2025-04-02 13:28:38 | [pearl_trainer] Logging to /home/h2khalil/MetaRL-Assistive-Robotics/data/local/experiment/pearl_trainer_2 2025-04-02 13:28:44 | [pearl_trainer] Obtaining samples... 2025-04-02 13:32:08 | [pearl_trainer] epoch #0 | Training... 2025-04-02 13:33:24 | [pearl_trainer] epoch #0 | Evaluating... 2025-04-02 13:33:24 | [pearl_trainer] epoch #0 | Sampling for adapation and meta-testing... 2025-04-02 13:34:04 | [pearl_trainer] epoch #0 | Finished meta-testing... 2025-04-02 13:34:04 | [pearl_trainer] epoch #0 | Saving snapshot... 2025-04-02 13:34:05 | [pearl_trainer] epoch #0 | Saved 2025-04-02 13:34:05 | [pearl_trainer] epoch #0 | Time 321.38 s 2025-04-02 13:34:05 | [pearl_trainer] epoch #0 | EpochTime 321.38 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -93.2202 MetaTest/Average/AverageReturn -93.2202 MetaTest/Average/Iteration 0 MetaTest/Average/MaxReturn -90.897 MetaTest/Average/MinReturn -95.2562 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.79117 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.2202 MetaTest/__unnamed_task__/AverageReturn -93.2202 MetaTest/__unnamed_task__/Iteration 0 MetaTest/__unnamed_task__/MaxReturn -90.897 MetaTest/__unnamed_task__/MinReturn -95.2562 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.79117 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 16600 ------------------------------------------------- ----------- 2025-04-02 13:34:25 | [pearl_trainer] epoch #1 | Training... 2025-04-02 13:35:42 | [pearl_trainer] epoch #1 | Evaluating... 2025-04-02 13:35:42 | [pearl_trainer] epoch #1 | Sampling for adapation and meta-testing... 2025-04-02 13:36:21 | [pearl_trainer] epoch #1 | Finished meta-testing... 2025-04-02 13:36:21 | [pearl_trainer] epoch #1 | Saving snapshot... 2025-04-02 13:36:22 | [pearl_trainer] epoch #1 | Saved 2025-04-02 13:36:22 | [pearl_trainer] epoch #1 | Time 458.66 s 2025-04-02 13:36:22 | [pearl_trainer] epoch #1 | EpochTime 137.28 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -91.0379 MetaTest/Average/AverageReturn -91.0379 MetaTest/Average/Iteration 1 MetaTest/Average/MaxReturn -89.1646 MetaTest/Average/MinReturn -93.5253 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.83246 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.0379 MetaTest/__unnamed_task__/AverageReturn -91.0379 MetaTest/__unnamed_task__/Iteration 1 MetaTest/__unnamed_task__/MaxReturn -89.1646 MetaTest/__unnamed_task__/MinReturn -93.5253 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.83246 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 18200 ------------------------------------------------- ----------- 2025-04-02 13:36:43 | [pearl_trainer] epoch #2 | Training... 2025-04-02 13:38:01 | [pearl_trainer] epoch #2 | Evaluating... 2025-04-02 13:38:01 | [pearl_trainer] epoch #2 | Sampling for adapation and meta-testing... 2025-04-02 13:38:48 | [pearl_trainer] epoch #2 | Finished meta-testing... 2025-04-02 13:38:48 | [pearl_trainer] epoch #2 | Saving snapshot... 2025-04-02 13:38:49 | [pearl_trainer] epoch #2 | Saved 2025-04-02 13:38:49 | [pearl_trainer] epoch #2 | Time 605.35 s 2025-04-02 13:38:49 | [pearl_trainer] epoch #2 | EpochTime 146.69 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -85.5846 MetaTest/Average/AverageReturn -85.5846 MetaTest/Average/Iteration 2 MetaTest/Average/MaxReturn -80.9422 MetaTest/Average/MinReturn -88.0083 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.28377 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -85.5846 MetaTest/__unnamed_task__/AverageReturn -85.5846 MetaTest/__unnamed_task__/Iteration 2 MetaTest/__unnamed_task__/MaxReturn -80.9422 MetaTest/__unnamed_task__/MinReturn -88.0083 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.28377 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 19800 ------------------------------------------------- ----------- 2025-04-02 13:39:09 | [pearl_trainer] epoch #3 | Training... 2025-04-02 13:40:26 | [pearl_trainer] epoch #3 | Evaluating... 2025-04-02 13:40:26 | [pearl_trainer] epoch #3 | Sampling for adapation and meta-testing... 2025-04-02 13:41:08 | [pearl_trainer] epoch #3 | Finished meta-testing... 2025-04-02 13:41:08 | [pearl_trainer] epoch #3 | Saving snapshot... 2025-04-02 13:41:09 | [pearl_trainer] epoch #3 | Saved 2025-04-02 13:41:09 | [pearl_trainer] epoch #3 | Time 745.58 s 2025-04-02 13:41:09 | [pearl_trainer] epoch #3 | EpochTime 140.23 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -88.7106 MetaTest/Average/AverageReturn -88.7106 MetaTest/Average/Iteration 3 MetaTest/Average/MaxReturn -85.8728 MetaTest/Average/MinReturn -94.2594 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.9239 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.7106 MetaTest/__unnamed_task__/AverageReturn -88.7106 MetaTest/__unnamed_task__/Iteration 3 MetaTest/__unnamed_task__/MaxReturn -85.8728 MetaTest/__unnamed_task__/MinReturn -94.2594 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.9239 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 21400 ------------------------------------------------- ---------- 2025-04-02 13:41:30 | [pearl_trainer] epoch #4 | Training... 2025-04-02 13:42:44 | [pearl_trainer] epoch #4 | Evaluating... 2025-04-02 13:42:44 | [pearl_trainer] epoch #4 | Sampling for adapation and meta-testing... 2025-04-02 13:43:26 | [pearl_trainer] epoch #4 | Finished meta-testing... 2025-04-02 13:43:26 | [pearl_trainer] epoch #4 | Saving snapshot... 2025-04-02 13:43:28 | [pearl_trainer] epoch #4 | Saved 2025-04-02 13:43:28 | [pearl_trainer] epoch #4 | Time 883.81 s 2025-04-02 13:43:28 | [pearl_trainer] epoch #4 | EpochTime 138.22 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -98.0442 MetaTest/Average/AverageReturn -98.0442 MetaTest/Average/Iteration 4 MetaTest/Average/MaxReturn -81.8104 MetaTest/Average/MinReturn -106.224 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.4791 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.0442 MetaTest/__unnamed_task__/AverageReturn -98.0442 MetaTest/__unnamed_task__/Iteration 4 MetaTest/__unnamed_task__/MaxReturn -81.8104 MetaTest/__unnamed_task__/MinReturn -106.224 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.4791 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 23000 ------------------------------------------------- ---------- 2025-04-02 13:43:48 | [pearl_trainer] epoch #5 | Training... 2025-04-02 13:45:04 | [pearl_trainer] epoch #5 | Evaluating... 2025-04-02 13:45:04 | [pearl_trainer] epoch #5 | Sampling for adapation and meta-testing... 2025-04-02 13:45:47 | [pearl_trainer] epoch #5 | Finished meta-testing... 2025-04-02 13:45:47 | [pearl_trainer] epoch #5 | Saving snapshot... 2025-04-02 13:45:48 | [pearl_trainer] epoch #5 | Saved 2025-04-02 13:45:48 | [pearl_trainer] epoch #5 | Time 1024.29 s 2025-04-02 13:45:48 | [pearl_trainer] epoch #5 | EpochTime 140.48 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -118.239 MetaTest/Average/AverageReturn -118.239 MetaTest/Average/Iteration 5 MetaTest/Average/MaxReturn -111.603 MetaTest/Average/MinReturn -128.376 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.28137 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -118.239 MetaTest/__unnamed_task__/AverageReturn -118.239 MetaTest/__unnamed_task__/Iteration 5 MetaTest/__unnamed_task__/MaxReturn -111.603 MetaTest/__unnamed_task__/MinReturn -128.376 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.28137 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 24600 ------------------------------------------------- ----------- 2025-04-02 13:46:09 | [pearl_trainer] epoch #6 | Training... 2025-04-02 13:47:28 | [pearl_trainer] epoch #6 | Evaluating... 2025-04-02 13:47:28 | [pearl_trainer] epoch #6 | Sampling for adapation and meta-testing... 2025-04-02 13:48:09 | [pearl_trainer] epoch #6 | Finished meta-testing... 2025-04-02 13:48:09 | [pearl_trainer] epoch #6 | Saving snapshot... 2025-04-02 13:48:10 | [pearl_trainer] epoch #6 | Saved 2025-04-02 13:48:10 | [pearl_trainer] epoch #6 | Time 1166.24 s 2025-04-02 13:48:10 | [pearl_trainer] epoch #6 | EpochTime 141.95 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -110.664 MetaTest/Average/AverageReturn -110.664 MetaTest/Average/Iteration 6 MetaTest/Average/MaxReturn -101 MetaTest/Average/MinReturn -124.591 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.0918 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -110.664 MetaTest/__unnamed_task__/AverageReturn -110.664 MetaTest/__unnamed_task__/Iteration 6 MetaTest/__unnamed_task__/MaxReturn -101 MetaTest/__unnamed_task__/MinReturn -124.591 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.0918 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 26200 ------------------------------------------------- ---------- 2025-04-02 13:48:31 | [pearl_trainer] epoch #7 | Training... 2025-04-02 13:49:47 | [pearl_trainer] epoch #7 | Evaluating... 2025-04-02 13:49:47 | [pearl_trainer] epoch #7 | Sampling for adapation and meta-testing... 2025-04-02 13:50:33 | [pearl_trainer] epoch #7 | Finished meta-testing... 2025-04-02 13:50:33 | [pearl_trainer] epoch #7 | Saving snapshot... 2025-04-02 13:50:35 | [pearl_trainer] epoch #7 | Saved 2025-04-02 13:50:35 | [pearl_trainer] epoch #7 | Time 1310.73 s 2025-04-02 13:50:35 | [pearl_trainer] epoch #7 | EpochTime 144.49 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -122.382 MetaTest/Average/AverageReturn -122.382 MetaTest/Average/Iteration 7 MetaTest/Average/MaxReturn -104.404 MetaTest/Average/MinReturn -133.199 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.7997 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -122.382 MetaTest/__unnamed_task__/AverageReturn -122.382 MetaTest/__unnamed_task__/Iteration 7 MetaTest/__unnamed_task__/MaxReturn -104.404 MetaTest/__unnamed_task__/MinReturn -133.199 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.7997 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 27800 ------------------------------------------------- ---------- 2025-04-02 13:50:56 | [pearl_trainer] epoch #8 | Training... 2025-04-02 13:52:16 | [pearl_trainer] epoch #8 | Evaluating... 2025-04-02 13:52:16 | [pearl_trainer] epoch #8 | Sampling for adapation and meta-testing... 2025-04-02 13:52:58 | [pearl_trainer] epoch #8 | Finished meta-testing... 2025-04-02 13:52:58 | [pearl_trainer] epoch #8 | Saving snapshot... 2025-04-02 13:52:59 | [pearl_trainer] epoch #8 | Saved 2025-04-02 13:52:59 | [pearl_trainer] epoch #8 | Time 1454.87 s 2025-04-02 13:52:59 | [pearl_trainer] epoch #8 | EpochTime 144.13 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -130.881 MetaTest/Average/AverageReturn -130.881 MetaTest/Average/Iteration 8 MetaTest/Average/MaxReturn -122.591 MetaTest/Average/MinReturn -140.938 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.5938 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -130.881 MetaTest/__unnamed_task__/AverageReturn -130.881 MetaTest/__unnamed_task__/Iteration 8 MetaTest/__unnamed_task__/MaxReturn -122.591 MetaTest/__unnamed_task__/MinReturn -140.938 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.5938 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 29400 ------------------------------------------------- ---------- 2025-04-02 13:53:19 | [pearl_trainer] epoch #9 | Training... 2025-04-02 13:54:54 | [pearl_trainer] epoch #9 | Evaluating... 2025-04-02 13:54:54 | [pearl_trainer] epoch #9 | Sampling for adapation and meta-testing... 2025-04-02 13:55:36 | [pearl_trainer] epoch #9 | Finished meta-testing... 2025-04-02 13:55:36 | [pearl_trainer] epoch #9 | Saving snapshot... 2025-04-02 13:55:37 | [pearl_trainer] epoch #9 | Saved 2025-04-02 13:55:37 | [pearl_trainer] epoch #9 | Time 1612.82 s 2025-04-02 13:55:37 | [pearl_trainer] epoch #9 | EpochTime 157.95 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -131.106 MetaTest/Average/AverageReturn -131.106 MetaTest/Average/Iteration 9 MetaTest/Average/MaxReturn -109.096 MetaTest/Average/MinReturn -144.228 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 15.6589 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -131.106 MetaTest/__unnamed_task__/AverageReturn -131.106 MetaTest/__unnamed_task__/Iteration 9 MetaTest/__unnamed_task__/MaxReturn -109.096 MetaTest/__unnamed_task__/MinReturn -144.228 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 15.6589 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 31000 ------------------------------------------------- ---------- 2025-04-02 13:55:56 | [pearl_trainer] epoch #10 | Training... 2025-04-02 13:57:25 | [pearl_trainer] epoch #10 | Evaluating... 2025-04-02 13:57:25 | [pearl_trainer] epoch #10 | Sampling for adapation and meta-testing... 2025-04-02 13:58:13 | [pearl_trainer] epoch #10 | Finished meta-testing... 2025-04-02 13:58:13 | [pearl_trainer] epoch #10 | Saving snapshot... 2025-04-02 13:58:14 | [pearl_trainer] epoch #10 | Saved 2025-04-02 13:58:14 | [pearl_trainer] epoch #10 | Time 1769.83 s 2025-04-02 13:58:14 | [pearl_trainer] epoch #10 | EpochTime 157.01 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -121.913 MetaTest/Average/AverageReturn -121.913 MetaTest/Average/Iteration 10 MetaTest/Average/MaxReturn -119.066 MetaTest/Average/MinReturn -126.027 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.97954 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -121.913 MetaTest/__unnamed_task__/AverageReturn -121.913 MetaTest/__unnamed_task__/Iteration 10 MetaTest/__unnamed_task__/MaxReturn -119.066 MetaTest/__unnamed_task__/MinReturn -126.027 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.97954 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 32600 ------------------------------------------------- ----------- 2025-04-02 13:58:34 | [pearl_trainer] epoch #11 | Training... 2025-04-02 13:59:59 | [pearl_trainer] epoch #11 | Evaluating... 2025-04-02 13:59:59 | [pearl_trainer] epoch #11 | Sampling for adapation and meta-testing... 2025-04-02 14:00:42 | [pearl_trainer] epoch #11 | Finished meta-testing... 2025-04-02 14:00:42 | [pearl_trainer] epoch #11 | Saving snapshot... 2025-04-02 14:00:43 | [pearl_trainer] epoch #11 | Saved 2025-04-02 14:00:43 | [pearl_trainer] epoch #11 | Time 1919.38 s 2025-04-02 14:00:43 | [pearl_trainer] epoch #11 | EpochTime 149.55 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -121.629 MetaTest/Average/AverageReturn -121.629 MetaTest/Average/Iteration 11 MetaTest/Average/MaxReturn -113.509 MetaTest/Average/MinReturn -127.65 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.96053 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -121.629 MetaTest/__unnamed_task__/AverageReturn -121.629 MetaTest/__unnamed_task__/Iteration 11 MetaTest/__unnamed_task__/MaxReturn -113.509 MetaTest/__unnamed_task__/MinReturn -127.65 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.96053 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 34200 ------------------------------------------------- ----------- 2025-04-02 14:01:05 | [pearl_trainer] epoch #12 | Training... 2025-04-02 14:02:34 | [pearl_trainer] epoch #12 | Evaluating... 2025-04-02 14:02:34 | [pearl_trainer] epoch #12 | Sampling for adapation and meta-testing... 2025-04-02 14:03:18 | [pearl_trainer] epoch #12 | Finished meta-testing... 2025-04-02 14:03:18 | [pearl_trainer] epoch #12 | Saving snapshot... 2025-04-02 14:03:20 | [pearl_trainer] epoch #12 | Saved 2025-04-02 14:03:20 | [pearl_trainer] epoch #12 | Time 2075.77 s 2025-04-02 14:03:20 | [pearl_trainer] epoch #12 | EpochTime 156.39 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -112.298 MetaTest/Average/AverageReturn -112.298 MetaTest/Average/Iteration 12 MetaTest/Average/MaxReturn -104.8 MetaTest/Average/MinReturn -116.584 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.32021 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -112.298 MetaTest/__unnamed_task__/AverageReturn -112.298 MetaTest/__unnamed_task__/Iteration 12 MetaTest/__unnamed_task__/MaxReturn -104.8 MetaTest/__unnamed_task__/MinReturn -116.584 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.32021 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 35800 ------------------------------------------------- ----------- 2025-04-02 14:03:41 | [pearl_trainer] epoch #13 | Training... 2025-04-02 14:05:04 | [pearl_trainer] epoch #13 | Evaluating... 2025-04-02 14:05:04 | [pearl_trainer] epoch #13 | Sampling for adapation and meta-testing... 2025-04-02 14:05:54 | [pearl_trainer] epoch #13 | Finished meta-testing... 2025-04-02 14:05:54 | [pearl_trainer] epoch #13 | Saving snapshot... 2025-04-02 14:05:55 | [pearl_trainer] epoch #13 | Saved 2025-04-02 14:05:55 | [pearl_trainer] epoch #13 | Time 2231.14 s 2025-04-02 14:05:55 | [pearl_trainer] epoch #13 | EpochTime 155.36 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -124.035 MetaTest/Average/AverageReturn -124.035 MetaTest/Average/Iteration 13 MetaTest/Average/MaxReturn -117.55 MetaTest/Average/MinReturn -135.691 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.25936 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -124.035 MetaTest/__unnamed_task__/AverageReturn -124.035 MetaTest/__unnamed_task__/Iteration 13 MetaTest/__unnamed_task__/MaxReturn -117.55 MetaTest/__unnamed_task__/MinReturn -135.691 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.25936 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 37400 ------------------------------------------------- ----------- 2025-04-02 14:06:17 | [pearl_trainer] epoch #14 | Training... 2025-04-02 14:07:36 | [pearl_trainer] epoch #14 | Evaluating... 2025-04-02 14:07:36 | [pearl_trainer] epoch #14 | Sampling for adapation and meta-testing... 2025-04-02 14:08:33 | [pearl_trainer] epoch #14 | Finished meta-testing... 2025-04-02 14:08:33 | [pearl_trainer] epoch #14 | Saving snapshot... 2025-04-02 14:08:34 | [pearl_trainer] epoch #14 | Saved 2025-04-02 14:08:34 | [pearl_trainer] epoch #14 | Time 2390.63 s 2025-04-02 14:08:34 | [pearl_trainer] epoch #14 | EpochTime 159.50 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -135.634 MetaTest/Average/AverageReturn -135.634 MetaTest/Average/Iteration 14 MetaTest/Average/MaxReturn -129.741 MetaTest/Average/MinReturn -144.951 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.66456 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -135.634 MetaTest/__unnamed_task__/AverageReturn -135.634 MetaTest/__unnamed_task__/Iteration 14 MetaTest/__unnamed_task__/MaxReturn -129.741 MetaTest/__unnamed_task__/MinReturn -144.951 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.66456 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 39000 ------------------------------------------------- ----------- 2025-04-02 14:09:05 | [pearl_trainer] epoch #15 | Training... 2025-04-02 14:10:30 | [pearl_trainer] epoch #15 | Evaluating... 2025-04-02 14:10:30 | [pearl_trainer] epoch #15 | Sampling for adapation and meta-testing... 2025-04-02 14:11:13 | [pearl_trainer] epoch #15 | Finished meta-testing... 2025-04-02 14:11:13 | [pearl_trainer] epoch #15 | Saving snapshot... 2025-04-02 14:11:14 | [pearl_trainer] epoch #15 | Saved 2025-04-02 14:11:14 | [pearl_trainer] epoch #15 | Time 2550.24 s 2025-04-02 14:11:14 | [pearl_trainer] epoch #15 | EpochTime 159.61 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -108.754 MetaTest/Average/AverageReturn -108.754 MetaTest/Average/Iteration 15 MetaTest/Average/MaxReturn -94.3384 MetaTest/Average/MinReturn -122.594 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.5424 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -108.754 MetaTest/__unnamed_task__/AverageReturn -108.754 MetaTest/__unnamed_task__/Iteration 15 MetaTest/__unnamed_task__/MaxReturn -94.3384 MetaTest/__unnamed_task__/MinReturn -122.594 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.5424 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 40600 ------------------------------------------------- ---------- 2025-04-02 14:11:37 | [pearl_trainer] epoch #16 | Training... 2025-04-02 14:13:11 | [pearl_trainer] epoch #16 | Evaluating... 2025-04-02 14:13:11 | [pearl_trainer] epoch #16 | Sampling for adapation and meta-testing... 2025-04-02 14:13:55 | [pearl_trainer] epoch #16 | Finished meta-testing... 2025-04-02 14:13:55 | [pearl_trainer] epoch #16 | Saving snapshot... 2025-04-02 14:13:56 | [pearl_trainer] epoch #16 | Saved 2025-04-02 14:13:56 | [pearl_trainer] epoch #16 | Time 2712.02 s 2025-04-02 14:13:56 | [pearl_trainer] epoch #16 | EpochTime 161.77 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -113.275 MetaTest/Average/AverageReturn -113.275 MetaTest/Average/Iteration 16 MetaTest/Average/MaxReturn -99.599 MetaTest/Average/MinReturn -131.935 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.6634 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -113.275 MetaTest/__unnamed_task__/AverageReturn -113.275 MetaTest/__unnamed_task__/Iteration 16 MetaTest/__unnamed_task__/MaxReturn -99.599 MetaTest/__unnamed_task__/MinReturn -131.935 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.6634 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 42200 ------------------------------------------------- ---------- 2025-04-02 14:14:18 | [pearl_trainer] epoch #17 | Training... 2025-04-02 14:15:40 | [pearl_trainer] epoch #17 | Evaluating... 2025-04-02 14:15:40 | [pearl_trainer] epoch #17 | Sampling for adapation and meta-testing... 2025-04-02 14:16:27 | [pearl_trainer] epoch #17 | Finished meta-testing... 2025-04-02 14:16:27 | [pearl_trainer] epoch #17 | Saving snapshot... 2025-04-02 14:16:28 | [pearl_trainer] epoch #17 | Saved 2025-04-02 14:16:28 | [pearl_trainer] epoch #17 | Time 2864.45 s 2025-04-02 14:16:28 | [pearl_trainer] epoch #17 | EpochTime 152.42 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -133.528 MetaTest/Average/AverageReturn -133.528 MetaTest/Average/Iteration 17 MetaTest/Average/MaxReturn -131.866 MetaTest/Average/MinReturn -136.495 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.1031 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -133.528 MetaTest/__unnamed_task__/AverageReturn -133.528 MetaTest/__unnamed_task__/Iteration 17 MetaTest/__unnamed_task__/MaxReturn -131.866 MetaTest/__unnamed_task__/MinReturn -136.495 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.1031 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 43800 ------------------------------------------------- ---------- 2025-04-02 14:16:53 | [pearl_trainer] epoch #18 | Training... 2025-04-02 14:18:15 | [pearl_trainer] epoch #18 | Evaluating... 2025-04-02 14:18:15 | [pearl_trainer] epoch #18 | Sampling for adapation and meta-testing... 2025-04-02 14:18:56 | [pearl_trainer] epoch #18 | Finished meta-testing... 2025-04-02 14:18:56 | [pearl_trainer] epoch #18 | Saving snapshot... 2025-04-02 14:18:57 | [pearl_trainer] epoch #18 | Saved 2025-04-02 14:18:57 | [pearl_trainer] epoch #18 | Time 3013.49 s 2025-04-02 14:18:57 | [pearl_trainer] epoch #18 | EpochTime 149.04 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -124.387 MetaTest/Average/AverageReturn -124.387 MetaTest/Average/Iteration 18 MetaTest/Average/MaxReturn -112.751 MetaTest/Average/MinReturn -130.56 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.2327 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -124.387 MetaTest/__unnamed_task__/AverageReturn -124.387 MetaTest/__unnamed_task__/Iteration 18 MetaTest/__unnamed_task__/MaxReturn -112.751 MetaTest/__unnamed_task__/MinReturn -130.56 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.2327 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 45400 ------------------------------------------------- ---------- 2025-04-02 14:19:17 | [pearl_trainer] epoch #19 | Training... 2025-04-02 14:20:53 | [pearl_trainer] epoch #19 | Evaluating... 2025-04-02 14:20:53 | [pearl_trainer] epoch #19 | Sampling for adapation and meta-testing... 2025-04-02 14:21:35 | [pearl_trainer] epoch #19 | Finished meta-testing... 2025-04-02 14:21:35 | [pearl_trainer] epoch #19 | Saving snapshot... 2025-04-02 14:21:36 | [pearl_trainer] epoch #19 | Saved 2025-04-02 14:21:36 | [pearl_trainer] epoch #19 | Time 3172.29 s 2025-04-02 14:21:36 | [pearl_trainer] epoch #19 | EpochTime 158.80 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -122.434 MetaTest/Average/AverageReturn -122.434 MetaTest/Average/Iteration 19 MetaTest/Average/MaxReturn -117.642 MetaTest/Average/MinReturn -126.764 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.73828 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -122.434 MetaTest/__unnamed_task__/AverageReturn -122.434 MetaTest/__unnamed_task__/Iteration 19 MetaTest/__unnamed_task__/MaxReturn -117.642 MetaTest/__unnamed_task__/MinReturn -126.764 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.73828 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 47000 ------------------------------------------------- ----------- 2025-04-02 14:21:56 | [pearl_trainer] epoch #20 | Training... 2025-04-02 14:23:19 | [pearl_trainer] epoch #20 | Evaluating... 2025-04-02 14:23:19 | [pearl_trainer] epoch #20 | Sampling for adapation and meta-testing... 2025-04-02 14:24:08 | [pearl_trainer] epoch #20 | Finished meta-testing... 2025-04-02 14:24:08 | [pearl_trainer] epoch #20 | Saving snapshot... 2025-04-02 14:24:09 | [pearl_trainer] epoch #20 | Saved 2025-04-02 14:24:09 | [pearl_trainer] epoch #20 | Time 3325.02 s 2025-04-02 14:24:09 | [pearl_trainer] epoch #20 | EpochTime 152.73 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -114.215 MetaTest/Average/AverageReturn -114.215 MetaTest/Average/Iteration 20 MetaTest/Average/MaxReturn -108.289 MetaTest/Average/MinReturn -125.546 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.0152 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -114.215 MetaTest/__unnamed_task__/AverageReturn -114.215 MetaTest/__unnamed_task__/Iteration 20 MetaTest/__unnamed_task__/MaxReturn -108.289 MetaTest/__unnamed_task__/MinReturn -125.546 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.0152 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 48600 ------------------------------------------------- ---------- 2025-04-02 14:24:34 | [pearl_trainer] epoch #21 | Training... 2025-04-02 14:25:53 | [pearl_trainer] epoch #21 | Evaluating... 2025-04-02 14:25:53 | [pearl_trainer] epoch #21 | Sampling for adapation and meta-testing... 2025-04-02 14:26:36 | [pearl_trainer] epoch #21 | Finished meta-testing... 2025-04-02 14:26:36 | [pearl_trainer] epoch #21 | Saving snapshot... 2025-04-02 14:26:37 | [pearl_trainer] epoch #21 | Saved 2025-04-02 14:26:37 | [pearl_trainer] epoch #21 | Time 3473.62 s 2025-04-02 14:26:37 | [pearl_trainer] epoch #21 | EpochTime 148.60 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -121.487 MetaTest/Average/AverageReturn -121.487 MetaTest/Average/Iteration 21 MetaTest/Average/MaxReturn -111.749 MetaTest/Average/MinReturn -133.743 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.15415 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -121.487 MetaTest/__unnamed_task__/AverageReturn -121.487 MetaTest/__unnamed_task__/Iteration 21 MetaTest/__unnamed_task__/MaxReturn -111.749 MetaTest/__unnamed_task__/MinReturn -133.743 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.15415 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 50200 ------------------------------------------------- ----------- 2025-04-02 14:27:00 | [pearl_trainer] epoch #22 | Training... 2025-04-02 14:28:31 | [pearl_trainer] epoch #22 | Evaluating... 2025-04-02 14:28:31 | [pearl_trainer] epoch #22 | Sampling for adapation and meta-testing... 2025-04-02 14:29:15 | [pearl_trainer] epoch #22 | Finished meta-testing... 2025-04-02 14:29:15 | [pearl_trainer] epoch #22 | Saving snapshot... 2025-04-02 14:29:16 | [pearl_trainer] epoch #22 | Saved 2025-04-02 14:29:16 | [pearl_trainer] epoch #22 | Time 3632.05 s 2025-04-02 14:29:16 | [pearl_trainer] epoch #22 | EpochTime 158.43 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -145.558 MetaTest/Average/AverageReturn -145.558 MetaTest/Average/Iteration 22 MetaTest/Average/MaxReturn -141.292 MetaTest/Average/MinReturn -148.947 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.18594 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -145.558 MetaTest/__unnamed_task__/AverageReturn -145.558 MetaTest/__unnamed_task__/Iteration 22 MetaTest/__unnamed_task__/MaxReturn -141.292 MetaTest/__unnamed_task__/MinReturn -148.947 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.18594 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 51800 ------------------------------------------------- ----------- 2025-04-02 14:29:36 | [pearl_trainer] epoch #23 | Training... 2025-04-02 14:31:07 | [pearl_trainer] epoch #23 | Evaluating... 2025-04-02 14:31:07 | [pearl_trainer] epoch #23 | Sampling for adapation and meta-testing... 2025-04-02 14:31:56 | [pearl_trainer] epoch #23 | Finished meta-testing... 2025-04-02 14:31:56 | [pearl_trainer] epoch #23 | Saving snapshot... 2025-04-02 14:31:57 | [pearl_trainer] epoch #23 | Saved 2025-04-02 14:31:57 | [pearl_trainer] epoch #23 | Time 3793.13 s 2025-04-02 14:31:57 | [pearl_trainer] epoch #23 | EpochTime 161.08 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -129.832 MetaTest/Average/AverageReturn -129.832 MetaTest/Average/Iteration 23 MetaTest/Average/MaxReturn -98.4371 MetaTest/Average/MinReturn -147.163 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 22.2396 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -129.832 MetaTest/__unnamed_task__/AverageReturn -129.832 MetaTest/__unnamed_task__/Iteration 23 MetaTest/__unnamed_task__/MaxReturn -98.4371 MetaTest/__unnamed_task__/MinReturn -147.163 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 22.2396 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 53400 ------------------------------------------------- ---------- 2025-04-02 14:32:17 | [pearl_trainer] epoch #24 | Training... 2025-04-02 14:33:35 | [pearl_trainer] epoch #24 | Evaluating... 2025-04-02 14:33:35 | [pearl_trainer] epoch #24 | Sampling for adapation and meta-testing... 2025-04-02 14:34:23 | [pearl_trainer] epoch #24 | Finished meta-testing... 2025-04-02 14:34:23 | [pearl_trainer] epoch #24 | Saving snapshot... 2025-04-02 14:34:24 | [pearl_trainer] epoch #24 | Saved 2025-04-02 14:34:24 | [pearl_trainer] epoch #24 | Time 3940.36 s 2025-04-02 14:34:24 | [pearl_trainer] epoch #24 | EpochTime 147.23 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -128.926 MetaTest/Average/AverageReturn -128.926 MetaTest/Average/Iteration 24 MetaTest/Average/MaxReturn -116.866 MetaTest/Average/MinReturn -140.521 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.66248 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -128.926 MetaTest/__unnamed_task__/AverageReturn -128.926 MetaTest/__unnamed_task__/Iteration 24 MetaTest/__unnamed_task__/MaxReturn -116.866 MetaTest/__unnamed_task__/MinReturn -140.521 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.66248 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 55000 ------------------------------------------------- ----------- 2025-04-02 14:34:46 | [pearl_trainer] epoch #25 | Training... 2025-04-02 14:36:07 | [pearl_trainer] epoch #25 | Evaluating... 2025-04-02 14:36:07 | [pearl_trainer] epoch #25 | Sampling for adapation and meta-testing... 2025-04-02 14:36:49 | [pearl_trainer] epoch #25 | Finished meta-testing... 2025-04-02 14:36:49 | [pearl_trainer] epoch #25 | Saving snapshot... 2025-04-02 14:36:50 | [pearl_trainer] epoch #25 | Saved 2025-04-02 14:36:50 | [pearl_trainer] epoch #25 | Time 4085.70 s 2025-04-02 14:36:50 | [pearl_trainer] epoch #25 | EpochTime 145.34 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -144.959 MetaTest/Average/AverageReturn -144.959 MetaTest/Average/Iteration 25 MetaTest/Average/MaxReturn -119.467 MetaTest/Average/MinReturn -164.903 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 18.9597 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -144.959 MetaTest/__unnamed_task__/AverageReturn -144.959 MetaTest/__unnamed_task__/Iteration 25 MetaTest/__unnamed_task__/MaxReturn -119.467 MetaTest/__unnamed_task__/MinReturn -164.903 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 18.9597 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 56600 ------------------------------------------------- ---------- 2025-04-02 14:37:09 | [pearl_trainer] epoch #26 | Training... 2025-04-02 14:38:43 | [pearl_trainer] epoch #26 | Evaluating... 2025-04-02 14:38:43 | [pearl_trainer] epoch #26 | Sampling for adapation and meta-testing... 2025-04-02 14:39:38 | [pearl_trainer] epoch #26 | Finished meta-testing... 2025-04-02 14:39:38 | [pearl_trainer] epoch #26 | Saving snapshot... 2025-04-02 14:39:38 | [pearl_trainer] epoch #26 | Saved 2025-04-02 14:39:38 | [pearl_trainer] epoch #26 | Time 4254.63 s 2025-04-02 14:39:38 | [pearl_trainer] epoch #26 | EpochTime 168.92 s ------------------------------------------------- --------- MetaTest/Average/AverageDiscountedReturn -130.361 MetaTest/Average/AverageReturn -130.361 MetaTest/Average/Iteration 26 MetaTest/Average/MaxReturn -105.286 MetaTest/Average/MinReturn -161.863 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 23.54 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -130.361 MetaTest/__unnamed_task__/AverageReturn -130.361 MetaTest/__unnamed_task__/Iteration 26 MetaTest/__unnamed_task__/MaxReturn -105.286 MetaTest/__unnamed_task__/MinReturn -161.863 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 23.54 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 58200 ------------------------------------------------- --------- 2025-04-02 14:40:04 | [pearl_trainer] epoch #27 | Training... 2025-04-02 14:41:29 | [pearl_trainer] epoch #27 | Evaluating... 2025-04-02 14:41:29 | [pearl_trainer] epoch #27 | Sampling for adapation and meta-testing... 2025-04-02 14:42:15 | [pearl_trainer] epoch #27 | Finished meta-testing... 2025-04-02 14:42:15 | [pearl_trainer] epoch #27 | Saving snapshot... 2025-04-02 14:42:16 | [pearl_trainer] epoch #27 | Saved 2025-04-02 14:42:16 | [pearl_trainer] epoch #27 | Time 4412.42 s 2025-04-02 14:42:16 | [pearl_trainer] epoch #27 | EpochTime 157.79 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -114.622 MetaTest/Average/AverageReturn -114.622 MetaTest/Average/Iteration 27 MetaTest/Average/MaxReturn -100.574 MetaTest/Average/MinReturn -125.627 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.4516 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -114.622 MetaTest/__unnamed_task__/AverageReturn -114.622 MetaTest/__unnamed_task__/Iteration 27 MetaTest/__unnamed_task__/MaxReturn -100.574 MetaTest/__unnamed_task__/MinReturn -125.627 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.4516 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 59800 ------------------------------------------------- ---------- 2025-04-02 14:42:43 | [pearl_trainer] epoch #28 | Training... 2025-04-02 14:44:07 | [pearl_trainer] epoch #28 | Evaluating... 2025-04-02 14:44:07 | [pearl_trainer] epoch #28 | Sampling for adapation and meta-testing... 2025-04-02 14:44:51 | [pearl_trainer] epoch #28 | Finished meta-testing... 2025-04-02 14:44:51 | [pearl_trainer] epoch #28 | Saving snapshot... 2025-04-02 14:44:52 | [pearl_trainer] epoch #28 | Saved 2025-04-02 14:44:52 | [pearl_trainer] epoch #28 | Time 4567.94 s 2025-04-02 14:44:52 | [pearl_trainer] epoch #28 | EpochTime 155.52 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -120.233 MetaTest/Average/AverageReturn -120.233 MetaTest/Average/Iteration 28 MetaTest/Average/MaxReturn -113.611 MetaTest/Average/MinReturn -127.926 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.8927 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -120.233 MetaTest/__unnamed_task__/AverageReturn -120.233 MetaTest/__unnamed_task__/Iteration 28 MetaTest/__unnamed_task__/MaxReturn -113.611 MetaTest/__unnamed_task__/MinReturn -127.926 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.8927 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 61400 ------------------------------------------------- ---------- 2025-04-02 14:45:13 | [pearl_trainer] epoch #29 | Training... 2025-04-02 14:46:45 | [pearl_trainer] epoch #29 | Evaluating... 2025-04-02 14:46:45 | [pearl_trainer] epoch #29 | Sampling for adapation and meta-testing... 2025-04-02 14:47:32 | [pearl_trainer] epoch #29 | Finished meta-testing... 2025-04-02 14:47:32 | [pearl_trainer] epoch #29 | Saving snapshot... 2025-04-02 14:47:33 | [pearl_trainer] epoch #29 | Saved 2025-04-02 14:47:33 | [pearl_trainer] epoch #29 | Time 4729.11 s 2025-04-02 14:47:33 | [pearl_trainer] epoch #29 | EpochTime 161.16 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -120.031 MetaTest/Average/AverageReturn -120.031 MetaTest/Average/Iteration 29 MetaTest/Average/MaxReturn -112.096 MetaTest/Average/MinReturn -131.475 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.29149 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -120.031 MetaTest/__unnamed_task__/AverageReturn -120.031 MetaTest/__unnamed_task__/Iteration 29 MetaTest/__unnamed_task__/MaxReturn -112.096 MetaTest/__unnamed_task__/MinReturn -131.475 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.29149 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 63000 ------------------------------------------------- ----------- 2025-04-02 14:47:55 | [pearl_trainer] epoch #30 | Training... 2025-04-02 14:49:11 | [pearl_trainer] epoch #30 | Evaluating... 2025-04-02 14:49:11 | [pearl_trainer] epoch #30 | Sampling for adapation and meta-testing... 2025-04-02 14:49:58 | [pearl_trainer] epoch #30 | Finished meta-testing... 2025-04-02 14:49:58 | [pearl_trainer] epoch #30 | Saving snapshot... 2025-04-02 14:49:59 | [pearl_trainer] epoch #30 | Saved 2025-04-02 14:49:59 | [pearl_trainer] epoch #30 | Time 4875.32 s 2025-04-02 14:49:59 | [pearl_trainer] epoch #30 | EpochTime 146.22 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -112.047 MetaTest/Average/AverageReturn -112.047 MetaTest/Average/Iteration 30 MetaTest/Average/MaxReturn -104.055 MetaTest/Average/MinReturn -119.631 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.3653 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -112.047 MetaTest/__unnamed_task__/AverageReturn -112.047 MetaTest/__unnamed_task__/Iteration 30 MetaTest/__unnamed_task__/MaxReturn -104.055 MetaTest/__unnamed_task__/MinReturn -119.631 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.3653 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 64600 ------------------------------------------------- ---------- 2025-04-02 14:50:22 | [pearl_trainer] epoch #31 | Training... 2025-04-02 14:51:48 | [pearl_trainer] epoch #31 | Evaluating... 2025-04-02 14:51:48 | [pearl_trainer] epoch #31 | Sampling for adapation and meta-testing... 2025-04-02 14:52:31 | [pearl_trainer] epoch #31 | Finished meta-testing... 2025-04-02 14:52:31 | [pearl_trainer] epoch #31 | Saving snapshot... 2025-04-02 14:52:31 | [pearl_trainer] epoch #31 | Saved 2025-04-02 14:52:31 | [pearl_trainer] epoch #31 | Time 5027.59 s 2025-04-02 14:52:31 | [pearl_trainer] epoch #31 | EpochTime 152.27 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -111.694 MetaTest/Average/AverageReturn -111.694 MetaTest/Average/Iteration 31 MetaTest/Average/MaxReturn -102.229 MetaTest/Average/MinReturn -117.463 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.74622 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.694 MetaTest/__unnamed_task__/AverageReturn -111.694 MetaTest/__unnamed_task__/Iteration 31 MetaTest/__unnamed_task__/MaxReturn -102.229 MetaTest/__unnamed_task__/MinReturn -117.463 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.74622 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 66200 ------------------------------------------------- ----------- 2025-04-02 14:52:51 | [pearl_trainer] epoch #32 | Training... 2025-04-02 14:54:14 | [pearl_trainer] epoch #32 | Evaluating... 2025-04-02 14:54:14 | [pearl_trainer] epoch #32 | Sampling for adapation and meta-testing... 2025-04-02 14:55:01 | [pearl_trainer] epoch #32 | Finished meta-testing... 2025-04-02 14:55:01 | [pearl_trainer] epoch #32 | Saving snapshot... 2025-04-02 14:55:02 | [pearl_trainer] epoch #32 | Saved 2025-04-02 14:55:02 | [pearl_trainer] epoch #32 | Time 5178.63 s 2025-04-02 14:55:02 | [pearl_trainer] epoch #32 | EpochTime 151.04 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -120.081 MetaTest/Average/AverageReturn -120.081 MetaTest/Average/Iteration 32 MetaTest/Average/MaxReturn -101.889 MetaTest/Average/MinReturn -142.482 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 16.8371 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -120.081 MetaTest/__unnamed_task__/AverageReturn -120.081 MetaTest/__unnamed_task__/Iteration 32 MetaTest/__unnamed_task__/MaxReturn -101.889 MetaTest/__unnamed_task__/MinReturn -142.482 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 16.8371 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 67800 ------------------------------------------------- ---------- 2025-04-02 14:55:24 | [pearl_trainer] epoch #33 | Training... 2025-04-02 14:56:48 | [pearl_trainer] epoch #33 | Evaluating... 2025-04-02 14:56:48 | [pearl_trainer] epoch #33 | Sampling for adapation and meta-testing... 2025-04-02 14:57:35 | [pearl_trainer] epoch #33 | Finished meta-testing... 2025-04-02 14:57:35 | [pearl_trainer] epoch #33 | Saving snapshot... 2025-04-02 14:57:36 | [pearl_trainer] epoch #33 | Saved 2025-04-02 14:57:36 | [pearl_trainer] epoch #33 | Time 5332.58 s 2025-04-02 14:57:36 | [pearl_trainer] epoch #33 | EpochTime 153.94 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -107.978 MetaTest/Average/AverageReturn -107.978 MetaTest/Average/Iteration 33 MetaTest/Average/MaxReturn -80.9001 MetaTest/Average/MinReturn -137.362 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 23.1079 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -107.978 MetaTest/__unnamed_task__/AverageReturn -107.978 MetaTest/__unnamed_task__/Iteration 33 MetaTest/__unnamed_task__/MaxReturn -80.9001 MetaTest/__unnamed_task__/MinReturn -137.362 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 23.1079 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 69400 ------------------------------------------------- ---------- 2025-04-02 14:57:58 | [pearl_trainer] epoch #34 | Training... 2025-04-02 14:59:22 | [pearl_trainer] epoch #34 | Evaluating... 2025-04-02 14:59:22 | [pearl_trainer] epoch #34 | Sampling for adapation and meta-testing... 2025-04-02 15:00:05 | [pearl_trainer] epoch #34 | Finished meta-testing... 2025-04-02 15:00:05 | [pearl_trainer] epoch #34 | Saving snapshot... 2025-04-02 15:00:06 | [pearl_trainer] epoch #34 | Saved 2025-04-02 15:00:06 | [pearl_trainer] epoch #34 | Time 5482.03 s 2025-04-02 15:00:06 | [pearl_trainer] epoch #34 | EpochTime 149.45 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -117.384 MetaTest/Average/AverageReturn -117.384 MetaTest/Average/Iteration 34 MetaTest/Average/MaxReturn -109.871 MetaTest/Average/MinReturn -132.384 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.6066 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -117.384 MetaTest/__unnamed_task__/AverageReturn -117.384 MetaTest/__unnamed_task__/Iteration 34 MetaTest/__unnamed_task__/MaxReturn -109.871 MetaTest/__unnamed_task__/MinReturn -132.384 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.6066 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 71000 ------------------------------------------------- ---------- 2025-04-02 15:00:29 | [pearl_trainer] epoch #35 | Training... 2025-04-02 15:01:58 | [pearl_trainer] epoch #35 | Evaluating... 2025-04-02 15:01:58 | [pearl_trainer] epoch #35 | Sampling for adapation and meta-testing... 2025-04-02 15:02:41 | [pearl_trainer] epoch #35 | Finished meta-testing... 2025-04-02 15:02:41 | [pearl_trainer] epoch #35 | Saving snapshot... 2025-04-02 15:02:42 | [pearl_trainer] epoch #35 | Saved 2025-04-02 15:02:42 | [pearl_trainer] epoch #35 | Time 5637.96 s 2025-04-02 15:02:42 | [pearl_trainer] epoch #35 | EpochTime 155.94 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -123.505 MetaTest/Average/AverageReturn -123.505 MetaTest/Average/Iteration 35 MetaTest/Average/MaxReturn -117.818 MetaTest/Average/MinReturn -132.306 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.31119 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -123.505 MetaTest/__unnamed_task__/AverageReturn -123.505 MetaTest/__unnamed_task__/Iteration 35 MetaTest/__unnamed_task__/MaxReturn -117.818 MetaTest/__unnamed_task__/MinReturn -132.306 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.31119 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 72600 ------------------------------------------------- ----------- 2025-04-02 15:03:03 | [pearl_trainer] epoch #36 | Training... 2025-04-02 15:04:33 | [pearl_trainer] epoch #36 | Evaluating... 2025-04-02 15:04:33 | [pearl_trainer] epoch #36 | Sampling for adapation and meta-testing... 2025-04-02 15:05:24 | [pearl_trainer] epoch #36 | Finished meta-testing... 2025-04-02 15:05:24 | [pearl_trainer] epoch #36 | Saving snapshot... 2025-04-02 15:05:25 | [pearl_trainer] epoch #36 | Saved 2025-04-02 15:05:25 | [pearl_trainer] epoch #36 | Time 5800.90 s 2025-04-02 15:05:25 | [pearl_trainer] epoch #36 | EpochTime 162.93 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -110.436 MetaTest/Average/AverageReturn -110.436 MetaTest/Average/Iteration 36 MetaTest/Average/MaxReturn -107.706 MetaTest/Average/MinReturn -115.641 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.68198 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -110.436 MetaTest/__unnamed_task__/AverageReturn -110.436 MetaTest/__unnamed_task__/Iteration 36 MetaTest/__unnamed_task__/MaxReturn -107.706 MetaTest/__unnamed_task__/MinReturn -115.641 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.68198 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 74200 ------------------------------------------------- ----------- 2025-04-02 15:05:47 | [pearl_trainer] epoch #37 | Training... 2025-04-02 15:07:12 | [pearl_trainer] epoch #37 | Evaluating... 2025-04-02 15:07:12 | [pearl_trainer] epoch #37 | Sampling for adapation and meta-testing... 2025-04-02 15:07:57 | [pearl_trainer] epoch #37 | Finished meta-testing... 2025-04-02 15:07:57 | [pearl_trainer] epoch #37 | Saving snapshot... 2025-04-02 15:07:58 | [pearl_trainer] epoch #37 | Saved 2025-04-02 15:07:58 | [pearl_trainer] epoch #37 | Time 5954.45 s 2025-04-02 15:07:58 | [pearl_trainer] epoch #37 | EpochTime 153.55 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -111.625 MetaTest/Average/AverageReturn -111.625 MetaTest/Average/Iteration 37 MetaTest/Average/MaxReturn -105.603 MetaTest/Average/MinReturn -120.741 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.55564 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.625 MetaTest/__unnamed_task__/AverageReturn -111.625 MetaTest/__unnamed_task__/Iteration 37 MetaTest/__unnamed_task__/MaxReturn -105.603 MetaTest/__unnamed_task__/MinReturn -120.741 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.55564 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 75800 ------------------------------------------------- ----------- 2025-04-02 15:08:21 | [pearl_trainer] epoch #38 | Training... 2025-04-02 15:10:05 | [pearl_trainer] epoch #38 | Evaluating... 2025-04-02 15:10:05 | [pearl_trainer] epoch #38 | Sampling for adapation and meta-testing... 2025-04-02 15:10:53 | [pearl_trainer] epoch #38 | Finished meta-testing... 2025-04-02 15:10:53 | [pearl_trainer] epoch #38 | Saving snapshot... 2025-04-02 15:10:54 | [pearl_trainer] epoch #38 | Saved 2025-04-02 15:10:54 | [pearl_trainer] epoch #38 | Time 6130.16 s 2025-04-02 15:10:54 | [pearl_trainer] epoch #38 | EpochTime 175.71 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -123.671 MetaTest/Average/AverageReturn -123.671 MetaTest/Average/Iteration 38 MetaTest/Average/MaxReturn -121.255 MetaTest/Average/MinReturn -125.314 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.74516 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -123.671 MetaTest/__unnamed_task__/AverageReturn -123.671 MetaTest/__unnamed_task__/Iteration 38 MetaTest/__unnamed_task__/MaxReturn -121.255 MetaTest/__unnamed_task__/MinReturn -125.314 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.74516 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 77400 ------------------------------------------------- ----------- 2025-04-02 15:11:15 | [pearl_trainer] epoch #39 | Training... 2025-04-02 15:12:46 | [pearl_trainer] epoch #39 | Evaluating... 2025-04-02 15:12:46 | [pearl_trainer] epoch #39 | Sampling for adapation and meta-testing... 2025-04-02 15:13:36 | [pearl_trainer] epoch #39 | Finished meta-testing... 2025-04-02 15:13:36 | [pearl_trainer] epoch #39 | Saving snapshot... 2025-04-02 15:13:37 | [pearl_trainer] epoch #39 | Saved 2025-04-02 15:13:37 | [pearl_trainer] epoch #39 | Time 6293.18 s 2025-04-02 15:13:37 | [pearl_trainer] epoch #39 | EpochTime 163.02 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -126.906 MetaTest/Average/AverageReturn -126.906 MetaTest/Average/Iteration 39 MetaTest/Average/MaxReturn -109.376 MetaTest/Average/MinReturn -139.841 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.8546 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -126.906 MetaTest/__unnamed_task__/AverageReturn -126.906 MetaTest/__unnamed_task__/Iteration 39 MetaTest/__unnamed_task__/MaxReturn -109.376 MetaTest/__unnamed_task__/MinReturn -139.841 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.8546 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 79000 ------------------------------------------------- ---------- 2025-04-02 15:13:58 | [pearl_trainer] epoch #40 | Training... 2025-04-02 15:15:23 | [pearl_trainer] epoch #40 | Evaluating... 2025-04-02 15:15:23 | [pearl_trainer] epoch #40 | Sampling for adapation and meta-testing... 2025-04-02 15:16:08 | [pearl_trainer] epoch #40 | Finished meta-testing... 2025-04-02 15:16:08 | [pearl_trainer] epoch #40 | Saving snapshot... 2025-04-02 15:16:10 | [pearl_trainer] epoch #40 | Saved 2025-04-02 15:16:10 | [pearl_trainer] epoch #40 | Time 6445.75 s 2025-04-02 15:16:10 | [pearl_trainer] epoch #40 | EpochTime 152.56 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -133.581 MetaTest/Average/AverageReturn -133.581 MetaTest/Average/Iteration 40 MetaTest/Average/MaxReturn -98.6261 MetaTest/Average/MinReturn -161.789 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 26.2237 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -133.581 MetaTest/__unnamed_task__/AverageReturn -133.581 MetaTest/__unnamed_task__/Iteration 40 MetaTest/__unnamed_task__/MaxReturn -98.6261 MetaTest/__unnamed_task__/MinReturn -161.789 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 26.2237 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 80600 ------------------------------------------------- ---------- 2025-04-02 15:16:31 | [pearl_trainer] epoch #41 | Training... 2025-04-02 15:18:03 | [pearl_trainer] epoch #41 | Evaluating... 2025-04-02 15:18:03 | [pearl_trainer] epoch #41 | Sampling for adapation and meta-testing... 2025-04-02 15:18:48 | [pearl_trainer] epoch #41 | Finished meta-testing... 2025-04-02 15:18:48 | [pearl_trainer] epoch #41 | Saving snapshot... 2025-04-02 15:18:49 | [pearl_trainer] epoch #41 | Saved 2025-04-02 15:18:49 | [pearl_trainer] epoch #41 | Time 6604.72 s 2025-04-02 15:18:49 | [pearl_trainer] epoch #41 | EpochTime 158.97 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -115.647 MetaTest/Average/AverageReturn -115.647 MetaTest/Average/Iteration 41 MetaTest/Average/MaxReturn -111.054 MetaTest/Average/MinReturn -121.391 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.29805 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -115.647 MetaTest/__unnamed_task__/AverageReturn -115.647 MetaTest/__unnamed_task__/Iteration 41 MetaTest/__unnamed_task__/MaxReturn -111.054 MetaTest/__unnamed_task__/MinReturn -121.391 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.29805 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 82200 ------------------------------------------------- ----------- 2025-04-02 15:19:10 | [pearl_trainer] epoch #42 | Training... 2025-04-02 15:20:37 | [pearl_trainer] epoch #42 | Evaluating... 2025-04-02 15:20:37 | [pearl_trainer] epoch #42 | Sampling for adapation and meta-testing... 2025-04-02 15:21:32 | [pearl_trainer] epoch #42 | Finished meta-testing... 2025-04-02 15:21:32 | [pearl_trainer] epoch #42 | Saving snapshot... 2025-04-02 15:21:33 | [pearl_trainer] epoch #42 | Saved 2025-04-02 15:21:33 | [pearl_trainer] epoch #42 | Time 6769.17 s 2025-04-02 15:21:33 | [pearl_trainer] epoch #42 | EpochTime 164.45 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -106.032 MetaTest/Average/AverageReturn -106.032 MetaTest/Average/Iteration 42 MetaTest/Average/MaxReturn -91.5546 MetaTest/Average/MinReturn -117.611 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.833 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -106.032 MetaTest/__unnamed_task__/AverageReturn -106.032 MetaTest/__unnamed_task__/Iteration 42 MetaTest/__unnamed_task__/MaxReturn -91.5546 MetaTest/__unnamed_task__/MinReturn -117.611 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.833 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 83800 ------------------------------------------------- ---------- 2025-04-02 15:21:54 | [pearl_trainer] epoch #43 | Training... 2025-04-02 15:23:14 | [pearl_trainer] epoch #43 | Evaluating... 2025-04-02 15:23:14 | [pearl_trainer] epoch #43 | Sampling for adapation and meta-testing... 2025-04-02 15:24:05 | [pearl_trainer] epoch #43 | Finished meta-testing... 2025-04-02 15:24:05 | [pearl_trainer] epoch #43 | Saving snapshot... 2025-04-02 15:24:06 | [pearl_trainer] epoch #43 | Saved 2025-04-02 15:24:06 | [pearl_trainer] epoch #43 | Time 6922.59 s 2025-04-02 15:24:06 | [pearl_trainer] epoch #43 | EpochTime 153.42 s ------------------------------------------------- --------- MetaTest/Average/AverageDiscountedReturn -120.494 MetaTest/Average/AverageReturn -120.494 MetaTest/Average/Iteration 43 MetaTest/Average/MaxReturn -104.213 MetaTest/Average/MinReturn -134.843 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.579 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -120.494 MetaTest/__unnamed_task__/AverageReturn -120.494 MetaTest/__unnamed_task__/Iteration 43 MetaTest/__unnamed_task__/MaxReturn -104.213 MetaTest/__unnamed_task__/MinReturn -134.843 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.579 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 85400 ------------------------------------------------- --------- 2025-04-02 15:24:32 | [pearl_trainer] epoch #44 | Training... 2025-04-02 15:25:53 | [pearl_trainer] epoch #44 | Evaluating... 2025-04-02 15:25:53 | [pearl_trainer] epoch #44 | Sampling for adapation and meta-testing... 2025-04-02 15:26:35 | [pearl_trainer] epoch #44 | Finished meta-testing... 2025-04-02 15:26:35 | [pearl_trainer] epoch #44 | Saving snapshot... 2025-04-02 15:26:36 | [pearl_trainer] epoch #44 | Saved 2025-04-02 15:26:36 | [pearl_trainer] epoch #44 | Time 7072.11 s 2025-04-02 15:26:36 | [pearl_trainer] epoch #44 | EpochTime 149.51 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -128.405 MetaTest/Average/AverageReturn -128.405 MetaTest/Average/Iteration 44 MetaTest/Average/MaxReturn -119.705 MetaTest/Average/MinReturn -137.842 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.42306 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -128.405 MetaTest/__unnamed_task__/AverageReturn -128.405 MetaTest/__unnamed_task__/Iteration 44 MetaTest/__unnamed_task__/MaxReturn -119.705 MetaTest/__unnamed_task__/MinReturn -137.842 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.42306 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 87000 ------------------------------------------------- ----------- 2025-04-02 15:26:58 | [pearl_trainer] epoch #45 | Training... 2025-04-02 15:28:26 | [pearl_trainer] epoch #45 | Evaluating... 2025-04-02 15:28:26 | [pearl_trainer] epoch #45 | Sampling for adapation and meta-testing... 2025-04-02 15:29:12 | [pearl_trainer] epoch #45 | Finished meta-testing... 2025-04-02 15:29:12 | [pearl_trainer] epoch #45 | Saving snapshot... 2025-04-02 15:29:14 | [pearl_trainer] epoch #45 | Saved 2025-04-02 15:29:14 | [pearl_trainer] epoch #45 | Time 7229.73 s 2025-04-02 15:29:14 | [pearl_trainer] epoch #45 | EpochTime 157.63 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -99.2314 MetaTest/Average/AverageReturn -99.2314 MetaTest/Average/Iteration 45 MetaTest/Average/MaxReturn -85.2965 MetaTest/Average/MinReturn -117.001 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.2244 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -99.2314 MetaTest/__unnamed_task__/AverageReturn -99.2314 MetaTest/__unnamed_task__/Iteration 45 MetaTest/__unnamed_task__/MaxReturn -85.2965 MetaTest/__unnamed_task__/MinReturn -117.001 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.2244 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 88600 ------------------------------------------------- ---------- 2025-04-02 15:29:35 | [pearl_trainer] epoch #46 | Training... 2025-04-02 15:30:59 | [pearl_trainer] epoch #46 | Evaluating... 2025-04-02 15:30:59 | [pearl_trainer] epoch #46 | Sampling for adapation and meta-testing... 2025-04-02 15:31:51 | [pearl_trainer] epoch #46 | Finished meta-testing... 2025-04-02 15:31:51 | [pearl_trainer] epoch #46 | Saving snapshot... 2025-04-02 15:31:52 | [pearl_trainer] epoch #46 | Saved 2025-04-02 15:31:52 | [pearl_trainer] epoch #46 | Time 7388.01 s 2025-04-02 15:31:52 | [pearl_trainer] epoch #46 | EpochTime 158.27 s ------------------------------------------------- --------- MetaTest/Average/AverageDiscountedReturn -125.638 MetaTest/Average/AverageReturn -125.638 MetaTest/Average/Iteration 46 MetaTest/Average/MaxReturn -113.237 MetaTest/Average/MinReturn -145.891 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.441 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -125.638 MetaTest/__unnamed_task__/AverageReturn -125.638 MetaTest/__unnamed_task__/Iteration 46 MetaTest/__unnamed_task__/MaxReturn -113.237 MetaTest/__unnamed_task__/MinReturn -145.891 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.441 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 90200 ------------------------------------------------- --------- 2025-04-02 15:32:18 | [pearl_trainer] epoch #47 | Training... 2025-04-02 15:33:41 | [pearl_trainer] epoch #47 | Evaluating... 2025-04-02 15:33:41 | [pearl_trainer] epoch #47 | Sampling for adapation and meta-testing... 2025-04-02 15:34:25 | [pearl_trainer] epoch #47 | Finished meta-testing... 2025-04-02 15:34:25 | [pearl_trainer] epoch #47 | Saving snapshot... 2025-04-02 15:34:26 | [pearl_trainer] epoch #47 | Saved 2025-04-02 15:34:26 | [pearl_trainer] epoch #47 | Time 7542.24 s 2025-04-02 15:34:26 | [pearl_trainer] epoch #47 | EpochTime 154.22 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -123.198 MetaTest/Average/AverageReturn -123.198 MetaTest/Average/Iteration 47 MetaTest/Average/MaxReturn -85.121 MetaTest/Average/MinReturn -144.446 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 26.9848 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -123.198 MetaTest/__unnamed_task__/AverageReturn -123.198 MetaTest/__unnamed_task__/Iteration 47 MetaTest/__unnamed_task__/MaxReturn -85.121 MetaTest/__unnamed_task__/MinReturn -144.446 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 26.9848 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 91800 ------------------------------------------------- ---------- 2025-04-02 15:34:48 | [pearl_trainer] epoch #48 | Training... 2025-04-02 15:36:22 | [pearl_trainer] epoch #48 | Evaluating... 2025-04-02 15:36:22 | [pearl_trainer] epoch #48 | Sampling for adapation and meta-testing... 2025-04-02 15:37:08 | [pearl_trainer] epoch #48 | Finished meta-testing... 2025-04-02 15:37:08 | [pearl_trainer] epoch #48 | Saving snapshot... 2025-04-02 15:37:09 | [pearl_trainer] epoch #48 | Saved 2025-04-02 15:37:09 | [pearl_trainer] epoch #48 | Time 7704.73 s 2025-04-02 15:37:09 | [pearl_trainer] epoch #48 | EpochTime 162.49 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -123.725 MetaTest/Average/AverageReturn -123.725 MetaTest/Average/Iteration 48 MetaTest/Average/MaxReturn -105.971 MetaTest/Average/MinReturn -136.677 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.9877 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -123.725 MetaTest/__unnamed_task__/AverageReturn -123.725 MetaTest/__unnamed_task__/Iteration 48 MetaTest/__unnamed_task__/MaxReturn -105.971 MetaTest/__unnamed_task__/MinReturn -136.677 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.9877 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 93400 ------------------------------------------------- ---------- 2025-04-02 15:37:30 | [pearl_trainer] epoch #49 | Training... 2025-04-02 15:38:56 | [pearl_trainer] epoch #49 | Evaluating... 2025-04-02 15:38:56 | [pearl_trainer] epoch #49 | Sampling for adapation and meta-testing... 2025-04-02 15:39:46 | [pearl_trainer] epoch #49 | Finished meta-testing... 2025-04-02 15:39:46 | [pearl_trainer] epoch #49 | Saving snapshot... 2025-04-02 15:39:47 | [pearl_trainer] epoch #49 | Saved 2025-04-02 15:39:47 | [pearl_trainer] epoch #49 | Time 7863.52 s 2025-04-02 15:39:47 | [pearl_trainer] epoch #49 | EpochTime 158.79 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -108.612 MetaTest/Average/AverageReturn -108.612 MetaTest/Average/Iteration 49 MetaTest/Average/MaxReturn -79.8934 MetaTest/Average/MinReturn -139.703 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 24.475 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -108.612 MetaTest/__unnamed_task__/AverageReturn -108.612 MetaTest/__unnamed_task__/Iteration 49 MetaTest/__unnamed_task__/MaxReturn -79.8934 MetaTest/__unnamed_task__/MinReturn -139.703 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 24.475 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 95000 ------------------------------------------------- ---------- 2025-04-02 15:40:10 | [pearl_trainer] epoch #50 | Training... 2025-04-02 15:41:38 | [pearl_trainer] epoch #50 | Evaluating... 2025-04-02 15:41:38 | [pearl_trainer] epoch #50 | Sampling for adapation and meta-testing... 2025-04-02 15:42:26 | [pearl_trainer] epoch #50 | Finished meta-testing... 2025-04-02 15:42:26 | [pearl_trainer] epoch #50 | Saving snapshot... 2025-04-02 15:42:27 | [pearl_trainer] epoch #50 | Saved 2025-04-02 15:42:27 | [pearl_trainer] epoch #50 | Time 8023.66 s 2025-04-02 15:42:27 | [pearl_trainer] epoch #50 | EpochTime 160.13 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -117.328 MetaTest/Average/AverageReturn -117.328 MetaTest/Average/Iteration 50 MetaTest/Average/MaxReturn -105.891 MetaTest/Average/MinReturn -125.048 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.25087 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -117.328 MetaTest/__unnamed_task__/AverageReturn -117.328 MetaTest/__unnamed_task__/Iteration 50 MetaTest/__unnamed_task__/MaxReturn -105.891 MetaTest/__unnamed_task__/MinReturn -125.048 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.25087 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 96600 ------------------------------------------------- ----------- 2025-04-02 15:42:49 | [pearl_trainer] epoch #51 | Training... 2025-04-02 15:44:17 | [pearl_trainer] epoch #51 | Evaluating... 2025-04-02 15:44:17 | [pearl_trainer] epoch #51 | Sampling for adapation and meta-testing... 2025-04-02 15:44:59 | [pearl_trainer] epoch #51 | Finished meta-testing... 2025-04-02 15:44:59 | [pearl_trainer] epoch #51 | Saving snapshot... 2025-04-02 15:45:00 | [pearl_trainer] epoch #51 | Saved 2025-04-02 15:45:00 | [pearl_trainer] epoch #51 | Time 8175.79 s 2025-04-02 15:45:00 | [pearl_trainer] epoch #51 | EpochTime 152.13 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -111.626 MetaTest/Average/AverageReturn -111.626 MetaTest/Average/Iteration 51 MetaTest/Average/MaxReturn -85.6066 MetaTest/Average/MinReturn -125.255 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 18.4056 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.626 MetaTest/__unnamed_task__/AverageReturn -111.626 MetaTest/__unnamed_task__/Iteration 51 MetaTest/__unnamed_task__/MaxReturn -85.6066 MetaTest/__unnamed_task__/MinReturn -125.255 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 18.4056 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 98200 ------------------------------------------------- ---------- 2025-04-02 15:45:20 | [pearl_trainer] epoch #52 | Training... 2025-04-02 15:46:39 | [pearl_trainer] epoch #52 | Evaluating... 2025-04-02 15:46:39 | [pearl_trainer] epoch #52 | Sampling for adapation and meta-testing... 2025-04-02 15:47:26 | [pearl_trainer] epoch #52 | Finished meta-testing... 2025-04-02 15:47:26 | [pearl_trainer] epoch #52 | Saving snapshot... 2025-04-02 15:47:27 | [pearl_trainer] epoch #52 | Saved 2025-04-02 15:47:27 | [pearl_trainer] epoch #52 | Time 8323.06 s 2025-04-02 15:47:27 | [pearl_trainer] epoch #52 | EpochTime 147.27 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -145.593 MetaTest/Average/AverageReturn -145.593 MetaTest/Average/Iteration 52 MetaTest/Average/MaxReturn -140.975 MetaTest/Average/MinReturn -151.289 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.27923 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -145.593 MetaTest/__unnamed_task__/AverageReturn -145.593 MetaTest/__unnamed_task__/Iteration 52 MetaTest/__unnamed_task__/MaxReturn -140.975 MetaTest/__unnamed_task__/MinReturn -151.289 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.27923 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 99800 ------------------------------------------------- ----------- 2025-04-02 15:47:48 | [pearl_trainer] epoch #53 | Training... 2025-04-02 15:49:12 | [pearl_trainer] epoch #53 | Evaluating... 2025-04-02 15:49:12 | [pearl_trainer] epoch #53 | Sampling for adapation and meta-testing... 2025-04-02 15:49:57 | [pearl_trainer] epoch #53 | Finished meta-testing... 2025-04-02 15:49:57 | [pearl_trainer] epoch #53 | Saving snapshot... 2025-04-02 15:49:59 | [pearl_trainer] epoch #53 | Saved 2025-04-02 15:49:59 | [pearl_trainer] epoch #53 | Time 8474.76 s 2025-04-02 15:49:59 | [pearl_trainer] epoch #53 | EpochTime 151.70 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -149.106 MetaTest/Average/AverageReturn -149.106 MetaTest/Average/Iteration 53 MetaTest/Average/MaxReturn -143.876 MetaTest/Average/MinReturn -152.703 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.78402 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -149.106 MetaTest/__unnamed_task__/AverageReturn -149.106 MetaTest/__unnamed_task__/Iteration 53 MetaTest/__unnamed_task__/MaxReturn -143.876 MetaTest/__unnamed_task__/MinReturn -152.703 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.78402 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 101400 ------------------------------------------------- ------------ 2025-04-02 15:50:21 | [pearl_trainer] epoch #54 | Training... 2025-04-02 15:51:59 | [pearl_trainer] epoch #54 | Evaluating... 2025-04-02 15:51:59 | [pearl_trainer] epoch #54 | Sampling for adapation and meta-testing... 2025-04-02 15:52:44 | [pearl_trainer] epoch #54 | Finished meta-testing... 2025-04-02 15:52:44 | [pearl_trainer] epoch #54 | Saving snapshot... 2025-04-02 15:52:45 | [pearl_trainer] epoch #54 | Saved 2025-04-02 15:52:45 | [pearl_trainer] epoch #54 | Time 8641.23 s 2025-04-02 15:52:45 | [pearl_trainer] epoch #54 | EpochTime 166.47 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -130.743 MetaTest/Average/AverageReturn -130.743 MetaTest/Average/Iteration 54 MetaTest/Average/MaxReturn -105.488 MetaTest/Average/MinReturn -145.685 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 17.9578 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -130.743 MetaTest/__unnamed_task__/AverageReturn -130.743 MetaTest/__unnamed_task__/Iteration 54 MetaTest/__unnamed_task__/MaxReturn -105.488 MetaTest/__unnamed_task__/MinReturn -145.685 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 17.9578 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 103000 ------------------------------------------------- ----------- 2025-04-02 15:53:07 | [pearl_trainer] epoch #55 | Training... 2025-04-02 15:54:34 | [pearl_trainer] epoch #55 | Evaluating... 2025-04-02 15:54:34 | [pearl_trainer] epoch #55 | Sampling for adapation and meta-testing... 2025-04-02 15:55:25 | [pearl_trainer] epoch #55 | Finished meta-testing... 2025-04-02 15:55:25 | [pearl_trainer] epoch #55 | Saving snapshot... 2025-04-02 15:55:26 | [pearl_trainer] epoch #55 | Saved 2025-04-02 15:55:26 | [pearl_trainer] epoch #55 | Time 8801.99 s 2025-04-02 15:55:26 | [pearl_trainer] epoch #55 | EpochTime 160.76 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -118.72 MetaTest/Average/AverageReturn -118.72 MetaTest/Average/Iteration 55 MetaTest/Average/MaxReturn -104.119 MetaTest/Average/MinReturn -127.889 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.4367 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -118.72 MetaTest/__unnamed_task__/AverageReturn -118.72 MetaTest/__unnamed_task__/Iteration 55 MetaTest/__unnamed_task__/MaxReturn -104.119 MetaTest/__unnamed_task__/MinReturn -127.889 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.4367 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 104600 ------------------------------------------------- ----------- 2025-04-02 15:55:49 | [pearl_trainer] epoch #56 | Training... 2025-04-02 15:57:12 | [pearl_trainer] epoch #56 | Evaluating... 2025-04-02 15:57:12 | [pearl_trainer] epoch #56 | Sampling for adapation and meta-testing... 2025-04-02 15:58:01 | [pearl_trainer] epoch #56 | Finished meta-testing... 2025-04-02 15:58:01 | [pearl_trainer] epoch #56 | Saving snapshot... 2025-04-02 15:58:02 | [pearl_trainer] epoch #56 | Saved 2025-04-02 15:58:02 | [pearl_trainer] epoch #56 | Time 8958.68 s 2025-04-02 15:58:02 | [pearl_trainer] epoch #56 | EpochTime 156.69 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -125.074 MetaTest/Average/AverageReturn -125.074 MetaTest/Average/Iteration 56 MetaTest/Average/MaxReturn -116.607 MetaTest/Average/MinReturn -132.975 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.69405 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -125.074 MetaTest/__unnamed_task__/AverageReturn -125.074 MetaTest/__unnamed_task__/Iteration 56 MetaTest/__unnamed_task__/MaxReturn -116.607 MetaTest/__unnamed_task__/MinReturn -132.975 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.69405 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 106200 ------------------------------------------------- ------------ 2025-04-02 15:58:26 | [pearl_trainer] epoch #57 | Training... 2025-04-02 15:59:52 | [pearl_trainer] epoch #57 | Evaluating... 2025-04-02 15:59:52 | [pearl_trainer] epoch #57 | Sampling for adapation and meta-testing... 2025-04-02 16:00:41 | [pearl_trainer] epoch #57 | Finished meta-testing... 2025-04-02 16:00:41 | [pearl_trainer] epoch #57 | Saving snapshot... 2025-04-02 16:00:42 | [pearl_trainer] epoch #57 | Saved 2025-04-02 16:00:42 | [pearl_trainer] epoch #57 | Time 9118.16 s 2025-04-02 16:00:42 | [pearl_trainer] epoch #57 | EpochTime 159.47 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -116.962 MetaTest/Average/AverageReturn -116.962 MetaTest/Average/Iteration 57 MetaTest/Average/MaxReturn -113.915 MetaTest/Average/MinReturn -119.127 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.21768 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -116.962 MetaTest/__unnamed_task__/AverageReturn -116.962 MetaTest/__unnamed_task__/Iteration 57 MetaTest/__unnamed_task__/MaxReturn -113.915 MetaTest/__unnamed_task__/MinReturn -119.127 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.21768 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 107800 ------------------------------------------------- ------------ 2025-04-02 16:01:03 | [pearl_trainer] epoch #58 | Training... 2025-04-02 16:02:30 | [pearl_trainer] epoch #58 | Evaluating... 2025-04-02 16:02:30 | [pearl_trainer] epoch #58 | Sampling for adapation and meta-testing... 2025-04-02 16:03:16 | [pearl_trainer] epoch #58 | Finished meta-testing... 2025-04-02 16:03:16 | [pearl_trainer] epoch #58 | Saving snapshot... 2025-04-02 16:03:18 | [pearl_trainer] epoch #58 | Saved 2025-04-02 16:03:18 | [pearl_trainer] epoch #58 | Time 9273.73 s 2025-04-02 16:03:18 | [pearl_trainer] epoch #58 | EpochTime 155.57 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -121.466 MetaTest/Average/AverageReturn -121.466 MetaTest/Average/Iteration 58 MetaTest/Average/MaxReturn -108.051 MetaTest/Average/MinReturn -132.216 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.044 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -121.466 MetaTest/__unnamed_task__/AverageReturn -121.466 MetaTest/__unnamed_task__/Iteration 58 MetaTest/__unnamed_task__/MaxReturn -108.051 MetaTest/__unnamed_task__/MinReturn -132.216 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.044 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 109400 ------------------------------------------------- ---------- 2025-04-02 16:03:38 | [pearl_trainer] epoch #59 | Training... 2025-04-02 16:05:07 | [pearl_trainer] epoch #59 | Evaluating... 2025-04-02 16:05:07 | [pearl_trainer] epoch #59 | Sampling for adapation and meta-testing... 