sampling for adapation and meta-testing... 2025-04-10 20:59:46 | [maml_trainer] epoch #358 | Finished meta-testing... 2025-04-10 20:59:46 | [maml_trainer] epoch #358 | Saving snapshot... 2025-04-10 21:00:07 | [maml_trainer] epoch #358 | Saved 2025-04-10 21:00:07 | [maml_trainer] epoch #358 | Time 620451.65 s 2025-04-10 21:00:07 | [maml_trainer] epoch #358 | EpochTime 1697.38 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.4594 Average/AverageReturn -47.8378 Average/Iteration 358 Average/MaxReturn -39.7995 Average/MinReturn -59.7202 Average/NumEpisodes 120 Average/StdReturn 4.02066 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.76232 GaussianMLPPolicy/KLAfter 0.00155588 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.59632e-05 GaussianMLPPolicy/LossBefore -7.15256e-10 GaussianMLPPolicy/dLoss -4.59639e-05 Iteration 358 MetaTest/Average/AverageDiscountedReturn -48.8982 MetaTest/Average/AverageReturn -48.8982 MetaTest/Average/Iteration 358 MetaTest/Average/MaxReturn -41.0996 MetaTest/Average/MinReturn -58.1018 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.73285 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.8982 MetaTest/__unnamed_task__/AverageReturn -48.8982 MetaTest/__unnamed_task__/Iteration 358 MetaTest/__unnamed_task__/MaxReturn -41.0996 MetaTest/__unnamed_task__/MinReturn -58.1018 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.73285 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7232e+07 __unnamed_task__/AverageDiscountedReturn -26.4594 __unnamed_task__/AverageReturn -47.8378 __unnamed_task__/Iteration 358 __unnamed_task__/MaxReturn -39.7995 __unnamed_task__/MinReturn -59.7202 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.02066 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 21:26:10 | [maml_trainer] epoch #359 | Sampling for adapation and meta-testing... 2025-04-10 21:34:20 | [maml_trainer] epoch #359 | Finished meta-testing... 2025-04-10 21:34:20 | [maml_trainer] epoch #359 | Saving snapshot... 2025-04-10 21:35:05 | [maml_trainer] epoch #359 | Saved 2025-04-10 21:35:05 | [maml_trainer] epoch #359 | Time 622549.48 s 2025-04-10 21:35:05 | [maml_trainer] epoch #359 | EpochTime 2097.83 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.5411 Average/AverageReturn -48.1379 Average/Iteration 359 Average/MaxReturn -39.3972 Average/MinReturn -64.3282 Average/NumEpisodes 120 Average/StdReturn 4.16013 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.75909 GaussianMLPPolicy/KLAfter 0.00152738 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.33267e-05 GaussianMLPPolicy/LossBefore 2.30471e-09 GaussianMLPPolicy/dLoss -8.33244e-05 Iteration 359 MetaTest/Average/AverageDiscountedReturn -46.8195 MetaTest/Average/AverageReturn -46.8195 MetaTest/Average/Iteration 359 MetaTest/Average/MaxReturn -43.4162 MetaTest/Average/MinReturn -55.8563 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.30201 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.8195 MetaTest/__unnamed_task__/AverageReturn -46.8195 MetaTest/__unnamed_task__/Iteration 359 MetaTest/__unnamed_task__/MaxReturn -43.4162 MetaTest/__unnamed_task__/MinReturn -55.8563 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.30201 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.728e+07 __unnamed_task__/AverageDiscountedReturn -26.5411 __unnamed_task__/AverageReturn -48.1379 __unnamed_task__/Iteration 359 __unnamed_task__/MaxReturn -39.3972 __unnamed_task__/MinReturn -64.3282 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.16013 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 22:19:03 | [maml_trainer] epoch #360 | Sampling for adapation and meta-testing... 2025-04-10 22:25:52 | [maml_trainer] epoch #360 | Finished meta-testing... 2025-04-10 22:25:52 | [maml_trainer] epoch #360 | Saving snapshot... 2025-04-10 22:26:30 | [maml_trainer] epoch #360 | Saved 2025-04-10 22:26:30 | [maml_trainer] epoch #360 | Time 625634.60 s 2025-04-10 22:26:30 | [maml_trainer] epoch #360 | EpochTime 3085.12 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.6566 Average/AverageReturn -48.1194 Average/Iteration 360 Average/MaxReturn -33.1978 Average/MinReturn -60.0951 Average/NumEpisodes 120 Average/StdReturn 4.01875 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.75694 GaussianMLPPolicy/KLAfter 0.00178989 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.04404e-05 GaussianMLPPolicy/LossBefore 1.10865e-08 GaussianMLPPolicy/dLoss -9.04293e-05 Iteration 360 MetaTest/Average/AverageDiscountedReturn -50.0833 MetaTest/Average/AverageReturn -50.0833 MetaTest/Average/Iteration 360 MetaTest/Average/MaxReturn -41.5464 MetaTest/Average/MinReturn -79.142 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.0338 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0833 MetaTest/__unnamed_task__/AverageReturn -50.0833 MetaTest/__unnamed_task__/Iteration 360 MetaTest/__unnamed_task__/MaxReturn -41.5464 MetaTest/__unnamed_task__/MinReturn -79.142 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.0338 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7328e+07 __unnamed_task__/AverageDiscountedReturn -26.6566 __unnamed_task__/AverageReturn -48.1194 __unnamed_task__/Iteration 360 __unnamed_task__/MaxReturn -33.1978 __unnamed_task__/MinReturn -60.0951 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.01875 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 23:07:17 | [maml_trainer] epoch #361 | Sampling for adapation and meta-testing... 2025-04-10 23:13:59 | [maml_trainer] epoch #361 | Finished meta-testing... 2025-04-10 23:13:59 | [maml_trainer] epoch #361 | Saving snapshot... 2025-04-10 23:14:35 | [maml_trainer] epoch #361 | Saved 2025-04-10 23:14:35 | [maml_trainer] epoch #361 | Time 628519.93 s 2025-04-10 23:14:35 | [maml_trainer] epoch #361 | EpochTime 2885.32 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.2684 Average/AverageReturn -47.2216 Average/Iteration 361 Average/MaxReturn -40.5096 Average/MinReturn -70.7171 Average/NumEpisodes 120 Average/StdReturn 4.45201 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.75369 GaussianMLPPolicy/KLAfter 0.00110998 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.85357e-05 GaussianMLPPolicy/LossBefore -8.5036e-09 GaussianMLPPolicy/dLoss -3.85442e-05 Iteration 361 MetaTest/Average/AverageDiscountedReturn -48.7528 MetaTest/Average/AverageReturn -48.7528 MetaTest/Average/Iteration 361 MetaTest/Average/MaxReturn -41.8007 MetaTest/Average/MinReturn -56.5087 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.9291 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.7528 MetaTest/__unnamed_task__/AverageReturn -48.7528 MetaTest/__unnamed_task__/Iteration 361 MetaTest/__unnamed_task__/MaxReturn -41.8007 MetaTest/__unnamed_task__/MinReturn -56.5087 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.9291 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7376e+07 __unnamed_task__/AverageDiscountedReturn -26.2684 __unnamed_task__/AverageReturn -47.2216 __unnamed_task__/Iteration 361 __unnamed_task__/MaxReturn -40.5096 __unnamed_task__/MinReturn -70.7171 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.45201 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-10 23:55:14 | [maml_trainer] epoch #362 | Sampling for adapation and meta-testing... 2025-04-11 00:01:58 | [maml_trainer] epoch #362 | Finished meta-testing... 2025-04-11 00:01:58 | [maml_trainer] epoch #362 | Saving snapshot... 2025-04-11 00:02:35 | [maml_trainer] epoch #362 | Saved 2025-04-11 00:02:35 | [maml_trainer] epoch #362 | Time 631399.94 s 2025-04-11 00:02:35 | [maml_trainer] epoch #362 | EpochTime 2880.00 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.3635 Average/AverageReturn -48.1188 Average/Iteration 362 Average/MaxReturn -40.3025 Average/MinReturn -108.161 Average/NumEpisodes 120 Average/StdReturn 7.37844 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.75081 GaussianMLPPolicy/KLAfter 0.000962979 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.22265e-05 GaussianMLPPolicy/LossBefore -5.16574e-10 GaussianMLPPolicy/dLoss 6.2226e-05 Iteration 362 MetaTest/Average/AverageDiscountedReturn -48.6433 MetaTest/Average/AverageReturn -48.6433 MetaTest/Average/Iteration 362 MetaTest/Average/MaxReturn -41.4452 MetaTest/Average/MinReturn -61.5311 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.70867 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.6433 MetaTest/__unnamed_task__/AverageReturn -48.6433 MetaTest/__unnamed_task__/Iteration 362 MetaTest/__unnamed_task__/MaxReturn -41.4452 MetaTest/__unnamed_task__/MinReturn -61.5311 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.70867 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7424e+07 __unnamed_task__/AverageDiscountedReturn -26.3635 __unnamed_task__/AverageReturn -48.1188 __unnamed_task__/Iteration 362 __unnamed_task__/MaxReturn -40.3025 __unnamed_task__/MinReturn -108.161 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.37844 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 00:43:05 | [maml_trainer] epoch #363 | Sampling for adapation and meta-testing... 2025-04-11 00:49:50 | [maml_trainer] epoch #363 | Finished meta-testing... 2025-04-11 00:49:50 | [maml_trainer] epoch #363 | Saving snapshot... 2025-04-11 00:50:26 | [maml_trainer] epoch #363 | Saved 2025-04-11 00:50:26 | [maml_trainer] epoch #363 | Time 634270.83 s 2025-04-11 00:50:26 | [maml_trainer] epoch #363 | EpochTime 2870.88 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.7352 Average/AverageReturn -48.7336 Average/Iteration 363 Average/MaxReturn -38.994 Average/MinReturn -102.472 Average/NumEpisodes 120 Average/StdReturn 7.50753 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.74754 GaussianMLPPolicy/KLAfter 0.00236871 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.09847e-05 GaussianMLPPolicy/LossBefore -9.45727e-09 GaussianMLPPolicy/dLoss -7.09941e-05 Iteration 363 MetaTest/Average/AverageDiscountedReturn -48.503 MetaTest/Average/AverageReturn -48.503 MetaTest/Average/Iteration 363 MetaTest/Average/MaxReturn -41.0585 MetaTest/Average/MinReturn -58.0362 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.41657 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.503 MetaTest/__unnamed_task__/AverageReturn -48.503 MetaTest/__unnamed_task__/Iteration 363 MetaTest/__unnamed_task__/MaxReturn -41.0585 MetaTest/__unnamed_task__/MinReturn -58.0362 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.41657 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7472e+07 __unnamed_task__/AverageDiscountedReturn -26.7352 __unnamed_task__/AverageReturn -48.7336 __unnamed_task__/Iteration 363 __unnamed_task__/MaxReturn -38.994 __unnamed_task__/MinReturn -102.472 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.50753 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 01:23:50 | [maml_trainer] epoch #364 | Sampling for adapation and meta-testing... 2025-04-11 01:27:56 | [maml_trainer] epoch #364 | Finished meta-testing... 2025-04-11 01:27:56 | [maml_trainer] epoch #364 | Saving snapshot... 2025-04-11 01:28:17 | [maml_trainer] epoch #364 | Saved 2025-04-11 01:28:17 | [maml_trainer] epoch #364 | Time 636541.69 s 2025-04-11 01:28:17 | [maml_trainer] epoch #364 | EpochTime 2270.86 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.4237 Average/AverageReturn -47.4927 Average/Iteration 364 Average/MaxReturn -38.4012 Average/MinReturn -58.5517 Average/NumEpisodes 120 Average/StdReturn 3.68562 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.74353 GaussianMLPPolicy/KLAfter 0.00282592 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.86421e-05 GaussianMLPPolicy/LossBefore 1.77224e-08 GaussianMLPPolicy/dLoss -6.86243e-05 Iteration 364 MetaTest/Average/AverageDiscountedReturn -49.4552 MetaTest/Average/AverageReturn -49.4552 MetaTest/Average/Iteration 364 MetaTest/Average/MaxReturn -44.5822 MetaTest/Average/MinReturn -56.8331 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.4856 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.4552 MetaTest/__unnamed_task__/AverageReturn -49.4552 MetaTest/__unnamed_task__/Iteration 364 MetaTest/__unnamed_task__/MaxReturn -44.5822 MetaTest/__unnamed_task__/MinReturn -56.8331 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.4856 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.752e+07 __unnamed_task__/AverageDiscountedReturn -26.4237 __unnamed_task__/AverageReturn -47.4927 __unnamed_task__/Iteration 364 __unnamed_task__/MaxReturn -38.4012 __unnamed_task__/MinReturn -58.5517 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 3.68562 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 01:52:18 | [maml_trainer] epoch #365 | Sampling for adapation and meta-testing... 2025-04-11 01:56:19 | [maml_trainer] epoch #365 | Finished meta-testing... 2025-04-11 01:56:19 | [maml_trainer] epoch #365 | Saving snapshot... 2025-04-11 01:56:40 | [maml_trainer] epoch #365 | Saved 2025-04-11 01:56:40 | [maml_trainer] epoch #365 | Time 638244.18 s 2025-04-11 01:56:40 | [maml_trainer] epoch #365 | EpochTime 1702.49 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.4331 Average/AverageReturn -48.0583 Average/Iteration 365 Average/MaxReturn -40.648 Average/MinReturn -109.88 Average/NumEpisodes 120 Average/StdReturn 6.89192 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.74028 GaussianMLPPolicy/KLAfter 0.00160521 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.44893e-06 GaussianMLPPolicy/LossBefore -7.70887e-09 GaussianMLPPolicy/dLoss -4.45664e-06 Iteration 365 MetaTest/Average/AverageDiscountedReturn -50.0305 MetaTest/Average/AverageReturn -50.0305 MetaTest/Average/Iteration 365 MetaTest/Average/MaxReturn -41.0323 MetaTest/Average/MinReturn -67.6948 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.82818 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0305 MetaTest/__unnamed_task__/AverageReturn -50.0305 MetaTest/__unnamed_task__/Iteration 365 MetaTest/__unnamed_task__/MaxReturn -41.0323 MetaTest/__unnamed_task__/MinReturn -67.6948 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.82818 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7568e+07 __unnamed_task__/AverageDiscountedReturn -26.4331 __unnamed_task__/AverageReturn -48.0583 __unnamed_task__/Iteration 365 __unnamed_task__/MaxReturn -40.648 __unnamed_task__/MinReturn -109.88 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.89192 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 02:20:32 | [maml_trainer] epoch #366 | Sampling for adapation and meta-testing... 2025-04-11 02:24:31 | [maml_trainer] epoch #366 | Finished meta-testing... 2025-04-11 02:24:31 | [maml_trainer] epoch #366 | Saving snapshot... 2025-04-11 02:24:53 | [maml_trainer] epoch #366 | Saved 2025-04-11 02:24:53 | [maml_trainer] epoch #366 | Time 639937.69 s 2025-04-11 02:24:53 | [maml_trainer] epoch #366 | EpochTime 1693.51 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.184 Average/AverageReturn -47.2083 Average/Iteration 366 Average/MaxReturn -37.9778 Average/MinReturn -59.8536 Average/NumEpisodes 120 Average/StdReturn 4.00732 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.7382 GaussianMLPPolicy/KLAfter 0.00111878 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.07023e-06 GaussianMLPPolicy/LossBefore 1.04109e-08 GaussianMLPPolicy/dLoss 8.08064e-06 Iteration 366 MetaTest/Average/AverageDiscountedReturn -45.9326 MetaTest/Average/AverageReturn -45.9326 MetaTest/Average/Iteration 366 MetaTest/Average/MaxReturn -39.7649 MetaTest/Average/MinReturn -55.9477 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.93733 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.9326 MetaTest/__unnamed_task__/AverageReturn -45.9326 MetaTest/__unnamed_task__/Iteration 366 MetaTest/__unnamed_task__/MaxReturn -39.7649 MetaTest/__unnamed_task__/MinReturn -55.9477 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.93733 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7616e+07 __unnamed_task__/AverageDiscountedReturn -26.184 __unnamed_task__/AverageReturn -47.2083 __unnamed_task__/Iteration 366 __unnamed_task__/MaxReturn -37.9778 __unnamed_task__/MinReturn -59.8536 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.00732 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 02:48:54 | [maml_trainer] epoch #367 | Sampling for adapation and meta-testing... 2025-04-11 02:52:53 | [maml_trainer] epoch #367 | Finished meta-testing... 2025-04-11 02:52:53 | [maml_trainer] epoch #367 | Saving snapshot... 2025-04-11 02:53:15 | [maml_trainer] epoch #367 | Saved 2025-04-11 02:53:15 | [maml_trainer] epoch #367 | Time 641639.76 s 2025-04-11 02:53:15 | [maml_trainer] epoch #367 | EpochTime 1702.07 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.1677 Average/AverageReturn -47.9124 Average/Iteration 367 Average/MaxReturn -39.5115 Average/MinReturn -167.938 Average/NumEpisodes 120 Average/StdReturn 11.7015 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73657 GaussianMLPPolicy/KLAfter 0.00113668 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.76715e-05 GaussianMLPPolicy/LossBefore 2.38419e-10 GaussianMLPPolicy/dLoss 3.76717e-05 Iteration 367 MetaTest/Average/AverageDiscountedReturn -47.2841 MetaTest/Average/AverageReturn -47.2841 MetaTest/Average/Iteration 367 MetaTest/Average/MaxReturn -41.1249 MetaTest/Average/MinReturn -59.7061 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.25877 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.2841 MetaTest/__unnamed_task__/AverageReturn -47.2841 MetaTest/__unnamed_task__/Iteration 367 MetaTest/__unnamed_task__/MaxReturn -41.1249 MetaTest/__unnamed_task__/MinReturn -59.7061 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.25877 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7664e+07 __unnamed_task__/AverageDiscountedReturn -26.1677 __unnamed_task__/AverageReturn -47.9124 __unnamed_task__/Iteration 367 __unnamed_task__/MaxReturn -39.5115 __unnamed_task__/MinReturn -167.938 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.7015 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 03:33:41 | [maml_trainer] epoch #368 | Sampling for adapation and meta-testing... 2025-04-11 03:40:32 | [maml_trainer] epoch #368 | Finished meta-testing... 2025-04-11 03:40:32 | [maml_trainer] epoch #368 | Saving snapshot... 2025-04-11 03:41:10 | [maml_trainer] epoch #368 | Saved 2025-04-11 03:41:10 | [maml_trainer] epoch #368 | Time 644514.19 s 2025-04-11 03:41:10 | [maml_trainer] epoch #368 | EpochTime 2874.42 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.7039 Average/AverageReturn -49.3855 Average/Iteration 368 Average/MaxReturn -41.209 Average/MinReturn -155.244 Average/NumEpisodes 120 Average/StdReturn 12.1678 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73682 GaussianMLPPolicy/KLAfter 0.00189755 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.18623e-05 GaussianMLPPolicy/LossBefore 1.94708e-09 GaussianMLPPolicy/dLoss -3.18603e-05 Iteration 368 MetaTest/Average/AverageDiscountedReturn -50.1332 MetaTest/Average/AverageReturn -50.1332 MetaTest/Average/Iteration 368 MetaTest/Average/MaxReturn -41.2118 MetaTest/Average/MinReturn -120.479 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.6617 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.1332 MetaTest/__unnamed_task__/AverageReturn -50.1332 MetaTest/__unnamed_task__/Iteration 368 MetaTest/__unnamed_task__/MaxReturn -41.2118 MetaTest/__unnamed_task__/MinReturn -120.479 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.6617 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7712e+07 __unnamed_task__/AverageDiscountedReturn -26.7039 __unnamed_task__/AverageReturn -49.3855 __unnamed_task__/Iteration 368 __unnamed_task__/MaxReturn -41.209 __unnamed_task__/MinReturn -155.244 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.1678 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 04:21:52 | [maml_trainer] epoch #369 | Sampling for adapation and meta-testing... 2025-04-11 04:28:38 | [maml_trainer] epoch #369 | Finished meta-testing... 2025-04-11 04:28:38 | [maml_trainer] epoch #369 | Saving snapshot... 2025-04-11 04:29:18 | [maml_trainer] epoch #369 | Saved 2025-04-11 04:29:18 | [maml_trainer] epoch #369 | Time 647402.81 s 2025-04-11 04:29:18 | [maml_trainer] epoch #369 | EpochTime 2888.61 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.1171 Average/AverageReturn -48.1624 Average/Iteration 369 Average/MaxReturn -40.1814 Average/MinReturn -132.741 Average/NumEpisodes 120 Average/StdReturn 10.4467 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73655 GaussianMLPPolicy/KLAfter 0.00171515 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.33855e-05 GaussianMLPPolicy/LossBefore 1.54972e-09 GaussianMLPPolicy/dLoss -2.33839e-05 Iteration 369 MetaTest/Average/AverageDiscountedReturn -46.1629 MetaTest/Average/AverageReturn -46.1629 MetaTest/Average/Iteration 369 MetaTest/Average/MaxReturn -41.1265 MetaTest/Average/MinReturn -54.1548 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.39795 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.1629 MetaTest/__unnamed_task__/AverageReturn -46.1629 MetaTest/__unnamed_task__/Iteration 369 MetaTest/__unnamed_task__/MaxReturn -41.1265 MetaTest/__unnamed_task__/MinReturn -54.1548 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.39795 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.776e+07 __unnamed_task__/AverageDiscountedReturn -26.1171 __unnamed_task__/AverageReturn -48.1624 __unnamed_task__/Iteration 369 __unnamed_task__/MaxReturn -40.1814 __unnamed_task__/MinReturn -132.741 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.4467 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 05:05:56 | [maml_trainer] epoch #370 | Sampling for adapation and meta-testing... 2025-04-11 05:09:58 | [maml_trainer] epoch #370 | Finished meta-testing... 2025-04-11 05:09:58 | [maml_trainer] epoch #370 | Saving snapshot... 2025-04-11 05:10:19 | [maml_trainer] epoch #370 | Saved 2025-04-11 05:10:19 | [maml_trainer] epoch #370 | Time 649863.91 s 2025-04-11 05:10:19 | [maml_trainer] epoch #370 | EpochTime 2461.10 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.9126 Average/AverageReturn -49.8282 Average/Iteration 370 Average/MaxReturn -40.2523 Average/MinReturn -120.727 Average/NumEpisodes 120 Average/StdReturn 10.583 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73576 GaussianMLPPolicy/KLAfter 0.00169278 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.47968e-05 GaussianMLPPolicy/LossBefore 5.20547e-09 GaussianMLPPolicy/dLoss -6.47916e-05 Iteration 370 MetaTest/Average/AverageDiscountedReturn -47.4627 MetaTest/Average/AverageReturn -47.4627 MetaTest/Average/Iteration 370 MetaTest/Average/MaxReturn -40.4365 MetaTest/Average/MinReturn -61.7782 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.63647 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4627 MetaTest/__unnamed_task__/AverageReturn -47.4627 MetaTest/__unnamed_task__/Iteration 370 MetaTest/__unnamed_task__/MaxReturn -40.4365 MetaTest/__unnamed_task__/MinReturn -61.7782 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.63647 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7808e+07 __unnamed_task__/AverageDiscountedReturn -26.9126 __unnamed_task__/AverageReturn -49.8282 __unnamed_task__/Iteration 370 __unnamed_task__/MaxReturn -40.2523 __unnamed_task__/MinReturn -120.727 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.583 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 05:34:22 | [maml_trainer] epoch #371 | Sampling for adapation and meta-testing... 2025-04-11 05:38:22 | [maml_trainer] epoch #371 | Finished meta-testing... 2025-04-11 05:38:22 | [maml_trainer] epoch #371 | Saving snapshot... 2025-04-11 05:38:42 | [maml_trainer] epoch #371 | Saved 2025-04-11 05:38:42 | [maml_trainer] epoch #371 | Time 651566.83 s 2025-04-11 05:38:42 | [maml_trainer] epoch #371 | EpochTime 1702.91 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.6905 Average/AverageReturn -50.4786 Average/Iteration 371 Average/MaxReturn -39.4588 Average/MinReturn -161.65 Average/NumEpisodes 120 Average/StdReturn 17.1082 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73489 GaussianMLPPolicy/KLAfter 0.00138772 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.95871e-05 GaussianMLPPolicy/LossBefore -7.53005e-09 GaussianMLPPolicy/dLoss -4.95946e-05 Iteration 371 MetaTest/Average/AverageDiscountedReturn -50.0365 MetaTest/Average/AverageReturn -50.0365 MetaTest/Average/Iteration 371 MetaTest/Average/MaxReturn -42.4177 MetaTest/Average/MinReturn -62.7385 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.98528 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0365 MetaTest/__unnamed_task__/AverageReturn -50.0365 MetaTest/__unnamed_task__/Iteration 371 MetaTest/__unnamed_task__/MaxReturn -42.4177 MetaTest/__unnamed_task__/MinReturn -62.7385 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.98528 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7856e+07 __unnamed_task__/AverageDiscountedReturn -26.6905 __unnamed_task__/AverageReturn -50.4786 __unnamed_task__/Iteration 371 __unnamed_task__/MaxReturn -39.4588 __unnamed_task__/MinReturn -161.65 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 17.1082 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 06:02:39 | [maml_trainer] epoch #372 | Sampling for adapation and meta-testing... 2025-04-11 06:06:38 | [maml_trainer] epoch #372 | Finished meta-testing... 2025-04-11 06:06:38 | [maml_trainer] epoch #372 | Saving snapshot... 2025-04-11 06:06:59 | [maml_trainer] epoch #372 | Saved 2025-04-11 06:06:59 | [maml_trainer] epoch #372 | Time 653263.08 s 2025-04-11 06:06:59 | [maml_trainer] epoch #372 | EpochTime 1696.25 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.0621 Average/AverageReturn -52.1296 Average/Iteration 372 Average/MaxReturn -39.4332 Average/MinReturn -172.221 Average/NumEpisodes 120 Average/StdReturn 21.1537 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73417 GaussianMLPPolicy/KLAfter 0.000972363 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.61174e-05 GaussianMLPPolicy/LossBefore 2.08616e-09 GaussianMLPPolicy/dLoss 6.61195e-05 Iteration 372 MetaTest/Average/AverageDiscountedReturn -46.7254 MetaTest/Average/AverageReturn -46.7254 MetaTest/Average/Iteration 372 MetaTest/Average/MaxReturn -42.8627 MetaTest/Average/MinReturn -52.7199 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.34193 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.7254 MetaTest/__unnamed_task__/AverageReturn -46.7254 MetaTest/__unnamed_task__/Iteration 372 MetaTest/__unnamed_task__/MaxReturn -42.8627 MetaTest/__unnamed_task__/MinReturn -52.7199 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.34193 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7904e+07 __unnamed_task__/AverageDiscountedReturn -27.0621 __unnamed_task__/AverageReturn -52.1296 __unnamed_task__/Iteration 372 __unnamed_task__/MaxReturn -39.4332 __unnamed_task__/MinReturn -172.221 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 21.1537 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 06:31:03 | [maml_trainer] epoch #373 | Sampling for adapation and meta-testing... 2025-04-11 06:35:06 | [maml_trainer] epoch #373 | Finished meta-testing... 2025-04-11 06:35:06 | [maml_trainer] epoch #373 | Saving snapshot... 2025-04-11 06:35:28 | [maml_trainer] epoch #373 | Saved 2025-04-11 06:35:28 | [maml_trainer] epoch #373 | Time 654972.85 s 2025-04-11 06:35:28 | [maml_trainer] epoch #373 | EpochTime 1709.76 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.4998 Average/AverageReturn -48.8809 Average/Iteration 373 Average/MaxReturn -41.3087 Average/MinReturn -161.216 Average/NumEpisodes 120 Average/StdReturn 12.3185 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73447 GaussianMLPPolicy/KLAfter 0.000608993 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.01188e-05 GaussianMLPPolicy/LossBefore -4.41074e-09 GaussianMLPPolicy/dLoss 2.01144e-05 Iteration 373 MetaTest/Average/AverageDiscountedReturn -47.1347 MetaTest/Average/AverageReturn -47.1347 MetaTest/Average/Iteration 373 MetaTest/Average/MaxReturn -40.6042 MetaTest/Average/MinReturn -67.7003 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.40341 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.1347 MetaTest/__unnamed_task__/AverageReturn -47.1347 MetaTest/__unnamed_task__/Iteration 373 MetaTest/__unnamed_task__/MaxReturn -40.6042 MetaTest/__unnamed_task__/MinReturn -67.7003 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.40341 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.7952e+07 __unnamed_task__/AverageDiscountedReturn -26.4998 __unnamed_task__/AverageReturn -48.8809 __unnamed_task__/Iteration 373 __unnamed_task__/MaxReturn -41.3087 __unnamed_task__/MinReturn -161.216 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.3185 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 06:59:32 | [maml_trainer] epoch #374 | Sampling for adapation and meta-testing... 2025-04-11 07:03:36 | [maml_trainer] epoch #374 | Finished meta-testing... 2025-04-11 07:03:36 | [maml_trainer] epoch #374 | Saving snapshot... 2025-04-11 07:03:58 | [maml_trainer] epoch #374 | Saved 2025-04-11 07:03:58 | [maml_trainer] epoch #374 | Time 656682.43 s 2025-04-11 07:03:58 | [maml_trainer] epoch #374 | EpochTime 1709.57 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.1725 Average/AverageReturn -47.4718 Average/Iteration 374 Average/MaxReturn -39.4356 Average/MinReturn -66.3626 Average/NumEpisodes 120 Average/StdReturn 4.67411 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73413 GaussianMLPPolicy/KLAfter 0.00095764 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.59007e-06 GaussianMLPPolicy/LossBefore -1.16825e-08 GaussianMLPPolicy/dLoss 9.57839e-06 Iteration 374 MetaTest/Average/AverageDiscountedReturn -47.468 MetaTest/Average/AverageReturn -47.468 MetaTest/Average/Iteration 374 MetaTest/Average/MaxReturn -41.5041 MetaTest/Average/MinReturn -54.749 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.93201 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.468 MetaTest/__unnamed_task__/AverageReturn -47.468 MetaTest/__unnamed_task__/Iteration 374 MetaTest/__unnamed_task__/MaxReturn -41.5041 MetaTest/__unnamed_task__/MinReturn -54.749 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.93201 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8e+07 __unnamed_task__/AverageDiscountedReturn -26.1725 __unnamed_task__/AverageReturn -47.4718 __unnamed_task__/Iteration 374 __unnamed_task__/MaxReturn -39.4356 __unnamed_task__/MinReturn -66.3626 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.67411 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 07:28:10 | [maml_trainer] epoch #375 | Sampling for adapation and meta-testing... 2025-04-11 07:32:17 | [maml_trainer] epoch #375 | Finished meta-testing... 2025-04-11 07:32:17 | [maml_trainer] epoch #375 | Saving snapshot... 2025-04-11 07:32:39 | [maml_trainer] epoch #375 | Saved 2025-04-11 07:32:39 | [maml_trainer] epoch #375 | Time 658403.43 s 2025-04-11 07:32:39 | [maml_trainer] epoch #375 | EpochTime 1720.99 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.8014 Average/AverageReturn -50.4797 Average/Iteration 375 Average/MaxReturn -38.409 Average/MinReturn -170.945 Average/NumEpisodes 120 Average/StdReturn 18.0741 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73394 GaussianMLPPolicy/KLAfter 0.00132386 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.65925e-05 GaussianMLPPolicy/LossBefore -5.126e-09 GaussianMLPPolicy/dLoss -2.65976e-05 Iteration 375 MetaTest/Average/AverageDiscountedReturn -53.6164 MetaTest/Average/AverageReturn -53.6164 MetaTest/Average/Iteration 375 MetaTest/Average/MaxReturn -40.3096 MetaTest/Average/MinReturn -157.219 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 24.1471 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.6164 MetaTest/__unnamed_task__/AverageReturn -53.6164 MetaTest/__unnamed_task__/Iteration 375 MetaTest/__unnamed_task__/MaxReturn -40.3096 MetaTest/__unnamed_task__/MinReturn -157.219 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 24.1471 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8048e+07 __unnamed_task__/AverageDiscountedReturn -26.8014 __unnamed_task__/AverageReturn -50.4797 __unnamed_task__/Iteration 375 __unnamed_task__/MaxReturn -38.409 __unnamed_task__/MinReturn -170.945 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 18.0741 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 07:56:46 | [maml_trainer] epoch #376 | Sampling for adapation and meta-testing... 