2025-04-02 16:05:52 | [pearl_trainer] epoch #59 | Finished meta-testing... 2025-04-02 16:05:52 | [pearl_trainer] epoch #59 | Saving snapshot... 2025-04-02 16:05:53 | [pearl_trainer] epoch #59 | Saved 2025-04-02 16:05:53 | [pearl_trainer] epoch #59 | Time 9429.63 s 2025-04-02 16:05:53 | [pearl_trainer] epoch #59 | EpochTime 155.89 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -121.05 MetaTest/Average/AverageReturn -121.05 MetaTest/Average/Iteration 59 MetaTest/Average/MaxReturn -105.755 MetaTest/Average/MinReturn -129.622 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.8418 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -121.05 MetaTest/__unnamed_task__/AverageReturn -121.05 MetaTest/__unnamed_task__/Iteration 59 MetaTest/__unnamed_task__/MaxReturn -105.755 MetaTest/__unnamed_task__/MinReturn -129.622 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.8418 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 111000 ------------------------------------------------- ----------- 2025-04-02 16:06:19 | [pearl_trainer] epoch #60 | Training... 2025-04-02 16:07:47 | [pearl_trainer] epoch #60 | Evaluating... 2025-04-02 16:07:47 | [pearl_trainer] epoch #60 | Sampling for adapation and meta-testing... 2025-04-02 16:08:29 | [pearl_trainer] epoch #60 | Finished meta-testing... 2025-04-02 16:08:29 | [pearl_trainer] epoch #60 | Saving snapshot... 2025-04-02 16:08:30 | [pearl_trainer] epoch #60 | Saved 2025-04-02 16:08:30 | [pearl_trainer] epoch #60 | Time 9586.44 s 2025-04-02 16:08:30 | [pearl_trainer] epoch #60 | EpochTime 156.81 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -131.466 MetaTest/Average/AverageReturn -131.466 MetaTest/Average/Iteration 60 MetaTest/Average/MaxReturn -114.992 MetaTest/Average/MinReturn -158.63 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 19.3524 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -131.466 MetaTest/__unnamed_task__/AverageReturn -131.466 MetaTest/__unnamed_task__/Iteration 60 MetaTest/__unnamed_task__/MaxReturn -114.992 MetaTest/__unnamed_task__/MinReturn -158.63 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 19.3524 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 112600 ------------------------------------------------- ----------- 2025-04-02 16:08:50 | [pearl_trainer] epoch #61 | Training... 2025-04-02 16:10:20 | [pearl_trainer] epoch #61 | Evaluating... 2025-04-02 16:10:20 | [pearl_trainer] epoch #61 | Sampling for adapation and meta-testing... 2025-04-02 16:11:04 | [pearl_trainer] epoch #61 | Finished meta-testing... 2025-04-02 16:11:04 | [pearl_trainer] epoch #61 | Saving snapshot... 2025-04-02 16:11:05 | [pearl_trainer] epoch #61 | Saved 2025-04-02 16:11:05 | [pearl_trainer] epoch #61 | Time 9741.22 s 2025-04-02 16:11:05 | [pearl_trainer] epoch #61 | EpochTime 154.78 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -128.994 MetaTest/Average/AverageReturn -128.994 MetaTest/Average/Iteration 61 MetaTest/Average/MaxReturn -109.561 MetaTest/Average/MinReturn -139.4 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.7526 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -128.994 MetaTest/__unnamed_task__/AverageReturn -128.994 MetaTest/__unnamed_task__/Iteration 61 MetaTest/__unnamed_task__/MaxReturn -109.561 MetaTest/__unnamed_task__/MinReturn -139.4 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.7526 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 114200 ------------------------------------------------- ----------- 2025-04-02 16:11:25 | [pearl_trainer] epoch #62 | Training... 2025-04-02 16:12:50 | [pearl_trainer] epoch #62 | Evaluating... 2025-04-02 16:12:50 | [pearl_trainer] epoch #62 | Sampling for adapation and meta-testing... 2025-04-02 16:13:42 | [pearl_trainer] epoch #62 | Finished meta-testing... 2025-04-02 16:13:42 | [pearl_trainer] epoch #62 | Saving snapshot... 2025-04-02 16:13:43 | [pearl_trainer] epoch #62 | Saved 2025-04-02 16:13:43 | [pearl_trainer] epoch #62 | Time 9899.04 s 2025-04-02 16:13:43 | [pearl_trainer] epoch #62 | EpochTime 157.82 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -134.216 MetaTest/Average/AverageReturn -134.216 MetaTest/Average/Iteration 62 MetaTest/Average/MaxReturn -86.8326 MetaTest/Average/MinReturn -162.441 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 33.7087 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -134.216 MetaTest/__unnamed_task__/AverageReturn -134.216 MetaTest/__unnamed_task__/Iteration 62 MetaTest/__unnamed_task__/MaxReturn -86.8326 MetaTest/__unnamed_task__/MinReturn -162.441 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 33.7087 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 115800 ------------------------------------------------- ----------- 2025-04-02 16:14:06 | [pearl_trainer] epoch #63 | Training... 2025-04-02 16:15:30 | [pearl_trainer] epoch #63 | Evaluating... 2025-04-02 16:15:30 | [pearl_trainer] epoch #63 | Sampling for adapation and meta-testing... 2025-04-02 16:16:15 | [pearl_trainer] epoch #63 | Finished meta-testing... 2025-04-02 16:16:15 | [pearl_trainer] epoch #63 | Saving snapshot... 2025-04-02 16:16:17 | [pearl_trainer] epoch #63 | Saved 2025-04-02 16:16:17 | [pearl_trainer] epoch #63 | Time 10052.78 s 2025-04-02 16:16:17 | [pearl_trainer] epoch #63 | EpochTime 153.74 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -156.62 MetaTest/Average/AverageReturn -156.62 MetaTest/Average/Iteration 63 MetaTest/Average/MaxReturn -147.352 MetaTest/Average/MinReturn -171.555 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.6622 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -156.62 MetaTest/__unnamed_task__/AverageReturn -156.62 MetaTest/__unnamed_task__/Iteration 63 MetaTest/__unnamed_task__/MaxReturn -147.352 MetaTest/__unnamed_task__/MinReturn -171.555 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.6622 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 117400 ------------------------------------------------- ----------- 2025-04-02 16:16:37 | [pearl_trainer] epoch #64 | Training... 2025-04-02 16:18:12 | [pearl_trainer] epoch #64 | Evaluating... 2025-04-02 16:18:12 | [pearl_trainer] epoch #64 | Sampling for adapation and meta-testing... 2025-04-02 16:18:56 | [pearl_trainer] epoch #64 | Finished meta-testing... 2025-04-02 16:18:56 | [pearl_trainer] epoch #64 | Saving snapshot... 2025-04-02 16:18:57 | [pearl_trainer] epoch #64 | Saved 2025-04-02 16:18:57 | [pearl_trainer] epoch #64 | Time 10213.26 s 2025-04-02 16:18:57 | [pearl_trainer] epoch #64 | EpochTime 160.48 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -111.014 MetaTest/Average/AverageReturn -111.014 MetaTest/Average/Iteration 64 MetaTest/Average/MaxReturn -104.183 MetaTest/Average/MinReturn -119.839 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.54551 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.014 MetaTest/__unnamed_task__/AverageReturn -111.014 MetaTest/__unnamed_task__/Iteration 64 MetaTest/__unnamed_task__/MaxReturn -104.183 MetaTest/__unnamed_task__/MinReturn -119.839 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.54551 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 119000 ------------------------------------------------- ------------ 2025-04-02 16:19:20 | [pearl_trainer] epoch #65 | Training... 2025-04-02 16:20:40 | [pearl_trainer] epoch #65 | Evaluating... 2025-04-02 16:20:40 | [pearl_trainer] epoch #65 | Sampling for adapation and meta-testing... 2025-04-02 16:21:28 | [pearl_trainer] epoch #65 | Finished meta-testing... 2025-04-02 16:21:28 | [pearl_trainer] epoch #65 | Saving snapshot... 2025-04-02 16:21:29 | [pearl_trainer] epoch #65 | Saved 2025-04-02 16:21:29 | [pearl_trainer] epoch #65 | Time 10364.86 s 2025-04-02 16:21:29 | [pearl_trainer] epoch #65 | EpochTime 151.60 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -116.604 MetaTest/Average/AverageReturn -116.604 MetaTest/Average/Iteration 65 MetaTest/Average/MaxReturn -112.731 MetaTest/Average/MinReturn -120.637 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.22961 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -116.604 MetaTest/__unnamed_task__/AverageReturn -116.604 MetaTest/__unnamed_task__/Iteration 65 MetaTest/__unnamed_task__/MaxReturn -112.731 MetaTest/__unnamed_task__/MinReturn -120.637 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.22961 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 120600 ------------------------------------------------- ------------ 2025-04-02 16:21:51 | [pearl_trainer] epoch #66 | Training... 2025-04-02 16:23:09 | [pearl_trainer] epoch #66 | Evaluating... 2025-04-02 16:23:09 | [pearl_trainer] epoch #66 | Sampling for adapation and meta-testing... 2025-04-02 16:23:51 | [pearl_trainer] epoch #66 | Finished meta-testing... 2025-04-02 16:23:51 | [pearl_trainer] epoch #66 | Saving snapshot... 2025-04-02 16:23:52 | [pearl_trainer] epoch #66 | Saved 2025-04-02 16:23:52 | [pearl_trainer] epoch #66 | Time 10508.61 s 2025-04-02 16:23:52 | [pearl_trainer] epoch #66 | EpochTime 143.75 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -116.066 MetaTest/Average/AverageReturn -116.066 MetaTest/Average/Iteration 66 MetaTest/Average/MaxReturn -110.52 MetaTest/Average/MinReturn -123.148 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.26848 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -116.066 MetaTest/__unnamed_task__/AverageReturn -116.066 MetaTest/__unnamed_task__/Iteration 66 MetaTest/__unnamed_task__/MaxReturn -110.52 MetaTest/__unnamed_task__/MinReturn -123.148 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.26848 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 122200 ------------------------------------------------- ------------ 2025-04-02 16:24:13 | [pearl_trainer] epoch #67 | Training... 2025-04-02 16:25:39 | [pearl_trainer] epoch #67 | Evaluating... 2025-04-02 16:25:39 | [pearl_trainer] epoch #67 | Sampling for adapation and meta-testing... 2025-04-02 16:26:25 | [pearl_trainer] epoch #67 | Finished meta-testing... 2025-04-02 16:26:25 | [pearl_trainer] epoch #67 | Saving snapshot... 2025-04-02 16:26:26 | [pearl_trainer] epoch #67 | Saved 2025-04-02 16:26:26 | [pearl_trainer] epoch #67 | Time 10662.64 s 2025-04-02 16:26:26 | [pearl_trainer] epoch #67 | EpochTime 154.02 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -141.176 MetaTest/Average/AverageReturn -141.176 MetaTest/Average/Iteration 67 MetaTest/Average/MaxReturn -124.648 MetaTest/Average/MinReturn -150.723 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.7343 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -141.176 MetaTest/__unnamed_task__/AverageReturn -141.176 MetaTest/__unnamed_task__/Iteration 67 MetaTest/__unnamed_task__/MaxReturn -124.648 MetaTest/__unnamed_task__/MinReturn -150.723 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.7343 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 123800 ------------------------------------------------- ----------- 2025-04-02 16:26:48 | [pearl_trainer] epoch #68 | Training... 2025-04-02 16:28:48 | [pearl_trainer] epoch #68 | Evaluating... 2025-04-02 16:28:48 | [pearl_trainer] epoch #68 | Sampling for adapation and meta-testing... 2025-04-02 16:29:55 | [pearl_trainer] epoch #68 | Finished meta-testing... 2025-04-02 16:29:55 | [pearl_trainer] epoch #68 | Saving snapshot... 2025-04-02 16:29:57 | [pearl_trainer] epoch #68 | Saved 2025-04-02 16:29:57 | [pearl_trainer] epoch #68 | Time 10872.93 s 2025-04-02 16:29:57 | [pearl_trainer] epoch #68 | EpochTime 210.29 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -128.222 MetaTest/Average/AverageReturn -128.222 MetaTest/Average/Iteration 68 MetaTest/Average/MaxReturn -125.871 MetaTest/Average/MinReturn -129.447 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.66296 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -128.222 MetaTest/__unnamed_task__/AverageReturn -128.222 MetaTest/__unnamed_task__/Iteration 68 MetaTest/__unnamed_task__/MaxReturn -125.871 MetaTest/__unnamed_task__/MinReturn -129.447 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.66296 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 125400 ------------------------------------------------- ------------ 2025-04-02 16:30:27 | [pearl_trainer] epoch #69 | Training... 2025-04-02 16:32:39 | [pearl_trainer] epoch #69 | Evaluating... 2025-04-02 16:32:39 | [pearl_trainer] epoch #69 | Sampling for adapation and meta-testing... 2025-04-02 16:33:31 | [pearl_trainer] epoch #69 | Finished meta-testing... 2025-04-02 16:33:31 | [pearl_trainer] epoch #69 | Saving snapshot... 2025-04-02 16:33:32 | [pearl_trainer] epoch #69 | Saved 2025-04-02 16:33:32 | [pearl_trainer] epoch #69 | Time 11087.96 s 2025-04-02 16:33:32 | [pearl_trainer] epoch #69 | EpochTime 215.03 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -113.807 MetaTest/Average/AverageReturn -113.807 MetaTest/Average/Iteration 69 MetaTest/Average/MaxReturn -96.4703 MetaTest/Average/MinReturn -128.22 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.1256 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -113.807 MetaTest/__unnamed_task__/AverageReturn -113.807 MetaTest/__unnamed_task__/Iteration 69 MetaTest/__unnamed_task__/MaxReturn -96.4703 MetaTest/__unnamed_task__/MinReturn -128.22 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.1256 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 127000 ------------------------------------------------- ----------- 2025-04-02 16:33:55 | [pearl_trainer] epoch #70 | Training... 2025-04-02 16:35:23 | [pearl_trainer] epoch #70 | Evaluating... 2025-04-02 16:35:23 | [pearl_trainer] epoch #70 | Sampling for adapation and meta-testing... 2025-04-02 16:36:12 | [pearl_trainer] epoch #70 | Finished meta-testing... 2025-04-02 16:36:12 | [pearl_trainer] epoch #70 | Saving snapshot... 2025-04-02 16:36:13 | [pearl_trainer] epoch #70 | Saved 2025-04-02 16:36:13 | [pearl_trainer] epoch #70 | Time 11249.40 s 2025-04-02 16:36:13 | [pearl_trainer] epoch #70 | EpochTime 161.44 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -110.365 MetaTest/Average/AverageReturn -110.365 MetaTest/Average/Iteration 70 MetaTest/Average/MaxReturn -106.823 MetaTest/Average/MinReturn -116.963 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.67013 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -110.365 MetaTest/__unnamed_task__/AverageReturn -110.365 MetaTest/__unnamed_task__/Iteration 70 MetaTest/__unnamed_task__/MaxReturn -106.823 MetaTest/__unnamed_task__/MinReturn -116.963 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.67013 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 128600 ------------------------------------------------- ------------ 2025-04-02 16:36:35 | [pearl_trainer] epoch #71 | Training... 2025-04-02 16:37:59 | [pearl_trainer] epoch #71 | Evaluating... 2025-04-02 16:37:59 | [pearl_trainer] epoch #71 | Sampling for adapation and meta-testing... 2025-04-02 16:38:53 | [pearl_trainer] epoch #71 | Finished meta-testing... 2025-04-02 16:38:53 | [pearl_trainer] epoch #71 | Saving snapshot... 2025-04-02 16:38:55 | [pearl_trainer] epoch #71 | Saved 2025-04-02 16:38:55 | [pearl_trainer] epoch #71 | Time 11410.82 s 2025-04-02 16:38:55 | [pearl_trainer] epoch #71 | EpochTime 161.42 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -148.26 MetaTest/Average/AverageReturn -148.26 MetaTest/Average/Iteration 71 MetaTest/Average/MaxReturn -134.876 MetaTest/Average/MinReturn -158.224 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.83379 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -148.26 MetaTest/__unnamed_task__/AverageReturn -148.26 MetaTest/__unnamed_task__/Iteration 71 MetaTest/__unnamed_task__/MaxReturn -134.876 MetaTest/__unnamed_task__/MinReturn -158.224 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.83379 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 130200 ------------------------------------------------- ------------ 2025-04-02 16:39:17 | [pearl_trainer] epoch #72 | Training... 2025-04-02 16:40:42 | [pearl_trainer] epoch #72 | Evaluating... 2025-04-02 16:40:42 | [pearl_trainer] epoch #72 | Sampling for adapation and meta-testing... 2025-04-02 16:41:29 | [pearl_trainer] epoch #72 | Finished meta-testing... 2025-04-02 16:41:29 | [pearl_trainer] epoch #72 | Saving snapshot... 2025-04-02 16:41:30 | [pearl_trainer] epoch #72 | Saved 2025-04-02 16:41:30 | [pearl_trainer] epoch #72 | Time 11565.88 s 2025-04-02 16:41:30 | [pearl_trainer] epoch #72 | EpochTime 155.05 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -109.22 MetaTest/Average/AverageReturn -109.22 MetaTest/Average/Iteration 72 MetaTest/Average/MaxReturn -104.634 MetaTest/Average/MinReturn -117.459 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.83805 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -109.22 MetaTest/__unnamed_task__/AverageReturn -109.22 MetaTest/__unnamed_task__/Iteration 72 MetaTest/__unnamed_task__/MaxReturn -104.634 MetaTest/__unnamed_task__/MinReturn -117.459 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.83805 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 131800 ------------------------------------------------- ------------ 2025-04-02 16:41:52 | [pearl_trainer] epoch #73 | Training... 2025-04-02 16:43:25 | [pearl_trainer] epoch #73 | Evaluating... 2025-04-02 16:43:25 | [pearl_trainer] epoch #73 | Sampling for adapation and meta-testing... 2025-04-02 16:44:09 | [pearl_trainer] epoch #73 | Finished meta-testing... 2025-04-02 16:44:09 | [pearl_trainer] epoch #73 | Saving snapshot... 2025-04-02 16:44:11 | [pearl_trainer] epoch #73 | Saved 2025-04-02 16:44:11 | [pearl_trainer] epoch #73 | Time 11726.84 s 2025-04-02 16:44:11 | [pearl_trainer] epoch #73 | EpochTime 160.95 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -111.561 MetaTest/Average/AverageReturn -111.561 MetaTest/Average/Iteration 73 MetaTest/Average/MaxReturn -108.628 MetaTest/Average/MinReturn -114.769 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.51426 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.561 MetaTest/__unnamed_task__/AverageReturn -111.561 MetaTest/__unnamed_task__/Iteration 73 MetaTest/__unnamed_task__/MaxReturn -108.628 MetaTest/__unnamed_task__/MinReturn -114.769 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.51426 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 133400 ------------------------------------------------- ------------ 2025-04-02 16:44:32 | [pearl_trainer] epoch #74 | Training... 2025-04-02 16:46:18 | [pearl_trainer] epoch #74 | Evaluating... 2025-04-02 16:46:18 | [pearl_trainer] epoch #74 | Sampling for adapation and meta-testing... 2025-04-02 16:47:11 | [pearl_trainer] epoch #74 | Finished meta-testing... 2025-04-02 16:47:11 | [pearl_trainer] epoch #74 | Saving snapshot... 2025-04-02 16:47:12 | [pearl_trainer] epoch #74 | Saved 2025-04-02 16:47:12 | [pearl_trainer] epoch #74 | Time 11908.25 s 2025-04-02 16:47:12 | [pearl_trainer] epoch #74 | EpochTime 181.41 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -132.351 MetaTest/Average/AverageReturn -132.351 MetaTest/Average/Iteration 74 MetaTest/Average/MaxReturn -117.993 MetaTest/Average/MinReturn -156.937 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 17.4666 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -132.351 MetaTest/__unnamed_task__/AverageReturn -132.351 MetaTest/__unnamed_task__/Iteration 74 MetaTest/__unnamed_task__/MaxReturn -117.993 MetaTest/__unnamed_task__/MinReturn -156.937 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 17.4666 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 135000 ------------------------------------------------- ----------- 2025-04-02 16:47:34 | [pearl_trainer] epoch #75 | Training... 2025-04-02 16:49:01 | [pearl_trainer] epoch #75 | Evaluating... 2025-04-02 16:49:01 | [pearl_trainer] epoch #75 | Sampling for adapation and meta-testing... 2025-04-02 16:49:49 | [pearl_trainer] epoch #75 | Finished meta-testing... 2025-04-02 16:49:49 | [pearl_trainer] epoch #75 | Saving snapshot... 2025-04-02 16:49:50 | [pearl_trainer] epoch #75 | Saved 2025-04-02 16:49:50 | [pearl_trainer] epoch #75 | Time 12065.93 s 2025-04-02 16:49:50 | [pearl_trainer] epoch #75 | EpochTime 157.68 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -123.487 MetaTest/Average/AverageReturn -123.487 MetaTest/Average/Iteration 75 MetaTest/Average/MaxReturn -120.516 MetaTest/Average/MinReturn -125.94 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.24462 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -123.487 MetaTest/__unnamed_task__/AverageReturn -123.487 MetaTest/__unnamed_task__/Iteration 75 MetaTest/__unnamed_task__/MaxReturn -120.516 MetaTest/__unnamed_task__/MinReturn -125.94 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.24462 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 136600 ------------------------------------------------- ------------ 2025-04-02 16:50:13 | [pearl_trainer] epoch #76 | Training... 2025-04-02 16:51:40 | [pearl_trainer] epoch #76 | Evaluating... 2025-04-02 16:51:40 | [pearl_trainer] epoch #76 | Sampling for adapation and meta-testing... 2025-04-02 16:52:25 | [pearl_trainer] epoch #76 | Finished meta-testing... 2025-04-02 16:52:25 | [pearl_trainer] epoch #76 | Saving snapshot... 2025-04-02 16:52:27 | [pearl_trainer] epoch #76 | Saved 2025-04-02 16:52:27 | [pearl_trainer] epoch #76 | Time 12223.05 s 2025-04-02 16:52:27 | [pearl_trainer] epoch #76 | EpochTime 157.12 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -123.755 MetaTest/Average/AverageReturn -123.755 MetaTest/Average/Iteration 76 MetaTest/Average/MaxReturn -121.036 MetaTest/Average/MinReturn -128.368 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.27872 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -123.755 MetaTest/__unnamed_task__/AverageReturn -123.755 MetaTest/__unnamed_task__/Iteration 76 MetaTest/__unnamed_task__/MaxReturn -121.036 MetaTest/__unnamed_task__/MinReturn -128.368 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.27872 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 138200 ------------------------------------------------- ------------ 2025-04-02 16:52:49 | [pearl_trainer] epoch #77 | Training... 2025-04-02 16:54:26 | [pearl_trainer] epoch #77 | Evaluating... 2025-04-02 16:54:26 | [pearl_trainer] epoch #77 | Sampling for adapation and meta-testing... 2025-04-02 16:55:13 | [pearl_trainer] epoch #77 | Finished meta-testing... 2025-04-02 16:55:13 | [pearl_trainer] epoch #77 | Saving snapshot... 2025-04-02 16:55:14 | [pearl_trainer] epoch #77 | Saved 2025-04-02 16:55:14 | [pearl_trainer] epoch #77 | Time 12390.64 s 2025-04-02 16:55:14 | [pearl_trainer] epoch #77 | EpochTime 167.59 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -118.503 MetaTest/Average/AverageReturn -118.503 MetaTest/Average/Iteration 77 MetaTest/Average/MaxReturn -116.667 MetaTest/Average/MinReturn -120.211 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.44974 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -118.503 MetaTest/__unnamed_task__/AverageReturn -118.503 MetaTest/__unnamed_task__/Iteration 77 MetaTest/__unnamed_task__/MaxReturn -116.667 MetaTest/__unnamed_task__/MinReturn -120.211 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.44974 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 139800 ------------------------------------------------- ------------ 2025-04-02 16:55:36 | [pearl_trainer] epoch #78 | Training... 2025-04-02 16:56:59 | [pearl_trainer] epoch #78 | Evaluating... 2025-04-02 16:56:59 | [pearl_trainer] epoch #78 | Sampling for adapation and meta-testing... 2025-04-02 16:57:50 | [pearl_trainer] epoch #78 | Finished meta-testing... 2025-04-02 16:57:50 | [pearl_trainer] epoch #78 | Saving snapshot... 2025-04-02 16:57:51 | [pearl_trainer] epoch #78 | Saved 2025-04-02 16:57:51 | [pearl_trainer] epoch #78 | Time 12547.10 s 2025-04-02 16:57:51 | [pearl_trainer] epoch #78 | EpochTime 156.46 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -129.682 MetaTest/Average/AverageReturn -129.682 MetaTest/Average/Iteration 78 MetaTest/Average/MaxReturn -115.274 MetaTest/Average/MinReturn -138.504 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.2734 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -129.682 MetaTest/__unnamed_task__/AverageReturn -129.682 MetaTest/__unnamed_task__/Iteration 78 MetaTest/__unnamed_task__/MaxReturn -115.274 MetaTest/__unnamed_task__/MinReturn -138.504 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.2734 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 141400 ------------------------------------------------- ----------- 2025-04-02 16:58:14 | [pearl_trainer] epoch #79 | Training... 2025-04-02 16:59:42 | [pearl_trainer] epoch #79 | Evaluating... 2025-04-02 16:59:42 | [pearl_trainer] epoch #79 | Sampling for adapation and meta-testing... 2025-04-02 17:00:27 | [pearl_trainer] epoch #79 | Finished meta-testing... 2025-04-02 17:00:27 | [pearl_trainer] epoch #79 | Saving snapshot... 2025-04-02 17:00:28 | [pearl_trainer] epoch #79 | Saved 2025-04-02 17:00:28 | [pearl_trainer] epoch #79 | Time 12704.66 s 2025-04-02 17:00:28 | [pearl_trainer] epoch #79 | EpochTime 157.55 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -124.913 MetaTest/Average/AverageReturn -124.913 MetaTest/Average/Iteration 79 MetaTest/Average/MaxReturn -121.558 MetaTest/Average/MinReturn -128.496 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.83699 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -124.913 MetaTest/__unnamed_task__/AverageReturn -124.913 MetaTest/__unnamed_task__/Iteration 79 MetaTest/__unnamed_task__/MaxReturn -121.558 MetaTest/__unnamed_task__/MinReturn -128.496 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.83699 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 143000 ------------------------------------------------- ------------ 2025-04-02 17:00:51 | [pearl_trainer] epoch #80 | Training... 2025-04-02 17:02:28 | [pearl_trainer] epoch #80 | Evaluating... 2025-04-02 17:02:28 | [pearl_trainer] epoch #80 | Sampling for adapation and meta-testing... 2025-04-02 17:03:14 | [pearl_trainer] epoch #80 | Finished meta-testing... 2025-04-02 17:03:14 | [pearl_trainer] epoch #80 | Saving snapshot... 2025-04-02 17:03:15 | [pearl_trainer] epoch #80 | Saved 2025-04-02 17:03:15 | [pearl_trainer] epoch #80 | Time 12871.27 s 2025-04-02 17:03:15 | [pearl_trainer] epoch #80 | EpochTime 166.62 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -137.038 MetaTest/Average/AverageReturn -137.038 MetaTest/Average/Iteration 80 MetaTest/Average/MaxReturn -120.334 MetaTest/Average/MinReturn -147.999 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.002 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -137.038 MetaTest/__unnamed_task__/AverageReturn -137.038 MetaTest/__unnamed_task__/Iteration 80 MetaTest/__unnamed_task__/MaxReturn -120.334 MetaTest/__unnamed_task__/MinReturn -147.999 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.002 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 144600 ------------------------------------------------- ---------- 2025-04-02 17:03:37 | [pearl_trainer] epoch #81 | Training... 2025-04-02 17:05:02 | [pearl_trainer] epoch #81 | Evaluating... 2025-04-02 17:05:02 | [pearl_trainer] epoch #81 | Sampling for adapation and meta-testing... 2025-04-02 17:05:51 | [pearl_trainer] epoch #81 | Finished meta-testing... 2025-04-02 17:05:51 | [pearl_trainer] epoch #81 | Saving snapshot... 2025-04-02 17:05:53 | [pearl_trainer] epoch #81 | Saved 2025-04-02 17:05:53 | [pearl_trainer] epoch #81 | Time 13028.98 s 2025-04-02 17:05:53 | [pearl_trainer] epoch #81 | EpochTime 157.70 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -125.351 MetaTest/Average/AverageReturn -125.351 MetaTest/Average/Iteration 81 MetaTest/Average/MaxReturn -115.846 MetaTest/Average/MinReturn -131.046 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.76497 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -125.351 MetaTest/__unnamed_task__/AverageReturn -125.351 MetaTest/__unnamed_task__/Iteration 81 MetaTest/__unnamed_task__/MaxReturn -115.846 MetaTest/__unnamed_task__/MinReturn -131.046 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.76497 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 146200 ------------------------------------------------- ------------ 2025-04-02 17:06:16 | [pearl_trainer] epoch #82 | Training... 2025-04-02 17:07:44 | [pearl_trainer] epoch #82 | Evaluating... 2025-04-02 17:07:44 | [pearl_trainer] epoch #82 | Sampling for adapation and meta-testing... 2025-04-02 17:08:27 | [pearl_trainer] epoch #82 | Finished meta-testing... 2025-04-02 17:08:27 | [pearl_trainer] epoch #82 | Saving snapshot... 2025-04-02 17:08:28 | [pearl_trainer] epoch #82 | Saved 2025-04-02 17:08:28 | [pearl_trainer] epoch #82 | Time 13184.52 s 2025-04-02 17:08:28 | [pearl_trainer] epoch #82 | EpochTime 155.54 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -135.684 MetaTest/Average/AverageReturn -135.684 MetaTest/Average/Iteration 82 MetaTest/Average/MaxReturn -127.035 MetaTest/Average/MinReturn -142.521 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.45079 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -135.684 MetaTest/__unnamed_task__/AverageReturn -135.684 MetaTest/__unnamed_task__/Iteration 82 MetaTest/__unnamed_task__/MaxReturn -127.035 MetaTest/__unnamed_task__/MinReturn -142.521 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.45079 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 147800 ------------------------------------------------- ------------ 2025-04-02 17:08:49 | [pearl_trainer] epoch #83 | Training... 2025-04-02 17:10:21 | [pearl_trainer] epoch #83 | Evaluating... 2025-04-02 17:10:21 | [pearl_trainer] epoch #83 | Sampling for adapation and meta-testing... 2025-04-02 17:11:05 | [pearl_trainer] epoch #83 | Finished meta-testing... 2025-04-02 17:11:05 | [pearl_trainer] epoch #83 | Saving snapshot... 2025-04-02 17:11:06 | [pearl_trainer] epoch #83 | Saved 2025-04-02 17:11:06 | [pearl_trainer] epoch #83 | Time 13342.69 s 2025-04-02 17:11:06 | [pearl_trainer] epoch #83 | EpochTime 158.17 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -119.545 MetaTest/Average/AverageReturn -119.545 MetaTest/Average/Iteration 83 MetaTest/Average/MaxReturn -114.162 MetaTest/Average/MinReturn -129.871 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.30343 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -119.545 MetaTest/__unnamed_task__/AverageReturn -119.545 MetaTest/__unnamed_task__/Iteration 83 MetaTest/__unnamed_task__/MaxReturn -114.162 MetaTest/__unnamed_task__/MinReturn -129.871 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.30343 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 149400 ------------------------------------------------- ------------ 2025-04-02 17:11:28 | [pearl_trainer] epoch #84 | Training... 2025-04-02 17:12:56 | [pearl_trainer] epoch #84 | Evaluating... 2025-04-02 17:12:56 | [pearl_trainer] epoch #84 | Sampling for adapation and meta-testing... 2025-04-02 17:13:47 | [pearl_trainer] epoch #84 | Finished meta-testing... 2025-04-02 17:13:47 | [pearl_trainer] epoch #84 | Saving snapshot... 2025-04-02 17:13:48 | [pearl_trainer] epoch #84 | Saved 2025-04-02 17:13:48 | [pearl_trainer] epoch #84 | Time 13504.39 s 2025-04-02 17:13:48 | [pearl_trainer] epoch #84 | EpochTime 161.69 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -114.476 MetaTest/Average/AverageReturn -114.476 MetaTest/Average/Iteration 84 MetaTest/Average/MaxReturn -105.523 MetaTest/Average/MinReturn -126.474 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.82049 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -114.476 MetaTest/__unnamed_task__/AverageReturn -114.476 MetaTest/__unnamed_task__/Iteration 84 MetaTest/__unnamed_task__/MaxReturn -105.523 MetaTest/__unnamed_task__/MinReturn -126.474 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.82049 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 151000 ------------------------------------------------- ------------ 2025-04-02 17:14:12 | [pearl_trainer] epoch #85 | Training... 2025-04-02 17:15:37 | [pearl_trainer] epoch #85 | Evaluating... 2025-04-02 17:15:37 | [pearl_trainer] epoch #85 | Sampling for adapation and meta-testing... 2025-04-02 17:16:22 | [pearl_trainer] epoch #85 | Finished meta-testing... 2025-04-02 17:16:22 | [pearl_trainer] epoch #85 | Saving snapshot... 2025-04-02 17:16:23 | [pearl_trainer] epoch #85 | Saved 2025-04-02 17:16:23 | [pearl_trainer] epoch #85 | Time 13659.28 s 2025-04-02 17:16:23 | [pearl_trainer] epoch #85 | EpochTime 154.90 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -98.1487 MetaTest/Average/AverageReturn -98.1487 MetaTest/Average/Iteration 85 MetaTest/Average/MaxReturn -84.7079 MetaTest/Average/MinReturn -104.883 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.50406 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.1487 MetaTest/__unnamed_task__/AverageReturn -98.1487 MetaTest/__unnamed_task__/Iteration 85 MetaTest/__unnamed_task__/MaxReturn -84.7079 MetaTest/__unnamed_task__/MinReturn -104.883 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.50406 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 152600 ------------------------------------------------- ------------ 2025-04-02 17:16:46 | [pearl_trainer] epoch #86 | Training... 2025-04-02 17:18:27 | [pearl_trainer] epoch #86 | Evaluating... 2025-04-02 17:18:27 | [pearl_trainer] epoch #86 | Sampling for adapation and meta-testing... 2025-04-02 17:19:21 | [pearl_trainer] epoch #86 | Finished meta-testing... 2025-04-02 17:19:21 | [pearl_trainer] epoch #86 | Saving snapshot... 2025-04-02 17:19:23 | [pearl_trainer] epoch #86 | Saved 2025-04-02 17:19:23 | [pearl_trainer] epoch #86 | Time 13838.74 s 2025-04-02 17:19:23 | [pearl_trainer] epoch #86 | EpochTime 179.46 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -107.967 MetaTest/Average/AverageReturn -107.967 MetaTest/Average/Iteration 86 MetaTest/Average/MaxReturn -100.044 MetaTest/Average/MinReturn -122.178 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.0704 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -107.967 MetaTest/__unnamed_task__/AverageReturn -107.967 MetaTest/__unnamed_task__/Iteration 86 MetaTest/__unnamed_task__/MaxReturn -100.044 MetaTest/__unnamed_task__/MinReturn -122.178 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.0704 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 154200 ------------------------------------------------- ----------- 2025-04-02 17:19:49 | [pearl_trainer] epoch #87 | Training... 2025-04-02 17:21:24 | [pearl_trainer] epoch #87 | Evaluating... 2025-04-02 17:21:24 | [pearl_trainer] epoch #87 | Sampling for adapation and meta-testing... 2025-04-02 17:22:17 | [pearl_trainer] epoch #87 | Finished meta-testing... 2025-04-02 17:22:17 | [pearl_trainer] epoch #87 | Saving snapshot... 2025-04-02 17:22:18 | [pearl_trainer] epoch #87 | Saved 2025-04-02 17:22:18 | [pearl_trainer] epoch #87 | Time 14013.93 s 2025-04-02 17:22:18 | [pearl_trainer] epoch #87 | EpochTime 175.18 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -113.995 MetaTest/Average/AverageReturn -113.995 MetaTest/Average/Iteration 87 MetaTest/Average/MaxReturn -98.7631 MetaTest/Average/MinReturn -128.167 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.0276 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -113.995 MetaTest/__unnamed_task__/AverageReturn -113.995 MetaTest/__unnamed_task__/Iteration 87 MetaTest/__unnamed_task__/MaxReturn -98.7631 MetaTest/__unnamed_task__/MinReturn -128.167 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.0276 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 155800 ------------------------------------------------- ----------- 2025-04-02 17:22:40 | [pearl_trainer] epoch #88 | Training... 2025-04-02 17:24:03 | [pearl_trainer] epoch #88 | Evaluating... 2025-04-02 17:24:03 | [pearl_trainer] epoch #88 | Sampling for adapation and meta-testing... 2025-04-02 17:24:51 | [pearl_trainer] epoch #88 | Finished meta-testing... 2025-04-02 17:24:51 | [pearl_trainer] epoch #88 | Saving snapshot... 2025-04-02 17:24:52 | [pearl_trainer] epoch #88 | Saved 2025-04-02 17:24:52 | [pearl_trainer] epoch #88 | Time 14167.86 s 2025-04-02 17:24:52 | [pearl_trainer] epoch #88 | EpochTime 153.93 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -127.171 MetaTest/Average/AverageReturn -127.171 MetaTest/Average/Iteration 88 MetaTest/Average/MaxReturn -121.097 MetaTest/Average/MinReturn -131.011 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.34485 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -127.171 MetaTest/__unnamed_task__/AverageReturn -127.171 MetaTest/__unnamed_task__/Iteration 88 MetaTest/__unnamed_task__/MaxReturn -121.097 MetaTest/__unnamed_task__/MinReturn -131.011 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.34485 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 157400 ------------------------------------------------- ------------ 2025-04-02 17:25:15 | [pearl_trainer] epoch #89 | Training... 2025-04-02 17:26:48 | [pearl_trainer] epoch #89 | Evaluating... 2025-04-02 17:26:48 | [pearl_trainer] epoch #89 | Sampling for adapation and meta-testing... 2025-04-02 17:27:34 | [pearl_trainer] epoch #89 | Finished meta-testing... 2025-04-02 17:27:34 | [pearl_trainer] epoch #89 | Saving snapshot... 2025-04-02 17:27:35 | [pearl_trainer] epoch #89 | Saved 2025-04-02 17:27:35 | [pearl_trainer] epoch #89 | Time 14331.33 s 2025-04-02 17:27:35 | [pearl_trainer] epoch #89 | EpochTime 163.47 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -114.323 MetaTest/Average/AverageReturn -114.323 MetaTest/Average/Iteration 89 MetaTest/Average/MaxReturn -111.855 MetaTest/Average/MinReturn -117.855 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.56243 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -114.323 MetaTest/__unnamed_task__/AverageReturn -114.323 MetaTest/__unnamed_task__/Iteration 89 MetaTest/__unnamed_task__/MaxReturn -111.855 MetaTest/__unnamed_task__/MinReturn -117.855 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.56243 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 159000 ------------------------------------------------- ------------ 2025-04-02 17:27:57 | [pearl_trainer] epoch #90 | Training... 2025-04-02 17:29:31 | [pearl_trainer] epoch #90 | Evaluating... 2025-04-02 17:29:31 | [pearl_trainer] epoch #90 | Sampling for adapation and meta-testing... 2025-04-02 17:30:20 | [pearl_trainer] epoch #90 | Finished meta-testing... 2025-04-02 17:30:20 | [pearl_trainer] epoch #90 | Saving snapshot... 2025-04-02 17:30:21 | [pearl_trainer] epoch #90 | Saved 2025-04-02 17:30:21 | [pearl_trainer] epoch #90 | Time 14497.41 s 2025-04-02 17:30:21 | [pearl_trainer] epoch #90 | EpochTime 166.08 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -111.116 MetaTest/Average/AverageReturn -111.116 MetaTest/Average/Iteration 90 MetaTest/Average/MaxReturn -93.1731 MetaTest/Average/MinReturn -122.606 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.8531 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.116 MetaTest/__unnamed_task__/AverageReturn -111.116 MetaTest/__unnamed_task__/Iteration 90 MetaTest/__unnamed_task__/MaxReturn -93.1731 MetaTest/__unnamed_task__/MinReturn -122.606 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.8531 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 160600 ------------------------------------------------- ----------- 2025-04-02 17:30:43 | [pearl_trainer] epoch #91 | Training... 2025-04-02 17:32:08 | [pearl_trainer] epoch #91 | Evaluating... 2025-04-02 17:32:08 | [pearl_trainer] epoch #91 | Sampling for adapation and meta-testing... 2025-04-02 17:32:53 | [pearl_trainer] epoch #91 | Finished meta-testing... 2025-04-02 17:32:53 | [pearl_trainer] epoch #91 | Saving snapshot... 2025-04-02 17:32:55 | [pearl_trainer] epoch #91 | Saved 2025-04-02 17:32:55 | [pearl_trainer] epoch #91 | Time 14650.71 s 2025-04-02 17:32:55 | [pearl_trainer] epoch #91 | EpochTime 153.29 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -132.727 MetaTest/Average/AverageReturn -132.727 MetaTest/Average/Iteration 91 MetaTest/Average/MaxReturn -111.372 MetaTest/Average/MinReturn -155.861 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 18.2064 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -132.727 MetaTest/__unnamed_task__/AverageReturn -132.727 MetaTest/__unnamed_task__/Iteration 91 MetaTest/__unnamed_task__/MaxReturn -111.372 MetaTest/__unnamed_task__/MinReturn -155.861 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 18.2064 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 162200 ------------------------------------------------- ----------- 2025-04-02 17:33:16 | [pearl_trainer] epoch #92 | Training... 2025-04-02 17:34:49 | [pearl_trainer] epoch #92 | Evaluating... 2025-04-02 17:34:49 | [pearl_trainer] epoch #92 | Sampling for adapation and meta-testing... 2025-04-02 17:35:34 | [pearl_trainer] epoch #92 | Finished meta-testing... 2025-04-02 17:35:34 | [pearl_trainer] epoch #92 | Saving snapshot... 2025-04-02 17:35:35 | [pearl_trainer] epoch #92 | Saved 2025-04-02 17:35:35 | [pearl_trainer] epoch #92 | Time 14810.76 s 2025-04-02 17:35:35 | [pearl_trainer] epoch #92 | EpochTime 160.05 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -138.557 MetaTest/Average/AverageReturn -138.557 MetaTest/Average/Iteration 92 MetaTest/Average/MaxReturn -112.49 MetaTest/Average/MinReturn -158.386 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 19.2492 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -138.557 MetaTest/__unnamed_task__/AverageReturn -138.557 MetaTest/__unnamed_task__/Iteration 92 MetaTest/__unnamed_task__/MaxReturn -112.49 MetaTest/__unnamed_task__/MinReturn -158.386 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 19.2492 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 163800 ------------------------------------------------- ----------- 2025-04-02 17:35:55 | [pearl_trainer] epoch #93 | Training... 2025-04-02 17:37:24 | [pearl_trainer] epoch #93 | Evaluating... 2025-04-02 17:37:24 | [pearl_trainer] epoch #93 | Sampling for adapation and meta-testing... 2025-04-02 17:38:12 | [pearl_trainer] epoch #93 | Finished meta-testing... 2025-04-02 17:38:12 | [pearl_trainer] epoch #93 | Saving snapshot... 2025-04-02 17:38:13 | [pearl_trainer] epoch #93 | Saved 2025-04-02 17:38:13 | [pearl_trainer] epoch #93 | Time 14969.68 s 2025-04-02 17:38:13 | [pearl_trainer] epoch #93 | EpochTime 158.92 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -133.375 MetaTest/Average/AverageReturn -133.375 MetaTest/Average/Iteration 93 MetaTest/Average/MaxReturn -121.963 MetaTest/Average/MinReturn -144.881 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.3564 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -133.375 MetaTest/__unnamed_task__/AverageReturn -133.375 MetaTest/__unnamed_task__/Iteration 93 MetaTest/__unnamed_task__/MaxReturn -121.963 MetaTest/__unnamed_task__/MinReturn -144.881 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.3564 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 165400 ------------------------------------------------- ----------- 2025-04-02 17:38:35 | [pearl_trainer] epoch #94 | Training... 2025-04-02 17:40:00 | [pearl_trainer] epoch #94 | Evaluating... 2025-04-02 17:40:00 | [pearl_trainer] epoch #94 | Sampling for adapation and meta-testing... 2025-04-02 17:40:47 | [pearl_trainer] epoch #94 | Finished meta-testing... 2025-04-02 17:40:47 | [pearl_trainer] epoch #94 | Saving snapshot... 2025-04-02 17:40:48 | [pearl_trainer] epoch #94 | Saved 2025-04-02 17:40:48 | [pearl_trainer] epoch #94 | Time 15124.22 s 2025-04-02 17:40:48 | [pearl_trainer] epoch #94 | EpochTime 154.53 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -153.711 MetaTest/Average/AverageReturn -153.711 MetaTest/Average/Iteration 94 MetaTest/Average/MaxReturn -142.256 MetaTest/Average/MinReturn -174.255 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.5588 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -153.711 MetaTest/__unnamed_task__/AverageReturn -153.711 MetaTest/__unnamed_task__/Iteration 94 MetaTest/__unnamed_task__/MaxReturn -142.256 MetaTest/__unnamed_task__/MinReturn -174.255 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.5588 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 167000 ------------------------------------------------- ----------- 2025-04-02 17:41:11 | [pearl_trainer] epoch #95 | Training... 2025-04-02 17:42:41 | [pearl_trainer] epoch #95 | Evaluating... 2025-04-02 17:42:41 | [pearl_trainer] epoch #95 | Sampling for adapation and meta-testing... 2025-04-02 17:43:26 | [pearl_trainer] epoch #95 | Finished meta-testing... 2025-04-02 17:43:26 | [pearl_trainer] epoch #95 | Saving snapshot... 2025-04-02 17:43:27 | [pearl_trainer] epoch #95 | Saved 2025-04-02 17:43:27 | [pearl_trainer] epoch #95 | Time 15283.12 s 2025-04-02 17:43:27 | [pearl_trainer] epoch #95 | EpochTime 158.90 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -121.715 MetaTest/Average/AverageReturn -121.715 MetaTest/Average/Iteration 95 MetaTest/Average/MaxReturn -115.059 MetaTest/Average/MinReturn -130.583 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.52783 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -121.715 MetaTest/__unnamed_task__/AverageReturn -121.715 MetaTest/__unnamed_task__/Iteration 95 MetaTest/__unnamed_task__/MaxReturn -115.059 MetaTest/__unnamed_task__/MinReturn -130.583 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.52783 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 168600 ------------------------------------------------- ------------ 2025-04-02 17:43:49 | [pearl_trainer] epoch #96 | Training... 2025-04-02 17:45:17 | [pearl_trainer] epoch #96 | Evaluating... 2025-04-02 17:45:17 | [pearl_trainer] epoch #96 | Sampling for adapation and meta-testing... 2025-04-02 17:46:09 | [pearl_trainer] epoch #96 | Finished meta-testing... 2025-04-02 17:46:09 | [pearl_trainer] epoch #96 | Saving snapshot... 2025-04-02 17:46:11 | [pearl_trainer] epoch #96 | Saved 2025-04-02 17:46:11 | [pearl_trainer] epoch #96 | Time 15446.74 s 2025-04-02 17:46:11 | [pearl_trainer] epoch #96 | EpochTime 163.62 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -123.896 MetaTest/Average/AverageReturn -123.896 MetaTest/Average/Iteration 96 MetaTest/Average/MaxReturn -98.42 MetaTest/Average/MinReturn -149.505 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 20.8556 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -123.896 MetaTest/__unnamed_task__/AverageReturn -123.896 MetaTest/__unnamed_task__/Iteration 96 MetaTest/__unnamed_task__/MaxReturn -98.42 MetaTest/__unnamed_task__/MinReturn -149.505 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 20.8556 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 170200 ------------------------------------------------- ----------- 2025-04-02 17:46:33 | [pearl_trainer] epoch #97 | Training... 2025-04-02 17:47:55 | [pearl_trainer] epoch #97 | Evaluating... 2025-04-02 17:47:55 | [pearl_trainer] epoch #97 | Sampling for adapation and meta-testing... 2025-04-02 17:48:45 | [pearl_trainer] epoch #97 | Finished meta-testing... 2025-04-02 17:48:45 | [pearl_trainer] epoch #97 | Saving snapshot... 2025-04-02 17:48:46 | [pearl_trainer] epoch #97 | Saved 2025-04-02 17:48:46 | [pearl_trainer] epoch #97 | Time 15602.06 s 2025-04-02 17:48:46 | [pearl_trainer] epoch #97 | EpochTime 155.32 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -128.847 MetaTest/Average/AverageReturn -128.847 MetaTest/Average/Iteration 97 MetaTest/Average/MaxReturn -112.325 MetaTest/Average/MinReturn -137.613 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.6901 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -128.847 MetaTest/__unnamed_task__/AverageReturn -128.847 MetaTest/__unnamed_task__/Iteration 97 MetaTest/__unnamed_task__/MaxReturn -112.325 MetaTest/__unnamed_task__/MinReturn -137.613 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.6901 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 171800 ------------------------------------------------- ----------- 2025-04-02 17:49:09 | [pearl_trainer] epoch #98 | Training... 2025-04-02 17:50:44 | [pearl_trainer] epoch #98 | Evaluating... 2025-04-02 17:50:44 | [pearl_trainer] epoch #98 | Sampling for adapation and meta-testing... 2025-04-02 17:51:34 | [pearl_trainer] epoch #98 | Finished meta-testing... 2025-04-02 17:51:34 | [pearl_trainer] epoch #98 | Saving snapshot... 2025-04-02 17:51:35 | [pearl_trainer] epoch #98 | Saved 2025-04-02 17:51:35 | [pearl_trainer] epoch #98 | Time 15770.77 s 2025-04-02 17:51:35 | [pearl_trainer] epoch #98 | EpochTime 168.70 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -153.442 MetaTest/Average/AverageReturn -153.442 MetaTest/Average/Iteration 98 MetaTest/Average/MaxReturn -147.854 MetaTest/Average/MinReturn -157.981 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.20065 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -153.442 MetaTest/__unnamed_task__/AverageReturn -153.442 MetaTest/__unnamed_task__/Iteration 98 MetaTest/__unnamed_task__/MaxReturn -147.854 MetaTest/__unnamed_task__/MinReturn -157.981 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.20065 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 173400 ------------------------------------------------- ------------ 2025-04-02 17:51:57 | [pearl_trainer] epoch #99 | Training... 2025-04-02 17:53:28 | [pearl_trainer] epoch #99 | Evaluating... 2025-04-02 17:53:28 | [pearl_trainer] epoch #99 | Sampling for adapation and meta-testing... 2025-04-02 17:54:20 | [pearl_trainer] epoch #99 | Finished meta-testing... 2025-04-02 17:54:20 | [pearl_trainer] epoch #99 | Saving snapshot... 2025-04-02 17:54:21 | [pearl_trainer] epoch #99 | Saved 2025-04-02 17:54:21 | [pearl_trainer] epoch #99 | Time 15937.06 s 2025-04-02 17:54:21 | [pearl_trainer] epoch #99 | EpochTime 166.29 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -104.221 MetaTest/Average/AverageReturn -104.221 MetaTest/Average/Iteration 99 MetaTest/Average/MaxReturn -97.4797 MetaTest/Average/MinReturn -112.289 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.11815 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -104.221 MetaTest/__unnamed_task__/AverageReturn -104.221 MetaTest/__unnamed_task__/Iteration 99 MetaTest/__unnamed_task__/MaxReturn -97.4797 MetaTest/__unnamed_task__/MinReturn -112.289 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.11815 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 175000 ------------------------------------------------- ------------ 2025-04-02 17:54:43 | [pearl_trainer] epoch #100 | Training... 2025-04-02 17:56:06 | [pearl_trainer] epoch #100 | Evaluating... 2025-04-02 17:56:06 | [pearl_trainer] epoch #100 | Sampling for adapation and meta-testing... 2025-04-02 17:56:57 | [pearl_trainer] epoch #100 | Finished meta-testing... 2025-04-02 17:56:57 | [pearl_trainer] epoch #100 | Saving snapshot... 2025-04-02 17:56:58 | [pearl_trainer] epoch #100 | Saved 2025-04-02 17:56:58 | [pearl_trainer] epoch #100 | Time 16094.62 s 2025-04-02 17:56:58 | [pearl_trainer] epoch #100 | EpochTime 157.56 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -124.593 MetaTest/Average/AverageReturn -124.593 MetaTest/Average/Iteration 100 MetaTest/Average/MaxReturn -120.098 MetaTest/Average/MinReturn -127.837 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.28091 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -124.593 MetaTest/__unnamed_task__/AverageReturn -124.593 MetaTest/__unnamed_task__/Iteration 100 MetaTest/__unnamed_task__/MaxReturn -120.098 MetaTest/__unnamed_task__/MinReturn -127.837 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.28091 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 176600 ------------------------------------------------- ------------ 2025-04-02 17:57:25 | [pearl_trainer] epoch #101 | Training... 2025-04-02 17:58:53 | [pearl_trainer] epoch #101 | Evaluating... 2025-04-02 17:58:53 | [pearl_trainer] epoch #101 | Sampling for adapation and meta-testing... 2025-04-02 17:59:39 | [pearl_trainer] epoch #101 | Finished meta-testing... 2025-04-02 17:59:39 | [pearl_trainer] epoch #101 | Saving snapshot... 2025-04-02 17:59:40 | [pearl_trainer] epoch #101 | Saved 2025-04-02 17:59:40 | [pearl_trainer] epoch #101 | Time 16256.59 s 2025-04-02 17:59:40 | [pearl_trainer] epoch #101 | EpochTime 161.97 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -122.162 MetaTest/Average/AverageReturn -122.162 MetaTest/Average/Iteration 101 MetaTest/Average/MaxReturn -105.581 MetaTest/Average/MinReturn -137.956 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.2289 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -122.162 MetaTest/__unnamed_task__/AverageReturn -122.162 MetaTest/__unnamed_task__/Iteration 101 MetaTest/__unnamed_task__/MaxReturn -105.581 MetaTest/__unnamed_task__/MinReturn -137.956 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.2289 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 178200 ------------------------------------------------- ----------- 2025-04-02 18:00:04 | [pearl_trainer] epoch #102 | Training... 2025-04-02 18:01:33 | [pearl_trainer] epoch #102 | Evaluating... 2025-04-02 18:01:33 | [pearl_trainer] epoch #102 | Sampling for adapation and meta-testing... 2025-04-02 18:02:19 | [pearl_trainer] epoch #102 | Finished meta-testing... 2025-04-02 18:02:19 | [pearl_trainer] epoch #102 | Saving snapshot... 2025-04-02 18:02:20 | [pearl_trainer] epoch #102 | Saved 2025-04-02 18:02:20 | [pearl_trainer] epoch #102 | Time 16416.03 s 2025-04-02 18:02:20 | [pearl_trainer] epoch #102 | EpochTime 159.44 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -117.771 MetaTest/Average/AverageReturn -117.771 MetaTest/Average/Iteration 102 MetaTest/Average/MaxReturn -110.201 MetaTest/Average/MinReturn -126.013 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.47262 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -117.771 MetaTest/__unnamed_task__/AverageReturn -117.771 MetaTest/__unnamed_task__/Iteration 102 MetaTest/__unnamed_task__/MaxReturn -110.201 MetaTest/__unnamed_task__/MinReturn -126.013 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.47262 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 179800 ------------------------------------------------- ------------ 2025-04-02 18:02:42 | [pearl_trainer] epoch #103 | Training... 2025-04-02 18:04:17 | [pearl_trainer] epoch #103 | Evaluating... 2025-04-02 18:04:17 | [pearl_trainer] epoch #103 | Sampling for adapation and meta-testing... 2025-04-02 18:05:13 | [pearl_trainer] epoch #103 | Finished meta-testing... 2025-04-02 18:05:13 | [pearl_trainer] epoch #103 | Saving snapshot... 2025-04-02 18:05:14 | [pearl_trainer] epoch #103 | Saved 2025-04-02 18:05:14 | [pearl_trainer] epoch #103 | Time 16589.86 s 2025-04-02 18:05:14 | [pearl_trainer] epoch #103 | EpochTime 173.82 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -113.691 MetaTest/Average/AverageReturn -113.691 MetaTest/Average/Iteration 103 MetaTest/Average/MaxReturn -106.069 MetaTest/Average/MinReturn -118.646 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.46972 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -113.691 MetaTest/__unnamed_task__/AverageReturn -113.691 MetaTest/__unnamed_task__/Iteration 103 MetaTest/__unnamed_task__/MaxReturn -106.069 MetaTest/__unnamed_task__/MinReturn -118.646 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.46972 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 181400 ------------------------------------------------- ------------ 2025-04-02 18:05:38 | [pearl_trainer] epoch #104 | Training... 2025-04-02 18:07:00 | [pearl_trainer] epoch #104 | Evaluating... 2025-04-02 18:07:00 | [pearl_trainer] epoch #104 | Sampling for adapation and meta-testing... 2025-04-02 18:07:49 | [pearl_trainer] epoch #104 | Finished meta-testing... 2025-04-02 18:07:49 | [pearl_trainer] epoch #104 | Saving snapshot... 2025-04-02 18:07:50 | [pearl_trainer] epoch #104 | Saved 2025-04-02 18:07:50 | [pearl_trainer] epoch #104 | Time 16746.39 s 2025-04-02 18:07:50 | [pearl_trainer] epoch #104 | EpochTime 156.52 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -129.498 MetaTest/Average/AverageReturn -129.498 MetaTest/Average/Iteration 104 MetaTest/Average/MaxReturn -125.236 MetaTest/Average/MinReturn -136.34 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.88668 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -129.498 MetaTest/__unnamed_task__/AverageReturn -129.498 MetaTest/__unnamed_task__/Iteration 104 MetaTest/__unnamed_task__/MaxReturn -125.236 MetaTest/__unnamed_task__/MinReturn -136.34 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.88668 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 183000 ------------------------------------------------- ------------ 2025-04-02 18:08:13 | [pearl_trainer] epoch #105 | Training... 2025-04-02 18:09:47 | [pearl_trainer] epoch #105 | Evaluating... 2025-04-02 18:09:47 | [pearl_trainer] epoch #105 | Sampling for adapation and meta-testing... 2025-04-02 18:10:31 | [pearl_trainer] epoch #105 | Finished meta-testing... 2025-04-02 18:10:31 | [pearl_trainer] epoch #105 | Saving snapshot... 2025-04-02 18:10:32 | [pearl_trainer] epoch #105 | Saved 2025-04-02 18:10:32 | [pearl_trainer] epoch #105 | Time 16908.68 s 2025-04-02 18:10:32 | [pearl_trainer] epoch #105 | EpochTime 162.29 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -120.835 MetaTest/Average/AverageReturn -120.835 MetaTest/Average/Iteration 105 MetaTest/Average/MaxReturn -118.851 MetaTest/Average/MinReturn -123.813 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.14417 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -120.835 MetaTest/__unnamed_task__/AverageReturn -120.835 MetaTest/__unnamed_task__/Iteration 105 MetaTest/__unnamed_task__/MaxReturn -118.851 MetaTest/__unnamed_task__/MinReturn -123.813 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.14417 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 184600 ------------------------------------------------- ------------ 2025-04-02 18:10:54 | [pearl_trainer] epoch #106 | Training... 2025-04-02 18:12:24 | [pearl_trainer] epoch #106 | Evaluating... 2025-04-02 18:12:24 | [pearl_trainer] epoch #106 | Sampling for adapation and meta-testing... 2025-04-02 18:13:13 | [pearl_trainer] epoch #106 | Finished meta-testing... 2025-04-02 18:13:13 | [pearl_trainer] epoch #106 | Saving snapshot... 2025-04-02 18:13:14 | [pearl_trainer] epoch #106 | Saved 2025-04-02 18:13:14 | [pearl_trainer] epoch #106 | Time 17070.36 s 2025-04-02 18:13:14 | [pearl_trainer] epoch #106 | EpochTime 161.68 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -123.964 MetaTest/Average/AverageReturn -123.964 MetaTest/Average/Iteration 106 MetaTest/Average/MaxReturn -113.008 MetaTest/Average/MinReturn -129.938 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.75732 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -123.964 MetaTest/__unnamed_task__/AverageReturn -123.964 MetaTest/__unnamed_task__/Iteration 106 MetaTest/__unnamed_task__/MaxReturn -113.008 MetaTest/__unnamed_task__/MinReturn -129.938 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.75732 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 186200 ------------------------------------------------- ------------ 2025-04-02 18:13:36 | [pearl_trainer] epoch #107 | Training... 2025-04-02 18:14:59 | [pearl_trainer] epoch #107 | Evaluating... 2025-04-02 18:14:59 | [pearl_trainer] epoch #107 | Sampling for adapation and meta-testing... 2025-04-02 18:15:45 | [pearl_trainer] epoch #107 | Finished meta-testing... 2025-04-02 18:15:45 | [pearl_trainer] epoch #107 | Saving snapshot... 2025-04-02 18:15:47 | [pearl_trainer] epoch #107 | Saved 2025-04-02 18:15:47 | [pearl_trainer] epoch #107 | Time 17222.97 s 2025-04-02 18:15:47 | [pearl_trainer] epoch #107 | EpochTime 152.61 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -130.66 MetaTest/Average/AverageReturn -130.66 MetaTest/Average/Iteration 107 MetaTest/Average/MaxReturn -121.299 MetaTest/Average/MinReturn -141.495 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.31084 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -130.66 MetaTest/__unnamed_task__/AverageReturn -130.66 MetaTest/__unnamed_task__/Iteration 107 MetaTest/__unnamed_task__/MaxReturn -121.299 MetaTest/__unnamed_task__/MinReturn -141.495 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.31084 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 187800 ------------------------------------------------- ------------ 2025-04-02 18:16:10 | [pearl_trainer] epoch #108 | Training... 2025-04-02 18:17:46 | [pearl_trainer] epoch #108 | Evaluating... 2025-04-02 18:17:46 | [pearl_trainer] epoch #108 | Sampling for adapation and meta-testing... 2025-04-02 18:18:31 | [pearl_trainer] epoch #108 | Finished meta-testing... 2025-04-02 18:18:31 | [pearl_trainer] epoch #108 | Saving snapshot... 2025-04-02 18:18:32 | [pearl_trainer] epoch #108 | Saved 2025-04-02 18:18:32 | [pearl_trainer] epoch #108 | Time 17388.59 s 2025-04-02 18:18:32 | [pearl_trainer] epoch #108 | EpochTime 165.61 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -105.146 MetaTest/Average/AverageReturn -105.146 MetaTest/Average/Iteration 108 MetaTest/Average/MaxReturn -89.311 MetaTest/Average/MinReturn -113.447 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.2015 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -105.146 MetaTest/__unnamed_task__/AverageReturn -105.146 MetaTest/__unnamed_task__/Iteration 108 MetaTest/__unnamed_task__/MaxReturn -89.311 MetaTest/__unnamed_task__/MinReturn -113.447 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.2015 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 189400 ------------------------------------------------- ----------- 2025-04-02 18:18:54 | [pearl_trainer] epoch #109 | Training... 2025-04-02 18:20:19 | [pearl_trainer] epoch #109 | Evaluating... 2025-04-02 18:20:19 | [pearl_trainer] epoch #109 | Sampling for adapation and meta-testing... 2025-04-02 18:21:15 | [pearl_trainer] epoch #109 | Finished meta-testing... 2025-04-02 18:21:15 | [pearl_trainer] epoch #109 | Saving snapshot... 2025-04-02 18:21:16 | [pearl_trainer] epoch #109 | Saved 2025-04-02 18:21:16 | [pearl_trainer] epoch #109 | Time 17552.52 s 2025-04-02 18:21:16 | [pearl_trainer] epoch #109 | EpochTime 163.93 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -106.953 MetaTest/Average/AverageReturn -106.953 MetaTest/Average/Iteration 109 MetaTest/Average/MaxReturn -101.235 MetaTest/Average/MinReturn -118.29 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.01681 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -106.953 MetaTest/__unnamed_task__/AverageReturn -106.953 MetaTest/__unnamed_task__/Iteration 109 MetaTest/__unnamed_task__/MaxReturn -101.235 MetaTest/__unnamed_task__/MinReturn -118.29 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.01681 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 191000 ------------------------------------------------- ------------ 2025-04-02 18:21:39 | [pearl_trainer] epoch #110 | Training... 2025-04-02 18:23:06 | [pearl_trainer] epoch #110 | Evaluating... 2025-04-02 18:23:06 | [pearl_trainer] epoch #110 | Sampling for adapation and meta-testing... 2025-04-02 18:24:04 | [pearl_trainer] epoch #110 | Finished meta-testing... 2025-04-02 18:24:04 | [pearl_trainer] epoch #110 | Saving snapshot... 2025-04-02 18:24:05 | [pearl_trainer] epoch #110 | Saved 2025-04-02 18:24:05 | [pearl_trainer] epoch #110 | Time 17720.90 s 2025-04-02 18:24:05 | [pearl_trainer] epoch #110 | EpochTime 168.38 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -115.174 MetaTest/Average/AverageReturn -115.174 MetaTest/Average/Iteration 110 MetaTest/Average/MaxReturn -101.677 MetaTest/Average/MinReturn -123.148 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.5961 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -115.174 MetaTest/__unnamed_task__/AverageReturn -115.174 MetaTest/__unnamed_task__/Iteration 110 MetaTest/__unnamed_task__/MaxReturn -101.677 MetaTest/__unnamed_task__/MinReturn -123.148 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.5961 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 192600 ------------------------------------------------- ----------- 2025-04-02 18:24:33 | [pearl_trainer] epoch #111 | Training... 2025-04-02 18:26:00 | [pearl_trainer] epoch #111 | Evaluating... 2025-04-02 18:26:00 | [pearl_trainer] epoch #111 | Sampling for adapation and meta-testing... 2025-04-02 18:26:43 | [pearl_trainer] epoch #111 | Finished meta-testing... 2025-04-02 18:26:43 | [pearl_trainer] epoch #111 | Saving snapshot... 2025-04-02 18:26:44 | [pearl_trainer] epoch #111 | Saved 2025-04-02 18:26:44 | [pearl_trainer] epoch #111 | Time 17880.18 s 2025-04-02 18:26:44 | [pearl_trainer] epoch #111 | EpochTime 159.27 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -110.232 MetaTest/Average/AverageReturn -110.232 MetaTest/Average/Iteration 111 MetaTest/Average/MaxReturn -107.739 MetaTest/Average/MinReturn -114.054 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.74445 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -110.232 MetaTest/__unnamed_task__/AverageReturn -110.232 MetaTest/__unnamed_task__/Iteration 111 MetaTest/__unnamed_task__/MaxReturn -107.739 MetaTest/__unnamed_task__/MinReturn -114.054 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.74445 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 194200 ------------------------------------------------- ------------ 2025-04-02 18:27:05 | [pearl_trainer] epoch #112 | Training... 2025-04-02 18:28:38 | [pearl_trainer] epoch #112 | Evaluating... 2025-04-02 18:28:38 | [pearl_trainer] epoch #112 | Sampling for adapation and meta-testing... 2025-04-02 18:29:27 | [pearl_trainer] epoch #112 | Finished meta-testing... 2025-04-02 18:29:27 | [pearl_trainer] epoch #112 | Saving snapshot... 2025-04-02 18:29:28 | [pearl_trainer] epoch #112 | Saved 2025-04-02 18:29:28 | [pearl_trainer] epoch #112 | Time 18044.14 s 2025-04-02 18:29:28 | [pearl_trainer] epoch #112 | EpochTime 163.96 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -122.854 MetaTest/Average/AverageReturn -122.854 MetaTest/Average/Iteration 112 MetaTest/Average/MaxReturn -116.263 MetaTest/Average/MinReturn -126.256 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.66147 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -122.854 MetaTest/__unnamed_task__/AverageReturn -122.854 MetaTest/__unnamed_task__/Iteration 112 MetaTest/__unnamed_task__/MaxReturn -116.263 MetaTest/__unnamed_task__/MinReturn -126.256 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.66147 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 195800 ------------------------------------------------- ------------ 2025-04-02 18:29:50 | [pearl_trainer] epoch #113 | Training... 2025-04-02 18:31:17 | [pearl_trainer] epoch #113 | Evaluating... 2025-04-02 18:31:17 | [pearl_trainer] epoch #113 | Sampling for adapation and meta-testing... 2025-04-02 18:32:04 | [pearl_trainer] epoch #113 | Finished meta-testing... 2025-04-02 18:32:04 | [pearl_trainer] epoch #113 | Saving snapshot... 2025-04-02 18:32:05 | [pearl_trainer] epoch #113 | Saved 2025-04-02 18:32:05 | [pearl_trainer] epoch #113 | Time 18201.35 s 2025-04-02 18:32:05 | [pearl_trainer] epoch #113 | EpochTime 157.21 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -114.187 MetaTest/Average/AverageReturn -114.187 MetaTest/Average/Iteration 113 MetaTest/Average/MaxReturn -103.765 MetaTest/Average/MinReturn -125.026 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.68478 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -114.187 MetaTest/__unnamed_task__/AverageReturn -114.187 MetaTest/__unnamed_task__/Iteration 113 MetaTest/__unnamed_task__/MaxReturn -103.765 MetaTest/__unnamed_task__/MinReturn -125.026 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.68478 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 197400 ------------------------------------------------- ------------ 2025-04-02 18:32:28 | [pearl_trainer] epoch #114 | Training... 2025-04-02 18:33:54 | [pearl_trainer] epoch #114 | Evaluating... 2025-04-02 18:33:54 | [pearl_trainer] epoch #114 | Sampling for adapation and meta-testing... 2025-04-02 18:34:39 | [pearl_trainer] epoch #114 | Finished meta-testing... 2025-04-02 18:34:39 | [pearl_trainer] epoch #114 | Saving snapshot... 2025-04-02 18:34:40 | [pearl_trainer] epoch #114 | Saved 2025-04-02 18:34:40 | [pearl_trainer] epoch #114 | Time 18356.40 s 2025-04-02 18:34:40 | [pearl_trainer] epoch #114 | EpochTime 155.05 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -112.025 MetaTest/Average/AverageReturn -112.025 MetaTest/Average/Iteration 114 MetaTest/Average/MaxReturn -103.626 MetaTest/Average/MinReturn -117.659 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.05361 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -112.025 MetaTest/__unnamed_task__/AverageReturn -112.025 MetaTest/__unnamed_task__/Iteration 114 MetaTest/__unnamed_task__/MaxReturn -103.626 MetaTest/__unnamed_task__/MinReturn -117.659 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.05361 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 199000 ------------------------------------------------- ------------ 2025-04-02 18:35:02 | [pearl_trainer] epoch #115 | Training... 2025-04-02 18:36:35 | [pearl_trainer] epoch #115 | Evaluating... 2025-04-02 18:36:35 | [pearl_trainer] epoch #115 | Sampling for adapation and meta-testing... 2025-04-02 18:37:23 | [pearl_trainer] epoch #115 | Finished meta-testing... 2025-04-02 18:37:23 | [pearl_trainer] epoch #115 | Saving snapshot... 2025-04-02 18:37:24 | [pearl_trainer] epoch #115 | Saved 2025-04-02 18:37:24 | [pearl_trainer] epoch #115 | Time 18520.35 s 2025-04-02 18:37:24 | [pearl_trainer] epoch #115 | EpochTime 163.96 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -120.74 MetaTest/Average/AverageReturn -120.74 MetaTest/Average/Iteration 115 MetaTest/Average/MaxReturn -113.885 MetaTest/Average/MinReturn -132.527 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.37153 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -120.74 MetaTest/__unnamed_task__/AverageReturn -120.74 MetaTest/__unnamed_task__/Iteration 115 MetaTest/__unnamed_task__/MaxReturn -113.885 MetaTest/__unnamed_task__/MinReturn -132.527 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.37153 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 200600 ------------------------------------------------- ------------ 2025-04-02 18:37:44 | [pearl_trainer] epoch #116 | Training... 2025-04-02 18:39:10 | [pearl_trainer] epoch #116 | Evaluating... 2025-04-02 18:39:10 | [pearl_trainer] epoch #116 | Sampling for adapation and meta-testing... 2025-04-02 18:39:57 | [pearl_trainer] epoch #116 | Finished meta-testing... 2025-04-02 18:39:57 | [pearl_trainer] epoch #116 | Saving snapshot... 2025-04-02 18:39:58 | [pearl_trainer] epoch #116 | Saved 2025-04-02 18:39:58 | [pearl_trainer] epoch #116 | Time 18674.44 s 2025-04-02 18:39:58 | [pearl_trainer] epoch #116 | EpochTime 154.08 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -108.351 MetaTest/Average/AverageReturn -108.351 MetaTest/Average/Iteration 116 MetaTest/Average/MaxReturn -106.653 MetaTest/Average/MinReturn -109.838 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.3088 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -108.351 MetaTest/__unnamed_task__/AverageReturn -108.351 MetaTest/__unnamed_task__/Iteration 116 MetaTest/__unnamed_task__/MaxReturn -106.653 MetaTest/__unnamed_task__/MinReturn -109.838 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.3088 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 202200 ------------------------------------------------- ----------- 2025-04-02 18:40:21 | [pearl_trainer] epoch #117 | Training... 2025-04-02 18:41:44 | [pearl_trainer] epoch #117 | Evaluating... 2025-04-02 18:41:44 | [pearl_trainer] epoch #117 | Sampling for adapation and meta-testing... 2025-04-02 18:42:33 | [pearl_trainer] epoch #117 | Finished meta-testing... 2025-04-02 18:42:33 | [pearl_trainer] epoch #117 | Saving snapshot... 2025-04-02 18:42:34 | [pearl_trainer] epoch #117 | Saved 2025-04-02 18:42:34 | [pearl_trainer] epoch #117 | Time 18830.05 s 2025-04-02 18:42:34 | [pearl_trainer] epoch #117 | EpochTime 155.61 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -128.979 MetaTest/Average/AverageReturn -128.979 MetaTest/Average/Iteration 117 MetaTest/Average/MaxReturn -126.759 MetaTest/Average/MinReturn -132.256 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.36549 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -128.979 MetaTest/__unnamed_task__/AverageReturn -128.979 MetaTest/__unnamed_task__/Iteration 117 MetaTest/__unnamed_task__/MaxReturn -126.759 MetaTest/__unnamed_task__/MinReturn -132.256 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.36549 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 203800 ------------------------------------------------- ------------ 2025-04-02 18:42:57 | [pearl_trainer] epoch #118 | Training... 2025-04-02 18:44:28 | [pearl_trainer] epoch #118 | Evaluating... 2025-04-02 18:44:28 | [pearl_trainer] epoch #118 | Sampling for adapation and meta-testing... 2025-04-02 18:45:16 | [pearl_trainer] epoch #118 | Finished meta-testing... 2025-04-02 18:45:16 | [pearl_trainer] epoch #118 | Saving snapshot... 2025-04-02 18:45:17 | [pearl_trainer] epoch #118 | Saved 2025-04-02 18:45:17 | [pearl_trainer] epoch #118 | Time 18992.77 s 2025-04-02 18:45:17 | [pearl_trainer] epoch #118 | EpochTime 162.71 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -130.924 MetaTest/Average/AverageReturn -130.924 MetaTest/Average/Iteration 118 MetaTest/Average/MaxReturn -124.79 MetaTest/Average/MinReturn -140.55 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.89116 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -130.924 MetaTest/__unnamed_task__/AverageReturn -130.924 MetaTest/__unnamed_task__/Iteration 118 MetaTest/__unnamed_task__/MaxReturn -124.79 MetaTest/__unnamed_task__/MinReturn -140.55 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.89116 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 205400 ------------------------------------------------- ------------ 2025-04-02 18:45:39 | [pearl_trainer] epoch #119 | Training... 2025-04-02 18:47:01 | [pearl_trainer] epoch #119 | Evaluating... 2025-04-02 18:47:01 | [pearl_trainer] epoch #119 | Sampling for adapation and meta-testing... 2025-04-02 18:47:57 | [pearl_trainer] epoch #119 | Finished meta-testing... 2025-04-02 18:47:57 | [pearl_trainer] epoch #119 | Saving snapshot... 2025-04-02 18:47:58 | [pearl_trainer] epoch #119 | Saved 2025-04-02 18:47:58 | [pearl_trainer] epoch #119 | Time 19154.61 s 2025-04-02 18:47:58 | [pearl_trainer] epoch #119 | EpochTime 161.84 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -114.449 MetaTest/Average/AverageReturn -114.449 MetaTest/Average/Iteration 119 MetaTest/Average/MaxReturn -105.644 MetaTest/Average/MinReturn -129.432 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.6483 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -114.449 MetaTest/__unnamed_task__/AverageReturn -114.449 MetaTest/__unnamed_task__/Iteration 119 MetaTest/__unnamed_task__/MaxReturn -105.644 MetaTest/__unnamed_task__/MinReturn -129.432 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.6483 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 207000 ------------------------------------------------- ----------- 2025-04-02 18:48:21 | [pearl_trainer] epoch #120 | Training... 2025-04-02 18:49:44 | [pearl_trainer] epoch #120 | Evaluating... 2025-04-02 18:49:44 | [pearl_trainer] epoch #120 | Sampling for adapation and meta-testing... 2025-04-02 18:50:33 | [pearl_trainer] epoch #120 | Finished meta-testing... 2025-04-02 18:50:33 | [pearl_trainer] epoch #120 | Saving snapshot... 2025-04-02 18:50:35 | [pearl_trainer] epoch #120 | Saved 2025-04-02 18:50:35 | [pearl_trainer] epoch #120 | Time 19310.91 s 2025-04-02 18:50:35 | [pearl_trainer] epoch #120 | EpochTime 156.29 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -98.3091 MetaTest/Average/AverageReturn -98.3091 MetaTest/Average/Iteration 120 MetaTest/Average/MaxReturn -93.6875 MetaTest/Average/MinReturn -104.618 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.61934 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.3091 MetaTest/__unnamed_task__/AverageReturn -98.3091 MetaTest/__unnamed_task__/Iteration 120 MetaTest/__unnamed_task__/MaxReturn -93.6875 MetaTest/__unnamed_task__/MinReturn -104.618 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.61934 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 208600 ------------------------------------------------- ------------ 2025-04-02 18:50:57 | [pearl_trainer] epoch #121 | Training... 2025-04-02 18:52:29 | [pearl_trainer] epoch #121 | Evaluating... 2025-04-02 18:52:29 | [pearl_trainer] epoch #121 | Sampling for adapation and meta-testing... 2025-04-02 18:53:15 | [pearl_trainer] epoch #121 | Finished meta-testing... 2025-04-02 18:53:15 | [pearl_trainer] epoch #121 | Saving snapshot... 2025-04-02 18:53:16 | [pearl_trainer] epoch #121 | Saved 2025-04-02 18:53:16 | [pearl_trainer] epoch #121 | Time 19472.57 s 2025-04-02 18:53:16 | [pearl_trainer] epoch #121 | EpochTime 161.66 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -110.315 MetaTest/Average/AverageReturn -110.315 MetaTest/Average/Iteration 121 MetaTest/Average/MaxReturn -96.1775 MetaTest/Average/MinReturn -132.744 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 16.0382 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -110.315 MetaTest/__unnamed_task__/AverageReturn -110.315 MetaTest/__unnamed_task__/Iteration 121 MetaTest/__unnamed_task__/MaxReturn -96.1775 MetaTest/__unnamed_task__/MinReturn -132.744 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 16.0382 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 210200 ------------------------------------------------- ----------- 2025-04-02 18:53:39 | [pearl_trainer] epoch #122 | Training... 2025-04-02 18:55:04 | [pearl_trainer] epoch #122 | Evaluating... 2025-04-02 18:55:04 | [pearl_trainer] epoch #122 | Sampling for adapation and meta-testing... 2025-04-02 18:55:58 | [pearl_trainer] epoch #122 | Finished meta-testing... 2025-04-02 18:55:58 | [pearl_trainer] epoch #122 | Saving snapshot... 2025-04-02 18:55:59 | [pearl_trainer] epoch #122 | Saved 2025-04-02 18:55:59 | [pearl_trainer] epoch #122 | Time 19635.57 s 2025-04-02 18:55:59 | [pearl_trainer] epoch #122 | EpochTime 163.00 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -122.362 MetaTest/Average/AverageReturn -122.362 MetaTest/Average/Iteration 122 MetaTest/Average/MaxReturn -105.583 MetaTest/Average/MinReturn -131.336 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.8746 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -122.362 MetaTest/__unnamed_task__/AverageReturn -122.362 MetaTest/__unnamed_task__/Iteration 122 MetaTest/__unnamed_task__/MaxReturn -105.583 MetaTest/__unnamed_task__/MinReturn -131.336 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.8746 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 211800 ------------------------------------------------- ----------- 2025-04-02 18:56:26 | [pearl_trainer] epoch #123 | Training... 2025-04-02 18:58:07 | [pearl_trainer] epoch #123 | Evaluating... 2025-04-02 18:58:07 | [pearl_trainer] epoch #123 | Sampling for adapation and meta-testing... 2025-04-02 18:58:53 | [pearl_trainer] epoch #123 | Finished meta-testing... 2025-04-02 18:58:53 | [pearl_trainer] epoch #123 | Saving snapshot... 2025-04-02 18:58:54 | [pearl_trainer] epoch #123 | Saved 2025-04-02 18:58:54 | [pearl_trainer] epoch #123 | Time 19810.39 s 2025-04-02 18:58:54 | [pearl_trainer] epoch #123 | EpochTime 174.81 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -118.901 MetaTest/Average/AverageReturn -118.901 MetaTest/Average/Iteration 123 MetaTest/Average/MaxReturn -81.6759 MetaTest/Average/MinReturn -143.715 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 26.8047 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -118.901 MetaTest/__unnamed_task__/AverageReturn -118.901 MetaTest/__unnamed_task__/Iteration 123 MetaTest/__unnamed_task__/MaxReturn -81.6759 MetaTest/__unnamed_task__/MinReturn -143.715 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 26.8047 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 213400 ------------------------------------------------- ----------- 2025-04-02 18:59:17 | [pearl_trainer] epoch #124 | Training... 2025-04-02 19:00:56 | [pearl_trainer] epoch #124 | Evaluating... 2025-04-02 19:00:56 | [pearl_trainer] epoch #124 | Sampling for adapation and meta-testing... 2025-04-02 19:01:42 | [pearl_trainer] epoch #124 | Finished meta-testing... 2025-04-02 19:01:42 | [pearl_trainer] epoch #124 | Saving snapshot... 2025-04-02 19:01:43 | [pearl_trainer] epoch #124 | Saved 2025-04-02 19:01:43 | [pearl_trainer] epoch #124 | Time 19979.12 s 2025-04-02 19:01:43 | [pearl_trainer] epoch #124 | EpochTime 168.73 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -119.351 MetaTest/Average/AverageReturn -119.351 MetaTest/Average/Iteration 124 MetaTest/Average/MaxReturn -108.399 MetaTest/Average/MinReturn -125.016 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.74558 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -119.351 MetaTest/__unnamed_task__/AverageReturn -119.351 MetaTest/__unnamed_task__/Iteration 124 MetaTest/__unnamed_task__/MaxReturn -108.399 MetaTest/__unnamed_task__/MinReturn -125.016 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.74558 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 215000 ------------------------------------------------- ------------ 2025-04-02 19:02:05 | [pearl_trainer] epoch #125 | Training... 2025-04-02 19:03:27 | [pearl_trainer] epoch #125 | Evaluating... 2025-04-02 19:03:27 | [pearl_trainer] epoch #125 | Sampling for adapation and meta-testing... 2025-04-02 19:04:22 | [pearl_trainer] epoch #125 | Finished meta-testing... 2025-04-02 19:04:22 | [pearl_trainer] epoch #125 | Saving snapshot... 2025-04-02 19:04:23 | [pearl_trainer] epoch #125 | Saved 2025-04-02 19:04:23 | [pearl_trainer] epoch #125 | Time 20139.05 s 2025-04-02 19:04:23 | [pearl_trainer] epoch #125 | EpochTime 159.93 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -108.637 MetaTest/Average/AverageReturn -108.637 MetaTest/Average/Iteration 125 MetaTest/Average/MaxReturn -103.9 MetaTest/Average/MinReturn -111.912 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.43051 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -108.637 MetaTest/__unnamed_task__/AverageReturn -108.637 MetaTest/__unnamed_task__/Iteration 125 MetaTest/__unnamed_task__/MaxReturn -103.9 MetaTest/__unnamed_task__/MinReturn -111.912 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.43051 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 216600 ------------------------------------------------- ------------ 2025-04-02 19:04:48 | [pearl_trainer] epoch #126 | Training... 2025-04-02 19:06:11 | [pearl_trainer] epoch #126 | Evaluating... 2025-04-02 19:06:11 | [pearl_trainer] epoch #126 | Sampling for adapation and meta-testing... 2025-04-02 19:06:59 | [pearl_trainer] epoch #126 | Finished meta-testing... 2025-04-02 19:06:59 | [pearl_trainer] epoch #126 | Saving snapshot... 2025-04-02 19:07:00 | [pearl_trainer] epoch #126 | Saved 2025-04-02 19:07:00 | [pearl_trainer] epoch #126 | Time 20295.82 s 2025-04-02 19:07:00 | [pearl_trainer] epoch #126 | EpochTime 156.77 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -128.573 MetaTest/Average/AverageReturn -128.573 MetaTest/Average/Iteration 126 MetaTest/Average/MaxReturn -112.652 MetaTest/Average/MinReturn -150.338 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 15.9306 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -128.573 MetaTest/__unnamed_task__/AverageReturn -128.573 MetaTest/__unnamed_task__/Iteration 126 MetaTest/__unnamed_task__/MaxReturn -112.652 MetaTest/__unnamed_task__/MinReturn -150.338 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 15.9306 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 218200 ------------------------------------------------- ----------- 2025-04-02 19:07:25 | [pearl_trainer] epoch #127 | Training... 2025-04-02 19:08:52 | [pearl_trainer] epoch #127 | Evaluating... 2025-04-02 19:08:52 | [pearl_trainer] epoch #127 | Sampling for adapation and meta-testing... 2025-04-02 19:09:35 | [pearl_trainer] epoch #127 | Finished meta-testing... 2025-04-02 19:09:35 | [pearl_trainer] epoch #127 | Saving snapshot... 2025-04-02 19:09:36 | [pearl_trainer] epoch #127 | Saved 2025-04-02 19:09:36 | [pearl_trainer] epoch #127 | Time 20451.86 s 2025-04-02 19:09:36 | [pearl_trainer] epoch #127 | EpochTime 156.04 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -118.652 MetaTest/Average/AverageReturn -118.652 MetaTest/Average/Iteration 127 MetaTest/Average/MaxReturn -96.2184 MetaTest/Average/MinReturn -139.799 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 17.8148 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -118.652 MetaTest/__unnamed_task__/AverageReturn -118.652 MetaTest/__unnamed_task__/Iteration 127 MetaTest/__unnamed_task__/MaxReturn -96.2184 MetaTest/__unnamed_task__/MinReturn -139.799 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 17.8148 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 219800 ------------------------------------------------- ----------- 2025-04-02 19:09:57 | [pearl_trainer] epoch #128 | Training... 2025-04-02 19:11:25 | [pearl_trainer] epoch #128 | Evaluating... 2025-04-02 19:11:25 | [pearl_trainer] epoch #128 | Sampling for adapation and meta-testing... 2025-04-02 19:12:13 | [pearl_trainer] epoch #128 | Finished meta-testing... 2025-04-02 19:12:13 | [pearl_trainer] epoch #128 | Saving snapshot... 2025-04-02 19:12:14 | [pearl_trainer] epoch #128 | Saved 2025-04-02 19:12:14 | [pearl_trainer] epoch #128 | Time 20610.42 s 2025-04-02 19:12:14 | [pearl_trainer] epoch #128 | EpochTime 158.56 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -113.262 MetaTest/Average/AverageReturn -113.262 MetaTest/Average/Iteration 128 MetaTest/Average/MaxReturn -103.861 MetaTest/Average/MinReturn -120.282 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.91169 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -113.262 MetaTest/__unnamed_task__/AverageReturn -113.262 MetaTest/__unnamed_task__/Iteration 128 MetaTest/__unnamed_task__/MaxReturn -103.861 MetaTest/__unnamed_task__/MinReturn -120.282 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.91169 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 221400 ------------------------------------------------- ------------ 2025-04-02 19:12:35 | [pearl_trainer] epoch #129 | Training... 2025-04-02 19:14:06 | [pearl_trainer] epoch #129 | Evaluating... 2025-04-02 19:14:06 | [pearl_trainer] epoch #129 | Sampling for adapation and meta-testing... 2025-04-02 19:14:50 | [pearl_trainer] epoch #129 | Finished meta-testing... 2025-04-02 19:14:50 | [pearl_trainer] epoch #129 | Saving snapshot... 2025-04-02 19:14:51 | [pearl_trainer] epoch #129 | Saved 2025-04-02 19:14:51 | [pearl_trainer] epoch #129 | Time 20766.74 s 2025-04-02 19:14:51 | [pearl_trainer] epoch #129 | EpochTime 156.32 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -119.236 MetaTest/Average/AverageReturn -119.236 MetaTest/Average/Iteration 129 MetaTest/Average/MaxReturn -115.573 MetaTest/Average/MinReturn -121.913 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.68061 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -119.236 MetaTest/__unnamed_task__/AverageReturn -119.236 MetaTest/__unnamed_task__/Iteration 129 MetaTest/__unnamed_task__/MaxReturn -115.573 MetaTest/__unnamed_task__/MinReturn -121.913 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.68061 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 223000 ------------------------------------------------- ------------ 2025-04-02 19:15:12 | [pearl_trainer] epoch #130 | Training... 2025-04-02 19:16:49 | [pearl_trainer] epoch #130 | Evaluating... 2025-04-02 19:16:49 | [pearl_trainer] epoch #130 | Sampling for adapation and meta-testing... 2025-04-02 19:17:33 | [pearl_trainer] epoch #130 | Finished meta-testing... 2025-04-02 19:17:33 | [pearl_trainer] epoch #130 | Saving snapshot... 2025-04-02 19:17:34 | [pearl_trainer] epoch #130 | Saved 2025-04-02 19:17:34 | [pearl_trainer] epoch #130 | Time 20930.49 s 2025-04-02 19:17:34 | [pearl_trainer] epoch #130 | EpochTime 163.75 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.6129 MetaTest/Average/AverageReturn -93.6129 MetaTest/Average/Iteration 130 MetaTest/Average/MaxReturn -88.3379 MetaTest/Average/MinReturn -98.8547 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.29353 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.6129 MetaTest/__unnamed_task__/AverageReturn -93.6129 MetaTest/__unnamed_task__/Iteration 130 MetaTest/__unnamed_task__/MaxReturn -88.3379 MetaTest/__unnamed_task__/MinReturn -98.8547 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.29353 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 224600 ------------------------------------------------- ------------ 2025-04-02 19:17:56 | [pearl_trainer] epoch #131 | Training... 2025-04-02 19:19:28 | [pearl_trainer] epoch #131 | Evaluating... 2025-04-02 19:19:28 | [pearl_trainer] epoch #131 | Sampling for adapation and meta-testing... 2025-04-02 19:20:21 | [pearl_trainer] epoch #131 | Finished meta-testing... 2025-04-02 19:20:21 | [pearl_trainer] epoch #131 | Saving snapshot... 2025-04-02 19:20:22 | [pearl_trainer] epoch #131 | Saved 2025-04-02 19:20:22 | [pearl_trainer] epoch #131 | Time 21098.44 s 2025-04-02 19:20:22 | [pearl_trainer] epoch #131 | EpochTime 167.95 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -108.732 MetaTest/Average/AverageReturn -108.732 MetaTest/Average/Iteration 131 MetaTest/Average/MaxReturn -100.425 MetaTest/Average/MinReturn -114.897 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.0992 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -108.732 MetaTest/__unnamed_task__/AverageReturn -108.732 MetaTest/__unnamed_task__/Iteration 131 MetaTest/__unnamed_task__/MaxReturn -100.425 MetaTest/__unnamed_task__/MinReturn -114.897 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.0992 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 226200 ------------------------------------------------- ----------- 2025-04-02 19:20:44 | [pearl_trainer] epoch #132 | Training... 2025-04-02 19:22:08 | [pearl_trainer] epoch #132 | Evaluating... 2025-04-02 19:22:08 | [pearl_trainer] epoch #132 | Sampling for adapation and meta-testing... 2025-04-02 19:23:05 | [pearl_trainer] epoch #132 | Finished meta-testing... 2025-04-02 19:23:05 | [pearl_trainer] epoch #132 | Saving snapshot... 2025-04-02 19:23:06 | [pearl_trainer] epoch #132 | Saved 2025-04-02 19:23:06 | [pearl_trainer] epoch #132 | Time 21261.87 s 2025-04-02 19:23:06 | [pearl_trainer] epoch #132 | EpochTime 163.43 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -109.087 MetaTest/Average/AverageReturn -109.087 MetaTest/Average/Iteration 132 MetaTest/Average/MaxReturn -106.886 MetaTest/Average/MinReturn -111.302 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.80288 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -109.087 MetaTest/__unnamed_task__/AverageReturn -109.087 MetaTest/__unnamed_task__/Iteration 132 MetaTest/__unnamed_task__/MaxReturn -106.886 MetaTest/__unnamed_task__/MinReturn -111.302 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.80288 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 227800 ------------------------------------------------- ------------ 2025-04-02 19:23:28 | [pearl_trainer] epoch #133 | Training... 2025-04-02 19:24:53 | [pearl_trainer] epoch #133 | Evaluating... 2025-04-02 19:24:53 | [pearl_trainer] epoch #133 | Sampling for adapation and meta-testing... 2025-04-02 19:25:42 | [pearl_trainer] epoch #133 | Finished meta-testing... 2025-04-02 19:25:42 | [pearl_trainer] epoch #133 | Saving snapshot... 2025-04-02 19:25:43 | [pearl_trainer] epoch #133 | Saved 2025-04-02 19:25:43 | [pearl_trainer] epoch #133 | Time 21419.39 s 2025-04-02 19:25:43 | [pearl_trainer] epoch #133 | EpochTime 157.52 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -109.836 MetaTest/Average/AverageReturn -109.836 MetaTest/Average/Iteration 133 MetaTest/Average/MaxReturn -104.406 MetaTest/Average/MinReturn -113.247 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.8817 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -109.836 MetaTest/__unnamed_task__/AverageReturn -109.836 MetaTest/__unnamed_task__/Iteration 133 MetaTest/__unnamed_task__/MaxReturn -104.406 MetaTest/__unnamed_task__/MinReturn -113.247 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.8817 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 229400 ------------------------------------------------- ----------- 2025-04-02 19:26:05 | [pearl_trainer] epoch #134 | Training... 2025-04-02 19:27:53 | [pearl_trainer] epoch #134 | Evaluating... 2025-04-02 19:27:53 | [pearl_trainer] epoch #134 | Sampling for adapation and meta-testing... 2025-04-02 19:28:48 | [pearl_trainer] epoch #134 | Finished meta-testing... 2025-04-02 19:28:48 | [pearl_trainer] epoch #134 | Saving snapshot... 2025-04-02 19:28:49 | [pearl_trainer] epoch #134 | Saved 2025-04-02 19:28:49 | [pearl_trainer] epoch #134 | Time 21604.84 s 2025-04-02 19:28:49 | [pearl_trainer] epoch #134 | EpochTime 185.44 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -107.539 MetaTest/Average/AverageReturn -107.539 MetaTest/Average/Iteration 134 MetaTest/Average/MaxReturn -103.552 MetaTest/Average/MinReturn -113.916 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.55604 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -107.539 MetaTest/__unnamed_task__/AverageReturn -107.539 MetaTest/__unnamed_task__/Iteration 134 MetaTest/__unnamed_task__/MaxReturn -103.552 MetaTest/__unnamed_task__/MinReturn -113.916 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.55604 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 231000 ------------------------------------------------- ------------ 2025-04-02 19:29:11 | [pearl_trainer] epoch #135 | Training... 2025-04-02 19:30:36 | [pearl_trainer] epoch #135 | Evaluating... 2025-04-02 19:30:36 | [pearl_trainer] epoch #135 | Sampling for adapation and meta-testing... 2025-04-02 19:31:31 | [pearl_trainer] epoch #135 | Finished meta-testing... 2025-04-02 19:31:31 | [pearl_trainer] epoch #135 | Saving snapshot... 2025-04-02 19:31:32 | [pearl_trainer] epoch #135 | Saved 2025-04-02 19:31:32 | [pearl_trainer] epoch #135 | Time 21768.15 s 2025-04-02 19:31:32 | [pearl_trainer] epoch #135 | EpochTime 163.32 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -105.674 MetaTest/Average/AverageReturn -105.674 MetaTest/Average/Iteration 135 MetaTest/Average/MaxReturn -84.227 MetaTest/Average/MinReturn -125.707 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 16.9636 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -105.674 MetaTest/__unnamed_task__/AverageReturn -105.674 MetaTest/__unnamed_task__/Iteration 135 MetaTest/__unnamed_task__/MaxReturn -84.227 MetaTest/__unnamed_task__/MinReturn -125.707 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 16.9636 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 232600 ------------------------------------------------- ----------- 2025-04-02 19:31:56 | [pearl_trainer] epoch #136 | Training... 2025-04-02 19:33:24 | [pearl_trainer] epoch #136 | Evaluating... 2025-04-02 19:33:24 | [pearl_trainer] epoch #136 | Sampling for adapation and meta-testing... 2025-04-02 19:34:10 | [pearl_trainer] epoch #136 | Finished meta-testing... 2025-04-02 19:34:10 | [pearl_trainer] epoch #136 | Saving snapshot... 2025-04-02 19:34:11 | [pearl_trainer] epoch #136 | Saved 2025-04-02 19:34:11 | [pearl_trainer] epoch #136 | Time 21926.92 s 2025-04-02 19:34:11 | [pearl_trainer] epoch #136 | EpochTime 158.76 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -107.803 MetaTest/Average/AverageReturn -107.803 MetaTest/Average/Iteration 136 MetaTest/Average/MaxReturn -93.149 MetaTest/Average/MinReturn -125.224 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.2398 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -107.803 MetaTest/__unnamed_task__/AverageReturn -107.803 MetaTest/__unnamed_task__/Iteration 136 MetaTest/__unnamed_task__/MaxReturn -93.149 MetaTest/__unnamed_task__/MinReturn -125.224 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.2398 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 234200 ------------------------------------------------- ----------- 2025-04-02 19:34:33 | [pearl_trainer] epoch #137 | Training... 2025-04-02 19:36:11 | [pearl_trainer] epoch #137 | Evaluating... 2025-04-02 19:36:11 | [pearl_trainer] epoch #137 | Sampling for adapation and meta-testing... 2025-04-02 19:36:56 | [pearl_trainer] epoch #137 | Finished meta-testing... 2025-04-02 19:36:56 | [pearl_trainer] epoch #137 | Saving snapshot... 2025-04-02 19:36:57 | [pearl_trainer] epoch #137 | Saved 2025-04-02 19:36:57 | [pearl_trainer] epoch #137 | Time 22093.67 s 2025-04-02 19:36:57 | [pearl_trainer] epoch #137 | EpochTime 166.75 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -101.211 MetaTest/Average/AverageReturn -101.211 MetaTest/Average/Iteration 137 MetaTest/Average/MaxReturn -86.0735 MetaTest/Average/MinReturn -113.939 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.5031 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.211 MetaTest/__unnamed_task__/AverageReturn -101.211 MetaTest/__unnamed_task__/Iteration 137 MetaTest/__unnamed_task__/MaxReturn -86.0735 MetaTest/__unnamed_task__/MinReturn -113.939 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.5031 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 235800 ------------------------------------------------- ----------- 2025-04-02 19:37:19 | [pearl_trainer] epoch #138 | Training... 2025-04-02 19:38:50 | [pearl_trainer] epoch #138 | Evaluating... 2025-04-02 19:38:50 | [pearl_trainer] epoch #138 | Sampling for adapation and meta-testing... 2025-04-02 19:39:41 | [pearl_trainer] epoch #138 | Finished meta-testing... 2025-04-02 19:39:41 | [pearl_trainer] epoch #138 | Saving snapshot... 2025-04-02 19:39:42 | [pearl_trainer] epoch #138 | Saved 2025-04-02 19:39:42 | [pearl_trainer] epoch #138 | Time 22258.24 s 2025-04-02 19:39:42 | [pearl_trainer] epoch #138 | EpochTime 164.57 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.6539 MetaTest/Average/AverageReturn -90.6539 MetaTest/Average/Iteration 138 MetaTest/Average/MaxReturn -89.1373 MetaTest/Average/MinReturn -91.6264 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.08656 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.6539 MetaTest/__unnamed_task__/AverageReturn -90.6539 MetaTest/__unnamed_task__/Iteration 138 MetaTest/__unnamed_task__/MaxReturn -89.1373 MetaTest/__unnamed_task__/MinReturn -91.6264 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.08656 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 237400 ------------------------------------------------- ------------ 2025-04-02 19:40:05 | [pearl_trainer] epoch #139 | Training... 2025-04-02 19:41:34 | [pearl_trainer] epoch #139 | Evaluating... 2025-04-02 19:41:34 | [pearl_trainer] epoch #139 | Sampling for adapation and meta-testing... 2025-04-02 19:42:17 | [pearl_trainer] epoch #139 | Finished meta-testing... 2025-04-02 19:42:17 | [pearl_trainer] epoch #139 | Saving snapshot... 2025-04-02 19:42:18 | [pearl_trainer] epoch #139 | Saved 2025-04-02 19:42:18 | [pearl_trainer] epoch #139 | Time 22414.01 s 2025-04-02 19:42:18 | [pearl_trainer] epoch #139 | EpochTime 155.77 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -103.268 MetaTest/Average/AverageReturn -103.268 MetaTest/Average/Iteration 139 MetaTest/Average/MaxReturn -98.1177 MetaTest/Average/MinReturn -107.877 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.00249 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -103.268 MetaTest/__unnamed_task__/AverageReturn -103.268 MetaTest/__unnamed_task__/Iteration 139 MetaTest/__unnamed_task__/MaxReturn -98.1177 MetaTest/__unnamed_task__/MinReturn -107.877 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.00249 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 239000 ------------------------------------------------- ------------ 2025-04-02 19:42:40 | [pearl_trainer] epoch #140 | Training... 2025-04-02 19:44:16 | [pearl_trainer] epoch #140 | Evaluating... 2025-04-02 19:44:16 | [pearl_trainer] epoch #140 | Sampling for adapation and meta-testing... 2025-04-02 19:44:59 | [pearl_trainer] epoch #140 | Finished meta-testing... 2025-04-02 19:44:59 | [pearl_trainer] epoch #140 | Saving snapshot... 2025-04-02 19:45:00 | [pearl_trainer] epoch #140 | Saved 2025-04-02 19:45:00 | [pearl_trainer] epoch #140 | Time 22576.04 s 2025-04-02 19:45:00 | [pearl_trainer] epoch #140 | EpochTime 162.03 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -96.0674 MetaTest/Average/AverageReturn -96.0674 MetaTest/Average/Iteration 140 MetaTest/Average/MaxReturn -84.0477 MetaTest/Average/MinReturn -111.65 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.547 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.0674 MetaTest/__unnamed_task__/AverageReturn -96.0674 MetaTest/__unnamed_task__/Iteration 140 MetaTest/__unnamed_task__/MaxReturn -84.0477 MetaTest/__unnamed_task__/MinReturn -111.65 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.547 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 240600 ------------------------------------------------- ----------- 2025-04-02 19:45:22 | [pearl_trainer] epoch #141 | Training... 2025-04-02 19:46:48 | [pearl_trainer] epoch #141 | Evaluating... 2025-04-02 19:46:48 | [pearl_trainer] epoch #141 | Sampling for adapation and meta-testing... 2025-04-02 19:47:46 | [pearl_trainer] epoch #141 | Finished meta-testing... 2025-04-02 19:47:46 | [pearl_trainer] epoch #141 | Saving snapshot... 2025-04-02 19:47:48 | [pearl_trainer] epoch #141 | Saved 2025-04-02 19:47:48 | [pearl_trainer] epoch #141 | Time 22743.99 s 2025-04-02 19:47:48 | [pearl_trainer] epoch #141 | EpochTime 167.94 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -98.6732 MetaTest/Average/AverageReturn -98.6732 MetaTest/Average/Iteration 141 MetaTest/Average/MaxReturn -92.3105 MetaTest/Average/MinReturn -101.89 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.49917 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.6732 MetaTest/__unnamed_task__/AverageReturn -98.6732 MetaTest/__unnamed_task__/Iteration 141 MetaTest/__unnamed_task__/MaxReturn -92.3105 MetaTest/__unnamed_task__/MinReturn -101.89 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.49917 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 242200 ------------------------------------------------- ------------ 2025-04-02 19:48:10 | [pearl_trainer] epoch #142 | Training... 2025-04-02 19:49:37 | [pearl_trainer] epoch #142 | Evaluating... 2025-04-02 19:49:37 | [pearl_trainer] epoch #142 | Sampling for adapation and meta-testing... 2025-04-02 19:50:24 | [pearl_trainer] epoch #142 | Finished meta-testing... 2025-04-02 19:50:24 | [pearl_trainer] epoch #142 | Saving snapshot... 2025-04-02 19:50:25 | [pearl_trainer] epoch #142 | Saved 2025-04-02 19:50:25 | [pearl_trainer] epoch #142 | Time 22901.14 s 2025-04-02 19:50:25 | [pearl_trainer] epoch #142 | EpochTime 157.15 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.7312 MetaTest/Average/AverageReturn -93.7312 MetaTest/Average/Iteration 142 MetaTest/Average/MaxReturn -91.9619 MetaTest/Average/MinReturn -96.7637 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.15422 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.7312 MetaTest/__unnamed_task__/AverageReturn -93.7312 MetaTest/__unnamed_task__/Iteration 142 MetaTest/__unnamed_task__/MaxReturn -91.9619 MetaTest/__unnamed_task__/MinReturn -96.7637 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.15422 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 243800 ------------------------------------------------- ------------ 2025-04-02 19:50:50 | [pearl_trainer] epoch #143 | Training... 2025-04-02 19:52:20 | [pearl_trainer] epoch #143 | Evaluating... 2025-04-02 19:52:20 | [pearl_trainer] epoch #143 | Sampling for adapation and meta-testing... 2025-04-02 19:53:06 | [pearl_trainer] epoch #143 | Finished meta-testing... 2025-04-02 19:53:06 | [pearl_trainer] epoch #143 | Saving snapshot... 2025-04-02 19:53:07 | [pearl_trainer] epoch #143 | Saved 2025-04-02 19:53:07 | [pearl_trainer] epoch #143 | Time 23063.63 s 2025-04-02 19:53:07 | [pearl_trainer] epoch #143 | EpochTime 162.49 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -92.1527 MetaTest/Average/AverageReturn -92.1527 MetaTest/Average/Iteration 143 MetaTest/Average/MaxReturn -86.7015 MetaTest/Average/MinReturn -95.8985 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.94355 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.1527 MetaTest/__unnamed_task__/AverageReturn -92.1527 MetaTest/__unnamed_task__/Iteration 143 MetaTest/__unnamed_task__/MaxReturn -86.7015 MetaTest/__unnamed_task__/MinReturn -95.8985 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.94355 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 245400 ------------------------------------------------- ------------ 2025-04-02 19:53:29 | [pearl_trainer] epoch #144 | Training... 2025-04-02 19:55:07 | [pearl_trainer] epoch #144 | Evaluating... 2025-04-02 19:55:07 | [pearl_trainer] epoch #144 | Sampling for adapation and meta-testing... 2025-04-02 19:55:56 | [pearl_trainer] epoch #144 | Finished meta-testing... 2025-04-02 19:55:56 | [pearl_trainer] epoch #144 | Saving snapshot... 2025-04-02 19:55:57 | [pearl_trainer] epoch #144 | Saved 2025-04-02 19:55:57 | [pearl_trainer] epoch #144 | Time 23232.82 s 2025-04-02 19:55:57 | [pearl_trainer] epoch #144 | EpochTime 169.19 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -84.7688 MetaTest/Average/AverageReturn -84.7688 MetaTest/Average/Iteration 144 MetaTest/Average/MaxReturn -80.1205 MetaTest/Average/MinReturn -90.3259 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.21559 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -84.7688 MetaTest/__unnamed_task__/AverageReturn -84.7688 MetaTest/__unnamed_task__/Iteration 144 MetaTest/__unnamed_task__/MaxReturn -80.1205 MetaTest/__unnamed_task__/MinReturn -90.3259 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.21559 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 247000 ------------------------------------------------- ------------ 2025-04-02 19:56:19 | [pearl_trainer] epoch #145 | Training... 2025-04-02 19:57:47 | [pearl_trainer] epoch #145 | Evaluating... 2025-04-02 19:57:47 | [pearl_trainer] epoch #145 | Sampling for adapation and meta-testing... 2025-04-02 19:58:34 | [pearl_trainer] epoch #145 | Finished meta-testing... 2025-04-02 19:58:34 | [pearl_trainer] epoch #145 | Saving snapshot... 2025-04-02 19:58:35 | [pearl_trainer] epoch #145 | Saved 2025-04-02 19:58:35 | [pearl_trainer] epoch #145 | Time 23391.64 s 2025-04-02 19:58:35 | [pearl_trainer] epoch #145 | EpochTime 158.82 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -94.1061 MetaTest/Average/AverageReturn -94.1061 MetaTest/Average/Iteration 145 MetaTest/Average/MaxReturn -92.3939 MetaTest/Average/MinReturn -96.4656 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.72415 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.1061 MetaTest/__unnamed_task__/AverageReturn -94.1061 MetaTest/__unnamed_task__/Iteration 145 MetaTest/__unnamed_task__/MaxReturn -92.3939 MetaTest/__unnamed_task__/MinReturn -96.4656 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.72415 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 248600 ------------------------------------------------- ------------ 2025-04-02 19:59:01 | [pearl_trainer] epoch #146 | Training... 2025-04-02 20:00:39 | [pearl_trainer] epoch #146 | Evaluating... 2025-04-02 20:00:39 | [pearl_trainer] epoch #146 | Sampling for adapation and meta-testing... 2025-04-02 20:01:25 | [pearl_trainer] epoch #146 | Finished meta-testing... 2025-04-02 20:01:25 | [pearl_trainer] epoch #146 | Saving snapshot... 2025-04-02 20:01:26 | [pearl_trainer] epoch #146 | Saved 2025-04-02 20:01:26 | [pearl_trainer] epoch #146 | Time 23562.53 s 2025-04-02 20:01:26 | [pearl_trainer] epoch #146 | EpochTime 170.89 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -89.5425 MetaTest/Average/AverageReturn -89.5425 MetaTest/Average/Iteration 146 MetaTest/Average/MaxReturn -86.6693 MetaTest/Average/MinReturn -91.9096 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.1691 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -89.5425 MetaTest/__unnamed_task__/AverageReturn -89.5425 MetaTest/__unnamed_task__/Iteration 146 MetaTest/__unnamed_task__/MaxReturn -86.6693 MetaTest/__unnamed_task__/MinReturn -91.9096 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.1691 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 250200 ------------------------------------------------- ----------- 2025-04-02 20:01:48 | [pearl_trainer] epoch #147 | Training... 2025-04-02 20:03:19 | [pearl_trainer] epoch #147 | Evaluating... 2025-04-02 20:03:19 | [pearl_trainer] epoch #147 | Sampling for adapation and meta-testing... 2025-04-02 20:04:06 | [pearl_trainer] epoch #147 | Finished meta-testing... 2025-04-02 20:04:06 | [pearl_trainer] epoch #147 | Saving snapshot... 2025-04-02 20:04:07 | [pearl_trainer] epoch #147 | Saved 2025-04-02 20:04:07 | [pearl_trainer] epoch #147 | Time 23723.69 s 2025-04-02 20:04:07 | [pearl_trainer] epoch #147 | EpochTime 161.16 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -88.2763 MetaTest/Average/AverageReturn -88.2763 MetaTest/Average/Iteration 147 MetaTest/Average/MaxReturn -85.6438 MetaTest/Average/MinReturn -90.9741 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.17657 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.2763 MetaTest/__unnamed_task__/AverageReturn -88.2763 MetaTest/__unnamed_task__/Iteration 147 MetaTest/__unnamed_task__/MaxReturn -85.6438 MetaTest/__unnamed_task__/MinReturn -90.9741 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.17657 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 251800 ------------------------------------------------- ------------ 2025-04-02 20:04:30 | [pearl_trainer] epoch #148 | Training... 2025-04-02 20:05:59 | [pearl_trainer] epoch #148 | Evaluating... 2025-04-02 20:05:59 | [pearl_trainer] epoch #148 | Sampling for adapation and meta-testing... 2025-04-02 20:06:48 | [pearl_trainer] epoch #148 | Finished meta-testing... 2025-04-02 20:06:48 | [pearl_trainer] epoch #148 | Saving snapshot... 2025-04-02 20:06:49 | [pearl_trainer] epoch #148 | Saved 2025-04-02 20:06:49 | [pearl_trainer] epoch #148 | Time 23885.26 s 2025-04-02 20:06:49 | [pearl_trainer] epoch #148 | EpochTime 161.56 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -103.697 MetaTest/Average/AverageReturn -103.697 MetaTest/Average/Iteration 148 MetaTest/Average/MaxReturn -87.4493 MetaTest/Average/MinReturn -131.895 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 20.0162 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -103.697 MetaTest/__unnamed_task__/AverageReturn -103.697 MetaTest/__unnamed_task__/Iteration 148 MetaTest/__unnamed_task__/MaxReturn -87.4493 MetaTest/__unnamed_task__/MinReturn -131.895 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 20.0162 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 253400 ------------------------------------------------- ----------- 2025-04-02 20:07:13 | [pearl_trainer] epoch #149 | Training... 2025-04-02 20:08:38 | [pearl_trainer] epoch #149 | Evaluating... 2025-04-02 20:08:38 | [pearl_trainer] epoch #149 | Sampling for adapation and meta-testing... 2025-04-02 20:09:25 | [pearl_trainer] epoch #149 | Finished meta-testing... 2025-04-02 20:09:25 | [pearl_trainer] epoch #149 | Saving snapshot... 2025-04-02 20:09:26 | [pearl_trainer] epoch #149 | Saved 2025-04-02 20:09:26 | [pearl_trainer] epoch #149 | Time 24042.16 s 2025-04-02 20:09:26 | [pearl_trainer] epoch #149 | EpochTime 156.90 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -87.9716 MetaTest/Average/AverageReturn -87.9716 MetaTest/Average/Iteration 149 MetaTest/Average/MaxReturn -84.8967 MetaTest/Average/MinReturn -93.7673 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.10072 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -87.9716 MetaTest/__unnamed_task__/AverageReturn -87.9716 MetaTest/__unnamed_task__/Iteration 149 MetaTest/__unnamed_task__/MaxReturn -84.8967 MetaTest/__unnamed_task__/MinReturn -93.7673 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.10072 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 255000 ------------------------------------------------- ------------ 2025-04-02 20:09:48 | [pearl_trainer] epoch #150 | Training... 2025-04-02 20:11:20 | [pearl_trainer] epoch #150 | Evaluating... 2025-04-02 20:11:20 | [pearl_trainer] epoch #150 | Sampling for adapation and meta-testing... 2025-04-02 20:12:10 | [pearl_trainer] epoch #150 | Finished meta-testing... 2025-04-02 20:12:10 | [pearl_trainer] epoch #150 | Saving snapshot... 2025-04-02 20:12:11 | [pearl_trainer] epoch #150 | Saved 2025-04-02 20:12:11 | [pearl_trainer] epoch #150 | Time 24207.25 s 2025-04-02 20:12:11 | [pearl_trainer] epoch #150 | EpochTime 165.09 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -95.9936 MetaTest/Average/AverageReturn -95.9936 MetaTest/Average/Iteration 150 MetaTest/Average/MaxReturn -89.4717 MetaTest/Average/MinReturn -105.151 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.66692 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.9936 MetaTest/__unnamed_task__/AverageReturn -95.9936 MetaTest/__unnamed_task__/Iteration 150 MetaTest/__unnamed_task__/MaxReturn -89.4717 MetaTest/__unnamed_task__/MinReturn -105.151 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.66692 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 256600 ------------------------------------------------- ------------ 2025-04-02 20:12:32 | [pearl_trainer] epoch #151 | Training... 2025-04-02 20:13:52 | [pearl_trainer] epoch #151 | Evaluating... 2025-04-02 20:13:52 | [pearl_trainer] epoch #151 | Sampling for adapation and meta-testing... 2025-04-02 20:14:38 | [pearl_trainer] epoch #151 | Finished meta-testing... 2025-04-02 20:14:38 | [pearl_trainer] epoch #151 | Saving snapshot... 2025-04-02 20:14:40 | [pearl_trainer] epoch #151 | Saved 2025-04-02 20:14:40 | [pearl_trainer] epoch #151 | Time 24355.92 s 2025-04-02 20:14:40 | [pearl_trainer] epoch #151 | EpochTime 148.66 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -101.091 MetaTest/Average/AverageReturn -101.091 MetaTest/Average/Iteration 151 MetaTest/Average/MaxReturn -98.6245 MetaTest/Average/MinReturn -103.474 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.9808 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.091 MetaTest/__unnamed_task__/AverageReturn -101.091 MetaTest/__unnamed_task__/Iteration 151 MetaTest/__unnamed_task__/MaxReturn -98.6245 MetaTest/__unnamed_task__/MinReturn -103.474 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.9808 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 258200 ------------------------------------------------- ----------- 2025-04-02 20:15:06 | [pearl_trainer] epoch #152 | Training... 2025-04-02 20:16:34 | [pearl_trainer] epoch #152 | Evaluating... 2025-04-02 20:16:34 | [pearl_trainer] epoch #152 | Sampling for adapation and meta-testing... 2025-04-02 20:17:19 | [pearl_trainer] epoch #152 | Finished meta-testing... 2025-04-02 20:17:19 | [pearl_trainer] epoch #152 | Saving snapshot... 2025-04-02 20:17:20 | [pearl_trainer] epoch #152 | Saved 2025-04-02 20:17:20 | [pearl_trainer] epoch #152 | Time 24515.99 s 2025-04-02 20:17:20 | [pearl_trainer] epoch #152 | EpochTime 160.07 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -91.6599 MetaTest/Average/AverageReturn -91.6599 MetaTest/Average/Iteration 152 MetaTest/Average/MaxReturn -83.5071 MetaTest/Average/MinReturn -98.1139 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.08298 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.6599 MetaTest/__unnamed_task__/AverageReturn -91.6599 MetaTest/__unnamed_task__/Iteration 152 MetaTest/__unnamed_task__/MaxReturn -83.5071 MetaTest/__unnamed_task__/MinReturn -98.1139 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.08298 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 259800 ------------------------------------------------- ------------ 2025-04-02 20:17:42 | [pearl_trainer] epoch #153 | Training... 2025-04-02 20:19:18 | [pearl_trainer] epoch #153 | Evaluating... 2025-04-02 20:19:18 | [pearl_trainer] epoch #153 | Sampling for adapation and meta-testing... 2025-04-02 20:20:05 | [pearl_trainer] epoch #153 | Finished meta-testing... 2025-04-02 20:20:05 | [pearl_trainer] epoch #153 | Saving snapshot... 2025-04-02 20:20:06 | [pearl_trainer] epoch #153 | Saved 2025-04-02 20:20:06 | [pearl_trainer] epoch #153 | Time 24681.77 s 2025-04-02 20:20:06 | [pearl_trainer] epoch #153 | EpochTime 165.78 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -96.4208 MetaTest/Average/AverageReturn -96.4208 MetaTest/Average/Iteration 153 MetaTest/Average/MaxReturn -84.0374 MetaTest/Average/MinReturn -110.16 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.7075 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.4208 MetaTest/__unnamed_task__/AverageReturn -96.4208 MetaTest/__unnamed_task__/Iteration 153 MetaTest/__unnamed_task__/MaxReturn -84.0374 MetaTest/__unnamed_task__/MinReturn -110.16 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.7075 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 261400 ------------------------------------------------- ----------- 2025-04-02 20:20:27 | [pearl_trainer] epoch #154 | Training... 2025-04-02 20:21:54 | [pearl_trainer] epoch #154 | Evaluating... 2025-04-02 20:21:54 | [pearl_trainer] epoch #154 | Sampling for adapation and meta-testing... 2025-04-02 20:22:44 | [pearl_trainer] epoch #154 | Finished meta-testing... 2025-04-02 20:22:44 | [pearl_trainer] epoch #154 | Saving snapshot... 2025-04-02 20:22:46 | [pearl_trainer] epoch #154 | Saved 2025-04-02 20:22:46 | [pearl_trainer] epoch #154 | Time 24842.00 s 2025-04-02 20:22:46 | [pearl_trainer] epoch #154 | EpochTime 160.23 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -107.357 MetaTest/Average/AverageReturn -107.357 MetaTest/Average/Iteration 154 MetaTest/Average/MaxReturn -91.3256 MetaTest/Average/MinReturn -128.035 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 15.3426 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -107.357 MetaTest/__unnamed_task__/AverageReturn -107.357 MetaTest/__unnamed_task__/Iteration 154 MetaTest/__unnamed_task__/MaxReturn -91.3256 MetaTest/__unnamed_task__/MinReturn -128.035 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 15.3426 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 263000 ------------------------------------------------- ----------- 2025-04-02 20:23:12 | [pearl_trainer] epoch #155 | Training... 2025-04-02 20:24:40 | [pearl_trainer] epoch #155 | Evaluating... 2025-04-02 20:24:40 | [pearl_trainer] epoch #155 | Sampling for adapation and meta-testing... 2025-04-02 20:25:23 | [pearl_trainer] epoch #155 | Finished meta-testing... 2025-04-02 20:25:23 | [pearl_trainer] epoch #155 | Saving snapshot... 2025-04-02 20:25:24 | [pearl_trainer] epoch #155 | Saved 2025-04-02 20:25:24 | [pearl_trainer] epoch #155 | Time 25000.60 s 2025-04-02 20:25:24 | [pearl_trainer] epoch #155 | EpochTime 158.60 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -95.7486 MetaTest/Average/AverageReturn -95.7486 MetaTest/Average/Iteration 155 MetaTest/Average/MaxReturn -92.5418 MetaTest/Average/MinReturn -101.07 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.78897 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.7486 MetaTest/__unnamed_task__/AverageReturn -95.7486 MetaTest/__unnamed_task__/Iteration 155 MetaTest/__unnamed_task__/MaxReturn -92.5418 MetaTest/__unnamed_task__/MinReturn -101.07 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.78897 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 264600 ------------------------------------------------- ------------ 2025-04-02 20:25:45 | [pearl_trainer] epoch #156 | Training... 2025-04-02 20:27:22 | [pearl_trainer] epoch #156 | Evaluating... 2025-04-02 20:27:22 | [pearl_trainer] epoch #156 | Sampling for adapation and meta-testing... 2025-04-02 20:28:04 | [pearl_trainer] epoch #156 | Finished meta-testing... 2025-04-02 20:28:04 | [pearl_trainer] epoch #156 | Saving snapshot... 2025-04-02 20:28:06 | [pearl_trainer] epoch #156 | Saved 2025-04-02 20:28:06 | [pearl_trainer] epoch #156 | Time 25161.83 s 2025-04-02 20:28:06 | [pearl_trainer] epoch #156 | EpochTime 161.22 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -91.9824 MetaTest/Average/AverageReturn -91.9824 MetaTest/Average/Iteration 156 MetaTest/Average/MaxReturn -86.7046 MetaTest/Average/MinReturn -102.348 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.33011 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.9824 MetaTest/__unnamed_task__/AverageReturn -91.9824 MetaTest/__unnamed_task__/Iteration 156 MetaTest/__unnamed_task__/MaxReturn -86.7046 MetaTest/__unnamed_task__/MinReturn -102.348 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.33011 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 266200 ------------------------------------------------- ------------ 2025-04-02 20:28:26 | [pearl_trainer] epoch #157 | Training... 2025-04-02 20:29:59 | [pearl_trainer] epoch #157 | Evaluating... 2025-04-02 20:29:59 | [pearl_trainer] epoch #157 | Sampling for adapation and meta-testing... 2025-04-02 20:30:53 | [pearl_trainer] epoch #157 | Finished meta-testing... 2025-04-02 20:30:53 | [pearl_trainer] epoch #157 | Saving snapshot... 2025-04-02 20:30:54 | [pearl_trainer] epoch #157 | Saved 2025-04-02 20:30:54 | [pearl_trainer] epoch #157 | Time 25330.66 s 2025-04-02 20:30:54 | [pearl_trainer] epoch #157 | EpochTime 168.83 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -96.2631 MetaTest/Average/AverageReturn -96.2631 MetaTest/Average/Iteration 157 MetaTest/Average/MaxReturn -90.1186 MetaTest/Average/MinReturn -101.197 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.60297 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.2631 MetaTest/__unnamed_task__/AverageReturn -96.2631 MetaTest/__unnamed_task__/Iteration 157 MetaTest/__unnamed_task__/MaxReturn -90.1186 MetaTest/__unnamed_task__/MinReturn -101.197 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.60297 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 267800 ------------------------------------------------- ------------ 2025-04-02 20:31:18 | [pearl_trainer] epoch #158 | Training... 2025-04-02 20:32:49 | [pearl_trainer] epoch #158 | Evaluating... 2025-04-02 20:32:49 | [pearl_trainer] epoch #158 | Sampling for adapation and meta-testing... 2025-04-02 20:33:33 | [pearl_trainer] epoch #158 | Finished meta-testing... 2025-04-02 20:33:33 | [pearl_trainer] epoch #158 | Saving snapshot... 2025-04-02 20:33:34 | [pearl_trainer] epoch #158 | Saved 2025-04-02 20:33:34 | [pearl_trainer] epoch #158 | Time 25490.32 s 2025-04-02 20:33:34 | [pearl_trainer] epoch #158 | EpochTime 159.66 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -91.6002 MetaTest/Average/AverageReturn -91.6002 MetaTest/Average/Iteration 158 MetaTest/Average/MaxReturn -86.1517 MetaTest/Average/MinReturn -96.7426 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.32912 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.6002 MetaTest/__unnamed_task__/AverageReturn -91.6002 MetaTest/__unnamed_task__/Iteration 158 MetaTest/__unnamed_task__/MaxReturn -86.1517 MetaTest/__unnamed_task__/MinReturn -96.7426 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.32912 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 269400 ------------------------------------------------- ------------ 2025-04-02 20:33:57 | [pearl_trainer] epoch #159 | Training... 2025-04-02 20:35:27 | [pearl_trainer] epoch #159 | Evaluating... 2025-04-02 20:35:27 | [pearl_trainer] epoch #159 | Sampling for adapation and meta-testing... 2025-04-02 20:36:18 | [pearl_trainer] epoch #159 | Finished meta-testing... 2025-04-02 20:36:18 | [pearl_trainer] epoch #159 | Saving snapshot... 2025-04-02 20:36:19 | [pearl_trainer] epoch #159 | Saved 2025-04-02 20:36:19 | [pearl_trainer] epoch #159 | Time 25655.09 s 2025-04-02 20:36:19 | [pearl_trainer] epoch #159 | EpochTime 164.77 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -89.3765 MetaTest/Average/AverageReturn -89.3765 MetaTest/Average/Iteration 159 MetaTest/Average/MaxReturn -82.3947 MetaTest/Average/MinReturn -99.7855 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.50197 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -89.3765 MetaTest/__unnamed_task__/AverageReturn -89.3765 MetaTest/__unnamed_task__/Iteration 159 MetaTest/__unnamed_task__/MaxReturn -82.3947 MetaTest/__unnamed_task__/MinReturn -99.7855 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.50197 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 271000 ------------------------------------------------- ------------ 2025-04-02 20:36:41 | [pearl_trainer] epoch #160 | Training... 2025-04-02 20:38:10 | [pearl_trainer] epoch #160 | Evaluating... 2025-04-02 20:38:10 | [pearl_trainer] epoch #160 | Sampling for adapation and meta-testing... 2025-04-02 20:39:07 | [pearl_trainer] epoch #160 | Finished meta-testing... 2025-04-02 20:39:07 | [pearl_trainer] epoch #160 | Saving snapshot... 2025-04-02 20:39:08 | [pearl_trainer] epoch #160 | Saved 2025-04-02 20:39:08 | [pearl_trainer] epoch #160 | Time 25824.22 s 2025-04-02 20:39:08 | [pearl_trainer] epoch #160 | EpochTime 169.12 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -98.1011 MetaTest/Average/AverageReturn -98.1011 MetaTest/Average/Iteration 160 MetaTest/Average/MaxReturn -86.8852 MetaTest/Average/MinReturn -117.974 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.0913 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.1011 MetaTest/__unnamed_task__/AverageReturn -98.1011 MetaTest/__unnamed_task__/Iteration 160 MetaTest/__unnamed_task__/MaxReturn -86.8852 MetaTest/__unnamed_task__/MinReturn -117.974 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.0913 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 272600 ------------------------------------------------- ----------- 2025-04-02 20:39:29 | [pearl_trainer] epoch #161 | Training... 2025-04-02 20:40:51 | [pearl_trainer] epoch #161 | Evaluating... 2025-04-02 20:40:51 | [pearl_trainer] epoch #161 | Sampling for adapation and meta-testing... 2025-04-02 20:41:42 | [pearl_trainer] epoch #161 | Finished meta-testing... 2025-04-02 20:41:42 | [pearl_trainer] epoch #161 | Saving snapshot... 2025-04-02 20:41:43 | [pearl_trainer] epoch #161 | Saved 2025-04-02 20:41:43 | [pearl_trainer] epoch #161 | Time 25979.35 s 2025-04-02 20:41:43 | [pearl_trainer] epoch #161 | EpochTime 155.13 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.4333 MetaTest/Average/AverageReturn -90.4333 MetaTest/Average/Iteration 161 MetaTest/Average/MaxReturn -81.0883 MetaTest/Average/MinReturn -95.8519 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.63588 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.4333 MetaTest/__unnamed_task__/AverageReturn -90.4333 MetaTest/__unnamed_task__/Iteration 161 MetaTest/__unnamed_task__/MaxReturn -81.0883 MetaTest/__unnamed_task__/MinReturn -95.8519 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.63588 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 274200 ------------------------------------------------- ------------ 2025-04-02 20:42:06 | [pearl_trainer] epoch #162 | Training... 2025-04-02 20:43:34 | [pearl_trainer] epoch #162 | Evaluating... 2025-04-02 20:43:34 | [pearl_trainer] epoch #162 | Sampling for adapation and meta-testing... 2025-04-02 20:44:19 | [pearl_trainer] epoch #162 | Finished meta-testing... 2025-04-02 20:44:19 | [pearl_trainer] epoch #162 | Saving snapshot... 2025-04-02 20:44:21 | [pearl_trainer] epoch #162 | Saved 2025-04-02 20:44:21 | [pearl_trainer] epoch #162 | Time 26136.79 s 2025-04-02 20:44:21 | [pearl_trainer] epoch #162 | EpochTime 157.44 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -92.2173 MetaTest/Average/AverageReturn -92.2173 MetaTest/Average/Iteration 162 MetaTest/Average/MaxReturn -88.9824 MetaTest/Average/MinReturn -94.5178 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.35447 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.2173 MetaTest/__unnamed_task__/AverageReturn -92.2173 MetaTest/__unnamed_task__/Iteration 162 MetaTest/__unnamed_task__/MaxReturn -88.9824 MetaTest/__unnamed_task__/MinReturn -94.5178 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.35447 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 275800 ------------------------------------------------- ------------ 2025-04-02 20:44:41 | [pearl_trainer] epoch #163 | Training... 2025-04-02 20:46:14 | [pearl_trainer] epoch #163 | Evaluating... 2025-04-02 20:46:14 | [pearl_trainer] epoch #163 | Sampling for adapation and meta-testing... 2025-04-02 20:47:04 | [pearl_trainer] epoch #163 | Finished meta-testing... 2025-04-02 20:47:04 | [pearl_trainer] epoch #163 | Saving snapshot... 2025-04-02 20:47:05 | [pearl_trainer] epoch #163 | Saved 2025-04-02 20:47:05 | [pearl_trainer] epoch #163 | Time 26300.97 s 2025-04-02 20:47:05 | [pearl_trainer] epoch #163 | EpochTime 164.18 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -98.2695 MetaTest/Average/AverageReturn -98.2695 MetaTest/Average/Iteration 163 MetaTest/Average/MaxReturn -88.3246 MetaTest/Average/MinReturn -117.364 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.5057 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.2695 MetaTest/__unnamed_task__/AverageReturn -98.2695 MetaTest/__unnamed_task__/Iteration 163 MetaTest/__unnamed_task__/MaxReturn -88.3246 MetaTest/__unnamed_task__/MinReturn -117.364 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.5057 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 277400 ------------------------------------------------- ----------- 2025-04-02 20:47:27 | [pearl_trainer] epoch #164 | Training... 2025-04-02 20:48:57 | [pearl_trainer] epoch #164 | Evaluating... 2025-04-02 20:48:57 | [pearl_trainer] epoch #164 | Sampling for adapation and meta-testing... 2025-04-02 20:49:46 | [pearl_trainer] epoch #164 | Finished meta-testing... 2025-04-02 20:49:46 | [pearl_trainer] epoch #164 | Saving snapshot... 2025-04-02 20:49:48 | [pearl_trainer] epoch #164 | Saved 2025-04-02 20:49:48 | [pearl_trainer] epoch #164 | Time 26463.76 s 2025-04-02 20:49:48 | [pearl_trainer] epoch #164 | EpochTime 162.80 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -101.606 MetaTest/Average/AverageReturn -101.606 MetaTest/Average/Iteration 164 MetaTest/Average/MaxReturn -94.0494 MetaTest/Average/MinReturn -105.471 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.34371 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.606 MetaTest/__unnamed_task__/AverageReturn -101.606 MetaTest/__unnamed_task__/Iteration 164 MetaTest/__unnamed_task__/MaxReturn -94.0494 MetaTest/__unnamed_task__/MinReturn -105.471 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.34371 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 279000 ------------------------------------------------- ------------ 2025-04-02 20:50:12 | [pearl_trainer] epoch #165 | Training... 2025-04-02 20:51:45 | [pearl_trainer] epoch #165 | Evaluating... 2025-04-02 20:51:45 | [pearl_trainer] epoch #165 | Sampling for adapation and meta-testing... 2025-04-02 20:52:35 | [pearl_trainer] epoch #165 | Finished meta-testing... 2025-04-02 20:52:35 | [pearl_trainer] epoch #165 | Saving snapshot... 2025-04-02 20:52:36 | [pearl_trainer] epoch #165 | Saved 2025-04-02 20:52:36 | [pearl_trainer] epoch #165 | Time 26631.96 s 2025-04-02 20:52:36 | [pearl_trainer] epoch #165 | EpochTime 168.19 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -105.369 MetaTest/Average/AverageReturn -105.369 MetaTest/Average/Iteration 165 MetaTest/Average/MaxReturn -103.075 MetaTest/Average/MinReturn -109.005 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.60064 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -105.369 MetaTest/__unnamed_task__/AverageReturn -105.369 MetaTest/__unnamed_task__/Iteration 165 MetaTest/__unnamed_task__/MaxReturn -103.075 MetaTest/__unnamed_task__/MinReturn -109.005 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.60064 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 280600 ------------------------------------------------- ------------ 2025-04-02 20:52:58 | [pearl_trainer] epoch #166 | Training... 2025-04-02 20:54:28 | [pearl_trainer] epoch #166 | Evaluating... 2025-04-02 20:54:28 | [pearl_trainer] epoch #166 | Sampling for adapation and meta-testing... 2025-04-02 20:55:23 | [pearl_trainer] epoch #166 | Finished meta-testing... 2025-04-02 20:55:23 | [pearl_trainer] epoch #166 | Saving snapshot... 2025-04-02 20:55:24 | [pearl_trainer] epoch #166 | Saved 2025-04-02 20:55:24 | [pearl_trainer] epoch #166 | Time 26800.19 s 2025-04-02 20:55:24 | [pearl_trainer] epoch #166 | EpochTime 168.22 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -92.1752 MetaTest/Average/AverageReturn -92.1752 MetaTest/Average/Iteration 166 MetaTest/Average/MaxReturn -88.0494 MetaTest/Average/MinReturn -94.9598 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.97628 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.1752 MetaTest/__unnamed_task__/AverageReturn -92.1752 MetaTest/__unnamed_task__/Iteration 166 MetaTest/__unnamed_task__/MaxReturn -88.0494 MetaTest/__unnamed_task__/MinReturn -94.9598 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.97628 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 282200 ------------------------------------------------- ------------ 2025-04-02 20:55:46 | [pearl_trainer] epoch #167 | Training... 2025-04-02 20:57:08 | [pearl_trainer] epoch #167 | Evaluating... 2025-04-02 20:57:08 | [pearl_trainer] epoch #167 | Sampling for adapation and meta-testing... 2025-04-02 20:57:56 | [pearl_trainer] epoch #167 | Finished meta-testing... 2025-04-02 20:57:56 | [pearl_trainer] epoch #167 | Saving snapshot... 2025-04-02 20:57:57 | [pearl_trainer] epoch #167 | Saved 2025-04-02 20:57:57 | [pearl_trainer] epoch #167 | Time 26953.61 s 2025-04-02 20:57:57 | [pearl_trainer] epoch #167 | EpochTime 153.42 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -87.1309 MetaTest/Average/AverageReturn -87.1309 MetaTest/Average/Iteration 167 MetaTest/Average/MaxReturn -84.1839 MetaTest/Average/MinReturn -92.4904 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.79597 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -87.1309 MetaTest/__unnamed_task__/AverageReturn -87.1309 MetaTest/__unnamed_task__/Iteration 167 MetaTest/__unnamed_task__/MaxReturn -84.1839 MetaTest/__unnamed_task__/MinReturn -92.4904 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.79597 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 283800 ------------------------------------------------- ------------ 2025-04-02 20:58:21 | [pearl_trainer] epoch #168 | Training... 2025-04-02 20:59:54 | [pearl_trainer] epoch #168 | Evaluating... 2025-04-02 20:59:54 | [pearl_trainer] epoch #168 | Sampling for adapation and meta-testing... 2025-04-02 21:00:40 | [pearl_trainer] epoch #168 | Finished meta-testing... 2025-04-02 21:00:40 | [pearl_trainer] epoch #168 | Saving snapshot... 2025-04-02 21:00:41 | [pearl_trainer] epoch #168 | Saved 2025-04-02 21:00:41 | [pearl_trainer] epoch #168 | Time 27116.77 s 2025-04-02 21:00:41 | [pearl_trainer] epoch #168 | EpochTime 163.16 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -92.1033 MetaTest/Average/AverageReturn -92.1033 MetaTest/Average/Iteration 168 MetaTest/Average/MaxReturn -90.2476 MetaTest/Average/MinReturn -93.252 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.32455 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.1033 MetaTest/__unnamed_task__/AverageReturn -92.1033 MetaTest/__unnamed_task__/Iteration 168 MetaTest/__unnamed_task__/MaxReturn -90.2476 MetaTest/__unnamed_task__/MinReturn -93.252 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.32455 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 285400 ------------------------------------------------- ------------ 2025-04-02 21:01:03 | [pearl_trainer] epoch #169 | Training... 2025-04-02 21:02:29 | [pearl_trainer] epoch #169 | Evaluating... 2025-04-02 21:02:29 | [pearl_trainer] epoch #169 | Sampling for adapation and meta-testing... 2025-04-02 21:03:20 | [pearl_trainer] epoch #169 | Finished meta-testing... 2025-04-02 21:03:20 | [pearl_trainer] epoch #169 | Saving snapshot... 2025-04-02 21:03:22 | [pearl_trainer] epoch #169 | Saved 2025-04-02 21:03:22 | [pearl_trainer] epoch #169 | Time 27277.85 s 2025-04-02 21:03:22 | [pearl_trainer] epoch #169 | EpochTime 161.08 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -96.1232 MetaTest/Average/AverageReturn -96.1232 MetaTest/Average/Iteration 169 MetaTest/Average/MaxReturn -93.6665 MetaTest/Average/MinReturn -100.819 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.32152 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.1232 MetaTest/__unnamed_task__/AverageReturn -96.1232 MetaTest/__unnamed_task__/Iteration 169 MetaTest/__unnamed_task__/MaxReturn -93.6665 MetaTest/__unnamed_task__/MinReturn -100.819 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.32152 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 287000 ------------------------------------------------- ------------ 2025-04-02 21:03:46 | [pearl_trainer] epoch #170 | Training... 2025-04-02 21:05:16 | [pearl_trainer] epoch #170 | Evaluating... 2025-04-02 21:05:16 | [pearl_trainer] epoch #170 | Sampling for adapation and meta-testing... 2025-04-02 21:06:04 | [pearl_trainer] epoch #170 | Finished meta-testing... 2025-04-02 21:06:04 | [pearl_trainer] epoch #170 | Saving snapshot... 2025-04-02 21:06:05 | [pearl_trainer] epoch #170 | Saved 2025-04-02 21:06:05 | [pearl_trainer] epoch #170 | Time 27441.66 s 2025-04-02 21:06:05 | [pearl_trainer] epoch #170 | EpochTime 163.80 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -95.1015 MetaTest/Average/AverageReturn -95.1015 MetaTest/Average/Iteration 170 MetaTest/Average/MaxReturn -87.8405 MetaTest/Average/MinReturn -103.354 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.37215 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.1015 MetaTest/__unnamed_task__/AverageReturn -95.1015 MetaTest/__unnamed_task__/Iteration 170 MetaTest/__unnamed_task__/MaxReturn -87.8405 MetaTest/__unnamed_task__/MinReturn -103.354 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.37215 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 288600 ------------------------------------------------- ------------ 2025-04-02 21:06:29 | [pearl_trainer] epoch #171 | Training... 2025-04-02 21:08:03 | [pearl_trainer] epoch #171 | Evaluating... 2025-04-02 21:08:03 | [pearl_trainer] epoch #171 | Sampling for adapation and meta-testing... 2025-04-02 21:08:49 | [pearl_trainer] epoch #171 | Finished meta-testing... 2025-04-02 21:08:49 | [pearl_trainer] epoch #171 | Saving snapshot... 2025-04-02 21:08:50 | [pearl_trainer] epoch #171 | Saved 2025-04-02 21:08:50 | [pearl_trainer] epoch #171 | Time 27605.98 s 2025-04-02 21:08:50 | [pearl_trainer] epoch #171 | EpochTime 164.32 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -109.48 MetaTest/Average/AverageReturn -109.48 MetaTest/Average/Iteration 171 MetaTest/Average/MaxReturn -98.3579 MetaTest/Average/MinReturn -119.567 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.68948 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -109.48 MetaTest/__unnamed_task__/AverageReturn -109.48 MetaTest/__unnamed_task__/Iteration 171 MetaTest/__unnamed_task__/MaxReturn -98.3579 MetaTest/__unnamed_task__/MinReturn -119.567 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.68948 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 290200 ------------------------------------------------- ------------ 2025-04-02 21:09:14 | [pearl_trainer] epoch #172 | Training... 2025-04-02 21:10:44 | [pearl_trainer] epoch #172 | Evaluating... 2025-04-02 21:10:44 | [pearl_trainer] epoch #172 | Sampling for adapation and meta-testing... 2025-04-02 21:11:31 | [pearl_trainer] epoch #172 | Finished meta-testing... 2025-04-02 21:11:31 | [pearl_trainer] epoch #172 | Saving snapshot... 2025-04-02 21:11:32 | [pearl_trainer] epoch #172 | Saved 2025-04-02 21:11:32 | [pearl_trainer] epoch #172 | Time 27768.57 s 2025-04-02 21:11:32 | [pearl_trainer] epoch #172 | EpochTime 162.58 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -89.5058 MetaTest/Average/AverageReturn -89.5058 MetaTest/Average/Iteration 172 MetaTest/Average/MaxReturn -80.8711 MetaTest/Average/MinReturn -99.2511 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.54458 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -89.5058 MetaTest/__unnamed_task__/AverageReturn -89.5058 MetaTest/__unnamed_task__/Iteration 172 MetaTest/__unnamed_task__/MaxReturn -80.8711 MetaTest/__unnamed_task__/MinReturn -99.2511 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.54458 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 291800 ------------------------------------------------- ------------ 2025-04-02 21:11:56 | [pearl_trainer] epoch #173 | Training... 2025-04-02 21:13:21 | [pearl_trainer] epoch #173 | Evaluating... 2025-04-02 21:13:21 | [pearl_trainer] epoch #173 | Sampling for adapation and meta-testing... 2025-04-02 21:14:11 | [pearl_trainer] epoch #173 | Finished meta-testing... 2025-04-02 21:14:11 | [pearl_trainer] epoch #173 | Saving snapshot... 2025-04-02 21:14:12 | [pearl_trainer] epoch #173 | Saved 2025-04-02 21:14:12 | [pearl_trainer] epoch #173 | Time 27928.51 s 2025-04-02 21:14:12 | [pearl_trainer] epoch #173 | EpochTime 159.95 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -92.6664 MetaTest/Average/AverageReturn -92.6664 MetaTest/Average/Iteration 173 MetaTest/Average/MaxReturn -89.8857 MetaTest/Average/MinReturn -97.2114 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.24049 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.6664 MetaTest/__unnamed_task__/AverageReturn -92.6664 MetaTest/__unnamed_task__/Iteration 173 MetaTest/__unnamed_task__/MaxReturn -89.8857 MetaTest/__unnamed_task__/MinReturn -97.2114 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.24049 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 293400 ------------------------------------------------- ------------ 2025-04-02 21:14:37 | [pearl_trainer] epoch #174 | Training... 2025-04-02 21:16:12 | [pearl_trainer] epoch #174 | Evaluating... 2025-04-02 21:16:12 | [pearl_trainer] epoch #174 | Sampling for adapation and meta-testing... 2025-04-02 21:16:57 | [pearl_trainer] epoch #174 | Finished meta-testing... 2025-04-02 21:16:57 | [pearl_trainer] epoch #174 | Saving snapshot... 2025-04-02 21:16:58 | [pearl_trainer] epoch #174 | Saved 2025-04-02 21:16:58 | [pearl_trainer] epoch #174 | Time 28094.48 s 2025-04-02 21:16:58 | [pearl_trainer] epoch #174 | EpochTime 165.96 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -96.0554 MetaTest/Average/AverageReturn -96.0554 MetaTest/Average/Iteration 174 MetaTest/Average/MaxReturn -92.9924 MetaTest/Average/MinReturn -99.0884 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.48876 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.0554 MetaTest/__unnamed_task__/AverageReturn -96.0554 MetaTest/__unnamed_task__/Iteration 174 MetaTest/__unnamed_task__/MaxReturn -92.9924 MetaTest/__unnamed_task__/MinReturn -99.0884 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.48876 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 295000 ------------------------------------------------- ------------ 2025-04-02 21:17:20 | [pearl_trainer] epoch #175 | Training... 2025-04-02 21:18:57 | [pearl_trainer] epoch #175 | Evaluating... 2025-04-02 21:18:57 | [pearl_trainer] epoch #175 | Sampling for adapation and meta-testing... 2025-04-02 21:19:44 | [pearl_trainer] epoch #175 | Finished meta-testing... 2025-04-02 21:19:44 | [pearl_trainer] epoch #175 | Saving snapshot... 2025-04-02 21:19:45 | [pearl_trainer] epoch #175 | Saved 2025-04-02 21:19:45 | [pearl_trainer] epoch #175 | Time 28261.57 s 2025-04-02 21:19:45 | [pearl_trainer] epoch #175 | EpochTime 167.09 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.6133 MetaTest/Average/AverageReturn -93.6133 MetaTest/Average/Iteration 175 MetaTest/Average/MaxReturn -84.7177 MetaTest/Average/MinReturn -101.505 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.89009 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.6133 MetaTest/__unnamed_task__/AverageReturn -93.6133 MetaTest/__unnamed_task__/Iteration 175 MetaTest/__unnamed_task__/MaxReturn -84.7177 MetaTest/__unnamed_task__/MinReturn -101.505 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.89009 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 296600 ------------------------------------------------- ------------ 2025-04-02 21:20:07 | [pearl_trainer] epoch #176 | Training... 2025-04-02 21:21:33 | [pearl_trainer] epoch #176 | Evaluating... 2025-04-02 21:21:33 | [pearl_trainer] epoch #176 | Sampling for adapation and meta-testing... 2025-04-02 21:22:30 | [pearl_trainer] epoch #176 | Finished meta-testing... 2025-04-02 21:22:30 | [pearl_trainer] epoch #176 | Saving snapshot... 2025-04-02 21:22:31 | [pearl_trainer] epoch #176 | Saved 2025-04-02 21:22:31 | [pearl_trainer] epoch #176 | Time 28427.26 s 2025-04-02 21:22:31 | [pearl_trainer] epoch #176 | EpochTime 165.68 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.3112 MetaTest/Average/AverageReturn -93.3112 MetaTest/Average/Iteration 176 MetaTest/Average/MaxReturn -88.7074 MetaTest/Average/MinReturn -97.9368 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.76791 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.3112 MetaTest/__unnamed_task__/AverageReturn -93.3112 MetaTest/__unnamed_task__/Iteration 176 MetaTest/__unnamed_task__/MaxReturn -88.7074 MetaTest/__unnamed_task__/MinReturn -97.9368 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.76791 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 298200 ------------------------------------------------- ------------ 2025-04-02 21:22:54 | [pearl_trainer] epoch #177 | Training... 