2025-04-11 08:00:48 | [maml_trainer] epoch #376 | Finished meta-testing... 2025-04-11 08:00:48 | [maml_trainer] epoch #376 | Saving snapshot... 2025-04-11 08:01:10 | [maml_trainer] epoch #376 | Saved 2025-04-11 08:01:10 | [maml_trainer] epoch #376 | Time 660114.04 s 2025-04-11 08:01:10 | [maml_trainer] epoch #376 | EpochTime 1710.61 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.8789 Average/AverageReturn -50.3198 Average/Iteration 376 Average/MaxReturn -38.997 Average/MinReturn -163.955 Average/NumEpisodes 120 Average/StdReturn 14.5844 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.7343 GaussianMLPPolicy/KLAfter 0.00318839 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000132923 GaussianMLPPolicy/LossBefore 5.28494e-09 GaussianMLPPolicy/dLoss 0.000132928 Iteration 376 MetaTest/Average/AverageDiscountedReturn -53.598 MetaTest/Average/AverageReturn -53.598 MetaTest/Average/Iteration 376 MetaTest/Average/MaxReturn -42.5656 MetaTest/Average/MinReturn -171.105 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 27.4439 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.598 MetaTest/__unnamed_task__/AverageReturn -53.598 MetaTest/__unnamed_task__/Iteration 376 MetaTest/__unnamed_task__/MaxReturn -42.5656 MetaTest/__unnamed_task__/MinReturn -171.105 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 27.4439 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8096e+07 __unnamed_task__/AverageDiscountedReturn -26.8789 __unnamed_task__/AverageReturn -50.3198 __unnamed_task__/Iteration 376 __unnamed_task__/MaxReturn -38.997 __unnamed_task__/MinReturn -163.955 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.5844 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 08:25:29 | [maml_trainer] epoch #377 | Sampling for adapation and meta-testing... 2025-04-11 08:29:33 | [maml_trainer] epoch #377 | Finished meta-testing... 2025-04-11 08:29:33 | [maml_trainer] epoch #377 | Saving snapshot... 2025-04-11 08:29:55 | [maml_trainer] epoch #377 | Saved 2025-04-11 08:29:55 | [maml_trainer] epoch #377 | Time 661839.15 s 2025-04-11 08:29:55 | [maml_trainer] epoch #377 | EpochTime 1725.11 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.7426 Average/AverageReturn -51.7024 Average/Iteration 377 Average/MaxReturn -39.5282 Average/MinReturn -166.797 Average/NumEpisodes 120 Average/StdReturn 21.1892 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73508 GaussianMLPPolicy/KLAfter 0.00419984 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.55652e-05 GaussianMLPPolicy/LossBefore 5.96047e-10 GaussianMLPPolicy/dLoss 2.55658e-05 Iteration 377 MetaTest/Average/AverageDiscountedReturn -50.0513 MetaTest/Average/AverageReturn -50.0513 MetaTest/Average/Iteration 377 MetaTest/Average/MaxReturn -40.5824 MetaTest/Average/MinReturn -69.0231 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.66534 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0513 MetaTest/__unnamed_task__/AverageReturn -50.0513 MetaTest/__unnamed_task__/Iteration 377 MetaTest/__unnamed_task__/MaxReturn -40.5824 MetaTest/__unnamed_task__/MinReturn -69.0231 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.66534 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8144e+07 __unnamed_task__/AverageDiscountedReturn -26.7426 __unnamed_task__/AverageReturn -51.7024 __unnamed_task__/Iteration 377 __unnamed_task__/MaxReturn -39.5282 __unnamed_task__/MinReturn -166.797 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 21.1892 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 08:54:19 | [maml_trainer] epoch #378 | Sampling for adapation and meta-testing... 2025-04-11 08:58:21 | [maml_trainer] epoch #378 | Finished meta-testing... 2025-04-11 08:58:21 | [maml_trainer] epoch #378 | Saving snapshot... 2025-04-11 08:58:43 | [maml_trainer] epoch #378 | Saved 2025-04-11 08:58:43 | [maml_trainer] epoch #378 | Time 663566.99 s 2025-04-11 08:58:43 | [maml_trainer] epoch #378 | EpochTime 1727.83 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.6177 Average/AverageReturn -50.0353 Average/Iteration 378 Average/MaxReturn -39.1544 Average/MinReturn -144.656 Average/NumEpisodes 120 Average/StdReturn 13.3339 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73587 GaussianMLPPolicy/KLAfter 0.00408746 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.05992e-05 GaussianMLPPolicy/LossBefore -1.38283e-08 GaussianMLPPolicy/dLoss 2.05854e-05 Iteration 378 MetaTest/Average/AverageDiscountedReturn -52.1532 MetaTest/Average/AverageReturn -52.1532 MetaTest/Average/Iteration 378 MetaTest/Average/MaxReturn -40.3568 MetaTest/Average/MinReturn -111.777 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.69 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.1532 MetaTest/__unnamed_task__/AverageReturn -52.1532 MetaTest/__unnamed_task__/Iteration 378 MetaTest/__unnamed_task__/MaxReturn -40.3568 MetaTest/__unnamed_task__/MinReturn -111.777 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.69 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8192e+07 __unnamed_task__/AverageDiscountedReturn -26.6177 __unnamed_task__/AverageReturn -50.0353 __unnamed_task__/Iteration 378 __unnamed_task__/MaxReturn -39.1544 __unnamed_task__/MinReturn -144.656 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 13.3339 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 09:22:47 | [maml_trainer] epoch #379 | Sampling for adapation and meta-testing... 2025-04-11 09:26:47 | [maml_trainer] epoch #379 | Finished meta-testing... 2025-04-11 09:26:47 | [maml_trainer] epoch #379 | Saving snapshot... 2025-04-11 09:27:09 | [maml_trainer] epoch #379 | Saved 2025-04-11 09:27:09 | [maml_trainer] epoch #379 | Time 665273.55 s 2025-04-11 09:27:09 | [maml_trainer] epoch #379 | EpochTime 1706.56 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.4689 Average/AverageReturn -49.4823 Average/Iteration 379 Average/MaxReturn -39.5882 Average/MinReturn -174.397 Average/NumEpisodes 120 Average/StdReturn 14.2985 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73614 GaussianMLPPolicy/KLAfter 0.00233615 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.02268e-05 GaussianMLPPolicy/LossBefore -4.45048e-09 GaussianMLPPolicy/dLoss -3.02312e-05 Iteration 379 MetaTest/Average/AverageDiscountedReturn -48.1556 MetaTest/Average/AverageReturn -48.1556 MetaTest/Average/Iteration 379 MetaTest/Average/MaxReturn -42.6227 MetaTest/Average/MinReturn -56.4624 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.74185 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1556 MetaTest/__unnamed_task__/AverageReturn -48.1556 MetaTest/__unnamed_task__/Iteration 379 MetaTest/__unnamed_task__/MaxReturn -42.6227 MetaTest/__unnamed_task__/MinReturn -56.4624 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.74185 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.824e+07 __unnamed_task__/AverageDiscountedReturn -26.4689 __unnamed_task__/AverageReturn -49.4823 __unnamed_task__/Iteration 379 __unnamed_task__/MaxReturn -39.5882 __unnamed_task__/MinReturn -174.397 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.2985 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 09:51:15 | [maml_trainer] epoch #380 | Sampling for adapation and meta-testing... 2025-04-11 09:55:17 | [maml_trainer] epoch #380 | Finished meta-testing... 2025-04-11 09:55:17 | [maml_trainer] epoch #380 | Saving snapshot... 2025-04-11 09:55:39 | [maml_trainer] epoch #380 | Saved 2025-04-11 09:55:39 | [maml_trainer] epoch #380 | Time 666983.20 s 2025-04-11 09:55:39 | [maml_trainer] epoch #380 | EpochTime 1709.65 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.1483 Average/AverageReturn -49.027 Average/Iteration 380 Average/MaxReturn -37.7841 Average/MinReturn -176.647 Average/NumEpisodes 120 Average/StdReturn 15.1789 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.7368 GaussianMLPPolicy/KLAfter 0.00110606 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.30037e-06 GaussianMLPPolicy/LossBefore -2.82129e-09 GaussianMLPPolicy/dLoss 3.29755e-06 Iteration 380 MetaTest/Average/AverageDiscountedReturn -47.932 MetaTest/Average/AverageReturn -47.932 MetaTest/Average/Iteration 380 MetaTest/Average/MaxReturn -43.4315 MetaTest/Average/MinReturn -52.3472 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 2.76516 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.932 MetaTest/__unnamed_task__/AverageReturn -47.932 MetaTest/__unnamed_task__/Iteration 380 MetaTest/__unnamed_task__/MaxReturn -43.4315 MetaTest/__unnamed_task__/MinReturn -52.3472 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 2.76516 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8288e+07 __unnamed_task__/AverageDiscountedReturn -26.1483 __unnamed_task__/AverageReturn -49.027 __unnamed_task__/Iteration 380 __unnamed_task__/MaxReturn -37.7841 __unnamed_task__/MinReturn -176.647 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 15.1789 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 10:19:54 | [maml_trainer] epoch #381 | Sampling for adapation and meta-testing... 2025-04-11 10:24:02 | [maml_trainer] epoch #381 | Finished meta-testing... 2025-04-11 10:24:02 | [maml_trainer] epoch #381 | Saving snapshot... 2025-04-11 10:24:25 | [maml_trainer] epoch #381 | Saved 2025-04-11 10:24:25 | [maml_trainer] epoch #381 | Time 668709.11 s 2025-04-11 10:24:25 | [maml_trainer] epoch #381 | EpochTime 1725.91 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.0862 Average/AverageReturn -48.5195 Average/Iteration 381 Average/MaxReturn -38.9155 Average/MinReturn -171.287 Average/NumEpisodes 120 Average/StdReturn 12.2734 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73679 GaussianMLPPolicy/KLAfter 0.00321483 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.45343e-05 GaussianMLPPolicy/LossBefore -1.24971e-08 GaussianMLPPolicy/dLoss -2.45468e-05 Iteration 381 MetaTest/Average/AverageDiscountedReturn -52.2272 MetaTest/Average/AverageReturn -52.2272 MetaTest/Average/Iteration 381 MetaTest/Average/MaxReturn -42.265 MetaTest/Average/MinReturn -134.087 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 19.0861 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2272 MetaTest/__unnamed_task__/AverageReturn -52.2272 MetaTest/__unnamed_task__/Iteration 381 MetaTest/__unnamed_task__/MaxReturn -42.265 MetaTest/__unnamed_task__/MinReturn -134.087 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 19.0861 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8336e+07 __unnamed_task__/AverageDiscountedReturn -26.0862 __unnamed_task__/AverageReturn -48.5195 __unnamed_task__/Iteration 381 __unnamed_task__/MaxReturn -38.9155 __unnamed_task__/MinReturn -171.287 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.2734 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 10:48:57 | [maml_trainer] epoch #382 | Sampling for adapation and meta-testing... 2025-04-11 10:53:01 | [maml_trainer] epoch #382 | Finished meta-testing... 2025-04-11 10:53:01 | [maml_trainer] epoch #382 | Saving snapshot... 2025-04-11 10:53:23 | [maml_trainer] epoch #382 | Saved 2025-04-11 10:53:23 | [maml_trainer] epoch #382 | Time 670447.48 s 2025-04-11 10:53:23 | [maml_trainer] epoch #382 | EpochTime 1738.36 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.5091 Average/AverageReturn -49.4704 Average/Iteration 382 Average/MaxReturn -40.7067 Average/MinReturn -113.737 Average/NumEpisodes 120 Average/StdReturn 9.34912 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73679 GaussianMLPPolicy/KLAfter 0.00238727 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 4.21964e-05 GaussianMLPPolicy/LossBefore -5.24521e-09 GaussianMLPPolicy/dLoss -4.22016e-05 Iteration 382 MetaTest/Average/AverageDiscountedReturn -50.4525 MetaTest/Average/AverageReturn -50.4525 MetaTest/Average/Iteration 382 MetaTest/Average/MaxReturn -42.0124 MetaTest/Average/MinReturn -91.2023 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.79487 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.4525 MetaTest/__unnamed_task__/AverageReturn -50.4525 MetaTest/__unnamed_task__/Iteration 382 MetaTest/__unnamed_task__/MaxReturn -42.0124 MetaTest/__unnamed_task__/MinReturn -91.2023 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.79487 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8384e+07 __unnamed_task__/AverageDiscountedReturn -26.5091 __unnamed_task__/AverageReturn -49.4704 __unnamed_task__/Iteration 382 __unnamed_task__/MaxReturn -40.7067 __unnamed_task__/MinReturn -113.737 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.34912 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 11:17:43 | [maml_trainer] epoch #383 | Sampling for adapation and meta-testing... 2025-04-11 11:21:45 | [maml_trainer] epoch #383 | Finished meta-testing... 2025-04-11 11:21:45 | [maml_trainer] epoch #383 | Saving snapshot... 2025-04-11 11:22:07 | [maml_trainer] epoch #383 | Saved 2025-04-11 11:22:07 | [maml_trainer] epoch #383 | Time 672171.40 s 2025-04-11 11:22:07 | [maml_trainer] epoch #383 | EpochTime 1723.92 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.5471 Average/AverageReturn -50.2329 Average/Iteration 383 Average/MaxReturn -40.7223 Average/MinReturn -151.881 Average/NumEpisodes 120 Average/StdReturn 12.9272 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73586 GaussianMLPPolicy/KLAfter 0.00236083 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.86939e-05 GaussianMLPPolicy/LossBefore -6.55651e-09 GaussianMLPPolicy/dLoss 4.86873e-05 Iteration 383 MetaTest/Average/AverageDiscountedReturn -50.9639 MetaTest/Average/AverageReturn -50.9639 MetaTest/Average/Iteration 383 MetaTest/Average/MaxReturn -44.8632 MetaTest/Average/MinReturn -72.0132 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.70137 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.9639 MetaTest/__unnamed_task__/AverageReturn -50.9639 MetaTest/__unnamed_task__/Iteration 383 MetaTest/__unnamed_task__/MaxReturn -44.8632 MetaTest/__unnamed_task__/MinReturn -72.0132 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.70137 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8432e+07 __unnamed_task__/AverageDiscountedReturn -26.5471 __unnamed_task__/AverageReturn -50.2329 __unnamed_task__/Iteration 383 __unnamed_task__/MaxReturn -40.7223 __unnamed_task__/MinReturn -151.881 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.9272 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 11:46:27 | [maml_trainer] epoch #384 | Sampling for adapation and meta-testing... 2025-04-11 11:50:27 | [maml_trainer] epoch #384 | Finished meta-testing... 2025-04-11 11:50:27 | [maml_trainer] epoch #384 | Saving snapshot... 2025-04-11 11:50:48 | [maml_trainer] epoch #384 | Saved 2025-04-11 11:50:48 | [maml_trainer] epoch #384 | Time 673892.84 s 2025-04-11 11:50:48 | [maml_trainer] epoch #384 | EpochTime 1721.44 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.8089 Average/AverageReturn -50.2248 Average/Iteration 384 Average/MaxReturn -40.5573 Average/MinReturn -104.318 Average/NumEpisodes 120 Average/StdReturn 7.09011 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73462 GaussianMLPPolicy/KLAfter 0.00172223 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.84991e-05 GaussianMLPPolicy/LossBefore 4.29153e-09 GaussianMLPPolicy/dLoss -2.84948e-05 Iteration 384 MetaTest/Average/AverageDiscountedReturn -50.324 MetaTest/Average/AverageReturn -50.324 MetaTest/Average/Iteration 384 MetaTest/Average/MaxReturn -41.4688 MetaTest/Average/MinReturn -68.7757 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.99252 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.324 MetaTest/__unnamed_task__/AverageReturn -50.324 MetaTest/__unnamed_task__/Iteration 384 MetaTest/__unnamed_task__/MaxReturn -41.4688 MetaTest/__unnamed_task__/MinReturn -68.7757 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.99252 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.848e+07 __unnamed_task__/AverageDiscountedReturn -26.8089 __unnamed_task__/AverageReturn -50.2248 __unnamed_task__/Iteration 384 __unnamed_task__/MaxReturn -40.5573 __unnamed_task__/MinReturn -104.318 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.09011 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 12:15:06 | [maml_trainer] epoch #385 | Sampling for adapation and meta-testing... 2025-04-11 12:19:08 | [maml_trainer] epoch #385 | Finished meta-testing... 2025-04-11 12:19:08 | [maml_trainer] epoch #385 | Saving snapshot... 2025-04-11 12:19:30 | [maml_trainer] epoch #385 | Saved 2025-04-11 12:19:30 | [maml_trainer] epoch #385 | Time 675614.67 s 2025-04-11 12:19:30 | [maml_trainer] epoch #385 | EpochTime 1721.83 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.8814 Average/AverageReturn -50.9412 Average/Iteration 385 Average/MaxReturn -41.4396 Average/MinReturn -123.622 Average/NumEpisodes 120 Average/StdReturn 10.09 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73322 GaussianMLPPolicy/KLAfter 0.00201219 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.02756e-05 GaussianMLPPolicy/LossBefore -3.45707e-09 GaussianMLPPolicy/dLoss -2.02791e-05 Iteration 385 MetaTest/Average/AverageDiscountedReturn -49.2546 MetaTest/Average/AverageReturn -49.2546 MetaTest/Average/Iteration 385 MetaTest/Average/MaxReturn -42.4525 MetaTest/Average/MinReturn -66.1154 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.48041 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.2546 MetaTest/__unnamed_task__/AverageReturn -49.2546 MetaTest/__unnamed_task__/Iteration 385 MetaTest/__unnamed_task__/MaxReturn -42.4525 MetaTest/__unnamed_task__/MinReturn -66.1154 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.48041 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8528e+07 __unnamed_task__/AverageDiscountedReturn -26.8814 __unnamed_task__/AverageReturn -50.9412 __unnamed_task__/Iteration 385 __unnamed_task__/MaxReturn -41.4396 __unnamed_task__/MinReturn -123.622 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.09 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 12:43:49 | [maml_trainer] epoch #386 | Sampling for adapation and meta-testing... 2025-04-11 12:47:53 | [maml_trainer] epoch #386 | Finished meta-testing... 2025-04-11 12:47:53 | [maml_trainer] epoch #386 | Saving snapshot... 2025-04-11 12:48:14 | [maml_trainer] epoch #386 | Saved 2025-04-11 12:48:14 | [maml_trainer] epoch #386 | Time 677338.53 s 2025-04-11 12:48:14 | [maml_trainer] epoch #386 | EpochTime 1723.85 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.6725 Average/AverageReturn -50.1921 Average/Iteration 386 Average/MaxReturn -42.6725 Average/MinReturn -89.5317 Average/NumEpisodes 120 Average/StdReturn 5.62343 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.7327 GaussianMLPPolicy/KLAfter 0.00183638 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000140135 GaussianMLPPolicy/LossBefore 1.15236e-09 GaussianMLPPolicy/dLoss 0.000140136 Iteration 386 MetaTest/Average/AverageDiscountedReturn -50.5005 MetaTest/Average/AverageReturn -50.5005 MetaTest/Average/Iteration 386 MetaTest/Average/MaxReturn -43.324 MetaTest/Average/MinReturn -60.3857 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.38695 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5005 MetaTest/__unnamed_task__/AverageReturn -50.5005 MetaTest/__unnamed_task__/Iteration 386 MetaTest/__unnamed_task__/MaxReturn -43.324 MetaTest/__unnamed_task__/MinReturn -60.3857 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.38695 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8576e+07 __unnamed_task__/AverageDiscountedReturn -26.6725 __unnamed_task__/AverageReturn -50.1921 __unnamed_task__/Iteration 386 __unnamed_task__/MaxReturn -42.6725 __unnamed_task__/MinReturn -89.5317 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.62343 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 13:12:43 | [maml_trainer] epoch #387 | Sampling for adapation and meta-testing... 2025-04-11 13:16:48 | [maml_trainer] epoch #387 | Finished meta-testing... 2025-04-11 13:16:48 | [maml_trainer] epoch #387 | Saving snapshot... 2025-04-11 13:17:09 | [maml_trainer] epoch #387 | Saved 2025-04-11 13:17:09 | [maml_trainer] epoch #387 | Time 679073.78 s 2025-04-11 13:17:09 | [maml_trainer] epoch #387 | EpochTime 1735.25 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.9034 Average/AverageReturn -51.1056 Average/Iteration 387 Average/MaxReturn -41.3693 Average/MinReturn -167.581 Average/NumEpisodes 120 Average/StdReturn 11.4795 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73298 GaussianMLPPolicy/KLAfter 0.00287621 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.83703e-05 GaussianMLPPolicy/LossBefore 3.29812e-09 GaussianMLPPolicy/dLoss -1.8367e-05 Iteration 387 MetaTest/Average/AverageDiscountedReturn -49.5632 MetaTest/Average/AverageReturn -49.5632 MetaTest/Average/Iteration 387 MetaTest/Average/MaxReturn -43.1023 MetaTest/Average/MinReturn -62.8795 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.84837 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5632 MetaTest/__unnamed_task__/AverageReturn -49.5632 MetaTest/__unnamed_task__/Iteration 387 MetaTest/__unnamed_task__/MaxReturn -43.1023 MetaTest/__unnamed_task__/MinReturn -62.8795 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.84837 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8624e+07 __unnamed_task__/AverageDiscountedReturn -26.9034 __unnamed_task__/AverageReturn -51.1056 __unnamed_task__/Iteration 387 __unnamed_task__/MaxReturn -41.3693 __unnamed_task__/MinReturn -167.581 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.4795 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 13:41:32 | [maml_trainer] epoch #388 | Sampling for adapation and meta-testing... 2025-04-11 13:45:36 | [maml_trainer] epoch #388 | Finished meta-testing... 2025-04-11 13:45:36 | [maml_trainer] epoch #388 | Saving snapshot... 2025-04-11 13:45:59 | [maml_trainer] epoch #388 | Saved 2025-04-11 13:45:59 | [maml_trainer] epoch #388 | Time 680803.26 s 2025-04-11 13:45:59 | [maml_trainer] epoch #388 | EpochTime 1729.47 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.0426 Average/AverageReturn -51.3022 Average/Iteration 388 Average/MaxReturn -42.0905 Average/MinReturn -123.827 Average/NumEpisodes 120 Average/StdReturn 7.98074 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73373 GaussianMLPPolicy/KLAfter 0.00399253 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.10963e-05 GaussianMLPPolicy/LossBefore 1.77224e-08 GaussianMLPPolicy/dLoss -7.10785e-05 Iteration 388 MetaTest/Average/AverageDiscountedReturn -49.1071 MetaTest/Average/AverageReturn -49.1071 MetaTest/Average/Iteration 388 MetaTest/Average/MaxReturn -43.4157 MetaTest/Average/MinReturn -53.5843 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 2.94185 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.1071 MetaTest/__unnamed_task__/AverageReturn -49.1071 MetaTest/__unnamed_task__/Iteration 388 MetaTest/__unnamed_task__/MaxReturn -43.4157 MetaTest/__unnamed_task__/MinReturn -53.5843 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 2.94185 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8672e+07 __unnamed_task__/AverageDiscountedReturn -27.0426 __unnamed_task__/AverageReturn -51.3022 __unnamed_task__/Iteration 388 __unnamed_task__/MaxReturn -42.0905 __unnamed_task__/MinReturn -123.827 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.98074 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 14:10:21 | [maml_trainer] epoch #389 | Sampling for adapation and meta-testing... 2025-04-11 14:14:25 | [maml_trainer] epoch #389 | Finished meta-testing... 2025-04-11 14:14:25 | [maml_trainer] epoch #389 | Saving snapshot... 2025-04-11 14:14:47 | [maml_trainer] epoch #389 | Saved 2025-04-11 14:14:47 | [maml_trainer] epoch #389 | Time 682531.22 s 2025-04-11 14:14:47 | [maml_trainer] epoch #389 | EpochTime 1727.96 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.4838 Average/AverageReturn -52.7533 Average/Iteration 389 Average/MaxReturn -43.0586 Average/MinReturn -104.702 Average/NumEpisodes 120 Average/StdReturn 8.56 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73309 GaussianMLPPolicy/KLAfter 0.00300918 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000120506 GaussianMLPPolicy/LossBefore -1.69277e-08 GaussianMLPPolicy/dLoss -0.000120523 Iteration 389 MetaTest/Average/AverageDiscountedReturn -50.8135 MetaTest/Average/AverageReturn -50.8135 MetaTest/Average/Iteration 389 MetaTest/Average/MaxReturn -43.8006 MetaTest/Average/MinReturn -66.6299 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.19209 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.8135 MetaTest/__unnamed_task__/AverageReturn -50.8135 MetaTest/__unnamed_task__/Iteration 389 MetaTest/__unnamed_task__/MaxReturn -43.8006 MetaTest/__unnamed_task__/MinReturn -66.6299 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.19209 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.872e+07 __unnamed_task__/AverageDiscountedReturn -27.4838 __unnamed_task__/AverageReturn -52.7533 __unnamed_task__/Iteration 389 __unnamed_task__/MaxReturn -43.0586 __unnamed_task__/MinReturn -104.702 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.56 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 14:39:01 | [maml_trainer] epoch #390 | Sampling for adapation and meta-testing... 2025-04-11 14:43:03 | [maml_trainer] epoch #390 | Finished meta-testing... 2025-04-11 14:43:03 | [maml_trainer] epoch #390 | Saving snapshot... 2025-04-11 14:43:25 | [maml_trainer] epoch #390 | Saved 2025-04-11 14:43:25 | [maml_trainer] epoch #390 | Time 684249.81 s 2025-04-11 14:43:25 | [maml_trainer] epoch #390 | EpochTime 1718.58 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.2631 Average/AverageReturn -52.2104 Average/Iteration 390 Average/MaxReturn -41.8582 Average/MinReturn -103.319 Average/NumEpisodes 120 Average/StdReturn 7.16505 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73351 GaussianMLPPolicy/KLAfter 0.00474778 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.49826e-05 GaussianMLPPolicy/LossBefore -5.48363e-09 GaussianMLPPolicy/dLoss -3.49881e-05 Iteration 390 MetaTest/Average/AverageDiscountedReturn -50.4766 MetaTest/Average/AverageReturn -50.4766 MetaTest/Average/Iteration 390 MetaTest/Average/MaxReturn -44.0111 MetaTest/Average/MinReturn -64.3624 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.3713 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.4766 MetaTest/__unnamed_task__/AverageReturn -50.4766 MetaTest/__unnamed_task__/Iteration 390 MetaTest/__unnamed_task__/MaxReturn -44.0111 MetaTest/__unnamed_task__/MinReturn -64.3624 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.3713 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8768e+07 __unnamed_task__/AverageDiscountedReturn -27.2631 __unnamed_task__/AverageReturn -52.2104 __unnamed_task__/Iteration 390 __unnamed_task__/MaxReturn -41.8582 __unnamed_task__/MinReturn -103.319 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.16505 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 15:07:49 | [maml_trainer] epoch #391 | Sampling for adapation and meta-testing... 2025-04-11 15:11:51 | [maml_trainer] epoch #391 | Finished meta-testing... 2025-04-11 15:11:51 | [maml_trainer] epoch #391 | Saving snapshot... 2025-04-11 15:12:12 | [maml_trainer] epoch #391 | Saved 2025-04-11 15:12:12 | [maml_trainer] epoch #391 | Time 685976.11 s 2025-04-11 15:12:12 | [maml_trainer] epoch #391 | EpochTime 1726.30 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.013 Average/AverageReturn -51.8774 Average/Iteration 391 Average/MaxReturn -44.1592 Average/MinReturn -80.1579 Average/NumEpisodes 120 Average/StdReturn 5.68098 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73368 GaussianMLPPolicy/KLAfter 0.00435495 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.67266e-05 GaussianMLPPolicy/LossBefore 2.14577e-08 GaussianMLPPolicy/dLoss 8.6748e-05 Iteration 391 MetaTest/Average/AverageDiscountedReturn -55.3498 MetaTest/Average/AverageReturn -55.3498 MetaTest/Average/Iteration 391 MetaTest/Average/MaxReturn -45.0201 MetaTest/Average/MinReturn -125.606 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.8295 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.3498 MetaTest/__unnamed_task__/AverageReturn -55.3498 MetaTest/__unnamed_task__/Iteration 391 MetaTest/__unnamed_task__/MaxReturn -45.0201 MetaTest/__unnamed_task__/MinReturn -125.606 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.8295 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8816e+07 __unnamed_task__/AverageDiscountedReturn -27.013 __unnamed_task__/AverageReturn -51.8774 __unnamed_task__/Iteration 391 __unnamed_task__/MaxReturn -44.1592 __unnamed_task__/MinReturn -80.1579 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.68098 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 15:36:38 | [maml_trainer] epoch #392 | Sampling for adapation and meta-testing... 2025-04-11 15:40:40 | [maml_trainer] epoch #392 | Finished meta-testing... 2025-04-11 15:40:40 | [maml_trainer] epoch #392 | Saving snapshot... 2025-04-11 15:41:03 | [maml_trainer] epoch #392 | Saved 2025-04-11 15:41:03 | [maml_trainer] epoch #392 | Time 687707.02 s 2025-04-11 15:41:03 | [maml_trainer] epoch #392 | EpochTime 1730.90 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.9397 Average/AverageReturn -51.8827 Average/Iteration 392 Average/MaxReturn -43.7292 Average/MinReturn -105.884 Average/NumEpisodes 120 Average/StdReturn 6.67461 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73314 GaussianMLPPolicy/KLAfter 0.00646529 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000102499 GaussianMLPPolicy/LossBefore -3.21865e-09 GaussianMLPPolicy/dLoss -0.000102502 Iteration 392 MetaTest/Average/AverageDiscountedReturn -52.552 MetaTest/Average/AverageReturn -52.552 MetaTest/Average/Iteration 392 MetaTest/Average/MaxReturn -45.4695 MetaTest/Average/MinReturn -63.3216 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.49635 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.552 MetaTest/__unnamed_task__/AverageReturn -52.552 MetaTest/__unnamed_task__/Iteration 392 MetaTest/__unnamed_task__/MaxReturn -45.4695 MetaTest/__unnamed_task__/MinReturn -63.3216 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.49635 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8864e+07 __unnamed_task__/AverageDiscountedReturn -26.9397 __unnamed_task__/AverageReturn -51.8827 __unnamed_task__/Iteration 392 __unnamed_task__/MaxReturn -43.7292 __unnamed_task__/MinReturn -105.884 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.67461 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 16:05:35 | [maml_trainer] epoch #393 | Sampling for adapation and meta-testing... 2025-04-11 16:09:41 | [maml_trainer] epoch #393 | Finished meta-testing... 2025-04-11 16:09:41 | [maml_trainer] epoch #393 | Saving snapshot... 2025-04-11 16:10:03 | [maml_trainer] epoch #393 | Saved 2025-04-11 16:10:03 | [maml_trainer] epoch #393 | Time 689447.85 s 2025-04-11 16:10:03 | [maml_trainer] epoch #393 | EpochTime 1740.83 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.0715 Average/AverageReturn -51.7885 Average/Iteration 393 Average/MaxReturn -43.2708 Average/MinReturn -66.8631 Average/NumEpisodes 120 Average/StdReturn 4.7168 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73272 GaussianMLPPolicy/KLAfter 0.00788474 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000246897 GaussianMLPPolicy/LossBefore 9.21885e-09 GaussianMLPPolicy/dLoss -0.000246888 Iteration 393 MetaTest/Average/AverageDiscountedReturn -51.6784 MetaTest/Average/AverageReturn -51.6784 MetaTest/Average/Iteration 393 MetaTest/Average/MaxReturn -45.5049 MetaTest/Average/MinReturn -63.5259 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.02267 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6784 MetaTest/__unnamed_task__/AverageReturn -51.6784 MetaTest/__unnamed_task__/Iteration 393 MetaTest/__unnamed_task__/MaxReturn -45.5049 MetaTest/__unnamed_task__/MinReturn -63.5259 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.02267 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.8912e+07 __unnamed_task__/AverageDiscountedReturn -27.0715 __unnamed_task__/AverageReturn -51.7885 __unnamed_task__/Iteration 393 __unnamed_task__/MaxReturn -43.2708 __unnamed_task__/MinReturn -66.8631 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.7168 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 16:34:31 | [maml_trainer] epoch #394 | Sampling for adapation and meta-testing... 2025-04-11 16:38:38 | [maml_trainer] epoch #394 | Finished meta-testing... 2025-04-11 16:38:38 | [maml_trainer] epoch #394 | Saving snapshot... 2025-04-11 16:39:00 | [maml_trainer] epoch #394 | Saved 2025-04-11 16:39:00 | [maml_trainer] epoch #394 | Time 691184.33 s 2025-04-11 16:39:00 | [maml_trainer] epoch #394 | EpochTime 1736.47 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.2483 Average/AverageReturn -52.1995 Average/Iteration 394 Average/MaxReturn -44.7898 Average/MinReturn -74.3169 Average/NumEpisodes 120 Average/StdReturn 4.92085 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73151 GaussianMLPPolicy/KLAfter 0.00635341 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.64412e-05 GaussianMLPPolicy/LossBefore 8.66254e-09 GaussianMLPPolicy/dLoss 1.64498e-05 Iteration 394 MetaTest/Average/AverageDiscountedReturn -52.4885 MetaTest/Average/AverageReturn -52.4885 MetaTest/Average/Iteration 394 MetaTest/Average/MaxReturn -46.5304 MetaTest/Average/MinReturn -66.7444 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.09415 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.4885 MetaTest/__unnamed_task__/AverageReturn -52.4885 MetaTest/__unnamed_task__/Iteration 394 MetaTest/__unnamed_task__/MaxReturn -46.5304 MetaTest/__unnamed_task__/MinReturn -66.7444 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.09415 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.896e+07 __unnamed_task__/AverageDiscountedReturn -27.2483 __unnamed_task__/AverageReturn -52.1995 __unnamed_task__/Iteration 394 __unnamed_task__/MaxReturn -44.7898 __unnamed_task__/MinReturn -74.3169 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.92085 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 17:03:29 | [maml_trainer] epoch #395 | Sampling for adapation and meta-testing... 2025-04-11 17:07:36 | [maml_trainer] epoch #395 | Finished meta-testing... 2025-04-11 17:07:36 | [maml_trainer] epoch #395 | Saving snapshot... 2025-04-11 17:07:57 | [maml_trainer] epoch #395 | Saved 2025-04-11 17:07:57 | [maml_trainer] epoch #395 | Time 692921.49 s 2025-04-11 17:07:57 | [maml_trainer] epoch #395 | EpochTime 1737.16 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -27.2975 Average/AverageReturn -53.0207 Average/Iteration 395 Average/MaxReturn -43.6633 Average/MinReturn -119.772 Average/NumEpisodes 120 Average/StdReturn 8.57364 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.73033 GaussianMLPPolicy/KLAfter 0.006482 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000182348 GaussianMLPPolicy/LossBefore -1.15236e-08 GaussianMLPPolicy/dLoss -0.00018236 Iteration 395 MetaTest/Average/AverageDiscountedReturn -52.347 MetaTest/Average/AverageReturn -52.347 MetaTest/Average/Iteration 395 MetaTest/Average/MaxReturn -43.4679 MetaTest/Average/MinReturn -64.8107 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.1214 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.347 MetaTest/__unnamed_task__/AverageReturn -52.347 MetaTest/__unnamed_task__/Iteration 395 MetaTest/__unnamed_task__/MaxReturn -43.4679 MetaTest/__unnamed_task__/MinReturn -64.8107 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.1214 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9008e+07 __unnamed_task__/AverageDiscountedReturn -27.2975 __unnamed_task__/AverageReturn -53.0207 __unnamed_task__/Iteration 395 __unnamed_task__/MaxReturn -43.6633 __unnamed_task__/MinReturn -119.772 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.57364 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 17:32:38 | [maml_trainer] epoch #396 | Sampling for adapation and meta-testing... 2025-04-11 17:36:41 | [maml_trainer] epoch #396 | Finished meta-testing... 2025-04-11 17:36:41 | [maml_trainer] epoch #396 | Saving snapshot... 2025-04-11 17:37:02 | [maml_trainer] epoch #396 | Saved 2025-04-11 17:37:02 | [maml_trainer] epoch #396 | Time 694666.29 s 2025-04-11 17:37:02 | [maml_trainer] epoch #396 | EpochTime 1744.80 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.9791 Average/AverageReturn -52.0137 Average/Iteration 396 Average/MaxReturn -42.9795 Average/MinReturn -69.0029 Average/NumEpisodes 120 Average/StdReturn 5.14976 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.72864 GaussianMLPPolicy/KLAfter 0.00525604 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.92448e-05 GaussianMLPPolicy/LossBefore -1.45435e-08 GaussianMLPPolicy/dLoss 4.92303e-05 Iteration 396 MetaTest/Average/AverageDiscountedReturn -55.2883 MetaTest/Average/AverageReturn -55.2883 MetaTest/Average/Iteration 396 MetaTest/Average/MaxReturn -46.0096 MetaTest/Average/MinReturn -102.656 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.1481 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.2883 MetaTest/__unnamed_task__/AverageReturn -55.2883 MetaTest/__unnamed_task__/Iteration 396 MetaTest/__unnamed_task__/MaxReturn -46.0096 MetaTest/__unnamed_task__/MinReturn -102.656 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.1481 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9056e+07 __unnamed_task__/AverageDiscountedReturn -26.9791 __unnamed_task__/AverageReturn -52.0137 __unnamed_task__/Iteration 396 __unnamed_task__/MaxReturn -42.9795 __unnamed_task__/MinReturn -69.0029 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.14976 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 18:01:32 | [maml_trainer] epoch #397 | Sampling for adapation and meta-testing... 2025-04-11 18:05:39 | [maml_trainer] epoch #397 | Finished meta-testing... 2025-04-11 18:05:39 | [maml_trainer] epoch #397 | Saving snapshot... 2025-04-11 18:06:01 | [maml_trainer] epoch #397 | Saved 2025-04-11 18:06:01 | [maml_trainer] epoch #397 | Time 696405.14 s 2025-04-11 18:06:01 | [maml_trainer] epoch #397 | EpochTime 1738.84 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.848 Average/AverageReturn -52.3357 Average/Iteration 397 Average/MaxReturn -44.1921 Average/MinReturn -152.213 Average/NumEpisodes 120 Average/StdReturn 10.1666 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.72599 GaussianMLPPolicy/KLAfter 0.00415391 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.05384e-05 GaussianMLPPolicy/LossBefore -1.1921e-10 GaussianMLPPolicy/dLoss -1.05385e-05 Iteration 397 MetaTest/Average/AverageDiscountedReturn -52.1024 MetaTest/Average/AverageReturn -52.1024 MetaTest/Average/Iteration 397 MetaTest/Average/MaxReturn -45.3573 MetaTest/Average/MinReturn -61.7407 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.80982 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.1024 MetaTest/__unnamed_task__/AverageReturn -52.1024 MetaTest/__unnamed_task__/Iteration 397 MetaTest/__unnamed_task__/MaxReturn -45.3573 MetaTest/__unnamed_task__/MinReturn -61.7407 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.80982 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9104e+07 __unnamed_task__/AverageDiscountedReturn -26.848 __unnamed_task__/AverageReturn -52.3357 __unnamed_task__/Iteration 397 __unnamed_task__/MaxReturn -44.1921 __unnamed_task__/MinReturn -152.213 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.1666 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 18:30:36 | [maml_trainer] epoch #398 | Sampling for adapation and meta-testing... 2025-04-11 18:34:42 | [maml_trainer] epoch #398 | Finished meta-testing... 2025-04-11 18:34:42 | [maml_trainer] epoch #398 | Saving snapshot... 2025-04-11 18:35:03 | [maml_trainer] epoch #398 | Saved 2025-04-11 18:35:03 | [maml_trainer] epoch #398 | Time 698147.16 s 2025-04-11 18:35:03 | [maml_trainer] epoch #398 | EpochTime 1742.02 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.7678 Average/AverageReturn -52.1131 Average/Iteration 398 Average/MaxReturn -45.2007 Average/MinReturn -69.8016 Average/NumEpisodes 120 Average/StdReturn 4.79912 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.72511 GaussianMLPPolicy/KLAfter 0.00249132 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.43641e-06 GaussianMLPPolicy/LossBefore -7.3115e-09 GaussianMLPPolicy/dLoss 4.4291e-06 Iteration 398 MetaTest/Average/AverageDiscountedReturn -54.1859 MetaTest/Average/AverageReturn -54.1859 MetaTest/Average/Iteration 398 MetaTest/Average/MaxReturn -44.7434 MetaTest/Average/MinReturn -75.1405 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.16882 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.1859 MetaTest/__unnamed_task__/AverageReturn -54.1859 MetaTest/__unnamed_task__/Iteration 398 MetaTest/__unnamed_task__/MaxReturn -44.7434 MetaTest/__unnamed_task__/MinReturn -75.1405 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.16882 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9152e+07 __unnamed_task__/AverageDiscountedReturn -26.7678 __unnamed_task__/AverageReturn -52.1131 __unnamed_task__/Iteration 398 __unnamed_task__/MaxReturn -45.2007 __unnamed_task__/MinReturn -69.8016 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.79912 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 18:59:44 | [maml_trainer] epoch #399 | Sampling for adapation and meta-testing... 2025-04-11 19:03:55 | [maml_trainer] epoch #399 | Finished meta-testing... 2025-04-11 19:03:55 | [maml_trainer] epoch #399 | Saving snapshot... 2025-04-11 19:04:17 | [maml_trainer] epoch #399 | Saved 2025-04-11 19:04:17 | [maml_trainer] epoch #399 | Time 699901.48 s 2025-04-11 19:04:17 | [maml_trainer] epoch #399 | EpochTime 1754.31 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.2784 Average/AverageReturn -53.4214 Average/Iteration 399 Average/MaxReturn -42.5207 Average/MinReturn -91.5584 Average/NumEpisodes 120 Average/StdReturn 7.00915 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.72487 GaussianMLPPolicy/KLAfter 0.00333151 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.09426e-05 GaussianMLPPolicy/LossBefore 1.29143e-08 GaussianMLPPolicy/dLoss -6.09297e-05 Iteration 399 MetaTest/Average/AverageDiscountedReturn -52.8459 MetaTest/Average/AverageReturn -52.8459 MetaTest/Average/Iteration 399 MetaTest/Average/MaxReturn -44.4622 MetaTest/Average/MinReturn -69.5019 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.60119 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.8459 MetaTest/__unnamed_task__/AverageReturn -52.8459 MetaTest/__unnamed_task__/Iteration 399 MetaTest/__unnamed_task__/MaxReturn -44.4622 MetaTest/__unnamed_task__/MinReturn -69.5019 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.60119 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.92e+07 __unnamed_task__/AverageDiscountedReturn -27.2784 __unnamed_task__/AverageReturn -53.4214 __unnamed_task__/Iteration 399 __unnamed_task__/MaxReturn -42.5207 __unnamed_task__/MinReturn -91.5584 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.00915 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 19:28:55 | [maml_trainer] epoch #400 | Sampling for adapation and meta-testing... 2025-04-11 19:32:59 | [maml_trainer] epoch #400 | Finished meta-testing... 2025-04-11 19:32:59 | [maml_trainer] epoch #400 | Saving snapshot... 2025-04-11 19:33:20 | [maml_trainer] epoch #400 | Saved 2025-04-11 19:33:20 | [maml_trainer] epoch #400 | Time 701644.36 s 2025-04-11 19:33:20 | [maml_trainer] epoch #400 | EpochTime 1742.88 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -27.2167 Average/AverageReturn -52.8298 Average/Iteration 400 Average/MaxReturn -44.0011 Average/MinReturn -68.2693 Average/NumEpisodes 120 Average/StdReturn 5.42342 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.72484 GaussianMLPPolicy/KLAfter 0.00341866 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.88008e-05 GaussianMLPPolicy/LossBefore 1.03315e-09 GaussianMLPPolicy/dLoss 6.88018e-05 Iteration 400 MetaTest/Average/AverageDiscountedReturn -51.729 MetaTest/Average/AverageReturn -51.729 MetaTest/Average/Iteration 400 MetaTest/Average/MaxReturn -45.3076 MetaTest/Average/MinReturn -62.3369 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.46671 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.729 MetaTest/__unnamed_task__/AverageReturn -51.729 MetaTest/__unnamed_task__/Iteration 400 MetaTest/__unnamed_task__/MaxReturn -45.3076 MetaTest/__unnamed_task__/MinReturn -62.3369 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.46671 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9248e+07 __unnamed_task__/AverageDiscountedReturn -27.2167 __unnamed_task__/AverageReturn -52.8298 __unnamed_task__/Iteration 400 __unnamed_task__/MaxReturn -44.0011 __unnamed_task__/MinReturn -68.2693 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.42342 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 19:57:43 | [maml_trainer] epoch #401 | Sampling for adapation and meta-testing... 2025-04-11 20:01:48 | [maml_trainer] epoch #401 | Finished meta-testing... 2025-04-11 20:01:48 | [maml_trainer] epoch #401 | Saving snapshot... 2025-04-11 20:02:10 | [maml_trainer] epoch #401 | Saved 2025-04-11 20:02:10 | [maml_trainer] epoch #401 | Time 703374.86 s 2025-04-11 20:02:10 | [maml_trainer] epoch #401 | EpochTime 1730.50 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.5341 Average/AverageReturn -51.1387 Average/Iteration 401 Average/MaxReturn -43.9647 Average/MinReturn -65.1325 Average/NumEpisodes 120 Average/StdReturn 4.27271 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.72371 GaussianMLPPolicy/KLAfter 0.00502229 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.45049e-05 GaussianMLPPolicy/LossBefore 1.63714e-08 GaussianMLPPolicy/dLoss 7.45213e-05 Iteration 401 MetaTest/Average/AverageDiscountedReturn -50.5974 MetaTest/Average/AverageReturn -50.5974 MetaTest/Average/Iteration 401 MetaTest/Average/MaxReturn -44.3238 MetaTest/Average/MinReturn -57.6279 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.89318 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5974 MetaTest/__unnamed_task__/AverageReturn -50.5974 MetaTest/__unnamed_task__/Iteration 401 MetaTest/__unnamed_task__/MaxReturn -44.3238 MetaTest/__unnamed_task__/MinReturn -57.6279 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.89318 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9296e+07 __unnamed_task__/AverageDiscountedReturn -26.5341 __unnamed_task__/AverageReturn -51.1387 __unnamed_task__/Iteration 401 __unnamed_task__/MaxReturn -43.9647 __unnamed_task__/MinReturn -65.1325 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.27271 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 20:26:41 | [maml_trainer] epoch #402 | Sampling for adapation and meta-testing... 2025-04-11 20:30:47 | [maml_trainer] epoch #402 | Finished meta-testing... 2025-04-11 20:30:47 | [maml_trainer] epoch #402 | Saving snapshot... 2025-04-11 20:31:09 | [maml_trainer] epoch #402 | Saved 2025-04-11 20:31:09 | [maml_trainer] epoch #402 | Time 705113.27 s 2025-04-11 20:31:09 | [maml_trainer] epoch #402 | EpochTime 1738.40 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.6874 Average/AverageReturn -51.1824 Average/Iteration 402 Average/MaxReturn -42.3631 Average/MinReturn -67.5592 Average/NumEpisodes 120 Average/StdReturn 4.87778 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.72228 GaussianMLPPolicy/KLAfter 0.00429981 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000129729 GaussianMLPPolicy/LossBefore -8.1857e-09 GaussianMLPPolicy/dLoss 0.00012972 Iteration 402 MetaTest/Average/AverageDiscountedReturn -51.2657 MetaTest/Average/AverageReturn -51.2657 MetaTest/Average/Iteration 402 MetaTest/Average/MaxReturn -44.629 MetaTest/Average/MinReturn -63.7477 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.76892 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2657 MetaTest/__unnamed_task__/AverageReturn -51.2657 MetaTest/__unnamed_task__/Iteration 402 MetaTest/__unnamed_task__/MaxReturn -44.629 MetaTest/__unnamed_task__/MinReturn -63.7477 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.76892 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9344e+07 __unnamed_task__/AverageDiscountedReturn -26.6874 __unnamed_task__/AverageReturn -51.1824 __unnamed_task__/Iteration 402 __unnamed_task__/MaxReturn -42.3631 __unnamed_task__/MinReturn -67.5592 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.87778 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 20:55:58 | [maml_trainer] epoch #403 | Sampling for adapation and meta-testing... 2025-04-11 21:00:05 | [maml_trainer] epoch #403 | Finished meta-testing... 2025-04-11 21:00:05 | [maml_trainer] epoch #403 | Saving snapshot... 2025-04-11 21:00:26 | [maml_trainer] epoch #403 | Saved 2025-04-11 21:00:26 | [maml_trainer] epoch #403 | Time 706870.65 s 2025-04-11 21:00:26 | [maml_trainer] epoch #403 | EpochTime 1757.38 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.7361 Average/AverageReturn -51.3556 Average/Iteration 403 Average/MaxReturn -44.0173 Average/MinReturn -74.4358 Average/NumEpisodes 120 Average/StdReturn 4.74206 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.72112 GaussianMLPPolicy/KLAfter 0.00268456 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000105203 GaussianMLPPolicy/LossBefore -2.03451e-08 GaussianMLPPolicy/dLoss 0.000105182 Iteration 403 MetaTest/Average/AverageDiscountedReturn -51.4008 MetaTest/Average/AverageReturn -51.4008 MetaTest/Average/Iteration 403 MetaTest/Average/MaxReturn -44.9982 MetaTest/Average/MinReturn -59.5969 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.97409 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.4008 MetaTest/__unnamed_task__/AverageReturn -51.4008 MetaTest/__unnamed_task__/Iteration 403 MetaTest/__unnamed_task__/MaxReturn -44.9982 MetaTest/__unnamed_task__/MinReturn -59.5969 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.97409 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9392e+07 __unnamed_task__/AverageDiscountedReturn -26.7361 __unnamed_task__/AverageReturn -51.3556 __unnamed_task__/Iteration 403 __unnamed_task__/MaxReturn -44.0173 __unnamed_task__/MinReturn -74.4358 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.74206 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 21:25:20 | [maml_trainer] epoch #404 | Sampling for adapation and meta-testing... 2025-04-11 21:29:31 | [maml_trainer] epoch #404 | Finished meta-testing... 2025-04-11 21:29:31 | [maml_trainer] epoch #404 | Saving snapshot... 2025-04-11 21:29:53 | [maml_trainer] epoch #404 | Saved 2025-04-11 21:29:53 | [maml_trainer] epoch #404 | Time 708637.65 s 2025-04-11 21:29:53 | [maml_trainer] epoch #404 | EpochTime 1766.99 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.5992 Average/AverageReturn -51.321 Average/Iteration 404 Average/MaxReturn -42.8712 Average/MinReturn -148.605 Average/NumEpisodes 120 Average/StdReturn 9.77794 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.71989 GaussianMLPPolicy/KLAfter 0.002695 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.95195e-05 GaussianMLPPolicy/LossBefore -1.40667e-08 GaussianMLPPolicy/dLoss -9.95336e-05 Iteration 404 MetaTest/Average/AverageDiscountedReturn -49.5972 MetaTest/Average/AverageReturn -49.5972 MetaTest/Average/Iteration 404 MetaTest/Average/MaxReturn -42.8999 MetaTest/Average/MinReturn -57.483 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.89641 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5972 MetaTest/__unnamed_task__/AverageReturn -49.5972 MetaTest/__unnamed_task__/Iteration 404 MetaTest/__unnamed_task__/MaxReturn -42.8999 MetaTest/__unnamed_task__/MinReturn -57.483 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.89641 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.944e+07 __unnamed_task__/AverageDiscountedReturn -26.5992 __unnamed_task__/AverageReturn -51.321 __unnamed_task__/Iteration 404 __unnamed_task__/MaxReturn -42.8712 __unnamed_task__/MinReturn -148.605 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.77794 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 21:54:53 | [maml_trainer] epoch #405 | Sampling for adapation and meta-testing... 2025-04-11 21:59:01 | [maml_trainer] epoch #405 | Finished meta-testing... 2025-04-11 21:59:01 | [maml_trainer] epoch #405 | Saving snapshot... 2025-04-11 21:59:23 | [maml_trainer] epoch #405 | Saved 2025-04-11 21:59:23 | [maml_trainer] epoch #405 | Time 710407.82 s 2025-04-11 21:59:23 | [maml_trainer] epoch #405 | EpochTime 1770.17 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.043 Average/AverageReturn -49.7134 Average/Iteration 405 Average/MaxReturn -42.2228 Average/MinReturn -67.6647 Average/NumEpisodes 120 Average/StdReturn 3.98018 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.71769 GaussianMLPPolicy/KLAfter 0.00222343 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.57218e-05 GaussianMLPPolicy/LossBefore 1.49409e-08 GaussianMLPPolicy/dLoss 6.57367e-05 Iteration 405 MetaTest/Average/AverageDiscountedReturn -49.8093 MetaTest/Average/AverageReturn -49.8093 MetaTest/Average/Iteration 405 MetaTest/Average/MaxReturn -44.7462 MetaTest/Average/MinReturn -56.9459 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.80524 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8093 MetaTest/__unnamed_task__/AverageReturn -49.8093 MetaTest/__unnamed_task__/Iteration 405 MetaTest/__unnamed_task__/MaxReturn -44.7462 MetaTest/__unnamed_task__/MinReturn -56.9459 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.80524 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9488e+07 __unnamed_task__/AverageDiscountedReturn -26.043 __unnamed_task__/AverageReturn -49.7134 __unnamed_task__/Iteration 405 __unnamed_task__/MaxReturn -42.2228 __unnamed_task__/MinReturn -67.6647 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 3.98018 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 22:24:50 | [maml_trainer] epoch #406 | Sampling for adapation and meta-testing... 2025-04-11 22:29:03 | [maml_trainer] epoch #406 | Finished meta-testing... 2025-04-11 22:29:03 | [maml_trainer] epoch #406 | Saving snapshot... 2025-04-11 22:29:25 | [maml_trainer] epoch #406 | Saved 2025-04-11 22:29:25 | [maml_trainer] epoch #406 | Time 712209.82 s 2025-04-11 22:29:25 | [maml_trainer] epoch #406 | EpochTime 1802.00 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -25.9601 Average/AverageReturn -49.2929 Average/Iteration 406 Average/MaxReturn -43.2377 Average/MinReturn -63.1984 Average/NumEpisodes 120 Average/StdReturn 3.46093 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.71483 GaussianMLPPolicy/KLAfter 0.00222272 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000139978 GaussianMLPPolicy/LossBefore -2.28882e-08 GaussianMLPPolicy/dLoss 0.000139956 Iteration 406 MetaTest/Average/AverageDiscountedReturn -49.9647 MetaTest/Average/AverageReturn -49.9647 MetaTest/Average/Iteration 406 MetaTest/Average/MaxReturn -45.5664 MetaTest/Average/MinReturn -55.9047 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 2.96144 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.9647 MetaTest/__unnamed_task__/AverageReturn -49.9647 MetaTest/__unnamed_task__/Iteration 406 MetaTest/__unnamed_task__/MaxReturn -45.5664 MetaTest/__unnamed_task__/MinReturn -55.9047 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 2.96144 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9536e+07 __unnamed_task__/AverageDiscountedReturn -25.9601 __unnamed_task__/AverageReturn -49.2929 __unnamed_task__/Iteration 406 __unnamed_task__/MaxReturn -43.2377 __unnamed_task__/MinReturn -63.1984 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 3.46093 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-11 22:54:20 | [maml_trainer] epoch #407 | Sampling for adapation and meta-testing... 2025-04-11 22:58:31 | [maml_trainer] epoch #407 | Finished meta-testing... 2025-04-11 22:58:31 | [maml_trainer] epoch #407 | Saving snapshot... 2025-04-11 22:58:52 | [maml_trainer] epoch #407 | Saved 2025-04-11 22:58:52 | [maml_trainer] epoch #407 | Time 713976.86 s 2025-04-11 22:58:52 | [maml_trainer] epoch #407 | EpochTime 1767.04 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.0649 Average/AverageReturn -49.9898 Average/Iteration 407 Average/MaxReturn -43.5763 Average/MinReturn -105.079 Average/NumEpisodes 120 Average/StdReturn 6.20756 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.71242 GaussianMLPPolicy/KLAfter 0.00431086 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.91141e-05 GaussianMLPPolicy/LossBefore -4.76837e-10 GaussianMLPPolicy/dLoss 7.91136e-05 Iteration 407 MetaTest/Average/AverageDiscountedReturn -48.3891 MetaTest/Average/AverageReturn -48.3891 MetaTest/Average/Iteration 407 MetaTest/Average/MaxReturn -41.736 MetaTest/Average/MinReturn -60.9145 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.15222 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.3891 MetaTest/__unnamed_task__/AverageReturn -48.3891 MetaTest/__unnamed_task__/Iteration 407 MetaTest/__unnamed_task__/MaxReturn -41.736 MetaTest/__unnamed_task__/MinReturn -60.9145 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.15222 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9584e+07 __unnamed_task__/AverageDiscountedReturn -26.0649 __unnamed_task__/AverageReturn -49.9898 __unnamed_task__/Iteration 407 __unnamed_task__/MaxReturn -43.5763 __unnamed_task__/MinReturn -105.079 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.20756 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 23:24:02 | [maml_trainer] epoch #408 | Sampling for adapation and meta-testing... 2025-04-11 23:28:12 | [maml_trainer] epoch #408 | Finished meta-testing... 2025-04-11 23:28:12 | [maml_trainer] epoch #408 | Saving snapshot... 2025-04-11 23:28:34 | [maml_trainer] epoch #408 | Saved 2025-04-11 23:28:34 | [maml_trainer] epoch #408 | Time 715758.83 s 2025-04-11 23:28:34 | [maml_trainer] epoch #408 | EpochTime 1781.96 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.1595 Average/AverageReturn -49.9426 Average/Iteration 408 Average/MaxReturn -42.8164 Average/MinReturn -114.148 Average/NumEpisodes 120 Average/StdReturn 7.30738 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.70962 GaussianMLPPolicy/KLAfter 0.00794484 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.49872e-05 GaussianMLPPolicy/LossBefore -5.5631e-09 GaussianMLPPolicy/dLoss -6.49928e-05 Iteration 408 MetaTest/Average/AverageDiscountedReturn -48.9374 MetaTest/Average/AverageReturn -48.9374 MetaTest/Average/Iteration 408 MetaTest/Average/MaxReturn -41.133 MetaTest/Average/MinReturn -58.8875 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.0769 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9374 MetaTest/__unnamed_task__/AverageReturn -48.9374 MetaTest/__unnamed_task__/Iteration 408 MetaTest/__unnamed_task__/MaxReturn -41.133 MetaTest/__unnamed_task__/MinReturn -58.8875 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.0769 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9632e+07 __unnamed_task__/AverageDiscountedReturn -26.1595 __unnamed_task__/AverageReturn -49.9426 __unnamed_task__/Iteration 408 __unnamed_task__/MaxReturn -42.8164 __unnamed_task__/MinReturn -114.148 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.30738 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-11 23:53:25 | [maml_trainer] epoch #409 | Sampling for adapation and meta-testing... 2025-04-11 23:57:31 | [maml_trainer] epoch #409 | Finished meta-testing... 2025-04-11 23:57:31 | [maml_trainer] epoch #409 | Saving snapshot... 2025-04-11 23:57:52 | [maml_trainer] epoch #409 | Saved 2025-04-11 23:57:52 | [maml_trainer] epoch #409 | Time 717516.92 s 2025-04-11 23:57:52 | [maml_trainer] epoch #409 | EpochTime 1758.09 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.2498 Average/AverageReturn -49.7597 Average/Iteration 409 Average/MaxReturn -43.3303 Average/MinReturn -67.9593 Average/NumEpisodes 120 Average/StdReturn 4.2085 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.70601 GaussianMLPPolicy/KLAfter 0.00609624 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.72737e-05 GaussianMLPPolicy/LossBefore 1.27157e-08 GaussianMLPPolicy/dLoss 1.72865e-05 Iteration 409 MetaTest/Average/AverageDiscountedReturn -48.7964 MetaTest/Average/AverageReturn -48.7964 MetaTest/Average/Iteration 409 MetaTest/Average/MaxReturn -42.131 MetaTest/Average/MinReturn -61.309 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.49014 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.7964 MetaTest/__unnamed_task__/AverageReturn -48.7964 MetaTest/__unnamed_task__/Iteration 409 MetaTest/__unnamed_task__/MaxReturn -42.131 MetaTest/__unnamed_task__/MinReturn -61.309 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.49014 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.968e+07 __unnamed_task__/AverageDiscountedReturn -26.2498 __unnamed_task__/AverageReturn -49.7597 __unnamed_task__/Iteration 409 __unnamed_task__/MaxReturn -43.3303 __unnamed_task__/MinReturn -67.9593 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.2085 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 00:22:34 | [maml_trainer] epoch #410 | Sampling for adapation and meta-testing... 2025-04-12 00:26:44 | [maml_trainer] epoch #410 | Finished meta-testing... 2025-04-12 00:26:44 | [maml_trainer] epoch #410 | Saving snapshot... 2025-04-12 00:27:05 | [maml_trainer] epoch #410 | Saved 2025-04-12 00:27:05 | [maml_trainer] epoch #410 | Time 719269.68 s 2025-04-12 00:27:05 | [maml_trainer] epoch #410 | EpochTime 1752.75 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.0749 Average/AverageReturn -49.3678 Average/Iteration 410 Average/MaxReturn -42.596 Average/MinReturn -64.3921 Average/NumEpisodes 120 Average/StdReturn 3.96236 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.70304 GaussianMLPPolicy/KLAfter 0.00456303 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.7024e-05 GaussianMLPPolicy/LossBefore -7.62939e-09 GaussianMLPPolicy/dLoss 1.70163e-05 Iteration 410 MetaTest/Average/AverageDiscountedReturn -50.2222 MetaTest/Average/AverageReturn -50.2222 MetaTest/Average/Iteration 410 MetaTest/Average/MaxReturn -41.7096 MetaTest/Average/MinReturn -66.9103 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.09523 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.2222 MetaTest/__unnamed_task__/AverageReturn -50.2222 MetaTest/__unnamed_task__/Iteration 410 MetaTest/__unnamed_task__/MaxReturn -41.7096 MetaTest/__unnamed_task__/MinReturn -66.9103 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.09523 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9728e+07 __unnamed_task__/AverageDiscountedReturn -26.0749 __unnamed_task__/AverageReturn -49.3678 __unnamed_task__/Iteration 410 __unnamed_task__/MaxReturn -42.596 __unnamed_task__/MinReturn -64.3921 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 3.96236 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 00:52:07 | [maml_trainer] epoch #411 | Sampling for adapation and meta-testing... 2025-04-12 00:56:15 | [maml_trainer] epoch #411 | Finished meta-testing... 2025-04-12 00:56:15 | [maml_trainer] epoch #411 | Saving snapshot... 