2025-04-02 21:24:18 | [pearl_trainer] epoch #177 | Evaluating... 2025-04-02 21:24:18 | [pearl_trainer] epoch #177 | Sampling for adapation and meta-testing... 2025-04-02 21:25:04 | [pearl_trainer] epoch #177 | Finished meta-testing... 2025-04-02 21:25:04 | [pearl_trainer] epoch #177 | Saving snapshot... 2025-04-02 21:25:06 | [pearl_trainer] epoch #177 | Saved 2025-04-02 21:25:06 | [pearl_trainer] epoch #177 | Time 28581.91 s 2025-04-02 21:25:06 | [pearl_trainer] epoch #177 | EpochTime 154.65 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -94.756 MetaTest/Average/AverageReturn -94.756 MetaTest/Average/Iteration 177 MetaTest/Average/MaxReturn -92.4229 MetaTest/Average/MinReturn -96.7412 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.78 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.756 MetaTest/__unnamed_task__/AverageReturn -94.756 MetaTest/__unnamed_task__/Iteration 177 MetaTest/__unnamed_task__/MaxReturn -92.4229 MetaTest/__unnamed_task__/MinReturn -96.7412 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.78 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 299800 ------------------------------------------------- ----------- 2025-04-02 21:25:29 | [pearl_trainer] epoch #178 | Training... 2025-04-02 21:27:06 | [pearl_trainer] epoch #178 | Evaluating... 2025-04-02 21:27:06 | [pearl_trainer] epoch #178 | Sampling for adapation and meta-testing... 2025-04-02 21:27:52 | [pearl_trainer] epoch #178 | Finished meta-testing... 2025-04-02 21:27:52 | [pearl_trainer] epoch #178 | Saving snapshot... 2025-04-02 21:27:53 | [pearl_trainer] epoch #178 | Saved 2025-04-02 21:27:53 | [pearl_trainer] epoch #178 | Time 28749.11 s 2025-04-02 21:27:53 | [pearl_trainer] epoch #178 | EpochTime 167.20 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.635 MetaTest/Average/AverageReturn -97.635 MetaTest/Average/Iteration 178 MetaTest/Average/MaxReturn -95.7737 MetaTest/Average/MinReturn -99.708 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.61313 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.635 MetaTest/__unnamed_task__/AverageReturn -97.635 MetaTest/__unnamed_task__/Iteration 178 MetaTest/__unnamed_task__/MaxReturn -95.7737 MetaTest/__unnamed_task__/MinReturn -99.708 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.61313 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 301400 ------------------------------------------------- ------------ 2025-04-02 21:28:17 | [pearl_trainer] epoch #179 | Training... 2025-04-02 21:29:46 | [pearl_trainer] epoch #179 | Evaluating... 2025-04-02 21:29:46 | [pearl_trainer] epoch #179 | Sampling for adapation and meta-testing... 2025-04-02 21:30:36 | [pearl_trainer] epoch #179 | Finished meta-testing... 2025-04-02 21:30:36 | [pearl_trainer] epoch #179 | Saving snapshot... 2025-04-02 21:30:37 | [pearl_trainer] epoch #179 | Saved 2025-04-02 21:30:37 | [pearl_trainer] epoch #179 | Time 28913.57 s 2025-04-02 21:30:37 | [pearl_trainer] epoch #179 | EpochTime 164.45 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.1077 MetaTest/Average/AverageReturn -90.1077 MetaTest/Average/Iteration 179 MetaTest/Average/MaxReturn -84.7751 MetaTest/Average/MinReturn -93.9414 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.88935 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.1077 MetaTest/__unnamed_task__/AverageReturn -90.1077 MetaTest/__unnamed_task__/Iteration 179 MetaTest/__unnamed_task__/MaxReturn -84.7751 MetaTest/__unnamed_task__/MinReturn -93.9414 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.88935 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 303000 ------------------------------------------------- ------------ 2025-04-02 21:31:01 | [pearl_trainer] epoch #180 | Training... 2025-04-02 21:32:29 | [pearl_trainer] epoch #180 | Evaluating... 2025-04-02 21:32:29 | [pearl_trainer] epoch #180 | Sampling for adapation and meta-testing... 2025-04-02 21:33:12 | [pearl_trainer] epoch #180 | Finished meta-testing... 2025-04-02 21:33:12 | [pearl_trainer] epoch #180 | Saving snapshot... 2025-04-02 21:33:14 | [pearl_trainer] epoch #180 | Saved 2025-04-02 21:33:14 | [pearl_trainer] epoch #180 | Time 29069.71 s 2025-04-02 21:33:14 | [pearl_trainer] epoch #180 | EpochTime 156.14 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -108.449 MetaTest/Average/AverageReturn -108.449 MetaTest/Average/Iteration 180 MetaTest/Average/MaxReturn -102.126 MetaTest/Average/MinReturn -113.296 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.6779 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -108.449 MetaTest/__unnamed_task__/AverageReturn -108.449 MetaTest/__unnamed_task__/Iteration 180 MetaTest/__unnamed_task__/MaxReturn -102.126 MetaTest/__unnamed_task__/MinReturn -113.296 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.6779 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 304600 ------------------------------------------------- ----------- 2025-04-02 21:33:35 | [pearl_trainer] epoch #181 | Training... 2025-04-02 21:35:14 | [pearl_trainer] epoch #181 | Evaluating... 2025-04-02 21:35:14 | [pearl_trainer] epoch #181 | Sampling for adapation and meta-testing... 2025-04-02 21:36:08 | [pearl_trainer] epoch #181 | Finished meta-testing... 2025-04-02 21:36:08 | [pearl_trainer] epoch #181 | Saving snapshot... 2025-04-02 21:36:09 | [pearl_trainer] epoch #181 | Saved 2025-04-02 21:36:09 | [pearl_trainer] epoch #181 | Time 29245.16 s 2025-04-02 21:36:09 | [pearl_trainer] epoch #181 | EpochTime 175.45 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -113.554 MetaTest/Average/AverageReturn -113.554 MetaTest/Average/Iteration 181 MetaTest/Average/MaxReturn -108.941 MetaTest/Average/MinReturn -118.482 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.90151 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -113.554 MetaTest/__unnamed_task__/AverageReturn -113.554 MetaTest/__unnamed_task__/Iteration 181 MetaTest/__unnamed_task__/MaxReturn -108.941 MetaTest/__unnamed_task__/MinReturn -118.482 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.90151 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 306200 ------------------------------------------------- ------------ 2025-04-02 21:36:30 | [pearl_trainer] epoch #182 | Training... 2025-04-02 21:37:53 | [pearl_trainer] epoch #182 | Evaluating... 2025-04-02 21:37:53 | [pearl_trainer] epoch #182 | Sampling for adapation and meta-testing... 2025-04-02 21:38:47 | [pearl_trainer] epoch #182 | Finished meta-testing... 2025-04-02 21:38:47 | [pearl_trainer] epoch #182 | Saving snapshot... 2025-04-02 21:38:48 | [pearl_trainer] epoch #182 | Saved 2025-04-02 21:38:48 | [pearl_trainer] epoch #182 | Time 29404.48 s 2025-04-02 21:38:48 | [pearl_trainer] epoch #182 | EpochTime 159.32 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -111.212 MetaTest/Average/AverageReturn -111.212 MetaTest/Average/Iteration 182 MetaTest/Average/MaxReturn -109.118 MetaTest/Average/MinReturn -113.215 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.67352 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.212 MetaTest/__unnamed_task__/AverageReturn -111.212 MetaTest/__unnamed_task__/Iteration 182 MetaTest/__unnamed_task__/MaxReturn -109.118 MetaTest/__unnamed_task__/MinReturn -113.215 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.67352 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 307800 ------------------------------------------------- ------------ 2025-04-02 21:39:10 | [pearl_trainer] epoch #183 | Training... 2025-04-02 21:40:34 | [pearl_trainer] epoch #183 | Evaluating... 2025-04-02 21:40:34 | [pearl_trainer] epoch #183 | Sampling for adapation and meta-testing... 2025-04-02 21:41:22 | [pearl_trainer] epoch #183 | Finished meta-testing... 2025-04-02 21:41:22 | [pearl_trainer] epoch #183 | Saving snapshot... 2025-04-02 21:41:23 | [pearl_trainer] epoch #183 | Saved 2025-04-02 21:41:23 | [pearl_trainer] epoch #183 | Time 29559.18 s 2025-04-02 21:41:23 | [pearl_trainer] epoch #183 | EpochTime 154.70 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -114.974 MetaTest/Average/AverageReturn -114.974 MetaTest/Average/Iteration 183 MetaTest/Average/MaxReturn -109.117 MetaTest/Average/MinReturn -120.58 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.68305 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -114.974 MetaTest/__unnamed_task__/AverageReturn -114.974 MetaTest/__unnamed_task__/Iteration 183 MetaTest/__unnamed_task__/MaxReturn -109.117 MetaTest/__unnamed_task__/MinReturn -120.58 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.68305 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 309400 ------------------------------------------------- ------------ 2025-04-02 21:41:47 | [pearl_trainer] epoch #184 | Training... 2025-04-02 21:43:20 | [pearl_trainer] epoch #184 | Evaluating... 2025-04-02 21:43:20 | [pearl_trainer] epoch #184 | Sampling for adapation and meta-testing... 2025-04-02 21:44:05 | [pearl_trainer] epoch #184 | Finished meta-testing... 2025-04-02 21:44:05 | [pearl_trainer] epoch #184 | Saving snapshot... 2025-04-02 21:44:06 | [pearl_trainer] epoch #184 | Saved 2025-04-02 21:44:06 | [pearl_trainer] epoch #184 | Time 29722.35 s 2025-04-02 21:44:06 | [pearl_trainer] epoch #184 | EpochTime 163.17 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -96.8211 MetaTest/Average/AverageReturn -96.8211 MetaTest/Average/Iteration 184 MetaTest/Average/MaxReturn -84.3362 MetaTest/Average/MinReturn -118.751 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 15.5566 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.8211 MetaTest/__unnamed_task__/AverageReturn -96.8211 MetaTest/__unnamed_task__/Iteration 184 MetaTest/__unnamed_task__/MaxReturn -84.3362 MetaTest/__unnamed_task__/MinReturn -118.751 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 15.5566 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 311000 ------------------------------------------------- ----------- 2025-04-02 21:44:27 | [pearl_trainer] epoch #185 | Training... 2025-04-02 21:45:50 | [pearl_trainer] epoch #185 | Evaluating... 2025-04-02 21:45:50 | [pearl_trainer] epoch #185 | Sampling for adapation and meta-testing... 2025-04-02 21:46:42 | [pearl_trainer] epoch #185 | Finished meta-testing... 2025-04-02 21:46:42 | [pearl_trainer] epoch #185 | Saving snapshot... 2025-04-02 21:46:44 | [pearl_trainer] epoch #185 | Saved 2025-04-02 21:46:44 | [pearl_trainer] epoch #185 | Time 29879.92 s 2025-04-02 21:46:44 | [pearl_trainer] epoch #185 | EpochTime 157.56 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -91.7894 MetaTest/Average/AverageReturn -91.7894 MetaTest/Average/Iteration 185 MetaTest/Average/MaxReturn -89.0968 MetaTest/Average/MinReturn -93.8397 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.98882 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.7894 MetaTest/__unnamed_task__/AverageReturn -91.7894 MetaTest/__unnamed_task__/Iteration 185 MetaTest/__unnamed_task__/MaxReturn -89.0968 MetaTest/__unnamed_task__/MinReturn -93.8397 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.98882 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 312600 ------------------------------------------------- ------------ 2025-04-02 21:47:04 | [pearl_trainer] epoch #186 | Training... 2025-04-02 21:48:33 | [pearl_trainer] epoch #186 | Evaluating... 2025-04-02 21:48:33 | [pearl_trainer] epoch #186 | Sampling for adapation and meta-testing... 2025-04-02 21:49:21 | [pearl_trainer] epoch #186 | Finished meta-testing... 2025-04-02 21:49:21 | [pearl_trainer] epoch #186 | Saving snapshot... 2025-04-02 21:49:22 | [pearl_trainer] epoch #186 | Saved 2025-04-02 21:49:22 | [pearl_trainer] epoch #186 | Time 30038.31 s 2025-04-02 21:49:22 | [pearl_trainer] epoch #186 | EpochTime 158.39 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.1341 MetaTest/Average/AverageReturn -97.1341 MetaTest/Average/Iteration 186 MetaTest/Average/MaxReturn -85.3339 MetaTest/Average/MinReturn -104.754 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.46128 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.1341 MetaTest/__unnamed_task__/AverageReturn -97.1341 MetaTest/__unnamed_task__/Iteration 186 MetaTest/__unnamed_task__/MaxReturn -85.3339 MetaTest/__unnamed_task__/MinReturn -104.754 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.46128 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 314200 ------------------------------------------------- ------------ 2025-04-02 21:49:45 | [pearl_trainer] epoch #187 | Training... 2025-04-02 21:51:14 | [pearl_trainer] epoch #187 | Evaluating... 2025-04-02 21:51:14 | [pearl_trainer] epoch #187 | Sampling for adapation and meta-testing... 2025-04-02 21:51:59 | [pearl_trainer] epoch #187 | Finished meta-testing... 2025-04-02 21:51:59 | [pearl_trainer] epoch #187 | Saving snapshot... 2025-04-02 21:52:00 | [pearl_trainer] epoch #187 | Saved 2025-04-02 21:52:00 | [pearl_trainer] epoch #187 | Time 30196.26 s 2025-04-02 21:52:00 | [pearl_trainer] epoch #187 | EpochTime 157.95 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -108.303 MetaTest/Average/AverageReturn -108.303 MetaTest/Average/Iteration 187 MetaTest/Average/MaxReturn -100.273 MetaTest/Average/MinReturn -123.662 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.8644 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -108.303 MetaTest/__unnamed_task__/AverageReturn -108.303 MetaTest/__unnamed_task__/Iteration 187 MetaTest/__unnamed_task__/MaxReturn -100.273 MetaTest/__unnamed_task__/MinReturn -123.662 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.8644 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 315800 ------------------------------------------------- ----------- 2025-04-02 21:52:21 | [pearl_trainer] epoch #188 | Training... 2025-04-02 21:53:46 | [pearl_trainer] epoch #188 | Evaluating... 2025-04-02 21:53:46 | [pearl_trainer] epoch #188 | Sampling for adapation and meta-testing... 2025-04-02 21:54:36 | [pearl_trainer] epoch #188 | Finished meta-testing... 2025-04-02 21:54:36 | [pearl_trainer] epoch #188 | Saving snapshot... 2025-04-02 21:54:37 | [pearl_trainer] epoch #188 | Saved 2025-04-02 21:54:37 | [pearl_trainer] epoch #188 | Time 30353.54 s 2025-04-02 21:54:37 | [pearl_trainer] epoch #188 | EpochTime 157.28 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.0215 MetaTest/Average/AverageReturn -90.0215 MetaTest/Average/Iteration 188 MetaTest/Average/MaxReturn -88.5824 MetaTest/Average/MinReturn -92.0101 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.45227 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.0215 MetaTest/__unnamed_task__/AverageReturn -90.0215 MetaTest/__unnamed_task__/Iteration 188 MetaTest/__unnamed_task__/MaxReturn -88.5824 MetaTest/__unnamed_task__/MinReturn -92.0101 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.45227 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 317400 ------------------------------------------------- ------------ 2025-04-02 21:54:58 | [pearl_trainer] epoch #189 | Training... 2025-04-02 21:56:24 | [pearl_trainer] epoch #189 | Evaluating... 2025-04-02 21:56:24 | [pearl_trainer] epoch #189 | Sampling for adapation and meta-testing... 2025-04-02 21:57:14 | [pearl_trainer] epoch #189 | Finished meta-testing... 2025-04-02 21:57:14 | [pearl_trainer] epoch #189 | Saving snapshot... 2025-04-02 21:57:15 | [pearl_trainer] epoch #189 | Saved 2025-04-02 21:57:15 | [pearl_trainer] epoch #189 | Time 30511.02 s 2025-04-02 21:57:15 | [pearl_trainer] epoch #189 | EpochTime 157.48 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -83.5374 MetaTest/Average/AverageReturn -83.5374 MetaTest/Average/Iteration 189 MetaTest/Average/MaxReturn -82.6748 MetaTest/Average/MinReturn -84.7457 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 0.880061 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -83.5374 MetaTest/__unnamed_task__/AverageReturn -83.5374 MetaTest/__unnamed_task__/Iteration 189 MetaTest/__unnamed_task__/MaxReturn -82.6748 MetaTest/__unnamed_task__/MinReturn -84.7457 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 0.880061 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 319000 ------------------------------------------------- ------------- 2025-04-02 21:57:37 | [pearl_trainer] epoch #190 | Training... 2025-04-02 21:59:03 | [pearl_trainer] epoch #190 | Evaluating... 2025-04-02 21:59:03 | [pearl_trainer] epoch #190 | Sampling for adapation and meta-testing... 2025-04-02 21:59:50 | [pearl_trainer] epoch #190 | Finished meta-testing... 2025-04-02 21:59:50 | [pearl_trainer] epoch #190 | Saving snapshot... 2025-04-02 21:59:52 | [pearl_trainer] epoch #190 | Saved 2025-04-02 21:59:52 | [pearl_trainer] epoch #190 | Time 30667.85 s 2025-04-02 21:59:52 | [pearl_trainer] epoch #190 | EpochTime 156.83 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -85.093 MetaTest/Average/AverageReturn -85.093 MetaTest/Average/Iteration 190 MetaTest/Average/MaxReturn -79.1419 MetaTest/Average/MinReturn -95.9112 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.66237 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -85.093 MetaTest/__unnamed_task__/AverageReturn -85.093 MetaTest/__unnamed_task__/Iteration 190 MetaTest/__unnamed_task__/MaxReturn -79.1419 MetaTest/__unnamed_task__/MinReturn -95.9112 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.66237 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 320600 ------------------------------------------------- ------------ 2025-04-02 22:00:12 | [pearl_trainer] epoch #191 | Training... 2025-04-02 22:01:47 | [pearl_trainer] epoch #191 | Evaluating... 2025-04-02 22:01:47 | [pearl_trainer] epoch #191 | Sampling for adapation and meta-testing... 2025-04-02 22:02:35 | [pearl_trainer] epoch #191 | Finished meta-testing... 2025-04-02 22:02:35 | [pearl_trainer] epoch #191 | Saving snapshot... 2025-04-02 22:02:36 | [pearl_trainer] epoch #191 | Saved 2025-04-02 22:02:36 | [pearl_trainer] epoch #191 | Time 30832.33 s 2025-04-02 22:02:36 | [pearl_trainer] epoch #191 | EpochTime 164.47 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -94.9312 MetaTest/Average/AverageReturn -94.9312 MetaTest/Average/Iteration 191 MetaTest/Average/MaxReturn -87.9801 MetaTest/Average/MinReturn -98.9911 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.93827 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.9312 MetaTest/__unnamed_task__/AverageReturn -94.9312 MetaTest/__unnamed_task__/Iteration 191 MetaTest/__unnamed_task__/MaxReturn -87.9801 MetaTest/__unnamed_task__/MinReturn -98.9911 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.93827 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 322200 ------------------------------------------------- ------------ 2025-04-02 22:02:57 | [pearl_trainer] epoch #192 | Training... 2025-04-02 22:04:32 | [pearl_trainer] epoch #192 | Evaluating... 2025-04-02 22:04:32 | [pearl_trainer] epoch #192 | Sampling for adapation and meta-testing... 2025-04-02 22:05:34 | [pearl_trainer] epoch #192 | Finished meta-testing... 2025-04-02 22:05:34 | [pearl_trainer] epoch #192 | Saving snapshot... 2025-04-02 22:05:36 | [pearl_trainer] epoch #192 | Saved 2025-04-02 22:05:36 | [pearl_trainer] epoch #192 | Time 31011.99 s 2025-04-02 22:05:36 | [pearl_trainer] epoch #192 | EpochTime 179.66 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -94.4169 MetaTest/Average/AverageReturn -94.4169 MetaTest/Average/Iteration 192 MetaTest/Average/MaxReturn -75.3703 MetaTest/Average/MinReturn -104.951 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.4932 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.4169 MetaTest/__unnamed_task__/AverageReturn -94.4169 MetaTest/__unnamed_task__/Iteration 192 MetaTest/__unnamed_task__/MaxReturn -75.3703 MetaTest/__unnamed_task__/MinReturn -104.951 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.4932 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 323800 ------------------------------------------------- ----------- 2025-04-02 22:06:02 | [pearl_trainer] epoch #193 | Training... 2025-04-02 22:07:48 | [pearl_trainer] epoch #193 | Evaluating... 2025-04-02 22:07:48 | [pearl_trainer] epoch #193 | Sampling for adapation and meta-testing... 2025-04-02 22:08:37 | [pearl_trainer] epoch #193 | Finished meta-testing... 2025-04-02 22:08:37 | [pearl_trainer] epoch #193 | Saving snapshot... 2025-04-02 22:08:38 | [pearl_trainer] epoch #193 | Saved 2025-04-02 22:08:38 | [pearl_trainer] epoch #193 | Time 31193.73 s 2025-04-02 22:08:38 | [pearl_trainer] epoch #193 | EpochTime 181.75 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -91.1389 MetaTest/Average/AverageReturn -91.1389 MetaTest/Average/Iteration 193 MetaTest/Average/MaxReturn -83.0401 MetaTest/Average/MinReturn -104.585 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.57416 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.1389 MetaTest/__unnamed_task__/AverageReturn -91.1389 MetaTest/__unnamed_task__/Iteration 193 MetaTest/__unnamed_task__/MaxReturn -83.0401 MetaTest/__unnamed_task__/MinReturn -104.585 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.57416 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 325400 ------------------------------------------------- ------------ 2025-04-02 22:09:00 | [pearl_trainer] epoch #194 | Training... 2025-04-02 22:10:34 | [pearl_trainer] epoch #194 | Evaluating... 2025-04-02 22:10:34 | [pearl_trainer] epoch #194 | Sampling for adapation and meta-testing... 2025-04-02 22:11:18 | [pearl_trainer] epoch #194 | Finished meta-testing... 2025-04-02 22:11:18 | [pearl_trainer] epoch #194 | Saving snapshot... 2025-04-02 22:11:18 | [pearl_trainer] epoch #194 | Saved 2025-04-02 22:11:18 | [pearl_trainer] epoch #194 | Time 31354.69 s 2025-04-02 22:11:18 | [pearl_trainer] epoch #194 | EpochTime 160.96 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -88.8647 MetaTest/Average/AverageReturn -88.8647 MetaTest/Average/Iteration 194 MetaTest/Average/MaxReturn -78.957 MetaTest/Average/MinReturn -95.8366 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.19698 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.8647 MetaTest/__unnamed_task__/AverageReturn -88.8647 MetaTest/__unnamed_task__/Iteration 194 MetaTest/__unnamed_task__/MaxReturn -78.957 MetaTest/__unnamed_task__/MinReturn -95.8366 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.19698 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 327000 ------------------------------------------------- ------------ 2025-04-02 22:11:39 | [pearl_trainer] epoch #195 | Training... 2025-04-02 22:13:10 | [pearl_trainer] epoch #195 | Evaluating... 2025-04-02 22:13:10 | [pearl_trainer] epoch #195 | Sampling for adapation and meta-testing... 2025-04-02 22:13:59 | [pearl_trainer] epoch #195 | Finished meta-testing... 2025-04-02 22:13:59 | [pearl_trainer] epoch #195 | Saving snapshot... 2025-04-02 22:14:00 | [pearl_trainer] epoch #195 | Saved 2025-04-02 22:14:00 | [pearl_trainer] epoch #195 | Time 31516.06 s 2025-04-02 22:14:00 | [pearl_trainer] epoch #195 | EpochTime 161.36 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -100.734 MetaTest/Average/AverageReturn -100.734 MetaTest/Average/Iteration 195 MetaTest/Average/MaxReturn -96.0076 MetaTest/Average/MinReturn -106.532 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.36314 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -100.734 MetaTest/__unnamed_task__/AverageReturn -100.734 MetaTest/__unnamed_task__/Iteration 195 MetaTest/__unnamed_task__/MaxReturn -96.0076 MetaTest/__unnamed_task__/MinReturn -106.532 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.36314 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 328600 ------------------------------------------------- ------------ 2025-04-02 22:14:22 | [pearl_trainer] epoch #196 | Training... 2025-04-02 22:15:51 | [pearl_trainer] epoch #196 | Evaluating... 2025-04-02 22:15:51 | [pearl_trainer] epoch #196 | Sampling for adapation and meta-testing... 2025-04-02 22:16:35 | [pearl_trainer] epoch #196 | Finished meta-testing... 2025-04-02 22:16:35 | [pearl_trainer] epoch #196 | Saving snapshot... 2025-04-02 22:16:36 | [pearl_trainer] epoch #196 | Saved 2025-04-02 22:16:36 | [pearl_trainer] epoch #196 | Time 31672.26 s 2025-04-02 22:16:36 | [pearl_trainer] epoch #196 | EpochTime 156.20 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -104.561 MetaTest/Average/AverageReturn -104.561 MetaTest/Average/Iteration 196 MetaTest/Average/MaxReturn -90.2699 MetaTest/Average/MinReturn -121.221 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.7464 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -104.561 MetaTest/__unnamed_task__/AverageReturn -104.561 MetaTest/__unnamed_task__/Iteration 196 MetaTest/__unnamed_task__/MaxReturn -90.2699 MetaTest/__unnamed_task__/MinReturn -121.221 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.7464 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 330200 ------------------------------------------------- ----------- 2025-04-02 22:16:59 | [pearl_trainer] epoch #197 | Training... 2025-04-02 22:18:24 | [pearl_trainer] epoch #197 | Evaluating... 2025-04-02 22:18:24 | [pearl_trainer] epoch #197 | Sampling for adapation and meta-testing... 2025-04-02 22:19:12 | [pearl_trainer] epoch #197 | Finished meta-testing... 2025-04-02 22:19:12 | [pearl_trainer] epoch #197 | Saving snapshot... 2025-04-02 22:19:13 | [pearl_trainer] epoch #197 | Saved 2025-04-02 22:19:13 | [pearl_trainer] epoch #197 | Time 31829.02 s 2025-04-02 22:19:13 | [pearl_trainer] epoch #197 | EpochTime 156.75 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -97.0388 MetaTest/Average/AverageReturn -97.0388 MetaTest/Average/Iteration 197 MetaTest/Average/MaxReturn -86.2239 MetaTest/Average/MinReturn -117.929 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.7745 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.0388 MetaTest/__unnamed_task__/AverageReturn -97.0388 MetaTest/__unnamed_task__/Iteration 197 MetaTest/__unnamed_task__/MaxReturn -86.2239 MetaTest/__unnamed_task__/MinReturn -117.929 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.7745 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 331800 ------------------------------------------------- ----------- 2025-04-02 22:19:34 | [pearl_trainer] epoch #198 | Training... 2025-04-02 22:20:59 | [pearl_trainer] epoch #198 | Evaluating... 2025-04-02 22:20:59 | [pearl_trainer] epoch #198 | Sampling for adapation and meta-testing... 2025-04-02 22:21:46 | [pearl_trainer] epoch #198 | Finished meta-testing... 2025-04-02 22:21:46 | [pearl_trainer] epoch #198 | Saving snapshot... 2025-04-02 22:21:47 | [pearl_trainer] epoch #198 | Saved 2025-04-02 22:21:47 | [pearl_trainer] epoch #198 | Time 31983.58 s 2025-04-02 22:21:47 | [pearl_trainer] epoch #198 | EpochTime 154.56 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -93.423 MetaTest/Average/AverageReturn -93.423 MetaTest/Average/Iteration 198 MetaTest/Average/MaxReturn -79.1495 MetaTest/Average/MinReturn -112.246 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.8892 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.423 MetaTest/__unnamed_task__/AverageReturn -93.423 MetaTest/__unnamed_task__/Iteration 198 MetaTest/__unnamed_task__/MaxReturn -79.1495 MetaTest/__unnamed_task__/MinReturn -112.246 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.8892 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 333400 ------------------------------------------------- ----------- 2025-04-02 22:22:10 | [pearl_trainer] epoch #199 | Training... 2025-04-02 22:23:40 | [pearl_trainer] epoch #199 | Evaluating... 2025-04-02 22:23:40 | [pearl_trainer] epoch #199 | Sampling for adapation and meta-testing... 2025-04-02 22:24:25 | [pearl_trainer] epoch #199 | Finished meta-testing... 2025-04-02 22:24:25 | [pearl_trainer] epoch #199 | Saving snapshot... 2025-04-02 22:24:26 | [pearl_trainer] epoch #199 | Saved 2025-04-02 22:24:26 | [pearl_trainer] epoch #199 | Time 32142.38 s 2025-04-02 22:24:26 | [pearl_trainer] epoch #199 | EpochTime 158.80 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -102.304 MetaTest/Average/AverageReturn -102.304 MetaTest/Average/Iteration 199 MetaTest/Average/MaxReturn -89.9301 MetaTest/Average/MinReturn -110.664 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.9278 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -102.304 MetaTest/__unnamed_task__/AverageReturn -102.304 MetaTest/__unnamed_task__/Iteration 199 MetaTest/__unnamed_task__/MaxReturn -89.9301 MetaTest/__unnamed_task__/MinReturn -110.664 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.9278 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 335000 ------------------------------------------------- ----------- 2025-04-02 22:24:51 | [pearl_trainer] epoch #200 | Training... 2025-04-02 22:26:18 | [pearl_trainer] epoch #200 | Evaluating... 2025-04-02 22:26:18 | [pearl_trainer] epoch #200 | Sampling for adapation and meta-testing... 2025-04-02 22:27:05 | [pearl_trainer] epoch #200 | Finished meta-testing... 2025-04-02 22:27:05 | [pearl_trainer] epoch #200 | Saving snapshot... 2025-04-02 22:27:06 | [pearl_trainer] epoch #200 | Saved 2025-04-02 22:27:06 | [pearl_trainer] epoch #200 | Time 32302.58 s 2025-04-02 22:27:06 | [pearl_trainer] epoch #200 | EpochTime 160.19 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -98.5316 MetaTest/Average/AverageReturn -98.5316 MetaTest/Average/Iteration 200 MetaTest/Average/MaxReturn -93.1503 MetaTest/Average/MinReturn -107.754 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.55116 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.5316 MetaTest/__unnamed_task__/AverageReturn -98.5316 MetaTest/__unnamed_task__/Iteration 200 MetaTest/__unnamed_task__/MaxReturn -93.1503 MetaTest/__unnamed_task__/MinReturn -107.754 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.55116 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 336600 ------------------------------------------------- ------------ 2025-04-02 22:27:30 | [pearl_trainer] epoch #201 | Training... 2025-04-02 22:28:58 | [pearl_trainer] epoch #201 | Evaluating... 2025-04-02 22:28:58 | [pearl_trainer] epoch #201 | Sampling for adapation and meta-testing... 2025-04-02 22:29:47 | [pearl_trainer] epoch #201 | Finished meta-testing... 2025-04-02 22:29:47 | [pearl_trainer] epoch #201 | Saving snapshot... 2025-04-02 22:29:48 | [pearl_trainer] epoch #201 | Saved 2025-04-02 22:29:48 | [pearl_trainer] epoch #201 | Time 32463.81 s 2025-04-02 22:29:48 | [pearl_trainer] epoch #201 | EpochTime 161.23 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -90.9835 MetaTest/Average/AverageReturn -90.9835 MetaTest/Average/Iteration 201 MetaTest/Average/MaxReturn -88.4142 MetaTest/Average/MinReturn -92.6092 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.838 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.9835 MetaTest/__unnamed_task__/AverageReturn -90.9835 MetaTest/__unnamed_task__/Iteration 201 MetaTest/__unnamed_task__/MaxReturn -88.4142 MetaTest/__unnamed_task__/MinReturn -92.6092 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.838 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 338200 ------------------------------------------------- ----------- 2025-04-02 22:30:10 | [pearl_trainer] epoch #202 | Training... 2025-04-02 22:31:36 | [pearl_trainer] epoch #202 | Evaluating... 2025-04-02 22:31:36 | [pearl_trainer] epoch #202 | Sampling for adapation and meta-testing... 2025-04-02 22:32:23 | [pearl_trainer] epoch #202 | Finished meta-testing... 2025-04-02 22:32:23 | [pearl_trainer] epoch #202 | Saving snapshot... 2025-04-02 22:32:24 | [pearl_trainer] epoch #202 | Saved 2025-04-02 22:32:24 | [pearl_trainer] epoch #202 | Time 32620.54 s 2025-04-02 22:32:24 | [pearl_trainer] epoch #202 | EpochTime 156.74 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -84.2349 MetaTest/Average/AverageReturn -84.2349 MetaTest/Average/Iteration 202 MetaTest/Average/MaxReturn -79.104 MetaTest/Average/MinReturn -88.7941 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.9766 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -84.2349 MetaTest/__unnamed_task__/AverageReturn -84.2349 MetaTest/__unnamed_task__/Iteration 202 MetaTest/__unnamed_task__/MaxReturn -79.104 MetaTest/__unnamed_task__/MinReturn -88.7941 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.9766 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 339800 ------------------------------------------------- ----------- 2025-04-02 22:32:47 | [pearl_trainer] epoch #203 | Training... 2025-04-02 22:34:18 | [pearl_trainer] epoch #203 | Evaluating... 2025-04-02 22:34:18 | [pearl_trainer] epoch #203 | Sampling for adapation and meta-testing... 2025-04-02 22:35:02 | [pearl_trainer] epoch #203 | Finished meta-testing... 2025-04-02 22:35:02 | [pearl_trainer] epoch #203 | Saving snapshot... 2025-04-02 22:35:03 | [pearl_trainer] epoch #203 | Saved 2025-04-02 22:35:03 | [pearl_trainer] epoch #203 | Time 32779.03 s 2025-04-02 22:35:03 | [pearl_trainer] epoch #203 | EpochTime 158.49 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -101.352 MetaTest/Average/AverageReturn -101.352 MetaTest/Average/Iteration 203 MetaTest/Average/MaxReturn -88.9327 MetaTest/Average/MinReturn -122.297 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.8952 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.352 MetaTest/__unnamed_task__/AverageReturn -101.352 MetaTest/__unnamed_task__/Iteration 203 MetaTest/__unnamed_task__/MaxReturn -88.9327 MetaTest/__unnamed_task__/MinReturn -122.297 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.8952 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 341400 ------------------------------------------------- ----------- 2025-04-02 22:35:24 | [pearl_trainer] epoch #204 | Training... 2025-04-02 22:36:52 | [pearl_trainer] epoch #204 | Evaluating... 2025-04-02 22:36:52 | [pearl_trainer] epoch #204 | Sampling for adapation and meta-testing... 2025-04-02 22:37:45 | [pearl_trainer] epoch #204 | Finished meta-testing... 2025-04-02 22:37:45 | [pearl_trainer] epoch #204 | Saving snapshot... 2025-04-02 22:37:46 | [pearl_trainer] epoch #204 | Saved 2025-04-02 22:37:46 | [pearl_trainer] epoch #204 | Time 32941.91 s 2025-04-02 22:37:46 | [pearl_trainer] epoch #204 | EpochTime 162.87 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -96.729 MetaTest/Average/AverageReturn -96.729 MetaTest/Average/Iteration 204 MetaTest/Average/MaxReturn -89.2451 MetaTest/Average/MinReturn -104.472 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.21887 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.729 MetaTest/__unnamed_task__/AverageReturn -96.729 MetaTest/__unnamed_task__/Iteration 204 MetaTest/__unnamed_task__/MaxReturn -89.2451 MetaTest/__unnamed_task__/MinReturn -104.472 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.21887 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 343000 ------------------------------------------------- ------------ 2025-04-02 22:38:09 | [pearl_trainer] epoch #205 | Training... 2025-04-02 22:39:34 | [pearl_trainer] epoch #205 | Evaluating... 2025-04-02 22:39:34 | [pearl_trainer] epoch #205 | Sampling for adapation and meta-testing... 2025-04-02 22:40:19 | [pearl_trainer] epoch #205 | Finished meta-testing... 2025-04-02 22:40:19 | [pearl_trainer] epoch #205 | Saving snapshot... 2025-04-02 22:40:21 | [pearl_trainer] epoch #205 | Saved 2025-04-02 22:40:21 | [pearl_trainer] epoch #205 | Time 33096.89 s 2025-04-02 22:40:21 | [pearl_trainer] epoch #205 | EpochTime 154.98 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -105.593 MetaTest/Average/AverageReturn -105.593 MetaTest/Average/Iteration 205 MetaTest/Average/MaxReturn -89.8183 MetaTest/Average/MinReturn -123.044 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.6162 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -105.593 MetaTest/__unnamed_task__/AverageReturn -105.593 MetaTest/__unnamed_task__/Iteration 205 MetaTest/__unnamed_task__/MaxReturn -89.8183 MetaTest/__unnamed_task__/MinReturn -123.044 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.6162 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 344600 ------------------------------------------------- ----------- 2025-04-02 22:40:43 | [pearl_trainer] epoch #206 | Training... 2025-04-02 22:42:07 | [pearl_trainer] epoch #206 | Evaluating... 2025-04-02 22:42:07 | [pearl_trainer] epoch #206 | Sampling for adapation and meta-testing... 2025-04-02 22:42:56 | [pearl_trainer] epoch #206 | Finished meta-testing... 2025-04-02 22:42:56 | [pearl_trainer] epoch #206 | Saving snapshot... 2025-04-02 22:42:57 | [pearl_trainer] epoch #206 | Saved 2025-04-02 22:42:57 | [pearl_trainer] epoch #206 | Time 33253.06 s 2025-04-02 22:42:57 | [pearl_trainer] epoch #206 | EpochTime 156.17 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -98.4953 MetaTest/Average/AverageReturn -98.4953 MetaTest/Average/Iteration 206 MetaTest/Average/MaxReturn -95.5398 MetaTest/Average/MinReturn -103.864 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.80251 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.4953 MetaTest/__unnamed_task__/AverageReturn -98.4953 MetaTest/__unnamed_task__/Iteration 206 MetaTest/__unnamed_task__/MaxReturn -95.5398 MetaTest/__unnamed_task__/MinReturn -103.864 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.80251 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 346200 ------------------------------------------------- ------------ 2025-04-02 22:43:18 | [pearl_trainer] epoch #207 | Training... 2025-04-02 22:44:42 | [pearl_trainer] epoch #207 | Evaluating... 2025-04-02 22:44:42 | [pearl_trainer] epoch #207 | Sampling for adapation and meta-testing... 2025-04-02 22:45:34 | [pearl_trainer] epoch #207 | Finished meta-testing... 2025-04-02 22:45:34 | [pearl_trainer] epoch #207 | Saving snapshot... 2025-04-02 22:45:35 | [pearl_trainer] epoch #207 | Saved 2025-04-02 22:45:35 | [pearl_trainer] epoch #207 | Time 33411.67 s 2025-04-02 22:45:35 | [pearl_trainer] epoch #207 | EpochTime 158.61 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -106.526 MetaTest/Average/AverageReturn -106.526 MetaTest/Average/Iteration 207 MetaTest/Average/MaxReturn -103.238 MetaTest/Average/MinReturn -110.79 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.15926 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -106.526 MetaTest/__unnamed_task__/AverageReturn -106.526 MetaTest/__unnamed_task__/Iteration 207 MetaTest/__unnamed_task__/MaxReturn -103.238 MetaTest/__unnamed_task__/MinReturn -110.79 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.15926 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 347800 ------------------------------------------------- ------------ 2025-04-02 22:45:56 | [pearl_trainer] epoch #208 | Training... 2025-04-02 22:47:15 | [pearl_trainer] epoch #208 | Evaluating... 2025-04-02 22:47:15 | [pearl_trainer] epoch #208 | Sampling for adapation and meta-testing... 2025-04-02 22:48:07 | [pearl_trainer] epoch #208 | Finished meta-testing... 2025-04-02 22:48:07 | [pearl_trainer] epoch #208 | Saving snapshot... 2025-04-02 22:48:08 | [pearl_trainer] epoch #208 | Saved 2025-04-02 22:48:08 | [pearl_trainer] epoch #208 | Time 33564.21 s 2025-04-02 22:48:08 | [pearl_trainer] epoch #208 | EpochTime 152.53 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -101.012 MetaTest/Average/AverageReturn -101.012 MetaTest/Average/Iteration 208 MetaTest/Average/MaxReturn -93.1824 MetaTest/Average/MinReturn -109.684 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.76318 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.012 MetaTest/__unnamed_task__/AverageReturn -101.012 MetaTest/__unnamed_task__/Iteration 208 MetaTest/__unnamed_task__/MaxReturn -93.1824 MetaTest/__unnamed_task__/MinReturn -109.684 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.76318 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 349400 ------------------------------------------------- ------------ 2025-04-02 22:48:33 | [pearl_trainer] epoch #209 | Training... 2025-04-02 22:50:04 | [pearl_trainer] epoch #209 | Evaluating... 2025-04-02 22:50:04 | [pearl_trainer] epoch #209 | Sampling for adapation and meta-testing... 2025-04-02 22:50:48 | [pearl_trainer] epoch #209 | Finished meta-testing... 2025-04-02 22:50:48 | [pearl_trainer] epoch #209 | Saving snapshot... 2025-04-02 22:50:49 | [pearl_trainer] epoch #209 | Saved 2025-04-02 22:50:49 | [pearl_trainer] epoch #209 | Time 33725.08 s 2025-04-02 22:50:49 | [pearl_trainer] epoch #209 | EpochTime 160.88 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -115.941 MetaTest/Average/AverageReturn -115.941 MetaTest/Average/Iteration 209 MetaTest/Average/MaxReturn -112.587 MetaTest/Average/MinReturn -118.936 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.60464 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -115.941 MetaTest/__unnamed_task__/AverageReturn -115.941 MetaTest/__unnamed_task__/Iteration 209 MetaTest/__unnamed_task__/MaxReturn -112.587 MetaTest/__unnamed_task__/MinReturn -118.936 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.60464 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 351000 ------------------------------------------------- ------------ 2025-04-02 22:51:12 | [pearl_trainer] epoch #210 | Training... 2025-04-02 22:52:39 | [pearl_trainer] epoch #210 | Evaluating... 2025-04-02 22:52:39 | [pearl_trainer] epoch #210 | Sampling for adapation and meta-testing... 2025-04-02 22:53:25 | [pearl_trainer] epoch #210 | Finished meta-testing... 2025-04-02 22:53:25 | [pearl_trainer] epoch #210 | Saving snapshot... 2025-04-02 22:53:27 | [pearl_trainer] epoch #210 | Saved 2025-04-02 22:53:27 | [pearl_trainer] epoch #210 | Time 33882.79 s 2025-04-02 22:53:27 | [pearl_trainer] epoch #210 | EpochTime 157.70 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -97.6536 MetaTest/Average/AverageReturn -97.6536 MetaTest/Average/Iteration 210 MetaTest/Average/MaxReturn -81.1599 MetaTest/Average/MinReturn -107.798 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.7652 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.6536 MetaTest/__unnamed_task__/AverageReturn -97.6536 MetaTest/__unnamed_task__/Iteration 210 MetaTest/__unnamed_task__/MaxReturn -81.1599 MetaTest/__unnamed_task__/MinReturn -107.798 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.7652 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 352600 ------------------------------------------------- ----------- 2025-04-02 22:53:47 | [pearl_trainer] epoch #211 | Training... 2025-04-02 22:55:18 | [pearl_trainer] epoch #211 | Evaluating... 2025-04-02 22:55:18 | [pearl_trainer] epoch #211 | Sampling for adapation and meta-testing... 2025-04-02 22:56:05 | [pearl_trainer] epoch #211 | Finished meta-testing... 2025-04-02 22:56:05 | [pearl_trainer] epoch #211 | Saving snapshot... 2025-04-02 22:56:06 | [pearl_trainer] epoch #211 | Saved 2025-04-02 22:56:06 | [pearl_trainer] epoch #211 | Time 34042.16 s 2025-04-02 22:56:06 | [pearl_trainer] epoch #211 | EpochTime 159.37 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -107.652 MetaTest/Average/AverageReturn -107.652 MetaTest/Average/Iteration 211 MetaTest/Average/MaxReturn -101.315 MetaTest/Average/MinReturn -113.443 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.96653 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -107.652 MetaTest/__unnamed_task__/AverageReturn -107.652 MetaTest/__unnamed_task__/Iteration 211 MetaTest/__unnamed_task__/MaxReturn -101.315 MetaTest/__unnamed_task__/MinReturn -113.443 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.96653 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 354200 ------------------------------------------------- ------------ 2025-04-02 22:56:29 | [pearl_trainer] epoch #212 | Training... 2025-04-02 22:57:53 | [pearl_trainer] epoch #212 | Evaluating... 2025-04-02 22:57:53 | [pearl_trainer] epoch #212 | Sampling for adapation and meta-testing... 2025-04-02 22:58:41 | [pearl_trainer] epoch #212 | Finished meta-testing... 2025-04-02 22:58:41 | [pearl_trainer] epoch #212 | Saving snapshot... 2025-04-02 22:58:42 | [pearl_trainer] epoch #212 | Saved 2025-04-02 22:58:42 | [pearl_trainer] epoch #212 | Time 34198.63 s 2025-04-02 22:58:42 | [pearl_trainer] epoch #212 | EpochTime 156.47 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -98.8835 MetaTest/Average/AverageReturn -98.8835 MetaTest/Average/Iteration 212 MetaTest/Average/MaxReturn -90.8362 MetaTest/Average/MinReturn -110.92 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.67103 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.8835 MetaTest/__unnamed_task__/AverageReturn -98.8835 MetaTest/__unnamed_task__/Iteration 212 MetaTest/__unnamed_task__/MaxReturn -90.8362 MetaTest/__unnamed_task__/MinReturn -110.92 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.67103 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 355800 ------------------------------------------------- ------------ 2025-04-02 22:59:03 | [pearl_trainer] epoch #213 | Training... 2025-04-02 23:00:33 | [pearl_trainer] epoch #213 | Evaluating... 2025-04-02 23:00:33 | [pearl_trainer] epoch #213 | Sampling for adapation and meta-testing... 2025-04-02 23:01:15 | [pearl_trainer] epoch #213 | Finished meta-testing... 2025-04-02 23:01:15 | [pearl_trainer] epoch #213 | Saving snapshot... 2025-04-02 23:01:17 | [pearl_trainer] epoch #213 | Saved 2025-04-02 23:01:17 | [pearl_trainer] epoch #213 | Time 34352.91 s 2025-04-02 23:01:17 | [pearl_trainer] epoch #213 | EpochTime 154.28 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -109.485 MetaTest/Average/AverageReturn -109.485 MetaTest/Average/Iteration 213 MetaTest/Average/MaxReturn -102.701 MetaTest/Average/MinReturn -119.806 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.4172 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -109.485 MetaTest/__unnamed_task__/AverageReturn -109.485 MetaTest/__unnamed_task__/Iteration 213 MetaTest/__unnamed_task__/MaxReturn -102.701 MetaTest/__unnamed_task__/MinReturn -119.806 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.4172 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 357400 ------------------------------------------------- ----------- 2025-04-02 23:01:39 | [pearl_trainer] epoch #214 | Training... 2025-04-02 23:03:12 | [pearl_trainer] epoch #214 | Evaluating... 2025-04-02 23:03:12 | [pearl_trainer] epoch #214 | Sampling for adapation and meta-testing... 2025-04-02 23:04:01 | [pearl_trainer] epoch #214 | Finished meta-testing... 2025-04-02 23:04:01 | [pearl_trainer] epoch #214 | Saving snapshot... 2025-04-02 23:04:02 | [pearl_trainer] epoch #214 | Saved 2025-04-02 23:04:02 | [pearl_trainer] epoch #214 | Time 34518.10 s 2025-04-02 23:04:02 | [pearl_trainer] epoch #214 | EpochTime 165.19 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -107.121 MetaTest/Average/AverageReturn -107.121 MetaTest/Average/Iteration 214 MetaTest/Average/MaxReturn -81.9075 MetaTest/Average/MinReturn -130.841 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 20.0048 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -107.121 MetaTest/__unnamed_task__/AverageReturn -107.121 MetaTest/__unnamed_task__/Iteration 214 MetaTest/__unnamed_task__/MaxReturn -81.9075 MetaTest/__unnamed_task__/MinReturn -130.841 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 20.0048 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 359000 ------------------------------------------------- ----------- 2025-04-02 23:04:27 | [pearl_trainer] epoch #215 | Training... 2025-04-02 23:05:55 | [pearl_trainer] epoch #215 | Evaluating... 2025-04-02 23:05:55 | [pearl_trainer] epoch #215 | Sampling for adapation and meta-testing... 2025-04-02 23:06:39 | [pearl_trainer] epoch #215 | Finished meta-testing... 2025-04-02 23:06:39 | [pearl_trainer] epoch #215 | Saving snapshot... 2025-04-02 23:06:40 | [pearl_trainer] epoch #215 | Saved 2025-04-02 23:06:40 | [pearl_trainer] epoch #215 | Time 34676.03 s 2025-04-02 23:06:40 | [pearl_trainer] epoch #215 | EpochTime 157.93 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -100.971 MetaTest/Average/AverageReturn -100.971 MetaTest/Average/Iteration 215 MetaTest/Average/MaxReturn -98.1266 MetaTest/Average/MinReturn -106.516 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.92119 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -100.971 MetaTest/__unnamed_task__/AverageReturn -100.971 MetaTest/__unnamed_task__/Iteration 215 MetaTest/__unnamed_task__/MaxReturn -98.1266 MetaTest/__unnamed_task__/MinReturn -106.516 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.92119 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 360600 ------------------------------------------------- ------------ 2025-04-02 23:07:01 | [pearl_trainer] epoch #216 | Training... 2025-04-02 23:08:35 | [pearl_trainer] epoch #216 | Evaluating... 2025-04-02 23:08:35 | [pearl_trainer] epoch #216 | Sampling for adapation and meta-testing... 2025-04-02 23:09:24 | [pearl_trainer] epoch #216 | Finished meta-testing... 2025-04-02 23:09:24 | [pearl_trainer] epoch #216 | Saving snapshot... 2025-04-02 23:09:25 | [pearl_trainer] epoch #216 | Saved 2025-04-02 23:09:25 | [pearl_trainer] epoch #216 | Time 34841.40 s 2025-04-02 23:09:25 | [pearl_trainer] epoch #216 | EpochTime 165.37 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -102.18 MetaTest/Average/AverageReturn -102.18 MetaTest/Average/Iteration 216 MetaTest/Average/MaxReturn -91.7764 MetaTest/Average/MinReturn -119.257 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.1712 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -102.18 MetaTest/__unnamed_task__/AverageReturn -102.18 MetaTest/__unnamed_task__/Iteration 216 MetaTest/__unnamed_task__/MaxReturn -91.7764 MetaTest/__unnamed_task__/MinReturn -119.257 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.1712 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 362200 ------------------------------------------------- ----------- 2025-04-02 23:09:47 | [pearl_trainer] epoch #217 | Training... 2025-04-02 23:11:27 | [pearl_trainer] epoch #217 | Evaluating... 2025-04-02 23:11:27 | [pearl_trainer] epoch #217 | Sampling for adapation and meta-testing... 2025-04-02 23:12:22 | [pearl_trainer] epoch #217 | Finished meta-testing... 2025-04-02 23:12:22 | [pearl_trainer] epoch #217 | Saving snapshot... 2025-04-02 23:12:23 | [pearl_trainer] epoch #217 | Saved 2025-04-02 23:12:23 | [pearl_trainer] epoch #217 | Time 35019.55 s 2025-04-02 23:12:23 | [pearl_trainer] epoch #217 | EpochTime 178.14 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -96.4665 MetaTest/Average/AverageReturn -96.4665 MetaTest/Average/Iteration 217 MetaTest/Average/MaxReturn -93.1483 MetaTest/Average/MinReturn -101.346 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.52387 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.4665 MetaTest/__unnamed_task__/AverageReturn -96.4665 MetaTest/__unnamed_task__/Iteration 217 MetaTest/__unnamed_task__/MaxReturn -93.1483 MetaTest/__unnamed_task__/MinReturn -101.346 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.52387 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 363800 ------------------------------------------------- ------------ 2025-04-02 23:12:44 | [pearl_trainer] epoch #218 | Training... 2025-04-02 23:14:08 | [pearl_trainer] epoch #218 | Evaluating... 2025-04-02 23:14:08 | [pearl_trainer] epoch #218 | Sampling for adapation and meta-testing... 2025-04-02 23:14:57 | [pearl_trainer] epoch #218 | Finished meta-testing... 2025-04-02 23:14:57 | [pearl_trainer] epoch #218 | Saving snapshot... 2025-04-02 23:14:58 | [pearl_trainer] epoch #218 | Saved 2025-04-02 23:14:58 | [pearl_trainer] epoch #218 | Time 35174.41 s 2025-04-02 23:14:58 | [pearl_trainer] epoch #218 | EpochTime 154.86 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -109.143 MetaTest/Average/AverageReturn -109.143 MetaTest/Average/Iteration 218 MetaTest/Average/MaxReturn -85.4617 MetaTest/Average/MinReturn -123.937 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 16.918 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -109.143 MetaTest/__unnamed_task__/AverageReturn -109.143 MetaTest/__unnamed_task__/Iteration 218 MetaTest/__unnamed_task__/MaxReturn -85.4617 MetaTest/__unnamed_task__/MinReturn -123.937 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 16.918 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 365400 ------------------------------------------------- ----------- 2025-04-02 23:15:20 | [pearl_trainer] epoch #219 | Training... 2025-04-02 23:16:42 | [pearl_trainer] epoch #219 | Evaluating... 2025-04-02 23:16:42 | [pearl_trainer] epoch #219 | Sampling for adapation and meta-testing... 2025-04-02 23:17:27 | [pearl_trainer] epoch #219 | Finished meta-testing... 2025-04-02 23:17:27 | [pearl_trainer] epoch #219 | Saving snapshot... 2025-04-02 23:17:28 | [pearl_trainer] epoch #219 | Saved 2025-04-02 23:17:28 | [pearl_trainer] epoch #219 | Time 35323.92 s 2025-04-02 23:17:28 | [pearl_trainer] epoch #219 | EpochTime 149.51 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -109.073 MetaTest/Average/AverageReturn -109.073 MetaTest/Average/Iteration 219 MetaTest/Average/MaxReturn -91.2175 MetaTest/Average/MinReturn -121.202 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.8935 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -109.073 MetaTest/__unnamed_task__/AverageReturn -109.073 MetaTest/__unnamed_task__/Iteration 219 MetaTest/__unnamed_task__/MaxReturn -91.2175 MetaTest/__unnamed_task__/MinReturn -121.202 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.8935 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 367000 ------------------------------------------------- ----------- 2025-04-02 23:17:50 | [pearl_trainer] epoch #220 | Training... 2025-04-02 23:19:20 | [pearl_trainer] epoch #220 | Evaluating... 2025-04-02 23:19:20 | [pearl_trainer] epoch #220 | Sampling for adapation and meta-testing... 2025-04-02 23:20:10 | [pearl_trainer] epoch #220 | Finished meta-testing... 2025-04-02 23:20:10 | [pearl_trainer] epoch #220 | Saving snapshot... 2025-04-02 23:20:10 | [pearl_trainer] epoch #220 | Saved 2025-04-02 23:20:10 | [pearl_trainer] epoch #220 | Time 35486.68 s 2025-04-02 23:20:10 | [pearl_trainer] epoch #220 | EpochTime 162.76 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -110.475 MetaTest/Average/AverageReturn -110.475 MetaTest/Average/Iteration 220 MetaTest/Average/MaxReturn -96.8075 MetaTest/Average/MinReturn -120.845 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.0866 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -110.475 MetaTest/__unnamed_task__/AverageReturn -110.475 MetaTest/__unnamed_task__/Iteration 220 MetaTest/__unnamed_task__/MaxReturn -96.8075 MetaTest/__unnamed_task__/MinReturn -120.845 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.0866 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 368600 ------------------------------------------------- ----------- 2025-04-02 23:20:32 | [pearl_trainer] epoch #221 | Training... 2025-04-02 23:21:56 | [pearl_trainer] epoch #221 | Evaluating... 2025-04-02 23:21:56 | [pearl_trainer] epoch #221 | Sampling for adapation and meta-testing... 2025-04-02 23:22:43 | [pearl_trainer] epoch #221 | Finished meta-testing... 2025-04-02 23:22:43 | [pearl_trainer] epoch #221 | Saving snapshot... 2025-04-02 23:22:44 | [pearl_trainer] epoch #221 | Saved 2025-04-02 23:22:44 | [pearl_trainer] epoch #221 | Time 35640.66 s 2025-04-02 23:22:44 | [pearl_trainer] epoch #221 | EpochTime 153.97 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -104.243 MetaTest/Average/AverageReturn -104.243 MetaTest/Average/Iteration 221 MetaTest/Average/MaxReturn -91.7797 MetaTest/Average/MinReturn -128.653 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 17.2619 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -104.243 MetaTest/__unnamed_task__/AverageReturn -104.243 MetaTest/__unnamed_task__/Iteration 221 MetaTest/__unnamed_task__/MaxReturn -91.7797 MetaTest/__unnamed_task__/MinReturn -128.653 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 17.2619 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 370200 ------------------------------------------------- ----------- 2025-04-02 23:23:07 | [pearl_trainer] epoch #222 | Training... 2025-04-02 23:24:40 | [pearl_trainer] epoch #222 | Evaluating... 2025-04-02 23:24:40 | [pearl_trainer] epoch #222 | Sampling for adapation and meta-testing... 2025-04-02 23:25:26 | [pearl_trainer] epoch #222 | Finished meta-testing... 2025-04-02 23:25:26 | [pearl_trainer] epoch #222 | Saving snapshot... 2025-04-02 23:25:27 | [pearl_trainer] epoch #222 | Saved 2025-04-02 23:25:27 | [pearl_trainer] epoch #222 | Time 35802.79 s 2025-04-02 23:25:27 | [pearl_trainer] epoch #222 | EpochTime 162.13 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -88.1106 MetaTest/Average/AverageReturn -88.1106 MetaTest/Average/Iteration 222 MetaTest/Average/MaxReturn -79.4338 MetaTest/Average/MinReturn -97.749 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.50802 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.1106 MetaTest/__unnamed_task__/AverageReturn -88.1106 MetaTest/__unnamed_task__/Iteration 222 MetaTest/__unnamed_task__/MaxReturn -79.4338 MetaTest/__unnamed_task__/MinReturn -97.749 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.50802 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 371800 ------------------------------------------------- ------------ 2025-04-02 23:25:49 | [pearl_trainer] epoch #223 | Training... 2025-04-02 23:27:23 | [pearl_trainer] epoch #223 | Evaluating... 2025-04-02 23:27:23 | [pearl_trainer] epoch #223 | Sampling for adapation and meta-testing... 2025-04-02 23:28:13 | [pearl_trainer] epoch #223 | Finished meta-testing... 2025-04-02 23:28:13 | [pearl_trainer] epoch #223 | Saving snapshot... 2025-04-02 23:28:14 | [pearl_trainer] epoch #223 | Saved 2025-04-02 23:28:14 | [pearl_trainer] epoch #223 | Time 35970.42 s 2025-04-02 23:28:14 | [pearl_trainer] epoch #223 | EpochTime 167.64 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -89.9035 MetaTest/Average/AverageReturn -89.9035 MetaTest/Average/Iteration 223 MetaTest/Average/MaxReturn -87.2664 MetaTest/Average/MinReturn -94.165 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.04153 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -89.9035 MetaTest/__unnamed_task__/AverageReturn -89.9035 MetaTest/__unnamed_task__/Iteration 223 MetaTest/__unnamed_task__/MaxReturn -87.2664 MetaTest/__unnamed_task__/MinReturn -94.165 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.04153 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 373400 ------------------------------------------------- ------------ 2025-04-02 23:28:38 | [pearl_trainer] epoch #224 | Training... 2025-04-02 23:30:05 | [pearl_trainer] epoch #224 | Evaluating... 2025-04-02 23:30:05 | [pearl_trainer] epoch #224 | Sampling for adapation and meta-testing... 2025-04-02 23:30:50 | [pearl_trainer] epoch #224 | Finished meta-testing... 2025-04-02 23:30:50 | [pearl_trainer] epoch #224 | Saving snapshot... 2025-04-02 23:30:51 | [pearl_trainer] epoch #224 | Saved 2025-04-02 23:30:51 | [pearl_trainer] epoch #224 | Time 36127.22 s 2025-04-02 23:30:51 | [pearl_trainer] epoch #224 | EpochTime 156.79 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -86.451 MetaTest/Average/AverageReturn -86.451 MetaTest/Average/Iteration 224 MetaTest/Average/MaxReturn -84.8515 MetaTest/Average/MinReturn -88.7863 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.68851 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -86.451 MetaTest/__unnamed_task__/AverageReturn -86.451 MetaTest/__unnamed_task__/Iteration 224 MetaTest/__unnamed_task__/MaxReturn -84.8515 MetaTest/__unnamed_task__/MinReturn -88.7863 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.68851 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 375000 ------------------------------------------------- ------------ 2025-04-02 23:31:17 | [pearl_trainer] epoch #225 | Training... 2025-04-02 23:32:53 | [pearl_trainer] epoch #225 | Evaluating... 2025-04-02 23:32:53 | [pearl_trainer] epoch #225 | Sampling for adapation and meta-testing... 2025-04-02 23:33:39 | [pearl_trainer] epoch #225 | Finished meta-testing... 2025-04-02 23:33:39 | [pearl_trainer] epoch #225 | Saving snapshot... 2025-04-02 23:33:40 | [pearl_trainer] epoch #225 | Saved 2025-04-02 23:33:40 | [pearl_trainer] epoch #225 | Time 36296.14 s 2025-04-02 23:33:40 | [pearl_trainer] epoch #225 | EpochTime 168.92 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -96.3156 MetaTest/Average/AverageReturn -96.3156 MetaTest/Average/Iteration 225 MetaTest/Average/MaxReturn -88.3572 MetaTest/Average/MinReturn -101.444 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.70515 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.3156 MetaTest/__unnamed_task__/AverageReturn -96.3156 MetaTest/__unnamed_task__/Iteration 225 MetaTest/__unnamed_task__/MaxReturn -88.3572 MetaTest/__unnamed_task__/MinReturn -101.444 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.70515 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 376600 ------------------------------------------------- ------------ 2025-04-02 23:34:03 | [pearl_trainer] epoch #226 | Training... 2025-04-02 23:35:34 | [pearl_trainer] epoch #226 | Evaluating... 2025-04-02 23:35:34 | [pearl_trainer] epoch #226 | Sampling for adapation and meta-testing... 2025-04-02 23:36:22 | [pearl_trainer] epoch #226 | Finished meta-testing... 2025-04-02 23:36:22 | [pearl_trainer] epoch #226 | Saving snapshot... 2025-04-02 23:36:24 | [pearl_trainer] epoch #226 | Saved 2025-04-02 23:36:24 | [pearl_trainer] epoch #226 | Time 36459.70 s 2025-04-02 23:36:24 | [pearl_trainer] epoch #226 | EpochTime 163.56 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -118.592 MetaTest/Average/AverageReturn -118.592 MetaTest/Average/Iteration 226 MetaTest/Average/MaxReturn -86.411 MetaTest/Average/MinReturn -177.994 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 42.0523 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -118.592 MetaTest/__unnamed_task__/AverageReturn -118.592 MetaTest/__unnamed_task__/Iteration 226 MetaTest/__unnamed_task__/MaxReturn -86.411 MetaTest/__unnamed_task__/MinReturn -177.994 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 42.0523 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 378200 ------------------------------------------------- ----------- 2025-04-02 23:36:44 | [pearl_trainer] epoch #227 | Training... 2025-04-02 23:38:09 | [pearl_trainer] epoch #227 | Evaluating... 2025-04-02 23:38:09 | [pearl_trainer] epoch #227 | Sampling for adapation and meta-testing... 2025-04-02 23:38:58 | [pearl_trainer] epoch #227 | Finished meta-testing... 2025-04-02 23:38:58 | [pearl_trainer] epoch #227 | Saving snapshot... 2025-04-02 23:38:59 | [pearl_trainer] epoch #227 | Saved 2025-04-02 23:38:59 | [pearl_trainer] epoch #227 | Time 36615.30 s 2025-04-02 23:38:59 | [pearl_trainer] epoch #227 | EpochTime 155.59 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -95.4513 MetaTest/Average/AverageReturn -95.4513 MetaTest/Average/Iteration 227 MetaTest/Average/MaxReturn -87.6463 MetaTest/Average/MinReturn -99.6699 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.52501 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.4513 MetaTest/__unnamed_task__/AverageReturn -95.4513 MetaTest/__unnamed_task__/Iteration 227 MetaTest/__unnamed_task__/MaxReturn -87.6463 MetaTest/__unnamed_task__/MinReturn -99.6699 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.52501 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 379800 ------------------------------------------------- ------------ 2025-04-02 23:39:22 | [pearl_trainer] epoch #228 | Training... 2025-04-02 23:40:58 | [pearl_trainer] epoch #228 | Evaluating... 2025-04-02 23:40:58 | [pearl_trainer] epoch #228 | Sampling for adapation and meta-testing... 2025-04-02 23:41:42 | [pearl_trainer] epoch #228 | Finished meta-testing... 2025-04-02 23:41:42 | [pearl_trainer] epoch #228 | Saving snapshot... 2025-04-02 23:41:43 | [pearl_trainer] epoch #228 | Saved 2025-04-02 23:41:43 | [pearl_trainer] epoch #228 | Time 36779.61 s 2025-04-02 23:41:43 | [pearl_trainer] epoch #228 | EpochTime 164.31 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -87.5038 MetaTest/Average/AverageReturn -87.5038 MetaTest/Average/Iteration 228 MetaTest/Average/MaxReturn -77.9955 MetaTest/Average/MinReturn -94.2631 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.91984 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -87.5038 MetaTest/__unnamed_task__/AverageReturn -87.5038 MetaTest/__unnamed_task__/Iteration 228 MetaTest/__unnamed_task__/MaxReturn -77.9955 MetaTest/__unnamed_task__/MinReturn -94.2631 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.91984 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 381400 ------------------------------------------------- ------------ 2025-04-02 23:42:05 | [pearl_trainer] epoch #229 | Training... 2025-04-02 23:43:36 | [pearl_trainer] epoch #229 | Evaluating... 2025-04-02 23:43:36 | [pearl_trainer] epoch #229 | Sampling for adapation and meta-testing... 2025-04-02 23:44:20 | [pearl_trainer] epoch #229 | Finished meta-testing... 2025-04-02 23:44:20 | [pearl_trainer] epoch #229 | Saving snapshot... 2025-04-02 23:44:21 | [pearl_trainer] epoch #229 | Saved 2025-04-02 23:44:21 | [pearl_trainer] epoch #229 | Time 36937.33 s 2025-04-02 23:44:21 | [pearl_trainer] epoch #229 | EpochTime 157.72 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -95.0804 MetaTest/Average/AverageReturn -95.0804 MetaTest/Average/Iteration 229 MetaTest/Average/MaxReturn -90.9472 MetaTest/Average/MinReturn -97.3937 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.92954 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.0804 MetaTest/__unnamed_task__/AverageReturn -95.0804 MetaTest/__unnamed_task__/Iteration 229 MetaTest/__unnamed_task__/MaxReturn -90.9472 MetaTest/__unnamed_task__/MinReturn -97.3937 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.92954 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 383000 ------------------------------------------------- ------------ 2025-04-02 23:44:44 | [pearl_trainer] epoch #230 | Training... 2025-04-02 23:46:06 | [pearl_trainer] epoch #230 | Evaluating... 2025-04-02 23:46:06 | [pearl_trainer] epoch #230 | Sampling for adapation and meta-testing... 2025-04-02 23:46:51 | [pearl_trainer] epoch #230 | Finished meta-testing... 2025-04-02 23:46:51 | [pearl_trainer] epoch #230 | Saving snapshot... 2025-04-02 23:46:52 | [pearl_trainer] epoch #230 | Saved 2025-04-02 23:46:52 | [pearl_trainer] epoch #230 | Time 37088.01 s 2025-04-02 23:46:52 | [pearl_trainer] epoch #230 | EpochTime 150.68 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -94.6116 MetaTest/Average/AverageReturn -94.6116 MetaTest/Average/Iteration 230 MetaTest/Average/MaxReturn -87.7435 MetaTest/Average/MinReturn -104.345 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.074 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.6116 MetaTest/__unnamed_task__/AverageReturn -94.6116 MetaTest/__unnamed_task__/Iteration 230 MetaTest/__unnamed_task__/MaxReturn -87.7435 MetaTest/__unnamed_task__/MinReturn -104.345 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.074 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 384600 ------------------------------------------------- ----------- 2025-04-02 23:47:15 | [pearl_trainer] epoch #231 | Training... 2025-04-02 23:48:51 | [pearl_trainer] epoch #231 | Evaluating... 2025-04-02 23:48:51 | [pearl_trainer] epoch #231 | Sampling for adapation and meta-testing... 2025-04-02 23:49:36 | [pearl_trainer] epoch #231 | Finished meta-testing... 2025-04-02 23:49:36 | [pearl_trainer] epoch #231 | Saving snapshot... 2025-04-02 23:49:38 | [pearl_trainer] epoch #231 | Saved 2025-04-02 23:49:38 | [pearl_trainer] epoch #231 | Time 37253.88 s 2025-04-02 23:49:38 | [pearl_trainer] epoch #231 | EpochTime 165.87 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -98.7731 MetaTest/Average/AverageReturn -98.7731 MetaTest/Average/Iteration 231 MetaTest/Average/MaxReturn -86.5788 MetaTest/Average/MinReturn -110.881 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.92173 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.7731 MetaTest/__unnamed_task__/AverageReturn -98.7731 MetaTest/__unnamed_task__/Iteration 231 MetaTest/__unnamed_task__/MaxReturn -86.5788 MetaTest/__unnamed_task__/MinReturn -110.881 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.92173 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 386200 ------------------------------------------------- ------------ 2025-04-02 23:50:00 | [pearl_trainer] epoch #232 | Training... 2025-04-02 23:51:51 | [pearl_trainer] epoch #232 | Evaluating... 2025-04-02 23:51:51 | [pearl_trainer] epoch #232 | Sampling for adapation and meta-testing... 2025-04-02 23:52:44 | [pearl_trainer] epoch #232 | Finished meta-testing... 2025-04-02 23:52:44 | [pearl_trainer] epoch #232 | Saving snapshot... 2025-04-02 23:52:45 | [pearl_trainer] epoch #232 | Saved 2025-04-02 23:52:45 | [pearl_trainer] epoch #232 | Time 37440.82 s 2025-04-02 23:52:45 | [pearl_trainer] epoch #232 | EpochTime 186.93 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -79.5211 MetaTest/Average/AverageReturn -79.5211 MetaTest/Average/Iteration 232 MetaTest/Average/MaxReturn -78.6562 MetaTest/Average/MinReturn -80.1367 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 0.629563 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -79.5211 MetaTest/__unnamed_task__/AverageReturn -79.5211 MetaTest/__unnamed_task__/Iteration 232 MetaTest/__unnamed_task__/MaxReturn -78.6562 MetaTest/__unnamed_task__/MinReturn -80.1367 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 0.629563 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 387800 ------------------------------------------------- ------------- 2025-04-02 23:53:07 | [pearl_trainer] epoch #233 | Training... 2025-04-02 23:54:33 | [pearl_trainer] epoch #233 | Evaluating... 2025-04-02 23:54:33 | [pearl_trainer] epoch #233 | Sampling for adapation and meta-testing... 2025-04-02 23:55:19 | [pearl_trainer] epoch #233 | Finished meta-testing... 2025-04-02 23:55:19 | [pearl_trainer] epoch #233 | Saving snapshot... 2025-04-02 23:55:20 | [pearl_trainer] epoch #233 | Saved 2025-04-02 23:55:20 | [pearl_trainer] epoch #233 | Time 37596.53 s 2025-04-02 23:55:20 | [pearl_trainer] epoch #233 | EpochTime 155.71 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -91.2114 MetaTest/Average/AverageReturn -91.2114 MetaTest/Average/Iteration 233 MetaTest/Average/MaxReturn -87.2436 MetaTest/Average/MinReturn -93.311 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.80727 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.2114 MetaTest/__unnamed_task__/AverageReturn -91.2114 MetaTest/__unnamed_task__/Iteration 233 MetaTest/__unnamed_task__/MaxReturn -87.2436 MetaTest/__unnamed_task__/MinReturn -93.311 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.80727 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 389400 ------------------------------------------------- ------------ 2025-04-02 23:55:43 | [pearl_trainer] epoch #234 | Training... 2025-04-02 23:57:17 | [pearl_trainer] epoch #234 | Evaluating... 2025-04-02 23:57:17 | [pearl_trainer] epoch #234 | Sampling for adapation and meta-testing... 2025-04-02 23:58:02 | [pearl_trainer] epoch #234 | Finished meta-testing... 2025-04-02 23:58:02 | [pearl_trainer] epoch #234 | Saving snapshot... 2025-04-02 23:58:03 | [pearl_trainer] epoch #234 | Saved 2025-04-02 23:58:03 | [pearl_trainer] epoch #234 | Time 37759.21 s 2025-04-02 23:58:03 | [pearl_trainer] epoch #234 | EpochTime 162.68 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -104.084 MetaTest/Average/AverageReturn -104.084 MetaTest/Average/Iteration 234 MetaTest/Average/MaxReturn -98.047 MetaTest/Average/MinReturn -109.073 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.5618 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -104.084 MetaTest/__unnamed_task__/AverageReturn -104.084 MetaTest/__unnamed_task__/Iteration 234 MetaTest/__unnamed_task__/MaxReturn -98.047 MetaTest/__unnamed_task__/MinReturn -109.073 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.5618 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 391000 ------------------------------------------------- ----------- 2025-04-02 23:58:25 | [pearl_trainer] epoch #235 | Training... 2025-04-02 23:59:56 | [pearl_trainer] epoch #235 | Evaluating... 2025-04-02 23:59:56 | [pearl_trainer] epoch #235 | Sampling for adapation and meta-testing... 2025-04-03 00:00:44 | [pearl_trainer] epoch #235 | Finished meta-testing... 2025-04-03 00:00:44 | [pearl_trainer] epoch #235 | Saving snapshot... 2025-04-03 00:00:45 | [pearl_trainer] epoch #235 | Saved 2025-04-03 00:00:45 | [pearl_trainer] epoch #235 | Time 37920.83 s 2025-04-03 00:00:45 | [pearl_trainer] epoch #235 | EpochTime 161.62 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -95.9882 MetaTest/Average/AverageReturn -95.9882 MetaTest/Average/Iteration 235 MetaTest/Average/MaxReturn -86.9059 MetaTest/Average/MinReturn -112.909 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.9755 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.9882 MetaTest/__unnamed_task__/AverageReturn -95.9882 MetaTest/__unnamed_task__/Iteration 235 MetaTest/__unnamed_task__/MaxReturn -86.9059 MetaTest/__unnamed_task__/MinReturn -112.909 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.9755 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 392600 ------------------------------------------------- ----------- 2025-04-03 00:01:08 | [pearl_trainer] epoch #236 | Training... 