2025-04-12 00:56:37 | [maml_trainer] epoch #411 | Saved 2025-04-12 00:56:37 | [maml_trainer] epoch #411 | Time 721040.98 s 2025-04-12 00:56:37 | [maml_trainer] epoch #411 | EpochTime 1771.30 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -26.1171 Average/AverageReturn -49.8206 Average/Iteration 411 Average/MaxReturn -41.3978 Average/MinReturn -89.9209 Average/NumEpisodes 120 Average/StdReturn 5.36615 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69927 GaussianMLPPolicy/KLAfter 0.00249786 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.32937e-05 GaussianMLPPolicy/LossBefore 1.7484e-09 GaussianMLPPolicy/dLoss 2.32954e-05 Iteration 411 MetaTest/Average/AverageDiscountedReturn -48.3262 MetaTest/Average/AverageReturn -48.3262 MetaTest/Average/Iteration 411 MetaTest/Average/MaxReturn -43.5117 MetaTest/Average/MinReturn -54.9406 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 2.93288 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.3262 MetaTest/__unnamed_task__/AverageReturn -48.3262 MetaTest/__unnamed_task__/Iteration 411 MetaTest/__unnamed_task__/MaxReturn -43.5117 MetaTest/__unnamed_task__/MinReturn -54.9406 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 2.93288 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9776e+07 __unnamed_task__/AverageDiscountedReturn -26.1171 __unnamed_task__/AverageReturn -49.8206 __unnamed_task__/Iteration 411 __unnamed_task__/MaxReturn -41.3978 __unnamed_task__/MinReturn -89.9209 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.36615 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 01:21:27 | [maml_trainer] epoch #412 | Sampling for adapation and meta-testing... 2025-04-12 01:25:36 | [maml_trainer] epoch #412 | Finished meta-testing... 2025-04-12 01:25:36 | [maml_trainer] epoch #412 | Saving snapshot... 2025-04-12 01:25:57 | [maml_trainer] epoch #412 | Saved 2025-04-12 01:25:57 | [maml_trainer] epoch #412 | Time 722801.38 s 2025-04-12 01:25:57 | [maml_trainer] epoch #412 | EpochTime 1760.39 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.0192 Average/AverageReturn -49.2314 Average/Iteration 412 Average/MaxReturn -40.9618 Average/MinReturn -100.281 Average/NumEpisodes 120 Average/StdReturn 6.0238 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69652 GaussianMLPPolicy/KLAfter 0.00338616 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.87846e-05 GaussianMLPPolicy/LossBefore -1.16825e-08 GaussianMLPPolicy/dLoss 7.87729e-05 Iteration 412 MetaTest/Average/AverageDiscountedReturn -50.1949 MetaTest/Average/AverageReturn -50.1949 MetaTest/Average/Iteration 412 MetaTest/Average/MaxReturn -42.8192 MetaTest/Average/MinReturn -62.5167 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.30909 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.1949 MetaTest/__unnamed_task__/AverageReturn -50.1949 MetaTest/__unnamed_task__/Iteration 412 MetaTest/__unnamed_task__/MaxReturn -42.8192 MetaTest/__unnamed_task__/MinReturn -62.5167 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.30909 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9824e+07 __unnamed_task__/AverageDiscountedReturn -26.0192 __unnamed_task__/AverageReturn -49.2314 __unnamed_task__/Iteration 412 __unnamed_task__/MaxReturn -40.9618 __unnamed_task__/MinReturn -100.281 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.0238 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 01:50:34 | [maml_trainer] epoch #413 | Sampling for adapation and meta-testing... 2025-04-12 01:54:47 | [maml_trainer] epoch #413 | Finished meta-testing... 2025-04-12 01:54:47 | [maml_trainer] epoch #413 | Saving snapshot... 2025-04-12 01:55:08 | [maml_trainer] epoch #413 | Saved 2025-04-12 01:55:08 | [maml_trainer] epoch #413 | Time 724552.93 s 2025-04-12 01:55:08 | [maml_trainer] epoch #413 | EpochTime 1751.54 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -25.6447 Average/AverageReturn -48.5356 Average/Iteration 413 Average/MaxReturn -42.1924 Average/MinReturn -73.2416 Average/NumEpisodes 120 Average/StdReturn 4.45418 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.6937 GaussianMLPPolicy/KLAfter 0.00289735 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.98184e-06 GaussianMLPPolicy/LossBefore -3.25044e-08 GaussianMLPPolicy/dLoss 4.94933e-06 Iteration 413 MetaTest/Average/AverageDiscountedReturn -48.5605 MetaTest/Average/AverageReturn -48.5605 MetaTest/Average/Iteration 413 MetaTest/Average/MaxReturn -40.121 MetaTest/Average/MinReturn -56.2503 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.91363 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.5605 MetaTest/__unnamed_task__/AverageReturn -48.5605 MetaTest/__unnamed_task__/Iteration 413 MetaTest/__unnamed_task__/MaxReturn -40.121 MetaTest/__unnamed_task__/MinReturn -56.2503 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.91363 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9872e+07 __unnamed_task__/AverageDiscountedReturn -25.6447 __unnamed_task__/AverageReturn -48.5356 __unnamed_task__/Iteration 413 __unnamed_task__/MaxReturn -42.1924 __unnamed_task__/MinReturn -73.2416 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.45418 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 02:19:57 | [maml_trainer] epoch #414 | Sampling for adapation and meta-testing... 2025-04-12 02:24:06 | [maml_trainer] epoch #414 | Finished meta-testing... 2025-04-12 02:24:06 | [maml_trainer] epoch #414 | Saving snapshot... 2025-04-12 02:24:28 | [maml_trainer] epoch #414 | Saved 2025-04-12 02:24:28 | [maml_trainer] epoch #414 | Time 726312.28 s 2025-04-12 02:24:28 | [maml_trainer] epoch #414 | EpochTime 1759.35 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -25.6798 Average/AverageReturn -48.5631 Average/Iteration 414 Average/MaxReturn -40.6723 Average/MinReturn -65.6389 Average/NumEpisodes 120 Average/StdReturn 4.287 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69174 GaussianMLPPolicy/KLAfter 0.0028878 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.23391e-05 GaussianMLPPolicy/LossBefore 1.38283e-08 GaussianMLPPolicy/dLoss 4.23529e-05 Iteration 414 MetaTest/Average/AverageDiscountedReturn -48.6917 MetaTest/Average/AverageReturn -48.6917 MetaTest/Average/Iteration 414 MetaTest/Average/MaxReturn -40.7698 MetaTest/Average/MinReturn -57.8856 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.74015 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.6917 MetaTest/__unnamed_task__/AverageReturn -48.6917 MetaTest/__unnamed_task__/Iteration 414 MetaTest/__unnamed_task__/MaxReturn -40.7698 MetaTest/__unnamed_task__/MinReturn -57.8856 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.74015 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.992e+07 __unnamed_task__/AverageDiscountedReturn -25.6798 __unnamed_task__/AverageReturn -48.5631 __unnamed_task__/Iteration 414 __unnamed_task__/MaxReturn -40.6723 __unnamed_task__/MinReturn -65.6389 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.287 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 02:49:15 | [maml_trainer] epoch #415 | Sampling for adapation and meta-testing... 2025-04-12 02:53:23 | [maml_trainer] epoch #415 | Finished meta-testing... 2025-04-12 02:53:23 | [maml_trainer] epoch #415 | Saving snapshot... 2025-04-12 02:53:45 | [maml_trainer] epoch #415 | Saved 2025-04-12 02:53:45 | [maml_trainer] epoch #415 | Time 728069.94 s 2025-04-12 02:53:45 | [maml_trainer] epoch #415 | EpochTime 1757.66 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -25.9407 Average/AverageReturn -49.3099 Average/Iteration 415 Average/MaxReturn -40.0121 Average/MinReturn -70.5578 Average/NumEpisodes 120 Average/StdReturn 5.25371 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69083 GaussianMLPPolicy/KLAfter 0.00250219 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.93705e-06 GaussianMLPPolicy/LossBefore -8.42412e-09 GaussianMLPPolicy/dLoss 3.92862e-06 Iteration 415 MetaTest/Average/AverageDiscountedReturn -48.9318 MetaTest/Average/AverageReturn -48.9318 MetaTest/Average/Iteration 415 MetaTest/Average/MaxReturn -40.295 MetaTest/Average/MinReturn -63.7715 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.59946 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9318 MetaTest/__unnamed_task__/AverageReturn -48.9318 MetaTest/__unnamed_task__/Iteration 415 MetaTest/__unnamed_task__/MaxReturn -40.295 MetaTest/__unnamed_task__/MinReturn -63.7715 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.59946 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.9968e+07 __unnamed_task__/AverageDiscountedReturn -25.9407 __unnamed_task__/AverageReturn -49.3099 __unnamed_task__/Iteration 415 __unnamed_task__/MaxReturn -40.0121 __unnamed_task__/MinReturn -70.5578 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.25371 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 03:18:15 | [maml_trainer] epoch #416 | Sampling for adapation and meta-testing... 2025-04-12 03:22:18 | [maml_trainer] epoch #416 | Finished meta-testing... 2025-04-12 03:22:18 | [maml_trainer] epoch #416 | Saving snapshot... 2025-04-12 03:22:39 | [maml_trainer] epoch #416 | Saved 2025-04-12 03:22:39 | [maml_trainer] epoch #416 | Time 729803.27 s 2025-04-12 03:22:39 | [maml_trainer] epoch #416 | EpochTime 1733.33 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -25.9196 Average/AverageReturn -49.2299 Average/Iteration 416 Average/MaxReturn -41.587 Average/MinReturn -72.0537 Average/NumEpisodes 120 Average/StdReturn 5.1897 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68893 GaussianMLPPolicy/KLAfter 0.00145986 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.09366e-06 GaussianMLPPolicy/LossBefore -8.74202e-10 GaussianMLPPolicy/dLoss -6.09454e-06 Iteration 416 MetaTest/Average/AverageDiscountedReturn -48.5987 MetaTest/Average/AverageReturn -48.5987 MetaTest/Average/Iteration 416 MetaTest/Average/MaxReturn -39.5893 MetaTest/Average/MinReturn -62.4714 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.18019 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.5987 MetaTest/__unnamed_task__/AverageReturn -48.5987 MetaTest/__unnamed_task__/Iteration 416 MetaTest/__unnamed_task__/MaxReturn -39.5893 MetaTest/__unnamed_task__/MinReturn -62.4714 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.18019 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0016e+07 __unnamed_task__/AverageDiscountedReturn -25.9196 __unnamed_task__/AverageReturn -49.2299 __unnamed_task__/Iteration 416 __unnamed_task__/MaxReturn -41.587 __unnamed_task__/MinReturn -72.0537 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.1897 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 03:46:52 | [maml_trainer] epoch #417 | Sampling for adapation and meta-testing... 2025-04-12 03:50:53 | [maml_trainer] epoch #417 | Finished meta-testing... 2025-04-12 03:50:53 | [maml_trainer] epoch #417 | Saving snapshot... 2025-04-12 03:51:14 | [maml_trainer] epoch #417 | Saved 2025-04-12 03:51:14 | [maml_trainer] epoch #417 | Time 731518.67 s 2025-04-12 03:51:14 | [maml_trainer] epoch #417 | EpochTime 1715.40 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -25.2946 Average/AverageReturn -47.7387 Average/Iteration 417 Average/MaxReturn -39.5605 Average/MinReturn -69.5652 Average/NumEpisodes 120 Average/StdReturn 4.51208 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.6866 GaussianMLPPolicy/KLAfter 0.00183537 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.83242e-05 GaussianMLPPolicy/LossBefore -7.78834e-09 GaussianMLPPolicy/dLoss -6.8332e-05 Iteration 417 MetaTest/Average/AverageDiscountedReturn -50.9015 MetaTest/Average/AverageReturn -50.9015 MetaTest/Average/Iteration 417 MetaTest/Average/MaxReturn -41.5113 MetaTest/Average/MinReturn -77.2844 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.62928 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.9015 MetaTest/__unnamed_task__/AverageReturn -50.9015 MetaTest/__unnamed_task__/Iteration 417 MetaTest/__unnamed_task__/MaxReturn -41.5113 MetaTest/__unnamed_task__/MinReturn -77.2844 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.62928 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0064e+07 __unnamed_task__/AverageDiscountedReturn -25.2946 __unnamed_task__/AverageReturn -47.7387 __unnamed_task__/Iteration 417 __unnamed_task__/MaxReturn -39.5605 __unnamed_task__/MinReturn -69.5652 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.51208 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 04:15:58 | [maml_trainer] epoch #418 | Sampling for adapation and meta-testing... 2025-04-12 04:20:01 | [maml_trainer] epoch #418 | Finished meta-testing... 2025-04-12 04:20:01 | [maml_trainer] epoch #418 | Saving snapshot... 2025-04-12 04:20:23 | [maml_trainer] epoch #418 | Saved 2025-04-12 04:20:23 | [maml_trainer] epoch #418 | Time 733267.94 s 2025-04-12 04:20:23 | [maml_trainer] epoch #418 | EpochTime 1749.27 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -26.0981 Average/AverageReturn -49.8901 Average/Iteration 418 Average/MaxReturn -39.8408 Average/MinReturn -72.5622 Average/NumEpisodes 120 Average/StdReturn 6.93756 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68568 GaussianMLPPolicy/KLAfter 0.00195872 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.88603e-05 GaussianMLPPolicy/LossBefore -5.72205e-09 GaussianMLPPolicy/dLoss 3.88546e-05 Iteration 418 MetaTest/Average/AverageDiscountedReturn -49.6256 MetaTest/Average/AverageReturn -49.6256 MetaTest/Average/Iteration 418 MetaTest/Average/MaxReturn -39.5342 MetaTest/Average/MinReturn -126.56 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.0275 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.6256 MetaTest/__unnamed_task__/AverageReturn -49.6256 MetaTest/__unnamed_task__/Iteration 418 MetaTest/__unnamed_task__/MaxReturn -39.5342 MetaTest/__unnamed_task__/MinReturn -126.56 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.0275 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0112e+07 __unnamed_task__/AverageDiscountedReturn -26.0981 __unnamed_task__/AverageReturn -49.8901 __unnamed_task__/Iteration 418 __unnamed_task__/MaxReturn -39.8408 __unnamed_task__/MinReturn -72.5622 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.93756 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 04:44:40 | [maml_trainer] epoch #419 | Sampling for adapation and meta-testing... 2025-04-12 04:48:45 | [maml_trainer] epoch #419 | Finished meta-testing... 2025-04-12 04:48:45 | [maml_trainer] epoch #419 | Saving snapshot... 2025-04-12 04:49:08 | [maml_trainer] epoch #419 | Saved 2025-04-12 04:49:08 | [maml_trainer] epoch #419 | Time 734992.03 s 2025-04-12 04:49:08 | [maml_trainer] epoch #419 | EpochTime 1724.08 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -25.1537 Average/AverageReturn -47.182 Average/Iteration 419 Average/MaxReturn -38.887 Average/MinReturn -62.8229 Average/NumEpisodes 120 Average/StdReturn 4.41433 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68569 GaussianMLPPolicy/KLAfter 0.00338315 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000109456 GaussianMLPPolicy/LossBefore 1.98682e-09 GaussianMLPPolicy/dLoss 0.000109457 Iteration 419 MetaTest/Average/AverageDiscountedReturn -47.4648 MetaTest/Average/AverageReturn -47.4648 MetaTest/Average/Iteration 419 MetaTest/Average/MaxReturn -40.3317 MetaTest/Average/MinReturn -66.7768 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.40842 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4648 MetaTest/__unnamed_task__/AverageReturn -47.4648 MetaTest/__unnamed_task__/Iteration 419 MetaTest/__unnamed_task__/MaxReturn -40.3317 MetaTest/__unnamed_task__/MinReturn -66.7768 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.40842 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.016e+07 __unnamed_task__/AverageDiscountedReturn -25.1537 __unnamed_task__/AverageReturn -47.182 __unnamed_task__/Iteration 419 __unnamed_task__/MaxReturn -38.887 __unnamed_task__/MinReturn -62.8229 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.41433 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 05:13:29 | [maml_trainer] epoch #420 | Sampling for adapation and meta-testing... 2025-04-12 05:17:35 | [maml_trainer] epoch #420 | Finished meta-testing... 2025-04-12 05:17:35 | [maml_trainer] epoch #420 | Saving snapshot... 2025-04-12 05:17:57 | [maml_trainer] epoch #420 | Saved 2025-04-12 05:17:57 | [maml_trainer] epoch #420 | Time 736721.38 s 2025-04-12 05:17:57 | [maml_trainer] epoch #420 | EpochTime 1729.35 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -25.6389 Average/AverageReturn -48.631 Average/Iteration 420 Average/MaxReturn -38.7306 Average/MinReturn -67.574 Average/NumEpisodes 120 Average/StdReturn 6.04645 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.6867 GaussianMLPPolicy/KLAfter 0.00544083 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000136226 GaussianMLPPolicy/LossBefore -9.53674e-10 GaussianMLPPolicy/dLoss -0.000136227 Iteration 420 MetaTest/Average/AverageDiscountedReturn -48.6493 MetaTest/Average/AverageReturn -48.6493 MetaTest/Average/Iteration 420 MetaTest/Average/MaxReturn -40.9392 MetaTest/Average/MinReturn -58.7531 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.61899 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.6493 MetaTest/__unnamed_task__/AverageReturn -48.6493 MetaTest/__unnamed_task__/Iteration 420 MetaTest/__unnamed_task__/MaxReturn -40.9392 MetaTest/__unnamed_task__/MinReturn -58.7531 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.61899 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0208e+07 __unnamed_task__/AverageDiscountedReturn -25.6389 __unnamed_task__/AverageReturn -48.631 __unnamed_task__/Iteration 420 __unnamed_task__/MaxReturn -38.7306 __unnamed_task__/MinReturn -67.574 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.04645 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 05:42:59 | [maml_trainer] epoch #421 | Sampling for adapation and meta-testing... 2025-04-12 05:47:02 | [maml_trainer] epoch #421 | Finished meta-testing... 2025-04-12 05:47:02 | [maml_trainer] epoch #421 | Saving snapshot... 2025-04-12 05:47:23 | [maml_trainer] epoch #421 | Saved 2025-04-12 05:47:23 | [maml_trainer] epoch #421 | Time 738487.31 s 2025-04-12 05:47:23 | [maml_trainer] epoch #421 | EpochTime 1765.93 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.238 Average/AverageReturn -47.3541 Average/Iteration 421 Average/MaxReturn -37.7746 Average/MinReturn -64.6536 Average/NumEpisodes 120 Average/StdReturn 5.06678 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68847 GaussianMLPPolicy/KLAfter 0.00481901 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.73218e-05 GaussianMLPPolicy/LossBefore -1.71661e-08 GaussianMLPPolicy/dLoss 2.73046e-05 Iteration 421 MetaTest/Average/AverageDiscountedReturn -50.1252 MetaTest/Average/AverageReturn -50.1252 MetaTest/Average/Iteration 421 MetaTest/Average/MaxReturn -41.2806 MetaTest/Average/MinReturn -100.017 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.8504 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.1252 MetaTest/__unnamed_task__/AverageReturn -50.1252 MetaTest/__unnamed_task__/Iteration 421 MetaTest/__unnamed_task__/MaxReturn -41.2806 MetaTest/__unnamed_task__/MinReturn -100.017 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.8504 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0256e+07 __unnamed_task__/AverageDiscountedReturn -25.238 __unnamed_task__/AverageReturn -47.3541 __unnamed_task__/Iteration 421 __unnamed_task__/MaxReturn -37.7746 __unnamed_task__/MinReturn -64.6536 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.06678 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 06:11:41 | [maml_trainer] epoch #422 | Sampling for adapation and meta-testing... 2025-04-12 06:15:47 | [maml_trainer] epoch #422 | Finished meta-testing... 2025-04-12 06:15:47 | [maml_trainer] epoch #422 | Saving snapshot... 2025-04-12 06:16:09 | [maml_trainer] epoch #422 | Saved 2025-04-12 06:16:09 | [maml_trainer] epoch #422 | Time 740213.87 s 2025-04-12 06:16:09 | [maml_trainer] epoch #422 | EpochTime 1726.56 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -25.0263 Average/AverageReturn -46.8799 Average/Iteration 422 Average/MaxReturn -37.7596 Average/MinReturn -69.4972 Average/NumEpisodes 120 Average/StdReturn 5.66455 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.691 GaussianMLPPolicy/KLAfter 0.00674391 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.00022455 GaussianMLPPolicy/LossBefore 3.33786e-09 GaussianMLPPolicy/dLoss 0.000224553 Iteration 422 MetaTest/Average/AverageDiscountedReturn -47.2368 MetaTest/Average/AverageReturn -47.2368 MetaTest/Average/Iteration 422 MetaTest/Average/MaxReturn -41.8377 MetaTest/Average/MinReturn -60.1403 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.33291 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.2368 MetaTest/__unnamed_task__/AverageReturn -47.2368 MetaTest/__unnamed_task__/Iteration 422 MetaTest/__unnamed_task__/MaxReturn -41.8377 MetaTest/__unnamed_task__/MinReturn -60.1403 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.33291 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0304e+07 __unnamed_task__/AverageDiscountedReturn -25.0263 __unnamed_task__/AverageReturn -46.8799 __unnamed_task__/Iteration 422 __unnamed_task__/MaxReturn -37.7596 __unnamed_task__/MinReturn -69.4972 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.66455 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 06:40:43 | [maml_trainer] epoch #423 | Sampling for adapation and meta-testing... 2025-04-12 06:44:46 | [maml_trainer] epoch #423 | Finished meta-testing... 2025-04-12 06:44:46 | [maml_trainer] epoch #423 | Saving snapshot... 2025-04-12 06:45:08 | [maml_trainer] epoch #423 | Saved 2025-04-12 06:45:08 | [maml_trainer] epoch #423 | Time 741952.43 s 2025-04-12 06:45:08 | [maml_trainer] epoch #423 | EpochTime 1738.55 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.0897 Average/AverageReturn -47.2607 Average/Iteration 423 Average/MaxReturn -38.5597 Average/MinReturn -126.469 Average/NumEpisodes 120 Average/StdReturn 8.73626 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69186 GaussianMLPPolicy/KLAfter 0.00543504 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.07935e-05 GaussianMLPPolicy/LossBefore 4.88758e-09 GaussianMLPPolicy/dLoss 6.07984e-05 Iteration 423 MetaTest/Average/AverageDiscountedReturn -44.9376 MetaTest/Average/AverageReturn -44.9376 MetaTest/Average/Iteration 423 MetaTest/Average/MaxReturn -41.3234 MetaTest/Average/MinReturn -52.0088 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 2.92842 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.9376 MetaTest/__unnamed_task__/AverageReturn -44.9376 MetaTest/__unnamed_task__/Iteration 423 MetaTest/__unnamed_task__/MaxReturn -41.3234 MetaTest/__unnamed_task__/MinReturn -52.0088 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 2.92842 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0352e+07 __unnamed_task__/AverageDiscountedReturn -25.0897 __unnamed_task__/AverageReturn -47.2607 __unnamed_task__/Iteration 423 __unnamed_task__/MaxReturn -38.5597 __unnamed_task__/MinReturn -126.469 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.73626 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 07:09:36 | [maml_trainer] epoch #424 | Sampling for adapation and meta-testing... 2025-04-12 07:13:41 | [maml_trainer] epoch #424 | Finished meta-testing... 2025-04-12 07:13:41 | [maml_trainer] epoch #424 | Saving snapshot... 2025-04-12 07:14:03 | [maml_trainer] epoch #424 | Saved 2025-04-12 07:14:03 | [maml_trainer] epoch #424 | Time 743687.27 s 2025-04-12 07:14:03 | [maml_trainer] epoch #424 | EpochTime 1734.84 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.0479 Average/AverageReturn -47.4139 Average/Iteration 424 Average/MaxReturn -37.5423 Average/MinReturn -123.548 Average/NumEpisodes 120 Average/StdReturn 9.71423 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69179 GaussianMLPPolicy/KLAfter 0.00657709 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000108118 GaussianMLPPolicy/LossBefore 2.90076e-09 GaussianMLPPolicy/dLoss -0.000108115 Iteration 424 MetaTest/Average/AverageDiscountedReturn -45.1099 MetaTest/Average/AverageReturn -45.1099 MetaTest/Average/Iteration 424 MetaTest/Average/MaxReturn -39.8151 MetaTest/Average/MinReturn -51.5798 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.07353 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.1099 MetaTest/__unnamed_task__/AverageReturn -45.1099 MetaTest/__unnamed_task__/Iteration 424 MetaTest/__unnamed_task__/MaxReturn -39.8151 MetaTest/__unnamed_task__/MinReturn -51.5798 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.07353 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.04e+07 __unnamed_task__/AverageDiscountedReturn -25.0479 __unnamed_task__/AverageReturn -47.4139 __unnamed_task__/Iteration 424 __unnamed_task__/MaxReturn -37.5423 __unnamed_task__/MinReturn -123.548 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.71423 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 07:38:35 | [maml_trainer] epoch #425 | Sampling for adapation and meta-testing... 2025-04-12 07:42:44 | [maml_trainer] epoch #425 | Finished meta-testing... 2025-04-12 07:42:44 | [maml_trainer] epoch #425 | Saving snapshot... 2025-04-12 07:43:05 | [maml_trainer] epoch #425 | Saved 2025-04-12 07:43:05 | [maml_trainer] epoch #425 | Time 745429.75 s 2025-04-12 07:43:05 | [maml_trainer] epoch #425 | EpochTime 1742.48 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.4655 Average/AverageReturn -45.8498 Average/Iteration 425 Average/MaxReturn -37.3991 Average/MinReturn -58.5289 Average/NumEpisodes 120 Average/StdReturn 4.33793 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69133 GaussianMLPPolicy/KLAfter 0.00498156 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.36079e-06 GaussianMLPPolicy/LossBefore -1.38283e-08 GaussianMLPPolicy/dLoss 9.34696e-06 Iteration 425 MetaTest/Average/AverageDiscountedReturn -46.9447 MetaTest/Average/AverageReturn -46.9447 MetaTest/Average/Iteration 425 MetaTest/Average/MaxReturn -41.267 MetaTest/Average/MinReturn -64.7598 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.32906 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.9447 MetaTest/__unnamed_task__/AverageReturn -46.9447 MetaTest/__unnamed_task__/Iteration 425 MetaTest/__unnamed_task__/MaxReturn -41.267 MetaTest/__unnamed_task__/MinReturn -64.7598 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.32906 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0448e+07 __unnamed_task__/AverageDiscountedReturn -24.4655 __unnamed_task__/AverageReturn -45.8498 __unnamed_task__/Iteration 425 __unnamed_task__/MaxReturn -37.3991 __unnamed_task__/MinReturn -58.5289 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.33793 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 08:07:58 | [maml_trainer] epoch #426 | Sampling for adapation and meta-testing... 2025-04-12 08:12:05 | [maml_trainer] epoch #426 | Finished meta-testing... 2025-04-12 08:12:05 | [maml_trainer] epoch #426 | Saving snapshot... 2025-04-12 08:12:27 | [maml_trainer] epoch #426 | Saved 2025-04-12 08:12:27 | [maml_trainer] epoch #426 | Time 747191.03 s 2025-04-12 08:12:27 | [maml_trainer] epoch #426 | EpochTime 1761.27 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.9687 Average/AverageReturn -47.263 Average/Iteration 426 Average/MaxReturn -38.6203 Average/MinReturn -131.444 Average/NumEpisodes 120 Average/StdReturn 11.7702 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69132 GaussianMLPPolicy/KLAfter 0.00274212 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.4908e-05 GaussianMLPPolicy/LossBefore 9.17912e-09 GaussianMLPPolicy/dLoss 6.49172e-05 Iteration 426 MetaTest/Average/AverageDiscountedReturn -46.0579 MetaTest/Average/AverageReturn -46.0579 MetaTest/Average/Iteration 426 MetaTest/Average/MaxReturn -40.0957 MetaTest/Average/MinReturn -52.8854 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.02208 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.0579 MetaTest/__unnamed_task__/AverageReturn -46.0579 MetaTest/__unnamed_task__/Iteration 426 MetaTest/__unnamed_task__/MaxReturn -40.0957 MetaTest/__unnamed_task__/MinReturn -52.8854 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.02208 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0496e+07 __unnamed_task__/AverageDiscountedReturn -24.9687 __unnamed_task__/AverageReturn -47.263 __unnamed_task__/Iteration 426 __unnamed_task__/MaxReturn -38.6203 __unnamed_task__/MinReturn -131.444 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.7702 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 08:37:16 | [maml_trainer] epoch #427 | Sampling for adapation and meta-testing... 2025-04-12 08:41:21 | [maml_trainer] epoch #427 | Finished meta-testing... 2025-04-12 08:41:21 | [maml_trainer] epoch #427 | Saving snapshot... 2025-04-12 08:41:43 | [maml_trainer] epoch #427 | Saved 2025-04-12 08:41:43 | [maml_trainer] epoch #427 | Time 748947.10 s 2025-04-12 08:41:43 | [maml_trainer] epoch #427 | EpochTime 1756.06 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.7189 Average/AverageReturn -46.7298 Average/Iteration 427 Average/MaxReturn -37.8251 Average/MinReturn -131.031 Average/NumEpisodes 120 Average/StdReturn 9.57238 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69003 GaussianMLPPolicy/KLAfter 0.00280768 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.68809e-05 GaussianMLPPolicy/LossBefore 1.47025e-08 GaussianMLPPolicy/dLoss -1.68662e-05 Iteration 427 MetaTest/Average/AverageDiscountedReturn -44.8657 MetaTest/Average/AverageReturn -44.8657 MetaTest/Average/Iteration 427 MetaTest/Average/MaxReturn -37.5817 MetaTest/Average/MinReturn -53.0405 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.9523 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.8657 MetaTest/__unnamed_task__/AverageReturn -44.8657 MetaTest/__unnamed_task__/Iteration 427 MetaTest/__unnamed_task__/MaxReturn -37.5817 MetaTest/__unnamed_task__/MinReturn -53.0405 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.9523 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0544e+07 __unnamed_task__/AverageDiscountedReturn -24.7189 __unnamed_task__/AverageReturn -46.7298 __unnamed_task__/Iteration 427 __unnamed_task__/MaxReturn -37.8251 __unnamed_task__/MinReturn -131.031 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.57238 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 09:06:26 | [maml_trainer] epoch #428 | Sampling for adapation and meta-testing... 2025-04-12 09:10:33 | [maml_trainer] epoch #428 | Finished meta-testing... 2025-04-12 09:10:33 | [maml_trainer] epoch #428 | Saving snapshot... 2025-04-12 09:10:54 | [maml_trainer] epoch #428 | Saved 2025-04-12 09:10:54 | [maml_trainer] epoch #428 | Time 750698.57 s 2025-04-12 09:10:54 | [maml_trainer] epoch #428 | EpochTime 1751.47 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.4549 Average/AverageReturn -45.6689 Average/Iteration 428 Average/MaxReturn -38.2038 Average/MinReturn -57.1196 Average/NumEpisodes 120 Average/StdReturn 4.04191 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69019 GaussianMLPPolicy/KLAfter 0.00416453 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000129856 GaussianMLPPolicy/LossBefore -1.20004e-08 GaussianMLPPolicy/dLoss 0.000129844 Iteration 428 MetaTest/Average/AverageDiscountedReturn -45.8633 MetaTest/Average/AverageReturn -45.8633 MetaTest/Average/Iteration 428 MetaTest/Average/MaxReturn -39.7233 MetaTest/Average/MinReturn -51.6863 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.76878 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.8633 MetaTest/__unnamed_task__/AverageReturn -45.8633 MetaTest/__unnamed_task__/Iteration 428 MetaTest/__unnamed_task__/MaxReturn -39.7233 MetaTest/__unnamed_task__/MinReturn -51.6863 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.76878 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0592e+07 __unnamed_task__/AverageDiscountedReturn -24.4549 __unnamed_task__/AverageReturn -45.6689 __unnamed_task__/Iteration 428 __unnamed_task__/MaxReturn -38.2038 __unnamed_task__/MinReturn -57.1196 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.04191 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 09:35:30 | [maml_trainer] epoch #429 | Sampling for adapation and meta-testing... 2025-04-12 09:39:35 | [maml_trainer] epoch #429 | Finished meta-testing... 2025-04-12 09:39:35 | [maml_trainer] epoch #429 | Saving snapshot... 