2025-04-03 00:02:30 | [pearl_trainer] epoch #236 | Evaluating... 2025-04-03 00:02:30 | [pearl_trainer] epoch #236 | Sampling for adapation and meta-testing... 2025-04-03 00:03:20 | [pearl_trainer] epoch #236 | Finished meta-testing... 2025-04-03 00:03:20 | [pearl_trainer] epoch #236 | Saving snapshot... 2025-04-03 00:03:21 | [pearl_trainer] epoch #236 | Saved 2025-04-03 00:03:21 | [pearl_trainer] epoch #236 | Time 38077.22 s 2025-04-03 00:03:21 | [pearl_trainer] epoch #236 | EpochTime 156.39 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -99.5166 MetaTest/Average/AverageReturn -99.5166 MetaTest/Average/Iteration 236 MetaTest/Average/MaxReturn -94.7569 MetaTest/Average/MinReturn -107 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.35638 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -99.5166 MetaTest/__unnamed_task__/AverageReturn -99.5166 MetaTest/__unnamed_task__/Iteration 236 MetaTest/__unnamed_task__/MaxReturn -94.7569 MetaTest/__unnamed_task__/MinReturn -107 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.35638 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 394200 ------------------------------------------------- ------------ 2025-04-03 00:03:44 | [pearl_trainer] epoch #237 | Training... 2025-04-03 00:05:17 | [pearl_trainer] epoch #237 | Evaluating... 2025-04-03 00:05:17 | [pearl_trainer] epoch #237 | Sampling for adapation and meta-testing... 2025-04-03 00:06:03 | [pearl_trainer] epoch #237 | Finished meta-testing... 2025-04-03 00:06:03 | [pearl_trainer] epoch #237 | Saving snapshot... 2025-04-03 00:06:04 | [pearl_trainer] epoch #237 | Saved 2025-04-03 00:06:04 | [pearl_trainer] epoch #237 | Time 38240.56 s 2025-04-03 00:06:04 | [pearl_trainer] epoch #237 | EpochTime 163.34 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -95.1194 MetaTest/Average/AverageReturn -95.1194 MetaTest/Average/Iteration 237 MetaTest/Average/MaxReturn -92.554 MetaTest/Average/MinReturn -97.7756 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.13267 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.1194 MetaTest/__unnamed_task__/AverageReturn -95.1194 MetaTest/__unnamed_task__/Iteration 237 MetaTest/__unnamed_task__/MaxReturn -92.554 MetaTest/__unnamed_task__/MinReturn -97.7756 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.13267 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 395800 ------------------------------------------------- ------------ 2025-04-03 00:06:26 | [pearl_trainer] epoch #238 | Training... 2025-04-03 00:08:05 | [pearl_trainer] epoch #238 | Evaluating... 2025-04-03 00:08:05 | [pearl_trainer] epoch #238 | Sampling for adapation and meta-testing... 2025-04-03 00:08:53 | [pearl_trainer] epoch #238 | Finished meta-testing... 2025-04-03 00:08:53 | [pearl_trainer] epoch #238 | Saving snapshot... 2025-04-03 00:08:54 | [pearl_trainer] epoch #238 | Saved 2025-04-03 00:08:54 | [pearl_trainer] epoch #238 | Time 38409.89 s 2025-04-03 00:08:54 | [pearl_trainer] epoch #238 | EpochTime 169.33 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -98.1396 MetaTest/Average/AverageReturn -98.1396 MetaTest/Average/Iteration 238 MetaTest/Average/MaxReturn -93.6523 MetaTest/Average/MinReturn -102.231 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.51346 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.1396 MetaTest/__unnamed_task__/AverageReturn -98.1396 MetaTest/__unnamed_task__/Iteration 238 MetaTest/__unnamed_task__/MaxReturn -93.6523 MetaTest/__unnamed_task__/MinReturn -102.231 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.51346 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 397400 ------------------------------------------------- ------------ 2025-04-03 00:09:14 | [pearl_trainer] epoch #239 | Training... 2025-04-03 00:10:33 | [pearl_trainer] epoch #239 | Evaluating... 2025-04-03 00:10:33 | [pearl_trainer] epoch #239 | Sampling for adapation and meta-testing... 2025-04-03 00:11:28 | [pearl_trainer] epoch #239 | Finished meta-testing... 2025-04-03 00:11:28 | [pearl_trainer] epoch #239 | Saving snapshot... 2025-04-03 00:11:29 | [pearl_trainer] epoch #239 | Saved 2025-04-03 00:11:29 | [pearl_trainer] epoch #239 | Time 38565.22 s 2025-04-03 00:11:29 | [pearl_trainer] epoch #239 | EpochTime 155.32 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -81.8471 MetaTest/Average/AverageReturn -81.8471 MetaTest/Average/Iteration 239 MetaTest/Average/MaxReturn -78.2648 MetaTest/Average/MinReturn -87.3506 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.9502 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -81.8471 MetaTest/__unnamed_task__/AverageReturn -81.8471 MetaTest/__unnamed_task__/Iteration 239 MetaTest/__unnamed_task__/MaxReturn -78.2648 MetaTest/__unnamed_task__/MinReturn -87.3506 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.9502 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 399000 ------------------------------------------------- ----------- 2025-04-03 00:11:51 | [pearl_trainer] epoch #240 | Training... 2025-04-03 00:13:15 | [pearl_trainer] epoch #240 | Evaluating... 2025-04-03 00:13:15 | [pearl_trainer] epoch #240 | Sampling for adapation and meta-testing... 2025-04-03 00:14:04 | [pearl_trainer] epoch #240 | Finished meta-testing... 2025-04-03 00:14:04 | [pearl_trainer] epoch #240 | Saving snapshot... 2025-04-03 00:14:05 | [pearl_trainer] epoch #240 | Saved 2025-04-03 00:14:05 | [pearl_trainer] epoch #240 | Time 38721.07 s 2025-04-03 00:14:05 | [pearl_trainer] epoch #240 | EpochTime 155.85 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -96.0831 MetaTest/Average/AverageReturn -96.0831 MetaTest/Average/Iteration 240 MetaTest/Average/MaxReturn -86.8881 MetaTest/Average/MinReturn -103.094 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.79387 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.0831 MetaTest/__unnamed_task__/AverageReturn -96.0831 MetaTest/__unnamed_task__/Iteration 240 MetaTest/__unnamed_task__/MaxReturn -86.8881 MetaTest/__unnamed_task__/MinReturn -103.094 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.79387 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 400600 ------------------------------------------------- ------------ 2025-04-03 00:14:28 | [pearl_trainer] epoch #241 | Training... 2025-04-03 00:16:14 | [pearl_trainer] epoch #241 | Evaluating... 2025-04-03 00:16:14 | [pearl_trainer] epoch #241 | Sampling for adapation and meta-testing... 2025-04-03 00:17:00 | [pearl_trainer] epoch #241 | Finished meta-testing... 2025-04-03 00:17:00 | [pearl_trainer] epoch #241 | Saving snapshot... 2025-04-03 00:17:01 | [pearl_trainer] epoch #241 | Saved 2025-04-03 00:17:01 | [pearl_trainer] epoch #241 | Time 38897.04 s 2025-04-03 00:17:01 | [pearl_trainer] epoch #241 | EpochTime 175.97 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.4781 MetaTest/Average/AverageReturn -90.4781 MetaTest/Average/Iteration 241 MetaTest/Average/MaxReturn -81.0597 MetaTest/Average/MinReturn -96.2646 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.71764 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.4781 MetaTest/__unnamed_task__/AverageReturn -90.4781 MetaTest/__unnamed_task__/Iteration 241 MetaTest/__unnamed_task__/MaxReturn -81.0597 MetaTest/__unnamed_task__/MinReturn -96.2646 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.71764 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 402200 ------------------------------------------------- ------------ 2025-04-03 00:17:23 | [pearl_trainer] epoch #242 | Training... 2025-04-03 00:18:53 | [pearl_trainer] epoch #242 | Evaluating... 2025-04-03 00:18:53 | [pearl_trainer] epoch #242 | Sampling for adapation and meta-testing... 2025-04-03 00:19:46 | [pearl_trainer] epoch #242 | Finished meta-testing... 2025-04-03 00:19:46 | [pearl_trainer] epoch #242 | Saving snapshot... 2025-04-03 00:19:48 | [pearl_trainer] epoch #242 | Saved 2025-04-03 00:19:48 | [pearl_trainer] epoch #242 | Time 39063.94 s 2025-04-03 00:19:48 | [pearl_trainer] epoch #242 | EpochTime 166.90 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -87.2953 MetaTest/Average/AverageReturn -87.2953 MetaTest/Average/Iteration 242 MetaTest/Average/MaxReturn -78.7652 MetaTest/Average/MinReturn -103.124 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.2037 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -87.2953 MetaTest/__unnamed_task__/AverageReturn -87.2953 MetaTest/__unnamed_task__/Iteration 242 MetaTest/__unnamed_task__/MaxReturn -78.7652 MetaTest/__unnamed_task__/MinReturn -103.124 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.2037 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 403800 ------------------------------------------------- ----------- 2025-04-03 00:20:11 | [pearl_trainer] epoch #243 | Training... 2025-04-03 00:21:35 | [pearl_trainer] epoch #243 | Evaluating... 2025-04-03 00:21:35 | [pearl_trainer] epoch #243 | Sampling for adapation and meta-testing... 2025-04-03 00:22:22 | [pearl_trainer] epoch #243 | Finished meta-testing... 2025-04-03 00:22:22 | [pearl_trainer] epoch #243 | Saving snapshot... 2025-04-03 00:22:23 | [pearl_trainer] epoch #243 | Saved 2025-04-03 00:22:23 | [pearl_trainer] epoch #243 | Time 39219.08 s 2025-04-03 00:22:23 | [pearl_trainer] epoch #243 | EpochTime 155.14 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -110.355 MetaTest/Average/AverageReturn -110.355 MetaTest/Average/Iteration 243 MetaTest/Average/MaxReturn -87.041 MetaTest/Average/MinReturn -138.546 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 21.3077 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -110.355 MetaTest/__unnamed_task__/AverageReturn -110.355 MetaTest/__unnamed_task__/Iteration 243 MetaTest/__unnamed_task__/MaxReturn -87.041 MetaTest/__unnamed_task__/MinReturn -138.546 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 21.3077 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 405400 ------------------------------------------------- ----------- 2025-04-03 00:22:47 | [pearl_trainer] epoch #244 | Training... 2025-04-03 00:24:20 | [pearl_trainer] epoch #244 | Evaluating... 2025-04-03 00:24:20 | [pearl_trainer] epoch #244 | Sampling for adapation and meta-testing... 2025-04-03 00:25:03 | [pearl_trainer] epoch #244 | Finished meta-testing... 2025-04-03 00:25:03 | [pearl_trainer] epoch #244 | Saving snapshot... 2025-04-03 00:25:04 | [pearl_trainer] epoch #244 | Saved 2025-04-03 00:25:04 | [pearl_trainer] epoch #244 | Time 39380.49 s 2025-04-03 00:25:04 | [pearl_trainer] epoch #244 | EpochTime 161.41 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -92.1755 MetaTest/Average/AverageReturn -92.1755 MetaTest/Average/Iteration 244 MetaTest/Average/MaxReturn -83.1571 MetaTest/Average/MinReturn -106.011 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.9321 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.1755 MetaTest/__unnamed_task__/AverageReturn -92.1755 MetaTest/__unnamed_task__/Iteration 244 MetaTest/__unnamed_task__/MaxReturn -83.1571 MetaTest/__unnamed_task__/MinReturn -106.011 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.9321 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 407000 ------------------------------------------------- ----------- 2025-04-03 00:25:25 | [pearl_trainer] epoch #245 | Training... 2025-04-03 00:26:57 | [pearl_trainer] epoch #245 | Evaluating... 2025-04-03 00:26:57 | [pearl_trainer] epoch #245 | Sampling for adapation and meta-testing... 2025-04-03 00:27:48 | [pearl_trainer] epoch #245 | Finished meta-testing... 2025-04-03 00:27:48 | [pearl_trainer] epoch #245 | Saving snapshot... 2025-04-03 00:27:49 | [pearl_trainer] epoch #245 | Saved 2025-04-03 00:27:49 | [pearl_trainer] epoch #245 | Time 39544.97 s 2025-04-03 00:27:49 | [pearl_trainer] epoch #245 | EpochTime 164.48 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -94.6693 MetaTest/Average/AverageReturn -94.6693 MetaTest/Average/Iteration 245 MetaTest/Average/MaxReturn -80.3529 MetaTest/Average/MinReturn -105.327 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.5187 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.6693 MetaTest/__unnamed_task__/AverageReturn -94.6693 MetaTest/__unnamed_task__/Iteration 245 MetaTest/__unnamed_task__/MaxReturn -80.3529 MetaTest/__unnamed_task__/MinReturn -105.327 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.5187 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 408600 ------------------------------------------------- ----------- 2025-04-03 00:28:11 | [pearl_trainer] epoch #246 | Training... 2025-04-03 00:29:44 | [pearl_trainer] epoch #246 | Evaluating... 2025-04-03 00:29:44 | [pearl_trainer] epoch #246 | Sampling for adapation and meta-testing... 2025-04-03 00:30:29 | [pearl_trainer] epoch #246 | Finished meta-testing... 2025-04-03 00:30:29 | [pearl_trainer] epoch #246 | Saving snapshot... 2025-04-03 00:30:30 | [pearl_trainer] epoch #246 | Saved 2025-04-03 00:30:30 | [pearl_trainer] epoch #246 | Time 39706.08 s 2025-04-03 00:30:30 | [pearl_trainer] epoch #246 | EpochTime 161.11 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -121.26 MetaTest/Average/AverageReturn -121.26 MetaTest/Average/Iteration 246 MetaTest/Average/MaxReturn -98.2892 MetaTest/Average/MinReturn -153.886 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 23.7019 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -121.26 MetaTest/__unnamed_task__/AverageReturn -121.26 MetaTest/__unnamed_task__/Iteration 246 MetaTest/__unnamed_task__/MaxReturn -98.2892 MetaTest/__unnamed_task__/MinReturn -153.886 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 23.7019 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 410200 ------------------------------------------------- ----------- 2025-04-03 00:30:53 | [pearl_trainer] epoch #247 | Training... 2025-04-03 00:32:21 | [pearl_trainer] epoch #247 | Evaluating... 2025-04-03 00:32:21 | [pearl_trainer] epoch #247 | Sampling for adapation and meta-testing... 2025-04-03 00:33:11 | [pearl_trainer] epoch #247 | Finished meta-testing... 2025-04-03 00:33:11 | [pearl_trainer] epoch #247 | Saving snapshot... 2025-04-03 00:33:12 | [pearl_trainer] epoch #247 | Saved 2025-04-03 00:33:12 | [pearl_trainer] epoch #247 | Time 39868.30 s 2025-04-03 00:33:12 | [pearl_trainer] epoch #247 | EpochTime 162.22 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.9302 MetaTest/Average/AverageReturn -93.9302 MetaTest/Average/Iteration 247 MetaTest/Average/MaxReturn -87.8678 MetaTest/Average/MinReturn -102.165 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.03545 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.9302 MetaTest/__unnamed_task__/AverageReturn -93.9302 MetaTest/__unnamed_task__/Iteration 247 MetaTest/__unnamed_task__/MaxReturn -87.8678 MetaTest/__unnamed_task__/MinReturn -102.165 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.03545 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 411800 ------------------------------------------------- ------------ 2025-04-03 00:33:34 | [pearl_trainer] epoch #248 | Training... 2025-04-03 00:35:06 | [pearl_trainer] epoch #248 | Evaluating... 2025-04-03 00:35:06 | [pearl_trainer] epoch #248 | Sampling for adapation and meta-testing... 2025-04-03 00:35:53 | [pearl_trainer] epoch #248 | Finished meta-testing... 2025-04-03 00:35:53 | [pearl_trainer] epoch #248 | Saving snapshot... 2025-04-03 00:35:54 | [pearl_trainer] epoch #248 | Saved 2025-04-03 00:35:54 | [pearl_trainer] epoch #248 | Time 40030.64 s 2025-04-03 00:35:54 | [pearl_trainer] epoch #248 | EpochTime 162.34 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -104.821 MetaTest/Average/AverageReturn -104.821 MetaTest/Average/Iteration 248 MetaTest/Average/MaxReturn -99.4287 MetaTest/Average/MinReturn -114.414 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.80081 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -104.821 MetaTest/__unnamed_task__/AverageReturn -104.821 MetaTest/__unnamed_task__/Iteration 248 MetaTest/__unnamed_task__/MaxReturn -99.4287 MetaTest/__unnamed_task__/MinReturn -114.414 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.80081 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 413400 ------------------------------------------------- ------------ 2025-04-03 00:36:16 | [pearl_trainer] epoch #249 | Training... 2025-04-03 00:37:42 | [pearl_trainer] epoch #249 | Evaluating... 2025-04-03 00:37:42 | [pearl_trainer] epoch #249 | Sampling for adapation and meta-testing... 2025-04-03 00:38:29 | [pearl_trainer] epoch #249 | Finished meta-testing... 2025-04-03 00:38:29 | [pearl_trainer] epoch #249 | Saving snapshot... 2025-04-03 00:38:30 | [pearl_trainer] epoch #249 | Saved 2025-04-03 00:38:30 | [pearl_trainer] epoch #249 | Time 40186.14 s 2025-04-03 00:38:30 | [pearl_trainer] epoch #249 | EpochTime 155.50 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.1684 MetaTest/Average/AverageReturn -97.1684 MetaTest/Average/Iteration 249 MetaTest/Average/MaxReturn -93.3455 MetaTest/Average/MinReturn -99.312 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.70985 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.1684 MetaTest/__unnamed_task__/AverageReturn -97.1684 MetaTest/__unnamed_task__/Iteration 249 MetaTest/__unnamed_task__/MaxReturn -93.3455 MetaTest/__unnamed_task__/MinReturn -99.312 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.70985 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 415000 ------------------------------------------------- ------------ 2025-04-03 00:38:54 | [pearl_trainer] epoch #250 | Training... 2025-04-03 00:40:25 | [pearl_trainer] epoch #250 | Evaluating... 2025-04-03 00:40:25 | [pearl_trainer] epoch #250 | Sampling for adapation and meta-testing... 2025-04-03 00:41:07 | [pearl_trainer] epoch #250 | Finished meta-testing... 2025-04-03 00:41:07 | [pearl_trainer] epoch #250 | Saving snapshot... 2025-04-03 00:41:08 | [pearl_trainer] epoch #250 | Saved 2025-04-03 00:41:08 | [pearl_trainer] epoch #250 | Time 40344.43 s 2025-04-03 00:41:08 | [pearl_trainer] epoch #250 | EpochTime 158.29 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -91.0551 MetaTest/Average/AverageReturn -91.0551 MetaTest/Average/Iteration 250 MetaTest/Average/MaxReturn -88.0416 MetaTest/Average/MinReturn -95.3496 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.11796 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.0551 MetaTest/__unnamed_task__/AverageReturn -91.0551 MetaTest/__unnamed_task__/Iteration 250 MetaTest/__unnamed_task__/MaxReturn -88.0416 MetaTest/__unnamed_task__/MinReturn -95.3496 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.11796 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 416600 ------------------------------------------------- ------------ 2025-04-03 00:41:29 | [pearl_trainer] epoch #251 | Training... 2025-04-03 00:43:07 | [pearl_trainer] epoch #251 | Evaluating... 2025-04-03 00:43:07 | [pearl_trainer] epoch #251 | Sampling for adapation and meta-testing... 2025-04-03 00:43:53 | [pearl_trainer] epoch #251 | Finished meta-testing... 2025-04-03 00:43:53 | [pearl_trainer] epoch #251 | Saving snapshot... 2025-04-03 00:43:54 | [pearl_trainer] epoch #251 | Saved 2025-04-03 00:43:54 | [pearl_trainer] epoch #251 | Time 40510.05 s 2025-04-03 00:43:54 | [pearl_trainer] epoch #251 | EpochTime 165.61 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -92.6113 MetaTest/Average/AverageReturn -92.6113 MetaTest/Average/Iteration 251 MetaTest/Average/MaxReturn -84.9294 MetaTest/Average/MinReturn -97.9288 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.56407 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.6113 MetaTest/__unnamed_task__/AverageReturn -92.6113 MetaTest/__unnamed_task__/Iteration 251 MetaTest/__unnamed_task__/MaxReturn -84.9294 MetaTest/__unnamed_task__/MinReturn -97.9288 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.56407 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 418200 ------------------------------------------------- ------------ 2025-04-03 00:44:14 | [pearl_trainer] epoch #252 | Training... 2025-04-03 00:45:42 | [pearl_trainer] epoch #252 | Evaluating... 2025-04-03 00:45:42 | [pearl_trainer] epoch #252 | Sampling for adapation and meta-testing... 2025-04-03 00:46:46 | [pearl_trainer] epoch #252 | Finished meta-testing... 2025-04-03 00:46:46 | [pearl_trainer] epoch #252 | Saving snapshot... 2025-04-03 00:46:47 | [pearl_trainer] epoch #252 | Saved 2025-04-03 00:46:47 | [pearl_trainer] epoch #252 | Time 40683.52 s 2025-04-03 00:46:47 | [pearl_trainer] epoch #252 | EpochTime 173.47 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -100.302 MetaTest/Average/AverageReturn -100.302 MetaTest/Average/Iteration 252 MetaTest/Average/MaxReturn -89.2152 MetaTest/Average/MinReturn -108.373 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.10666 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -100.302 MetaTest/__unnamed_task__/AverageReturn -100.302 MetaTest/__unnamed_task__/Iteration 252 MetaTest/__unnamed_task__/MaxReturn -89.2152 MetaTest/__unnamed_task__/MinReturn -108.373 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.10666 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 419800 ------------------------------------------------- ------------ 2025-04-03 00:47:13 | [pearl_trainer] epoch #253 | Training... 2025-04-03 00:48:43 | [pearl_trainer] epoch #253 | Evaluating... 2025-04-03 00:48:43 | [pearl_trainer] epoch #253 | Sampling for adapation and meta-testing... 2025-04-03 00:49:30 | [pearl_trainer] epoch #253 | Finished meta-testing... 2025-04-03 00:49:30 | [pearl_trainer] epoch #253 | Saving snapshot... 2025-04-03 00:49:31 | [pearl_trainer] epoch #253 | Saved 2025-04-03 00:49:31 | [pearl_trainer] epoch #253 | Time 40846.91 s 2025-04-03 00:49:31 | [pearl_trainer] epoch #253 | EpochTime 163.39 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -104.776 MetaTest/Average/AverageReturn -104.776 MetaTest/Average/Iteration 253 MetaTest/Average/MaxReturn -102.198 MetaTest/Average/MinReturn -109.431 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.29808 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -104.776 MetaTest/__unnamed_task__/AverageReturn -104.776 MetaTest/__unnamed_task__/Iteration 253 MetaTest/__unnamed_task__/MaxReturn -102.198 MetaTest/__unnamed_task__/MinReturn -109.431 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.29808 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 421400 ------------------------------------------------- ------------ 2025-04-03 00:49:54 | [pearl_trainer] epoch #254 | Training... 2025-04-03 00:51:27 | [pearl_trainer] epoch #254 | Evaluating... 2025-04-03 00:51:27 | [pearl_trainer] epoch #254 | Sampling for adapation and meta-testing... 2025-04-03 00:52:19 | [pearl_trainer] epoch #254 | Finished meta-testing... 2025-04-03 00:52:19 | [pearl_trainer] epoch #254 | Saving snapshot... 2025-04-03 00:52:20 | [pearl_trainer] epoch #254 | Saved 2025-04-03 00:52:20 | [pearl_trainer] epoch #254 | Time 41015.96 s 2025-04-03 00:52:20 | [pearl_trainer] epoch #254 | EpochTime 169.05 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -112.784 MetaTest/Average/AverageReturn -112.784 MetaTest/Average/Iteration 254 MetaTest/Average/MaxReturn -92.9455 MetaTest/Average/MinReturn -124.738 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.1258 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -112.784 MetaTest/__unnamed_task__/AverageReturn -112.784 MetaTest/__unnamed_task__/Iteration 254 MetaTest/__unnamed_task__/MaxReturn -92.9455 MetaTest/__unnamed_task__/MinReturn -124.738 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.1258 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 423000 ------------------------------------------------- ----------- 2025-04-03 00:52:41 | [pearl_trainer] epoch #255 | Training... 2025-04-03 00:54:05 | [pearl_trainer] epoch #255 | Evaluating... 2025-04-03 00:54:05 | [pearl_trainer] epoch #255 | Sampling for adapation and meta-testing... 2025-04-03 00:54:55 | [pearl_trainer] epoch #255 | Finished meta-testing... 2025-04-03 00:54:55 | [pearl_trainer] epoch #255 | Saving snapshot... 2025-04-03 00:54:57 | [pearl_trainer] epoch #255 | Saved 2025-04-03 00:54:57 | [pearl_trainer] epoch #255 | Time 41172.92 s 2025-04-03 00:54:57 | [pearl_trainer] epoch #255 | EpochTime 156.96 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -111.755 MetaTest/Average/AverageReturn -111.755 MetaTest/Average/Iteration 255 MetaTest/Average/MaxReturn -93.4269 MetaTest/Average/MinReturn -129.718 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.8179 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.755 MetaTest/__unnamed_task__/AverageReturn -111.755 MetaTest/__unnamed_task__/Iteration 255 MetaTest/__unnamed_task__/MaxReturn -93.4269 MetaTest/__unnamed_task__/MinReturn -129.718 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.8179 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 424600 ------------------------------------------------- ----------- 2025-04-03 00:55:23 | [pearl_trainer] epoch #256 | Training... 2025-04-03 00:56:50 | [pearl_trainer] epoch #256 | Evaluating... 2025-04-03 00:56:50 | [pearl_trainer] epoch #256 | Sampling for adapation and meta-testing... 2025-04-03 00:57:34 | [pearl_trainer] epoch #256 | Finished meta-testing... 2025-04-03 00:57:34 | [pearl_trainer] epoch #256 | Saving snapshot... 2025-04-03 00:57:35 | [pearl_trainer] epoch #256 | Saved 2025-04-03 00:57:35 | [pearl_trainer] epoch #256 | Time 41330.94 s 2025-04-03 00:57:35 | [pearl_trainer] epoch #256 | EpochTime 158.02 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -117.158 MetaTest/Average/AverageReturn -117.158 MetaTest/Average/Iteration 256 MetaTest/Average/MaxReturn -82.8895 MetaTest/Average/MinReturn -140.347 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 24.7307 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -117.158 MetaTest/__unnamed_task__/AverageReturn -117.158 MetaTest/__unnamed_task__/Iteration 256 MetaTest/__unnamed_task__/MaxReturn -82.8895 MetaTest/__unnamed_task__/MinReturn -140.347 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 24.7307 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 426200 ------------------------------------------------- ----------- 2025-04-03 00:57:57 | [pearl_trainer] epoch #257 | Training... 2025-04-03 00:59:30 | [pearl_trainer] epoch #257 | Evaluating... 2025-04-03 00:59:30 | [pearl_trainer] epoch #257 | Sampling for adapation and meta-testing... 2025-04-03 01:00:15 | [pearl_trainer] epoch #257 | Finished meta-testing... 2025-04-03 01:00:15 | [pearl_trainer] epoch #257 | Saving snapshot... 2025-04-03 01:00:17 | [pearl_trainer] epoch #257 | Saved 2025-04-03 01:00:17 | [pearl_trainer] epoch #257 | Time 41493.06 s 2025-04-03 01:00:17 | [pearl_trainer] epoch #257 | EpochTime 162.12 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -129.511 MetaTest/Average/AverageReturn -129.511 MetaTest/Average/Iteration 257 MetaTest/Average/MaxReturn -125.953 MetaTest/Average/MinReturn -134.55 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.66271 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -129.511 MetaTest/__unnamed_task__/AverageReturn -129.511 MetaTest/__unnamed_task__/Iteration 257 MetaTest/__unnamed_task__/MaxReturn -125.953 MetaTest/__unnamed_task__/MinReturn -134.55 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.66271 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 427800 ------------------------------------------------- ------------ 2025-04-03 01:00:39 | [pearl_trainer] epoch #258 | Training... 2025-04-03 01:02:06 | [pearl_trainer] epoch #258 | Evaluating... 2025-04-03 01:02:06 | [pearl_trainer] epoch #258 | Sampling for adapation and meta-testing... 2025-04-03 01:02:56 | [pearl_trainer] epoch #258 | Finished meta-testing... 2025-04-03 01:02:56 | [pearl_trainer] epoch #258 | Saving snapshot... 2025-04-03 01:02:57 | [pearl_trainer] epoch #258 | Saved 2025-04-03 01:02:57 | [pearl_trainer] epoch #258 | Time 41653.05 s 2025-04-03 01:02:57 | [pearl_trainer] epoch #258 | EpochTime 159.99 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -99.2003 MetaTest/Average/AverageReturn -99.2003 MetaTest/Average/Iteration 258 MetaTest/Average/MaxReturn -82.5993 MetaTest/Average/MinReturn -121.765 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 16.5361 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -99.2003 MetaTest/__unnamed_task__/AverageReturn -99.2003 MetaTest/__unnamed_task__/Iteration 258 MetaTest/__unnamed_task__/MaxReturn -82.5993 MetaTest/__unnamed_task__/MinReturn -121.765 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 16.5361 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 429400 ------------------------------------------------- ----------- 2025-04-03 01:03:20 | [pearl_trainer] epoch #259 | Training... 2025-04-03 01:04:46 | [pearl_trainer] epoch #259 | Evaluating... 2025-04-03 01:04:46 | [pearl_trainer] epoch #259 | Sampling for adapation and meta-testing... 2025-04-03 01:05:34 | [pearl_trainer] epoch #259 | Finished meta-testing... 2025-04-03 01:05:34 | [pearl_trainer] epoch #259 | Saving snapshot... 2025-04-03 01:05:35 | [pearl_trainer] epoch #259 | Saved 2025-04-03 01:05:35 | [pearl_trainer] epoch #259 | Time 41811.24 s 2025-04-03 01:05:35 | [pearl_trainer] epoch #259 | EpochTime 158.19 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -99.7892 MetaTest/Average/AverageReturn -99.7892 MetaTest/Average/Iteration 259 MetaTest/Average/MaxReturn -94.4445 MetaTest/Average/MinReturn -109.469 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.85717 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -99.7892 MetaTest/__unnamed_task__/AverageReturn -99.7892 MetaTest/__unnamed_task__/Iteration 259 MetaTest/__unnamed_task__/MaxReturn -94.4445 MetaTest/__unnamed_task__/MinReturn -109.469 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.85717 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 431000 ------------------------------------------------- ------------ 2025-04-03 01:05:58 | [pearl_trainer] epoch #260 | Training... 2025-04-03 01:07:26 | [pearl_trainer] epoch #260 | Evaluating... 2025-04-03 01:07:26 | [pearl_trainer] epoch #260 | Sampling for adapation and meta-testing... 2025-04-03 01:08:12 | [pearl_trainer] epoch #260 | Finished meta-testing... 2025-04-03 01:08:12 | [pearl_trainer] epoch #260 | Saving snapshot... 2025-04-03 01:08:13 | [pearl_trainer] epoch #260 | Saved 2025-04-03 01:08:13 | [pearl_trainer] epoch #260 | Time 41969.33 s 2025-04-03 01:08:13 | [pearl_trainer] epoch #260 | EpochTime 158.09 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -91.8259 MetaTest/Average/AverageReturn -91.8259 MetaTest/Average/Iteration 260 MetaTest/Average/MaxReturn -80.1389 MetaTest/Average/MinReturn -100.763 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.6413 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.8259 MetaTest/__unnamed_task__/AverageReturn -91.8259 MetaTest/__unnamed_task__/Iteration 260 MetaTest/__unnamed_task__/MaxReturn -80.1389 MetaTest/__unnamed_task__/MinReturn -100.763 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.6413 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 432600 ------------------------------------------------- ----------- 2025-04-03 01:08:35 | [pearl_trainer] epoch #261 | Training... 2025-04-03 01:10:03 | [pearl_trainer] epoch #261 | Evaluating... 2025-04-03 01:10:03 | [pearl_trainer] epoch #261 | Sampling for adapation and meta-testing... 2025-04-03 01:10:52 | [pearl_trainer] epoch #261 | Finished meta-testing... 2025-04-03 01:10:52 | [pearl_trainer] epoch #261 | Saving snapshot... 2025-04-03 01:10:53 | [pearl_trainer] epoch #261 | Saved 2025-04-03 01:10:53 | [pearl_trainer] epoch #261 | Time 42129.44 s 2025-04-03 01:10:53 | [pearl_trainer] epoch #261 | EpochTime 160.11 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -100.545 MetaTest/Average/AverageReturn -100.545 MetaTest/Average/Iteration 261 MetaTest/Average/MaxReturn -96.9243 MetaTest/Average/MinReturn -104.737 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.21483 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -100.545 MetaTest/__unnamed_task__/AverageReturn -100.545 MetaTest/__unnamed_task__/Iteration 261 MetaTest/__unnamed_task__/MaxReturn -96.9243 MetaTest/__unnamed_task__/MinReturn -104.737 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.21483 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 434200 ------------------------------------------------- ------------ 2025-04-03 01:11:16 | [pearl_trainer] epoch #262 | Training... 2025-04-03 01:12:41 | [pearl_trainer] epoch #262 | Evaluating... 2025-04-03 01:12:41 | [pearl_trainer] epoch #262 | Sampling for adapation and meta-testing... 2025-04-03 01:13:27 | [pearl_trainer] epoch #262 | Finished meta-testing... 2025-04-03 01:13:27 | [pearl_trainer] epoch #262 | Saving snapshot... 2025-04-03 01:13:28 | [pearl_trainer] epoch #262 | Saved 2025-04-03 01:13:28 | [pearl_trainer] epoch #262 | Time 42284.00 s 2025-04-03 01:13:28 | [pearl_trainer] epoch #262 | EpochTime 154.56 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.0988 MetaTest/Average/AverageReturn -93.0988 MetaTest/Average/Iteration 262 MetaTest/Average/MaxReturn -89.3011 MetaTest/Average/MinReturn -95.3688 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.70241 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.0988 MetaTest/__unnamed_task__/AverageReturn -93.0988 MetaTest/__unnamed_task__/Iteration 262 MetaTest/__unnamed_task__/MaxReturn -89.3011 MetaTest/__unnamed_task__/MinReturn -95.3688 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.70241 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 435800 ------------------------------------------------- ------------ 2025-04-03 01:13:50 | [pearl_trainer] epoch #263 | Training... 2025-04-03 01:15:20 | [pearl_trainer] epoch #263 | Evaluating... 2025-04-03 01:15:20 | [pearl_trainer] epoch #263 | Sampling for adapation and meta-testing... 2025-04-03 01:16:07 | [pearl_trainer] epoch #263 | Finished meta-testing... 2025-04-03 01:16:07 | [pearl_trainer] epoch #263 | Saving snapshot... 2025-04-03 01:16:09 | [pearl_trainer] epoch #263 | Saved 2025-04-03 01:16:09 | [pearl_trainer] epoch #263 | Time 42444.74 s 2025-04-03 01:16:09 | [pearl_trainer] epoch #263 | EpochTime 160.74 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -99.489 MetaTest/Average/AverageReturn -99.489 MetaTest/Average/Iteration 263 MetaTest/Average/MaxReturn -96.5741 MetaTest/Average/MinReturn -103.029 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.67211 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -99.489 MetaTest/__unnamed_task__/AverageReturn -99.489 MetaTest/__unnamed_task__/Iteration 263 MetaTest/__unnamed_task__/MaxReturn -96.5741 MetaTest/__unnamed_task__/MinReturn -103.029 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.67211 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 437400 ------------------------------------------------- ------------ 2025-04-03 01:16:30 | [pearl_trainer] epoch #264 | Training... 2025-04-03 01:17:51 | [pearl_trainer] epoch #264 | Evaluating... 2025-04-03 01:17:51 | [pearl_trainer] epoch #264 | Sampling for adapation and meta-testing... 2025-04-03 01:18:51 | [pearl_trainer] epoch #264 | Finished meta-testing... 2025-04-03 01:18:51 | [pearl_trainer] epoch #264 | Saving snapshot... 2025-04-03 01:18:52 | [pearl_trainer] epoch #264 | Saved 2025-04-03 01:18:52 | [pearl_trainer] epoch #264 | Time 42608.46 s 2025-04-03 01:18:52 | [pearl_trainer] epoch #264 | EpochTime 163.71 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.2332 MetaTest/Average/AverageReturn -97.2332 MetaTest/Average/Iteration 264 MetaTest/Average/MaxReturn -94.5343 MetaTest/Average/MinReturn -101.193 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.86095 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.2332 MetaTest/__unnamed_task__/AverageReturn -97.2332 MetaTest/__unnamed_task__/Iteration 264 MetaTest/__unnamed_task__/MaxReturn -94.5343 MetaTest/__unnamed_task__/MinReturn -101.193 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.86095 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 439000 ------------------------------------------------- ------------ 2025-04-03 01:19:20 | [pearl_trainer] epoch #265 | Training... 2025-04-03 01:20:47 | [pearl_trainer] epoch #265 | Evaluating... 2025-04-03 01:20:47 | [pearl_trainer] epoch #265 | Sampling for adapation and meta-testing... 2025-04-03 01:21:31 | [pearl_trainer] epoch #265 | Finished meta-testing... 2025-04-03 01:21:31 | [pearl_trainer] epoch #265 | Saving snapshot... 2025-04-03 01:21:33 | [pearl_trainer] epoch #265 | Saved 2025-04-03 01:21:33 | [pearl_trainer] epoch #265 | Time 42768.90 s 2025-04-03 01:21:33 | [pearl_trainer] epoch #265 | EpochTime 160.44 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.0791 MetaTest/Average/AverageReturn -97.0791 MetaTest/Average/Iteration 265 MetaTest/Average/MaxReturn -83.7031 MetaTest/Average/MinReturn -107.05 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.83078 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.0791 MetaTest/__unnamed_task__/AverageReturn -97.0791 MetaTest/__unnamed_task__/Iteration 265 MetaTest/__unnamed_task__/MaxReturn -83.7031 MetaTest/__unnamed_task__/MinReturn -107.05 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.83078 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 440600 ------------------------------------------------- ------------ 2025-04-03 01:21:55 | [pearl_trainer] epoch #266 | Training... 2025-04-03 01:23:32 | [pearl_trainer] epoch #266 | Evaluating... 2025-04-03 01:23:32 | [pearl_trainer] epoch #266 | Sampling for adapation and meta-testing... 2025-04-03 01:24:18 | [pearl_trainer] epoch #266 | Finished meta-testing... 2025-04-03 01:24:18 | [pearl_trainer] epoch #266 | Saving snapshot... 2025-04-03 01:24:19 | [pearl_trainer] epoch #266 | Saved 2025-04-03 01:24:19 | [pearl_trainer] epoch #266 | Time 42935.04 s 2025-04-03 01:24:19 | [pearl_trainer] epoch #266 | EpochTime 166.14 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -96.1198 MetaTest/Average/AverageReturn -96.1198 MetaTest/Average/Iteration 266 MetaTest/Average/MaxReturn -89.4645 MetaTest/Average/MinReturn -103.108 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.57484 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.1198 MetaTest/__unnamed_task__/AverageReturn -96.1198 MetaTest/__unnamed_task__/Iteration 266 MetaTest/__unnamed_task__/MaxReturn -89.4645 MetaTest/__unnamed_task__/MinReturn -103.108 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.57484 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 442200 ------------------------------------------------- ------------ 2025-04-03 01:24:41 | [pearl_trainer] epoch #267 | Training... 2025-04-03 01:26:11 | [pearl_trainer] epoch #267 | Evaluating... 2025-04-03 01:26:11 | [pearl_trainer] epoch #267 | Sampling for adapation and meta-testing... 2025-04-03 01:27:01 | [pearl_trainer] epoch #267 | Finished meta-testing... 2025-04-03 01:27:01 | [pearl_trainer] epoch #267 | Saving snapshot... 2025-04-03 01:27:02 | [pearl_trainer] epoch #267 | Saved 2025-04-03 01:27:02 | [pearl_trainer] epoch #267 | Time 43098.09 s 2025-04-03 01:27:02 | [pearl_trainer] epoch #267 | EpochTime 163.04 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -88.2482 MetaTest/Average/AverageReturn -88.2482 MetaTest/Average/Iteration 267 MetaTest/Average/MaxReturn -86.6045 MetaTest/Average/MinReturn -90.4973 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.6459 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.2482 MetaTest/__unnamed_task__/AverageReturn -88.2482 MetaTest/__unnamed_task__/Iteration 267 MetaTest/__unnamed_task__/MaxReturn -86.6045 MetaTest/__unnamed_task__/MinReturn -90.4973 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.6459 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 443800 ------------------------------------------------- ----------- 2025-04-03 01:27:24 | [pearl_trainer] epoch #268 | Training... 2025-04-03 01:28:52 | [pearl_trainer] epoch #268 | Evaluating... 2025-04-03 01:28:52 | [pearl_trainer] epoch #268 | Sampling for adapation and meta-testing... 2025-04-03 01:29:36 | [pearl_trainer] epoch #268 | Finished meta-testing... 2025-04-03 01:29:36 | [pearl_trainer] epoch #268 | Saving snapshot... 2025-04-03 01:29:38 | [pearl_trainer] epoch #268 | Saved 2025-04-03 01:29:38 | [pearl_trainer] epoch #268 | Time 43253.99 s 2025-04-03 01:29:38 | [pearl_trainer] epoch #268 | EpochTime 155.91 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -92.7193 MetaTest/Average/AverageReturn -92.7193 MetaTest/Average/Iteration 268 MetaTest/Average/MaxReturn -83.4419 MetaTest/Average/MinReturn -110.067 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.2762 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.7193 MetaTest/__unnamed_task__/AverageReturn -92.7193 MetaTest/__unnamed_task__/Iteration 268 MetaTest/__unnamed_task__/MaxReturn -83.4419 MetaTest/__unnamed_task__/MinReturn -110.067 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.2762 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 445400 ------------------------------------------------- ----------- 2025-04-03 01:30:01 | [pearl_trainer] epoch #269 | Training... 2025-04-03 01:31:30 | [pearl_trainer] epoch #269 | Evaluating... 2025-04-03 01:31:30 | [pearl_trainer] epoch #269 | Sampling for adapation and meta-testing... 2025-04-03 01:32:20 | [pearl_trainer] epoch #269 | Finished meta-testing... 2025-04-03 01:32:20 | [pearl_trainer] epoch #269 | Saving snapshot... 2025-04-03 01:32:21 | [pearl_trainer] epoch #269 | Saved 2025-04-03 01:32:21 | [pearl_trainer] epoch #269 | Time 43417.42 s 2025-04-03 01:32:21 | [pearl_trainer] epoch #269 | EpochTime 163.42 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -114.88 MetaTest/Average/AverageReturn -114.88 MetaTest/Average/Iteration 269 MetaTest/Average/MaxReturn -98.5209 MetaTest/Average/MinReturn -143.768 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 20.4867 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -114.88 MetaTest/__unnamed_task__/AverageReturn -114.88 MetaTest/__unnamed_task__/Iteration 269 MetaTest/__unnamed_task__/MaxReturn -98.5209 MetaTest/__unnamed_task__/MinReturn -143.768 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 20.4867 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 447000 ------------------------------------------------- ----------- 2025-04-03 01:32:43 | [pearl_trainer] epoch #270 | Training... 2025-04-03 01:34:06 | [pearl_trainer] epoch #270 | Evaluating... 2025-04-03 01:34:06 | [pearl_trainer] epoch #270 | Sampling for adapation and meta-testing... 2025-04-03 01:34:56 | [pearl_trainer] epoch #270 | Finished meta-testing... 2025-04-03 01:34:56 | [pearl_trainer] epoch #270 | Saving snapshot... 2025-04-03 01:34:58 | [pearl_trainer] epoch #270 | Saved 2025-04-03 01:34:58 | [pearl_trainer] epoch #270 | Time 43573.73 s 2025-04-03 01:34:58 | [pearl_trainer] epoch #270 | EpochTime 156.31 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -140.905 MetaTest/Average/AverageReturn -140.905 MetaTest/Average/Iteration 270 MetaTest/Average/MaxReturn -138.281 MetaTest/Average/MinReturn -143.772 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.24839 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -140.905 MetaTest/__unnamed_task__/AverageReturn -140.905 MetaTest/__unnamed_task__/Iteration 270 MetaTest/__unnamed_task__/MaxReturn -138.281 MetaTest/__unnamed_task__/MinReturn -143.772 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.24839 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 448600 ------------------------------------------------- ------------ 2025-04-03 01:35:20 | [pearl_trainer] epoch #271 | Training... 2025-04-03 01:36:49 | [pearl_trainer] epoch #271 | Evaluating... 2025-04-03 01:36:49 | [pearl_trainer] epoch #271 | Sampling for adapation and meta-testing... 2025-04-03 01:37:34 | [pearl_trainer] epoch #271 | Finished meta-testing... 2025-04-03 01:37:34 | [pearl_trainer] epoch #271 | Saving snapshot... 2025-04-03 01:37:35 | [pearl_trainer] epoch #271 | Saved 2025-04-03 01:37:35 | [pearl_trainer] epoch #271 | Time 43731.40 s 2025-04-03 01:37:35 | [pearl_trainer] epoch #271 | EpochTime 157.67 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.2145 MetaTest/Average/AverageReturn -90.2145 MetaTest/Average/Iteration 271 MetaTest/Average/MaxReturn -82.278 MetaTest/Average/MinReturn -95.3602 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.69372 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.2145 MetaTest/__unnamed_task__/AverageReturn -90.2145 MetaTest/__unnamed_task__/Iteration 271 MetaTest/__unnamed_task__/MaxReturn -82.278 MetaTest/__unnamed_task__/MinReturn -95.3602 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.69372 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 450200 ------------------------------------------------- ------------ 2025-04-03 01:37:58 | [pearl_trainer] epoch #272 | Training... 2025-04-03 01:39:34 | [pearl_trainer] epoch #272 | Evaluating... 2025-04-03 01:39:34 | [pearl_trainer] epoch #272 | Sampling for adapation and meta-testing... 2025-04-03 01:40:19 | [pearl_trainer] epoch #272 | Finished meta-testing... 2025-04-03 01:40:19 | [pearl_trainer] epoch #272 | Saving snapshot... 2025-04-03 01:40:20 | [pearl_trainer] epoch #272 | Saved 2025-04-03 01:40:20 | [pearl_trainer] epoch #272 | Time 43896.19 s 2025-04-03 01:40:20 | [pearl_trainer] epoch #272 | EpochTime 164.79 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.5913 MetaTest/Average/AverageReturn -97.5913 MetaTest/Average/Iteration 272 MetaTest/Average/MaxReturn -90.6234 MetaTest/Average/MinReturn -109.186 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.25408 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.5913 MetaTest/__unnamed_task__/AverageReturn -97.5913 MetaTest/__unnamed_task__/Iteration 272 MetaTest/__unnamed_task__/MaxReturn -90.6234 MetaTest/__unnamed_task__/MinReturn -109.186 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.25408 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 451800 ------------------------------------------------- ------------ 2025-04-03 01:40:42 | [pearl_trainer] epoch #273 | Training... 2025-04-03 01:42:15 | [pearl_trainer] epoch #273 | Evaluating... 2025-04-03 01:42:15 | [pearl_trainer] epoch #273 | Sampling for adapation and meta-testing... 2025-04-03 01:43:06 | [pearl_trainer] epoch #273 | Finished meta-testing... 2025-04-03 01:43:06 | [pearl_trainer] epoch #273 | Saving snapshot... 2025-04-03 01:43:08 | [pearl_trainer] epoch #273 | Saved 2025-04-03 01:43:08 | [pearl_trainer] epoch #273 | Time 44063.98 s 2025-04-03 01:43:08 | [pearl_trainer] epoch #273 | EpochTime 167.78 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -79.8825 MetaTest/Average/AverageReturn -79.8825 MetaTest/Average/Iteration 273 MetaTest/Average/MaxReturn -74.2566 MetaTest/Average/MinReturn -89.7905 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.02746 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -79.8825 MetaTest/__unnamed_task__/AverageReturn -79.8825 MetaTest/__unnamed_task__/Iteration 273 MetaTest/__unnamed_task__/MaxReturn -74.2566 MetaTest/__unnamed_task__/MinReturn -89.7905 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.02746 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 453400 ------------------------------------------------- ------------ 2025-04-03 01:43:30 | [pearl_trainer] epoch #274 | Training... 2025-04-03 01:44:58 | [pearl_trainer] epoch #274 | Evaluating... 2025-04-03 01:44:58 | [pearl_trainer] epoch #274 | Sampling for adapation and meta-testing... 2025-04-03 01:45:44 | [pearl_trainer] epoch #274 | Finished meta-testing... 2025-04-03 01:45:44 | [pearl_trainer] epoch #274 | Saving snapshot... 2025-04-03 01:45:45 | [pearl_trainer] epoch #274 | Saved 2025-04-03 01:45:45 | [pearl_trainer] epoch #274 | Time 44221.07 s 2025-04-03 01:45:45 | [pearl_trainer] epoch #274 | EpochTime 157.09 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -89.64 MetaTest/Average/AverageReturn -89.64 MetaTest/Average/Iteration 274 MetaTest/Average/MaxReturn -83.4921 MetaTest/Average/MinReturn -96.3768 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.27663 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -89.64 MetaTest/__unnamed_task__/AverageReturn -89.64 MetaTest/__unnamed_task__/Iteration 274 MetaTest/__unnamed_task__/MaxReturn -83.4921 MetaTest/__unnamed_task__/MinReturn -96.3768 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.27663 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 455000 ------------------------------------------------- ------------ 2025-04-03 01:46:08 | [pearl_trainer] epoch #275 | Training... 2025-04-03 01:47:41 | [pearl_trainer] epoch #275 | Evaluating... 2025-04-03 01:47:41 | [pearl_trainer] epoch #275 | Sampling for adapation and meta-testing... 2025-04-03 01:48:26 | [pearl_trainer] epoch #275 | Finished meta-testing... 2025-04-03 01:48:26 | [pearl_trainer] epoch #275 | Saving snapshot... 2025-04-03 01:48:27 | [pearl_trainer] epoch #275 | Saved 2025-04-03 01:48:27 | [pearl_trainer] epoch #275 | Time 44383.52 s 2025-04-03 01:48:27 | [pearl_trainer] epoch #275 | EpochTime 162.45 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -104.55 MetaTest/Average/AverageReturn -104.55 MetaTest/Average/Iteration 275 MetaTest/Average/MaxReturn -89.3739 MetaTest/Average/MinReturn -116.118 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.2126 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -104.55 MetaTest/__unnamed_task__/AverageReturn -104.55 MetaTest/__unnamed_task__/Iteration 275 MetaTest/__unnamed_task__/MaxReturn -89.3739 MetaTest/__unnamed_task__/MinReturn -116.118 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.2126 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 456600 ------------------------------------------------- ----------- 2025-04-03 01:48:49 | [pearl_trainer] epoch #276 | Training... 2025-04-03 01:50:34 | [pearl_trainer] epoch #276 | Evaluating... 2025-04-03 01:50:34 | [pearl_trainer] epoch #276 | Sampling for adapation and meta-testing... 2025-04-03 01:51:29 | [pearl_trainer] epoch #276 | Finished meta-testing... 2025-04-03 01:51:29 | [pearl_trainer] epoch #276 | Saving snapshot... 2025-04-03 01:51:31 | [pearl_trainer] epoch #276 | Saved 2025-04-03 01:51:31 | [pearl_trainer] epoch #276 | Time 44566.79 s 2025-04-03 01:51:31 | [pearl_trainer] epoch #276 | EpochTime 183.27 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -88.1294 MetaTest/Average/AverageReturn -88.1294 MetaTest/Average/Iteration 276 MetaTest/Average/MaxReturn -83.9332 MetaTest/Average/MinReturn -94.4455 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.54591 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.1294 MetaTest/__unnamed_task__/AverageReturn -88.1294 MetaTest/__unnamed_task__/Iteration 276 MetaTest/__unnamed_task__/MaxReturn -83.9332 MetaTest/__unnamed_task__/MinReturn -94.4455 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.54591 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 458200 ------------------------------------------------- ------------ 2025-04-03 01:51:53 | [pearl_trainer] epoch #277 | Training... 2025-04-03 01:53:24 | [pearl_trainer] epoch #277 | Evaluating... 2025-04-03 01:53:24 | [pearl_trainer] epoch #277 | Sampling for adapation and meta-testing... 2025-04-03 01:54:11 | [pearl_trainer] epoch #277 | Finished meta-testing... 2025-04-03 01:54:11 | [pearl_trainer] epoch #277 | Saving snapshot... 2025-04-03 01:54:12 | [pearl_trainer] epoch #277 | Saved 2025-04-03 01:54:12 | [pearl_trainer] epoch #277 | Time 44728.08 s 2025-04-03 01:54:12 | [pearl_trainer] epoch #277 | EpochTime 161.29 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -88.8795 MetaTest/Average/AverageReturn -88.8795 MetaTest/Average/Iteration 277 MetaTest/Average/MaxReturn -85.5339 MetaTest/Average/MinReturn -90.722 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.3698 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.8795 MetaTest/__unnamed_task__/AverageReturn -88.8795 MetaTest/__unnamed_task__/Iteration 277 MetaTest/__unnamed_task__/MaxReturn -85.5339 MetaTest/__unnamed_task__/MinReturn -90.722 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.3698 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 459800 ------------------------------------------------- ----------- 2025-04-03 01:54:35 | [pearl_trainer] epoch #278 | Training... 2025-04-03 01:56:07 | [pearl_trainer] epoch #278 | Evaluating... 2025-04-03 01:56:07 | [pearl_trainer] epoch #278 | Sampling for adapation and meta-testing... 2025-04-03 01:56:52 | [pearl_trainer] epoch #278 | Finished meta-testing... 2025-04-03 01:56:52 | [pearl_trainer] epoch #278 | Saving snapshot... 2025-04-03 01:56:53 | [pearl_trainer] epoch #278 | Saved 2025-04-03 01:56:53 | [pearl_trainer] epoch #278 | Time 44889.22 s 2025-04-03 01:56:53 | [pearl_trainer] epoch #278 | EpochTime 161.14 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -94.6377 MetaTest/Average/AverageReturn -94.6377 MetaTest/Average/Iteration 278 MetaTest/Average/MaxReturn -86.2898 MetaTest/Average/MinReturn -103.253 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.92788 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.6377 MetaTest/__unnamed_task__/AverageReturn -94.6377 MetaTest/__unnamed_task__/Iteration 278 MetaTest/__unnamed_task__/MaxReturn -86.2898 MetaTest/__unnamed_task__/MinReturn -103.253 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.92788 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 461400 ------------------------------------------------- ------------ 2025-04-03 01:57:15 | [pearl_trainer] epoch #279 | Training... 2025-04-03 01:58:46 | [pearl_trainer] epoch #279 | Evaluating... 2025-04-03 01:58:46 | [pearl_trainer] epoch #279 | Sampling for adapation and meta-testing... 2025-04-03 01:59:37 | [pearl_trainer] epoch #279 | Finished meta-testing... 2025-04-03 01:59:37 | [pearl_trainer] epoch #279 | Saving snapshot... 2025-04-03 01:59:39 | [pearl_trainer] epoch #279 | Saved 2025-04-03 01:59:39 | [pearl_trainer] epoch #279 | Time 45054.83 s 2025-04-03 01:59:39 | [pearl_trainer] epoch #279 | EpochTime 165.61 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -101.068 MetaTest/Average/AverageReturn -101.068 MetaTest/Average/Iteration 279 MetaTest/Average/MaxReturn -85.9944 MetaTest/Average/MinReturn -120.203 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.2579 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.068 MetaTest/__unnamed_task__/AverageReturn -101.068 MetaTest/__unnamed_task__/Iteration 279 MetaTest/__unnamed_task__/MaxReturn -85.9944 MetaTest/__unnamed_task__/MinReturn -120.203 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.2579 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 463000 ------------------------------------------------- ----------- 2025-04-03 02:00:00 | [pearl_trainer] epoch #280 | Training... 2025-04-03 02:01:25 | [pearl_trainer] epoch #280 | Evaluating... 2025-04-03 02:01:25 | [pearl_trainer] epoch #280 | Sampling for adapation and meta-testing... 2025-04-03 02:02:13 | [pearl_trainer] epoch #280 | Finished meta-testing... 2025-04-03 02:02:13 | [pearl_trainer] epoch #280 | Saving snapshot... 2025-04-03 02:02:14 | [pearl_trainer] epoch #280 | Saved 2025-04-03 02:02:14 | [pearl_trainer] epoch #280 | Time 45209.74 s 2025-04-03 02:02:14 | [pearl_trainer] epoch #280 | EpochTime 154.91 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -101.401 MetaTest/Average/AverageReturn -101.401 MetaTest/Average/Iteration 280 MetaTest/Average/MaxReturn -92.5267 MetaTest/Average/MinReturn -112.242 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.16806 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.401 MetaTest/__unnamed_task__/AverageReturn -101.401 MetaTest/__unnamed_task__/Iteration 280 MetaTest/__unnamed_task__/MaxReturn -92.5267 MetaTest/__unnamed_task__/MinReturn -112.242 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.16806 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 464600 ------------------------------------------------- ------------ 2025-04-03 02:02:37 | [pearl_trainer] epoch #281 | Training... 2025-04-03 02:04:11 | [pearl_trainer] epoch #281 | Evaluating... 2025-04-03 02:04:11 | [pearl_trainer] epoch #281 | Sampling for adapation and meta-testing... 2025-04-03 02:04:56 | [pearl_trainer] epoch #281 | Finished meta-testing... 2025-04-03 02:04:56 | [pearl_trainer] epoch #281 | Saving snapshot... 2025-04-03 02:04:58 | [pearl_trainer] epoch #281 | Saved 2025-04-03 02:04:58 | [pearl_trainer] epoch #281 | Time 45373.90 s 2025-04-03 02:04:58 | [pearl_trainer] epoch #281 | EpochTime 164.15 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -101.373 MetaTest/Average/AverageReturn -101.373 MetaTest/Average/Iteration 281 MetaTest/Average/MaxReturn -95.8556 MetaTest/Average/MinReturn -105.099 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.98039 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.373 MetaTest/__unnamed_task__/AverageReturn -101.373 MetaTest/__unnamed_task__/Iteration 281 MetaTest/__unnamed_task__/MaxReturn -95.8556 MetaTest/__unnamed_task__/MinReturn -105.099 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.98039 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 466200 ------------------------------------------------- ------------ 2025-04-03 02:05:22 | [pearl_trainer] epoch #282 | Training... 2025-04-03 02:06:48 | [pearl_trainer] epoch #282 | Evaluating... 2025-04-03 02:06:48 | [pearl_trainer] epoch #282 | Sampling for adapation and meta-testing... 2025-04-03 02:07:36 | [pearl_trainer] epoch #282 | Finished meta-testing... 2025-04-03 02:07:36 | [pearl_trainer] epoch #282 | Saving snapshot... 2025-04-03 02:07:37 | [pearl_trainer] epoch #282 | Saved 2025-04-03 02:07:37 | [pearl_trainer] epoch #282 | Time 45533.60 s 2025-04-03 02:07:37 | [pearl_trainer] epoch #282 | EpochTime 159.70 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -80.7852 MetaTest/Average/AverageReturn -80.7852 MetaTest/Average/Iteration 282 MetaTest/Average/MaxReturn -79.206 MetaTest/Average/MinReturn -82.1111 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.19948 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -80.7852 MetaTest/__unnamed_task__/AverageReturn -80.7852 MetaTest/__unnamed_task__/Iteration 282 MetaTest/__unnamed_task__/MaxReturn -79.206 MetaTest/__unnamed_task__/MinReturn -82.1111 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.19948 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 467800 ------------------------------------------------- ------------ 2025-04-03 02:07:59 | [pearl_trainer] epoch #283 | Training... 2025-04-03 02:09:25 | [pearl_trainer] epoch #283 | Evaluating... 2025-04-03 02:09:25 | [pearl_trainer] epoch #283 | Sampling for adapation and meta-testing... 2025-04-03 02:10:13 | [pearl_trainer] epoch #283 | Finished meta-testing... 2025-04-03 02:10:13 | [pearl_trainer] epoch #283 | Saving snapshot... 2025-04-03 02:10:14 | [pearl_trainer] epoch #283 | Saved 2025-04-03 02:10:14 | [pearl_trainer] epoch #283 | Time 45690.24 s 2025-04-03 02:10:14 | [pearl_trainer] epoch #283 | EpochTime 156.63 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -97.6304 MetaTest/Average/AverageReturn -97.6304 MetaTest/Average/Iteration 283 MetaTest/Average/MaxReturn -76.9739 MetaTest/Average/MinReturn -126.439 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 21.0004 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.6304 MetaTest/__unnamed_task__/AverageReturn -97.6304 MetaTest/__unnamed_task__/Iteration 283 MetaTest/__unnamed_task__/MaxReturn -76.9739 MetaTest/__unnamed_task__/MinReturn -126.439 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 21.0004 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 469400 ------------------------------------------------- ----------- 2025-04-03 02:10:38 | [pearl_trainer] epoch #284 | Training... 2025-04-03 02:12:06 | [pearl_trainer] epoch #284 | Evaluating... 2025-04-03 02:12:06 | [pearl_trainer] epoch #284 | Sampling for adapation and meta-testing... 2025-04-03 02:12:56 | [pearl_trainer] epoch #284 | Finished meta-testing... 2025-04-03 02:12:56 | [pearl_trainer] epoch #284 | Saving snapshot... 2025-04-03 02:12:57 | [pearl_trainer] epoch #284 | Saved 2025-04-03 02:12:57 | [pearl_trainer] epoch #284 | Time 45853.67 s 2025-04-03 02:12:57 | [pearl_trainer] epoch #284 | EpochTime 163.43 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -88.0392 MetaTest/Average/AverageReturn -88.0392 MetaTest/Average/Iteration 284 MetaTest/Average/MaxReturn -81.0308 MetaTest/Average/MinReturn -94.3714 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.46723 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.0392 MetaTest/__unnamed_task__/AverageReturn -88.0392 MetaTest/__unnamed_task__/Iteration 284 MetaTest/__unnamed_task__/MaxReturn -81.0308 MetaTest/__unnamed_task__/MinReturn -94.3714 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.46723 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 471000 ------------------------------------------------- ------------ 2025-04-03 02:13:19 | [pearl_trainer] epoch #285 | Training... 2025-04-03 02:14:46 | [pearl_trainer] epoch #285 | Evaluating... 2025-04-03 02:14:46 | [pearl_trainer] epoch #285 | Sampling for adapation and meta-testing... 2025-04-03 02:15:35 | [pearl_trainer] epoch #285 | Finished meta-testing... 2025-04-03 02:15:35 | [pearl_trainer] epoch #285 | Saving snapshot... 2025-04-03 02:15:36 | [pearl_trainer] epoch #285 | Saved 2025-04-03 02:15:36 | [pearl_trainer] epoch #285 | Time 46012.19 s 2025-04-03 02:15:36 | [pearl_trainer] epoch #285 | EpochTime 158.52 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.7666 MetaTest/Average/AverageReturn -93.7666 MetaTest/Average/Iteration 285 MetaTest/Average/MaxReturn -89.0835 MetaTest/Average/MinReturn -96.9198 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.37712 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.7666 MetaTest/__unnamed_task__/AverageReturn -93.7666 MetaTest/__unnamed_task__/Iteration 285 MetaTest/__unnamed_task__/MaxReturn -89.0835 MetaTest/__unnamed_task__/MinReturn -96.9198 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.37712 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 472600 ------------------------------------------------- ------------ 2025-04-03 02:16:00 | [pearl_trainer] epoch #286 | Training... 2025-04-03 02:17:25 | [pearl_trainer] epoch #286 | Evaluating... 2025-04-03 02:17:25 | [pearl_trainer] epoch #286 | Sampling for adapation and meta-testing... 2025-04-03 02:18:12 | [pearl_trainer] epoch #286 | Finished meta-testing... 2025-04-03 02:18:12 | [pearl_trainer] epoch #286 | Saving snapshot... 2025-04-03 02:18:14 | [pearl_trainer] epoch #286 | Saved 2025-04-03 02:18:14 | [pearl_trainer] epoch #286 | Time 46169.89 s 2025-04-03 02:18:14 | [pearl_trainer] epoch #286 | EpochTime 157.70 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.6781 MetaTest/Average/AverageReturn -90.6781 MetaTest/Average/Iteration 286 MetaTest/Average/MaxReturn -79.0822 MetaTest/Average/MinReturn -96.5595 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.19983 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.6781 MetaTest/__unnamed_task__/AverageReturn -90.6781 MetaTest/__unnamed_task__/Iteration 286 MetaTest/__unnamed_task__/MaxReturn -79.0822 MetaTest/__unnamed_task__/MinReturn -96.5595 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.19983 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 474200 ------------------------------------------------- ------------ 2025-04-03 02:18:37 | [pearl_trainer] epoch #287 | Training... 2025-04-03 02:20:22 | [pearl_trainer] epoch #287 | Evaluating... 2025-04-03 02:20:22 | [pearl_trainer] epoch #287 | Sampling for adapation and meta-testing... 2025-04-03 02:21:07 | [pearl_trainer] epoch #287 | Finished meta-testing... 2025-04-03 02:21:07 | [pearl_trainer] epoch #287 | Saving snapshot... 2025-04-03 02:21:08 | [pearl_trainer] epoch #287 | Saved 2025-04-03 02:21:08 | [pearl_trainer] epoch #287 | Time 46344.20 s 2025-04-03 02:21:08 | [pearl_trainer] epoch #287 | EpochTime 174.31 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -100.043 MetaTest/Average/AverageReturn -100.043 MetaTest/Average/Iteration 287 MetaTest/Average/MaxReturn -87.1734 MetaTest/Average/MinReturn -118.03 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.1066 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -100.043 MetaTest/__unnamed_task__/AverageReturn -100.043 MetaTest/__unnamed_task__/Iteration 287 MetaTest/__unnamed_task__/MaxReturn -87.1734 MetaTest/__unnamed_task__/MinReturn -118.03 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.1066 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 475800 ------------------------------------------------- ----------- 2025-04-03 02:21:29 | [pearl_trainer] epoch #288 | Training... 2025-04-03 02:22:54 | [pearl_trainer] epoch #288 | Evaluating... 2025-04-03 02:22:54 | [pearl_trainer] epoch #288 | Sampling for adapation and meta-testing... 2025-04-03 02:23:43 | [pearl_trainer] epoch #288 | Finished meta-testing... 2025-04-03 02:23:43 | [pearl_trainer] epoch #288 | Saving snapshot... 2025-04-03 02:23:44 | [pearl_trainer] epoch #288 | Saved 2025-04-03 02:23:44 | [pearl_trainer] epoch #288 | Time 46500.67 s 2025-04-03 02:23:44 | [pearl_trainer] epoch #288 | EpochTime 156.46 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.835 MetaTest/Average/AverageReturn -90.835 MetaTest/Average/Iteration 288 MetaTest/Average/MaxReturn -81.6573 MetaTest/Average/MinReturn -95.713 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.49391 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.835 MetaTest/__unnamed_task__/AverageReturn -90.835 MetaTest/__unnamed_task__/Iteration 288 MetaTest/__unnamed_task__/MaxReturn -81.6573 MetaTest/__unnamed_task__/MinReturn -95.713 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.49391 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 477400 ------------------------------------------------- ------------ 2025-04-03 02:24:08 | [pearl_trainer] epoch #289 | Training... 2025-04-03 02:25:28 | [pearl_trainer] epoch #289 | Evaluating... 2025-04-03 02:25:28 | [pearl_trainer] epoch #289 | Sampling for adapation and meta-testing... 2025-04-03 02:26:16 | [pearl_trainer] epoch #289 | Finished meta-testing... 2025-04-03 02:26:16 | [pearl_trainer] epoch #289 | Saving snapshot... 2025-04-03 02:26:17 | [pearl_trainer] epoch #289 | Saved 2025-04-03 02:26:17 | [pearl_trainer] epoch #289 | Time 46653.12 s 2025-04-03 02:26:17 | [pearl_trainer] epoch #289 | EpochTime 152.45 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -88.8167 MetaTest/Average/AverageReturn -88.8167 MetaTest/Average/Iteration 289 MetaTest/Average/MaxReturn -74.7087 MetaTest/Average/MinReturn -102.224 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.2439 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.8167 MetaTest/__unnamed_task__/AverageReturn -88.8167 MetaTest/__unnamed_task__/Iteration 289 MetaTest/__unnamed_task__/MaxReturn -74.7087 MetaTest/__unnamed_task__/MinReturn -102.224 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.2439 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 479000 ------------------------------------------------- ----------- 2025-04-03 02:26:40 | [pearl_trainer] epoch #290 | Training... 2025-04-03 02:28:07 | [pearl_trainer] epoch #290 | Evaluating... 2025-04-03 02:28:07 | [pearl_trainer] epoch #290 | Sampling for adapation and meta-testing... 2025-04-03 02:28:55 | [pearl_trainer] epoch #290 | Finished meta-testing... 2025-04-03 02:28:55 | [pearl_trainer] epoch #290 | Saving snapshot... 2025-04-03 02:28:56 | [pearl_trainer] epoch #290 | Saved 2025-04-03 02:28:56 | [pearl_trainer] epoch #290 | Time 46812.23 s 2025-04-03 02:28:56 | [pearl_trainer] epoch #290 | EpochTime 159.11 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -113.227 MetaTest/Average/AverageReturn -113.227 MetaTest/Average/Iteration 290 MetaTest/Average/MaxReturn -91.0258 MetaTest/Average/MinReturn -133.032 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 17.2325 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -113.227 MetaTest/__unnamed_task__/AverageReturn -113.227 MetaTest/__unnamed_task__/Iteration 290 MetaTest/__unnamed_task__/MaxReturn -91.0258 MetaTest/__unnamed_task__/MinReturn -133.032 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 17.2325 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 480600 ------------------------------------------------- ----------- 2025-04-03 02:29:18 | [pearl_trainer] epoch #291 | Training... 2025-04-03 02:30:48 | [pearl_trainer] epoch #291 | Evaluating... 2025-04-03 02:30:48 | [pearl_trainer] epoch #291 | Sampling for adapation and meta-testing... 2025-04-03 02:31:35 | [pearl_trainer] epoch #291 | Finished meta-testing... 2025-04-03 02:31:35 | [pearl_trainer] epoch #291 | Saving snapshot... 2025-04-03 02:31:36 | [pearl_trainer] epoch #291 | Saved 2025-04-03 02:31:36 | [pearl_trainer] epoch #291 | Time 46972.33 s 2025-04-03 02:31:36 | [pearl_trainer] epoch #291 | EpochTime 160.10 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.4343 MetaTest/Average/AverageReturn -90.4343 MetaTest/Average/Iteration 291 MetaTest/Average/MaxReturn -83.4086 MetaTest/Average/MinReturn -97.0629 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.58141 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.4343 MetaTest/__unnamed_task__/AverageReturn -90.4343 MetaTest/__unnamed_task__/Iteration 291 MetaTest/__unnamed_task__/MaxReturn -83.4086 MetaTest/__unnamed_task__/MinReturn -97.0629 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.58141 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 482200 ------------------------------------------------- ------------ 2025-04-03 02:31:58 | [pearl_trainer] epoch #292 | Training... 2025-04-03 02:33:32 | [pearl_trainer] epoch #292 | Evaluating... 2025-04-03 02:33:32 | [pearl_trainer] epoch #292 | Sampling for adapation and meta-testing... 2025-04-03 02:34:22 | [pearl_trainer] epoch #292 | Finished meta-testing... 2025-04-03 02:34:22 | [pearl_trainer] epoch #292 | Saving snapshot... 2025-04-03 02:34:23 | [pearl_trainer] epoch #292 | Saved 2025-04-03 02:34:23 | [pearl_trainer] epoch #292 | Time 47139.27 s 2025-04-03 02:34:23 | [pearl_trainer] epoch #292 | EpochTime 166.94 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.5942 MetaTest/Average/AverageReturn -90.5942 MetaTest/Average/Iteration 292 MetaTest/Average/MaxReturn -80.3756 MetaTest/Average/MinReturn -103.763 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.77295 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.5942 MetaTest/__unnamed_task__/AverageReturn -90.5942 MetaTest/__unnamed_task__/Iteration 292 MetaTest/__unnamed_task__/MaxReturn -80.3756 MetaTest/__unnamed_task__/MinReturn -103.763 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.77295 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 483800 ------------------------------------------------- ------------ 2025-04-03 02:34:46 | [pearl_trainer] epoch #293 | Training... 2025-04-03 02:36:09 | [pearl_trainer] epoch #293 | Evaluating... 2025-04-03 02:36:09 | [pearl_trainer] epoch #293 | Sampling for adapation and meta-testing... 2025-04-03 02:36:59 | [pearl_trainer] epoch #293 | Finished meta-testing... 2025-04-03 02:36:59 | [pearl_trainer] epoch #293 | Saving snapshot... 2025-04-03 02:37:00 | [pearl_trainer] epoch #293 | Saved 2025-04-03 02:37:00 | [pearl_trainer] epoch #293 | Time 47296.49 s 2025-04-03 02:37:00 | [pearl_trainer] epoch #293 | EpochTime 157.21 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.7635 MetaTest/Average/AverageReturn -97.7635 MetaTest/Average/Iteration 293 MetaTest/Average/MaxReturn -89.7258 MetaTest/Average/MinReturn -104.971 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.25146 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.7635 MetaTest/__unnamed_task__/AverageReturn -97.7635 MetaTest/__unnamed_task__/Iteration 293 MetaTest/__unnamed_task__/MaxReturn -89.7258 MetaTest/__unnamed_task__/MinReturn -104.971 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.25146 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 485400 ------------------------------------------------- ------------ 2025-04-03 02:37:22 | [pearl_trainer] epoch #294 | Training... 2025-04-03 02:39:00 | [pearl_trainer] epoch #294 | Evaluating... 2025-04-03 02:39:00 | [pearl_trainer] epoch #294 | Sampling for adapation and meta-testing... 2025-04-03 02:39:46 | [pearl_trainer] epoch #294 | Finished meta-testing... 2025-04-03 02:39:46 | [pearl_trainer] epoch #294 | Saving snapshot... 2025-04-03 02:39:47 | [pearl_trainer] epoch #294 | Saved 2025-04-03 02:39:47 | [pearl_trainer] epoch #294 | Time 47463.41 s 2025-04-03 02:39:47 | [pearl_trainer] epoch #294 | EpochTime 166.92 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -94.6141 MetaTest/Average/AverageReturn -94.6141 MetaTest/Average/Iteration 294 MetaTest/Average/MaxReturn -85.2491 MetaTest/Average/MinReturn -112.974 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.9833 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.6141 MetaTest/__unnamed_task__/AverageReturn -94.6141 MetaTest/__unnamed_task__/Iteration 294 MetaTest/__unnamed_task__/MaxReturn -85.2491 MetaTest/__unnamed_task__/MinReturn -112.974 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.9833 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 487000 ------------------------------------------------- ----------- 2025-04-03 02:40:09 | [pearl_trainer] epoch #295 | Training... 