2025-04-12 09:39:56 | [maml_trainer] epoch #429 | Saved 2025-04-12 09:39:56 | [maml_trainer] epoch #429 | Time 752440.53 s 2025-04-12 09:39:56 | [maml_trainer] epoch #429 | EpochTime 1741.95 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.4585 Average/AverageReturn -45.6438 Average/Iteration 429 Average/MaxReturn -39.1163 Average/MinReturn -61.9524 Average/NumEpisodes 120 Average/StdReturn 4.2234 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69115 GaussianMLPPolicy/KLAfter 0.00683764 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000152164 GaussianMLPPolicy/LossBefore -5.72205e-09 GaussianMLPPolicy/dLoss 0.000152159 Iteration 429 MetaTest/Average/AverageDiscountedReturn -46.2572 MetaTest/Average/AverageReturn -46.2572 MetaTest/Average/Iteration 429 MetaTest/Average/MaxReturn -39.7968 MetaTest/Average/MinReturn -54.9442 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.72915 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.2572 MetaTest/__unnamed_task__/AverageReturn -46.2572 MetaTest/__unnamed_task__/Iteration 429 MetaTest/__unnamed_task__/MaxReturn -39.7968 MetaTest/__unnamed_task__/MinReturn -54.9442 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.72915 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.064e+07 __unnamed_task__/AverageDiscountedReturn -24.4585 __unnamed_task__/AverageReturn -45.6438 __unnamed_task__/Iteration 429 __unnamed_task__/MaxReturn -39.1163 __unnamed_task__/MinReturn -61.9524 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.2234 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 10:04:38 | [maml_trainer] epoch #430 | Sampling for adapation and meta-testing... 2025-04-12 10:08:42 | [maml_trainer] epoch #430 | Finished meta-testing... 2025-04-12 10:08:42 | [maml_trainer] epoch #430 | Saving snapshot... 2025-04-12 10:09:05 | [maml_trainer] epoch #430 | Saved 2025-04-12 10:09:05 | [maml_trainer] epoch #430 | Time 754189.30 s 2025-04-12 10:09:05 | [maml_trainer] epoch #430 | EpochTime 1748.77 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.7478 Average/AverageReturn -46.1474 Average/Iteration 430 Average/MaxReturn -37.3128 Average/MinReturn -62.966 Average/NumEpisodes 120 Average/StdReturn 4.89072 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69109 GaussianMLPPolicy/KLAfter 0.00604016 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000140621 GaussianMLPPolicy/LossBefore 6.67572e-09 GaussianMLPPolicy/dLoss -0.000140615 Iteration 430 MetaTest/Average/AverageDiscountedReturn -44.8423 MetaTest/Average/AverageReturn -44.8423 MetaTest/Average/Iteration 430 MetaTest/Average/MaxReturn -41.5991 MetaTest/Average/MinReturn -52.2215 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 2.43119 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.8423 MetaTest/__unnamed_task__/AverageReturn -44.8423 MetaTest/__unnamed_task__/Iteration 430 MetaTest/__unnamed_task__/MaxReturn -41.5991 MetaTest/__unnamed_task__/MinReturn -52.2215 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 2.43119 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0688e+07 __unnamed_task__/AverageDiscountedReturn -24.7478 __unnamed_task__/AverageReturn -46.1474 __unnamed_task__/Iteration 430 __unnamed_task__/MaxReturn -37.3128 __unnamed_task__/MinReturn -62.966 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 4.89072 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 10:33:43 | [maml_trainer] epoch #431 | Sampling for adapation and meta-testing... 2025-04-12 10:37:52 | [maml_trainer] epoch #431 | Finished meta-testing... 2025-04-12 10:37:52 | [maml_trainer] epoch #431 | Saving snapshot... 2025-04-12 10:38:13 | [maml_trainer] epoch #431 | Saved 2025-04-12 10:38:13 | [maml_trainer] epoch #431 | Time 755937.76 s 2025-04-12 10:38:13 | [maml_trainer] epoch #431 | EpochTime 1748.46 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.454 Average/AverageReturn -45.5316 Average/Iteration 431 Average/MaxReturn -38.0984 Average/MinReturn -92.7389 Average/NumEpisodes 120 Average/StdReturn 6.35722 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68998 GaussianMLPPolicy/KLAfter 0.00488215 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.25553e-05 GaussianMLPPolicy/LossBefore 1.50999e-09 GaussianMLPPolicy/dLoss -9.25538e-05 Iteration 431 MetaTest/Average/AverageDiscountedReturn -45.8107 MetaTest/Average/AverageReturn -45.8107 MetaTest/Average/Iteration 431 MetaTest/Average/MaxReturn -41.1511 MetaTest/Average/MinReturn -58.8066 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.0006 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.8107 MetaTest/__unnamed_task__/AverageReturn -45.8107 MetaTest/__unnamed_task__/Iteration 431 MetaTest/__unnamed_task__/MaxReturn -41.1511 MetaTest/__unnamed_task__/MinReturn -58.8066 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.0006 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0736e+07 __unnamed_task__/AverageDiscountedReturn -24.454 __unnamed_task__/AverageReturn -45.5316 __unnamed_task__/Iteration 431 __unnamed_task__/MaxReturn -38.0984 __unnamed_task__/MinReturn -92.7389 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.35722 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 11:02:48 | [maml_trainer] epoch #432 | Sampling for adapation and meta-testing... 2025-04-12 11:06:53 | [maml_trainer] epoch #432 | Finished meta-testing... 2025-04-12 11:06:53 | [maml_trainer] epoch #432 | Saving snapshot... 2025-04-12 11:07:15 | [maml_trainer] epoch #432 | Saved 2025-04-12 11:07:15 | [maml_trainer] epoch #432 | Time 757679.07 s 2025-04-12 11:07:15 | [maml_trainer] epoch #432 | EpochTime 1741.30 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.3941 Average/AverageReturn -45.9368 Average/Iteration 432 Average/MaxReturn -37.78 Average/MinReturn -127.024 Average/NumEpisodes 120 Average/StdReturn 10.953 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68907 GaussianMLPPolicy/KLAfter 0.00488181 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.17769e-05 GaussianMLPPolicy/LossBefore -3.73522e-09 GaussianMLPPolicy/dLoss -8.17806e-05 Iteration 432 MetaTest/Average/AverageDiscountedReturn -45.3815 MetaTest/Average/AverageReturn -45.3815 MetaTest/Average/Iteration 432 MetaTest/Average/MaxReturn -40.2913 MetaTest/Average/MinReturn -61.9352 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.00687 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.3815 MetaTest/__unnamed_task__/AverageReturn -45.3815 MetaTest/__unnamed_task__/Iteration 432 MetaTest/__unnamed_task__/MaxReturn -40.2913 MetaTest/__unnamed_task__/MinReturn -61.9352 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.00687 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0784e+07 __unnamed_task__/AverageDiscountedReturn -24.3941 __unnamed_task__/AverageReturn -45.9368 __unnamed_task__/Iteration 432 __unnamed_task__/MaxReturn -37.78 __unnamed_task__/MinReturn -127.024 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.953 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 11:31:42 | [maml_trainer] epoch #433 | Sampling for adapation and meta-testing... 2025-04-12 11:35:45 | [maml_trainer] epoch #433 | Finished meta-testing... 2025-04-12 11:35:45 | [maml_trainer] epoch #433 | Saving snapshot... 2025-04-12 11:36:07 | [maml_trainer] epoch #433 | Saved 2025-04-12 11:36:07 | [maml_trainer] epoch #433 | Time 759411.31 s 2025-04-12 11:36:07 | [maml_trainer] epoch #433 | EpochTime 1732.24 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.6132 Average/AverageReturn -45.7982 Average/Iteration 433 Average/MaxReturn -37.5116 Average/MinReturn -79.0186 Average/NumEpisodes 120 Average/StdReturn 5.58344 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68796 GaussianMLPPolicy/KLAfter 0.00658139 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.75164e-06 GaussianMLPPolicy/LossBefore 2.30471e-09 GaussianMLPPolicy/dLoss -9.74933e-06 Iteration 433 MetaTest/Average/AverageDiscountedReturn -44.3107 MetaTest/Average/AverageReturn -44.3107 MetaTest/Average/Iteration 433 MetaTest/Average/MaxReturn -39.1497 MetaTest/Average/MinReturn -57.362 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.0113 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.3107 MetaTest/__unnamed_task__/AverageReturn -44.3107 MetaTest/__unnamed_task__/Iteration 433 MetaTest/__unnamed_task__/MaxReturn -39.1497 MetaTest/__unnamed_task__/MinReturn -57.362 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.0113 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0832e+07 __unnamed_task__/AverageDiscountedReturn -24.6132 __unnamed_task__/AverageReturn -45.7982 __unnamed_task__/Iteration 433 __unnamed_task__/MaxReturn -37.5116 __unnamed_task__/MinReturn -79.0186 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.58344 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 12:00:46 | [maml_trainer] epoch #434 | Sampling for adapation and meta-testing... 2025-04-12 12:04:54 | [maml_trainer] epoch #434 | Finished meta-testing... 2025-04-12 12:04:54 | [maml_trainer] epoch #434 | Saving snapshot... 2025-04-12 12:05:16 | [maml_trainer] epoch #434 | Saved 2025-04-12 12:05:16 | [maml_trainer] epoch #434 | Time 761160.35 s 2025-04-12 12:05:16 | [maml_trainer] epoch #434 | EpochTime 1749.03 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.7793 Average/AverageReturn -46.5032 Average/Iteration 434 Average/MaxReturn -38.2494 Average/MinReturn -108.809 Average/NumEpisodes 120 Average/StdReturn 7.97819 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.6871 GaussianMLPPolicy/KLAfter 0.00558726 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000145513 GaussianMLPPolicy/LossBefore 1.1603e-08 GaussianMLPPolicy/dLoss -0.000145501 Iteration 434 MetaTest/Average/AverageDiscountedReturn -44.1156 MetaTest/Average/AverageReturn -44.1156 MetaTest/Average/Iteration 434 MetaTest/Average/MaxReturn -37.618 MetaTest/Average/MinReturn -50.7268 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.28776 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.1156 MetaTest/__unnamed_task__/AverageReturn -44.1156 MetaTest/__unnamed_task__/Iteration 434 MetaTest/__unnamed_task__/MaxReturn -37.618 MetaTest/__unnamed_task__/MinReturn -50.7268 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.28776 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.088e+07 __unnamed_task__/AverageDiscountedReturn -24.7793 __unnamed_task__/AverageReturn -46.5032 __unnamed_task__/Iteration 434 __unnamed_task__/MaxReturn -38.2494 __unnamed_task__/MinReturn -108.809 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.97819 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 12:29:51 | [maml_trainer] epoch #435 | Sampling for adapation and meta-testing... 2025-04-12 12:33:53 | [maml_trainer] epoch #435 | Finished meta-testing... 2025-04-12 12:33:53 | [maml_trainer] epoch #435 | Saving snapshot... 2025-04-12 12:34:15 | [maml_trainer] epoch #435 | Saved 2025-04-12 12:34:15 | [maml_trainer] epoch #435 | Time 762899.33 s 2025-04-12 12:34:15 | [maml_trainer] epoch #435 | EpochTime 1738.98 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.4541 Average/AverageReturn -46.0047 Average/Iteration 435 Average/MaxReturn -37.2202 Average/MinReturn -135.432 Average/NumEpisodes 120 Average/StdReturn 10.0211 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68645 GaussianMLPPolicy/KLAfter 0.00446326 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.30159e-05 GaussianMLPPolicy/LossBefore 4.09285e-09 GaussianMLPPolicy/dLoss -5.30118e-05 Iteration 435 MetaTest/Average/AverageDiscountedReturn -44.2343 MetaTest/Average/AverageReturn -44.2343 MetaTest/Average/Iteration 435 MetaTest/Average/MaxReturn -35.8434 MetaTest/Average/MinReturn -51.9248 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.44788 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.2343 MetaTest/__unnamed_task__/AverageReturn -44.2343 MetaTest/__unnamed_task__/Iteration 435 MetaTest/__unnamed_task__/MaxReturn -35.8434 MetaTest/__unnamed_task__/MinReturn -51.9248 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.44788 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0928e+07 __unnamed_task__/AverageDiscountedReturn -24.4541 __unnamed_task__/AverageReturn -46.0047 __unnamed_task__/Iteration 435 __unnamed_task__/MaxReturn -37.2202 __unnamed_task__/MinReturn -135.432 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.0211 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 12:58:42 | [maml_trainer] epoch #436 | Sampling for adapation and meta-testing... 2025-04-12 13:02:53 | [maml_trainer] epoch #436 | Finished meta-testing... 2025-04-12 13:02:53 | [maml_trainer] epoch #436 | Saving snapshot... 2025-04-12 13:03:16 | [maml_trainer] epoch #436 | Saved 2025-04-12 13:03:16 | [maml_trainer] epoch #436 | Time 764640.05 s 2025-04-12 13:03:16 | [maml_trainer] epoch #436 | EpochTime 1740.72 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.0031 Average/AverageReturn -44.9791 Average/Iteration 436 Average/MaxReturn -37.6222 Average/MinReturn -96.2741 Average/NumEpisodes 120 Average/StdReturn 7.66114 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68526 GaussianMLPPolicy/KLAfter 0.00451956 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.48788e-05 GaussianMLPPolicy/LossBefore 1.04109e-08 GaussianMLPPolicy/dLoss -9.48684e-05 Iteration 436 MetaTest/Average/AverageDiscountedReturn -47.0124 MetaTest/Average/AverageReturn -47.0124 MetaTest/Average/Iteration 436 MetaTest/Average/MaxReturn -37.795 MetaTest/Average/MinReturn -61.6111 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.96871 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.0124 MetaTest/__unnamed_task__/AverageReturn -47.0124 MetaTest/__unnamed_task__/Iteration 436 MetaTest/__unnamed_task__/MaxReturn -37.795 MetaTest/__unnamed_task__/MinReturn -61.6111 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.96871 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.0976e+07 __unnamed_task__/AverageDiscountedReturn -24.0031 __unnamed_task__/AverageReturn -44.9791 __unnamed_task__/Iteration 436 __unnamed_task__/MaxReturn -37.6222 __unnamed_task__/MinReturn -96.2741 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.66114 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 13:27:48 | [maml_trainer] epoch #437 | Sampling for adapation and meta-testing... 2025-04-12 13:31:57 | [maml_trainer] epoch #437 | Finished meta-testing... 2025-04-12 13:31:57 | [maml_trainer] epoch #437 | Saving snapshot... 2025-04-12 13:32:18 | [maml_trainer] epoch #437 | Saved 2025-04-12 13:32:18 | [maml_trainer] epoch #437 | Time 766382.60 s 2025-04-12 13:32:18 | [maml_trainer] epoch #437 | EpochTime 1742.55 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.6174 Average/AverageReturn -46.135 Average/Iteration 437 Average/MaxReturn -37.2563 Average/MinReturn -116.1 Average/NumEpisodes 120 Average/StdReturn 8.22173 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68333 GaussianMLPPolicy/KLAfter 0.00580051 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000100231 GaussianMLPPolicy/LossBefore 8.54333e-09 GaussianMLPPolicy/dLoss 0.00010024 Iteration 437 MetaTest/Average/AverageDiscountedReturn -46.2404 MetaTest/Average/AverageReturn -46.2404 MetaTest/Average/Iteration 437 MetaTest/Average/MaxReturn -39.76 MetaTest/Average/MinReturn -71.7823 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.66027 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.2404 MetaTest/__unnamed_task__/AverageReturn -46.2404 MetaTest/__unnamed_task__/Iteration 437 MetaTest/__unnamed_task__/MaxReturn -39.76 MetaTest/__unnamed_task__/MinReturn -71.7823 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.66027 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1024e+07 __unnamed_task__/AverageDiscountedReturn -24.6174 __unnamed_task__/AverageReturn -46.135 __unnamed_task__/Iteration 437 __unnamed_task__/MaxReturn -37.2563 __unnamed_task__/MinReturn -116.1 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.22173 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 13:56:46 | [maml_trainer] epoch #438 | Sampling for adapation and meta-testing... 2025-04-12 14:00:51 | [maml_trainer] epoch #438 | Finished meta-testing... 2025-04-12 14:00:51 | [maml_trainer] epoch #438 | Saving snapshot... 2025-04-12 14:01:13 | [maml_trainer] epoch #438 | Saved 2025-04-12 14:01:13 | [maml_trainer] epoch #438 | Time 768117.44 s 2025-04-12 14:01:13 | [maml_trainer] epoch #438 | EpochTime 1734.83 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.6307 Average/AverageReturn -46.0917 Average/Iteration 438 Average/MaxReturn -37.1681 Average/MinReturn -62.0213 Average/NumEpisodes 120 Average/StdReturn 5.15375 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68198 GaussianMLPPolicy/KLAfter 0.00608549 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.05978e-05 GaussianMLPPolicy/LossBefore -6.35783e-10 GaussianMLPPolicy/dLoss 7.05972e-05 Iteration 438 MetaTest/Average/AverageDiscountedReturn -49.5184 MetaTest/Average/AverageReturn -49.5184 MetaTest/Average/Iteration 438 MetaTest/Average/MaxReturn -37.8345 MetaTest/Average/MinReturn -84.958 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 10.7737 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5184 MetaTest/__unnamed_task__/AverageReturn -49.5184 MetaTest/__unnamed_task__/Iteration 438 MetaTest/__unnamed_task__/MaxReturn -37.8345 MetaTest/__unnamed_task__/MinReturn -84.958 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 10.7737 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1072e+07 __unnamed_task__/AverageDiscountedReturn -24.6307 __unnamed_task__/AverageReturn -46.0917 __unnamed_task__/Iteration 438 __unnamed_task__/MaxReturn -37.1681 __unnamed_task__/MinReturn -62.0213 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 5.15375 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 14:25:30 | [maml_trainer] epoch #439 | Sampling for adapation and meta-testing... 2025-04-12 14:29:34 | [maml_trainer] epoch #439 | Finished meta-testing... 2025-04-12 14:29:34 | [maml_trainer] epoch #439 | Saving snapshot... 2025-04-12 14:29:57 | [maml_trainer] epoch #439 | Saved 2025-04-12 14:29:57 | [maml_trainer] epoch #439 | Time 769841.13 s 2025-04-12 14:29:57 | [maml_trainer] epoch #439 | EpochTime 1723.69 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.4009 Average/AverageReturn -45.8002 Average/Iteration 439 Average/MaxReturn -36.2447 Average/MinReturn -107.566 Average/NumEpisodes 120 Average/StdReturn 7.5982 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68153 GaussianMLPPolicy/KLAfter 0.00526735 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.18266e-05 GaussianMLPPolicy/LossBefore 5.64257e-09 GaussianMLPPolicy/dLoss 8.18322e-05 Iteration 439 MetaTest/Average/AverageDiscountedReturn -45.9622 MetaTest/Average/AverageReturn -45.9622 MetaTest/Average/Iteration 439 MetaTest/Average/MaxReturn -39.2487 MetaTest/Average/MinReturn -74.2821 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.339 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.9622 MetaTest/__unnamed_task__/AverageReturn -45.9622 MetaTest/__unnamed_task__/Iteration 439 MetaTest/__unnamed_task__/MaxReturn -39.2487 MetaTest/__unnamed_task__/MinReturn -74.2821 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.339 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.112e+07 __unnamed_task__/AverageDiscountedReturn -24.4009 __unnamed_task__/AverageReturn -45.8002 __unnamed_task__/Iteration 439 __unnamed_task__/MaxReturn -36.2447 __unnamed_task__/MinReturn -107.566 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.5982 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 14:54:32 | [maml_trainer] epoch #440 | Sampling for adapation and meta-testing... 2025-04-12 14:58:36 | [maml_trainer] epoch #440 | Finished meta-testing... 2025-04-12 14:58:36 | [maml_trainer] epoch #440 | Saving snapshot... 2025-04-12 14:58:57 | [maml_trainer] epoch #440 | Saved 2025-04-12 14:58:57 | [maml_trainer] epoch #440 | Time 771581.26 s 2025-04-12 14:58:57 | [maml_trainer] epoch #440 | EpochTime 1740.13 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.7787 Average/AverageReturn -46.4537 Average/Iteration 440 Average/MaxReturn -38.2624 Average/MinReturn -97.6427 Average/NumEpisodes 120 Average/StdReturn 7.84305 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68215 GaussianMLPPolicy/KLAfter 0.00442547 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000167479 GaussianMLPPolicy/LossBefore -3.09944e-09 GaussianMLPPolicy/dLoss 0.000167476 Iteration 440 MetaTest/Average/AverageDiscountedReturn -44.9835 MetaTest/Average/AverageReturn -44.9835 MetaTest/Average/Iteration 440 MetaTest/Average/MaxReturn -37.6165 MetaTest/Average/MinReturn -58.3052 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.19881 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.9835 MetaTest/__unnamed_task__/AverageReturn -44.9835 MetaTest/__unnamed_task__/Iteration 440 MetaTest/__unnamed_task__/MaxReturn -37.6165 MetaTest/__unnamed_task__/MinReturn -58.3052 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.19881 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1168e+07 __unnamed_task__/AverageDiscountedReturn -24.7787 __unnamed_task__/AverageReturn -46.4537 __unnamed_task__/Iteration 440 __unnamed_task__/MaxReturn -38.2624 __unnamed_task__/MinReturn -97.6427 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.84305 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 15:23:11 | [maml_trainer] epoch #441 | Sampling for adapation and meta-testing... 2025-04-12 15:27:12 | [maml_trainer] epoch #441 | Finished meta-testing... 2025-04-12 15:27:12 | [maml_trainer] epoch #441 | Saving snapshot... 2025-04-12 15:27:34 | [maml_trainer] epoch #441 | Saved 2025-04-12 15:27:34 | [maml_trainer] epoch #441 | Time 773298.68 s 2025-04-12 15:27:34 | [maml_trainer] epoch #441 | EpochTime 1717.42 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.7786 Average/AverageReturn -47.0021 Average/Iteration 441 Average/MaxReturn -37.2986 Average/MinReturn -127 Average/NumEpisodes 120 Average/StdReturn 11.1218 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.6831 GaussianMLPPolicy/KLAfter 0.00431396 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.0596e-05 GaussianMLPPolicy/LossBefore -3.53654e-09 GaussianMLPPolicy/dLoss 9.05924e-05 Iteration 441 MetaTest/Average/AverageDiscountedReturn -48.2443 MetaTest/Average/AverageReturn -48.2443 MetaTest/Average/Iteration 441 MetaTest/Average/MaxReturn -39.3287 MetaTest/Average/MinReturn -120.578 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.7803 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.2443 MetaTest/__unnamed_task__/AverageReturn -48.2443 MetaTest/__unnamed_task__/Iteration 441 MetaTest/__unnamed_task__/MaxReturn -39.3287 MetaTest/__unnamed_task__/MinReturn -120.578 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.7803 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1216e+07 __unnamed_task__/AverageDiscountedReturn -24.7786 __unnamed_task__/AverageReturn -47.0021 __unnamed_task__/Iteration 441 __unnamed_task__/MaxReturn -37.2986 __unnamed_task__/MinReturn -127 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.1218 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 15:52:03 | [maml_trainer] epoch #442 | Sampling for adapation and meta-testing... 2025-04-12 15:56:08 | [maml_trainer] epoch #442 | Finished meta-testing... 2025-04-12 15:56:08 | [maml_trainer] epoch #442 | Saving snapshot... 2025-04-12 15:56:31 | [maml_trainer] epoch #442 | Saved 2025-04-12 15:56:31 | [maml_trainer] epoch #442 | Time 775035.04 s 2025-04-12 15:56:31 | [maml_trainer] epoch #442 | EpochTime 1736.36 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.7486 Average/AverageReturn -46.8192 Average/Iteration 442 Average/MaxReturn -36.5909 Average/MinReturn -84.7391 Average/NumEpisodes 120 Average/StdReturn 6.89742 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68385 GaussianMLPPolicy/KLAfter 0.00438567 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000100238 GaussianMLPPolicy/LossBefore 5.88099e-09 GaussianMLPPolicy/dLoss -0.000100232 Iteration 442 MetaTest/Average/AverageDiscountedReturn -44.7947 MetaTest/Average/AverageReturn -44.7947 MetaTest/Average/Iteration 442 MetaTest/Average/MaxReturn -38.4958 MetaTest/Average/MinReturn -55.5427 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.30812 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.7947 MetaTest/__unnamed_task__/AverageReturn -44.7947 MetaTest/__unnamed_task__/Iteration 442 MetaTest/__unnamed_task__/MaxReturn -38.4958 MetaTest/__unnamed_task__/MinReturn -55.5427 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.30812 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1264e+07 __unnamed_task__/AverageDiscountedReturn -24.7486 __unnamed_task__/AverageReturn -46.8192 __unnamed_task__/Iteration 442 __unnamed_task__/MaxReturn -36.5909 __unnamed_task__/MinReturn -84.7391 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.89742 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-12 16:20:58 | [maml_trainer] epoch #443 | Sampling for adapation and meta-testing... 2025-04-12 16:25:06 | [maml_trainer] epoch #443 | Finished meta-testing... 2025-04-12 16:25:06 | [maml_trainer] epoch #443 | Saving snapshot... 2025-04-12 16:25:27 | [maml_trainer] epoch #443 | Saved 2025-04-12 16:25:27 | [maml_trainer] epoch #443 | Time 776771.15 s 2025-04-12 16:25:27 | [maml_trainer] epoch #443 | EpochTime 1736.11 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.5915 Average/AverageReturn -46.3637 Average/Iteration 443 Average/MaxReturn -37.0321 Average/MinReturn -102.835 Average/NumEpisodes 120 Average/StdReturn 8.17182 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68529 GaussianMLPPolicy/KLAfter 0.00234534 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.86147e-05 GaussianMLPPolicy/LossBefore 1.23183e-09 GaussianMLPPolicy/dLoss -1.86135e-05 Iteration 443 MetaTest/Average/AverageDiscountedReturn -46.9666 MetaTest/Average/AverageReturn -46.9666 MetaTest/Average/Iteration 443 MetaTest/Average/MaxReturn -35.8224 MetaTest/Average/MinReturn -64.6975 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.33295 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.9666 MetaTest/__unnamed_task__/AverageReturn -46.9666 MetaTest/__unnamed_task__/Iteration 443 MetaTest/__unnamed_task__/MaxReturn -35.8224 MetaTest/__unnamed_task__/MinReturn -64.6975 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.33295 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1312e+07 __unnamed_task__/AverageDiscountedReturn -24.5915 __unnamed_task__/AverageReturn -46.3637 __unnamed_task__/Iteration 443 __unnamed_task__/MaxReturn -37.0321 __unnamed_task__/MinReturn -102.835 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.17182 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 16:50:01 | [maml_trainer] epoch #444 | Sampling for adapation and meta-testing... 2025-04-12 16:54:03 | [maml_trainer] epoch #444 | Finished meta-testing... 2025-04-12 16:54:03 | [maml_trainer] epoch #444 | Saving snapshot... 2025-04-12 16:54:24 | [maml_trainer] epoch #444 | Saved 2025-04-12 16:54:24 | [maml_trainer] epoch #444 | Time 778508.59 s 2025-04-12 16:54:24 | [maml_trainer] epoch #444 | EpochTime 1737.43 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.9099 Average/AverageReturn -48.0851 Average/Iteration 444 Average/MaxReturn -37.0657 Average/MinReturn -124.184 Average/NumEpisodes 120 Average/StdReturn 13.0359 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68601 GaussianMLPPolicy/KLAfter 0.00290786 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.10431e-05 GaussianMLPPolicy/LossBefore 1.02917e-08 GaussianMLPPolicy/dLoss -7.10328e-05 Iteration 444 MetaTest/Average/AverageDiscountedReturn -49.2988 MetaTest/Average/AverageReturn -49.2988 MetaTest/Average/Iteration 444 MetaTest/Average/MaxReturn -38.0731 MetaTest/Average/MinReturn -95.5123 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.6878 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.2988 MetaTest/__unnamed_task__/AverageReturn -49.2988 MetaTest/__unnamed_task__/Iteration 444 MetaTest/__unnamed_task__/MaxReturn -38.0731 MetaTest/__unnamed_task__/MinReturn -95.5123 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.6878 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.136e+07 __unnamed_task__/AverageDiscountedReturn -24.9099 __unnamed_task__/AverageReturn -48.0851 __unnamed_task__/Iteration 444 __unnamed_task__/MaxReturn -37.0657 __unnamed_task__/MinReturn -124.184 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 13.0359 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 17:18:45 | [maml_trainer] epoch #445 | Sampling for adapation and meta-testing... 2025-04-12 17:22:50 | [maml_trainer] epoch #445 | Finished meta-testing... 2025-04-12 17:22:50 | [maml_trainer] epoch #445 | Saving snapshot... 2025-04-12 17:23:11 | [maml_trainer] epoch #445 | Saved 2025-04-12 17:23:11 | [maml_trainer] epoch #445 | Time 780235.89 s 2025-04-12 17:23:11 | [maml_trainer] epoch #445 | EpochTime 1727.30 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.5741 Average/AverageReturn -47.3555 Average/Iteration 445 Average/MaxReturn -37.7101 Average/MinReturn -134.612 Average/NumEpisodes 120 Average/StdReturn 12.1213 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68625 GaussianMLPPolicy/KLAfter 0.00236335 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.05673e-05 GaussianMLPPolicy/LossBefore -1.4027e-08 GaussianMLPPolicy/dLoss -2.05813e-05 Iteration 445 MetaTest/Average/AverageDiscountedReturn -43.7294 MetaTest/Average/AverageReturn -43.7294 MetaTest/Average/Iteration 445 MetaTest/Average/MaxReturn -36.7827 MetaTest/Average/MinReturn -52.7779 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.42264 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -43.7294 MetaTest/__unnamed_task__/AverageReturn -43.7294 MetaTest/__unnamed_task__/Iteration 445 MetaTest/__unnamed_task__/MaxReturn -36.7827 MetaTest/__unnamed_task__/MinReturn -52.7779 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.42264 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1408e+07 __unnamed_task__/AverageDiscountedReturn -24.5741 __unnamed_task__/AverageReturn -47.3555 __unnamed_task__/Iteration 445 __unnamed_task__/MaxReturn -37.7101 __unnamed_task__/MinReturn -134.612 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.1213 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 17:48:01 | [maml_trainer] epoch #446 | Sampling for adapation and meta-testing... 2025-04-12 17:52:10 | [maml_trainer] epoch #446 | Finished meta-testing... 2025-04-12 17:52:10 | [maml_trainer] epoch #446 | Saving snapshot... 2025-04-12 17:52:32 | [maml_trainer] epoch #446 | Saved 2025-04-12 17:52:32 | [maml_trainer] epoch #446 | Time 781996.70 s 2025-04-12 17:52:32 | [maml_trainer] epoch #446 | EpochTime 1760.81 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.5849 Average/AverageReturn -46.8943 Average/Iteration 446 Average/MaxReturn -36.7121 Average/MinReturn -100.575 Average/NumEpisodes 120 Average/StdReturn 10.3281 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68614 GaussianMLPPolicy/KLAfter 0.00233374 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.18727e-05 GaussianMLPPolicy/LossBefore -9.25859e-09 GaussianMLPPolicy/dLoss 5.18635e-05 Iteration 446 MetaTest/Average/AverageDiscountedReturn -49.0933 MetaTest/Average/AverageReturn -49.0933 MetaTest/Average/Iteration 446 MetaTest/Average/MaxReturn -37.3831 MetaTest/Average/MinReturn -101.956 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.4867 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.0933 MetaTest/__unnamed_task__/AverageReturn -49.0933 MetaTest/__unnamed_task__/Iteration 446 MetaTest/__unnamed_task__/MaxReturn -37.3831 MetaTest/__unnamed_task__/MinReturn -101.956 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.4867 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1456e+07 __unnamed_task__/AverageDiscountedReturn -24.5849 __unnamed_task__/AverageReturn -46.8943 __unnamed_task__/Iteration 446 __unnamed_task__/MaxReturn -36.7121 __unnamed_task__/MinReturn -100.575 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.3281 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 18:17:09 | [maml_trainer] epoch #447 | Sampling for adapation and meta-testing... 