2025-04-03 02:41:39 | [pearl_trainer] epoch #295 | Evaluating... 2025-04-03 02:41:39 | [pearl_trainer] epoch #295 | Sampling for adapation and meta-testing... 2025-04-03 02:42:29 | [pearl_trainer] epoch #295 | Finished meta-testing... 2025-04-03 02:42:29 | [pearl_trainer] epoch #295 | Saving snapshot... 2025-04-03 02:42:30 | [pearl_trainer] epoch #295 | Saved 2025-04-03 02:42:30 | [pearl_trainer] epoch #295 | Time 47626.19 s 2025-04-03 02:42:30 | [pearl_trainer] epoch #295 | EpochTime 162.78 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -86.9903 MetaTest/Average/AverageReturn -86.9903 MetaTest/Average/Iteration 295 MetaTest/Average/MaxReturn -81.4627 MetaTest/Average/MinReturn -95.4223 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.05775 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -86.9903 MetaTest/__unnamed_task__/AverageReturn -86.9903 MetaTest/__unnamed_task__/Iteration 295 MetaTest/__unnamed_task__/MaxReturn -81.4627 MetaTest/__unnamed_task__/MinReturn -95.4223 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.05775 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 488600 ------------------------------------------------- ------------ 2025-04-03 02:42:53 | [pearl_trainer] epoch #296 | Training... 2025-04-03 02:44:23 | [pearl_trainer] epoch #296 | Evaluating... 2025-04-03 02:44:23 | [pearl_trainer] epoch #296 | Sampling for adapation and meta-testing... 2025-04-03 02:45:08 | [pearl_trainer] epoch #296 | Finished meta-testing... 2025-04-03 02:45:08 | [pearl_trainer] epoch #296 | Saving snapshot... 2025-04-03 02:45:09 | [pearl_trainer] epoch #296 | Saved 2025-04-03 02:45:09 | [pearl_trainer] epoch #296 | Time 47785.49 s 2025-04-03 02:45:09 | [pearl_trainer] epoch #296 | EpochTime 159.29 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -87.3489 MetaTest/Average/AverageReturn -87.3489 MetaTest/Average/Iteration 296 MetaTest/Average/MaxReturn -77.9382 MetaTest/Average/MinReturn -97.2309 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.88324 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -87.3489 MetaTest/__unnamed_task__/AverageReturn -87.3489 MetaTest/__unnamed_task__/Iteration 296 MetaTest/__unnamed_task__/MaxReturn -77.9382 MetaTest/__unnamed_task__/MinReturn -97.2309 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.88324 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 490200 ------------------------------------------------- ------------ 2025-04-03 02:45:31 | [pearl_trainer] epoch #297 | Training... 2025-04-03 02:47:02 | [pearl_trainer] epoch #297 | Evaluating... 2025-04-03 02:47:02 | [pearl_trainer] epoch #297 | Sampling for adapation and meta-testing... 2025-04-03 02:47:51 | [pearl_trainer] epoch #297 | Finished meta-testing... 2025-04-03 02:47:51 | [pearl_trainer] epoch #297 | Saving snapshot... 2025-04-03 02:47:52 | [pearl_trainer] epoch #297 | Saved 2025-04-03 02:47:52 | [pearl_trainer] epoch #297 | Time 47948.67 s 2025-04-03 02:47:52 | [pearl_trainer] epoch #297 | EpochTime 163.18 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -102.833 MetaTest/Average/AverageReturn -102.833 MetaTest/Average/Iteration 297 MetaTest/Average/MaxReturn -93.1493 MetaTest/Average/MinReturn -117.175 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.3466 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -102.833 MetaTest/__unnamed_task__/AverageReturn -102.833 MetaTest/__unnamed_task__/Iteration 297 MetaTest/__unnamed_task__/MaxReturn -93.1493 MetaTest/__unnamed_task__/MinReturn -117.175 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.3466 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 491800 ------------------------------------------------- ----------- 2025-04-03 02:48:15 | [pearl_trainer] epoch #298 | Training... 2025-04-03 02:49:41 | [pearl_trainer] epoch #298 | Evaluating... 2025-04-03 02:49:41 | [pearl_trainer] epoch #298 | Sampling for adapation and meta-testing... 2025-04-03 02:50:47 | [pearl_trainer] epoch #298 | Finished meta-testing... 2025-04-03 02:50:47 | [pearl_trainer] epoch #298 | Saving snapshot... 2025-04-03 02:50:48 | [pearl_trainer] epoch #298 | Saved 2025-04-03 02:50:48 | [pearl_trainer] epoch #298 | Time 48124.24 s 2025-04-03 02:50:48 | [pearl_trainer] epoch #298 | EpochTime 175.56 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.3008 MetaTest/Average/AverageReturn -93.3008 MetaTest/Average/Iteration 298 MetaTest/Average/MaxReturn -80.1589 MetaTest/Average/MinReturn -100.304 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.29943 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.3008 MetaTest/__unnamed_task__/AverageReturn -93.3008 MetaTest/__unnamed_task__/Iteration 298 MetaTest/__unnamed_task__/MaxReturn -80.1589 MetaTest/__unnamed_task__/MinReturn -100.304 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.29943 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 493400 ------------------------------------------------- ------------ 2025-04-03 02:51:15 | [pearl_trainer] epoch #299 | Training... 2025-04-03 02:52:37 | [pearl_trainer] epoch #299 | Evaluating... 2025-04-03 02:52:37 | [pearl_trainer] epoch #299 | Sampling for adapation and meta-testing... 2025-04-03 02:53:27 | [pearl_trainer] epoch #299 | Finished meta-testing... 2025-04-03 02:53:27 | [pearl_trainer] epoch #299 | Saving snapshot... 2025-04-03 02:53:29 | [pearl_trainer] epoch #299 | Saved 2025-04-03 02:53:29 | [pearl_trainer] epoch #299 | Time 48284.94 s 2025-04-03 02:53:29 | [pearl_trainer] epoch #299 | EpochTime 160.70 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -92.272 MetaTest/Average/AverageReturn -92.272 MetaTest/Average/Iteration 299 MetaTest/Average/MaxReturn -79.8718 MetaTest/Average/MinReturn -102.979 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.50911 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.272 MetaTest/__unnamed_task__/AverageReturn -92.272 MetaTest/__unnamed_task__/Iteration 299 MetaTest/__unnamed_task__/MaxReturn -79.8718 MetaTest/__unnamed_task__/MinReturn -102.979 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.50911 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 495000 ------------------------------------------------- ------------ 2025-04-03 02:53:52 | [pearl_trainer] epoch #300 | Training... 2025-04-03 02:55:20 | [pearl_trainer] epoch #300 | Evaluating... 2025-04-03 02:55:20 | [pearl_trainer] epoch #300 | Sampling for adapation and meta-testing... 2025-04-03 02:56:10 | [pearl_trainer] epoch #300 | Finished meta-testing... 2025-04-03 02:56:10 | [pearl_trainer] epoch #300 | Saving snapshot... 2025-04-03 02:56:11 | [pearl_trainer] epoch #300 | Saved 2025-04-03 02:56:11 | [pearl_trainer] epoch #300 | Time 48447.23 s 2025-04-03 02:56:11 | [pearl_trainer] epoch #300 | EpochTime 162.29 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -95.5124 MetaTest/Average/AverageReturn -95.5124 MetaTest/Average/Iteration 300 MetaTest/Average/MaxReturn -79.8811 MetaTest/Average/MinReturn -107.39 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.5399 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.5124 MetaTest/__unnamed_task__/AverageReturn -95.5124 MetaTest/__unnamed_task__/Iteration 300 MetaTest/__unnamed_task__/MaxReturn -79.8811 MetaTest/__unnamed_task__/MinReturn -107.39 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.5399 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 496600 ------------------------------------------------- ----------- 2025-04-03 02:56:33 | [pearl_trainer] epoch #301 | Training... 2025-04-03 02:58:01 | [pearl_trainer] epoch #301 | Evaluating... 2025-04-03 02:58:01 | [pearl_trainer] epoch #301 | Sampling for adapation and meta-testing... 2025-04-03 02:58:54 | [pearl_trainer] epoch #301 | Finished meta-testing... 2025-04-03 02:58:54 | [pearl_trainer] epoch #301 | Saving snapshot... 2025-04-03 02:58:55 | [pearl_trainer] epoch #301 | Saved 2025-04-03 02:58:55 | [pearl_trainer] epoch #301 | Time 48611.24 s 2025-04-03 02:58:55 | [pearl_trainer] epoch #301 | EpochTime 164.01 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -102.181 MetaTest/Average/AverageReturn -102.181 MetaTest/Average/Iteration 301 MetaTest/Average/MaxReturn -101.389 MetaTest/Average/MinReturn -102.653 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 0.563282 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -102.181 MetaTest/__unnamed_task__/AverageReturn -102.181 MetaTest/__unnamed_task__/Iteration 301 MetaTest/__unnamed_task__/MaxReturn -101.389 MetaTest/__unnamed_task__/MinReturn -102.653 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 0.563282 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 498200 ------------------------------------------------- ------------- 2025-04-03 02:59:18 | [pearl_trainer] epoch #302 | Training... 2025-04-03 03:00:41 | [pearl_trainer] epoch #302 | Evaluating... 2025-04-03 03:00:41 | [pearl_trainer] epoch #302 | Sampling for adapation and meta-testing... 2025-04-03 03:01:31 | [pearl_trainer] epoch #302 | Finished meta-testing... 2025-04-03 03:01:31 | [pearl_trainer] epoch #302 | Saving snapshot... 2025-04-03 03:01:33 | [pearl_trainer] epoch #302 | Saved 2025-04-03 03:01:33 | [pearl_trainer] epoch #302 | Time 48769.03 s 2025-04-03 03:01:33 | [pearl_trainer] epoch #302 | EpochTime 157.78 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -84.417 MetaTest/Average/AverageReturn -84.417 MetaTest/Average/Iteration 302 MetaTest/Average/MaxReturn -82.8886 MetaTest/Average/MinReturn -86.4493 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.49669 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -84.417 MetaTest/__unnamed_task__/AverageReturn -84.417 MetaTest/__unnamed_task__/Iteration 302 MetaTest/__unnamed_task__/MaxReturn -82.8886 MetaTest/__unnamed_task__/MinReturn -86.4493 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.49669 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 499800 ------------------------------------------------- ------------ 2025-04-03 03:01:56 | [pearl_trainer] epoch #303 | Training... 2025-04-03 03:03:23 | [pearl_trainer] epoch #303 | Evaluating... 2025-04-03 03:03:23 | [pearl_trainer] epoch #303 | Sampling for adapation and meta-testing... 2025-04-03 03:04:10 | [pearl_trainer] epoch #303 | Finished meta-testing... 2025-04-03 03:04:10 | [pearl_trainer] epoch #303 | Saving snapshot... 2025-04-03 03:04:11 | [pearl_trainer] epoch #303 | Saved 2025-04-03 03:04:11 | [pearl_trainer] epoch #303 | Time 48927.48 s 2025-04-03 03:04:11 | [pearl_trainer] epoch #303 | EpochTime 158.45 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -88.8926 MetaTest/Average/AverageReturn -88.8926 MetaTest/Average/Iteration 303 MetaTest/Average/MaxReturn -85.2849 MetaTest/Average/MinReturn -94.2467 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.86143 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.8926 MetaTest/__unnamed_task__/AverageReturn -88.8926 MetaTest/__unnamed_task__/Iteration 303 MetaTest/__unnamed_task__/MaxReturn -85.2849 MetaTest/__unnamed_task__/MinReturn -94.2467 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.86143 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 501400 ------------------------------------------------- ------------ 2025-04-03 03:04:35 | [pearl_trainer] epoch #304 | Training... 2025-04-03 03:06:03 | [pearl_trainer] epoch #304 | Evaluating... 2025-04-03 03:06:03 | [pearl_trainer] epoch #304 | Sampling for adapation and meta-testing... 2025-04-03 03:06:54 | [pearl_trainer] epoch #304 | Finished meta-testing... 2025-04-03 03:06:54 | [pearl_trainer] epoch #304 | Saving snapshot... 2025-04-03 03:06:55 | [pearl_trainer] epoch #304 | Saved 2025-04-03 03:06:55 | [pearl_trainer] epoch #304 | Time 49090.86 s 2025-04-03 03:06:55 | [pearl_trainer] epoch #304 | EpochTime 163.37 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -82.646 MetaTest/Average/AverageReturn -82.646 MetaTest/Average/Iteration 304 MetaTest/Average/MaxReturn -78.9143 MetaTest/Average/MinReturn -88.2364 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.02628 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -82.646 MetaTest/__unnamed_task__/AverageReturn -82.646 MetaTest/__unnamed_task__/Iteration 304 MetaTest/__unnamed_task__/MaxReturn -78.9143 MetaTest/__unnamed_task__/MinReturn -88.2364 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.02628 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 503000 ------------------------------------------------- ------------ 2025-04-03 03:07:18 | [pearl_trainer] epoch #305 | Training... 2025-04-03 03:08:41 | [pearl_trainer] epoch #305 | Evaluating... 2025-04-03 03:08:41 | [pearl_trainer] epoch #305 | Sampling for adapation and meta-testing... 2025-04-03 03:09:30 | [pearl_trainer] epoch #305 | Finished meta-testing... 2025-04-03 03:09:30 | [pearl_trainer] epoch #305 | Saving snapshot... 2025-04-03 03:09:31 | [pearl_trainer] epoch #305 | Saved 2025-04-03 03:09:31 | [pearl_trainer] epoch #305 | Time 49247.18 s 2025-04-03 03:09:31 | [pearl_trainer] epoch #305 | EpochTime 156.32 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -88.0882 MetaTest/Average/AverageReturn -88.0882 MetaTest/Average/Iteration 305 MetaTest/Average/MaxReturn -81.9598 MetaTest/Average/MinReturn -93.0821 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.611 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.0882 MetaTest/__unnamed_task__/AverageReturn -88.0882 MetaTest/__unnamed_task__/Iteration 305 MetaTest/__unnamed_task__/MaxReturn -81.9598 MetaTest/__unnamed_task__/MinReturn -93.0821 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.611 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 504600 ------------------------------------------------- ----------- 2025-04-03 03:09:54 | [pearl_trainer] epoch #306 | Training... 2025-04-03 03:11:25 | [pearl_trainer] epoch #306 | Evaluating... 2025-04-03 03:11:25 | [pearl_trainer] epoch #306 | Sampling for adapation and meta-testing... 2025-04-03 03:12:10 | [pearl_trainer] epoch #306 | Finished meta-testing... 2025-04-03 03:12:10 | [pearl_trainer] epoch #306 | Saving snapshot... 2025-04-03 03:12:11 | [pearl_trainer] epoch #306 | Saved 2025-04-03 03:12:11 | [pearl_trainer] epoch #306 | Time 49407.34 s 2025-04-03 03:12:11 | [pearl_trainer] epoch #306 | EpochTime 160.16 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -91.5475 MetaTest/Average/AverageReturn -91.5475 MetaTest/Average/Iteration 306 MetaTest/Average/MaxReturn -85.9237 MetaTest/Average/MinReturn -100.861 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.6328 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.5475 MetaTest/__unnamed_task__/AverageReturn -91.5475 MetaTest/__unnamed_task__/Iteration 306 MetaTest/__unnamed_task__/MaxReturn -85.9237 MetaTest/__unnamed_task__/MinReturn -100.861 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.6328 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 506200 ------------------------------------------------- ----------- 2025-04-03 03:12:33 | [pearl_trainer] epoch #307 | Training... 2025-04-03 03:14:08 | [pearl_trainer] epoch #307 | Evaluating... 2025-04-03 03:14:08 | [pearl_trainer] epoch #307 | Sampling for adapation and meta-testing... 2025-04-03 03:14:57 | [pearl_trainer] epoch #307 | Finished meta-testing... 2025-04-03 03:14:57 | [pearl_trainer] epoch #307 | Saving snapshot... 2025-04-03 03:14:58 | [pearl_trainer] epoch #307 | Saved 2025-04-03 03:14:58 | [pearl_trainer] epoch #307 | Time 49574.56 s 2025-04-03 03:14:58 | [pearl_trainer] epoch #307 | EpochTime 167.22 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -86.0236 MetaTest/Average/AverageReturn -86.0236 MetaTest/Average/Iteration 307 MetaTest/Average/MaxReturn -76.9151 MetaTest/Average/MinReturn -94.3328 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.13314 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -86.0236 MetaTest/__unnamed_task__/AverageReturn -86.0236 MetaTest/__unnamed_task__/Iteration 307 MetaTest/__unnamed_task__/MaxReturn -76.9151 MetaTest/__unnamed_task__/MinReturn -94.3328 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.13314 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 507800 ------------------------------------------------- ------------ 2025-04-03 03:15:20 | [pearl_trainer] epoch #308 | Training... 2025-04-03 03:16:43 | [pearl_trainer] epoch #308 | Evaluating... 2025-04-03 03:16:43 | [pearl_trainer] epoch #308 | Sampling for adapation and meta-testing... 2025-04-03 03:17:32 | [pearl_trainer] epoch #308 | Finished meta-testing... 2025-04-03 03:17:32 | [pearl_trainer] epoch #308 | Saving snapshot... 2025-04-03 03:17:33 | [pearl_trainer] epoch #308 | Saved 2025-04-03 03:17:33 | [pearl_trainer] epoch #308 | Time 49729.15 s 2025-04-03 03:17:33 | [pearl_trainer] epoch #308 | EpochTime 154.59 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -83.2059 MetaTest/Average/AverageReturn -83.2059 MetaTest/Average/Iteration 308 MetaTest/Average/MaxReturn -73.0296 MetaTest/Average/MinReturn -89.4162 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.2538 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -83.2059 MetaTest/__unnamed_task__/AverageReturn -83.2059 MetaTest/__unnamed_task__/Iteration 308 MetaTest/__unnamed_task__/MaxReturn -73.0296 MetaTest/__unnamed_task__/MinReturn -89.4162 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.2538 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 509400 ------------------------------------------------- ----------- 2025-04-03 03:18:05 | [pearl_trainer] epoch #309 | Training... 2025-04-03 03:19:41 | [pearl_trainer] epoch #309 | Evaluating... 2025-04-03 03:19:41 | [pearl_trainer] epoch #309 | Sampling for adapation and meta-testing... 2025-04-03 03:20:26 | [pearl_trainer] epoch #309 | Finished meta-testing... 2025-04-03 03:20:26 | [pearl_trainer] epoch #309 | Saving snapshot... 2025-04-03 03:20:27 | [pearl_trainer] epoch #309 | Saved 2025-04-03 03:20:27 | [pearl_trainer] epoch #309 | Time 49903.30 s 2025-04-03 03:20:27 | [pearl_trainer] epoch #309 | EpochTime 174.14 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -87.0119 MetaTest/Average/AverageReturn -87.0119 MetaTest/Average/Iteration 309 MetaTest/Average/MaxReturn -70.8502 MetaTest/Average/MinReturn -96.7822 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.511 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -87.0119 MetaTest/__unnamed_task__/AverageReturn -87.0119 MetaTest/__unnamed_task__/Iteration 309 MetaTest/__unnamed_task__/MaxReturn -70.8502 MetaTest/__unnamed_task__/MinReturn -96.7822 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.511 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 511000 ------------------------------------------------- ----------- 2025-04-03 03:20:49 | [pearl_trainer] epoch #310 | Training... 2025-04-03 03:22:23 | [pearl_trainer] epoch #310 | Evaluating... 2025-04-03 03:22:23 | [pearl_trainer] epoch #310 | Sampling for adapation and meta-testing... 2025-04-03 03:23:14 | [pearl_trainer] epoch #310 | Finished meta-testing... 2025-04-03 03:23:14 | [pearl_trainer] epoch #310 | Saving snapshot... 2025-04-03 03:23:15 | [pearl_trainer] epoch #310 | Saved 2025-04-03 03:23:15 | [pearl_trainer] epoch #310 | Time 50071.42 s 2025-04-03 03:23:15 | [pearl_trainer] epoch #310 | EpochTime 168.13 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.2048 MetaTest/Average/AverageReturn -97.2048 MetaTest/Average/Iteration 310 MetaTest/Average/MaxReturn -93.4901 MetaTest/Average/MinReturn -102.857 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.06185 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.2048 MetaTest/__unnamed_task__/AverageReturn -97.2048 MetaTest/__unnamed_task__/Iteration 310 MetaTest/__unnamed_task__/MaxReturn -93.4901 MetaTest/__unnamed_task__/MinReturn -102.857 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.06185 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 512600 ------------------------------------------------- ------------ 2025-04-03 03:23:39 | [pearl_trainer] epoch #311 | Training... 2025-04-03 03:25:03 | [pearl_trainer] epoch #311 | Evaluating... 2025-04-03 03:25:03 | [pearl_trainer] epoch #311 | Sampling for adapation and meta-testing... 2025-04-03 03:25:57 | [pearl_trainer] epoch #311 | Finished meta-testing... 2025-04-03 03:25:57 | [pearl_trainer] epoch #311 | Saving snapshot... 2025-04-03 03:25:59 | [pearl_trainer] epoch #311 | Saved 2025-04-03 03:25:59 | [pearl_trainer] epoch #311 | Time 50234.80 s 2025-04-03 03:25:59 | [pearl_trainer] epoch #311 | EpochTime 163.37 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.9567 MetaTest/Average/AverageReturn -93.9567 MetaTest/Average/Iteration 311 MetaTest/Average/MaxReturn -85.6101 MetaTest/Average/MinReturn -106.13 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.80306 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.9567 MetaTest/__unnamed_task__/AverageReturn -93.9567 MetaTest/__unnamed_task__/Iteration 311 MetaTest/__unnamed_task__/MaxReturn -85.6101 MetaTest/__unnamed_task__/MinReturn -106.13 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.80306 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 514200 ------------------------------------------------- ------------ 2025-04-03 03:26:21 | [pearl_trainer] epoch #312 | Training... 2025-04-03 03:27:44 | [pearl_trainer] epoch #312 | Evaluating... 2025-04-03 03:27:44 | [pearl_trainer] epoch #312 | Sampling for adapation and meta-testing... 2025-04-03 03:28:29 | [pearl_trainer] epoch #312 | Finished meta-testing... 2025-04-03 03:28:29 | [pearl_trainer] epoch #312 | Saving snapshot... 2025-04-03 03:28:30 | [pearl_trainer] epoch #312 | Saved 2025-04-03 03:28:30 | [pearl_trainer] epoch #312 | Time 50386.61 s 2025-04-03 03:28:30 | [pearl_trainer] epoch #312 | EpochTime 151.81 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -102.456 MetaTest/Average/AverageReturn -102.456 MetaTest/Average/Iteration 312 MetaTest/Average/MaxReturn -89.1151 MetaTest/Average/MinReturn -111.65 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.65579 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -102.456 MetaTest/__unnamed_task__/AverageReturn -102.456 MetaTest/__unnamed_task__/Iteration 312 MetaTest/__unnamed_task__/MaxReturn -89.1151 MetaTest/__unnamed_task__/MinReturn -111.65 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.65579 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 515800 ------------------------------------------------- ------------ 2025-04-03 03:28:53 | [pearl_trainer] epoch #313 | Training... 2025-04-03 03:30:30 | [pearl_trainer] epoch #313 | Evaluating... 2025-04-03 03:30:30 | [pearl_trainer] epoch #313 | Sampling for adapation and meta-testing... 2025-04-03 03:31:15 | [pearl_trainer] epoch #313 | Finished meta-testing... 2025-04-03 03:31:15 | [pearl_trainer] epoch #313 | Saving snapshot... 2025-04-03 03:31:16 | [pearl_trainer] epoch #313 | Saved 2025-04-03 03:31:16 | [pearl_trainer] epoch #313 | Time 50552.41 s 2025-04-03 03:31:16 | [pearl_trainer] epoch #313 | EpochTime 165.80 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -101.701 MetaTest/Average/AverageReturn -101.701 MetaTest/Average/Iteration 313 MetaTest/Average/MaxReturn -93.4536 MetaTest/Average/MinReturn -108.804 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.3187 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.701 MetaTest/__unnamed_task__/AverageReturn -101.701 MetaTest/__unnamed_task__/Iteration 313 MetaTest/__unnamed_task__/MaxReturn -93.4536 MetaTest/__unnamed_task__/MinReturn -108.804 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.3187 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 517400 ------------------------------------------------- ----------- 2025-04-03 03:31:38 | [pearl_trainer] epoch #314 | Training... 2025-04-03 03:33:06 | [pearl_trainer] epoch #314 | Evaluating... 2025-04-03 03:33:06 | [pearl_trainer] epoch #314 | Sampling for adapation and meta-testing... 2025-04-03 03:33:56 | [pearl_trainer] epoch #314 | Finished meta-testing... 2025-04-03 03:33:56 | [pearl_trainer] epoch #314 | Saving snapshot... 2025-04-03 03:33:57 | [pearl_trainer] epoch #314 | Saved 2025-04-03 03:33:57 | [pearl_trainer] epoch #314 | Time 50713.52 s 2025-04-03 03:33:57 | [pearl_trainer] epoch #314 | EpochTime 161.11 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -123.974 MetaTest/Average/AverageReturn -123.974 MetaTest/Average/Iteration 314 MetaTest/Average/MaxReturn -110.918 MetaTest/Average/MinReturn -148.392 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 17.2801 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -123.974 MetaTest/__unnamed_task__/AverageReturn -123.974 MetaTest/__unnamed_task__/Iteration 314 MetaTest/__unnamed_task__/MaxReturn -110.918 MetaTest/__unnamed_task__/MinReturn -148.392 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 17.2801 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 519000 ------------------------------------------------- ----------- 2025-04-03 03:34:21 | [pearl_trainer] epoch #315 | Training... 2025-04-03 03:35:50 | [pearl_trainer] epoch #315 | Evaluating... 2025-04-03 03:35:50 | [pearl_trainer] epoch #315 | Sampling for adapation and meta-testing... 2025-04-03 03:36:35 | [pearl_trainer] epoch #315 | Finished meta-testing... 2025-04-03 03:36:35 | [pearl_trainer] epoch #315 | Saving snapshot... 2025-04-03 03:36:36 | [pearl_trainer] epoch #315 | Saved 2025-04-03 03:36:36 | [pearl_trainer] epoch #315 | Time 50872.09 s 2025-04-03 03:36:36 | [pearl_trainer] epoch #315 | EpochTime 158.57 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -101.86 MetaTest/Average/AverageReturn -101.86 MetaTest/Average/Iteration 315 MetaTest/Average/MaxReturn -86.5259 MetaTest/Average/MinReturn -116.005 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.0639 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.86 MetaTest/__unnamed_task__/AverageReturn -101.86 MetaTest/__unnamed_task__/Iteration 315 MetaTest/__unnamed_task__/MaxReturn -86.5259 MetaTest/__unnamed_task__/MinReturn -116.005 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.0639 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 520600 ------------------------------------------------- ----------- 2025-04-03 03:36:58 | [pearl_trainer] epoch #316 | Training... 2025-04-03 03:38:38 | [pearl_trainer] epoch #316 | Evaluating... 2025-04-03 03:38:38 | [pearl_trainer] epoch #316 | Sampling for adapation and meta-testing... 2025-04-03 03:39:23 | [pearl_trainer] epoch #316 | Finished meta-testing... 2025-04-03 03:39:23 | [pearl_trainer] epoch #316 | Saving snapshot... 2025-04-03 03:39:24 | [pearl_trainer] epoch #316 | Saved 2025-04-03 03:39:24 | [pearl_trainer] epoch #316 | Time 51040.37 s 2025-04-03 03:39:24 | [pearl_trainer] epoch #316 | EpochTime 168.27 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -103.644 MetaTest/Average/AverageReturn -103.644 MetaTest/Average/Iteration 316 MetaTest/Average/MaxReturn -95.7559 MetaTest/Average/MinReturn -111.49 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.42364 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -103.644 MetaTest/__unnamed_task__/AverageReturn -103.644 MetaTest/__unnamed_task__/Iteration 316 MetaTest/__unnamed_task__/MaxReturn -95.7559 MetaTest/__unnamed_task__/MinReturn -111.49 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.42364 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 522200 ------------------------------------------------- ------------ 2025-04-03 03:39:46 | [pearl_trainer] epoch #317 | Training... 2025-04-03 03:41:11 | [pearl_trainer] epoch #317 | Evaluating... 2025-04-03 03:41:11 | [pearl_trainer] epoch #317 | Sampling for adapation and meta-testing... 2025-04-03 03:42:01 | [pearl_trainer] epoch #317 | Finished meta-testing... 2025-04-03 03:42:01 | [pearl_trainer] epoch #317 | Saving snapshot... 2025-04-03 03:42:02 | [pearl_trainer] epoch #317 | Saved 2025-04-03 03:42:02 | [pearl_trainer] epoch #317 | Time 51198.01 s 2025-04-03 03:42:02 | [pearl_trainer] epoch #317 | EpochTime 157.64 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -85.5653 MetaTest/Average/AverageReturn -85.5653 MetaTest/Average/Iteration 317 MetaTest/Average/MaxReturn -80.9934 MetaTest/Average/MinReturn -91.2731 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.27283 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -85.5653 MetaTest/__unnamed_task__/AverageReturn -85.5653 MetaTest/__unnamed_task__/Iteration 317 MetaTest/__unnamed_task__/MaxReturn -80.9934 MetaTest/__unnamed_task__/MinReturn -91.2731 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.27283 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 523800 ------------------------------------------------- ------------ 2025-04-03 03:42:25 | [pearl_trainer] epoch #318 | Training... 2025-04-03 03:43:50 | [pearl_trainer] epoch #318 | Evaluating... 2025-04-03 03:43:50 | [pearl_trainer] epoch #318 | Sampling for adapation and meta-testing... 2025-04-03 03:44:36 | [pearl_trainer] epoch #318 | Finished meta-testing... 2025-04-03 03:44:36 | [pearl_trainer] epoch #318 | Saving snapshot... 2025-04-03 03:44:38 | [pearl_trainer] epoch #318 | Saved 2025-04-03 03:44:38 | [pearl_trainer] epoch #318 | Time 51353.81 s 2025-04-03 03:44:38 | [pearl_trainer] epoch #318 | EpochTime 155.79 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -111.798 MetaTest/Average/AverageReturn -111.798 MetaTest/Average/Iteration 318 MetaTest/Average/MaxReturn -100.066 MetaTest/Average/MinReturn -119.812 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.47927 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.798 MetaTest/__unnamed_task__/AverageReturn -111.798 MetaTest/__unnamed_task__/Iteration 318 MetaTest/__unnamed_task__/MaxReturn -100.066 MetaTest/__unnamed_task__/MinReturn -119.812 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.47927 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 525400 ------------------------------------------------- ------------ 2025-04-03 03:45:00 | [pearl_trainer] epoch #319 | Training... 2025-04-03 03:46:31 | [pearl_trainer] epoch #319 | Evaluating... 2025-04-03 03:46:31 | [pearl_trainer] epoch #319 | Sampling for adapation and meta-testing... 2025-04-03 03:47:21 | [pearl_trainer] epoch #319 | Finished meta-testing... 2025-04-03 03:47:21 | [pearl_trainer] epoch #319 | Saving snapshot... 2025-04-03 03:47:22 | [pearl_trainer] epoch #319 | Saved 2025-04-03 03:47:22 | [pearl_trainer] epoch #319 | Time 51517.83 s 2025-04-03 03:47:22 | [pearl_trainer] epoch #319 | EpochTime 164.02 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -103.69 MetaTest/Average/AverageReturn -103.69 MetaTest/Average/Iteration 319 MetaTest/Average/MaxReturn -89.559 MetaTest/Average/MinReturn -120.897 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.9772 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -103.69 MetaTest/__unnamed_task__/AverageReturn -103.69 MetaTest/__unnamed_task__/Iteration 319 MetaTest/__unnamed_task__/MaxReturn -89.559 MetaTest/__unnamed_task__/MinReturn -120.897 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.9772 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 527000 ------------------------------------------------- ----------- 2025-04-03 03:47:44 | [pearl_trainer] epoch #320 | Training... 2025-04-03 03:49:22 | [pearl_trainer] epoch #320 | Evaluating... 2025-04-03 03:49:22 | [pearl_trainer] epoch #320 | Sampling for adapation and meta-testing... 2025-04-03 03:50:13 | [pearl_trainer] epoch #320 | Finished meta-testing... 2025-04-03 03:50:13 | [pearl_trainer] epoch #320 | Saving snapshot... 2025-04-03 03:50:14 | [pearl_trainer] epoch #320 | Saved 2025-04-03 03:50:14 | [pearl_trainer] epoch #320 | Time 51690.63 s 2025-04-03 03:50:14 | [pearl_trainer] epoch #320 | EpochTime 172.80 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -111.482 MetaTest/Average/AverageReturn -111.482 MetaTest/Average/Iteration 320 MetaTest/Average/MaxReturn -95.111 MetaTest/Average/MinReturn -121.235 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.6463 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.482 MetaTest/__unnamed_task__/AverageReturn -111.482 MetaTest/__unnamed_task__/Iteration 320 MetaTest/__unnamed_task__/MaxReturn -95.111 MetaTest/__unnamed_task__/MinReturn -121.235 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.6463 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 528600 ------------------------------------------------- ----------- 2025-04-03 03:50:38 | [pearl_trainer] epoch #321 | Training... 2025-04-03 03:52:06 | [pearl_trainer] epoch #321 | Evaluating... 2025-04-03 03:52:06 | [pearl_trainer] epoch #321 | Sampling for adapation and meta-testing... 2025-04-03 03:52:51 | [pearl_trainer] epoch #321 | Finished meta-testing... 2025-04-03 03:52:51 | [pearl_trainer] epoch #321 | Saving snapshot... 2025-04-03 03:52:52 | [pearl_trainer] epoch #321 | Saved 2025-04-03 03:52:52 | [pearl_trainer] epoch #321 | Time 51848.43 s 2025-04-03 03:52:52 | [pearl_trainer] epoch #321 | EpochTime 157.79 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -106.806 MetaTest/Average/AverageReturn -106.806 MetaTest/Average/Iteration 321 MetaTest/Average/MaxReturn -88.3499 MetaTest/Average/MinReturn -117.851 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.1345 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -106.806 MetaTest/__unnamed_task__/AverageReturn -106.806 MetaTest/__unnamed_task__/Iteration 321 MetaTest/__unnamed_task__/MaxReturn -88.3499 MetaTest/__unnamed_task__/MinReturn -117.851 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.1345 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 530200 ------------------------------------------------- ----------- 2025-04-03 03:53:14 | [pearl_trainer] epoch #322 | Training... 2025-04-03 03:54:43 | [pearl_trainer] epoch #322 | Evaluating... 2025-04-03 03:54:43 | [pearl_trainer] epoch #322 | Sampling for adapation and meta-testing... 2025-04-03 03:55:29 | [pearl_trainer] epoch #322 | Finished meta-testing... 2025-04-03 03:55:29 | [pearl_trainer] epoch #322 | Saving snapshot... 2025-04-03 03:55:30 | [pearl_trainer] epoch #322 | Saved 2025-04-03 03:55:30 | [pearl_trainer] epoch #322 | Time 52006.21 s 2025-04-03 03:55:30 | [pearl_trainer] epoch #322 | EpochTime 157.78 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -109.155 MetaTest/Average/AverageReturn -109.155 MetaTest/Average/Iteration 322 MetaTest/Average/MaxReturn -98.6974 MetaTest/Average/MinReturn -115.45 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.44579 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -109.155 MetaTest/__unnamed_task__/AverageReturn -109.155 MetaTest/__unnamed_task__/Iteration 322 MetaTest/__unnamed_task__/MaxReturn -98.6974 MetaTest/__unnamed_task__/MinReturn -115.45 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.44579 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 531800 ------------------------------------------------- ------------ 2025-04-03 03:55:52 | [pearl_trainer] epoch #323 | Training... 2025-04-03 03:57:18 | [pearl_trainer] epoch #323 | Evaluating... 2025-04-03 03:57:18 | [pearl_trainer] epoch #323 | Sampling for adapation and meta-testing... 2025-04-03 03:58:07 | [pearl_trainer] epoch #323 | Finished meta-testing... 2025-04-03 03:58:07 | [pearl_trainer] epoch #323 | Saving snapshot... 2025-04-03 03:58:08 | [pearl_trainer] epoch #323 | Saved 2025-04-03 03:58:08 | [pearl_trainer] epoch #323 | Time 52164.18 s 2025-04-03 03:58:08 | [pearl_trainer] epoch #323 | EpochTime 157.97 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -126.5 MetaTest/Average/AverageReturn -126.5 MetaTest/Average/Iteration 323 MetaTest/Average/MaxReturn -122.429 MetaTest/Average/MinReturn -130.235 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.19554 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -126.5 MetaTest/__unnamed_task__/AverageReturn -126.5 MetaTest/__unnamed_task__/Iteration 323 MetaTest/__unnamed_task__/MaxReturn -122.429 MetaTest/__unnamed_task__/MinReturn -130.235 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.19554 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 533400 ------------------------------------------------- ------------ 2025-04-03 03:58:34 | [pearl_trainer] epoch #324 | Training... 2025-04-03 04:00:02 | [pearl_trainer] epoch #324 | Evaluating... 2025-04-03 04:00:02 | [pearl_trainer] epoch #324 | Sampling for adapation and meta-testing... 2025-04-03 04:00:47 | [pearl_trainer] epoch #324 | Finished meta-testing... 2025-04-03 04:00:47 | [pearl_trainer] epoch #324 | Saving snapshot... 2025-04-03 04:00:48 | [pearl_trainer] epoch #324 | Saved 2025-04-03 04:00:48 | [pearl_trainer] epoch #324 | Time 52324.64 s 2025-04-03 04:00:48 | [pearl_trainer] epoch #324 | EpochTime 160.46 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -97.4264 MetaTest/Average/AverageReturn -97.4264 MetaTest/Average/Iteration 324 MetaTest/Average/MaxReturn -74.1077 MetaTest/Average/MinReturn -116.614 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 17.5973 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.4264 MetaTest/__unnamed_task__/AverageReturn -97.4264 MetaTest/__unnamed_task__/Iteration 324 MetaTest/__unnamed_task__/MaxReturn -74.1077 MetaTest/__unnamed_task__/MinReturn -116.614 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 17.5973 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 535000 ------------------------------------------------- ----------- 2025-04-03 04:01:11 | [pearl_trainer] epoch #325 | Training... 2025-04-03 04:02:45 | [pearl_trainer] epoch #325 | Evaluating... 2025-04-03 04:02:45 | [pearl_trainer] epoch #325 | Sampling for adapation and meta-testing... 2025-04-03 04:03:32 | [pearl_trainer] epoch #325 | Finished meta-testing... 2025-04-03 04:03:32 | [pearl_trainer] epoch #325 | Saving snapshot... 2025-04-03 04:03:33 | [pearl_trainer] epoch #325 | Saved 2025-04-03 04:03:33 | [pearl_trainer] epoch #325 | Time 52489.39 s 2025-04-03 04:03:33 | [pearl_trainer] epoch #325 | EpochTime 164.75 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -122.003 MetaTest/Average/AverageReturn -122.003 MetaTest/Average/Iteration 325 MetaTest/Average/MaxReturn -119.127 MetaTest/Average/MinReturn -125.525 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.65138 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -122.003 MetaTest/__unnamed_task__/AverageReturn -122.003 MetaTest/__unnamed_task__/Iteration 325 MetaTest/__unnamed_task__/MaxReturn -119.127 MetaTest/__unnamed_task__/MinReturn -125.525 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.65138 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 536600 ------------------------------------------------- ------------ 2025-04-03 04:03:56 | [pearl_trainer] epoch #326 | Training... 2025-04-03 04:05:22 | [pearl_trainer] epoch #326 | Evaluating... 2025-04-03 04:05:22 | [pearl_trainer] epoch #326 | Sampling for adapation and meta-testing... 2025-04-03 04:06:11 | [pearl_trainer] epoch #326 | Finished meta-testing... 2025-04-03 04:06:11 | [pearl_trainer] epoch #326 | Saving snapshot... 2025-04-03 04:06:12 | [pearl_trainer] epoch #326 | Saved 2025-04-03 04:06:12 | [pearl_trainer] epoch #326 | Time 52647.88 s 2025-04-03 04:06:12 | [pearl_trainer] epoch #326 | EpochTime 158.48 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -111.822 MetaTest/Average/AverageReturn -111.822 MetaTest/Average/Iteration 326 MetaTest/Average/MaxReturn -109.637 MetaTest/Average/MinReturn -115.41 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.55716 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.822 MetaTest/__unnamed_task__/AverageReturn -111.822 MetaTest/__unnamed_task__/Iteration 326 MetaTest/__unnamed_task__/MaxReturn -109.637 MetaTest/__unnamed_task__/MinReturn -115.41 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.55716 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 538200 ------------------------------------------------- ------------ 2025-04-03 04:06:35 | [pearl_trainer] epoch #327 | Training... 2025-04-03 04:08:04 | [pearl_trainer] epoch #327 | Evaluating... 2025-04-03 04:08:04 | [pearl_trainer] epoch #327 | Sampling for adapation and meta-testing... 2025-04-03 04:08:49 | [pearl_trainer] epoch #327 | Finished meta-testing... 2025-04-03 04:08:49 | [pearl_trainer] epoch #327 | Saving snapshot... 2025-04-03 04:08:50 | [pearl_trainer] epoch #327 | Saved 2025-04-03 04:08:50 | [pearl_trainer] epoch #327 | Time 52806.51 s 2025-04-03 04:08:50 | [pearl_trainer] epoch #327 | EpochTime 158.63 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -115.215 MetaTest/Average/AverageReturn -115.215 MetaTest/Average/Iteration 327 MetaTest/Average/MaxReturn -96.5086 MetaTest/Average/MinReturn -133.216 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.9942 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -115.215 MetaTest/__unnamed_task__/AverageReturn -115.215 MetaTest/__unnamed_task__/Iteration 327 MetaTest/__unnamed_task__/MaxReturn -96.5086 MetaTest/__unnamed_task__/MinReturn -133.216 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.9942 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 539800 ------------------------------------------------- ----------- 2025-04-03 04:09:12 | [pearl_trainer] epoch #328 | Training... 2025-04-03 04:10:51 | [pearl_trainer] epoch #328 | Evaluating... 2025-04-03 04:10:51 | [pearl_trainer] epoch #328 | Sampling for adapation and meta-testing... 2025-04-03 04:11:37 | [pearl_trainer] epoch #328 | Finished meta-testing... 2025-04-03 04:11:37 | [pearl_trainer] epoch #328 | Saving snapshot... 2025-04-03 04:11:38 | [pearl_trainer] epoch #328 | Saved 2025-04-03 04:11:38 | [pearl_trainer] epoch #328 | Time 52974.06 s 2025-04-03 04:11:38 | [pearl_trainer] epoch #328 | EpochTime 167.55 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -110.094 MetaTest/Average/AverageReturn -110.094 MetaTest/Average/Iteration 328 MetaTest/Average/MaxReturn -103.87 MetaTest/Average/MinReturn -119.51 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.77189 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -110.094 MetaTest/__unnamed_task__/AverageReturn -110.094 MetaTest/__unnamed_task__/Iteration 328 MetaTest/__unnamed_task__/MaxReturn -103.87 MetaTest/__unnamed_task__/MinReturn -119.51 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.77189 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 541400 ------------------------------------------------- ------------ 2025-04-03 04:11:59 | [pearl_trainer] epoch #329 | Training... 2025-04-03 04:13:28 | [pearl_trainer] epoch #329 | Evaluating... 2025-04-03 04:13:28 | [pearl_trainer] epoch #329 | Sampling for adapation and meta-testing... 2025-04-03 04:14:19 | [pearl_trainer] epoch #329 | Finished meta-testing... 2025-04-03 04:14:19 | [pearl_trainer] epoch #329 | Saving snapshot... 2025-04-03 04:14:20 | [pearl_trainer] epoch #329 | Saved 2025-04-03 04:14:20 | [pearl_trainer] epoch #329 | Time 53136.36 s 2025-04-03 04:14:20 | [pearl_trainer] epoch #329 | EpochTime 162.29 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -103.741 MetaTest/Average/AverageReturn -103.741 MetaTest/Average/Iteration 329 MetaTest/Average/MaxReturn -97.5834 MetaTest/Average/MinReturn -113.713 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.1159 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -103.741 MetaTest/__unnamed_task__/AverageReturn -103.741 MetaTest/__unnamed_task__/Iteration 329 MetaTest/__unnamed_task__/MaxReturn -97.5834 MetaTest/__unnamed_task__/MinReturn -113.713 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.1159 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 543000 ------------------------------------------------- ----------- 2025-04-03 04:14:43 | [pearl_trainer] epoch #330 | Training... 2025-04-03 04:16:11 | [pearl_trainer] epoch #330 | Evaluating... 2025-04-03 04:16:11 | [pearl_trainer] epoch #330 | Sampling for adapation and meta-testing... 2025-04-03 04:17:00 | [pearl_trainer] epoch #330 | Finished meta-testing... 2025-04-03 04:17:00 | [pearl_trainer] epoch #330 | Saving snapshot... 2025-04-03 04:17:01 | [pearl_trainer] epoch #330 | Saved 2025-04-03 04:17:01 | [pearl_trainer] epoch #330 | Time 53297.03 s 2025-04-03 04:17:01 | [pearl_trainer] epoch #330 | EpochTime 160.67 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -102.633 MetaTest/Average/AverageReturn -102.633 MetaTest/Average/Iteration 330 MetaTest/Average/MaxReturn -94.6785 MetaTest/Average/MinReturn -107.747 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.70093 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -102.633 MetaTest/__unnamed_task__/AverageReturn -102.633 MetaTest/__unnamed_task__/Iteration 330 MetaTest/__unnamed_task__/MaxReturn -94.6785 MetaTest/__unnamed_task__/MinReturn -107.747 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.70093 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 544600 ------------------------------------------------- ------------ 2025-04-03 04:17:24 | [pearl_trainer] epoch #331 | Training... 2025-04-03 04:18:57 | [pearl_trainer] epoch #331 | Evaluating... 2025-04-03 04:18:57 | [pearl_trainer] epoch #331 | Sampling for adapation and meta-testing... 2025-04-03 04:19:47 | [pearl_trainer] epoch #331 | Finished meta-testing... 2025-04-03 04:19:47 | [pearl_trainer] epoch #331 | Saving snapshot... 2025-04-03 04:19:49 | [pearl_trainer] epoch #331 | Saved 2025-04-03 04:19:49 | [pearl_trainer] epoch #331 | Time 53464.73 s 2025-04-03 04:19:49 | [pearl_trainer] epoch #331 | EpochTime 167.70 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -96.3205 MetaTest/Average/AverageReturn -96.3205 MetaTest/Average/Iteration 331 MetaTest/Average/MaxReturn -87.4001 MetaTest/Average/MinReturn -107.031 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.11339 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.3205 MetaTest/__unnamed_task__/AverageReturn -96.3205 MetaTest/__unnamed_task__/Iteration 331 MetaTest/__unnamed_task__/MaxReturn -87.4001 MetaTest/__unnamed_task__/MinReturn -107.031 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.11339 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 546200 ------------------------------------------------- ------------ 2025-04-03 04:20:10 | [pearl_trainer] epoch #332 | Training... 2025-04-03 04:21:31 | [pearl_trainer] epoch #332 | Evaluating... 2025-04-03 04:21:31 | [pearl_trainer] epoch #332 | Sampling for adapation and meta-testing... 2025-04-03 04:22:19 | [pearl_trainer] epoch #332 | Finished meta-testing... 2025-04-03 04:22:19 | [pearl_trainer] epoch #332 | Saving snapshot... 2025-04-03 04:22:21 | [pearl_trainer] epoch #332 | Saved 2025-04-03 04:22:21 | [pearl_trainer] epoch #332 | Time 53616.73 s 2025-04-03 04:22:21 | [pearl_trainer] epoch #332 | EpochTime 152.00 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -84.3376 MetaTest/Average/AverageReturn -84.3376 MetaTest/Average/Iteration 332 MetaTest/Average/MaxReturn -76.7569 MetaTest/Average/MinReturn -88.4227 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.36577 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -84.3376 MetaTest/__unnamed_task__/AverageReturn -84.3376 MetaTest/__unnamed_task__/Iteration 332 MetaTest/__unnamed_task__/MaxReturn -76.7569 MetaTest/__unnamed_task__/MinReturn -88.4227 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.36577 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 547800 ------------------------------------------------- ------------ 2025-04-03 04:22:43 | [pearl_trainer] epoch #333 | Training... 2025-04-03 04:24:06 | [pearl_trainer] epoch #333 | Evaluating... 2025-04-03 04:24:06 | [pearl_trainer] epoch #333 | Sampling for adapation and meta-testing... 2025-04-03 04:24:56 | [pearl_trainer] epoch #333 | Finished meta-testing... 2025-04-03 04:24:56 | [pearl_trainer] epoch #333 | Saving snapshot... 2025-04-03 04:24:57 | [pearl_trainer] epoch #333 | Saved 2025-04-03 04:24:57 | [pearl_trainer] epoch #333 | Time 53773.44 s 2025-04-03 04:24:57 | [pearl_trainer] epoch #333 | EpochTime 156.70 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -91.75 MetaTest/Average/AverageReturn -91.75 MetaTest/Average/Iteration 333 MetaTest/Average/MaxReturn -84.2221 MetaTest/Average/MinReturn -105.045 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.42867 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.75 MetaTest/__unnamed_task__/AverageReturn -91.75 MetaTest/__unnamed_task__/Iteration 333 MetaTest/__unnamed_task__/MaxReturn -84.2221 MetaTest/__unnamed_task__/MinReturn -105.045 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.42867 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 549400 ------------------------------------------------- ------------ 2025-04-03 04:25:19 | [pearl_trainer] epoch #334 | Training... 2025-04-03 04:26:49 | [pearl_trainer] epoch #334 | Evaluating... 2025-04-03 04:26:49 | [pearl_trainer] epoch #334 | Sampling for adapation and meta-testing... 2025-04-03 04:27:39 | [pearl_trainer] epoch #334 | Finished meta-testing... 2025-04-03 04:27:39 | [pearl_trainer] epoch #334 | Saving snapshot... 2025-04-03 04:27:40 | [pearl_trainer] epoch #334 | Saved 2025-04-03 04:27:40 | [pearl_trainer] epoch #334 | Time 53935.93 s 2025-04-03 04:27:40 | [pearl_trainer] epoch #334 | EpochTime 162.49 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.3989 MetaTest/Average/AverageReturn -97.3989 MetaTest/Average/Iteration 334 MetaTest/Average/MaxReturn -87.9089 MetaTest/Average/MinReturn -107.87 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.17843 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.3989 MetaTest/__unnamed_task__/AverageReturn -97.3989 MetaTest/__unnamed_task__/Iteration 334 MetaTest/__unnamed_task__/MaxReturn -87.9089 MetaTest/__unnamed_task__/MinReturn -107.87 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.17843 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 551000 ------------------------------------------------- ------------ 2025-04-03 04:28:03 | [pearl_trainer] epoch #335 | Training... 2025-04-03 04:29:24 | [pearl_trainer] epoch #335 | Evaluating... 2025-04-03 04:29:24 | [pearl_trainer] epoch #335 | Sampling for adapation and meta-testing... 2025-04-03 04:30:14 | [pearl_trainer] epoch #335 | Finished meta-testing... 2025-04-03 04:30:14 | [pearl_trainer] epoch #335 | Saving snapshot... 2025-04-03 04:30:15 | [pearl_trainer] epoch #335 | Saved 2025-04-03 04:30:15 | [pearl_trainer] epoch #335 | Time 54091.43 s 2025-04-03 04:30:15 | [pearl_trainer] epoch #335 | EpochTime 155.50 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -98.8516 MetaTest/Average/AverageReturn -98.8516 MetaTest/Average/Iteration 335 MetaTest/Average/MaxReturn -84.536 MetaTest/Average/MinReturn -112.065 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.2656 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.8516 MetaTest/__unnamed_task__/AverageReturn -98.8516 MetaTest/__unnamed_task__/Iteration 335 MetaTest/__unnamed_task__/MaxReturn -84.536 MetaTest/__unnamed_task__/MinReturn -112.065 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.2656 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 552600 ------------------------------------------------- ----------- 2025-04-03 04:30:38 | [pearl_trainer] epoch #336 | Training... 2025-04-03 04:31:59 | [pearl_trainer] epoch #336 | Evaluating... 2025-04-03 04:31:59 | [pearl_trainer] epoch #336 | Sampling for adapation and meta-testing... 2025-04-03 04:32:50 | [pearl_trainer] epoch #336 | Finished meta-testing... 2025-04-03 04:32:50 | [pearl_trainer] epoch #336 | Saving snapshot... 2025-04-03 04:32:51 | [pearl_trainer] epoch #336 | Saved 2025-04-03 04:32:51 | [pearl_trainer] epoch #336 | Time 54247.28 s 2025-04-03 04:32:51 | [pearl_trainer] epoch #336 | EpochTime 155.84 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -98.1547 MetaTest/Average/AverageReturn -98.1547 MetaTest/Average/Iteration 336 MetaTest/Average/MaxReturn -88.0778 MetaTest/Average/MinReturn -104.683 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.22859 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.1547 MetaTest/__unnamed_task__/AverageReturn -98.1547 MetaTest/__unnamed_task__/Iteration 336 MetaTest/__unnamed_task__/MaxReturn -88.0778 MetaTest/__unnamed_task__/MinReturn -104.683 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.22859 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 554200 ------------------------------------------------- ------------ 2025-04-03 04:33:13 | [pearl_trainer] epoch #337 | Training... 2025-04-03 04:34:42 | [pearl_trainer] epoch #337 | Evaluating... 2025-04-03 04:34:42 | [pearl_trainer] epoch #337 | Sampling for adapation and meta-testing... 2025-04-03 04:35:28 | [pearl_trainer] epoch #337 | Finished meta-testing... 2025-04-03 04:35:28 | [pearl_trainer] epoch #337 | Saving snapshot... 2025-04-03 04:35:29 | [pearl_trainer] epoch #337 | Saved 2025-04-03 04:35:29 | [pearl_trainer] epoch #337 | Time 54405.26 s 2025-04-03 04:35:29 | [pearl_trainer] epoch #337 | EpochTime 157.98 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -93.1601 MetaTest/Average/AverageReturn -93.1601 MetaTest/Average/Iteration 337 MetaTest/Average/MaxReturn -77.6952 MetaTest/Average/MinReturn -106.351 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.8086 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.1601 MetaTest/__unnamed_task__/AverageReturn -93.1601 MetaTest/__unnamed_task__/Iteration 337 MetaTest/__unnamed_task__/MaxReturn -77.6952 MetaTest/__unnamed_task__/MinReturn -106.351 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.8086 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 555800 ------------------------------------------------- ----------- 2025-04-03 04:35:51 | [pearl_trainer] epoch #338 | Training... 2025-04-03 04:37:17 | [pearl_trainer] epoch #338 | Evaluating... 2025-04-03 04:37:17 | [pearl_trainer] epoch #338 | Sampling for adapation and meta-testing... 2025-04-03 04:38:07 | [pearl_trainer] epoch #338 | Finished meta-testing... 2025-04-03 04:38:07 | [pearl_trainer] epoch #338 | Saving snapshot... 2025-04-03 04:38:09 | [pearl_trainer] epoch #338 | Saved 2025-04-03 04:38:09 | [pearl_trainer] epoch #338 | Time 54564.95 s 2025-04-03 04:38:09 | [pearl_trainer] epoch #338 | EpochTime 159.69 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -96.6823 MetaTest/Average/AverageReturn -96.6823 MetaTest/Average/Iteration 338 MetaTest/Average/MaxReturn -80.9326 MetaTest/Average/MinReturn -106.803 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.2867 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.6823 MetaTest/__unnamed_task__/AverageReturn -96.6823 MetaTest/__unnamed_task__/Iteration 338 MetaTest/__unnamed_task__/MaxReturn -80.9326 MetaTest/__unnamed_task__/MinReturn -106.803 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.2867 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 557400 ------------------------------------------------- ----------- 2025-04-03 04:38:33 | [pearl_trainer] epoch #339 | Training... 2025-04-03 04:40:05 | [pearl_trainer] epoch #339 | Evaluating... 2025-04-03 04:40:05 | [pearl_trainer] epoch #339 | Sampling for adapation and meta-testing... 2025-04-03 04:40:50 | [pearl_trainer] epoch #339 | Finished meta-testing... 2025-04-03 04:40:50 | [pearl_trainer] epoch #339 | Saving snapshot... 2025-04-03 04:40:51 | [pearl_trainer] epoch #339 | Saved 2025-04-03 04:40:51 | [pearl_trainer] epoch #339 | Time 54727.13 s 2025-04-03 04:40:51 | [pearl_trainer] epoch #339 | EpochTime 162.18 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -94.1401 MetaTest/Average/AverageReturn -94.1401 MetaTest/Average/Iteration 339 MetaTest/Average/MaxReturn -81.5331 MetaTest/Average/MinReturn -106.637 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.2491 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.1401 MetaTest/__unnamed_task__/AverageReturn -94.1401 MetaTest/__unnamed_task__/Iteration 339 MetaTest/__unnamed_task__/MaxReturn -81.5331 MetaTest/__unnamed_task__/MinReturn -106.637 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.2491 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 559000 ------------------------------------------------- ----------- 2025-04-03 04:41:13 | [pearl_trainer] epoch #340 | Training... 2025-04-03 04:42:47 | [pearl_trainer] epoch #340 | Evaluating... 2025-04-03 04:42:47 | [pearl_trainer] epoch #340 | Sampling for adapation and meta-testing... 2025-04-03 04:43:35 | [pearl_trainer] epoch #340 | Finished meta-testing... 2025-04-03 04:43:35 | [pearl_trainer] epoch #340 | Saving snapshot... 2025-04-03 04:43:36 | [pearl_trainer] epoch #340 | Saved 2025-04-03 04:43:36 | [pearl_trainer] epoch #340 | Time 54892.22 s 2025-04-03 04:43:36 | [pearl_trainer] epoch #340 | EpochTime 165.09 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -101.949 MetaTest/Average/AverageReturn -101.949 MetaTest/Average/Iteration 340 MetaTest/Average/MaxReturn -92.8743 MetaTest/Average/MinReturn -106.691 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.41885 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.949 MetaTest/__unnamed_task__/AverageReturn -101.949 MetaTest/__unnamed_task__/Iteration 340 MetaTest/__unnamed_task__/MaxReturn -92.8743 MetaTest/__unnamed_task__/MinReturn -106.691 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.41885 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 560600 ------------------------------------------------- ------------ 2025-04-03 04:43:58 | [pearl_trainer] epoch #341 | Training... 2025-04-03 04:45:28 | [pearl_trainer] epoch #341 | Evaluating... 2025-04-03 04:45:28 | [pearl_trainer] epoch #341 | Sampling for adapation and meta-testing... 2025-04-03 04:46:22 | [pearl_trainer] epoch #341 | Finished meta-testing... 2025-04-03 04:46:22 | [pearl_trainer] epoch #341 | Saving snapshot... 2025-04-03 04:46:23 | [pearl_trainer] epoch #341 | Saved 2025-04-03 04:46:23 | [pearl_trainer] epoch #341 | Time 55059.08 s 2025-04-03 04:46:23 | [pearl_trainer] epoch #341 | EpochTime 166.86 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -94.4149 MetaTest/Average/AverageReturn -94.4149 MetaTest/Average/Iteration 341 MetaTest/Average/MaxReturn -85.4081 MetaTest/Average/MinReturn -100.497 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.49787 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.4149 MetaTest/__unnamed_task__/AverageReturn -94.4149 MetaTest/__unnamed_task__/Iteration 341 MetaTest/__unnamed_task__/MaxReturn -85.4081 MetaTest/__unnamed_task__/MinReturn -100.497 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.49787 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 562200 ------------------------------------------------- ------------ 2025-04-03 04:46:48 | [pearl_trainer] epoch #342 | Training... 2025-04-03 04:48:19 | [pearl_trainer] epoch #342 | Evaluating... 2025-04-03 04:48:19 | [pearl_trainer] epoch #342 | Sampling for adapation and meta-testing... 2025-04-03 04:49:08 | [pearl_trainer] epoch #342 | Finished meta-testing... 2025-04-03 04:49:08 | [pearl_trainer] epoch #342 | Saving snapshot... 2025-04-03 04:49:09 | [pearl_trainer] epoch #342 | Saved 2025-04-03 04:49:09 | [pearl_trainer] epoch #342 | Time 55225.54 s 2025-04-03 04:49:09 | [pearl_trainer] epoch #342 | EpochTime 166.46 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.0313 MetaTest/Average/AverageReturn -97.0313 MetaTest/Average/Iteration 342 MetaTest/Average/MaxReturn -92.0761 MetaTest/Average/MinReturn -101.873 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.00018 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.0313 MetaTest/__unnamed_task__/AverageReturn -97.0313 MetaTest/__unnamed_task__/Iteration 342 MetaTest/__unnamed_task__/MaxReturn -92.0761 MetaTest/__unnamed_task__/MinReturn -101.873 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.00018 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 563800 ------------------------------------------------- ------------ 2025-04-03 04:49:34 | [pearl_trainer] epoch #343 | Training... 2025-04-03 04:51:03 | [pearl_trainer] epoch #343 | Evaluating... 2025-04-03 04:51:03 | [pearl_trainer] epoch #343 | Sampling for adapation and meta-testing... 2025-04-03 04:51:51 | [pearl_trainer] epoch #343 | Finished meta-testing... 2025-04-03 04:51:51 | [pearl_trainer] epoch #343 | Saving snapshot... 2025-04-03 04:51:52 | [pearl_trainer] epoch #343 | Saved 2025-04-03 04:51:52 | [pearl_trainer] epoch #343 | Time 55388.40 s 2025-04-03 04:51:52 | [pearl_trainer] epoch #343 | EpochTime 162.85 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -89.3646 MetaTest/Average/AverageReturn -89.3646 MetaTest/Average/Iteration 343 MetaTest/Average/MaxReturn -78.2547 MetaTest/Average/MinReturn -102.778 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.143 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -89.3646 MetaTest/__unnamed_task__/AverageReturn -89.3646 MetaTest/__unnamed_task__/Iteration 343 MetaTest/__unnamed_task__/MaxReturn -78.2547 MetaTest/__unnamed_task__/MinReturn -102.778 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.143 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 565400 ------------------------------------------------- ----------- 2025-04-03 04:52:16 | [pearl_trainer] epoch #344 | Training... 2025-04-03 04:53:48 | [pearl_trainer] epoch #344 | Evaluating... 2025-04-03 04:53:48 | [pearl_trainer] epoch #344 | Sampling for adapation and meta-testing... 2025-04-03 04:54:44 | [pearl_trainer] epoch #344 | Finished meta-testing... 2025-04-03 04:54:44 | [pearl_trainer] epoch #344 | Saving snapshot... 2025-04-03 04:54:45 | [pearl_trainer] epoch #344 | Saved 2025-04-03 04:54:45 | [pearl_trainer] epoch #344 | Time 55561.25 s 2025-04-03 04:54:45 | [pearl_trainer] epoch #344 | EpochTime 172.85 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.2132 MetaTest/Average/AverageReturn -93.2132 MetaTest/Average/Iteration 344 MetaTest/Average/MaxReturn -84.0811 MetaTest/Average/MinReturn -99.2603 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.56964 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.2132 MetaTest/__unnamed_task__/AverageReturn -93.2132 MetaTest/__unnamed_task__/Iteration 344 MetaTest/__unnamed_task__/MaxReturn -84.0811 MetaTest/__unnamed_task__/MinReturn -99.2603 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.56964 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 567000 ------------------------------------------------- ------------ 2025-04-03 04:55:07 | [pearl_trainer] epoch #345 | Training... 2025-04-03 04:56:33 | [pearl_trainer] epoch #345 | Evaluating... 2025-04-03 04:56:33 | [pearl_trainer] epoch #345 | Sampling for adapation and meta-testing... 2025-04-03 04:57:20 | [pearl_trainer] epoch #345 | Finished meta-testing... 2025-04-03 04:57:20 | [pearl_trainer] epoch #345 | Saving snapshot... 2025-04-03 04:57:22 | [pearl_trainer] epoch #345 | Saved 2025-04-03 04:57:22 | [pearl_trainer] epoch #345 | Time 55717.76 s 2025-04-03 04:57:22 | [pearl_trainer] epoch #345 | EpochTime 156.51 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -94.8889 MetaTest/Average/AverageReturn -94.8889 MetaTest/Average/Iteration 345 MetaTest/Average/MaxReturn -79.2547 MetaTest/Average/MinReturn -105.467 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.2826 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.8889 MetaTest/__unnamed_task__/AverageReturn -94.8889 MetaTest/__unnamed_task__/Iteration 345 MetaTest/__unnamed_task__/MaxReturn -79.2547 MetaTest/__unnamed_task__/MinReturn -105.467 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.2826 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 568600 ------------------------------------------------- ----------- 2025-04-03 04:57:45 | [pearl_trainer] epoch #346 | Training... 2025-04-03 04:59:20 | [pearl_trainer] epoch #346 | Evaluating... 2025-04-03 04:59:20 | [pearl_trainer] epoch #346 | Sampling for adapation and meta-testing... 2025-04-03 05:00:06 | [pearl_trainer] epoch #346 | Finished meta-testing... 2025-04-03 05:00:06 | [pearl_trainer] epoch #346 | Saving snapshot... 2025-04-03 05:00:07 | [pearl_trainer] epoch #346 | Saved 2025-04-03 05:00:07 | [pearl_trainer] epoch #346 | Time 55883.66 s 2025-04-03 05:00:07 | [pearl_trainer] epoch #346 | EpochTime 165.90 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -101.685 MetaTest/Average/AverageReturn -101.685 MetaTest/Average/Iteration 346 MetaTest/Average/MaxReturn -95.0222 MetaTest/Average/MinReturn -106.46 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.85644 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.685 MetaTest/__unnamed_task__/AverageReturn -101.685 MetaTest/__unnamed_task__/Iteration 346 MetaTest/__unnamed_task__/MaxReturn -95.0222 MetaTest/__unnamed_task__/MinReturn -106.46 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.85644 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 570200 ------------------------------------------------- ------------ 2025-04-03 05:00:29 | [pearl_trainer] epoch #347 | Training... 2025-04-03 05:02:00 | [pearl_trainer] epoch #347 | Evaluating... 2025-04-03 05:02:00 | [pearl_trainer] epoch #347 | Sampling for adapation and meta-testing... 2025-04-03 05:02:53 | [pearl_trainer] epoch #347 | Finished meta-testing... 2025-04-03 05:02:53 | [pearl_trainer] epoch #347 | Saving snapshot... 2025-04-03 05:02:54 | [pearl_trainer] epoch #347 | Saved 2025-04-03 05:02:54 | [pearl_trainer] epoch #347 | Time 56049.81 s 2025-04-03 05:02:54 | [pearl_trainer] epoch #347 | EpochTime 166.15 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.8266 MetaTest/Average/AverageReturn -93.8266 MetaTest/Average/Iteration 347 MetaTest/Average/MaxReturn -89.2692 MetaTest/Average/MinReturn -101.554 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.49343 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.8266 MetaTest/__unnamed_task__/AverageReturn -93.8266 MetaTest/__unnamed_task__/Iteration 347 MetaTest/__unnamed_task__/MaxReturn -89.2692 MetaTest/__unnamed_task__/MinReturn -101.554 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.49343 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 571800 ------------------------------------------------- ------------ 2025-04-03 05:03:16 | [pearl_trainer] epoch #348 | Training... 2025-04-03 05:04:46 | [pearl_trainer] epoch #348 | Evaluating... 2025-04-03 05:04:46 | [pearl_trainer] epoch #348 | Sampling for adapation and meta-testing... 2025-04-03 05:05:33 | [pearl_trainer] epoch #348 | Finished meta-testing... 2025-04-03 05:05:33 | [pearl_trainer] epoch #348 | Saving snapshot... 2025-04-03 05:05:34 | [pearl_trainer] epoch #348 | Saved 2025-04-03 05:05:34 | [pearl_trainer] epoch #348 | Time 56210.50 s 2025-04-03 05:05:34 | [pearl_trainer] epoch #348 | EpochTime 160.68 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -100.204 MetaTest/Average/AverageReturn -100.204 MetaTest/Average/Iteration 348 MetaTest/Average/MaxReturn -83.1637 MetaTest/Average/MinReturn -116.109 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.474 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -100.204 MetaTest/__unnamed_task__/AverageReturn -100.204 MetaTest/__unnamed_task__/Iteration 348 MetaTest/__unnamed_task__/MaxReturn -83.1637 MetaTest/__unnamed_task__/MinReturn -116.109 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.474 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 573400 ------------------------------------------------- ----------- 2025-04-03 05:05:57 | [pearl_trainer] epoch #349 | Training... 2025-04-03 05:07:22 | [pearl_trainer] epoch #349 | Evaluating... 2025-04-03 05:07:22 | [pearl_trainer] epoch #349 | Sampling for adapation and meta-testing... 2025-04-03 05:08:11 | [pearl_trainer] epoch #349 | Finished meta-testing... 2025-04-03 05:08:11 | [pearl_trainer] epoch #349 | Saving snapshot... 2025-04-03 05:08:12 | [pearl_trainer] epoch #349 | Saved 2025-04-03 05:08:12 | [pearl_trainer] epoch #349 | Time 56368.19 s 2025-04-03 05:08:12 | [pearl_trainer] epoch #349 | EpochTime 157.69 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -112.971 MetaTest/Average/AverageReturn -112.971 MetaTest/Average/Iteration 349 MetaTest/Average/MaxReturn -111.452 MetaTest/Average/MinReturn -114.426 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.21485 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -112.971 MetaTest/__unnamed_task__/AverageReturn -112.971 MetaTest/__unnamed_task__/Iteration 349 MetaTest/__unnamed_task__/MaxReturn -111.452 MetaTest/__unnamed_task__/MinReturn -114.426 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.21485 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 575000 ------------------------------------------------- ------------ 2025-04-03 05:08:34 | [pearl_trainer] epoch #350 | Training... 2025-04-03 05:10:01 | [pearl_trainer] epoch #350 | Evaluating... 2025-04-03 05:10:01 | [pearl_trainer] epoch #350 | Sampling for adapation and meta-testing... 2025-04-03 05:10:49 | [pearl_trainer] epoch #350 | Finished meta-testing... 2025-04-03 05:10:49 | [pearl_trainer] epoch #350 | Saving snapshot... 2025-04-03 05:10:50 | [pearl_trainer] epoch #350 | Saved 2025-04-03 05:10:50 | [pearl_trainer] epoch #350 | Time 56526.00 s 2025-04-03 05:10:50 | [pearl_trainer] epoch #350 | EpochTime 157.81 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -90.9572 MetaTest/Average/AverageReturn -90.9572 MetaTest/Average/Iteration 350 MetaTest/Average/MaxReturn -80.065 MetaTest/Average/MinReturn -105.823 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.8846 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.9572 MetaTest/__unnamed_task__/AverageReturn -90.9572 MetaTest/__unnamed_task__/Iteration 350 MetaTest/__unnamed_task__/MaxReturn -80.065 MetaTest/__unnamed_task__/MinReturn -105.823 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.8846 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 576600 ------------------------------------------------- ----------- 2025-04-03 05:11:11 | [pearl_trainer] epoch #351 | Training... 2025-04-03 05:12:43 | [pearl_trainer] epoch #351 | Evaluating... 2025-04-03 05:12:43 | [pearl_trainer] epoch #351 | Sampling for adapation and meta-testing... 2025-04-03 05:13:32 | [pearl_trainer] epoch #351 | Finished meta-testing... 2025-04-03 05:13:32 | [pearl_trainer] epoch #351 | Saving snapshot... 2025-04-03 05:13:33 | [pearl_trainer] epoch #351 | Saved 2025-04-03 05:13:33 | [pearl_trainer] epoch #351 | Time 56689.56 s 2025-04-03 05:13:33 | [pearl_trainer] epoch #351 | EpochTime 163.55 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -94.0795 MetaTest/Average/AverageReturn -94.0795 MetaTest/Average/Iteration 351 MetaTest/Average/MaxReturn -91.0694 MetaTest/Average/MinReturn -97.7353 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.75935 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.0795 MetaTest/__unnamed_task__/AverageReturn -94.0795 MetaTest/__unnamed_task__/Iteration 351 MetaTest/__unnamed_task__/MaxReturn -91.0694 MetaTest/__unnamed_task__/MinReturn -97.7353 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.75935 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 578200 ------------------------------------------------- ------------ 2025-04-03 05:13:57 | [pearl_trainer] epoch #352 | Training... 2025-04-03 05:15:27 | [pearl_trainer] epoch #352 | Evaluating... 2025-04-03 05:15:27 | [pearl_trainer] epoch #352 | Sampling for adapation and meta-testing... 2025-04-03 05:16:12 | [pearl_trainer] epoch #352 | Finished meta-testing... 2025-04-03 05:16:12 | [pearl_trainer] epoch #352 | Saving snapshot... 2025-04-03 05:16:13 | [pearl_trainer] epoch #352 | Saved 2025-04-03 05:16:13 | [pearl_trainer] epoch #352 | Time 56849.12 s 2025-04-03 05:16:13 | [pearl_trainer] epoch #352 | EpochTime 159.56 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -89.2977 MetaTest/Average/AverageReturn -89.2977 MetaTest/Average/Iteration 352 MetaTest/Average/MaxReturn -88.5518 MetaTest/Average/MinReturn -90.3541 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 0.767854 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -89.2977 MetaTest/__unnamed_task__/AverageReturn -89.2977 MetaTest/__unnamed_task__/Iteration 352 MetaTest/__unnamed_task__/MaxReturn -88.5518 MetaTest/__unnamed_task__/MinReturn -90.3541 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 0.767854 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 579800 ------------------------------------------------- ------------- 2025-04-03 05:16:36 | [pearl_trainer] epoch #353 | Training... 2025-04-03 05:18:30 | [pearl_trainer] epoch #353 | Evaluating... 2025-04-03 05:18:30 | [pearl_trainer] epoch #353 | Sampling for adapation and meta-testing... 2025-04-03 05:19:18 | [pearl_trainer] epoch #353 | Finished meta-testing... 2025-04-03 05:19:18 | [pearl_trainer] epoch #353 | Saving snapshot... 