2025-04-12 18:21:10 | [maml_trainer] epoch #447 | Finished meta-testing... 2025-04-12 18:21:10 | [maml_trainer] epoch #447 | Saving snapshot... 2025-04-12 18:21:32 | [maml_trainer] epoch #447 | Saved 2025-04-12 18:21:32 | [maml_trainer] epoch #447 | Time 783736.72 s 2025-04-12 18:21:32 | [maml_trainer] epoch #447 | EpochTime 1740.01 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.1287 Average/AverageReturn -48.6332 Average/Iteration 447 Average/MaxReturn -36.9279 Average/MinReturn -137.801 Average/NumEpisodes 120 Average/StdReturn 12.4693 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68738 GaussianMLPPolicy/KLAfter 0.00242976 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 5.39103e-05 GaussianMLPPolicy/LossBefore 7.11282e-09 GaussianMLPPolicy/dLoss -5.39032e-05 Iteration 447 MetaTest/Average/AverageDiscountedReturn -44.7703 MetaTest/Average/AverageReturn -44.7703 MetaTest/Average/Iteration 447 MetaTest/Average/MaxReturn -38.13 MetaTest/Average/MinReturn -64.0873 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.16116 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.7703 MetaTest/__unnamed_task__/AverageReturn -44.7703 MetaTest/__unnamed_task__/Iteration 447 MetaTest/__unnamed_task__/MaxReturn -38.13 MetaTest/__unnamed_task__/MinReturn -64.0873 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.16116 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1504e+07 __unnamed_task__/AverageDiscountedReturn -25.1287 __unnamed_task__/AverageReturn -48.6332 __unnamed_task__/Iteration 447 __unnamed_task__/MaxReturn -36.9279 __unnamed_task__/MinReturn -137.801 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.4693 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 19:02:51 | [maml_trainer] epoch #448 | Sampling for adapation and meta-testing... 2025-04-12 19:10:11 | [maml_trainer] epoch #448 | Finished meta-testing... 2025-04-12 19:10:11 | [maml_trainer] epoch #448 | Saving snapshot... 2025-04-12 19:10:51 | [maml_trainer] epoch #448 | Saved 2025-04-12 19:10:51 | [maml_trainer] epoch #448 | Time 786695.16 s 2025-04-12 19:10:51 | [maml_trainer] epoch #448 | EpochTime 2958.44 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.1598 Average/AverageReturn -49.3257 Average/Iteration 448 Average/MaxReturn -36.3882 Average/MinReturn -133.012 Average/NumEpisodes 120 Average/StdReturn 16.1929 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68863 GaussianMLPPolicy/KLAfter 0.000890228 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.46678e-05 GaussianMLPPolicy/LossBefore 9.29832e-09 GaussianMLPPolicy/dLoss -3.46585e-05 Iteration 448 MetaTest/Average/AverageDiscountedReturn -46.3732 MetaTest/Average/AverageReturn -46.3732 MetaTest/Average/Iteration 448 MetaTest/Average/MaxReturn -37.8904 MetaTest/Average/MinReturn -66.0798 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.74797 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.3732 MetaTest/__unnamed_task__/AverageReturn -46.3732 MetaTest/__unnamed_task__/Iteration 448 MetaTest/__unnamed_task__/MaxReturn -37.8904 MetaTest/__unnamed_task__/MinReturn -66.0798 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.74797 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1552e+07 __unnamed_task__/AverageDiscountedReturn -25.1598 __unnamed_task__/AverageReturn -49.3257 __unnamed_task__/Iteration 448 __unnamed_task__/MaxReturn -36.3882 __unnamed_task__/MinReturn -133.012 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 16.1929 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 19:53:47 | [maml_trainer] epoch #449 | Sampling for adapation and meta-testing... 2025-04-12 20:00:55 | [maml_trainer] epoch #449 | Finished meta-testing... 2025-04-12 20:00:55 | [maml_trainer] epoch #449 | Saving snapshot... 2025-04-12 20:01:37 | [maml_trainer] epoch #449 | Saved 2025-04-12 20:01:37 | [maml_trainer] epoch #449 | Time 789741.06 s 2025-04-12 20:01:37 | [maml_trainer] epoch #449 | EpochTime 3045.90 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.2637 Average/AverageReturn -49.3167 Average/Iteration 449 Average/MaxReturn -36.6811 Average/MinReturn -133.926 Average/NumEpisodes 120 Average/StdReturn 15.2297 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68943 GaussianMLPPolicy/KLAfter 0.0011468 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.04399e-05 GaussianMLPPolicy/LossBefore 6.67572e-09 GaussianMLPPolicy/dLoss 2.04465e-05 Iteration 449 MetaTest/Average/AverageDiscountedReturn -47.0777 MetaTest/Average/AverageReturn -47.0777 MetaTest/Average/Iteration 449 MetaTest/Average/MaxReturn -36.1739 MetaTest/Average/MinReturn -77.5793 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.56879 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.0777 MetaTest/__unnamed_task__/AverageReturn -47.0777 MetaTest/__unnamed_task__/Iteration 449 MetaTest/__unnamed_task__/MaxReturn -36.1739 MetaTest/__unnamed_task__/MinReturn -77.5793 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.56879 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.16e+07 __unnamed_task__/AverageDiscountedReturn -25.2637 __unnamed_task__/AverageReturn -49.3167 __unnamed_task__/Iteration 449 __unnamed_task__/MaxReturn -36.6811 __unnamed_task__/MinReturn -133.926 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 15.2297 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 20:44:53 | [maml_trainer] epoch #450 | Sampling for adapation and meta-testing... 2025-04-12 20:50:36 | [maml_trainer] epoch #450 | Finished meta-testing... 2025-04-12 20:50:36 | [maml_trainer] epoch #450 | Saving snapshot... 2025-04-12 20:51:06 | [maml_trainer] epoch #450 | Saved 2025-04-12 20:51:06 | [maml_trainer] epoch #450 | Time 792710.51 s 2025-04-12 20:51:06 | [maml_trainer] epoch #450 | EpochTime 2969.45 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.6276 Average/AverageReturn -46.9041 Average/Iteration 450 Average/MaxReturn -35.8054 Average/MinReturn -128.904 Average/NumEpisodes 120 Average/StdReturn 10.8044 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69068 GaussianMLPPolicy/KLAfter 0.00103666 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.56891e-05 GaussianMLPPolicy/LossBefore 1.15236e-08 GaussianMLPPolicy/dLoss 1.57006e-05 Iteration 450 MetaTest/Average/AverageDiscountedReturn -51.8638 MetaTest/Average/AverageReturn -51.8638 MetaTest/Average/Iteration 450 MetaTest/Average/MaxReturn -37.3028 MetaTest/Average/MinReturn -106.362 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.9365 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.8638 MetaTest/__unnamed_task__/AverageReturn -51.8638 MetaTest/__unnamed_task__/Iteration 450 MetaTest/__unnamed_task__/MaxReturn -37.3028 MetaTest/__unnamed_task__/MinReturn -106.362 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.9365 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1648e+07 __unnamed_task__/AverageDiscountedReturn -24.6276 __unnamed_task__/AverageReturn -46.9041 __unnamed_task__/Iteration 450 __unnamed_task__/MaxReturn -35.8054 __unnamed_task__/MinReturn -128.904 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.8044 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 21:19:19 | [maml_trainer] epoch #451 | Sampling for adapation and meta-testing... 2025-04-12 21:23:25 | [maml_trainer] epoch #451 | Finished meta-testing... 2025-04-12 21:23:25 | [maml_trainer] epoch #451 | Saving snapshot... 2025-04-12 21:23:46 | [maml_trainer] epoch #451 | Saved 2025-04-12 21:23:46 | [maml_trainer] epoch #451 | Time 794670.31 s 2025-04-12 21:23:46 | [maml_trainer] epoch #451 | EpochTime 1959.80 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.0583 Average/AverageReturn -47.963 Average/Iteration 451 Average/MaxReturn -37.3314 Average/MinReturn -102.18 Average/NumEpisodes 120 Average/StdReturn 9.21532 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69133 GaussianMLPPolicy/KLAfter 0.00174953 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.86406e-05 GaussianMLPPolicy/LossBefore 7.15256e-09 GaussianMLPPolicy/dLoss -2.86334e-05 Iteration 451 MetaTest/Average/AverageDiscountedReturn -47.119 MetaTest/Average/AverageReturn -47.119 MetaTest/Average/Iteration 451 MetaTest/Average/MaxReturn -37.1325 MetaTest/Average/MinReturn -99.7285 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.1148 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.119 MetaTest/__unnamed_task__/AverageReturn -47.119 MetaTest/__unnamed_task__/Iteration 451 MetaTest/__unnamed_task__/MaxReturn -37.1325 MetaTest/__unnamed_task__/MinReturn -99.7285 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.1148 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1696e+07 __unnamed_task__/AverageDiscountedReturn -25.0583 __unnamed_task__/AverageReturn -47.963 __unnamed_task__/Iteration 451 __unnamed_task__/MaxReturn -37.3314 __unnamed_task__/MinReturn -102.18 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.21532 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 21:48:19 | [maml_trainer] epoch #452 | Sampling for adapation and meta-testing... 2025-04-12 21:52:24 | [maml_trainer] epoch #452 | Finished meta-testing... 2025-04-12 21:52:24 | [maml_trainer] epoch #452 | Saving snapshot... 2025-04-12 21:52:45 | [maml_trainer] epoch #452 | Saved 2025-04-12 21:52:45 | [maml_trainer] epoch #452 | Time 796409.69 s 2025-04-12 21:52:45 | [maml_trainer] epoch #452 | EpochTime 1739.38 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.7938 Average/AverageReturn -47.7124 Average/Iteration 452 Average/MaxReturn -36.6009 Average/MinReturn -118.882 Average/NumEpisodes 120 Average/StdReturn 12.0522 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69207 GaussianMLPPolicy/KLAfter 0.0024542 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.29246e-05 GaussianMLPPolicy/LossBefore 1.22388e-08 GaussianMLPPolicy/dLoss 4.29368e-05 Iteration 452 MetaTest/Average/AverageDiscountedReturn -48.1207 MetaTest/Average/AverageReturn -48.1207 MetaTest/Average/Iteration 452 MetaTest/Average/MaxReturn -38.2305 MetaTest/Average/MinReturn -72.3435 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.75997 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1207 MetaTest/__unnamed_task__/AverageReturn -48.1207 MetaTest/__unnamed_task__/Iteration 452 MetaTest/__unnamed_task__/MaxReturn -38.2305 MetaTest/__unnamed_task__/MinReturn -72.3435 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.75997 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1744e+07 __unnamed_task__/AverageDiscountedReturn -24.7938 __unnamed_task__/AverageReturn -47.7124 __unnamed_task__/Iteration 452 __unnamed_task__/MaxReturn -36.6009 __unnamed_task__/MinReturn -118.882 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.0522 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 22:17:22 | [maml_trainer] epoch #453 | Sampling for adapation and meta-testing... 2025-04-12 22:21:30 | [maml_trainer] epoch #453 | Finished meta-testing... 2025-04-12 22:21:30 | [maml_trainer] epoch #453 | Saving snapshot... 2025-04-12 22:21:53 | [maml_trainer] epoch #453 | Saved 2025-04-12 22:21:53 | [maml_trainer] epoch #453 | Time 798157.37 s 2025-04-12 22:21:53 | [maml_trainer] epoch #453 | EpochTime 1747.67 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.2346 Average/AverageReturn -49.189 Average/Iteration 453 Average/MaxReturn -36.7171 Average/MinReturn -128.748 Average/NumEpisodes 120 Average/StdReturn 14.8822 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69204 GaussianMLPPolicy/KLAfter 0.00336771 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000109619 GaussianMLPPolicy/LossBefore 1.52985e-08 GaussianMLPPolicy/dLoss -0.000109603 Iteration 453 MetaTest/Average/AverageDiscountedReturn -45.5221 MetaTest/Average/AverageReturn -45.5221 MetaTest/Average/Iteration 453 MetaTest/Average/MaxReturn -37.2677 MetaTest/Average/MinReturn -56.9127 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.78722 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.5221 MetaTest/__unnamed_task__/AverageReturn -45.5221 MetaTest/__unnamed_task__/Iteration 453 MetaTest/__unnamed_task__/MaxReturn -37.2677 MetaTest/__unnamed_task__/MinReturn -56.9127 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.78722 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1792e+07 __unnamed_task__/AverageDiscountedReturn -25.2346 __unnamed_task__/AverageReturn -49.189 __unnamed_task__/Iteration 453 __unnamed_task__/MaxReturn -36.7171 __unnamed_task__/MinReturn -128.748 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.8822 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 22:46:42 | [maml_trainer] epoch #454 | Sampling for adapation and meta-testing... 2025-04-12 22:50:52 | [maml_trainer] epoch #454 | Finished meta-testing... 2025-04-12 22:50:52 | [maml_trainer] epoch #454 | Saving snapshot... 2025-04-12 22:51:14 | [maml_trainer] epoch #454 | Saved 2025-04-12 22:51:14 | [maml_trainer] epoch #454 | Time 799918.76 s 2025-04-12 22:51:14 | [maml_trainer] epoch #454 | EpochTime 1761.39 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.1784 Average/AverageReturn -48.5409 Average/Iteration 454 Average/MaxReturn -38.0776 Average/MinReturn -118.018 Average/NumEpisodes 120 Average/StdReturn 12.7805 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69154 GaussianMLPPolicy/KLAfter 0.00305489 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.32346e-05 GaussianMLPPolicy/LossBefore -1.30335e-08 GaussianMLPPolicy/dLoss 9.32216e-05 Iteration 454 MetaTest/Average/AverageDiscountedReturn -46.3252 MetaTest/Average/AverageReturn -46.3252 MetaTest/Average/Iteration 454 MetaTest/Average/MaxReturn -39.4988 MetaTest/Average/MinReturn -55.2744 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.81691 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.3252 MetaTest/__unnamed_task__/AverageReturn -46.3252 MetaTest/__unnamed_task__/Iteration 454 MetaTest/__unnamed_task__/MaxReturn -39.4988 MetaTest/__unnamed_task__/MinReturn -55.2744 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.81691 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.184e+07 __unnamed_task__/AverageDiscountedReturn -25.1784 __unnamed_task__/AverageReturn -48.5409 __unnamed_task__/Iteration 454 __unnamed_task__/MaxReturn -38.0776 __unnamed_task__/MinReturn -118.018 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.7805 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 23:15:55 | [maml_trainer] epoch #455 | Sampling for adapation and meta-testing... 2025-04-12 23:20:01 | [maml_trainer] epoch #455 | Finished meta-testing... 2025-04-12 23:20:01 | [maml_trainer] epoch #455 | Saving snapshot... 2025-04-12 23:20:22 | [maml_trainer] epoch #455 | Saved 2025-04-12 23:20:22 | [maml_trainer] epoch #455 | Time 801666.35 s 2025-04-12 23:20:22 | [maml_trainer] epoch #455 | EpochTime 1747.59 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.877 Average/AverageReturn -47.4779 Average/Iteration 455 Average/MaxReturn -38.1071 Average/MinReturn -113.126 Average/NumEpisodes 120 Average/StdReturn 8.78683 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69167 GaussianMLPPolicy/KLAfter 0.00351538 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000129939 GaussianMLPPolicy/LossBefore 3.33786e-09 GaussianMLPPolicy/dLoss 0.000129943 Iteration 455 MetaTest/Average/AverageDiscountedReturn -45.5608 MetaTest/Average/AverageReturn -45.5608 MetaTest/Average/Iteration 455 MetaTest/Average/MaxReturn -38.531 MetaTest/Average/MinReturn -58.3229 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.66354 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.5608 MetaTest/__unnamed_task__/AverageReturn -45.5608 MetaTest/__unnamed_task__/Iteration 455 MetaTest/__unnamed_task__/MaxReturn -38.531 MetaTest/__unnamed_task__/MinReturn -58.3229 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.66354 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1888e+07 __unnamed_task__/AverageDiscountedReturn -24.877 __unnamed_task__/AverageReturn -47.4779 __unnamed_task__/Iteration 455 __unnamed_task__/MaxReturn -38.1071 __unnamed_task__/MinReturn -113.126 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.78683 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-12 23:44:46 | [maml_trainer] epoch #456 | Sampling for adapation and meta-testing... 2025-04-12 23:48:51 | [maml_trainer] epoch #456 | Finished meta-testing... 2025-04-12 23:48:51 | [maml_trainer] epoch #456 | Saving snapshot... 2025-04-12 23:49:13 | [maml_trainer] epoch #456 | Saved 2025-04-12 23:49:13 | [maml_trainer] epoch #456 | Time 803397.11 s 2025-04-12 23:49:13 | [maml_trainer] epoch #456 | EpochTime 1730.75 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.6407 Average/AverageReturn -47.0165 Average/Iteration 456 Average/MaxReturn -35.3978 Average/MinReturn -130.82 Average/NumEpisodes 120 Average/StdReturn 10.993 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69073 GaussianMLPPolicy/KLAfter 0.00277673 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.73208e-05 GaussianMLPPolicy/LossBefore -2.9405e-09 GaussianMLPPolicy/dLoss -7.73238e-05 Iteration 456 MetaTest/Average/AverageDiscountedReturn -49.1142 MetaTest/Average/AverageReturn -49.1142 MetaTest/Average/Iteration 456 MetaTest/Average/MaxReturn -40.3587 MetaTest/Average/MinReturn -65.2457 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.65378 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.1142 MetaTest/__unnamed_task__/AverageReturn -49.1142 MetaTest/__unnamed_task__/Iteration 456 MetaTest/__unnamed_task__/MaxReturn -40.3587 MetaTest/__unnamed_task__/MinReturn -65.2457 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.65378 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1936e+07 __unnamed_task__/AverageDiscountedReturn -24.6407 __unnamed_task__/AverageReturn -47.0165 __unnamed_task__/Iteration 456 __unnamed_task__/MaxReturn -35.3978 __unnamed_task__/MinReturn -130.82 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.993 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 00:13:50 | [maml_trainer] epoch #457 | Sampling for adapation and meta-testing... 2025-04-13 00:17:58 | [maml_trainer] epoch #457 | Finished meta-testing... 2025-04-13 00:17:58 | [maml_trainer] epoch #457 | Saving snapshot... 2025-04-13 00:18:20 | [maml_trainer] epoch #457 | Saved 2025-04-13 00:18:20 | [maml_trainer] epoch #457 | Time 805144.29 s 2025-04-13 00:18:20 | [maml_trainer] epoch #457 | EpochTime 1747.18 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.9935 Average/AverageReturn -48.1974 Average/Iteration 457 Average/MaxReturn -38.1027 Average/MinReturn -139.035 Average/NumEpisodes 120 Average/StdReturn 11.4771 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69124 GaussianMLPPolicy/KLAfter 0.00169391 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.09106e-05 GaussianMLPPolicy/LossBefore 5.80152e-09 GaussianMLPPolicy/dLoss 3.09164e-05 Iteration 457 MetaTest/Average/AverageDiscountedReturn -49.3352 MetaTest/Average/AverageReturn -49.3352 MetaTest/Average/Iteration 457 MetaTest/Average/MaxReturn -40.5382 MetaTest/Average/MinReturn -101.369 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.3951 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.3352 MetaTest/__unnamed_task__/AverageReturn -49.3352 MetaTest/__unnamed_task__/Iteration 457 MetaTest/__unnamed_task__/MaxReturn -40.5382 MetaTest/__unnamed_task__/MinReturn -101.369 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.3951 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.1984e+07 __unnamed_task__/AverageDiscountedReturn -24.9935 __unnamed_task__/AverageReturn -48.1974 __unnamed_task__/Iteration 457 __unnamed_task__/MaxReturn -38.1027 __unnamed_task__/MinReturn -139.035 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.4771 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 00:43:02 | [maml_trainer] epoch #458 | Sampling for adapation and meta-testing... 2025-04-13 00:47:18 | [maml_trainer] epoch #458 | Finished meta-testing... 2025-04-13 00:47:18 | [maml_trainer] epoch #458 | Saving snapshot... 2025-04-13 00:47:39 | [maml_trainer] epoch #458 | Saved 2025-04-13 00:47:39 | [maml_trainer] epoch #458 | Time 806903.89 s 2025-04-13 00:47:39 | [maml_trainer] epoch #458 | EpochTime 1759.60 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.3934 Average/AverageReturn -49.4056 Average/Iteration 458 Average/MaxReturn -37.4562 Average/MinReturn -125.032 Average/NumEpisodes 120 Average/StdReturn 13.2969 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69011 GaussianMLPPolicy/KLAfter 0.00147652 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.18661e-05 GaussianMLPPolicy/LossBefore 3.49681e-09 GaussianMLPPolicy/dLoss -2.18626e-05 Iteration 458 MetaTest/Average/AverageDiscountedReturn -48.148 MetaTest/Average/AverageReturn -48.148 MetaTest/Average/Iteration 458 MetaTest/Average/MaxReturn -39.9819 MetaTest/Average/MinReturn -58.8253 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.44904 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.148 MetaTest/__unnamed_task__/AverageReturn -48.148 MetaTest/__unnamed_task__/Iteration 458 MetaTest/__unnamed_task__/MaxReturn -39.9819 MetaTest/__unnamed_task__/MinReturn -58.8253 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.44904 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2032e+07 __unnamed_task__/AverageDiscountedReturn -25.3934 __unnamed_task__/AverageReturn -49.4056 __unnamed_task__/Iteration 458 __unnamed_task__/MaxReturn -37.4562 __unnamed_task__/MinReturn -125.032 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 13.2969 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 01:12:32 | [maml_trainer] epoch #459 | Sampling for adapation and meta-testing... 2025-04-13 01:16:38 | [maml_trainer] epoch #459 | Finished meta-testing... 2025-04-13 01:16:38 | [maml_trainer] epoch #459 | Saving snapshot... 2025-04-13 01:17:00 | [maml_trainer] epoch #459 | Saved 2025-04-13 01:17:00 | [maml_trainer] epoch #459 | Time 808664.43 s 2025-04-13 01:17:00 | [maml_trainer] epoch #459 | EpochTime 1760.53 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.4163 Average/AverageReturn -49.2488 Average/Iteration 459 Average/MaxReturn -37.4941 Average/MinReturn -127.661 Average/NumEpisodes 120 Average/StdReturn 11.1156 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68926 GaussianMLPPolicy/KLAfter 0.00124072 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.75133e-05 GaussianMLPPolicy/LossBefore -9.13938e-10 GaussianMLPPolicy/dLoss 8.75123e-05 Iteration 459 MetaTest/Average/AverageDiscountedReturn -52.6029 MetaTest/Average/AverageReturn -52.6029 MetaTest/Average/Iteration 459 MetaTest/Average/MaxReturn -40.6906 MetaTest/Average/MinReturn -118.868 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.8804 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6029 MetaTest/__unnamed_task__/AverageReturn -52.6029 MetaTest/__unnamed_task__/Iteration 459 MetaTest/__unnamed_task__/MaxReturn -40.6906 MetaTest/__unnamed_task__/MinReturn -118.868 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.8804 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.208e+07 __unnamed_task__/AverageDiscountedReturn -25.4163 __unnamed_task__/AverageReturn -49.2488 __unnamed_task__/Iteration 459 __unnamed_task__/MaxReturn -37.4941 __unnamed_task__/MinReturn -127.661 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.1156 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 01:54:09 | [maml_trainer] epoch #460 | Sampling for adapation and meta-testing... 2025-04-13 02:01:27 | [maml_trainer] epoch #460 | Finished meta-testing... 2025-04-13 02:01:27 | [maml_trainer] epoch #460 | Saving snapshot... 2025-04-13 02:02:07 | [maml_trainer] epoch #460 | Saved 2025-04-13 02:02:07 | [maml_trainer] epoch #460 | Time 811371.66 s 2025-04-13 02:02:07 | [maml_trainer] epoch #460 | EpochTime 2707.22 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.6085 Average/AverageReturn -50.0782 Average/Iteration 460 Average/MaxReturn -37.7344 Average/MinReturn -122.189 Average/NumEpisodes 120 Average/StdReturn 12.3223 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68987 GaussianMLPPolicy/KLAfter 0.00132837 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.1048e-05 GaussianMLPPolicy/LossBefore -9.73542e-09 GaussianMLPPolicy/dLoss 3.10382e-05 Iteration 460 MetaTest/Average/AverageDiscountedReturn -47.4393 MetaTest/Average/AverageReturn -47.4393 MetaTest/Average/Iteration 460 MetaTest/Average/MaxReturn -37.4736 MetaTest/Average/MinReturn -62.802 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.09797 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4393 MetaTest/__unnamed_task__/AverageReturn -47.4393 MetaTest/__unnamed_task__/Iteration 460 MetaTest/__unnamed_task__/MaxReturn -37.4736 MetaTest/__unnamed_task__/MinReturn -62.802 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.09797 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2128e+07 __unnamed_task__/AverageDiscountedReturn -25.6085 __unnamed_task__/AverageReturn -50.0782 __unnamed_task__/Iteration 460 __unnamed_task__/MaxReturn -37.7344 __unnamed_task__/MinReturn -122.189 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.3223 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 02:46:42 | [maml_trainer] epoch #461 | Sampling for adapation and meta-testing... 2025-04-13 02:53:52 | [maml_trainer] epoch #461 | Finished meta-testing... 2025-04-13 02:53:52 | [maml_trainer] epoch #461 | Saving snapshot... 2025-04-13 02:54:33 | [maml_trainer] epoch #461 | Saved 2025-04-13 02:54:33 | [maml_trainer] epoch #461 | Time 814517.03 s 2025-04-13 02:54:33 | [maml_trainer] epoch #461 | EpochTime 3145.37 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.1848 Average/AverageReturn -48.7047 Average/Iteration 461 Average/MaxReturn -36.8366 Average/MinReturn -126.01 Average/NumEpisodes 120 Average/StdReturn 11.5304 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69072 GaussianMLPPolicy/KLAfter 0.00130342 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.75346e-05 GaussianMLPPolicy/LossBefore -7.35124e-09 GaussianMLPPolicy/dLoss 3.75273e-05 Iteration 461 MetaTest/Average/AverageDiscountedReturn -50.551 MetaTest/Average/AverageReturn -50.551 MetaTest/Average/Iteration 461 MetaTest/Average/MaxReturn -39.2442 MetaTest/Average/MinReturn -97.229 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 13.5349 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.551 MetaTest/__unnamed_task__/AverageReturn -50.551 MetaTest/__unnamed_task__/Iteration 461 MetaTest/__unnamed_task__/MaxReturn -39.2442 MetaTest/__unnamed_task__/MinReturn -97.229 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 13.5349 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2176e+07 __unnamed_task__/AverageDiscountedReturn -25.1848 __unnamed_task__/AverageReturn -48.7047 __unnamed_task__/Iteration 461 __unnamed_task__/MaxReturn -36.8366 __unnamed_task__/MinReturn -126.01 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.5304 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 03:37:41 | [maml_trainer] epoch #462 | Sampling for adapation and meta-testing... 2025-04-13 03:43:17 | [maml_trainer] epoch #462 | Finished meta-testing... 2025-04-13 03:43:17 | [maml_trainer] epoch #462 | Saving snapshot... 2025-04-13 03:43:47 | [maml_trainer] epoch #462 | Saved 2025-04-13 03:43:47 | [maml_trainer] epoch #462 | Time 817471.14 s 2025-04-13 03:43:47 | [maml_trainer] epoch #462 | EpochTime 2954.10 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.1804 Average/AverageReturn -49.1083 Average/Iteration 462 Average/MaxReturn -37.3771 Average/MinReturn -118.371 Average/NumEpisodes 120 Average/StdReturn 12.7197 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69116 GaussianMLPPolicy/KLAfter 0.000722662 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.59724e-05 GaussianMLPPolicy/LossBefore 6.27836e-09 GaussianMLPPolicy/dLoss -1.59661e-05 Iteration 462 MetaTest/Average/AverageDiscountedReturn -43.2431 MetaTest/Average/AverageReturn -43.2431 MetaTest/Average/Iteration 462 MetaTest/Average/MaxReturn -37.3407 MetaTest/Average/MinReturn -55.4537 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.28769 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -43.2431 MetaTest/__unnamed_task__/AverageReturn -43.2431 MetaTest/__unnamed_task__/Iteration 462 MetaTest/__unnamed_task__/MaxReturn -37.3407 MetaTest/__unnamed_task__/MinReturn -55.4537 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.28769 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2224e+07 __unnamed_task__/AverageDiscountedReturn -25.1804 __unnamed_task__/AverageReturn -49.1083 __unnamed_task__/Iteration 462 __unnamed_task__/MaxReturn -37.3771 __unnamed_task__/MinReturn -118.371 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.7197 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 04:12:00 | [maml_trainer] epoch #463 | Sampling for adapation and meta-testing... 2025-04-13 04:16:11 | [maml_trainer] epoch #463 | Finished meta-testing... 2025-04-13 04:16:11 | [maml_trainer] epoch #463 | Saving snapshot... 2025-04-13 04:16:32 | [maml_trainer] epoch #463 | Saved 2025-04-13 04:16:32 | [maml_trainer] epoch #463 | Time 819436.71 s 2025-04-13 04:16:32 | [maml_trainer] epoch #463 | EpochTime 1965.57 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.82 Average/AverageReturn -50.6225 Average/Iteration 463 Average/MaxReturn -37.5319 Average/MinReturn -138.65 Average/NumEpisodes 120 Average/StdReturn 14.7081 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69148 GaussianMLPPolicy/KLAfter 0.00106157 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.66108e-06 GaussianMLPPolicy/LossBefore -1.6133e-08 GaussianMLPPolicy/dLoss 4.64495e-06 Iteration 463 MetaTest/Average/AverageDiscountedReturn -52.3429 MetaTest/Average/AverageReturn -52.3429 MetaTest/Average/Iteration 463 MetaTest/Average/MaxReturn -37.4231 MetaTest/Average/MinReturn -112.268 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 18.1367 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -52.3429 MetaTest/__unnamed_task__/AverageReturn -52.3429 MetaTest/__unnamed_task__/Iteration 463 MetaTest/__unnamed_task__/MaxReturn -37.4231 MetaTest/__unnamed_task__/MinReturn -112.268 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 18.1367 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2272e+07 __unnamed_task__/AverageDiscountedReturn -25.82 __unnamed_task__/AverageReturn -50.6225 __unnamed_task__/Iteration 463 __unnamed_task__/MaxReturn -37.5319 __unnamed_task__/MinReturn -138.65 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.7081 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 04:41:34 | [maml_trainer] epoch #464 | Sampling for adapation and meta-testing... 2025-04-13 04:45:45 | [maml_trainer] epoch #464 | Finished meta-testing... 2025-04-13 04:45:45 | [maml_trainer] epoch #464 | Saving snapshot... 2025-04-13 04:46:08 | [maml_trainer] epoch #464 | Saved 2025-04-13 04:46:08 | [maml_trainer] epoch #464 | Time 821212.11 s 2025-04-13 04:46:08 | [maml_trainer] epoch #464 | EpochTime 1775.40 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.0981 Average/AverageReturn -49.0219 Average/Iteration 464 Average/MaxReturn -38.1135 Average/MinReturn -126.116 Average/NumEpisodes 120 Average/StdReturn 14.604 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69176 GaussianMLPPolicy/KLAfter 0.000619828 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.84946e-05 GaussianMLPPolicy/LossBefore 1.03315e-09 GaussianMLPPolicy/dLoss -3.84936e-05 Iteration 464 MetaTest/Average/AverageDiscountedReturn -47.3716 MetaTest/Average/AverageReturn -47.3716 MetaTest/Average/Iteration 464 MetaTest/Average/MaxReturn -38.7987 MetaTest/Average/MinReturn -59.3521 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.14507 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.3716 MetaTest/__unnamed_task__/AverageReturn -47.3716 MetaTest/__unnamed_task__/Iteration 464 MetaTest/__unnamed_task__/MaxReturn -38.7987 MetaTest/__unnamed_task__/MinReturn -59.3521 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.14507 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.232e+07 __unnamed_task__/AverageDiscountedReturn -25.0981 __unnamed_task__/AverageReturn -49.0219 __unnamed_task__/Iteration 464 __unnamed_task__/MaxReturn -38.1135 __unnamed_task__/MinReturn -126.116 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.604 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 05:10:48 | [maml_trainer] epoch #465 | Sampling for adapation and meta-testing... 2025-04-13 05:14:55 | [maml_trainer] epoch #465 | Finished meta-testing... 2025-04-13 05:14:55 | [maml_trainer] epoch #465 | Saving snapshot... 2025-04-13 05:15:17 | [maml_trainer] epoch #465 | Saved 2025-04-13 05:15:17 | [maml_trainer] epoch #465 | Time 822961.24 s 2025-04-13 05:15:17 | [maml_trainer] epoch #465 | EpochTime 1749.12 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.9351 Average/AverageReturn -48.3196 Average/Iteration 465 Average/MaxReturn -37.6069 Average/MinReturn -135.705 Average/NumEpisodes 120 Average/StdReturn 12.8316 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69191 GaussianMLPPolicy/KLAfter 0.00134824 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.78283e-06 GaussianMLPPolicy/LossBefore -5.36442e-09 GaussianMLPPolicy/dLoss -9.7882e-06 Iteration 465 MetaTest/Average/AverageDiscountedReturn -50.7057 MetaTest/Average/AverageReturn -50.7057 MetaTest/Average/Iteration 465 MetaTest/Average/MaxReturn -38.1333 MetaTest/Average/MinReturn -111.617 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 15.1227 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.7057 MetaTest/__unnamed_task__/AverageReturn -50.7057 MetaTest/__unnamed_task__/Iteration 465 MetaTest/__unnamed_task__/MaxReturn -38.1333 MetaTest/__unnamed_task__/MinReturn -111.617 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 15.1227 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2368e+07 __unnamed_task__/AverageDiscountedReturn -24.9351 __unnamed_task__/AverageReturn -48.3196 __unnamed_task__/Iteration 465 __unnamed_task__/MaxReturn -37.6069 __unnamed_task__/MinReturn -135.705 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.8316 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 05:40:08 | [maml_trainer] epoch #466 | Sampling for adapation and meta-testing... 2025-04-13 05:44:16 | [maml_trainer] epoch #466 | Finished meta-testing... 2025-04-13 05:44:16 | [maml_trainer] epoch #466 | Saving snapshot... 2025-04-13 05:44:37 | [maml_trainer] epoch #466 | Saved 2025-04-13 05:44:37 | [maml_trainer] epoch #466 | Time 824721.45 s 2025-04-13 05:44:37 | [maml_trainer] epoch #466 | EpochTime 1760.20 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.1705 Average/AverageReturn -49.0755 Average/Iteration 466 Average/MaxReturn -35.7172 Average/MinReturn -123.401 Average/NumEpisodes 120 Average/StdReturn 14.2257 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69218 GaussianMLPPolicy/KLAfter 0.00135775 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.64227e-05 GaussianMLPPolicy/LossBefore -8.42412e-09 GaussianMLPPolicy/dLoss 3.64143e-05 Iteration 466 MetaTest/Average/AverageDiscountedReturn -51.8893 MetaTest/Average/AverageReturn -51.8893 MetaTest/Average/Iteration 466 MetaTest/Average/MaxReturn -40.5762 MetaTest/Average/MinReturn -105.642 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.5446 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.8893 MetaTest/__unnamed_task__/AverageReturn -51.8893 MetaTest/__unnamed_task__/Iteration 466 MetaTest/__unnamed_task__/MaxReturn -40.5762 MetaTest/__unnamed_task__/MinReturn -105.642 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.5446 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2416e+07 __unnamed_task__/AverageDiscountedReturn -25.1705 __unnamed_task__/AverageReturn -49.0755 __unnamed_task__/Iteration 466 __unnamed_task__/MaxReturn -35.7172 __unnamed_task__/MinReturn -123.401 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.2257 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 06:09:14 | [maml_trainer] epoch #467 | Sampling for adapation and meta-testing... 2025-04-13 06:13:27 | [maml_trainer] epoch #467 | Finished meta-testing... 2025-04-13 06:13:27 | [maml_trainer] epoch #467 | Saving snapshot... 2025-04-13 06:13:50 | [maml_trainer] epoch #467 | Saved 2025-04-13 06:13:50 | [maml_trainer] epoch #467 | Time 826474.35 s 2025-04-13 06:13:50 | [maml_trainer] epoch #467 | EpochTime 1752.90 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.9916 Average/AverageReturn -48.202 Average/Iteration 467 Average/MaxReturn -37.1279 Average/MinReturn -101.01 Average/NumEpisodes 120 Average/StdReturn 10.3615 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69171 GaussianMLPPolicy/KLAfter 0.00212855 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000100398 GaussianMLPPolicy/LossBefore -1.41859e-08 GaussianMLPPolicy/dLoss -0.000100412 Iteration 467 MetaTest/Average/AverageDiscountedReturn -46.689 MetaTest/Average/AverageReturn -46.689 MetaTest/Average/Iteration 467 MetaTest/Average/MaxReturn -38.3238 MetaTest/Average/MinReturn -62.6795 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.07676 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.689 MetaTest/__unnamed_task__/AverageReturn -46.689 MetaTest/__unnamed_task__/Iteration 467 MetaTest/__unnamed_task__/MaxReturn -38.3238 MetaTest/__unnamed_task__/MinReturn -62.6795 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.07676 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2464e+07 __unnamed_task__/AverageDiscountedReturn -24.9916 __unnamed_task__/AverageReturn -48.202 __unnamed_task__/Iteration 467 __unnamed_task__/MaxReturn -37.1279 __unnamed_task__/MinReturn -101.01 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 10.3615 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 06:38:36 | [maml_trainer] epoch #468 | Sampling for adapation and meta-testing... 2025-04-13 06:42:43 | [maml_trainer] epoch #468 | Finished meta-testing... 2025-04-13 06:42:43 | [maml_trainer] epoch #468 | Saving snapshot... 2025-04-13 06:43:04 | [maml_trainer] epoch #468 | Saved 2025-04-13 06:43:04 | [maml_trainer] epoch #468 | Time 828228.51 s 2025-04-13 06:43:04 | [maml_trainer] epoch #468 | EpochTime 1754.16 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.2551 Average/AverageReturn -49.4234 Average/Iteration 468 Average/MaxReturn -37.4976 Average/MinReturn -130.023 Average/NumEpisodes 120 Average/StdReturn 14.9268 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69148 GaussianMLPPolicy/KLAfter 0.00268117 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 3.26095e-05 GaussianMLPPolicy/LossBefore -3.8147e-09 GaussianMLPPolicy/dLoss -3.26133e-05 Iteration 468 MetaTest/Average/AverageDiscountedReturn -54.4013 MetaTest/Average/AverageReturn -54.4013 MetaTest/Average/Iteration 468 MetaTest/Average/MaxReturn -37.7363 MetaTest/Average/MinReturn -117.829 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.1579 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.4013 MetaTest/__unnamed_task__/AverageReturn -54.4013 MetaTest/__unnamed_task__/Iteration 468 MetaTest/__unnamed_task__/MaxReturn -37.7363 MetaTest/__unnamed_task__/MinReturn -117.829 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.1579 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2512e+07 __unnamed_task__/AverageDiscountedReturn -25.2551 __unnamed_task__/AverageReturn -49.4234 __unnamed_task__/Iteration 468 __unnamed_task__/MaxReturn -37.4976 __unnamed_task__/MinReturn -130.023 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.9268 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 07:07:56 | [maml_trainer] epoch #469 | Sampling for adapation and meta-testing... 2025-04-13 07:12:02 | [maml_trainer] epoch #469 | Finished meta-testing... 2025-04-13 07:12:02 | [maml_trainer] epoch #469 | Saving snapshot... 2025-04-13 07:12:23 | [maml_trainer] epoch #469 | Saved 2025-04-13 07:12:23 | [maml_trainer] epoch #469 | Time 829987.65 s 2025-04-13 07:12:23 | [maml_trainer] epoch #469 | EpochTime 1759.14 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.3998 Average/AverageReturn -50.0614 Average/Iteration 469 Average/MaxReturn -35.0622 Average/MinReturn -144.91 Average/NumEpisodes 120 Average/StdReturn 16.5334 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69063 GaussianMLPPolicy/KLAfter 0.00510049 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.92011e-05 GaussianMLPPolicy/LossBefore -6.07967e-09 GaussianMLPPolicy/dLoss -7.92072e-05 Iteration 469 MetaTest/Average/AverageDiscountedReturn -46.4231 MetaTest/Average/AverageReturn -46.4231 MetaTest/Average/Iteration 469 MetaTest/Average/MaxReturn -38.3078 MetaTest/Average/MinReturn -65.5556 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.02133 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.4231 MetaTest/__unnamed_task__/AverageReturn -46.4231 MetaTest/__unnamed_task__/Iteration 469 MetaTest/__unnamed_task__/MaxReturn -38.3078 MetaTest/__unnamed_task__/MinReturn -65.5556 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.02133 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.256e+07 __unnamed_task__/AverageDiscountedReturn -25.3998 __unnamed_task__/AverageReturn -50.0614 __unnamed_task__/Iteration 469 __unnamed_task__/MaxReturn -35.0622 __unnamed_task__/MinReturn -144.91 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 16.5334 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 07:37:12 | [maml_trainer] epoch #470 | Sampling for adapation and meta-testing... 2025-04-13 07:41:20 | [maml_trainer] epoch #470 | Finished meta-testing... 2025-04-13 07:41:20 | [maml_trainer] epoch #470 | Saving snapshot... 2025-04-13 07:41:42 | [maml_trainer] epoch #470 | Saved 2025-04-13 07:41:42 | [maml_trainer] epoch #470 | Time 831746.67 s 2025-04-13 07:41:42 | [maml_trainer] epoch #470 | EpochTime 1759.02 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.8804 Average/AverageReturn -52.9804 Average/Iteration 470 Average/MaxReturn -37.2287 Average/MinReturn -157.391 Average/NumEpisodes 120 Average/StdReturn 19.9632 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68946 GaussianMLPPolicy/KLAfter 0.00824071 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.55242e-05 GaussianMLPPolicy/LossBefore 1.47025e-09 GaussianMLPPolicy/dLoss 1.55257e-05 Iteration 470 MetaTest/Average/AverageDiscountedReturn -49.7106 MetaTest/Average/AverageReturn -49.7106 MetaTest/Average/Iteration 470 MetaTest/Average/MaxReturn -38.3264 MetaTest/Average/MinReturn -108.912 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.1784 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.7106 MetaTest/__unnamed_task__/AverageReturn -49.7106 MetaTest/__unnamed_task__/Iteration 470 MetaTest/__unnamed_task__/MaxReturn -38.3264 MetaTest/__unnamed_task__/MinReturn -108.912 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.1784 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2608e+07 __unnamed_task__/AverageDiscountedReturn -25.8804 __unnamed_task__/AverageReturn -52.9804 __unnamed_task__/Iteration 470 __unnamed_task__/MaxReturn -37.2287 __unnamed_task__/MinReturn -157.391 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 19.9632 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 08:06:18 | [maml_trainer] epoch #471 | Sampling for adapation and meta-testing... 2025-04-13 08:10:23 | [maml_trainer] epoch #471 | Finished meta-testing... 2025-04-13 08:10:23 | [maml_trainer] epoch #471 | Saving snapshot... 2025-04-13 08:10:45 | [maml_trainer] epoch #471 | Saved 2025-04-13 08:10:45 | [maml_trainer] epoch #471 | Time 833489.42 s 2025-04-13 08:10:45 | [maml_trainer] epoch #471 | EpochTime 1742.75 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.1159 Average/AverageReturn -51.5196 Average/Iteration 471 Average/MaxReturn -35.931 Average/MinReturn -147.675 Average/NumEpisodes 120 Average/StdReturn 19.7965 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68864 GaussianMLPPolicy/KLAfter 0.0040371 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.37884e-05 GaussianMLPPolicy/LossBefore -4.15246e-09 GaussianMLPPolicy/dLoss -8.37926e-05 Iteration 471 MetaTest/Average/AverageDiscountedReturn -63.2981 MetaTest/Average/AverageReturn -63.2981 MetaTest/Average/Iteration 471 MetaTest/Average/MaxReturn -38.9344 MetaTest/Average/MinReturn -136.237 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 29.5742 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -63.2981 MetaTest/__unnamed_task__/AverageReturn -63.2981 MetaTest/__unnamed_task__/Iteration 471 MetaTest/__unnamed_task__/MaxReturn -38.9344 MetaTest/__unnamed_task__/MinReturn -136.237 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 29.5742 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2656e+07 __unnamed_task__/AverageDiscountedReturn -25.1159 __unnamed_task__/AverageReturn -51.5196 __unnamed_task__/Iteration 471 __unnamed_task__/MaxReturn -35.931 __unnamed_task__/MinReturn -147.675 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 19.7965 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 08:35:26 | [maml_trainer] epoch #472 | Sampling for adapation and meta-testing... 2025-04-13 08:39:38 | [maml_trainer] epoch #472 | Finished meta-testing... 2025-04-13 08:39:38 | [maml_trainer] epoch #472 | Saving snapshot... 2025-04-13 08:40:00 | [maml_trainer] epoch #472 | Saved 2025-04-13 08:40:00 | [maml_trainer] epoch #472 | Time 835244.67 s 2025-04-13 08:40:00 | [maml_trainer] epoch #472 | EpochTime 1755.24 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.3991 Average/AverageReturn -52.5674 Average/Iteration 472 Average/MaxReturn -34.957 Average/MinReturn -152.502 Average/NumEpisodes 120 Average/StdReturn 21.8751 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68808 GaussianMLPPolicy/KLAfter 0.00335697 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.09724e-06 GaussianMLPPolicy/LossBefore -7.94729e-11 GaussianMLPPolicy/dLoss -1.09732e-06 Iteration 472 MetaTest/Average/AverageDiscountedReturn -51.3768 MetaTest/Average/AverageReturn -51.3768 MetaTest/Average/Iteration 472 MetaTest/Average/MaxReturn -38.1489 MetaTest/Average/MinReturn -124.342 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.7945 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.3768 MetaTest/__unnamed_task__/AverageReturn -51.3768 MetaTest/__unnamed_task__/Iteration 472 MetaTest/__unnamed_task__/MaxReturn -38.1489 MetaTest/__unnamed_task__/MinReturn -124.342 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.7945 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2704e+07 __unnamed_task__/AverageDiscountedReturn -25.3991 __unnamed_task__/AverageReturn -52.5674 __unnamed_task__/Iteration 472 __unnamed_task__/MaxReturn -34.957 __unnamed_task__/MinReturn -152.502 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 21.8751 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 09:04:39 | [maml_trainer] epoch #473 | Sampling for adapation and meta-testing... 2025-04-13 09:08:51 | [maml_trainer] epoch #473 | Finished meta-testing... 2025-04-13 09:08:51 | [maml_trainer] epoch #473 | Saving snapshot... 2025-04-13 09:09:12 | [maml_trainer] epoch #473 | Saved 2025-04-13 09:09:12 | [maml_trainer] epoch #473 | Time 836996.27 s 2025-04-13 09:09:12 | [maml_trainer] epoch #473 | EpochTime 1751.60 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.639 Average/AverageReturn -48.6053 Average/Iteration 473 Average/MaxReturn -34.8489 Average/MinReturn -135.065 Average/NumEpisodes 120 Average/StdReturn 14.2276 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68796 GaussianMLPPolicy/KLAfter 0.00247317 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.09965e-05 GaussianMLPPolicy/LossBefore 3.41733e-09 GaussianMLPPolicy/dLoss 1.1e-05 Iteration 473 MetaTest/Average/AverageDiscountedReturn -48.1697 MetaTest/Average/AverageReturn -48.1697 MetaTest/Average/Iteration 473 MetaTest/Average/MaxReturn -37.6256 MetaTest/Average/MinReturn -72.9055 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 8.68649 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1697 MetaTest/__unnamed_task__/AverageReturn -48.1697 MetaTest/__unnamed_task__/Iteration 473 MetaTest/__unnamed_task__/MaxReturn -37.6256 MetaTest/__unnamed_task__/MinReturn -72.9055 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 8.68649 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2752e+07 __unnamed_task__/AverageDiscountedReturn -24.639 __unnamed_task__/AverageReturn -48.6053 __unnamed_task__/Iteration 473 __unnamed_task__/MaxReturn -34.8489 __unnamed_task__/MinReturn -135.065 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 14.2276 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 09:33:50 | [maml_trainer] epoch #474 | Sampling for adapation and meta-testing... 2025-04-13 09:37:54 | [maml_trainer] epoch #474 | Finished meta-testing... 2025-04-13 09:37:54 | [maml_trainer] epoch #474 | Saving snapshot... 2025-04-13 09:38:16 | [maml_trainer] epoch #474 | Saved 2025-04-13 09:38:16 | [maml_trainer] epoch #474 | Time 838740.27 s 2025-04-13 09:38:16 | [maml_trainer] epoch #474 | EpochTime 1744.00 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.2977 Average/AverageReturn -51.1657 Average/Iteration 474 Average/MaxReturn -35.9761 Average/MinReturn -142.516 Average/NumEpisodes 120 Average/StdReturn 20.0056 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68809 GaussianMLPPolicy/KLAfter 0.00233404 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000100223 GaussianMLPPolicy/LossBefore -7.90755e-09 GaussianMLPPolicy/dLoss 0.000100215 Iteration 474 MetaTest/Average/AverageDiscountedReturn -49.9986 MetaTest/Average/AverageReturn -49.9986 MetaTest/Average/Iteration 474 MetaTest/Average/MaxReturn -37.6338 MetaTest/Average/MinReturn -134.061 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.2617 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.9986 MetaTest/__unnamed_task__/AverageReturn -49.9986 MetaTest/__unnamed_task__/Iteration 474 MetaTest/__unnamed_task__/MaxReturn -37.6338 MetaTest/__unnamed_task__/MinReturn -134.061 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.2617 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.28e+07 __unnamed_task__/AverageDiscountedReturn -25.2977 __unnamed_task__/AverageReturn -51.1657 __unnamed_task__/Iteration 474 __unnamed_task__/MaxReturn -35.9761 __unnamed_task__/MinReturn -142.516 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 20.0056 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 10:02:46 | [maml_trainer] epoch #475 | Sampling for adapation and meta-testing... 2025-04-13 10:06:53 | [maml_trainer] epoch #475 | Finished meta-testing... 2025-04-13 10:06:53 | [maml_trainer] epoch #475 | Saving snapshot... 2025-04-13 10:07:15 | [maml_trainer] epoch #475 | Saved 2025-04-13 10:07:15 | [maml_trainer] epoch #475 | Time 840479.87 s 2025-04-13 10:07:15 | [maml_trainer] epoch #475 | EpochTime 1739.60 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.4161 Average/AverageReturn -48.4703 Average/Iteration 475 Average/MaxReturn -35.9097 Average/MinReturn -117.167 Average/NumEpisodes 120 Average/StdReturn 13.6475 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68844 GaussianMLPPolicy/KLAfter 0.00341142 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.21033e-05 GaussianMLPPolicy/LossBefore 8.52346e-09 GaussianMLPPolicy/dLoss 3.21118e-05 Iteration 475 MetaTest/Average/AverageDiscountedReturn -49.9938 MetaTest/Average/AverageReturn -49.9938 MetaTest/Average/Iteration 475 MetaTest/Average/MaxReturn -38.6739 MetaTest/Average/MinReturn -90.5431 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.6909 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.9938 MetaTest/__unnamed_task__/AverageReturn -49.9938 MetaTest/__unnamed_task__/Iteration 475 MetaTest/__unnamed_task__/MaxReturn -38.6739 MetaTest/__unnamed_task__/MinReturn -90.5431 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.6909 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2848e+07 __unnamed_task__/AverageDiscountedReturn -24.4161 __unnamed_task__/AverageReturn -48.4703 __unnamed_task__/Iteration 475 __unnamed_task__/MaxReturn -35.9097 __unnamed_task__/MinReturn -117.167 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 13.6475 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 10:32:03 | [maml_trainer] epoch #476 | Sampling for adapation and meta-testing... 2025-04-13 10:36:12 | [maml_trainer] epoch #476 | Finished meta-testing... 2025-04-13 10:36:12 | [maml_trainer] epoch #476 | Saving snapshot... 2025-04-13 10:36:33 | [maml_trainer] epoch #476 | Saved 2025-04-13 10:36:33 | [maml_trainer] epoch #476 | Time 842237.45 s 2025-04-13 10:36:33 | [maml_trainer] epoch #476 | EpochTime 1757.58 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.4456 Average/AverageReturn -47.8469 Average/Iteration 476 Average/MaxReturn -36.0614 Average/MinReturn -144.133 Average/NumEpisodes 120 Average/StdReturn 13.9006 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.6882 GaussianMLPPolicy/KLAfter 0.0027002 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.23435e-05 GaussianMLPPolicy/LossBefore 6.63598e-09 GaussianMLPPolicy/dLoss 5.23502e-05 Iteration 476 MetaTest/Average/AverageDiscountedReturn -49.8064 MetaTest/Average/AverageReturn -49.8064 MetaTest/Average/Iteration 476 MetaTest/Average/MaxReturn -40.3387 MetaTest/Average/MinReturn -69.6496 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.34713 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8064 MetaTest/__unnamed_task__/AverageReturn -49.8064 MetaTest/__unnamed_task__/Iteration 476 MetaTest/__unnamed_task__/MaxReturn -40.3387 MetaTest/__unnamed_task__/MinReturn -69.6496 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.34713 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2896e+07 __unnamed_task__/AverageDiscountedReturn -24.4456 __unnamed_task__/AverageReturn -47.8469 __unnamed_task__/Iteration 476 __unnamed_task__/MaxReturn -36.0614 __unnamed_task__/MinReturn -144.133 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 13.9006 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 11:01:09 | [maml_trainer] epoch #477 | Sampling for adapation and meta-testing... 2025-04-13 11:05:15 | [maml_trainer] epoch #477 | Finished meta-testing... 2025-04-13 11:05:15 | [maml_trainer] epoch #477 | Saving snapshot... 2025-04-13 11:05:37 | [maml_trainer] epoch #477 | Saved 2025-04-13 11:05:37 | [maml_trainer] epoch #477 | Time 843981.28 s 2025-04-13 11:05:37 | [maml_trainer] epoch #477 | EpochTime 1743.83 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.012 Average/AverageReturn -50.3534 Average/Iteration 477 Average/MaxReturn -34.874 Average/MinReturn -143.596 Average/NumEpisodes 120 Average/StdReturn 18.8437 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68914 GaussianMLPPolicy/KLAfter 0.00218556 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.94811e-05 GaussianMLPPolicy/LossBefore 6.79493e-09 GaussianMLPPolicy/dLoss 2.94879e-05 Iteration 477 MetaTest/Average/AverageDiscountedReturn -53.4059 MetaTest/Average/AverageReturn -53.4059 MetaTest/Average/Iteration 477 MetaTest/Average/MaxReturn -40.1869 MetaTest/Average/MinReturn -156.932 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.47 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.4059 MetaTest/__unnamed_task__/AverageReturn -53.4059 MetaTest/__unnamed_task__/Iteration 477 MetaTest/__unnamed_task__/MaxReturn -40.1869 MetaTest/__unnamed_task__/MinReturn -156.932 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.47 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2944e+07 __unnamed_task__/AverageDiscountedReturn -25.012 __unnamed_task__/AverageReturn -50.3534 __unnamed_task__/Iteration 477 __unnamed_task__/MaxReturn -34.874 __unnamed_task__/MinReturn -143.596 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 18.8437 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 11:30:06 | [maml_trainer] epoch #478 | Sampling for adapation and meta-testing... 2025-04-13 11:34:12 | [maml_trainer] epoch #478 | Finished meta-testing... 2025-04-13 11:34:12 | [maml_trainer] epoch #478 | Saving snapshot... 2025-04-13 11:34:33 | [maml_trainer] epoch #478 | Saved 2025-04-13 11:34:33 | [maml_trainer] epoch #478 | Time 845717.26 s 2025-04-13 11:34:33 | [maml_trainer] epoch #478 | EpochTime 1735.97 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.7128 Average/AverageReturn -48.0374 Average/Iteration 478 Average/MaxReturn -35.026 Average/MinReturn -83.6475 Average/NumEpisodes 120 Average/StdReturn 7.75657 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68967 GaussianMLPPolicy/KLAfter 0.00243361 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 7.47247e-05 GaussianMLPPolicy/LossBefore 2.05835e-08 GaussianMLPPolicy/dLoss -7.47041e-05 Iteration 478 MetaTest/Average/AverageDiscountedReturn -46.5951 MetaTest/Average/AverageReturn -46.5951 MetaTest/Average/Iteration 478 MetaTest/Average/MaxReturn -39.0783 MetaTest/Average/MinReturn -56.4781 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 4.38924 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.5951 MetaTest/__unnamed_task__/AverageReturn -46.5951 MetaTest/__unnamed_task__/Iteration 478 MetaTest/__unnamed_task__/MaxReturn -39.0783 MetaTest/__unnamed_task__/MinReturn -56.4781 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 4.38924 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.2992e+07 __unnamed_task__/AverageDiscountedReturn -24.7128 __unnamed_task__/AverageReturn -48.0374 __unnamed_task__/Iteration 478 __unnamed_task__/MaxReturn -35.026 __unnamed_task__/MinReturn -83.6475 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 7.75657 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-13 11:58:55 | [maml_trainer] epoch #479 | Sampling for adapation and meta-testing... 2025-04-13 12:02:54 | [maml_trainer] epoch #479 | Finished meta-testing... 2025-04-13 12:02:54 | [maml_trainer] epoch #479 | Saving snapshot... 2025-04-13 12:03:15 | [maml_trainer] epoch #479 | Saved 2025-04-13 12:03:15 | [maml_trainer] epoch #479 | Time 847439.85 s 2025-04-13 12:03:15 | [maml_trainer] epoch #479 | EpochTime 1722.59 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.5712 Average/AverageReturn -47.836 Average/Iteration 479 Average/MaxReturn -37.2019 Average/MinReturn -84.5094 Average/NumEpisodes 120 Average/StdReturn 8.06228 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69031 GaussianMLPPolicy/KLAfter 0.00299514 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -7.91701e-06 GaussianMLPPolicy/LossBefore 4.60943e-09 GaussianMLPPolicy/dLoss 7.92162e-06 Iteration 479 MetaTest/Average/AverageDiscountedReturn -49.8231 MetaTest/Average/AverageReturn -49.8231 MetaTest/Average/Iteration 479 MetaTest/Average/MaxReturn -38.8096 MetaTest/Average/MinReturn -82.1697 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 11.2153 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8231 MetaTest/__unnamed_task__/AverageReturn -49.8231 MetaTest/__unnamed_task__/Iteration 479 MetaTest/__unnamed_task__/MaxReturn -38.8096 MetaTest/__unnamed_task__/MinReturn -82.1697 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 11.2153 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.304e+07 __unnamed_task__/AverageDiscountedReturn -24.5712 __unnamed_task__/AverageReturn -47.836 __unnamed_task__/Iteration 479 __unnamed_task__/MaxReturn -37.2019 __unnamed_task__/MinReturn -84.5094 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 8.06228 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-13 12:27:22 | [maml_trainer] epoch #480 | Sampling for adapation and meta-testing... 2025-04-13 12:31:22 | [maml_trainer] epoch #480 | Finished meta-testing... 2025-04-13 12:31:22 | [maml_trainer] epoch #480 | Saving snapshot... 2025-04-13 12:31:44 | [maml_trainer] epoch #480 | Saved 2025-04-13 12:31:44 | [maml_trainer] epoch #480 | Time 849148.54 s 2025-04-13 12:31:44 | [maml_trainer] epoch #480 | EpochTime 1708.69 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.119 Average/AverageReturn -49.3903 Average/Iteration 480 Average/MaxReturn -37.3337 Average/MinReturn -103.975 Average/NumEpisodes 120 Average/StdReturn 9.01486 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69185 GaussianMLPPolicy/KLAfter 0.00314561 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.00013583 GaussianMLPPolicy/LossBefore -2.61466e-08 GaussianMLPPolicy/dLoss -0.000135856 Iteration 480 MetaTest/Average/AverageDiscountedReturn -50.6371 MetaTest/Average/AverageReturn -50.6371 MetaTest/Average/Iteration 480 MetaTest/Average/MaxReturn -40.1461 MetaTest/Average/MinReturn -102.693 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 12.5815 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.6371 MetaTest/__unnamed_task__/AverageReturn -50.6371 MetaTest/__unnamed_task__/Iteration 480 MetaTest/__unnamed_task__/MaxReturn -40.1461 MetaTest/__unnamed_task__/MinReturn -102.693 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 12.5815 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3088e+07 __unnamed_task__/AverageDiscountedReturn -25.119 __unnamed_task__/AverageReturn -49.3903 __unnamed_task__/Iteration 480 __unnamed_task__/MaxReturn -37.3337 __unnamed_task__/MinReturn -103.975 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 9.01486 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 12:55:49 | [maml_trainer] epoch #481 | Sampling for adapation and meta-testing... 2025-04-13 12:59:49 | [maml_trainer] epoch #481 | Finished meta-testing... 2025-04-13 12:59:50 | [maml_trainer] epoch #481 | Saving snapshot... 2025-04-13 13:00:12 | [maml_trainer] epoch #481 | Saved 2025-04-13 13:00:12 | [maml_trainer] epoch #481 | Time 850856.19 s 2025-04-13 13:00:12 | [maml_trainer] epoch #481 | EpochTime 1707.64 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.5102 Average/AverageReturn -50.3003 Average/Iteration 481 Average/MaxReturn -39.2861 Average/MinReturn -135.514 Average/NumEpisodes 120 Average/StdReturn 11.6343 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69303 GaussianMLPPolicy/KLAfter 0.0023941 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 9.82202e-05 GaussianMLPPolicy/LossBefore 9.33806e-09 GaussianMLPPolicy/dLoss -9.82109e-05 Iteration 481 MetaTest/Average/AverageDiscountedReturn -50.4037 MetaTest/Average/AverageReturn -50.4037 MetaTest/Average/Iteration 481 MetaTest/Average/MaxReturn -42.1529 MetaTest/Average/MinReturn -74.8224 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 9.37635 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.4037 MetaTest/__unnamed_task__/AverageReturn -50.4037 MetaTest/__unnamed_task__/Iteration 481 MetaTest/__unnamed_task__/MaxReturn -42.1529 MetaTest/__unnamed_task__/MinReturn -74.8224 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 9.37635 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3136e+07 __unnamed_task__/AverageDiscountedReturn -25.5102 __unnamed_task__/AverageReturn -50.3003 __unnamed_task__/Iteration 481 __unnamed_task__/MaxReturn -39.2861 __unnamed_task__/MinReturn -135.514 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.6343 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 13:24:19 | [maml_trainer] epoch #482 | Sampling for adapation and meta-testing... 2025-04-13 13:28:21 | [maml_trainer] epoch #482 | Finished meta-testing... 2025-04-13 13:28:21 | [maml_trainer] epoch #482 | Saving snapshot... 