2025-04-03 05:19:19 | [pearl_trainer] epoch #353 | Saved 2025-04-03 05:19:19 | [pearl_trainer] epoch #353 | Time 57035.21 s 2025-04-03 05:19:19 | [pearl_trainer] epoch #353 | EpochTime 186.09 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -87.3519 MetaTest/Average/AverageReturn -87.3519 MetaTest/Average/Iteration 353 MetaTest/Average/MaxReturn -80.5189 MetaTest/Average/MinReturn -95.9599 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.42753 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -87.3519 MetaTest/__unnamed_task__/AverageReturn -87.3519 MetaTest/__unnamed_task__/Iteration 353 MetaTest/__unnamed_task__/MaxReturn -80.5189 MetaTest/__unnamed_task__/MinReturn -95.9599 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.42753 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 581400 ------------------------------------------------- ------------ 2025-04-03 05:19:41 | [pearl_trainer] epoch #354 | Training... 2025-04-03 05:21:09 | [pearl_trainer] epoch #354 | Evaluating... 2025-04-03 05:21:09 | [pearl_trainer] epoch #354 | Sampling for adapation and meta-testing... 2025-04-03 05:21:58 | [pearl_trainer] epoch #354 | Finished meta-testing... 2025-04-03 05:21:58 | [pearl_trainer] epoch #354 | Saving snapshot... 2025-04-03 05:21:59 | [pearl_trainer] epoch #354 | Saved 2025-04-03 05:21:59 | [pearl_trainer] epoch #354 | Time 57195.45 s 2025-04-03 05:21:59 | [pearl_trainer] epoch #354 | EpochTime 160.23 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -105.865 MetaTest/Average/AverageReturn -105.865 MetaTest/Average/Iteration 354 MetaTest/Average/MaxReturn -99.441 MetaTest/Average/MinReturn -113.08 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.59621 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -105.865 MetaTest/__unnamed_task__/AverageReturn -105.865 MetaTest/__unnamed_task__/Iteration 354 MetaTest/__unnamed_task__/MaxReturn -99.441 MetaTest/__unnamed_task__/MinReturn -113.08 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.59621 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 583000 ------------------------------------------------- ------------ 2025-04-03 05:22:23 | [pearl_trainer] epoch #355 | Training... 2025-04-03 05:23:52 | [pearl_trainer] epoch #355 | Evaluating... 2025-04-03 05:23:52 | [pearl_trainer] epoch #355 | Sampling for adapation and meta-testing... 2025-04-03 05:24:39 | [pearl_trainer] epoch #355 | Finished meta-testing... 2025-04-03 05:24:39 | [pearl_trainer] epoch #355 | Saving snapshot... 2025-04-03 05:24:40 | [pearl_trainer] epoch #355 | Saved 2025-04-03 05:24:40 | [pearl_trainer] epoch #355 | Time 57356.27 s 2025-04-03 05:24:40 | [pearl_trainer] epoch #355 | EpochTime 160.83 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.2871 MetaTest/Average/AverageReturn -90.2871 MetaTest/Average/Iteration 355 MetaTest/Average/MaxReturn -86.227 MetaTest/Average/MinReturn -92.7982 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.89769 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.2871 MetaTest/__unnamed_task__/AverageReturn -90.2871 MetaTest/__unnamed_task__/Iteration 355 MetaTest/__unnamed_task__/MaxReturn -86.227 MetaTest/__unnamed_task__/MinReturn -92.7982 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.89769 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 584600 ------------------------------------------------- ------------ 2025-04-03 05:25:02 | [pearl_trainer] epoch #356 | Training... 2025-04-03 05:26:32 | [pearl_trainer] epoch #356 | Evaluating... 2025-04-03 05:26:32 | [pearl_trainer] epoch #356 | Sampling for adapation and meta-testing... 2025-04-03 05:27:19 | [pearl_trainer] epoch #356 | Finished meta-testing... 2025-04-03 05:27:19 | [pearl_trainer] epoch #356 | Saving snapshot... 2025-04-03 05:27:20 | [pearl_trainer] epoch #356 | Saved 2025-04-03 05:27:20 | [pearl_trainer] epoch #356 | Time 57515.90 s 2025-04-03 05:27:20 | [pearl_trainer] epoch #356 | EpochTime 159.63 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -96.7637 MetaTest/Average/AverageReturn -96.7637 MetaTest/Average/Iteration 356 MetaTest/Average/MaxReturn -78.348 MetaTest/Average/MinReturn -106.182 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.023 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.7637 MetaTest/__unnamed_task__/AverageReturn -96.7637 MetaTest/__unnamed_task__/Iteration 356 MetaTest/__unnamed_task__/MaxReturn -78.348 MetaTest/__unnamed_task__/MinReturn -106.182 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.023 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 586200 ------------------------------------------------- ----------- 2025-04-03 05:27:44 | [pearl_trainer] epoch #357 | Training... 2025-04-03 05:29:09 | [pearl_trainer] epoch #357 | Evaluating... 2025-04-03 05:29:09 | [pearl_trainer] epoch #357 | Sampling for adapation and meta-testing... 2025-04-03 05:30:00 | [pearl_trainer] epoch #357 | Finished meta-testing... 2025-04-03 05:30:00 | [pearl_trainer] epoch #357 | Saving snapshot... 2025-04-03 05:30:01 | [pearl_trainer] epoch #357 | Saved 2025-04-03 05:30:01 | [pearl_trainer] epoch #357 | Time 57677.14 s 2025-04-03 05:30:01 | [pearl_trainer] epoch #357 | EpochTime 161.24 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.2856 MetaTest/Average/AverageReturn -97.2856 MetaTest/Average/Iteration 357 MetaTest/Average/MaxReturn -93.1816 MetaTest/Average/MinReturn -100.264 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.99894 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.2856 MetaTest/__unnamed_task__/AverageReturn -97.2856 MetaTest/__unnamed_task__/Iteration 357 MetaTest/__unnamed_task__/MaxReturn -93.1816 MetaTest/__unnamed_task__/MinReturn -100.264 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.99894 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 587800 ------------------------------------------------- ------------ 2025-04-03 05:30:24 | [pearl_trainer] epoch #358 | Training... 2025-04-03 05:31:55 | [pearl_trainer] epoch #358 | Evaluating... 2025-04-03 05:31:55 | [pearl_trainer] epoch #358 | Sampling for adapation and meta-testing... 2025-04-03 05:32:42 | [pearl_trainer] epoch #358 | Finished meta-testing... 2025-04-03 05:32:42 | [pearl_trainer] epoch #358 | Saving snapshot... 2025-04-03 05:32:43 | [pearl_trainer] epoch #358 | Saved 2025-04-03 05:32:43 | [pearl_trainer] epoch #358 | Time 57839.12 s 2025-04-03 05:32:43 | [pearl_trainer] epoch #358 | EpochTime 161.98 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -92.6827 MetaTest/Average/AverageReturn -92.6827 MetaTest/Average/Iteration 358 MetaTest/Average/MaxReturn -88.5646 MetaTest/Average/MinReturn -97.4064 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.63498 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.6827 MetaTest/__unnamed_task__/AverageReturn -92.6827 MetaTest/__unnamed_task__/Iteration 358 MetaTest/__unnamed_task__/MaxReturn -88.5646 MetaTest/__unnamed_task__/MinReturn -97.4064 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.63498 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 589400 ------------------------------------------------- ------------ 2025-04-03 05:33:05 | [pearl_trainer] epoch #359 | Training... 2025-04-03 05:34:44 | [pearl_trainer] epoch #359 | Evaluating... 2025-04-03 05:34:44 | [pearl_trainer] epoch #359 | Sampling for adapation and meta-testing... 2025-04-03 05:35:29 | [pearl_trainer] epoch #359 | Finished meta-testing... 2025-04-03 05:35:29 | [pearl_trainer] epoch #359 | Saving snapshot... 2025-04-03 05:35:31 | [pearl_trainer] epoch #359 | Saved 2025-04-03 05:35:31 | [pearl_trainer] epoch #359 | Time 58007.07 s 2025-04-03 05:35:31 | [pearl_trainer] epoch #359 | EpochTime 167.94 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -90.3056 MetaTest/Average/AverageReturn -90.3056 MetaTest/Average/Iteration 359 MetaTest/Average/MaxReturn -87.8452 MetaTest/Average/MinReturn -93.5765 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.409 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.3056 MetaTest/__unnamed_task__/AverageReturn -90.3056 MetaTest/__unnamed_task__/Iteration 359 MetaTest/__unnamed_task__/MaxReturn -87.8452 MetaTest/__unnamed_task__/MinReturn -93.5765 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.409 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 591000 ------------------------------------------------- ----------- 2025-04-03 05:35:53 | [pearl_trainer] epoch #360 | Training... 2025-04-03 05:37:22 | [pearl_trainer] epoch #360 | Evaluating... 2025-04-03 05:37:22 | [pearl_trainer] epoch #360 | Sampling for adapation and meta-testing... 2025-04-03 05:38:12 | [pearl_trainer] epoch #360 | Finished meta-testing... 2025-04-03 05:38:12 | [pearl_trainer] epoch #360 | Saving snapshot... 2025-04-03 05:38:13 | [pearl_trainer] epoch #360 | Saved 2025-04-03 05:38:13 | [pearl_trainer] epoch #360 | Time 58169.39 s 2025-04-03 05:38:13 | [pearl_trainer] epoch #360 | EpochTime 162.32 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -95.5493 MetaTest/Average/AverageReturn -95.5493 MetaTest/Average/Iteration 360 MetaTest/Average/MaxReturn -73.6757 MetaTest/Average/MinReturn -128.096 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 23.4637 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.5493 MetaTest/__unnamed_task__/AverageReturn -95.5493 MetaTest/__unnamed_task__/Iteration 360 MetaTest/__unnamed_task__/MaxReturn -73.6757 MetaTest/__unnamed_task__/MinReturn -128.096 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 23.4637 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 592600 ------------------------------------------------- ----------- 2025-04-03 05:38:37 | [pearl_trainer] epoch #361 | Training... 2025-04-03 05:40:05 | [pearl_trainer] epoch #361 | Evaluating... 2025-04-03 05:40:05 | [pearl_trainer] epoch #361 | Sampling for adapation and meta-testing... 2025-04-03 05:40:52 | [pearl_trainer] epoch #361 | Finished meta-testing... 2025-04-03 05:40:52 | [pearl_trainer] epoch #361 | Saving snapshot... 2025-04-03 05:40:53 | [pearl_trainer] epoch #361 | Saved 2025-04-03 05:40:53 | [pearl_trainer] epoch #361 | Time 58329.02 s 2025-04-03 05:40:53 | [pearl_trainer] epoch #361 | EpochTime 159.63 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -94.7568 MetaTest/Average/AverageReturn -94.7568 MetaTest/Average/Iteration 361 MetaTest/Average/MaxReturn -90.538 MetaTest/Average/MinReturn -100.508 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.21194 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.7568 MetaTest/__unnamed_task__/AverageReturn -94.7568 MetaTest/__unnamed_task__/Iteration 361 MetaTest/__unnamed_task__/MaxReturn -90.538 MetaTest/__unnamed_task__/MinReturn -100.508 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.21194 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 594200 ------------------------------------------------- ------------ 2025-04-03 05:41:15 | [pearl_trainer] epoch #362 | Training... 2025-04-03 05:42:52 | [pearl_trainer] epoch #362 | Evaluating... 2025-04-03 05:42:52 | [pearl_trainer] epoch #362 | Sampling for adapation and meta-testing... 2025-04-03 05:43:37 | [pearl_trainer] epoch #362 | Finished meta-testing... 2025-04-03 05:43:37 | [pearl_trainer] epoch #362 | Saving snapshot... 2025-04-03 05:43:39 | [pearl_trainer] epoch #362 | Saved 2025-04-03 05:43:39 | [pearl_trainer] epoch #362 | Time 58494.85 s 2025-04-03 05:43:39 | [pearl_trainer] epoch #362 | EpochTime 165.83 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -80.564 MetaTest/Average/AverageReturn -80.564 MetaTest/Average/Iteration 362 MetaTest/Average/MaxReturn -76.05 MetaTest/Average/MinReturn -83.8485 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.30029 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -80.564 MetaTest/__unnamed_task__/AverageReturn -80.564 MetaTest/__unnamed_task__/Iteration 362 MetaTest/__unnamed_task__/MaxReturn -76.05 MetaTest/__unnamed_task__/MinReturn -83.8485 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.30029 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 595800 ------------------------------------------------- ------------ 2025-04-03 05:44:01 | [pearl_trainer] epoch #363 | Training... 2025-04-03 05:45:23 | [pearl_trainer] epoch #363 | Evaluating... 2025-04-03 05:45:23 | [pearl_trainer] epoch #363 | Sampling for adapation and meta-testing... 2025-04-03 05:46:19 | [pearl_trainer] epoch #363 | Finished meta-testing... 2025-04-03 05:46:19 | [pearl_trainer] epoch #363 | Saving snapshot... 2025-04-03 05:46:20 | [pearl_trainer] epoch #363 | Saved 2025-04-03 05:46:20 | [pearl_trainer] epoch #363 | Time 58656.02 s 2025-04-03 05:46:20 | [pearl_trainer] epoch #363 | EpochTime 161.16 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -87.1127 MetaTest/Average/AverageReturn -87.1127 MetaTest/Average/Iteration 363 MetaTest/Average/MaxReturn -71.9609 MetaTest/Average/MinReturn -95.3988 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.7296 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -87.1127 MetaTest/__unnamed_task__/AverageReturn -87.1127 MetaTest/__unnamed_task__/Iteration 363 MetaTest/__unnamed_task__/MaxReturn -71.9609 MetaTest/__unnamed_task__/MinReturn -95.3988 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.7296 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 597400 ------------------------------------------------- ----------- 2025-04-03 05:46:44 | [pearl_trainer] epoch #364 | Training... 2025-04-03 05:48:10 | [pearl_trainer] epoch #364 | Evaluating... 2025-04-03 05:48:10 | [pearl_trainer] epoch #364 | Sampling for adapation and meta-testing... 2025-04-03 05:49:01 | [pearl_trainer] epoch #364 | Finished meta-testing... 2025-04-03 05:49:01 | [pearl_trainer] epoch #364 | Saving snapshot... 2025-04-03 05:49:02 | [pearl_trainer] epoch #364 | Saved 2025-04-03 05:49:02 | [pearl_trainer] epoch #364 | Time 58818.41 s 2025-04-03 05:49:02 | [pearl_trainer] epoch #364 | EpochTime 162.39 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -119.696 MetaTest/Average/AverageReturn -119.696 MetaTest/Average/Iteration 364 MetaTest/Average/MaxReturn -88.9226 MetaTest/Average/MinReturn -142.166 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 22.5154 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -119.696 MetaTest/__unnamed_task__/AverageReturn -119.696 MetaTest/__unnamed_task__/Iteration 364 MetaTest/__unnamed_task__/MaxReturn -88.9226 MetaTest/__unnamed_task__/MinReturn -142.166 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 22.5154 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 599000 ------------------------------------------------- ----------- 2025-04-03 05:49:28 | [pearl_trainer] epoch #365 | Training... 2025-04-03 05:51:04 | [pearl_trainer] epoch #365 | Evaluating... 2025-04-03 05:51:04 | [pearl_trainer] epoch #365 | Sampling for adapation and meta-testing... 2025-04-03 05:51:49 | [pearl_trainer] epoch #365 | Finished meta-testing... 2025-04-03 05:51:49 | [pearl_trainer] epoch #365 | Saving snapshot... 2025-04-03 05:51:51 | [pearl_trainer] epoch #365 | Saved 2025-04-03 05:51:51 | [pearl_trainer] epoch #365 | Time 58986.71 s 2025-04-03 05:51:51 | [pearl_trainer] epoch #365 | EpochTime 168.30 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -111.552 MetaTest/Average/AverageReturn -111.552 MetaTest/Average/Iteration 365 MetaTest/Average/MaxReturn -77.4836 MetaTest/Average/MinReturn -130.788 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 24.1569 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.552 MetaTest/__unnamed_task__/AverageReturn -111.552 MetaTest/__unnamed_task__/Iteration 365 MetaTest/__unnamed_task__/MaxReturn -77.4836 MetaTest/__unnamed_task__/MinReturn -130.788 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 24.1569 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 600600 ------------------------------------------------- ----------- 2025-04-03 05:52:13 | [pearl_trainer] epoch #366 | Training... 2025-04-03 05:53:41 | [pearl_trainer] epoch #366 | Evaluating... 2025-04-03 05:53:41 | [pearl_trainer] epoch #366 | Sampling for adapation and meta-testing... 2025-04-03 05:54:31 | [pearl_trainer] epoch #366 | Finished meta-testing... 2025-04-03 05:54:31 | [pearl_trainer] epoch #366 | Saving snapshot... 2025-04-03 05:54:32 | [pearl_trainer] epoch #366 | Saved 2025-04-03 05:54:32 | [pearl_trainer] epoch #366 | Time 59148.29 s 2025-04-03 05:54:32 | [pearl_trainer] epoch #366 | EpochTime 161.59 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -92.885 MetaTest/Average/AverageReturn -92.885 MetaTest/Average/Iteration 366 MetaTest/Average/MaxReturn -74.884 MetaTest/Average/MinReturn -109.922 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.3203 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.885 MetaTest/__unnamed_task__/AverageReturn -92.885 MetaTest/__unnamed_task__/Iteration 366 MetaTest/__unnamed_task__/MaxReturn -74.884 MetaTest/__unnamed_task__/MinReturn -109.922 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.3203 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 602200 ------------------------------------------------- ----------- 2025-04-03 05:54:55 | [pearl_trainer] epoch #367 | Training... 2025-04-03 05:56:23 | [pearl_trainer] epoch #367 | Evaluating... 2025-04-03 05:56:23 | [pearl_trainer] epoch #367 | Sampling for adapation and meta-testing... 2025-04-03 05:57:08 | [pearl_trainer] epoch #367 | Finished meta-testing... 2025-04-03 05:57:08 | [pearl_trainer] epoch #367 | Saving snapshot... 2025-04-03 05:57:10 | [pearl_trainer] epoch #367 | Saved 2025-04-03 05:57:10 | [pearl_trainer] epoch #367 | Time 59306.03 s 2025-04-03 05:57:10 | [pearl_trainer] epoch #367 | EpochTime 157.73 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -110.274 MetaTest/Average/AverageReturn -110.274 MetaTest/Average/Iteration 367 MetaTest/Average/MaxReturn -87.2746 MetaTest/Average/MinReturn -128.923 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 17.2789 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -110.274 MetaTest/__unnamed_task__/AverageReturn -110.274 MetaTest/__unnamed_task__/Iteration 367 MetaTest/__unnamed_task__/MaxReturn -87.2746 MetaTest/__unnamed_task__/MinReturn -128.923 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 17.2789 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 603800 ------------------------------------------------- ----------- 2025-04-03 05:57:33 | [pearl_trainer] epoch #368 | Training... 2025-04-03 05:59:01 | [pearl_trainer] epoch #368 | Evaluating... 2025-04-03 05:59:01 | [pearl_trainer] epoch #368 | Sampling for adapation and meta-testing... 2025-04-03 05:59:51 | [pearl_trainer] epoch #368 | Finished meta-testing... 2025-04-03 05:59:51 | [pearl_trainer] epoch #368 | Saving snapshot... 2025-04-03 05:59:52 | [pearl_trainer] epoch #368 | Saved 2025-04-03 05:59:52 | [pearl_trainer] epoch #368 | Time 59468.61 s 2025-04-03 05:59:52 | [pearl_trainer] epoch #368 | EpochTime 162.57 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -121.189 MetaTest/Average/AverageReturn -121.189 MetaTest/Average/Iteration 368 MetaTest/Average/MaxReturn -105.668 MetaTest/Average/MinReturn -132.46 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.3434 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -121.189 MetaTest/__unnamed_task__/AverageReturn -121.189 MetaTest/__unnamed_task__/Iteration 368 MetaTest/__unnamed_task__/MaxReturn -105.668 MetaTest/__unnamed_task__/MinReturn -132.46 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.3434 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 605400 ------------------------------------------------- ----------- 2025-04-03 06:00:15 | [pearl_trainer] epoch #369 | Training... 2025-04-03 06:01:41 | [pearl_trainer] epoch #369 | Evaluating... 2025-04-03 06:01:41 | [pearl_trainer] epoch #369 | Sampling for adapation and meta-testing... 2025-04-03 06:02:31 | [pearl_trainer] epoch #369 | Finished meta-testing... 2025-04-03 06:02:31 | [pearl_trainer] epoch #369 | Saving snapshot... 2025-04-03 06:02:33 | [pearl_trainer] epoch #369 | Saved 2025-04-03 06:02:33 | [pearl_trainer] epoch #369 | Time 59628.78 s 2025-04-03 06:02:33 | [pearl_trainer] epoch #369 | EpochTime 160.18 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -99.3159 MetaTest/Average/AverageReturn -99.3159 MetaTest/Average/Iteration 369 MetaTest/Average/MaxReturn -82.8959 MetaTest/Average/MinReturn -111.866 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.1396 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -99.3159 MetaTest/__unnamed_task__/AverageReturn -99.3159 MetaTest/__unnamed_task__/Iteration 369 MetaTest/__unnamed_task__/MaxReturn -82.8959 MetaTest/__unnamed_task__/MinReturn -111.866 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.1396 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 607000 ------------------------------------------------- ----------- 2025-04-03 06:02:55 | [pearl_trainer] epoch #370 | Training... 2025-04-03 06:04:28 | [pearl_trainer] epoch #370 | Evaluating... 2025-04-03 06:04:28 | [pearl_trainer] epoch #370 | Sampling for adapation and meta-testing... 2025-04-03 06:05:14 | [pearl_trainer] epoch #370 | Finished meta-testing... 2025-04-03 06:05:14 | [pearl_trainer] epoch #370 | Saving snapshot... 2025-04-03 06:05:15 | [pearl_trainer] epoch #370 | Saved 2025-04-03 06:05:15 | [pearl_trainer] epoch #370 | Time 59791.10 s 2025-04-03 06:05:15 | [pearl_trainer] epoch #370 | EpochTime 162.31 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -98.8894 MetaTest/Average/AverageReturn -98.8894 MetaTest/Average/Iteration 370 MetaTest/Average/MaxReturn -85.7704 MetaTest/Average/MinReturn -114.515 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.8679 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -98.8894 MetaTest/__unnamed_task__/AverageReturn -98.8894 MetaTest/__unnamed_task__/Iteration 370 MetaTest/__unnamed_task__/MaxReturn -85.7704 MetaTest/__unnamed_task__/MinReturn -114.515 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.8679 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 608600 ------------------------------------------------- ----------- 2025-04-03 06:05:39 | [pearl_trainer] epoch #371 | Training... 2025-04-03 06:07:15 | [pearl_trainer] epoch #371 | Evaluating... 2025-04-03 06:07:15 | [pearl_trainer] epoch #371 | Sampling for adapation and meta-testing... 2025-04-03 06:08:01 | [pearl_trainer] epoch #371 | Finished meta-testing... 2025-04-03 06:08:01 | [pearl_trainer] epoch #371 | Saving snapshot... 2025-04-03 06:08:02 | [pearl_trainer] epoch #371 | Saved 2025-04-03 06:08:02 | [pearl_trainer] epoch #371 | Time 59958.21 s 2025-04-03 06:08:02 | [pearl_trainer] epoch #371 | EpochTime 167.11 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -125.298 MetaTest/Average/AverageReturn -125.298 MetaTest/Average/Iteration 371 MetaTest/Average/MaxReturn -96.59 MetaTest/Average/MinReturn -139.726 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 20.3001 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -125.298 MetaTest/__unnamed_task__/AverageReturn -125.298 MetaTest/__unnamed_task__/Iteration 371 MetaTest/__unnamed_task__/MaxReturn -96.59 MetaTest/__unnamed_task__/MinReturn -139.726 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 20.3001 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 610200 ------------------------------------------------- ----------- 2025-04-03 06:08:24 | [pearl_trainer] epoch #372 | Training... 2025-04-03 06:09:57 | [pearl_trainer] epoch #372 | Evaluating... 2025-04-03 06:09:57 | [pearl_trainer] epoch #372 | Sampling for adapation and meta-testing... 2025-04-03 06:10:47 | [pearl_trainer] epoch #372 | Finished meta-testing... 2025-04-03 06:10:47 | [pearl_trainer] epoch #372 | Saving snapshot... 2025-04-03 06:10:48 | [pearl_trainer] epoch #372 | Saved 2025-04-03 06:10:48 | [pearl_trainer] epoch #372 | Time 60124.11 s 2025-04-03 06:10:48 | [pearl_trainer] epoch #372 | EpochTime 165.90 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -101.782 MetaTest/Average/AverageReturn -101.782 MetaTest/Average/Iteration 372 MetaTest/Average/MaxReturn -98.1258 MetaTest/Average/MinReturn -107.187 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.90073 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.782 MetaTest/__unnamed_task__/AverageReturn -101.782 MetaTest/__unnamed_task__/Iteration 372 MetaTest/__unnamed_task__/MaxReturn -98.1258 MetaTest/__unnamed_task__/MinReturn -107.187 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.90073 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 611800 ------------------------------------------------- ------------ 2025-04-03 06:11:10 | [pearl_trainer] epoch #373 | Training... 2025-04-03 06:12:34 | [pearl_trainer] epoch #373 | Evaluating... 2025-04-03 06:12:34 | [pearl_trainer] epoch #373 | Sampling for adapation and meta-testing... 2025-04-03 06:13:25 | [pearl_trainer] epoch #373 | Finished meta-testing... 2025-04-03 06:13:25 | [pearl_trainer] epoch #373 | Saving snapshot... 2025-04-03 06:13:26 | [pearl_trainer] epoch #373 | Saved 2025-04-03 06:13:26 | [pearl_trainer] epoch #373 | Time 60282.01 s 2025-04-03 06:13:26 | [pearl_trainer] epoch #373 | EpochTime 157.90 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -130.196 MetaTest/Average/AverageReturn -130.196 MetaTest/Average/Iteration 373 MetaTest/Average/MaxReturn -124.978 MetaTest/Average/MinReturn -138.2 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.74664 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -130.196 MetaTest/__unnamed_task__/AverageReturn -130.196 MetaTest/__unnamed_task__/Iteration 373 MetaTest/__unnamed_task__/MaxReturn -124.978 MetaTest/__unnamed_task__/MinReturn -138.2 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.74664 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 613400 ------------------------------------------------- ------------ 2025-04-03 06:13:50 | [pearl_trainer] epoch #374 | Training... 2025-04-03 06:15:17 | [pearl_trainer] epoch #374 | Evaluating... 2025-04-03 06:15:17 | [pearl_trainer] epoch #374 | Sampling for adapation and meta-testing... 2025-04-03 06:16:03 | [pearl_trainer] epoch #374 | Finished meta-testing... 2025-04-03 06:16:03 | [pearl_trainer] epoch #374 | Saving snapshot... 2025-04-03 06:16:05 | [pearl_trainer] epoch #374 | Saved 2025-04-03 06:16:05 | [pearl_trainer] epoch #374 | Time 60440.83 s 2025-04-03 06:16:05 | [pearl_trainer] epoch #374 | EpochTime 158.82 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -115.797 MetaTest/Average/AverageReturn -115.797 MetaTest/Average/Iteration 374 MetaTest/Average/MaxReturn -110.014 MetaTest/Average/MinReturn -126.214 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.38039 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -115.797 MetaTest/__unnamed_task__/AverageReturn -115.797 MetaTest/__unnamed_task__/Iteration 374 MetaTest/__unnamed_task__/MaxReturn -110.014 MetaTest/__unnamed_task__/MinReturn -126.214 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.38039 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 615000 ------------------------------------------------- ------------ 2025-04-03 06:16:27 | [pearl_trainer] epoch #375 | Training... 2025-04-03 06:17:58 | [pearl_trainer] epoch #375 | Evaluating... 2025-04-03 06:17:58 | [pearl_trainer] epoch #375 | Sampling for adapation and meta-testing... 2025-04-03 06:18:47 | [pearl_trainer] epoch #375 | Finished meta-testing... 2025-04-03 06:18:47 | [pearl_trainer] epoch #375 | Saving snapshot... 2025-04-03 06:18:48 | [pearl_trainer] epoch #375 | Saved 2025-04-03 06:18:48 | [pearl_trainer] epoch #375 | Time 60604.37 s 2025-04-03 06:18:48 | [pearl_trainer] epoch #375 | EpochTime 163.54 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -117.216 MetaTest/Average/AverageReturn -117.216 MetaTest/Average/Iteration 375 MetaTest/Average/MaxReturn -106.176 MetaTest/Average/MinReturn -131.531 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.6068 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -117.216 MetaTest/__unnamed_task__/AverageReturn -117.216 MetaTest/__unnamed_task__/Iteration 375 MetaTest/__unnamed_task__/MaxReturn -106.176 MetaTest/__unnamed_task__/MinReturn -131.531 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.6068 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 616600 ------------------------------------------------- ----------- 2025-04-03 06:19:10 | [pearl_trainer] epoch #376 | Training... 2025-04-03 06:20:46 | [pearl_trainer] epoch #376 | Evaluating... 2025-04-03 06:20:46 | [pearl_trainer] epoch #376 | Sampling for adapation and meta-testing... 2025-04-03 06:21:36 | [pearl_trainer] epoch #376 | Finished meta-testing... 2025-04-03 06:21:36 | [pearl_trainer] epoch #376 | Saving snapshot... 2025-04-03 06:21:37 | [pearl_trainer] epoch #376 | Saved 2025-04-03 06:21:37 | [pearl_trainer] epoch #376 | Time 60772.78 s 2025-04-03 06:21:37 | [pearl_trainer] epoch #376 | EpochTime 168.40 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -121.454 MetaTest/Average/AverageReturn -121.454 MetaTest/Average/Iteration 376 MetaTest/Average/MaxReturn -112.139 MetaTest/Average/MinReturn -133.987 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.20531 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -121.454 MetaTest/__unnamed_task__/AverageReturn -121.454 MetaTest/__unnamed_task__/Iteration 376 MetaTest/__unnamed_task__/MaxReturn -112.139 MetaTest/__unnamed_task__/MinReturn -133.987 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.20531 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 618200 ------------------------------------------------- ------------ 2025-04-03 06:22:00 | [pearl_trainer] epoch #377 | Training... 2025-04-03 06:23:42 | [pearl_trainer] epoch #377 | Evaluating... 2025-04-03 06:23:42 | [pearl_trainer] epoch #377 | Sampling for adapation and meta-testing... 2025-04-03 06:24:30 | [pearl_trainer] epoch #377 | Finished meta-testing... 2025-04-03 06:24:30 | [pearl_trainer] epoch #377 | Saving snapshot... 2025-04-03 06:24:31 | [pearl_trainer] epoch #377 | Saved 2025-04-03 06:24:31 | [pearl_trainer] epoch #377 | Time 60947.18 s 2025-04-03 06:24:31 | [pearl_trainer] epoch #377 | EpochTime 174.39 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -133.267 MetaTest/Average/AverageReturn -133.267 MetaTest/Average/Iteration 377 MetaTest/Average/MaxReturn -130.477 MetaTest/Average/MinReturn -134.872 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.98017 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -133.267 MetaTest/__unnamed_task__/AverageReturn -133.267 MetaTest/__unnamed_task__/Iteration 377 MetaTest/__unnamed_task__/MaxReturn -130.477 MetaTest/__unnamed_task__/MinReturn -134.872 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.98017 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 619800 ------------------------------------------------- ------------ 2025-04-03 06:24:54 | [pearl_trainer] epoch #378 | Training... 2025-04-03 06:26:23 | [pearl_trainer] epoch #378 | Evaluating... 2025-04-03 06:26:23 | [pearl_trainer] epoch #378 | Sampling for adapation and meta-testing... 2025-04-03 06:27:13 | [pearl_trainer] epoch #378 | Finished meta-testing... 2025-04-03 06:27:13 | [pearl_trainer] epoch #378 | Saving snapshot... 2025-04-03 06:27:14 | [pearl_trainer] epoch #378 | Saved 2025-04-03 06:27:14 | [pearl_trainer] epoch #378 | Time 61110.10 s 2025-04-03 06:27:14 | [pearl_trainer] epoch #378 | EpochTime 162.92 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -118.2 MetaTest/Average/AverageReturn -118.2 MetaTest/Average/Iteration 378 MetaTest/Average/MaxReturn -110.329 MetaTest/Average/MinReturn -124.025 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.77519 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -118.2 MetaTest/__unnamed_task__/AverageReturn -118.2 MetaTest/__unnamed_task__/Iteration 378 MetaTest/__unnamed_task__/MaxReturn -110.329 MetaTest/__unnamed_task__/MinReturn -124.025 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.77519 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 621400 ------------------------------------------------- ------------ 2025-04-03 06:27:36 | [pearl_trainer] epoch #379 | Training... 2025-04-03 06:29:05 | [pearl_trainer] epoch #379 | Evaluating... 2025-04-03 06:29:05 | [pearl_trainer] epoch #379 | Sampling for adapation and meta-testing... 2025-04-03 06:29:51 | [pearl_trainer] epoch #379 | Finished meta-testing... 2025-04-03 06:29:51 | [pearl_trainer] epoch #379 | Saving snapshot... 2025-04-03 06:29:52 | [pearl_trainer] epoch #379 | Saved 2025-04-03 06:29:52 | [pearl_trainer] epoch #379 | Time 61268.30 s 2025-04-03 06:29:52 | [pearl_trainer] epoch #379 | EpochTime 158.21 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -94.6413 MetaTest/Average/AverageReturn -94.6413 MetaTest/Average/Iteration 379 MetaTest/Average/MaxReturn -91.0531 MetaTest/Average/MinReturn -98.5582 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.07276 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.6413 MetaTest/__unnamed_task__/AverageReturn -94.6413 MetaTest/__unnamed_task__/Iteration 379 MetaTest/__unnamed_task__/MaxReturn -91.0531 MetaTest/__unnamed_task__/MinReturn -98.5582 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.07276 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 623000 ------------------------------------------------- ------------ 2025-04-03 06:30:15 | [pearl_trainer] epoch #380 | Training... 2025-04-03 06:31:41 | [pearl_trainer] epoch #380 | Evaluating... 2025-04-03 06:31:41 | [pearl_trainer] epoch #380 | Sampling for adapation and meta-testing... 2025-04-03 06:32:26 | [pearl_trainer] epoch #380 | Finished meta-testing... 2025-04-03 06:32:26 | [pearl_trainer] epoch #380 | Saving snapshot... 2025-04-03 06:32:28 | [pearl_trainer] epoch #380 | Saved 2025-04-03 06:32:28 | [pearl_trainer] epoch #380 | Time 61423.85 s 2025-04-03 06:32:28 | [pearl_trainer] epoch #380 | EpochTime 155.54 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -111.713 MetaTest/Average/AverageReturn -111.713 MetaTest/Average/Iteration 380 MetaTest/Average/MaxReturn -110.168 MetaTest/Average/MinReturn -114.255 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.81109 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.713 MetaTest/__unnamed_task__/AverageReturn -111.713 MetaTest/__unnamed_task__/Iteration 380 MetaTest/__unnamed_task__/MaxReturn -110.168 MetaTest/__unnamed_task__/MinReturn -114.255 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.81109 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 624600 ------------------------------------------------- ------------ 2025-04-03 06:32:51 | [pearl_trainer] epoch #381 | Training... 2025-04-03 06:34:20 | [pearl_trainer] epoch #381 | Evaluating... 2025-04-03 06:34:20 | [pearl_trainer] epoch #381 | Sampling for adapation and meta-testing... 2025-04-03 06:35:10 | [pearl_trainer] epoch #381 | Finished meta-testing... 2025-04-03 06:35:10 | [pearl_trainer] epoch #381 | Saving snapshot... 2025-04-03 06:35:11 | [pearl_trainer] epoch #381 | Saved 2025-04-03 06:35:11 | [pearl_trainer] epoch #381 | Time 61586.96 s 2025-04-03 06:35:11 | [pearl_trainer] epoch #381 | EpochTime 163.11 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -103.371 MetaTest/Average/AverageReturn -103.371 MetaTest/Average/Iteration 381 MetaTest/Average/MaxReturn -83.3302 MetaTest/Average/MinReturn -113.651 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.1723 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -103.371 MetaTest/__unnamed_task__/AverageReturn -103.371 MetaTest/__unnamed_task__/Iteration 381 MetaTest/__unnamed_task__/MaxReturn -83.3302 MetaTest/__unnamed_task__/MinReturn -113.651 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.1723 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 626200 ------------------------------------------------- ----------- 2025-04-03 06:35:34 | [pearl_trainer] epoch #382 | Training... 2025-04-03 06:37:00 | [pearl_trainer] epoch #382 | Evaluating... 2025-04-03 06:37:00 | [pearl_trainer] epoch #382 | Sampling for adapation and meta-testing... 2025-04-03 06:37:47 | [pearl_trainer] epoch #382 | Finished meta-testing... 2025-04-03 06:37:47 | [pearl_trainer] epoch #382 | Saving snapshot... 2025-04-03 06:37:49 | [pearl_trainer] epoch #382 | Saved 2025-04-03 06:37:49 | [pearl_trainer] epoch #382 | Time 61744.84 s 2025-04-03 06:37:49 | [pearl_trainer] epoch #382 | EpochTime 157.88 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -104.055 MetaTest/Average/AverageReturn -104.055 MetaTest/Average/Iteration 382 MetaTest/Average/MaxReturn -90.3754 MetaTest/Average/MinReturn -119.855 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.1282 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -104.055 MetaTest/__unnamed_task__/AverageReturn -104.055 MetaTest/__unnamed_task__/Iteration 382 MetaTest/__unnamed_task__/MaxReturn -90.3754 MetaTest/__unnamed_task__/MinReturn -119.855 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.1282 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 627800 ------------------------------------------------- ----------- 2025-04-03 06:38:14 | [pearl_trainer] epoch #383 | Training... 2025-04-03 06:39:45 | [pearl_trainer] epoch #383 | Evaluating... 2025-04-03 06:39:45 | [pearl_trainer] epoch #383 | Sampling for adapation and meta-testing... 2025-04-03 06:40:31 | [pearl_trainer] epoch #383 | Finished meta-testing... 2025-04-03 06:40:31 | [pearl_trainer] epoch #383 | Saving snapshot... 2025-04-03 06:40:32 | [pearl_trainer] epoch #383 | Saved 2025-04-03 06:40:32 | [pearl_trainer] epoch #383 | Time 61907.85 s 2025-04-03 06:40:32 | [pearl_trainer] epoch #383 | EpochTime 163.00 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -125.565 MetaTest/Average/AverageReturn -125.565 MetaTest/Average/Iteration 383 MetaTest/Average/MaxReturn -116.95 MetaTest/Average/MinReturn -130.045 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.09293 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -125.565 MetaTest/__unnamed_task__/AverageReturn -125.565 MetaTest/__unnamed_task__/Iteration 383 MetaTest/__unnamed_task__/MaxReturn -116.95 MetaTest/__unnamed_task__/MinReturn -130.045 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.09293 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 629400 ------------------------------------------------- ------------ 2025-04-03 06:40:53 | [pearl_trainer] epoch #384 | Training... 2025-04-03 06:42:29 | [pearl_trainer] epoch #384 | Evaluating... 2025-04-03 06:42:29 | [pearl_trainer] epoch #384 | Sampling for adapation and meta-testing... 2025-04-03 06:43:18 | [pearl_trainer] epoch #384 | Finished meta-testing... 2025-04-03 06:43:18 | [pearl_trainer] epoch #384 | Saving snapshot... 2025-04-03 06:43:19 | [pearl_trainer] epoch #384 | Saved 2025-04-03 06:43:19 | [pearl_trainer] epoch #384 | Time 62074.98 s 2025-04-03 06:43:19 | [pearl_trainer] epoch #384 | EpochTime 167.13 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -119.635 MetaTest/Average/AverageReturn -119.635 MetaTest/Average/Iteration 384 MetaTest/Average/MaxReturn -115.41 MetaTest/Average/MinReturn -124.434 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.70628 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -119.635 MetaTest/__unnamed_task__/AverageReturn -119.635 MetaTest/__unnamed_task__/Iteration 384 MetaTest/__unnamed_task__/MaxReturn -115.41 MetaTest/__unnamed_task__/MinReturn -124.434 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.70628 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 631000 ------------------------------------------------- ------------ 2025-04-03 06:43:41 | [pearl_trainer] epoch #385 | Training... 2025-04-03 06:45:01 | [pearl_trainer] epoch #385 | Evaluating... 2025-04-03 06:45:01 | [pearl_trainer] epoch #385 | Sampling for adapation and meta-testing... 2025-04-03 06:45:53 | [pearl_trainer] epoch #385 | Finished meta-testing... 2025-04-03 06:45:53 | [pearl_trainer] epoch #385 | Saving snapshot... 2025-04-03 06:45:54 | [pearl_trainer] epoch #385 | Saved 2025-04-03 06:45:54 | [pearl_trainer] epoch #385 | Time 62230.49 s 2025-04-03 06:45:54 | [pearl_trainer] epoch #385 | EpochTime 155.51 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -110.476 MetaTest/Average/AverageReturn -110.476 MetaTest/Average/Iteration 385 MetaTest/Average/MaxReturn -91.2532 MetaTest/Average/MinReturn -129.938 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 15.794 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -110.476 MetaTest/__unnamed_task__/AverageReturn -110.476 MetaTest/__unnamed_task__/Iteration 385 MetaTest/__unnamed_task__/MaxReturn -91.2532 MetaTest/__unnamed_task__/MinReturn -129.938 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 15.794 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 632600 ------------------------------------------------- ----------- 2025-04-03 06:46:20 | [pearl_trainer] epoch #386 | Training... 2025-04-03 06:47:47 | [pearl_trainer] epoch #386 | Evaluating... 2025-04-03 06:47:47 | [pearl_trainer] epoch #386 | Sampling for adapation and meta-testing... 2025-04-03 06:48:32 | [pearl_trainer] epoch #386 | Finished meta-testing... 2025-04-03 06:48:32 | [pearl_trainer] epoch #386 | Saving snapshot... 2025-04-03 06:48:33 | [pearl_trainer] epoch #386 | Saved 2025-04-03 06:48:33 | [pearl_trainer] epoch #386 | Time 62389.07 s 2025-04-03 06:48:33 | [pearl_trainer] epoch #386 | EpochTime 158.57 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -112.062 MetaTest/Average/AverageReturn -112.062 MetaTest/Average/Iteration 386 MetaTest/Average/MaxReturn -103.878 MetaTest/Average/MinReturn -127.334 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.8083 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -112.062 MetaTest/__unnamed_task__/AverageReturn -112.062 MetaTest/__unnamed_task__/Iteration 386 MetaTest/__unnamed_task__/MaxReturn -103.878 MetaTest/__unnamed_task__/MinReturn -127.334 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.8083 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 634200 ------------------------------------------------- ----------- 2025-04-03 06:48:54 | [pearl_trainer] epoch #387 | Training... 2025-04-03 06:50:26 | [pearl_trainer] epoch #387 | Evaluating... 2025-04-03 06:50:26 | [pearl_trainer] epoch #387 | Sampling for adapation and meta-testing... 2025-04-03 06:51:17 | [pearl_trainer] epoch #387 | Finished meta-testing... 2025-04-03 06:51:17 | [pearl_trainer] epoch #387 | Saving snapshot... 2025-04-03 06:51:19 | [pearl_trainer] epoch #387 | Saved 2025-04-03 06:51:19 | [pearl_trainer] epoch #387 | Time 62554.91 s 2025-04-03 06:51:19 | [pearl_trainer] epoch #387 | EpochTime 165.84 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -111.337 MetaTest/Average/AverageReturn -111.337 MetaTest/Average/Iteration 387 MetaTest/Average/MaxReturn -87.8897 MetaTest/Average/MinReturn -123.211 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 16.5799 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -111.337 MetaTest/__unnamed_task__/AverageReturn -111.337 MetaTest/__unnamed_task__/Iteration 387 MetaTest/__unnamed_task__/MaxReturn -87.8897 MetaTest/__unnamed_task__/MinReturn -123.211 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 16.5799 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 635800 ------------------------------------------------- ----------- 2025-04-03 06:51:40 | [pearl_trainer] epoch #388 | Training... 2025-04-03 06:53:07 | [pearl_trainer] epoch #388 | Evaluating... 2025-04-03 06:53:07 | [pearl_trainer] epoch #388 | Sampling for adapation and meta-testing... 2025-04-03 06:54:01 | [pearl_trainer] epoch #388 | Finished meta-testing... 2025-04-03 06:54:01 | [pearl_trainer] epoch #388 | Saving snapshot... 2025-04-03 06:54:02 | [pearl_trainer] epoch #388 | Saved 2025-04-03 06:54:02 | [pearl_trainer] epoch #388 | Time 62718.31 s 2025-04-03 06:54:02 | [pearl_trainer] epoch #388 | EpochTime 163.39 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -104.973 MetaTest/Average/AverageReturn -104.973 MetaTest/Average/Iteration 388 MetaTest/Average/MaxReturn -95.822 MetaTest/Average/MinReturn -111.69 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.70266 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -104.973 MetaTest/__unnamed_task__/AverageReturn -104.973 MetaTest/__unnamed_task__/Iteration 388 MetaTest/__unnamed_task__/MaxReturn -95.822 MetaTest/__unnamed_task__/MinReturn -111.69 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.70266 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 637400 ------------------------------------------------- ------------ 2025-04-03 06:54:29 | [pearl_trainer] epoch #389 | Training... 2025-04-03 06:56:09 | [pearl_trainer] epoch #389 | Evaluating... 2025-04-03 06:56:09 | [pearl_trainer] epoch #389 | Sampling for adapation and meta-testing... 2025-04-03 06:56:55 | [pearl_trainer] epoch #389 | Finished meta-testing... 2025-04-03 06:56:55 | [pearl_trainer] epoch #389 | Saving snapshot... 2025-04-03 06:56:56 | [pearl_trainer] epoch #389 | Saved 2025-04-03 06:56:56 | [pearl_trainer] epoch #389 | Time 62891.83 s 2025-04-03 06:56:56 | [pearl_trainer] epoch #389 | EpochTime 173.52 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -104.911 MetaTest/Average/AverageReturn -104.911 MetaTest/Average/Iteration 389 MetaTest/Average/MaxReturn -97.4318 MetaTest/Average/MinReturn -109.522 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.33631 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -104.911 MetaTest/__unnamed_task__/AverageReturn -104.911 MetaTest/__unnamed_task__/Iteration 389 MetaTest/__unnamed_task__/MaxReturn -97.4318 MetaTest/__unnamed_task__/MinReturn -109.522 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.33631 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 639000 ------------------------------------------------- ------------ 2025-04-03 06:57:18 | [pearl_trainer] epoch #390 | Training... 2025-04-03 06:58:49 | [pearl_trainer] epoch #390 | Evaluating... 2025-04-03 06:58:49 | [pearl_trainer] epoch #390 | Sampling for adapation and meta-testing... 2025-04-03 06:59:38 | [pearl_trainer] epoch #390 | Finished meta-testing... 2025-04-03 06:59:38 | [pearl_trainer] epoch #390 | Saving snapshot... 2025-04-03 06:59:40 | [pearl_trainer] epoch #390 | Saved 2025-04-03 06:59:40 | [pearl_trainer] epoch #390 | Time 63056.09 s 2025-04-03 06:59:40 | [pearl_trainer] epoch #390 | EpochTime 164.25 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -119.267 MetaTest/Average/AverageReturn -119.267 MetaTest/Average/Iteration 390 MetaTest/Average/MaxReturn -112.789 MetaTest/Average/MinReturn -123.558 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.66045 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -119.267 MetaTest/__unnamed_task__/AverageReturn -119.267 MetaTest/__unnamed_task__/Iteration 390 MetaTest/__unnamed_task__/MaxReturn -112.789 MetaTest/__unnamed_task__/MinReturn -123.558 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.66045 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 640600 ------------------------------------------------- ------------ 2025-04-03 07:00:02 | [pearl_trainer] epoch #391 | Training... 2025-04-03 07:01:28 | [pearl_trainer] epoch #391 | Evaluating... 2025-04-03 07:01:28 | [pearl_trainer] epoch #391 | Sampling for adapation and meta-testing... 2025-04-03 07:02:18 | [pearl_trainer] epoch #391 | Finished meta-testing... 2025-04-03 07:02:18 | [pearl_trainer] epoch #391 | Saving snapshot... 2025-04-03 07:02:19 | [pearl_trainer] epoch #391 | Saved 2025-04-03 07:02:19 | [pearl_trainer] epoch #391 | Time 63214.97 s 2025-04-03 07:02:19 | [pearl_trainer] epoch #391 | EpochTime 158.88 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -137.082 MetaTest/Average/AverageReturn -137.082 MetaTest/Average/Iteration 391 MetaTest/Average/MaxReturn -122.529 MetaTest/Average/MinReturn -146.411 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.4258 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -137.082 MetaTest/__unnamed_task__/AverageReturn -137.082 MetaTest/__unnamed_task__/Iteration 391 MetaTest/__unnamed_task__/MaxReturn -122.529 MetaTest/__unnamed_task__/MinReturn -146.411 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.4258 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 642200 ------------------------------------------------- ----------- 2025-04-03 07:02:42 | [pearl_trainer] epoch #392 | Training... 2025-04-03 07:04:15 | [pearl_trainer] epoch #392 | Evaluating... 2025-04-03 07:04:15 | [pearl_trainer] epoch #392 | Sampling for adapation and meta-testing... 2025-04-03 07:05:01 | [pearl_trainer] epoch #392 | Finished meta-testing... 2025-04-03 07:05:01 | [pearl_trainer] epoch #392 | Saving snapshot... 2025-04-03 07:05:02 | [pearl_trainer] epoch #392 | Saved 2025-04-03 07:05:02 | [pearl_trainer] epoch #392 | Time 63378.20 s 2025-04-03 07:05:02 | [pearl_trainer] epoch #392 | EpochTime 163.23 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -117.674 MetaTest/Average/AverageReturn -117.674 MetaTest/Average/Iteration 392 MetaTest/Average/MaxReturn -104.93 MetaTest/Average/MinReturn -132.205 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.2064 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -117.674 MetaTest/__unnamed_task__/AverageReturn -117.674 MetaTest/__unnamed_task__/Iteration 392 MetaTest/__unnamed_task__/MaxReturn -104.93 MetaTest/__unnamed_task__/MinReturn -132.205 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.2064 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 643800 ------------------------------------------------- ----------- 2025-04-03 07:05:24 | [pearl_trainer] epoch #393 | Training... 2025-04-03 07:07:01 | [pearl_trainer] epoch #393 | Evaluating... 2025-04-03 07:07:01 | [pearl_trainer] epoch #393 | Sampling for adapation and meta-testing... 2025-04-03 07:07:46 | [pearl_trainer] epoch #393 | Finished meta-testing... 2025-04-03 07:07:46 | [pearl_trainer] epoch #393 | Saving snapshot... 2025-04-03 07:07:47 | [pearl_trainer] epoch #393 | Saved 2025-04-03 07:07:47 | [pearl_trainer] epoch #393 | Time 63543.26 s 2025-04-03 07:07:47 | [pearl_trainer] epoch #393 | EpochTime 165.07 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -99.8276 MetaTest/Average/AverageReturn -99.8276 MetaTest/Average/Iteration 393 MetaTest/Average/MaxReturn -88.176 MetaTest/Average/MinReturn -116.543 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.122 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -99.8276 MetaTest/__unnamed_task__/AverageReturn -99.8276 MetaTest/__unnamed_task__/Iteration 393 MetaTest/__unnamed_task__/MaxReturn -88.176 MetaTest/__unnamed_task__/MinReturn -116.543 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.122 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 645400 ------------------------------------------------- ----------- 2025-04-03 07:08:09 | [pearl_trainer] epoch #394 | Training... 2025-04-03 07:09:33 | [pearl_trainer] epoch #394 | Evaluating... 2025-04-03 07:09:33 | [pearl_trainer] epoch #394 | Sampling for adapation and meta-testing... 2025-04-03 07:10:30 | [pearl_trainer] epoch #394 | Finished meta-testing... 2025-04-03 07:10:30 | [pearl_trainer] epoch #394 | Saving snapshot... 2025-04-03 07:10:31 | [pearl_trainer] epoch #394 | Saved 2025-04-03 07:10:31 | [pearl_trainer] epoch #394 | Time 63707.16 s 2025-04-03 07:10:31 | [pearl_trainer] epoch #394 | EpochTime 163.89 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -109 MetaTest/Average/AverageReturn -109 MetaTest/Average/Iteration 394 MetaTest/Average/MaxReturn -104.152 MetaTest/Average/MinReturn -111.468 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.42838 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -109 MetaTest/__unnamed_task__/AverageReturn -109 MetaTest/__unnamed_task__/Iteration 394 MetaTest/__unnamed_task__/MaxReturn -104.152 MetaTest/__unnamed_task__/MinReturn -111.468 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.42838 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 647000 ------------------------------------------------- ------------ 2025-04-03 07:10:54 | [pearl_trainer] epoch #395 | Training... 2025-04-03 07:12:18 | [pearl_trainer] epoch #395 | Evaluating... 2025-04-03 07:12:18 | [pearl_trainer] epoch #395 | Sampling for adapation and meta-testing... 2025-04-03 07:13:07 | [pearl_trainer] epoch #395 | Finished meta-testing... 2025-04-03 07:13:07 | [pearl_trainer] epoch #395 | Saving snapshot... 2025-04-03 07:13:08 | [pearl_trainer] epoch #395 | Saved 2025-04-03 07:13:08 | [pearl_trainer] epoch #395 | Time 63864.33 s 2025-04-03 07:13:08 | [pearl_trainer] epoch #395 | EpochTime 157.17 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -104.95 MetaTest/Average/AverageReturn -104.95 MetaTest/Average/Iteration 395 MetaTest/Average/MaxReturn -99.9298 MetaTest/Average/MinReturn -111.223 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.69487 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -104.95 MetaTest/__unnamed_task__/AverageReturn -104.95 MetaTest/__unnamed_task__/Iteration 395 MetaTest/__unnamed_task__/MaxReturn -99.9298 MetaTest/__unnamed_task__/MinReturn -111.223 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.69487 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 648600 ------------------------------------------------- ------------ 2025-04-03 07:13:32 | [pearl_trainer] epoch #396 | Training... 2025-04-03 07:15:01 | [pearl_trainer] epoch #396 | Evaluating... 2025-04-03 07:15:01 | [pearl_trainer] epoch #396 | Sampling for adapation and meta-testing... 2025-04-03 07:15:47 | [pearl_trainer] epoch #396 | Finished meta-testing... 2025-04-03 07:15:47 | [pearl_trainer] epoch #396 | Saving snapshot... 2025-04-03 07:15:48 | [pearl_trainer] epoch #396 | Saved 2025-04-03 07:15:48 | [pearl_trainer] epoch #396 | Time 64023.83 s 2025-04-03 07:15:48 | [pearl_trainer] epoch #396 | EpochTime 159.49 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -92.4523 MetaTest/Average/AverageReturn -92.4523 MetaTest/Average/Iteration 396 MetaTest/Average/MaxReturn -87.5742 MetaTest/Average/MinReturn -100.22 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.55258 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.4523 MetaTest/__unnamed_task__/AverageReturn -92.4523 MetaTest/__unnamed_task__/Iteration 396 MetaTest/__unnamed_task__/MaxReturn -87.5742 MetaTest/__unnamed_task__/MinReturn -100.22 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.55258 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 650200 ------------------------------------------------- ------------ 2025-04-03 07:16:10 | [pearl_trainer] epoch #397 | Training... 2025-04-03 07:17:36 | [pearl_trainer] epoch #397 | Evaluating... 2025-04-03 07:17:36 | [pearl_trainer] epoch #397 | Sampling for adapation and meta-testing... 2025-04-03 07:18:26 | [pearl_trainer] epoch #397 | Finished meta-testing... 2025-04-03 07:18:26 | [pearl_trainer] epoch #397 | Saving snapshot... 2025-04-03 07:18:27 | [pearl_trainer] epoch #397 | Saved 2025-04-03 07:18:27 | [pearl_trainer] epoch #397 | Time 64183.10 s 2025-04-03 07:18:27 | [pearl_trainer] epoch #397 | EpochTime 159.28 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -112.618 MetaTest/Average/AverageReturn -112.618 MetaTest/Average/Iteration 397 MetaTest/Average/MaxReturn -91.4374 MetaTest/Average/MinReturn -133.313 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 17.0991 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -112.618 MetaTest/__unnamed_task__/AverageReturn -112.618 MetaTest/__unnamed_task__/Iteration 397 MetaTest/__unnamed_task__/MaxReturn -91.4374 MetaTest/__unnamed_task__/MinReturn -133.313 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 17.0991 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 651800 ------------------------------------------------- ----------- 2025-04-03 07:18:50 | [pearl_trainer] epoch #398 | Training... 2025-04-03 07:20:21 | [pearl_trainer] epoch #398 | Evaluating... 2025-04-03 07:20:21 | [pearl_trainer] epoch #398 | Sampling for adapation and meta-testing... 2025-04-03 07:21:05 | [pearl_trainer] epoch #398 | Finished meta-testing... 2025-04-03 07:21:05 | [pearl_trainer] epoch #398 | Saving snapshot... 2025-04-03 07:21:06 | [pearl_trainer] epoch #398 | Saved 2025-04-03 07:21:06 | [pearl_trainer] epoch #398 | Time 64342.54 s 2025-04-03 07:21:06 | [pearl_trainer] epoch #398 | EpochTime 159.43 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -86.1982 MetaTest/Average/AverageReturn -86.1982 MetaTest/Average/Iteration 398 MetaTest/Average/MaxReturn -82.8855 MetaTest/Average/MinReturn -91.4067 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.72813 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -86.1982 MetaTest/__unnamed_task__/AverageReturn -86.1982 MetaTest/__unnamed_task__/Iteration 398 MetaTest/__unnamed_task__/MaxReturn -82.8855 MetaTest/__unnamed_task__/MinReturn -91.4067 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.72813 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 653400 ------------------------------------------------- ------------ 2025-04-03 07:21:28 | [pearl_trainer] epoch #399 | Training... 2025-04-03 07:23:08 | [pearl_trainer] epoch #399 | Evaluating... 2025-04-03 07:23:08 | [pearl_trainer] epoch #399 | Sampling for adapation and meta-testing... 2025-04-03 07:23:55 | [pearl_trainer] epoch #399 | Finished meta-testing... 2025-04-03 07:23:55 | [pearl_trainer] epoch #399 | Saving snapshot... 2025-04-03 07:23:56 | [pearl_trainer] epoch #399 | Saved 2025-04-03 07:23:56 | [pearl_trainer] epoch #399 | Time 64512.69 s 2025-04-03 07:23:56 | [pearl_trainer] epoch #399 | EpochTime 170.15 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -100.141 MetaTest/Average/AverageReturn -100.141 MetaTest/Average/Iteration 399 MetaTest/Average/MaxReturn -89.111 MetaTest/Average/MinReturn -105.711 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.7998 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -100.141 MetaTest/__unnamed_task__/AverageReturn -100.141 MetaTest/__unnamed_task__/Iteration 399 MetaTest/__unnamed_task__/MaxReturn -89.111 MetaTest/__unnamed_task__/MinReturn -105.711 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.7998 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 655000 ------------------------------------------------- ----------- 2025-04-03 07:24:18 | [pearl_trainer] epoch #400 | Training... 2025-04-03 07:25:46 | [pearl_trainer] epoch #400 | Evaluating... 2025-04-03 07:25:46 | [pearl_trainer] epoch #400 | Sampling for adapation and meta-testing... 2025-04-03 07:26:43 | [pearl_trainer] epoch #400 | Finished meta-testing... 2025-04-03 07:26:43 | [pearl_trainer] epoch #400 | Saving snapshot... 2025-04-03 07:26:44 | [pearl_trainer] epoch #400 | Saved 2025-04-03 07:26:44 | [pearl_trainer] epoch #400 | Time 64680.43 s 2025-04-03 07:26:44 | [pearl_trainer] epoch #400 | EpochTime 167.74 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -101.722 MetaTest/Average/AverageReturn -101.722 MetaTest/Average/Iteration 400 MetaTest/Average/MaxReturn -90.1269 MetaTest/Average/MinReturn -113.026 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.35074 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.722 MetaTest/__unnamed_task__/AverageReturn -101.722 MetaTest/__unnamed_task__/Iteration 400 MetaTest/__unnamed_task__/MaxReturn -90.1269 MetaTest/__unnamed_task__/MinReturn -113.026 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.35074 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 656600 ------------------------------------------------- ------------ 2025-04-03 07:27:11 | [pearl_trainer] epoch #401 | Training... 2025-04-03 07:28:42 | [pearl_trainer] epoch #401 | Evaluating... 2025-04-03 07:28:42 | [pearl_trainer] epoch #401 | Sampling for adapation and meta-testing... 2025-04-03 07:29:28 | [pearl_trainer] epoch #401 | Finished meta-testing... 2025-04-03 07:29:28 | [pearl_trainer] epoch #401 | Saving snapshot... 2025-04-03 07:29:29 | [pearl_trainer] epoch #401 | Saved 2025-04-03 07:29:29 | [pearl_trainer] epoch #401 | Time 64845.11 s 2025-04-03 07:29:29 | [pearl_trainer] epoch #401 | EpochTime 164.68 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.1043 MetaTest/Average/AverageReturn -97.1043 MetaTest/Average/Iteration 401 MetaTest/Average/MaxReturn -88.4051 MetaTest/Average/MinReturn -106.731 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.51005 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.1043 MetaTest/__unnamed_task__/AverageReturn -97.1043 MetaTest/__unnamed_task__/Iteration 401 MetaTest/__unnamed_task__/MaxReturn -88.4051 MetaTest/__unnamed_task__/MinReturn -106.731 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.51005 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 658200 ------------------------------------------------- ------------ 2025-04-03 07:29:51 | [pearl_trainer] epoch #402 | Training... 2025-04-03 07:31:29 | [pearl_trainer] epoch #402 | Evaluating... 2025-04-03 07:31:29 | [pearl_trainer] epoch #402 | Sampling for adapation and meta-testing... 2025-04-03 07:32:15 | [pearl_trainer] epoch #402 | Finished meta-testing... 2025-04-03 07:32:15 | [pearl_trainer] epoch #402 | Saving snapshot... 2025-04-03 07:32:16 | [pearl_trainer] epoch #402 | Saved 2025-04-03 07:32:16 | [pearl_trainer] epoch #402 | Time 65012.28 s 2025-04-03 07:32:16 | [pearl_trainer] epoch #402 | EpochTime 167.17 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -91.7753 MetaTest/Average/AverageReturn -91.7753 MetaTest/Average/Iteration 402 MetaTest/Average/MaxReturn -82.1475 MetaTest/Average/MinReturn -98.1906 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.93228 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.7753 MetaTest/__unnamed_task__/AverageReturn -91.7753 MetaTest/__unnamed_task__/Iteration 402 MetaTest/__unnamed_task__/MaxReturn -82.1475 MetaTest/__unnamed_task__/MinReturn -98.1906 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.93228 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 659800 ------------------------------------------------- ------------ 2025-04-03 07:32:38 | [pearl_trainer] epoch #403 | Training... 2025-04-03 07:34:02 | [pearl_trainer] epoch #403 | Evaluating... 2025-04-03 07:34:02 | [pearl_trainer] epoch #403 | Sampling for adapation and meta-testing... 2025-04-03 07:34:53 | [pearl_trainer] epoch #403 | Finished meta-testing... 2025-04-03 07:34:53 | [pearl_trainer] epoch #403 | Saving snapshot... 2025-04-03 07:34:54 | [pearl_trainer] epoch #403 | Saved 2025-04-03 07:34:54 | [pearl_trainer] epoch #403 | Time 65170.66 s 2025-04-03 07:34:54 | [pearl_trainer] epoch #403 | EpochTime 158.38 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -90.2202 MetaTest/Average/AverageReturn -90.2202 MetaTest/Average/Iteration 403 MetaTest/Average/MaxReturn -77.962 MetaTest/Average/MinReturn -103.965 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.6675 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.2202 MetaTest/__unnamed_task__/AverageReturn -90.2202 MetaTest/__unnamed_task__/Iteration 403 MetaTest/__unnamed_task__/MaxReturn -77.962 MetaTest/__unnamed_task__/MinReturn -103.965 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.6675 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 661400 ------------------------------------------------- ----------- 2025-04-03 07:35:21 | [pearl_trainer] epoch #404 | Training... 2025-04-03 07:36:42 | [pearl_trainer] epoch #404 | Evaluating... 2025-04-03 07:36:42 | [pearl_trainer] epoch #404 | Sampling for adapation and meta-testing... 2025-04-03 07:37:29 | [pearl_trainer] epoch #404 | Finished meta-testing... 2025-04-03 07:37:29 | [pearl_trainer] epoch #404 | Saving snapshot... 2025-04-03 07:37:30 | [pearl_trainer] epoch #404 | Saved 2025-04-03 07:37:30 | [pearl_trainer] epoch #404 | Time 65325.90 s 2025-04-03 07:37:30 | [pearl_trainer] epoch #404 | EpochTime 155.24 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -99.3924 MetaTest/Average/AverageReturn -99.3924 MetaTest/Average/Iteration 404 MetaTest/Average/MaxReturn -95.7638 MetaTest/Average/MinReturn -104.695 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.83375 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -99.3924 MetaTest/__unnamed_task__/AverageReturn -99.3924 MetaTest/__unnamed_task__/Iteration 404 MetaTest/__unnamed_task__/MaxReturn -95.7638 MetaTest/__unnamed_task__/MinReturn -104.695 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.83375 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 663000 ------------------------------------------------- ------------ 2025-04-03 07:37:54 | [pearl_trainer] epoch #405 | Training... 2025-04-03 07:39:30 | [pearl_trainer] epoch #405 | Evaluating... 2025-04-03 07:39:30 | [pearl_trainer] epoch #405 | Sampling for adapation and meta-testing... 2025-04-03 07:40:16 | [pearl_trainer] epoch #405 | Finished meta-testing... 2025-04-03 07:40:16 | [pearl_trainer] epoch #405 | Saving snapshot... 2025-04-03 07:40:18 | [pearl_trainer] epoch #405 | Saved 2025-04-03 07:40:18 | [pearl_trainer] epoch #405 | Time 65493.91 s 2025-04-03 07:40:18 | [pearl_trainer] epoch #405 | EpochTime 168.01 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -92.8706 MetaTest/Average/AverageReturn -92.8706 MetaTest/Average/Iteration 405 MetaTest/Average/MaxReturn -82.5156 MetaTest/Average/MinReturn -99.9117 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.47847 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.8706 MetaTest/__unnamed_task__/AverageReturn -92.8706 MetaTest/__unnamed_task__/Iteration 405 MetaTest/__unnamed_task__/MaxReturn -82.5156 MetaTest/__unnamed_task__/MinReturn -99.9117 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.47847 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 664600 ------------------------------------------------- ------------ 2025-04-03 07:40:40 | [pearl_trainer] epoch #406 | Training... 2025-04-03 07:42:09 | [pearl_trainer] epoch #406 | Evaluating... 2025-04-03 07:42:09 | [pearl_trainer] epoch #406 | Sampling for adapation and meta-testing... 2025-04-03 07:42:59 | [pearl_trainer] epoch #406 | Finished meta-testing... 2025-04-03 07:42:59 | [pearl_trainer] epoch #406 | Saving snapshot... 2025-04-03 07:43:00 | [pearl_trainer] epoch #406 | Saved 2025-04-03 07:43:00 | [pearl_trainer] epoch #406 | Time 65656.61 s 2025-04-03 07:43:00 | [pearl_trainer] epoch #406 | EpochTime 162.69 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -99.7121 MetaTest/Average/AverageReturn -99.7121 MetaTest/Average/Iteration 406 MetaTest/Average/MaxReturn -92.9929 MetaTest/Average/MinReturn -108.073 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.26518 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -99.7121 MetaTest/__unnamed_task__/AverageReturn -99.7121 MetaTest/__unnamed_task__/Iteration 406 MetaTest/__unnamed_task__/MaxReturn -92.9929 MetaTest/__unnamed_task__/MinReturn -108.073 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.26518 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 666200 ------------------------------------------------- ------------ 2025-04-03 07:43:23 | [pearl_trainer] epoch #407 | Training... 2025-04-03 07:44:48 | [pearl_trainer] epoch #407 | Evaluating... 2025-04-03 07:44:48 | [pearl_trainer] epoch #407 | Sampling for adapation and meta-testing... 2025-04-03 07:45:36 | [pearl_trainer] epoch #407 | Finished meta-testing... 2025-04-03 07:45:36 | [pearl_trainer] epoch #407 | Saving snapshot... 2025-04-03 07:45:37 | [pearl_trainer] epoch #407 | Saved 2025-04-03 07:45:37 | [pearl_trainer] epoch #407 | Time 65813.44 s 2025-04-03 07:45:37 | [pearl_trainer] epoch #407 | EpochTime 156.83 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -106.488 MetaTest/Average/AverageReturn -106.488 MetaTest/Average/Iteration 407 MetaTest/Average/MaxReturn -103.504 MetaTest/Average/MinReturn -109.157 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.31851 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -106.488 MetaTest/__unnamed_task__/AverageReturn -106.488 MetaTest/__unnamed_task__/Iteration 407 MetaTest/__unnamed_task__/MaxReturn -103.504 MetaTest/__unnamed_task__/MinReturn -109.157 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.31851 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 667800 ------------------------------------------------- ------------ 2025-04-03 07:46:01 | [pearl_trainer] epoch #408 | Training... 2025-04-03 07:47:27 | [pearl_trainer] epoch #408 | Evaluating... 2025-04-03 07:47:27 | [pearl_trainer] epoch #408 | Sampling for adapation and meta-testing... 2025-04-03 07:48:13 | [pearl_trainer] epoch #408 | Finished meta-testing... 2025-04-03 07:48:13 | [pearl_trainer] epoch #408 | Saving snapshot... 2025-04-03 07:48:14 | [pearl_trainer] epoch #408 | Saved 2025-04-03 07:48:14 | [pearl_trainer] epoch #408 | Time 65970.24 s 2025-04-03 07:48:14 | [pearl_trainer] epoch #408 | EpochTime 156.80 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -86.9524 MetaTest/Average/AverageReturn -86.9524 MetaTest/Average/Iteration 408 MetaTest/Average/MaxReturn -84.8475 MetaTest/Average/MinReturn -88.4145 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.52549 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -86.9524 MetaTest/__unnamed_task__/AverageReturn -86.9524 MetaTest/__unnamed_task__/Iteration 408 MetaTest/__unnamed_task__/MaxReturn -84.8475 MetaTest/__unnamed_task__/MinReturn -88.4145 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.52549 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 669400 ------------------------------------------------- ------------ 2025-04-03 07:48:37 | [pearl_trainer] epoch #409 | Training... 2025-04-03 07:50:06 | [pearl_trainer] epoch #409 | Evaluating... 2025-04-03 07:50:06 | [pearl_trainer] epoch #409 | Sampling for adapation and meta-testing... 2025-04-03 07:50:56 | [pearl_trainer] epoch #409 | Finished meta-testing... 2025-04-03 07:50:56 | [pearl_trainer] epoch #409 | Saving snapshot... 2025-04-03 07:50:57 | [pearl_trainer] epoch #409 | Saved 2025-04-03 07:50:57 | [pearl_trainer] epoch #409 | Time 66133.37 s 2025-04-03 07:50:57 | [pearl_trainer] epoch #409 | EpochTime 163.13 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -88.3413 MetaTest/Average/AverageReturn -88.3413 MetaTest/Average/Iteration 409 MetaTest/Average/MaxReturn -83.9861 MetaTest/Average/MinReturn -93.0563 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.71161 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.3413 MetaTest/__unnamed_task__/AverageReturn -88.3413 MetaTest/__unnamed_task__/Iteration 409 MetaTest/__unnamed_task__/MaxReturn -83.9861 MetaTest/__unnamed_task__/MinReturn -93.0563 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.71161 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 671000 ------------------------------------------------- ------------ 2025-04-03 07:51:19 | [pearl_trainer] epoch #410 | Training... 2025-04-03 07:52:47 | [pearl_trainer] epoch #410 | Evaluating... 2025-04-03 07:52:47 | [pearl_trainer] epoch #410 | Sampling for adapation and meta-testing... 2025-04-03 07:53:32 | [pearl_trainer] epoch #410 | Finished meta-testing... 2025-04-03 07:53:32 | [pearl_trainer] epoch #410 | Saving snapshot... 2025-04-03 07:53:34 | [pearl_trainer] epoch #410 | Saved 2025-04-03 07:53:34 | [pearl_trainer] epoch #410 | Time 66289.90 s 2025-04-03 07:53:34 | [pearl_trainer] epoch #410 | EpochTime 156.53 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -95.3409 MetaTest/Average/AverageReturn -95.3409 MetaTest/Average/Iteration 410 MetaTest/Average/MaxReturn -75.6086 MetaTest/Average/MinReturn -109.011 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.2943 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.3409 MetaTest/__unnamed_task__/AverageReturn -95.3409 MetaTest/__unnamed_task__/Iteration 410 MetaTest/__unnamed_task__/MaxReturn -75.6086 MetaTest/__unnamed_task__/MinReturn -109.011 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.2943 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 672600 ------------------------------------------------- ----------- 2025-04-03 07:53:57 | [pearl_trainer] epoch #411 | Training... 2025-04-03 07:55:31 | [pearl_trainer] epoch #411 | Evaluating... 2025-04-03 07:55:31 | [pearl_trainer] epoch #411 | Sampling for adapation and meta-testing... 2025-04-03 07:56:16 | [pearl_trainer] epoch #411 | Finished meta-testing... 2025-04-03 07:56:16 | [pearl_trainer] epoch #411 | Saving snapshot... 2025-04-03 07:56:17 | [pearl_trainer] epoch #411 | Saved 2025-04-03 07:56:17 | [pearl_trainer] epoch #411 | Time 66453.52 s 2025-04-03 07:56:17 | [pearl_trainer] epoch #411 | EpochTime 163.62 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -84.4647 MetaTest/Average/AverageReturn -84.4647 MetaTest/Average/Iteration 411 MetaTest/Average/MaxReturn -81.1886 MetaTest/Average/MinReturn -89.6448 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.70549 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -84.4647 MetaTest/__unnamed_task__/AverageReturn -84.4647 MetaTest/__unnamed_task__/Iteration 411 MetaTest/__unnamed_task__/MaxReturn -81.1886 MetaTest/__unnamed_task__/MinReturn -89.6448 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.70549 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 674200 ------------------------------------------------- ------------ 2025-04-03 07:56:39 | [pearl_trainer] epoch #412 | Training... 2025-04-03 07:58:16 | [pearl_trainer] epoch #412 | Evaluating... 2025-04-03 07:58:16 | [pearl_trainer] epoch #412 | Sampling for adapation and meta-testing... 2025-04-03 07:59:15 | [pearl_trainer] epoch #412 | Finished meta-testing... 2025-04-03 07:59:15 | [pearl_trainer] epoch #412 | Saving snapshot... 