2025-04-13 13:28:42 | [maml_trainer] epoch #482 | Saved 2025-04-13 13:28:42 | [maml_trainer] epoch #482 | Time 852566.66 s 2025-04-13 13:28:42 | [maml_trainer] epoch #482 | EpochTime 1710.47 s ------------------------------------------------- ------------- Average/AverageDiscountedReturn -24.7694 Average/AverageReturn -48.5927 Average/Iteration 482 Average/MaxReturn -37.7682 Average/MinReturn -68.2881 Average/NumEpisodes 120 Average/StdReturn 6.70435 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69423 GaussianMLPPolicy/KLAfter 0.0025646 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -9.82452e-05 GaussianMLPPolicy/LossBefore -7.62939e-09 GaussianMLPPolicy/dLoss 9.82376e-05 Iteration 482 MetaTest/Average/AverageDiscountedReturn -47.4713 MetaTest/Average/AverageReturn -47.4713 MetaTest/Average/Iteration 482 MetaTest/Average/MaxReturn -41.1449 MetaTest/Average/MinReturn -62.7586 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.29534 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4713 MetaTest/__unnamed_task__/AverageReturn -47.4713 MetaTest/__unnamed_task__/Iteration 482 MetaTest/__unnamed_task__/MaxReturn -41.1449 MetaTest/__unnamed_task__/MinReturn -62.7586 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.29534 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3184e+07 __unnamed_task__/AverageDiscountedReturn -24.7694 __unnamed_task__/AverageReturn -48.5927 __unnamed_task__/Iteration 482 __unnamed_task__/MaxReturn -37.7682 __unnamed_task__/MinReturn -68.2881 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.70435 __unnamed_task__/TerminationRate 0 ------------------------------------------------- ------------- 2025-04-13 13:52:52 | [maml_trainer] epoch #483 | Sampling for adapation and meta-testing... 2025-04-13 13:56:56 | [maml_trainer] epoch #483 | Finished meta-testing... 2025-04-13 13:56:56 | [maml_trainer] epoch #483 | Saving snapshot... 2025-04-13 13:57:17 | [maml_trainer] epoch #483 | Saved 2025-04-13 13:57:17 | [maml_trainer] epoch #483 | Time 854281.29 s 2025-04-13 13:57:17 | [maml_trainer] epoch #483 | EpochTime 1714.63 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.1147 Average/AverageReturn -49.6094 Average/Iteration 483 Average/MaxReturn -34.7636 Average/MinReturn -137.547 Average/NumEpisodes 120 Average/StdReturn 12.9544 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69562 GaussianMLPPolicy/KLAfter 0.00276083 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 6.00057e-05 GaussianMLPPolicy/LossBefore -2.54313e-09 GaussianMLPPolicy/dLoss -6.00082e-05 Iteration 483 MetaTest/Average/AverageDiscountedReturn -49.7532 MetaTest/Average/AverageReturn -49.7532 MetaTest/Average/Iteration 483 MetaTest/Average/MaxReturn -39.1484 MetaTest/Average/MinReturn -68.4788 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.94146 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.7532 MetaTest/__unnamed_task__/AverageReturn -49.7532 MetaTest/__unnamed_task__/Iteration 483 MetaTest/__unnamed_task__/MaxReturn -39.1484 MetaTest/__unnamed_task__/MinReturn -68.4788 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.94146 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3232e+07 __unnamed_task__/AverageDiscountedReturn -25.1147 __unnamed_task__/AverageReturn -49.6094 __unnamed_task__/Iteration 483 __unnamed_task__/MaxReturn -34.7636 __unnamed_task__/MinReturn -137.547 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.9544 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 14:21:27 | [maml_trainer] epoch #484 | Sampling for adapation and meta-testing... 2025-04-13 14:25:24 | [maml_trainer] epoch #484 | Finished meta-testing... 2025-04-13 14:25:24 | [maml_trainer] epoch #484 | Saving snapshot... 2025-04-13 14:25:47 | [maml_trainer] epoch #484 | Saved 2025-04-13 14:25:47 | [maml_trainer] epoch #484 | Time 855991.09 s 2025-04-13 14:25:47 | [maml_trainer] epoch #484 | EpochTime 1709.79 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.7963 Average/AverageReturn -48.7492 Average/Iteration 484 Average/MaxReturn -39.0258 Average/MinReturn -146.362 Average/NumEpisodes 120 Average/StdReturn 11.7636 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69731 GaussianMLPPolicy/KLAfter 0.00378086 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.000120675 GaussianMLPPolicy/LossBefore 2.9405e-09 GaussianMLPPolicy/dLoss 0.000120678 Iteration 484 MetaTest/Average/AverageDiscountedReturn -47.6939 MetaTest/Average/AverageReturn -47.6939 MetaTest/Average/Iteration 484 MetaTest/Average/MaxReturn -40.4039 MetaTest/Average/MinReturn -71.9115 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 7.22812 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -47.6939 MetaTest/__unnamed_task__/AverageReturn -47.6939 MetaTest/__unnamed_task__/Iteration 484 MetaTest/__unnamed_task__/MaxReturn -40.4039 MetaTest/__unnamed_task__/MinReturn -71.9115 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 7.22812 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.328e+07 __unnamed_task__/AverageDiscountedReturn -24.7963 __unnamed_task__/AverageReturn -48.7492 __unnamed_task__/Iteration 484 __unnamed_task__/MaxReturn -39.0258 __unnamed_task__/MinReturn -146.362 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.7636 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 14:49:46 | [maml_trainer] epoch #485 | Sampling for adapation and meta-testing... 2025-04-13 14:53:47 | [maml_trainer] epoch #485 | Finished meta-testing... 2025-04-13 14:53:47 | [maml_trainer] epoch #485 | Saving snapshot... 2025-04-13 14:54:09 | [maml_trainer] epoch #485 | Saved 2025-04-13 14:54:09 | [maml_trainer] epoch #485 | Time 857693.66 s 2025-04-13 14:54:09 | [maml_trainer] epoch #485 | EpochTime 1702.57 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.5941 Average/AverageReturn -48.7878 Average/Iteration 485 Average/MaxReturn -38.1195 Average/MinReturn -137.349 Average/NumEpisodes 120 Average/StdReturn 11.7572 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69818 GaussianMLPPolicy/KLAfter 0.00195634 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000120339 GaussianMLPPolicy/LossBefore -1.20401e-08 GaussianMLPPolicy/dLoss -0.000120351 Iteration 485 MetaTest/Average/AverageDiscountedReturn -46.653 MetaTest/Average/AverageReturn -46.653 MetaTest/Average/Iteration 485 MetaTest/Average/MaxReturn -40.2031 MetaTest/Average/MinReturn -63.4127 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 5.52831 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.653 MetaTest/__unnamed_task__/AverageReturn -46.653 MetaTest/__unnamed_task__/Iteration 485 MetaTest/__unnamed_task__/MaxReturn -40.2031 MetaTest/__unnamed_task__/MinReturn -63.4127 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 5.52831 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3328e+07 __unnamed_task__/AverageDiscountedReturn -24.5941 __unnamed_task__/AverageReturn -48.7878 __unnamed_task__/Iteration 485 __unnamed_task__/MaxReturn -38.1195 __unnamed_task__/MinReturn -137.349 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.7572 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 15:18:34 | [maml_trainer] epoch #486 | Sampling for adapation and meta-testing... 2025-04-13 15:22:40 | [maml_trainer] epoch #486 | Finished meta-testing... 2025-04-13 15:22:40 | [maml_trainer] epoch #486 | Saving snapshot... 2025-04-13 15:23:02 | [maml_trainer] epoch #486 | Saved 2025-04-13 15:23:02 | [maml_trainer] epoch #486 | Time 859425.97 s 2025-04-13 15:23:02 | [maml_trainer] epoch #486 | EpochTime 1732.31 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.2746 Average/AverageReturn -46.9807 Average/Iteration 486 Average/MaxReturn -37.344 Average/MinReturn -156.203 Average/NumEpisodes 120 Average/StdReturn 11.5389 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69829 GaussianMLPPolicy/KLAfter 0.00290714 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -0.00011594 GaussianMLPPolicy/LossBefore 7.54992e-09 GaussianMLPPolicy/dLoss 0.000115947 Iteration 486 MetaTest/Average/AverageDiscountedReturn -46.4597 MetaTest/Average/AverageReturn -46.4597 MetaTest/Average/Iteration 486 MetaTest/Average/MaxReturn -37.8856 MetaTest/Average/MinReturn -69.0323 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 6.29547 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.4597 MetaTest/__unnamed_task__/AverageReturn -46.4597 MetaTest/__unnamed_task__/Iteration 486 MetaTest/__unnamed_task__/MaxReturn -37.8856 MetaTest/__unnamed_task__/MinReturn -69.0323 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 6.29547 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3376e+07 __unnamed_task__/AverageDiscountedReturn -24.2746 __unnamed_task__/AverageReturn -46.9807 __unnamed_task__/Iteration 486 __unnamed_task__/MaxReturn -37.344 __unnamed_task__/MinReturn -156.203 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 11.5389 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 15:47:25 | [maml_trainer] epoch #487 | Sampling for adapation and meta-testing... 2025-04-13 15:51:29 | [maml_trainer] epoch #487 | Finished meta-testing... 2025-04-13 15:51:29 | [maml_trainer] epoch #487 | Saving snapshot... 2025-04-13 15:51:50 | [maml_trainer] epoch #487 | Saved 2025-04-13 15:51:50 | [maml_trainer] epoch #487 | Time 861154.83 s 2025-04-13 15:51:50 | [maml_trainer] epoch #487 | EpochTime 1728.86 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -23.9875 Average/AverageReturn -45.9283 Average/Iteration 487 Average/MaxReturn -33.8996 Average/MinReturn -81.9916 Average/NumEpisodes 120 Average/StdReturn 6.71015 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69844 GaussianMLPPolicy/KLAfter 0.0034377 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -2.99501e-05 GaussianMLPPolicy/LossBefore -1.50998e-08 GaussianMLPPolicy/dLoss 2.9935e-05 Iteration 487 MetaTest/Average/AverageDiscountedReturn -51.6614 MetaTest/Average/AverageReturn -51.6614 MetaTest/Average/Iteration 487 MetaTest/Average/MaxReturn -33.9955 MetaTest/Average/MinReturn -115.358 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 22.5854 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6614 MetaTest/__unnamed_task__/AverageReturn -51.6614 MetaTest/__unnamed_task__/Iteration 487 MetaTest/__unnamed_task__/MaxReturn -33.9955 MetaTest/__unnamed_task__/MinReturn -115.358 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 22.5854 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3424e+07 __unnamed_task__/AverageDiscountedReturn -23.9875 __unnamed_task__/AverageReturn -45.9283 __unnamed_task__/Iteration 487 __unnamed_task__/MaxReturn -33.8996 __unnamed_task__/MinReturn -81.9916 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 6.71015 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 16:16:13 | [maml_trainer] epoch #488 | Sampling for adapation and meta-testing... 2025-04-13 16:20:16 | [maml_trainer] epoch #488 | Finished meta-testing... 2025-04-13 16:20:16 | [maml_trainer] epoch #488 | Saving snapshot... 2025-04-13 16:20:38 | [maml_trainer] epoch #488 | Saved 2025-04-13 16:20:38 | [maml_trainer] epoch #488 | Time 862882.31 s 2025-04-13 16:20:38 | [maml_trainer] epoch #488 | EpochTime 1727.47 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.1356 Average/AverageReturn -48.518 Average/Iteration 488 Average/MaxReturn -34.8822 Average/MinReturn -140.795 Average/NumEpisodes 120 Average/StdReturn 16.9888 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69707 GaussianMLPPolicy/KLAfter 0.00499524 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.50038e-05 GaussianMLPPolicy/LossBefore -1.66893e-09 GaussianMLPPolicy/dLoss 1.50021e-05 Iteration 488 MetaTest/Average/AverageDiscountedReturn -50.2408 MetaTest/Average/AverageReturn -50.2408 MetaTest/Average/Iteration 488 MetaTest/Average/MaxReturn -36.5485 MetaTest/Average/MinReturn -161.904 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 26.5133 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.2408 MetaTest/__unnamed_task__/AverageReturn -50.2408 MetaTest/__unnamed_task__/Iteration 488 MetaTest/__unnamed_task__/MaxReturn -36.5485 MetaTest/__unnamed_task__/MinReturn -161.904 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 26.5133 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3472e+07 __unnamed_task__/AverageDiscountedReturn -24.1356 __unnamed_task__/AverageReturn -48.518 __unnamed_task__/Iteration 488 __unnamed_task__/MaxReturn -34.8822 __unnamed_task__/MinReturn -140.795 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 16.9888 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 16:45:03 | [maml_trainer] epoch #489 | Sampling for adapation and meta-testing... 2025-04-13 16:49:05 | [maml_trainer] epoch #489 | Finished meta-testing... 2025-04-13 16:49:05 | [maml_trainer] epoch #489 | Saving snapshot... 2025-04-13 16:49:26 | [maml_trainer] epoch #489 | Saved 2025-04-13 16:49:26 | [maml_trainer] epoch #489 | Time 864610.71 s 2025-04-13 16:49:26 | [maml_trainer] epoch #489 | EpochTime 1728.40 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -23.6326 Average/AverageReturn -46.9464 Average/Iteration 489 Average/MaxReturn -33.2619 Average/MinReturn -147.941 Average/NumEpisodes 120 Average/StdReturn 16.289 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69689 GaussianMLPPolicy/KLAfter 0.00383406 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -1.32259e-05 GaussianMLPPolicy/LossBefore -5.64257e-09 GaussianMLPPolicy/dLoss 1.32203e-05 Iteration 489 MetaTest/Average/AverageDiscountedReturn -54.3048 MetaTest/Average/AverageReturn -54.3048 MetaTest/Average/Iteration 489 MetaTest/Average/MaxReturn -38.7283 MetaTest/Average/MinReturn -150.558 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.143 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -54.3048 MetaTest/__unnamed_task__/AverageReturn -54.3048 MetaTest/__unnamed_task__/Iteration 489 MetaTest/__unnamed_task__/MaxReturn -38.7283 MetaTest/__unnamed_task__/MinReturn -150.558 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.143 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.352e+07 __unnamed_task__/AverageDiscountedReturn -23.6326 __unnamed_task__/AverageReturn -46.9464 __unnamed_task__/Iteration 489 __unnamed_task__/MaxReturn -33.2619 __unnamed_task__/MinReturn -147.941 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 16.289 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 17:13:54 | [maml_trainer] epoch #490 | Sampling for adapation and meta-testing... 2025-04-13 17:17:59 | [maml_trainer] epoch #490 | Finished meta-testing... 2025-04-13 17:17:59 | [maml_trainer] epoch #490 | Saving snapshot... 2025-04-13 17:18:20 | [maml_trainer] epoch #490 | Saved 2025-04-13 17:18:20 | [maml_trainer] epoch #490 | Time 866344.54 s 2025-04-13 17:18:20 | [maml_trainer] epoch #490 | EpochTime 1733.83 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.4125 Average/AverageReturn -50.6142 Average/Iteration 490 Average/MaxReturn -34.8146 Average/MinReturn -157.415 Average/NumEpisodes 120 Average/StdReturn 23.3176 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69672 GaussianMLPPolicy/KLAfter 0.00390165 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 0.000134698 GaussianMLPPolicy/LossBefore 3.0299e-09 GaussianMLPPolicy/dLoss -0.000134695 Iteration 490 MetaTest/Average/AverageDiscountedReturn -46.7207 MetaTest/Average/AverageReturn -46.7207 MetaTest/Average/Iteration 490 MetaTest/Average/MaxReturn -37.5499 MetaTest/Average/MinReturn -103.029 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 14.0247 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.7207 MetaTest/__unnamed_task__/AverageReturn -46.7207 MetaTest/__unnamed_task__/Iteration 490 MetaTest/__unnamed_task__/MaxReturn -37.5499 MetaTest/__unnamed_task__/MinReturn -103.029 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 14.0247 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3568e+07 __unnamed_task__/AverageDiscountedReturn -24.4125 __unnamed_task__/AverageReturn -50.6142 __unnamed_task__/Iteration 490 __unnamed_task__/MaxReturn -34.8146 __unnamed_task__/MinReturn -157.415 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 23.3176 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 17:43:02 | [maml_trainer] epoch #491 | Sampling for adapation and meta-testing... 2025-04-13 17:47:06 | [maml_trainer] epoch #491 | Finished meta-testing... 2025-04-13 17:47:06 | [maml_trainer] epoch #491 | Saving snapshot... 2025-04-13 17:47:28 | [maml_trainer] epoch #491 | Saved 2025-04-13 17:47:28 | [maml_trainer] epoch #491 | Time 868091.98 s 2025-04-13 17:47:28 | [maml_trainer] epoch #491 | EpochTime 1747.43 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.2827 Average/AverageReturn -51.1435 Average/Iteration 491 Average/MaxReturn -34.2685 Average/MinReturn -164.861 Average/NumEpisodes 120 Average/StdReturn 24.9581 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69699 GaussianMLPPolicy/KLAfter 0.00403642 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -5.16093e-05 GaussianMLPPolicy/LossBefore 2.00669e-09 GaussianMLPPolicy/dLoss 5.16113e-05 Iteration 491 MetaTest/Average/AverageDiscountedReturn -42.1084 MetaTest/Average/AverageReturn -42.1084 MetaTest/Average/Iteration 491 MetaTest/Average/MaxReturn -34.3941 MetaTest/Average/MinReturn -49.0909 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 3.60757 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -42.1084 MetaTest/__unnamed_task__/AverageReturn -42.1084 MetaTest/__unnamed_task__/Iteration 491 MetaTest/__unnamed_task__/MaxReturn -34.3941 MetaTest/__unnamed_task__/MinReturn -49.0909 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 3.60757 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3616e+07 __unnamed_task__/AverageDiscountedReturn -24.2827 __unnamed_task__/AverageReturn -51.1435 __unnamed_task__/Iteration 491 __unnamed_task__/MaxReturn -34.2685 __unnamed_task__/MinReturn -164.861 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 24.9581 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 18:12:05 | [maml_trainer] epoch #492 | Sampling for adapation and meta-testing... 2025-04-13 18:16:10 | [maml_trainer] epoch #492 | Finished meta-testing... 2025-04-13 18:16:10 | [maml_trainer] epoch #492 | Saving snapshot... 2025-04-13 18:16:33 | [maml_trainer] epoch #492 | Saved 2025-04-13 18:16:33 | [maml_trainer] epoch #492 | Time 869837.02 s 2025-04-13 18:16:33 | [maml_trainer] epoch #492 | EpochTime 1745.04 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.441 Average/AverageReturn -51.7723 Average/Iteration 492 Average/MaxReturn 19.4298 Average/MinReturn -167.739 Average/NumEpisodes 120 Average/StdReturn 26.3526 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69664 GaussianMLPPolicy/KLAfter 0.00370771 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 2.34492e-05 GaussianMLPPolicy/LossBefore 3.88424e-09 GaussianMLPPolicy/dLoss -2.34453e-05 Iteration 492 MetaTest/Average/AverageDiscountedReturn -58.2623 MetaTest/Average/AverageReturn -58.2623 MetaTest/Average/Iteration 492 MetaTest/Average/MaxReturn -37.2367 MetaTest/Average/MinReturn -138.754 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 28.3935 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -58.2623 MetaTest/__unnamed_task__/AverageReturn -58.2623 MetaTest/__unnamed_task__/Iteration 492 MetaTest/__unnamed_task__/MaxReturn -37.2367 MetaTest/__unnamed_task__/MinReturn -138.754 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 28.3935 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3664e+07 __unnamed_task__/AverageDiscountedReturn -24.441 __unnamed_task__/AverageReturn -51.7723 __unnamed_task__/Iteration 492 __unnamed_task__/MaxReturn 19.4298 __unnamed_task__/MinReturn -167.739 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 26.3526 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 18:41:17 | [maml_trainer] epoch #493 | Sampling for adapation and meta-testing... 2025-04-13 18:45:20 | [maml_trainer] epoch #493 | Finished meta-testing... 2025-04-13 18:45:20 | [maml_trainer] epoch #493 | Saving snapshot... 2025-04-13 18:45:42 | [maml_trainer] epoch #493 | Saved 2025-04-13 18:45:42 | [maml_trainer] epoch #493 | Time 871586.62 s 2025-04-13 18:45:42 | [maml_trainer] epoch #493 | EpochTime 1749.59 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.2471 Average/AverageReturn -55.5879 Average/Iteration 493 Average/MaxReturn -35.3932 Average/MinReturn -157.848 Average/NumEpisodes 120 Average/StdReturn 30.3456 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69632 GaussianMLPPolicy/KLAfter 0.00292 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.02766e-05 GaussianMLPPolicy/LossBefore -3.29812e-09 GaussianMLPPolicy/dLoss 4.02733e-05 Iteration 493 MetaTest/Average/AverageDiscountedReturn -58.3316 MetaTest/Average/AverageReturn -58.3316 MetaTest/Average/Iteration 493 MetaTest/Average/MaxReturn -38.2442 MetaTest/Average/MinReturn -127.134 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 25.1011 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -58.3316 MetaTest/__unnamed_task__/AverageReturn -58.3316 MetaTest/__unnamed_task__/Iteration 493 MetaTest/__unnamed_task__/MaxReturn -38.2442 MetaTest/__unnamed_task__/MinReturn -127.134 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 25.1011 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3712e+07 __unnamed_task__/AverageDiscountedReturn -25.2471 __unnamed_task__/AverageReturn -55.5879 __unnamed_task__/Iteration 493 __unnamed_task__/MaxReturn -35.3932 __unnamed_task__/MinReturn -157.848 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 30.3456 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 19:10:14 | [maml_trainer] epoch #494 | Sampling for adapation and meta-testing... 2025-04-13 19:14:22 | [maml_trainer] epoch #494 | Finished meta-testing... 2025-04-13 19:14:22 | [maml_trainer] epoch #494 | Saving snapshot... 2025-04-13 19:14:44 | [maml_trainer] epoch #494 | Saved 2025-04-13 19:14:44 | [maml_trainer] epoch #494 | Time 873328.93 s 2025-04-13 19:14:44 | [maml_trainer] epoch #494 | EpochTime 1742.31 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -25.4783 Average/AverageReturn -56.9623 Average/Iteration 494 Average/MaxReturn -35.6629 Average/MinReturn -174.382 Average/NumEpisodes 120 Average/StdReturn 33.1153 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.6953 GaussianMLPPolicy/KLAfter 0.00196831 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 1.17921e-06 GaussianMLPPolicy/LossBefore -9.73542e-10 GaussianMLPPolicy/dLoss -1.18018e-06 Iteration 494 MetaTest/Average/AverageDiscountedReturn -53.9928 MetaTest/Average/AverageReturn -53.9928 MetaTest/Average/Iteration 494 MetaTest/Average/MaxReturn -36.2099 MetaTest/Average/MinReturn -152.379 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 31.3183 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -53.9928 MetaTest/__unnamed_task__/AverageReturn -53.9928 MetaTest/__unnamed_task__/Iteration 494 MetaTest/__unnamed_task__/MaxReturn -36.2099 MetaTest/__unnamed_task__/MinReturn -152.379 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 31.3183 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.376e+07 __unnamed_task__/AverageDiscountedReturn -25.4783 __unnamed_task__/AverageReturn -56.9623 __unnamed_task__/Iteration 494 __unnamed_task__/MaxReturn -35.6629 __unnamed_task__/MinReturn -174.382 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 33.1153 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 19:38:52 | [maml_trainer] epoch #495 | Sampling for adapation and meta-testing... 2025-04-13 19:42:53 | [maml_trainer] epoch #495 | Finished meta-testing... 2025-04-13 19:42:53 | [maml_trainer] epoch #495 | Saving snapshot... 2025-04-13 19:43:15 | [maml_trainer] epoch #495 | Saved 2025-04-13 19:43:15 | [maml_trainer] epoch #495 | Time 875039.40 s 2025-04-13 19:43:15 | [maml_trainer] epoch #495 | EpochTime 1710.47 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.5992 Average/AverageReturn -50.8746 Average/Iteration 495 Average/MaxReturn -35.1535 Average/MinReturn -157.302 Average/NumEpisodes 120 Average/StdReturn 23.2235 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69339 GaussianMLPPolicy/KLAfter 0.00161742 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -4.7699e-05 GaussianMLPPolicy/LossBefore 4.29153e-09 GaussianMLPPolicy/dLoss 4.77032e-05 Iteration 495 MetaTest/Average/AverageDiscountedReturn -49.2652 MetaTest/Average/AverageReturn -49.2652 MetaTest/Average/Iteration 495 MetaTest/Average/MaxReturn -36.3411 MetaTest/Average/MinReturn -133.458 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 20.1406 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -49.2652 MetaTest/__unnamed_task__/AverageReturn -49.2652 MetaTest/__unnamed_task__/Iteration 495 MetaTest/__unnamed_task__/MaxReturn -36.3411 MetaTest/__unnamed_task__/MinReturn -133.458 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 20.1406 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3808e+07 __unnamed_task__/AverageDiscountedReturn -24.5992 __unnamed_task__/AverageReturn -50.8746 __unnamed_task__/Iteration 495 __unnamed_task__/MaxReturn -35.1535 __unnamed_task__/MinReturn -157.302 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 23.2235 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 20:07:27 | [maml_trainer] epoch #496 | Sampling for adapation and meta-testing... 2025-04-13 20:11:28 | [maml_trainer] epoch #496 | Finished meta-testing... 2025-04-13 20:11:28 | [maml_trainer] epoch #496 | Saving snapshot... 2025-04-13 20:11:51 | [maml_trainer] epoch #496 | Saved 2025-04-13 20:11:51 | [maml_trainer] epoch #496 | Time 876755.10 s 2025-04-13 20:11:51 | [maml_trainer] epoch #496 | EpochTime 1715.69 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -23.8107 Average/AverageReturn -47.8101 Average/Iteration 496 Average/MaxReturn -28.4616 Average/MinReturn -146.148 Average/NumEpisodes 120 Average/StdReturn 20.6118 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.69107 GaussianMLPPolicy/KLAfter 0.0016981 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -3.73617e-06 GaussianMLPPolicy/LossBefore 3.67562e-09 GaussianMLPPolicy/dLoss 3.73984e-06 Iteration 496 MetaTest/Average/AverageDiscountedReturn -45.8328 MetaTest/Average/AverageReturn -45.8328 MetaTest/Average/Iteration 496 MetaTest/Average/MaxReturn -35.4434 MetaTest/Average/MinReturn -113.537 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 16.0447 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.8328 MetaTest/__unnamed_task__/AverageReturn -45.8328 MetaTest/__unnamed_task__/Iteration 496 MetaTest/__unnamed_task__/MaxReturn -35.4434 MetaTest/__unnamed_task__/MinReturn -113.537 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 16.0447 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3856e+07 __unnamed_task__/AverageDiscountedReturn -23.8107 __unnamed_task__/AverageReturn -47.8101 __unnamed_task__/Iteration 496 __unnamed_task__/MaxReturn -28.4616 __unnamed_task__/MinReturn -146.148 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 20.6118 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 20:42:46 | [maml_trainer] epoch #497 | Sampling for adapation and meta-testing... 2025-04-13 20:48:37 | [maml_trainer] epoch #497 | Finished meta-testing... 2025-04-13 20:48:37 | [maml_trainer] epoch #497 | Saving snapshot... 2025-04-13 20:49:11 | [maml_trainer] epoch #497 | Saved 2025-04-13 20:49:11 | [maml_trainer] epoch #497 | Time 878995.55 s 2025-04-13 20:49:11 | [maml_trainer] epoch #497 | EpochTime 2240.44 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.8921 Average/AverageReturn -51.2775 Average/Iteration 497 Average/MaxReturn -33.9596 Average/MinReturn -160.212 Average/NumEpisodes 120 Average/StdReturn 26.147 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68863 GaussianMLPPolicy/KLAfter 0.00136542 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -6.95573e-05 GaussianMLPPolicy/LossBefore -1.19209e-09 GaussianMLPPolicy/dLoss 6.95561e-05 Iteration 497 MetaTest/Average/AverageDiscountedReturn -55.3159 MetaTest/Average/AverageReturn -55.3159 MetaTest/Average/Iteration 497 MetaTest/Average/MaxReturn -35.7941 MetaTest/Average/MinReturn -145.094 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 30.6329 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -55.3159 MetaTest/__unnamed_task__/AverageReturn -55.3159 MetaTest/__unnamed_task__/Iteration 497 MetaTest/__unnamed_task__/MaxReturn -35.7941 MetaTest/__unnamed_task__/MinReturn -145.094 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 30.6329 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3904e+07 __unnamed_task__/AverageDiscountedReturn -24.8921 __unnamed_task__/AverageReturn -51.2775 __unnamed_task__/Iteration 497 __unnamed_task__/MaxReturn -33.9596 __unnamed_task__/MinReturn -160.212 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 26.147 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 21:24:18 | [maml_trainer] epoch #498 | Sampling for adapation and meta-testing... 2025-04-13 21:30:11 | [maml_trainer] epoch #498 | Finished meta-testing... 2025-04-13 21:30:11 | [maml_trainer] epoch #498 | Saving snapshot... 2025-04-13 21:30:44 | [maml_trainer] epoch #498 | Saved 2025-04-13 21:30:44 | [maml_trainer] epoch #498 | Time 881488.15 s 2025-04-13 21:30:44 | [maml_trainer] epoch #498 | EpochTime 2492.60 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -24.0413 Average/AverageReturn -49.7993 Average/Iteration 498 Average/MaxReturn -33.9479 Average/MinReturn -175.834 Average/NumEpisodes 120 Average/StdReturn 26.3871 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68673 GaussianMLPPolicy/KLAfter 0.00245724 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter -8.12384e-05 GaussianMLPPolicy/LossBefore -5.46376e-09 GaussianMLPPolicy/dLoss 8.12329e-05 Iteration 498 MetaTest/Average/AverageDiscountedReturn -50.282 MetaTest/Average/AverageReturn -50.282 MetaTest/Average/Iteration 498 MetaTest/Average/MaxReturn -37.1169 MetaTest/Average/MinReturn -117.78 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 17.37 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.282 MetaTest/__unnamed_task__/AverageReturn -50.282 MetaTest/__unnamed_task__/Iteration 498 MetaTest/__unnamed_task__/MaxReturn -37.1169 MetaTest/__unnamed_task__/MinReturn -117.78 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 17.37 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.3952e+07 __unnamed_task__/AverageDiscountedReturn -24.0413 __unnamed_task__/AverageReturn -49.7993 __unnamed_task__/Iteration 498 __unnamed_task__/MaxReturn -33.9479 __unnamed_task__/MinReturn -175.834 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 26.3871 __unnamed_task__/TerminationRate 0 ------------------------------------------------- -------------- 2025-04-13 22:05:50 | [maml_trainer] epoch #499 | Sampling for adapation and meta-testing... 2025-04-13 22:11:42 | [maml_trainer] epoch #499 | Finished meta-testing... 2025-04-13 22:11:42 | [maml_trainer] epoch #499 | Saving snapshot... 2025-04-13 22:12:16 | [maml_trainer] epoch #499 | Saved 2025-04-13 22:12:16 | [maml_trainer] epoch #499 | Time 883980.16 s 2025-04-13 22:12:16 | [maml_trainer] epoch #499 | EpochTime 2492.01 s ------------------------------------------------- -------------- Average/AverageDiscountedReturn -23.4739 Average/AverageReturn -45.2006 Average/Iteration 499 Average/MaxReturn -35.0396 Average/MinReturn -135.32 Average/NumEpisodes 120 Average/StdReturn 12.958 Average/TerminationRate 0 GaussianMLPPolicy/Entropy 9.68443 GaussianMLPPolicy/KLAfter 0.00337118 GaussianMLPPolicy/KLBefore 0 GaussianMLPPolicy/LossAfter 8.81191e-05 GaussianMLPPolicy/LossBefore -3.13918e-09 GaussianMLPPolicy/dLoss -8.81223e-05 Iteration 499 MetaTest/Average/AverageDiscountedReturn -50.2644 MetaTest/Average/AverageReturn -50.2644 MetaTest/Average/Iteration 499 MetaTest/Average/MaxReturn -36.6546 MetaTest/Average/MinReturn -150.917 MetaTest/Average/NumEpisodes 20 MetaTest/Average/StdReturn 23.6726 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.2644 MetaTest/__unnamed_task__/AverageReturn -50.2644 MetaTest/__unnamed_task__/Iteration 499 MetaTest/__unnamed_task__/MaxReturn -36.6546 MetaTest/__unnamed_task__/MinReturn -150.917 MetaTest/__unnamed_task__/NumEpisodes 20 MetaTest/__unnamed_task__/StdReturn 23.6726 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 2.4e+07 __unnamed_task__/AverageDiscountedReturn -23.4739 __unnamed_task__/AverageReturn -45.2006 __unnamed_task__/Iteration 499 __unnamed_task__/MaxReturn -35.0396 __unnamed_task__/MinReturn -135.32 __unnamed_task__/NumEpisodes 120 __unnamed_task__/StdReturn 12.958 __unnamed_task__/TerminationRate 0 ------------------------------------------------- --------------