2025-04-03 07:59:16 | [pearl_trainer] epoch #412 | Saved 2025-04-03 07:59:16 | [pearl_trainer] epoch #412 | Time 66632.37 s 2025-04-03 07:59:16 | [pearl_trainer] epoch #412 | EpochTime 178.85 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -92.0846 MetaTest/Average/AverageReturn -92.0846 MetaTest/Average/Iteration 412 MetaTest/Average/MaxReturn -81.1355 MetaTest/Average/MinReturn -109.75 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.6102 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.0846 MetaTest/__unnamed_task__/AverageReturn -92.0846 MetaTest/__unnamed_task__/Iteration 412 MetaTest/__unnamed_task__/MaxReturn -81.1355 MetaTest/__unnamed_task__/MinReturn -109.75 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.6102 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 675800 ------------------------------------------------- ----------- 2025-04-03 07:59:39 | [pearl_trainer] epoch #413 | Training... 2025-04-03 08:01:05 | [pearl_trainer] epoch #413 | Evaluating... 2025-04-03 08:01:05 | [pearl_trainer] epoch #413 | Sampling for adapation and meta-testing... 2025-04-03 08:01:55 | [pearl_trainer] epoch #413 | Finished meta-testing... 2025-04-03 08:01:55 | [pearl_trainer] epoch #413 | Saving snapshot... 2025-04-03 08:01:56 | [pearl_trainer] epoch #413 | Saved 2025-04-03 08:01:56 | [pearl_trainer] epoch #413 | Time 66792.64 s 2025-04-03 08:01:56 | [pearl_trainer] epoch #413 | EpochTime 160.27 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -86.2512 MetaTest/Average/AverageReturn -86.2512 MetaTest/Average/Iteration 413 MetaTest/Average/MaxReturn -76.9493 MetaTest/Average/MinReturn -95.5561 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.59617 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -86.2512 MetaTest/__unnamed_task__/AverageReturn -86.2512 MetaTest/__unnamed_task__/Iteration 413 MetaTest/__unnamed_task__/MaxReturn -76.9493 MetaTest/__unnamed_task__/MinReturn -95.5561 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.59617 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 677400 ------------------------------------------------- ------------ 2025-04-03 08:02:20 | [pearl_trainer] epoch #414 | Training... 2025-04-03 08:03:45 | [pearl_trainer] epoch #414 | Evaluating... 2025-04-03 08:03:45 | [pearl_trainer] epoch #414 | Sampling for adapation and meta-testing... 2025-04-03 08:04:31 | [pearl_trainer] epoch #414 | Finished meta-testing... 2025-04-03 08:04:31 | [pearl_trainer] epoch #414 | Saving snapshot... 2025-04-03 08:04:32 | [pearl_trainer] epoch #414 | Saved 2025-04-03 08:04:32 | [pearl_trainer] epoch #414 | Time 66948.36 s 2025-04-03 08:04:32 | [pearl_trainer] epoch #414 | EpochTime 155.72 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.7363 MetaTest/Average/AverageReturn -90.7363 MetaTest/Average/Iteration 414 MetaTest/Average/MaxReturn -87.0462 MetaTest/Average/MinReturn -93.9959 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.85348 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.7363 MetaTest/__unnamed_task__/AverageReturn -90.7363 MetaTest/__unnamed_task__/Iteration 414 MetaTest/__unnamed_task__/MaxReturn -87.0462 MetaTest/__unnamed_task__/MinReturn -93.9959 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.85348 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 679000 ------------------------------------------------- ------------ 2025-04-03 08:04:55 | [pearl_trainer] epoch #415 | Training... 2025-04-03 08:06:26 | [pearl_trainer] epoch #415 | Evaluating... 2025-04-03 08:06:26 | [pearl_trainer] epoch #415 | Sampling for adapation and meta-testing... 2025-04-03 08:07:16 | [pearl_trainer] epoch #415 | Finished meta-testing... 2025-04-03 08:07:16 | [pearl_trainer] epoch #415 | Saving snapshot... 2025-04-03 08:07:18 | [pearl_trainer] epoch #415 | Saved 2025-04-03 08:07:18 | [pearl_trainer] epoch #415 | Time 67114.06 s 2025-04-03 08:07:18 | [pearl_trainer] epoch #415 | EpochTime 165.70 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -81.5692 MetaTest/Average/AverageReturn -81.5692 MetaTest/Average/Iteration 415 MetaTest/Average/MaxReturn -78.2442 MetaTest/Average/MinReturn -84.1554 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.46911 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -81.5692 MetaTest/__unnamed_task__/AverageReturn -81.5692 MetaTest/__unnamed_task__/Iteration 415 MetaTest/__unnamed_task__/MaxReturn -78.2442 MetaTest/__unnamed_task__/MinReturn -84.1554 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.46911 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 680600 ------------------------------------------------- ------------ 2025-04-03 08:07:43 | [pearl_trainer] epoch #416 | Training... 2025-04-03 08:09:06 | [pearl_trainer] epoch #416 | Evaluating... 2025-04-03 08:09:06 | [pearl_trainer] epoch #416 | Sampling for adapation and meta-testing... 2025-04-03 08:09:52 | [pearl_trainer] epoch #416 | Finished meta-testing... 2025-04-03 08:09:52 | [pearl_trainer] epoch #416 | Saving snapshot... 2025-04-03 08:09:53 | [pearl_trainer] epoch #416 | Saved 2025-04-03 08:09:53 | [pearl_trainer] epoch #416 | Time 67269.07 s 2025-04-03 08:09:53 | [pearl_trainer] epoch #416 | EpochTime 155.00 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -92.5602 MetaTest/Average/AverageReturn -92.5602 MetaTest/Average/Iteration 416 MetaTest/Average/MaxReturn -86.1256 MetaTest/Average/MinReturn -99.7467 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.58617 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.5602 MetaTest/__unnamed_task__/AverageReturn -92.5602 MetaTest/__unnamed_task__/Iteration 416 MetaTest/__unnamed_task__/MaxReturn -86.1256 MetaTest/__unnamed_task__/MinReturn -99.7467 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.58617 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 682200 ------------------------------------------------- ------------ 2025-04-03 08:10:17 | [pearl_trainer] epoch #417 | Training... 2025-04-03 08:11:49 | [pearl_trainer] epoch #417 | Evaluating... 2025-04-03 08:11:49 | [pearl_trainer] epoch #417 | Sampling for adapation and meta-testing... 2025-04-03 08:12:35 | [pearl_trainer] epoch #417 | Finished meta-testing... 2025-04-03 08:12:35 | [pearl_trainer] epoch #417 | Saving snapshot... 2025-04-03 08:12:36 | [pearl_trainer] epoch #417 | Saved 2025-04-03 08:12:36 | [pearl_trainer] epoch #417 | Time 67431.91 s 2025-04-03 08:12:36 | [pearl_trainer] epoch #417 | EpochTime 162.85 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -96.2293 MetaTest/Average/AverageReturn -96.2293 MetaTest/Average/Iteration 417 MetaTest/Average/MaxReturn -91.6452 MetaTest/Average/MinReturn -104.058 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.56286 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.2293 MetaTest/__unnamed_task__/AverageReturn -96.2293 MetaTest/__unnamed_task__/Iteration 417 MetaTest/__unnamed_task__/MaxReturn -91.6452 MetaTest/__unnamed_task__/MinReturn -104.058 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.56286 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 683800 ------------------------------------------------- ------------ 2025-04-03 08:12:58 | [pearl_trainer] epoch #418 | Training... 2025-04-03 08:14:34 | [pearl_trainer] epoch #418 | Evaluating... 2025-04-03 08:14:34 | [pearl_trainer] epoch #418 | Sampling for adapation and meta-testing... 2025-04-03 08:15:24 | [pearl_trainer] epoch #418 | Finished meta-testing... 2025-04-03 08:15:24 | [pearl_trainer] epoch #418 | Saving snapshot... 2025-04-03 08:15:25 | [pearl_trainer] epoch #418 | Saved 2025-04-03 08:15:25 | [pearl_trainer] epoch #418 | Time 67601.10 s 2025-04-03 08:15:25 | [pearl_trainer] epoch #418 | EpochTime 169.18 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -100.92 MetaTest/Average/AverageReturn -100.92 MetaTest/Average/Iteration 418 MetaTest/Average/MaxReturn -84.461 MetaTest/Average/MinReturn -116.984 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.2805 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -100.92 MetaTest/__unnamed_task__/AverageReturn -100.92 MetaTest/__unnamed_task__/Iteration 418 MetaTest/__unnamed_task__/MaxReturn -84.461 MetaTest/__unnamed_task__/MinReturn -116.984 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.2805 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 685400 ------------------------------------------------- ----------- 2025-04-03 08:15:47 | [pearl_trainer] epoch #419 | Training... 2025-04-03 08:17:14 | [pearl_trainer] epoch #419 | Evaluating... 2025-04-03 08:17:14 | [pearl_trainer] epoch #419 | Sampling for adapation and meta-testing... 2025-04-03 08:18:01 | [pearl_trainer] epoch #419 | Finished meta-testing... 2025-04-03 08:18:01 | [pearl_trainer] epoch #419 | Saving snapshot... 2025-04-03 08:18:02 | [pearl_trainer] epoch #419 | Saved 2025-04-03 08:18:02 | [pearl_trainer] epoch #419 | Time 67757.94 s 2025-04-03 08:18:02 | [pearl_trainer] epoch #419 | EpochTime 156.83 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -105.711 MetaTest/Average/AverageReturn -105.711 MetaTest/Average/Iteration 419 MetaTest/Average/MaxReturn -88.0301 MetaTest/Average/MinReturn -118.331 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.8775 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -105.711 MetaTest/__unnamed_task__/AverageReturn -105.711 MetaTest/__unnamed_task__/Iteration 419 MetaTest/__unnamed_task__/MaxReturn -88.0301 MetaTest/__unnamed_task__/MinReturn -118.331 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.8775 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 687000 ------------------------------------------------- ----------- 2025-04-03 08:18:25 | [pearl_trainer] epoch #420 | Training... 2025-04-03 08:19:57 | [pearl_trainer] epoch #420 | Evaluating... 2025-04-03 08:19:57 | [pearl_trainer] epoch #420 | Sampling for adapation and meta-testing... 2025-04-03 08:20:42 | [pearl_trainer] epoch #420 | Finished meta-testing... 2025-04-03 08:20:42 | [pearl_trainer] epoch #420 | Saving snapshot... 2025-04-03 08:20:44 | [pearl_trainer] epoch #420 | Saved 2025-04-03 08:20:44 | [pearl_trainer] epoch #420 | Time 67919.90 s 2025-04-03 08:20:44 | [pearl_trainer] epoch #420 | EpochTime 161.96 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -101.074 MetaTest/Average/AverageReturn -101.074 MetaTest/Average/Iteration 420 MetaTest/Average/MaxReturn -94.1197 MetaTest/Average/MinReturn -106.222 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.10318 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.074 MetaTest/__unnamed_task__/AverageReturn -101.074 MetaTest/__unnamed_task__/Iteration 420 MetaTest/__unnamed_task__/MaxReturn -94.1197 MetaTest/__unnamed_task__/MinReturn -106.222 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.10318 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 688600 ------------------------------------------------- ------------ 2025-04-03 08:21:06 | [pearl_trainer] epoch #421 | Training... 2025-04-03 08:22:38 | [pearl_trainer] epoch #421 | Evaluating... 2025-04-03 08:22:38 | [pearl_trainer] epoch #421 | Sampling for adapation and meta-testing... 2025-04-03 08:23:34 | [pearl_trainer] epoch #421 | Finished meta-testing... 2025-04-03 08:23:34 | [pearl_trainer] epoch #421 | Saving snapshot... 2025-04-03 08:23:36 | [pearl_trainer] epoch #421 | Saved 2025-04-03 08:23:36 | [pearl_trainer] epoch #421 | Time 68091.74 s 2025-04-03 08:23:36 | [pearl_trainer] epoch #421 | EpochTime 171.83 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -90.2173 MetaTest/Average/AverageReturn -90.2173 MetaTest/Average/Iteration 421 MetaTest/Average/MaxReturn -85.3238 MetaTest/Average/MinReturn -99.1817 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.34768 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.2173 MetaTest/__unnamed_task__/AverageReturn -90.2173 MetaTest/__unnamed_task__/Iteration 421 MetaTest/__unnamed_task__/MaxReturn -85.3238 MetaTest/__unnamed_task__/MinReturn -99.1817 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.34768 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 690200 ------------------------------------------------- ------------ 2025-04-03 08:23:57 | [pearl_trainer] epoch #422 | Training... 2025-04-03 08:25:21 | [pearl_trainer] epoch #422 | Evaluating... 2025-04-03 08:25:21 | [pearl_trainer] epoch #422 | Sampling for adapation and meta-testing... 2025-04-03 08:26:13 | [pearl_trainer] epoch #422 | Finished meta-testing... 2025-04-03 08:26:13 | [pearl_trainer] epoch #422 | Saving snapshot... 2025-04-03 08:26:14 | [pearl_trainer] epoch #422 | Saved 2025-04-03 08:26:14 | [pearl_trainer] epoch #422 | Time 68250.37 s 2025-04-03 08:26:14 | [pearl_trainer] epoch #422 | EpochTime 158.63 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -94.5508 MetaTest/Average/AverageReturn -94.5508 MetaTest/Average/Iteration 422 MetaTest/Average/MaxReturn -91.4645 MetaTest/Average/MinReturn -99.7994 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.73047 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.5508 MetaTest/__unnamed_task__/AverageReturn -94.5508 MetaTest/__unnamed_task__/Iteration 422 MetaTest/__unnamed_task__/MaxReturn -91.4645 MetaTest/__unnamed_task__/MinReturn -99.7994 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.73047 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 691800 ------------------------------------------------- ------------ 2025-04-03 08:26:39 | [pearl_trainer] epoch #423 | Training... 2025-04-03 08:28:06 | [pearl_trainer] epoch #423 | Evaluating... 2025-04-03 08:28:06 | [pearl_trainer] epoch #423 | Sampling for adapation and meta-testing... 2025-04-03 08:28:52 | [pearl_trainer] epoch #423 | Finished meta-testing... 2025-04-03 08:28:52 | [pearl_trainer] epoch #423 | Saving snapshot... 2025-04-03 08:28:53 | [pearl_trainer] epoch #423 | Saved 2025-04-03 08:28:53 | [pearl_trainer] epoch #423 | Time 68409.18 s 2025-04-03 08:28:53 | [pearl_trainer] epoch #423 | EpochTime 158.81 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -93.4276 MetaTest/Average/AverageReturn -93.4276 MetaTest/Average/Iteration 423 MetaTest/Average/MaxReturn -77.7696 MetaTest/Average/MinReturn -108.039 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.3796 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.4276 MetaTest/__unnamed_task__/AverageReturn -93.4276 MetaTest/__unnamed_task__/Iteration 423 MetaTest/__unnamed_task__/MaxReturn -77.7696 MetaTest/__unnamed_task__/MinReturn -108.039 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.3796 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 693400 ------------------------------------------------- ----------- 2025-04-03 08:29:15 | [pearl_trainer] epoch #424 | Training... 2025-04-03 08:31:03 | [pearl_trainer] epoch #424 | Evaluating... 2025-04-03 08:31:03 | [pearl_trainer] epoch #424 | Sampling for adapation and meta-testing... 2025-04-03 08:31:57 | [pearl_trainer] epoch #424 | Finished meta-testing... 2025-04-03 08:31:57 | [pearl_trainer] epoch #424 | Saving snapshot... 2025-04-03 08:31:58 | [pearl_trainer] epoch #424 | Saved 2025-04-03 08:31:58 | [pearl_trainer] epoch #424 | Time 68594.36 s 2025-04-03 08:31:58 | [pearl_trainer] epoch #424 | EpochTime 185.18 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -106.702 MetaTest/Average/AverageReturn -106.702 MetaTest/Average/Iteration 424 MetaTest/Average/MaxReturn -96.5557 MetaTest/Average/MinReturn -113.788 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.36034 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -106.702 MetaTest/__unnamed_task__/AverageReturn -106.702 MetaTest/__unnamed_task__/Iteration 424 MetaTest/__unnamed_task__/MaxReturn -96.5557 MetaTest/__unnamed_task__/MinReturn -113.788 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.36034 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 695000 ------------------------------------------------- ------------ 2025-04-03 08:32:20 | [pearl_trainer] epoch #425 | Training... 2025-04-03 08:33:43 | [pearl_trainer] epoch #425 | Evaluating... 2025-04-03 08:33:43 | [pearl_trainer] epoch #425 | Sampling for adapation and meta-testing... 2025-04-03 08:34:37 | [pearl_trainer] epoch #425 | Finished meta-testing... 2025-04-03 08:34:37 | [pearl_trainer] epoch #425 | Saving snapshot... 2025-04-03 08:34:38 | [pearl_trainer] epoch #425 | Saved 2025-04-03 08:34:38 | [pearl_trainer] epoch #425 | Time 68754.32 s 2025-04-03 08:34:38 | [pearl_trainer] epoch #425 | EpochTime 159.96 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -95.3964 MetaTest/Average/AverageReturn -95.3964 MetaTest/Average/Iteration 425 MetaTest/Average/MaxReturn -83.7847 MetaTest/Average/MinReturn -109.186 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.4839 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.3964 MetaTest/__unnamed_task__/AverageReturn -95.3964 MetaTest/__unnamed_task__/Iteration 425 MetaTest/__unnamed_task__/MaxReturn -83.7847 MetaTest/__unnamed_task__/MinReturn -109.186 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.4839 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 696600 ------------------------------------------------- ----------- 2025-04-03 08:35:03 | [pearl_trainer] epoch #426 | Training... 2025-04-03 08:36:29 | [pearl_trainer] epoch #426 | Evaluating... 2025-04-03 08:36:29 | [pearl_trainer] epoch #426 | Sampling for adapation and meta-testing... 2025-04-03 08:37:15 | [pearl_trainer] epoch #426 | Finished meta-testing... 2025-04-03 08:37:15 | [pearl_trainer] epoch #426 | Saving snapshot... 2025-04-03 08:37:17 | [pearl_trainer] epoch #426 | Saved 2025-04-03 08:37:17 | [pearl_trainer] epoch #426 | Time 68912.91 s 2025-04-03 08:37:17 | [pearl_trainer] epoch #426 | EpochTime 158.58 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -105.056 MetaTest/Average/AverageReturn -105.056 MetaTest/Average/Iteration 426 MetaTest/Average/MaxReturn -91.7552 MetaTest/Average/MinReturn -113.506 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.51921 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -105.056 MetaTest/__unnamed_task__/AverageReturn -105.056 MetaTest/__unnamed_task__/Iteration 426 MetaTest/__unnamed_task__/MaxReturn -91.7552 MetaTest/__unnamed_task__/MinReturn -113.506 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.51921 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 698200 ------------------------------------------------- ------------ 2025-04-03 08:37:41 | [pearl_trainer] epoch #427 | Training... 2025-04-03 08:39:15 | [pearl_trainer] epoch #427 | Evaluating... 2025-04-03 08:39:15 | [pearl_trainer] epoch #427 | Sampling for adapation and meta-testing... 2025-04-03 08:40:02 | [pearl_trainer] epoch #427 | Finished meta-testing... 2025-04-03 08:40:02 | [pearl_trainer] epoch #427 | Saving snapshot... 2025-04-03 08:40:03 | [pearl_trainer] epoch #427 | Saved 2025-04-03 08:40:03 | [pearl_trainer] epoch #427 | Time 69079.46 s 2025-04-03 08:40:03 | [pearl_trainer] epoch #427 | EpochTime 166.56 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -97.6253 MetaTest/Average/AverageReturn -97.6253 MetaTest/Average/Iteration 427 MetaTest/Average/MaxReturn -86.5536 MetaTest/Average/MinReturn -114.161 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.9146 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.6253 MetaTest/__unnamed_task__/AverageReturn -97.6253 MetaTest/__unnamed_task__/Iteration 427 MetaTest/__unnamed_task__/MaxReturn -86.5536 MetaTest/__unnamed_task__/MinReturn -114.161 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.9146 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 699800 ------------------------------------------------- ----------- 2025-04-03 08:40:25 | [pearl_trainer] epoch #428 | Training... 2025-04-03 08:41:54 | [pearl_trainer] epoch #428 | Evaluating... 2025-04-03 08:41:54 | [pearl_trainer] epoch #428 | Sampling for adapation and meta-testing... 2025-04-03 08:42:44 | [pearl_trainer] epoch #428 | Finished meta-testing... 2025-04-03 08:42:44 | [pearl_trainer] epoch #428 | Saving snapshot... 2025-04-03 08:42:46 | [pearl_trainer] epoch #428 | Saved 2025-04-03 08:42:46 | [pearl_trainer] epoch #428 | Time 69241.91 s 2025-04-03 08:42:46 | [pearl_trainer] epoch #428 | EpochTime 162.44 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -91.0941 MetaTest/Average/AverageReturn -91.0941 MetaTest/Average/Iteration 428 MetaTest/Average/MaxReturn -79.0532 MetaTest/Average/MinReturn -107.605 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.0773 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.0941 MetaTest/__unnamed_task__/AverageReturn -91.0941 MetaTest/__unnamed_task__/Iteration 428 MetaTest/__unnamed_task__/MaxReturn -79.0532 MetaTest/__unnamed_task__/MinReturn -107.605 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.0773 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 701400 ------------------------------------------------- ----------- 2025-04-03 08:43:09 | [pearl_trainer] epoch #429 | Training... 2025-04-03 08:44:40 | [pearl_trainer] epoch #429 | Evaluating... 2025-04-03 08:44:40 | [pearl_trainer] epoch #429 | Sampling for adapation and meta-testing... 2025-04-03 08:45:26 | [pearl_trainer] epoch #429 | Finished meta-testing... 2025-04-03 08:45:26 | [pearl_trainer] epoch #429 | Saving snapshot... 2025-04-03 08:45:27 | [pearl_trainer] epoch #429 | Saved 2025-04-03 08:45:27 | [pearl_trainer] epoch #429 | Time 69402.78 s 2025-04-03 08:45:27 | [pearl_trainer] epoch #429 | EpochTime 160.87 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -101.411 MetaTest/Average/AverageReturn -101.411 MetaTest/Average/Iteration 429 MetaTest/Average/MaxReturn -95.4384 MetaTest/Average/MinReturn -106.334 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.50959 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -101.411 MetaTest/__unnamed_task__/AverageReturn -101.411 MetaTest/__unnamed_task__/Iteration 429 MetaTest/__unnamed_task__/MaxReturn -95.4384 MetaTest/__unnamed_task__/MinReturn -106.334 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.50959 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 703000 ------------------------------------------------- ------------ 2025-04-03 08:45:48 | [pearl_trainer] epoch #430 | Training... 2025-04-03 08:47:21 | [pearl_trainer] epoch #430 | Evaluating... 2025-04-03 08:47:21 | [pearl_trainer] epoch #430 | Sampling for adapation and meta-testing... 2025-04-03 08:48:06 | [pearl_trainer] epoch #430 | Finished meta-testing... 2025-04-03 08:48:06 | [pearl_trainer] epoch #430 | Saving snapshot... 2025-04-03 08:48:07 | [pearl_trainer] epoch #430 | Saved 2025-04-03 08:48:07 | [pearl_trainer] epoch #430 | Time 69563.44 s 2025-04-03 08:48:07 | [pearl_trainer] epoch #430 | EpochTime 160.66 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -97.77 MetaTest/Average/AverageReturn -97.77 MetaTest/Average/Iteration 430 MetaTest/Average/MaxReturn -95.2515 MetaTest/Average/MinReturn -99.7154 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.86688 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -97.77 MetaTest/__unnamed_task__/AverageReturn -97.77 MetaTest/__unnamed_task__/Iteration 430 MetaTest/__unnamed_task__/MaxReturn -95.2515 MetaTest/__unnamed_task__/MinReturn -99.7154 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.86688 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 704600 ------------------------------------------------- ------------ 2025-04-03 08:48:31 | [pearl_trainer] epoch #431 | Training... 2025-04-03 08:49:57 | [pearl_trainer] epoch #431 | Evaluating... 2025-04-03 08:49:57 | [pearl_trainer] epoch #431 | Sampling for adapation and meta-testing... 2025-04-03 08:50:48 | [pearl_trainer] epoch #431 | Finished meta-testing... 2025-04-03 08:50:48 | [pearl_trainer] epoch #431 | Saving snapshot... 2025-04-03 08:50:49 | [pearl_trainer] epoch #431 | Saved 2025-04-03 08:50:49 | [pearl_trainer] epoch #431 | Time 69725.20 s 2025-04-03 08:50:49 | [pearl_trainer] epoch #431 | EpochTime 161.76 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -91.1822 MetaTest/Average/AverageReturn -91.1822 MetaTest/Average/Iteration 431 MetaTest/Average/MaxReturn -85.3967 MetaTest/Average/MinReturn -101.31 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.18529 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.1822 MetaTest/__unnamed_task__/AverageReturn -91.1822 MetaTest/__unnamed_task__/Iteration 431 MetaTest/__unnamed_task__/MaxReturn -85.3967 MetaTest/__unnamed_task__/MinReturn -101.31 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.18529 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 706200 ------------------------------------------------- ------------ 2025-04-03 08:51:13 | [pearl_trainer] epoch #432 | Training... 2025-04-03 08:52:44 | [pearl_trainer] epoch #432 | Evaluating... 2025-04-03 08:52:44 | [pearl_trainer] epoch #432 | Sampling for adapation and meta-testing... 2025-04-03 08:53:29 | [pearl_trainer] epoch #432 | Finished meta-testing... 2025-04-03 08:53:29 | [pearl_trainer] epoch #432 | Saving snapshot... 2025-04-03 08:53:30 | [pearl_trainer] epoch #432 | Saved 2025-04-03 08:53:30 | [pearl_trainer] epoch #432 | Time 69886.41 s 2025-04-03 08:53:30 | [pearl_trainer] epoch #432 | EpochTime 161.20 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -88.3741 MetaTest/Average/AverageReturn -88.3741 MetaTest/Average/Iteration 432 MetaTest/Average/MaxReturn -83.3063 MetaTest/Average/MinReturn -94.9098 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.84949 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.3741 MetaTest/__unnamed_task__/AverageReturn -88.3741 MetaTest/__unnamed_task__/Iteration 432 MetaTest/__unnamed_task__/MaxReturn -83.3063 MetaTest/__unnamed_task__/MinReturn -94.9098 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.84949 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 707800 ------------------------------------------------- ------------ 2025-04-03 08:53:53 | [pearl_trainer] epoch #433 | Training... 2025-04-03 08:55:31 | [pearl_trainer] epoch #433 | Evaluating... 2025-04-03 08:55:31 | [pearl_trainer] epoch #433 | Sampling for adapation and meta-testing... 2025-04-03 08:56:15 | [pearl_trainer] epoch #433 | Finished meta-testing... 2025-04-03 08:56:15 | [pearl_trainer] epoch #433 | Saving snapshot... 2025-04-03 08:56:16 | [pearl_trainer] epoch #433 | Saved 2025-04-03 08:56:16 | [pearl_trainer] epoch #433 | Time 70052.12 s 2025-04-03 08:56:16 | [pearl_trainer] epoch #433 | EpochTime 165.71 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -90.4078 MetaTest/Average/AverageReturn -90.4078 MetaTest/Average/Iteration 433 MetaTest/Average/MaxReturn -78.8989 MetaTest/Average/MinReturn -106.352 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 11.6384 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -90.4078 MetaTest/__unnamed_task__/AverageReturn -90.4078 MetaTest/__unnamed_task__/Iteration 433 MetaTest/__unnamed_task__/MaxReturn -78.8989 MetaTest/__unnamed_task__/MinReturn -106.352 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 11.6384 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 709400 ------------------------------------------------- ----------- 2025-04-03 08:56:37 | [pearl_trainer] epoch #434 | Training... 2025-04-03 08:57:53 | [pearl_trainer] epoch #434 | Evaluating... 2025-04-03 08:57:53 | [pearl_trainer] epoch #434 | Sampling for adapation and meta-testing... 2025-04-03 08:58:49 | [pearl_trainer] epoch #434 | Finished meta-testing... 2025-04-03 08:58:49 | [pearl_trainer] epoch #434 | Saving snapshot... 2025-04-03 08:58:51 | [pearl_trainer] epoch #434 | Saved 2025-04-03 08:58:51 | [pearl_trainer] epoch #434 | Time 70206.81 s 2025-04-03 08:58:51 | [pearl_trainer] epoch #434 | EpochTime 154.70 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -81.9232 MetaTest/Average/AverageReturn -81.9232 MetaTest/Average/Iteration 434 MetaTest/Average/MaxReturn -76.8759 MetaTest/Average/MinReturn -87.4813 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.34468 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -81.9232 MetaTest/__unnamed_task__/AverageReturn -81.9232 MetaTest/__unnamed_task__/Iteration 434 MetaTest/__unnamed_task__/MaxReturn -76.8759 MetaTest/__unnamed_task__/MinReturn -87.4813 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.34468 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 711000 ------------------------------------------------- ------------ 2025-04-03 08:59:13 | [pearl_trainer] epoch #435 | Training... 2025-04-03 09:00:38 | [pearl_trainer] epoch #435 | Evaluating... 2025-04-03 09:00:38 | [pearl_trainer] epoch #435 | Sampling for adapation and meta-testing... 2025-04-03 09:01:32 | [pearl_trainer] epoch #435 | Finished meta-testing... 2025-04-03 09:01:32 | [pearl_trainer] epoch #435 | Saving snapshot... 2025-04-03 09:01:33 | [pearl_trainer] epoch #435 | Saved 2025-04-03 09:01:33 | [pearl_trainer] epoch #435 | Time 70369.59 s 2025-04-03 09:01:33 | [pearl_trainer] epoch #435 | EpochTime 162.77 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -94.3264 MetaTest/Average/AverageReturn -94.3264 MetaTest/Average/Iteration 435 MetaTest/Average/MaxReturn -88.7685 MetaTest/Average/MinReturn -103.795 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.72884 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.3264 MetaTest/__unnamed_task__/AverageReturn -94.3264 MetaTest/__unnamed_task__/Iteration 435 MetaTest/__unnamed_task__/MaxReturn -88.7685 MetaTest/__unnamed_task__/MinReturn -103.795 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.72884 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 712600 ------------------------------------------------- ------------ 2025-04-03 09:01:55 | [pearl_trainer] epoch #436 | Training... 2025-04-03 09:03:25 | [pearl_trainer] epoch #436 | Evaluating... 2025-04-03 09:03:25 | [pearl_trainer] epoch #436 | Sampling for adapation and meta-testing... 2025-04-03 09:04:12 | [pearl_trainer] epoch #436 | Finished meta-testing... 2025-04-03 09:04:12 | [pearl_trainer] epoch #436 | Saving snapshot... 2025-04-03 09:04:13 | [pearl_trainer] epoch #436 | Saved 2025-04-03 09:04:13 | [pearl_trainer] epoch #436 | Time 70529.20 s 2025-04-03 09:04:13 | [pearl_trainer] epoch #436 | EpochTime 159.61 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -94.626 MetaTest/Average/AverageReturn -94.626 MetaTest/Average/Iteration 436 MetaTest/Average/MaxReturn -90.9575 MetaTest/Average/MinReturn -101.586 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.92352 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -94.626 MetaTest/__unnamed_task__/AverageReturn -94.626 MetaTest/__unnamed_task__/Iteration 436 MetaTest/__unnamed_task__/MaxReturn -90.9575 MetaTest/__unnamed_task__/MinReturn -101.586 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.92352 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 714200 ------------------------------------------------- ------------ 2025-04-03 09:04:34 | [pearl_trainer] epoch #437 | Training... 2025-04-03 09:06:00 | [pearl_trainer] epoch #437 | Evaluating... 2025-04-03 09:06:00 | [pearl_trainer] epoch #437 | Sampling for adapation and meta-testing... 2025-04-03 09:06:48 | [pearl_trainer] epoch #437 | Finished meta-testing... 2025-04-03 09:06:48 | [pearl_trainer] epoch #437 | Saving snapshot... 2025-04-03 09:06:49 | [pearl_trainer] epoch #437 | Saved 2025-04-03 09:06:49 | [pearl_trainer] epoch #437 | Time 70684.84 s 2025-04-03 09:06:49 | [pearl_trainer] epoch #437 | EpochTime 155.64 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -86.1643 MetaTest/Average/AverageReturn -86.1643 MetaTest/Average/Iteration 437 MetaTest/Average/MaxReturn -77.019 MetaTest/Average/MinReturn -91.3519 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.48618 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -86.1643 MetaTest/__unnamed_task__/AverageReturn -86.1643 MetaTest/__unnamed_task__/Iteration 437 MetaTest/__unnamed_task__/MaxReturn -77.019 MetaTest/__unnamed_task__/MinReturn -91.3519 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.48618 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 715800 ------------------------------------------------- ------------ 2025-04-03 09:07:11 | [pearl_trainer] epoch #438 | Training... 2025-04-03 09:08:34 | [pearl_trainer] epoch #438 | Evaluating... 2025-04-03 09:08:34 | [pearl_trainer] epoch #438 | Sampling for adapation and meta-testing... 2025-04-03 09:09:18 | [pearl_trainer] epoch #438 | Finished meta-testing... 2025-04-03 09:09:18 | [pearl_trainer] epoch #438 | Saving snapshot... 2025-04-03 09:09:19 | [pearl_trainer] epoch #438 | Saved 2025-04-03 09:09:19 | [pearl_trainer] epoch #438 | Time 70835.02 s 2025-04-03 09:09:19 | [pearl_trainer] epoch #438 | EpochTime 150.18 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -88.4011 MetaTest/Average/AverageReturn -88.4011 MetaTest/Average/Iteration 438 MetaTest/Average/MaxReturn -82.7023 MetaTest/Average/MinReturn -93.7923 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.5327 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.4011 MetaTest/__unnamed_task__/AverageReturn -88.4011 MetaTest/__unnamed_task__/Iteration 438 MetaTest/__unnamed_task__/MaxReturn -82.7023 MetaTest/__unnamed_task__/MinReturn -93.7923 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.5327 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 717400 ------------------------------------------------- ----------- 2025-04-03 09:09:40 | [pearl_trainer] epoch #439 | Training... 2025-04-03 09:11:15 | [pearl_trainer] epoch #439 | Evaluating... 2025-04-03 09:11:15 | [pearl_trainer] epoch #439 | Sampling for adapation and meta-testing... 2025-04-03 09:12:00 | [pearl_trainer] epoch #439 | Finished meta-testing... 2025-04-03 09:12:00 | [pearl_trainer] epoch #439 | Saving snapshot... 2025-04-03 09:12:02 | [pearl_trainer] epoch #439 | Saved 2025-04-03 09:12:02 | [pearl_trainer] epoch #439 | Time 70997.75 s 2025-04-03 09:12:02 | [pearl_trainer] epoch #439 | EpochTime 162.73 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -100.271 MetaTest/Average/AverageReturn -100.271 MetaTest/Average/Iteration 439 MetaTest/Average/MaxReturn -76.4156 MetaTest/Average/MinReturn -139.275 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 27.8079 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -100.271 MetaTest/__unnamed_task__/AverageReturn -100.271 MetaTest/__unnamed_task__/Iteration 439 MetaTest/__unnamed_task__/MaxReturn -76.4156 MetaTest/__unnamed_task__/MinReturn -139.275 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 27.8079 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 719000 ------------------------------------------------- ----------- 2025-04-03 09:12:22 | [pearl_trainer] epoch #440 | Training... 2025-04-03 09:13:54 | [pearl_trainer] epoch #440 | Evaluating... 2025-04-03 09:13:54 | [pearl_trainer] epoch #440 | Sampling for adapation and meta-testing... 2025-04-03 09:14:43 | [pearl_trainer] epoch #440 | Finished meta-testing... 2025-04-03 09:14:43 | [pearl_trainer] epoch #440 | Saving snapshot... 2025-04-03 09:14:44 | [pearl_trainer] epoch #440 | Saved 2025-04-03 09:14:44 | [pearl_trainer] epoch #440 | Time 71160.26 s 2025-04-03 09:14:44 | [pearl_trainer] epoch #440 | EpochTime 162.51 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -115.929 MetaTest/Average/AverageReturn -115.929 MetaTest/Average/Iteration 440 MetaTest/Average/MaxReturn -105.661 MetaTest/Average/MinReturn -121.716 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.27998 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -115.929 MetaTest/__unnamed_task__/AverageReturn -115.929 MetaTest/__unnamed_task__/Iteration 440 MetaTest/__unnamed_task__/MaxReturn -105.661 MetaTest/__unnamed_task__/MinReturn -121.716 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.27998 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 720600 ------------------------------------------------- ------------ 2025-04-03 09:15:06 | [pearl_trainer] epoch #441 | Training... 2025-04-03 09:16:30 | [pearl_trainer] epoch #441 | Evaluating... 2025-04-03 09:16:30 | [pearl_trainer] epoch #441 | Sampling for adapation and meta-testing... 2025-04-03 09:17:13 | [pearl_trainer] epoch #441 | Finished meta-testing... 2025-04-03 09:17:13 | [pearl_trainer] epoch #441 | Saving snapshot... 2025-04-03 09:17:15 | [pearl_trainer] epoch #441 | Saved 2025-04-03 09:17:15 | [pearl_trainer] epoch #441 | Time 71310.84 s 2025-04-03 09:17:15 | [pearl_trainer] epoch #441 | EpochTime 150.57 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.8157 MetaTest/Average/AverageReturn -93.8157 MetaTest/Average/Iteration 441 MetaTest/Average/MaxReturn -82.0836 MetaTest/Average/MinReturn -105.472 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.54854 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.8157 MetaTest/__unnamed_task__/AverageReturn -93.8157 MetaTest/__unnamed_task__/Iteration 441 MetaTest/__unnamed_task__/MaxReturn -82.0836 MetaTest/__unnamed_task__/MinReturn -105.472 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.54854 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 722200 ------------------------------------------------- ------------ 2025-04-03 09:17:38 | [pearl_trainer] epoch #442 | Training... 2025-04-03 09:19:16 | [pearl_trainer] epoch #442 | Evaluating... 2025-04-03 09:19:16 | [pearl_trainer] epoch #442 | Sampling for adapation and meta-testing... 2025-04-03 09:20:05 | [pearl_trainer] epoch #442 | Finished meta-testing... 2025-04-03 09:20:05 | [pearl_trainer] epoch #442 | Saving snapshot... 2025-04-03 09:20:06 | [pearl_trainer] epoch #442 | Saved 2025-04-03 09:20:06 | [pearl_trainer] epoch #442 | Time 71481.86 s 2025-04-03 09:20:06 | [pearl_trainer] epoch #442 | EpochTime 171.02 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -107.551 MetaTest/Average/AverageReturn -107.551 MetaTest/Average/Iteration 442 MetaTest/Average/MaxReturn -88.3406 MetaTest/Average/MinReturn -135.844 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 20.4291 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -107.551 MetaTest/__unnamed_task__/AverageReturn -107.551 MetaTest/__unnamed_task__/Iteration 442 MetaTest/__unnamed_task__/MaxReturn -88.3406 MetaTest/__unnamed_task__/MinReturn -135.844 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 20.4291 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 723800 ------------------------------------------------- ----------- 2025-04-03 09:20:27 | [pearl_trainer] epoch #443 | Training... 2025-04-03 09:21:55 | [pearl_trainer] epoch #443 | Evaluating... 2025-04-03 09:21:55 | [pearl_trainer] epoch #443 | Sampling for adapation and meta-testing... 2025-04-03 09:22:51 | [pearl_trainer] epoch #443 | Finished meta-testing... 2025-04-03 09:22:51 | [pearl_trainer] epoch #443 | Saving snapshot... 2025-04-03 09:22:52 | [pearl_trainer] epoch #443 | Saved 2025-04-03 09:22:52 | [pearl_trainer] epoch #443 | Time 71648.39 s 2025-04-03 09:22:52 | [pearl_trainer] epoch #443 | EpochTime 166.52 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -107.37 MetaTest/Average/AverageReturn -107.37 MetaTest/Average/Iteration 443 MetaTest/Average/MaxReturn -85.5259 MetaTest/Average/MinReturn -144.352 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 26.2931 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -107.37 MetaTest/__unnamed_task__/AverageReturn -107.37 MetaTest/__unnamed_task__/Iteration 443 MetaTest/__unnamed_task__/MaxReturn -85.5259 MetaTest/__unnamed_task__/MinReturn -144.352 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 26.2931 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 725400 ------------------------------------------------- ----------- 2025-04-03 09:23:13 | [pearl_trainer] epoch #444 | Training... 2025-04-03 09:24:34 | [pearl_trainer] epoch #444 | Evaluating... 2025-04-03 09:24:34 | [pearl_trainer] epoch #444 | Sampling for adapation and meta-testing... 2025-04-03 09:25:18 | [pearl_trainer] epoch #444 | Finished meta-testing... 2025-04-03 09:25:18 | [pearl_trainer] epoch #444 | Saving snapshot... 2025-04-03 09:25:19 | [pearl_trainer] epoch #444 | Saved 2025-04-03 09:25:19 | [pearl_trainer] epoch #444 | Time 71795.42 s 2025-04-03 09:25:19 | [pearl_trainer] epoch #444 | EpochTime 147.04 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.3885 MetaTest/Average/AverageReturn -93.3885 MetaTest/Average/Iteration 444 MetaTest/Average/MaxReturn -89.5376 MetaTest/Average/MinReturn -97.8128 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.40258 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.3885 MetaTest/__unnamed_task__/AverageReturn -93.3885 MetaTest/__unnamed_task__/Iteration 444 MetaTest/__unnamed_task__/MaxReturn -89.5376 MetaTest/__unnamed_task__/MinReturn -97.8128 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.40258 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 727000 ------------------------------------------------- ------------ 2025-04-03 09:25:43 | [pearl_trainer] epoch #445 | Training... 2025-04-03 09:27:15 | [pearl_trainer] epoch #445 | Evaluating... 2025-04-03 09:27:15 | [pearl_trainer] epoch #445 | Sampling for adapation and meta-testing... 2025-04-03 09:28:04 | [pearl_trainer] epoch #445 | Finished meta-testing... 2025-04-03 09:28:04 | [pearl_trainer] epoch #445 | Saving snapshot... 2025-04-03 09:28:05 | [pearl_trainer] epoch #445 | Saved 2025-04-03 09:28:05 | [pearl_trainer] epoch #445 | Time 71960.75 s 2025-04-03 09:28:05 | [pearl_trainer] epoch #445 | EpochTime 165.32 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -91.2935 MetaTest/Average/AverageReturn -91.2935 MetaTest/Average/Iteration 445 MetaTest/Average/MaxReturn -85.5132 MetaTest/Average/MinReturn -102.195 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.71318 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.2935 MetaTest/__unnamed_task__/AverageReturn -91.2935 MetaTest/__unnamed_task__/Iteration 445 MetaTest/__unnamed_task__/MaxReturn -85.5132 MetaTest/__unnamed_task__/MinReturn -102.195 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.71318 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 728600 ------------------------------------------------- ------------ 2025-04-03 09:28:28 | [pearl_trainer] epoch #446 | Training... 2025-04-03 09:30:07 | [pearl_trainer] epoch #446 | Evaluating... 2025-04-03 09:30:07 | [pearl_trainer] epoch #446 | Sampling for adapation and meta-testing... 2025-04-03 09:30:53 | [pearl_trainer] epoch #446 | Finished meta-testing... 2025-04-03 09:30:53 | [pearl_trainer] epoch #446 | Saving snapshot... 2025-04-03 09:30:54 | [pearl_trainer] epoch #446 | Saved 2025-04-03 09:30:54 | [pearl_trainer] epoch #446 | Time 72130.28 s 2025-04-03 09:30:54 | [pearl_trainer] epoch #446 | EpochTime 169.53 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -83.2061 MetaTest/Average/AverageReturn -83.2061 MetaTest/Average/Iteration 446 MetaTest/Average/MaxReturn -68.8789 MetaTest/Average/MinReturn -91.2547 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.1566 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -83.2061 MetaTest/__unnamed_task__/AverageReturn -83.2061 MetaTest/__unnamed_task__/Iteration 446 MetaTest/__unnamed_task__/MaxReturn -68.8789 MetaTest/__unnamed_task__/MinReturn -91.2547 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.1566 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 730200 ------------------------------------------------- ----------- 2025-04-03 09:31:15 | [pearl_trainer] epoch #447 | Training... 2025-04-03 09:32:44 | [pearl_trainer] epoch #447 | Evaluating... 2025-04-03 09:32:44 | [pearl_trainer] epoch #447 | Sampling for adapation and meta-testing... 2025-04-03 09:33:31 | [pearl_trainer] epoch #447 | Finished meta-testing... 2025-04-03 09:33:31 | [pearl_trainer] epoch #447 | Saving snapshot... 2025-04-03 09:33:32 | [pearl_trainer] epoch #447 | Saved 2025-04-03 09:33:32 | [pearl_trainer] epoch #447 | Time 72288.29 s 2025-04-03 09:33:32 | [pearl_trainer] epoch #447 | EpochTime 158.01 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -89.6733 MetaTest/Average/AverageReturn -89.6733 MetaTest/Average/Iteration 447 MetaTest/Average/MaxReturn -81.3053 MetaTest/Average/MinReturn -99.2333 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.36746 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -89.6733 MetaTest/__unnamed_task__/AverageReturn -89.6733 MetaTest/__unnamed_task__/Iteration 447 MetaTest/__unnamed_task__/MaxReturn -81.3053 MetaTest/__unnamed_task__/MinReturn -99.2333 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.36746 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 731800 ------------------------------------------------- ------------ 2025-04-03 09:33:54 | [pearl_trainer] epoch #448 | Training... 2025-04-03 09:35:25 | [pearl_trainer] epoch #448 | Evaluating... 2025-04-03 09:35:25 | [pearl_trainer] epoch #448 | Sampling for adapation and meta-testing... 2025-04-03 09:36:08 | [pearl_trainer] epoch #448 | Finished meta-testing... 2025-04-03 09:36:08 | [pearl_trainer] epoch #448 | Saving snapshot... 2025-04-03 09:36:09 | [pearl_trainer] epoch #448 | Saved 2025-04-03 09:36:09 | [pearl_trainer] epoch #448 | Time 72445.14 s 2025-04-03 09:36:09 | [pearl_trainer] epoch #448 | EpochTime 156.85 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -88.1648 MetaTest/Average/AverageReturn -88.1648 MetaTest/Average/Iteration 448 MetaTest/Average/MaxReturn -86.7314 MetaTest/Average/MinReturn -90.0197 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.37515 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -88.1648 MetaTest/__unnamed_task__/AverageReturn -88.1648 MetaTest/__unnamed_task__/Iteration 448 MetaTest/__unnamed_task__/MaxReturn -86.7314 MetaTest/__unnamed_task__/MinReturn -90.0197 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.37515 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 733400 ------------------------------------------------- ------------ 2025-04-03 09:36:30 | [pearl_trainer] epoch #449 | Training... 2025-04-03 09:38:02 | [pearl_trainer] epoch #449 | Evaluating... 2025-04-03 09:38:02 | [pearl_trainer] epoch #449 | Sampling for adapation and meta-testing... 2025-04-03 09:38:53 | [pearl_trainer] epoch #449 | Finished meta-testing... 2025-04-03 09:38:53 | [pearl_trainer] epoch #449 | Saving snapshot... 2025-04-03 09:38:55 | [pearl_trainer] epoch #449 | Saved 2025-04-03 09:38:55 | [pearl_trainer] epoch #449 | Time 72610.83 s 2025-04-03 09:38:55 | [pearl_trainer] epoch #449 | EpochTime 165.69 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.3644 MetaTest/Average/AverageReturn -93.3644 MetaTest/Average/Iteration 449 MetaTest/Average/MaxReturn -84.1786 MetaTest/Average/MinReturn -98.1014 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.49647 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.3644 MetaTest/__unnamed_task__/AverageReturn -93.3644 MetaTest/__unnamed_task__/Iteration 449 MetaTest/__unnamed_task__/MaxReturn -84.1786 MetaTest/__unnamed_task__/MinReturn -98.1014 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.49647 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 735000 ------------------------------------------------- ------------ 2025-04-03 09:39:16 | [pearl_trainer] epoch #450 | Training... 2025-04-03 09:40:43 | [pearl_trainer] epoch #450 | Evaluating... 2025-04-03 09:40:43 | [pearl_trainer] epoch #450 | Sampling for adapation and meta-testing... 2025-04-03 09:41:39 | [pearl_trainer] epoch #450 | Finished meta-testing... 2025-04-03 09:41:39 | [pearl_trainer] epoch #450 | Saving snapshot... 2025-04-03 09:41:40 | [pearl_trainer] epoch #450 | Saved 2025-04-03 09:41:40 | [pearl_trainer] epoch #450 | Time 72776.60 s 2025-04-03 09:41:40 | [pearl_trainer] epoch #450 | EpochTime 165.76 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -96.7965 MetaTest/Average/AverageReturn -96.7965 MetaTest/Average/Iteration 450 MetaTest/Average/MaxReturn -84.7926 MetaTest/Average/MinReturn -115.224 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 13.2276 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -96.7965 MetaTest/__unnamed_task__/AverageReturn -96.7965 MetaTest/__unnamed_task__/Iteration 450 MetaTest/__unnamed_task__/MaxReturn -84.7926 MetaTest/__unnamed_task__/MinReturn -115.224 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 13.2276 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 736600 ------------------------------------------------- ----------- 2025-04-03 09:42:03 | [pearl_trainer] epoch #451 | Training... 2025-04-03 09:43:26 | [pearl_trainer] epoch #451 | Evaluating... 2025-04-03 09:43:26 | [pearl_trainer] epoch #451 | Sampling for adapation and meta-testing... 2025-04-03 09:44:09 | [pearl_trainer] epoch #451 | Finished meta-testing... 2025-04-03 09:44:09 | [pearl_trainer] epoch #451 | Saving snapshot... 2025-04-03 09:44:10 | [pearl_trainer] epoch #451 | Saved 2025-04-03 09:44:10 | [pearl_trainer] epoch #451 | Time 72926.28 s 2025-04-03 09:44:10 | [pearl_trainer] epoch #451 | EpochTime 149.68 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -95.2809 MetaTest/Average/AverageReturn -95.2809 MetaTest/Average/Iteration 451 MetaTest/Average/MaxReturn -92.3219 MetaTest/Average/MinReturn -99.2152 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.89743 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.2809 MetaTest/__unnamed_task__/AverageReturn -95.2809 MetaTest/__unnamed_task__/Iteration 451 MetaTest/__unnamed_task__/MaxReturn -92.3219 MetaTest/__unnamed_task__/MinReturn -99.2152 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.89743 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 738200 ------------------------------------------------- ------------ 2025-04-03 09:44:35 | [pearl_trainer] epoch #452 | Training... 2025-04-03 09:46:10 | [pearl_trainer] epoch #452 | Evaluating... 2025-04-03 09:46:10 | [pearl_trainer] epoch #452 | Sampling for adapation and meta-testing... 2025-04-03 09:46:54 | [pearl_trainer] epoch #452 | Finished meta-testing... 2025-04-03 09:46:54 | [pearl_trainer] epoch #452 | Saving snapshot... 2025-04-03 09:46:55 | [pearl_trainer] epoch #452 | Saved 2025-04-03 09:46:55 | [pearl_trainer] epoch #452 | Time 73091.38 s 2025-04-03 09:46:55 | [pearl_trainer] epoch #452 | EpochTime 165.10 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -119.839 MetaTest/Average/AverageReturn -119.839 MetaTest/Average/Iteration 452 MetaTest/Average/MaxReturn -80.0385 MetaTest/Average/MinReturn -196.4 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 54.1512 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -119.839 MetaTest/__unnamed_task__/AverageReturn -119.839 MetaTest/__unnamed_task__/Iteration 452 MetaTest/__unnamed_task__/MaxReturn -80.0385 MetaTest/__unnamed_task__/MinReturn -196.4 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 54.1512 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 739800 ------------------------------------------------- ----------- 2025-04-03 09:47:18 | [pearl_trainer] epoch #453 | Training... 2025-04-03 09:48:44 | [pearl_trainer] epoch #453 | Evaluating... 2025-04-03 09:48:44 | [pearl_trainer] epoch #453 | Sampling for adapation and meta-testing... 2025-04-03 09:49:34 | [pearl_trainer] epoch #453 | Finished meta-testing... 2025-04-03 09:49:34 | [pearl_trainer] epoch #453 | Saving snapshot... 2025-04-03 09:49:35 | [pearl_trainer] epoch #453 | Saved 2025-04-03 09:49:35 | [pearl_trainer] epoch #453 | Time 73251.27 s 2025-04-03 09:49:35 | [pearl_trainer] epoch #453 | EpochTime 159.89 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -89.6238 MetaTest/Average/AverageReturn -89.6238 MetaTest/Average/Iteration 453 MetaTest/Average/MaxReturn -82.0131 MetaTest/Average/MinReturn -101.203 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.3215 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -89.6238 MetaTest/__unnamed_task__/AverageReturn -89.6238 MetaTest/__unnamed_task__/Iteration 453 MetaTest/__unnamed_task__/MaxReturn -82.0131 MetaTest/__unnamed_task__/MinReturn -101.203 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.3215 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 741400 ------------------------------------------------- ----------- 2025-04-03 09:49:58 | [pearl_trainer] epoch #454 | Training... 2025-04-03 09:51:26 | [pearl_trainer] epoch #454 | Evaluating... 2025-04-03 09:51:26 | [pearl_trainer] epoch #454 | Sampling for adapation and meta-testing... 2025-04-03 09:52:13 | [pearl_trainer] epoch #454 | Finished meta-testing... 2025-04-03 09:52:13 | [pearl_trainer] epoch #454 | Saving snapshot... 2025-04-03 09:52:14 | [pearl_trainer] epoch #454 | Saved 2025-04-03 09:52:14 | [pearl_trainer] epoch #454 | Time 73410.52 s 2025-04-03 09:52:14 | [pearl_trainer] epoch #454 | EpochTime 159.25 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -95.3785 MetaTest/Average/AverageReturn -95.3785 MetaTest/Average/Iteration 454 MetaTest/Average/MaxReturn -82.4352 MetaTest/Average/MinReturn -121.08 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 18.1739 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.3785 MetaTest/__unnamed_task__/AverageReturn -95.3785 MetaTest/__unnamed_task__/Iteration 454 MetaTest/__unnamed_task__/MaxReturn -82.4352 MetaTest/__unnamed_task__/MinReturn -121.08 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 18.1739 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 743000 ------------------------------------------------- ----------- 2025-04-03 09:52:38 | [pearl_trainer] epoch #455 | Training... 2025-04-03 09:54:17 | [pearl_trainer] epoch #455 | Evaluating... 2025-04-03 09:54:17 | [pearl_trainer] epoch #455 | Sampling for adapation and meta-testing... 2025-04-03 09:55:02 | [pearl_trainer] epoch #455 | Finished meta-testing... 2025-04-03 09:55:02 | [pearl_trainer] epoch #455 | Saving snapshot... 2025-04-03 09:55:03 | [pearl_trainer] epoch #455 | Saved 2025-04-03 09:55:03 | [pearl_trainer] epoch #455 | Time 73579.54 s 2025-04-03 09:55:03 | [pearl_trainer] epoch #455 | EpochTime 169.01 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -83.039 MetaTest/Average/AverageReturn -83.039 MetaTest/Average/Iteration 455 MetaTest/Average/MaxReturn -80.0353 MetaTest/Average/MinReturn -87.5433 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.24358 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -83.039 MetaTest/__unnamed_task__/AverageReturn -83.039 MetaTest/__unnamed_task__/Iteration 455 MetaTest/__unnamed_task__/MaxReturn -80.0353 MetaTest/__unnamed_task__/MinReturn -87.5433 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.24358 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 744600 ------------------------------------------------- ------------ 2025-04-03 09:55:26 | [pearl_trainer] epoch #456 | Training... 2025-04-03 09:57:02 | [pearl_trainer] epoch #456 | Evaluating... 2025-04-03 09:57:02 | [pearl_trainer] epoch #456 | Sampling for adapation and meta-testing... 2025-04-03 09:57:56 | [pearl_trainer] epoch #456 | Finished meta-testing... 2025-04-03 09:57:56 | [pearl_trainer] epoch #456 | Saving snapshot... 2025-04-03 09:57:58 | [pearl_trainer] epoch #456 | Saved 2025-04-03 09:57:58 | [pearl_trainer] epoch #456 | Time 73753.70 s 2025-04-03 09:57:58 | [pearl_trainer] epoch #456 | EpochTime 174.16 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -84.1184 MetaTest/Average/AverageReturn -84.1184 MetaTest/Average/Iteration 456 MetaTest/Average/MaxReturn -73.135 MetaTest/Average/MinReturn -92.1652 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.04178 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -84.1184 MetaTest/__unnamed_task__/AverageReturn -84.1184 MetaTest/__unnamed_task__/Iteration 456 MetaTest/__unnamed_task__/MaxReturn -73.135 MetaTest/__unnamed_task__/MinReturn -92.1652 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.04178 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 746200 ------------------------------------------------- ------------ 2025-04-03 09:58:21 | [pearl_trainer] epoch #457 | Training... 2025-04-03 09:59:53 | [pearl_trainer] epoch #457 | Evaluating... 2025-04-03 09:59:53 | [pearl_trainer] epoch #457 | Sampling for adapation and meta-testing... 2025-04-03 10:00:42 | [pearl_trainer] epoch #457 | Finished meta-testing... 2025-04-03 10:00:42 | [pearl_trainer] epoch #457 | Saving snapshot... 2025-04-03 10:00:43 | [pearl_trainer] epoch #457 | Saved 2025-04-03 10:00:43 | [pearl_trainer] epoch #457 | Time 73919.59 s 2025-04-03 10:00:43 | [pearl_trainer] epoch #457 | EpochTime 165.89 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -87.2853 MetaTest/Average/AverageReturn -87.2853 MetaTest/Average/Iteration 457 MetaTest/Average/MaxReturn -82.4822 MetaTest/Average/MinReturn -92.0461 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.90457 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -87.2853 MetaTest/__unnamed_task__/AverageReturn -87.2853 MetaTest/__unnamed_task__/Iteration 457 MetaTest/__unnamed_task__/MaxReturn -82.4822 MetaTest/__unnamed_task__/MinReturn -92.0461 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.90457 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 747800 ------------------------------------------------- ------------ 2025-04-03 10:01:07 | [pearl_trainer] epoch #458 | Training... 2025-04-03 10:02:36 | [pearl_trainer] epoch #458 | Evaluating... 2025-04-03 10:02:36 | [pearl_trainer] epoch #458 | Sampling for adapation and meta-testing... 2025-04-03 10:03:25 | [pearl_trainer] epoch #458 | Finished meta-testing... 2025-04-03 10:03:25 | [pearl_trainer] epoch #458 | Saving snapshot... 2025-04-03 10:03:26 | [pearl_trainer] epoch #458 | Saved 2025-04-03 10:03:26 | [pearl_trainer] epoch #458 | Time 74082.06 s 2025-04-03 10:03:26 | [pearl_trainer] epoch #458 | EpochTime 162.47 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.149 MetaTest/Average/AverageReturn -93.149 MetaTest/Average/Iteration 458 MetaTest/Average/MaxReturn -85.8926 MetaTest/Average/MinReturn -100.733 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.06308 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.149 MetaTest/__unnamed_task__/AverageReturn -93.149 MetaTest/__unnamed_task__/Iteration 458 MetaTest/__unnamed_task__/MaxReturn -85.8926 MetaTest/__unnamed_task__/MinReturn -100.733 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.06308 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 749400 ------------------------------------------------- ------------ 2025-04-03 10:03:48 | [pearl_trainer] epoch #459 | Training... 2025-04-03 10:05:17 | [pearl_trainer] epoch #459 | Evaluating... 2025-04-03 10:05:17 | [pearl_trainer] epoch #459 | Sampling for adapation and meta-testing... 2025-04-03 10:06:08 | [pearl_trainer] epoch #459 | Finished meta-testing... 2025-04-03 10:06:08 | [pearl_trainer] epoch #459 | Saving snapshot... 2025-04-03 10:06:09 | [pearl_trainer] epoch #459 | Saved 2025-04-03 10:06:09 | [pearl_trainer] epoch #459 | Time 74245.10 s 2025-04-03 10:06:09 | [pearl_trainer] epoch #459 | EpochTime 163.04 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -84.3835 MetaTest/Average/AverageReturn -84.3835 MetaTest/Average/Iteration 459 MetaTest/Average/MaxReturn -78.4173 MetaTest/Average/MinReturn -90.7876 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.05965 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -84.3835 MetaTest/__unnamed_task__/AverageReturn -84.3835 MetaTest/__unnamed_task__/Iteration 459 MetaTest/__unnamed_task__/MaxReturn -78.4173 MetaTest/__unnamed_task__/MinReturn -90.7876 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.05965 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 751000 ------------------------------------------------- ------------ 2025-04-03 10:06:33 | [pearl_trainer] epoch #460 | Training... 2025-04-03 10:07:54 | [pearl_trainer] epoch #460 | Evaluating... 2025-04-03 10:07:54 | [pearl_trainer] epoch #460 | Sampling for adapation and meta-testing... 2025-04-03 10:08:43 | [pearl_trainer] epoch #460 | Finished meta-testing... 2025-04-03 10:08:43 | [pearl_trainer] epoch #460 | Saving snapshot... 2025-04-03 10:08:45 | [pearl_trainer] epoch #460 | Saved 2025-04-03 10:08:45 | [pearl_trainer] epoch #460 | Time 74400.74 s 2025-04-03 10:08:45 | [pearl_trainer] epoch #460 | EpochTime 155.63 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -85.8064 MetaTest/Average/AverageReturn -85.8064 MetaTest/Average/Iteration 460 MetaTest/Average/MaxReturn -84.3928 MetaTest/Average/MinReturn -88.293 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.76381 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -85.8064 MetaTest/__unnamed_task__/AverageReturn -85.8064 MetaTest/__unnamed_task__/Iteration 460 MetaTest/__unnamed_task__/MaxReturn -84.3928 MetaTest/__unnamed_task__/MinReturn -88.293 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.76381 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 752600 ------------------------------------------------- ------------ 2025-04-03 10:09:08 | [pearl_trainer] epoch #461 | Training... 2025-04-03 10:10:39 | [pearl_trainer] epoch #461 | Evaluating... 2025-04-03 10:10:39 | [pearl_trainer] epoch #461 | Sampling for adapation and meta-testing... 2025-04-03 10:11:25 | [pearl_trainer] epoch #461 | Finished meta-testing... 2025-04-03 10:11:25 | [pearl_trainer] epoch #461 | Saving snapshot... 2025-04-03 10:11:26 | [pearl_trainer] epoch #461 | Saved 2025-04-03 10:11:26 | [pearl_trainer] epoch #461 | Time 74562.58 s 2025-04-03 10:11:26 | [pearl_trainer] epoch #461 | EpochTime 161.84 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -85.8618 MetaTest/Average/AverageReturn -85.8618 MetaTest/Average/Iteration 461 MetaTest/Average/MaxReturn -79.4635 MetaTest/Average/MinReturn -94.2165 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.17969 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -85.8618 MetaTest/__unnamed_task__/AverageReturn -85.8618 MetaTest/__unnamed_task__/Iteration 461 MetaTest/__unnamed_task__/MaxReturn -79.4635 MetaTest/__unnamed_task__/MinReturn -94.2165 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.17969 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 754200 ------------------------------------------------- ------------ 2025-04-03 10:11:48 | [pearl_trainer] epoch #462 | Training... 2025-04-03 10:13:24 | [pearl_trainer] epoch #462 | Evaluating... 2025-04-03 10:13:24 | [pearl_trainer] epoch #462 | Sampling for adapation and meta-testing... 2025-04-03 10:14:12 | [pearl_trainer] epoch #462 | Finished meta-testing... 2025-04-03 10:14:12 | [pearl_trainer] epoch #462 | Saving snapshot... 2025-04-03 10:14:14 | [pearl_trainer] epoch #462 | Saved 2025-04-03 10:14:14 | [pearl_trainer] epoch #462 | Time 74729.84 s 2025-04-03 10:14:14 | [pearl_trainer] epoch #462 | EpochTime 167.26 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -79.0893 MetaTest/Average/AverageReturn -79.0893 MetaTest/Average/Iteration 462 MetaTest/Average/MaxReturn -76.3716 MetaTest/Average/MinReturn -81.6295 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.15023 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -79.0893 MetaTest/__unnamed_task__/AverageReturn -79.0893 MetaTest/__unnamed_task__/Iteration 462 MetaTest/__unnamed_task__/MaxReturn -76.3716 MetaTest/__unnamed_task__/MinReturn -81.6295 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.15023 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 755800 ------------------------------------------------- ------------ 2025-04-03 10:14:36 | [pearl_trainer] epoch #463 | Training... 2025-04-03 10:16:01 | [pearl_trainer] epoch #463 | Evaluating... 2025-04-03 10:16:01 | [pearl_trainer] epoch #463 | Sampling for adapation and meta-testing... 2025-04-03 10:16:52 | [pearl_trainer] epoch #463 | Finished meta-testing... 2025-04-03 10:16:52 | [pearl_trainer] epoch #463 | Saving snapshot... 2025-04-03 10:16:53 | [pearl_trainer] epoch #463 | Saved 2025-04-03 10:16:53 | [pearl_trainer] epoch #463 | Time 74889.32 s 2025-04-03 10:16:53 | [pearl_trainer] epoch #463 | EpochTime 159.48 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -91.0116 MetaTest/Average/AverageReturn -91.0116 MetaTest/Average/Iteration 463 MetaTest/Average/MaxReturn -79.9913 MetaTest/Average/MinReturn -111.133 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.2497 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -91.0116 MetaTest/__unnamed_task__/AverageReturn -91.0116 MetaTest/__unnamed_task__/Iteration 463 MetaTest/__unnamed_task__/MaxReturn -79.9913 MetaTest/__unnamed_task__/MinReturn -111.133 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.2497 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 757400 ------------------------------------------------- ----------- 2025-04-03 10:17:20 | [pearl_trainer] epoch #464 | Training... 2025-04-03 10:18:50 | [pearl_trainer] epoch #464 | Evaluating... 2025-04-03 10:18:50 | [pearl_trainer] epoch #464 | Sampling for adapation and meta-testing... 2025-04-03 10:19:39 | [pearl_trainer] epoch #464 | Finished meta-testing... 2025-04-03 10:19:39 | [pearl_trainer] epoch #464 | Saving snapshot... 2025-04-03 10:19:40 | [pearl_trainer] epoch #464 | Saved 2025-04-03 10:19:40 | [pearl_trainer] epoch #464 | Time 75056.68 s 2025-04-03 10:19:40 | [pearl_trainer] epoch #464 | EpochTime 167.37 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -81.7742 MetaTest/Average/AverageReturn -81.7742 MetaTest/Average/Iteration 464 MetaTest/Average/MaxReturn -80.2857 MetaTest/Average/MinReturn -83.0555 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.14023 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -81.7742 MetaTest/__unnamed_task__/AverageReturn -81.7742 MetaTest/__unnamed_task__/Iteration 464 MetaTest/__unnamed_task__/MaxReturn -80.2857 MetaTest/__unnamed_task__/MinReturn -83.0555 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.14023 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 759000 ------------------------------------------------- ------------ 2025-04-03 10:20:04 | [pearl_trainer] epoch #465 | Training... 2025-04-03 10:21:36 | [pearl_trainer] epoch #465 | Evaluating... 2025-04-03 10:21:36 | [pearl_trainer] epoch #465 | Sampling for adapation and meta-testing... 2025-04-03 10:22:22 | [pearl_trainer] epoch #465 | Finished meta-testing... 2025-04-03 10:22:22 | [pearl_trainer] epoch #465 | Saving snapshot... 2025-04-03 10:22:23 | [pearl_trainer] epoch #465 | Saved 2025-04-03 10:22:23 | [pearl_trainer] epoch #465 | Time 75219.09 s 2025-04-03 10:22:23 | [pearl_trainer] epoch #465 | EpochTime 162.40 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -85.4386 MetaTest/Average/AverageReturn -85.4386 MetaTest/Average/Iteration 465 MetaTest/Average/MaxReturn -81.0243 MetaTest/Average/MinReturn -88.0092 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.13541 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -85.4386 MetaTest/__unnamed_task__/AverageReturn -85.4386 MetaTest/__unnamed_task__/Iteration 465 MetaTest/__unnamed_task__/MaxReturn -81.0243 MetaTest/__unnamed_task__/MinReturn -88.0092 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.13541 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 760600 ------------------------------------------------- ------------ 2025-04-03 10:22:45 | [pearl_trainer] epoch #466 | Training... 2025-04-03 10:24:14 | [pearl_trainer] epoch #466 | Evaluating... 2025-04-03 10:24:14 | [pearl_trainer] epoch #466 | Sampling for adapation and meta-testing... 2025-04-03 10:25:04 | [pearl_trainer] epoch #466 | Finished meta-testing... 2025-04-03 10:25:04 | [pearl_trainer] epoch #466 | Saving snapshot... 2025-04-03 10:25:05 | [pearl_trainer] epoch #466 | Saved 2025-04-03 10:25:05 | [pearl_trainer] epoch #466 | Time 75381.53 s 2025-04-03 10:25:05 | [pearl_trainer] epoch #466 | EpochTime 162.44 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -78.8121 MetaTest/Average/AverageReturn -78.8121 MetaTest/Average/Iteration 466 MetaTest/Average/MaxReturn -74.6333 MetaTest/Average/MinReturn -84.8226 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.35675 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -78.8121 MetaTest/__unnamed_task__/AverageReturn -78.8121 MetaTest/__unnamed_task__/Iteration 466 MetaTest/__unnamed_task__/MaxReturn -74.6333 MetaTest/__unnamed_task__/MinReturn -84.8226 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.35675 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 762200 ------------------------------------------------- ------------ 2025-04-03 10:25:29 | [pearl_trainer] epoch #467 | Training... 2025-04-03 10:26:55 | [pearl_trainer] epoch #467 | Evaluating... 2025-04-03 10:26:55 | [pearl_trainer] epoch #467 | Sampling for adapation and meta-testing... 2025-04-03 10:27:46 | [pearl_trainer] epoch #467 | Finished meta-testing... 2025-04-03 10:27:46 | [pearl_trainer] epoch #467 | Saving snapshot... 2025-04-03 10:27:47 | [pearl_trainer] epoch #467 | Saved 2025-04-03 10:27:47 | [pearl_trainer] epoch #467 | Time 75543.37 s 2025-04-03 10:27:47 | [pearl_trainer] epoch #467 | EpochTime 161.84 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -81.8661 MetaTest/Average/AverageReturn -81.8661 MetaTest/Average/Iteration 467 MetaTest/Average/MaxReturn -75.2076 MetaTest/Average/MinReturn -86.2795 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.7908 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -81.8661 MetaTest/__unnamed_task__/AverageReturn -81.8661 MetaTest/__unnamed_task__/Iteration 467 MetaTest/__unnamed_task__/MaxReturn -75.2076 MetaTest/__unnamed_task__/MinReturn -86.2795 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.7908 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 763800 ------------------------------------------------- ----------- 2025-04-03 10:28:12 | [pearl_trainer] epoch #468 | Training... 2025-04-03 10:29:57 | [pearl_trainer] epoch #468 | Evaluating... 2025-04-03 10:29:57 | [pearl_trainer] epoch #468 | Sampling for adapation and meta-testing... 2025-04-03 10:30:43 | [pearl_trainer] epoch #468 | Finished meta-testing... 2025-04-03 10:30:43 | [pearl_trainer] epoch #468 | Saving snapshot... 2025-04-03 10:30:44 | [pearl_trainer] epoch #468 | Saved 2025-04-03 10:30:44 | [pearl_trainer] epoch #468 | Time 75719.99 s 2025-04-03 10:30:44 | [pearl_trainer] epoch #468 | EpochTime 176.61 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -80.3709 MetaTest/Average/AverageReturn -80.3709 MetaTest/Average/Iteration 468 MetaTest/Average/MaxReturn -74.5195 MetaTest/Average/MinReturn -86.2505 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.78921 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -80.3709 MetaTest/__unnamed_task__/AverageReturn -80.3709 MetaTest/__unnamed_task__/Iteration 468 MetaTest/__unnamed_task__/MaxReturn -74.5195 MetaTest/__unnamed_task__/MinReturn -86.2505 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.78921 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 765400 ------------------------------------------------- ------------ 2025-04-03 10:31:06 | [pearl_trainer] epoch #469 | Training... 2025-04-03 10:32:34 | [pearl_trainer] epoch #469 | Evaluating... 2025-04-03 10:32:34 | [pearl_trainer] epoch #469 | Sampling for adapation and meta-testing... 2025-04-03 10:33:28 | [pearl_trainer] epoch #469 | Finished meta-testing... 2025-04-03 10:33:28 | [pearl_trainer] epoch #469 | Saving snapshot... 2025-04-03 10:33:29 | [pearl_trainer] epoch #469 | Saved 2025-04-03 10:33:29 | [pearl_trainer] epoch #469 | Time 75885.46 s 2025-04-03 10:33:29 | [pearl_trainer] epoch #469 | EpochTime 165.47 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -86.5398 MetaTest/Average/AverageReturn -86.5398 MetaTest/Average/Iteration 469 MetaTest/Average/MaxReturn -83.6458 MetaTest/Average/MinReturn -89.362 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.33419 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -86.5398 MetaTest/__unnamed_task__/AverageReturn -86.5398 MetaTest/__unnamed_task__/Iteration 469 MetaTest/__unnamed_task__/MaxReturn -83.6458 MetaTest/__unnamed_task__/MinReturn -89.362 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.33419 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 767000 ------------------------------------------------- ------------ 2025-04-03 10:33:52 | [pearl_trainer] epoch #470 | Training... 2025-04-03 10:35:14 | [pearl_trainer] epoch #470 | Evaluating... 2025-04-03 10:35:14 | [pearl_trainer] epoch #470 | Sampling for adapation and meta-testing... 2025-04-03 10:36:04 | [pearl_trainer] epoch #470 | Finished meta-testing... 2025-04-03 10:36:04 | [pearl_trainer] epoch #470 | Saving snapshot... 2025-04-03 10:36:06 | [pearl_trainer] epoch #470 | Saved 2025-04-03 10:36:06 | [pearl_trainer] epoch #470 | Time 76041.72 s 2025-04-03 10:36:06 | [pearl_trainer] epoch #470 | EpochTime 156.25 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -87.391 MetaTest/Average/AverageReturn -87.391 MetaTest/Average/Iteration 470 MetaTest/Average/MaxReturn -82.1522 MetaTest/Average/MinReturn -91.7351 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.963 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -87.391 MetaTest/__unnamed_task__/AverageReturn -87.391 MetaTest/__unnamed_task__/Iteration 470 MetaTest/__unnamed_task__/MaxReturn -82.1522 MetaTest/__unnamed_task__/MinReturn -91.7351 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.963 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 768600 ------------------------------------------------- ----------- 2025-04-03 10:36:28 | [pearl_trainer] epoch #471 | Training... 2025-04-03 10:37:58 | [pearl_trainer] epoch #471 | Evaluating... 2025-04-03 10:37:58 | [pearl_trainer] epoch #471 | Sampling for adapation and meta-testing... 2025-04-03 10:38:47 | [pearl_trainer] epoch #471 | Finished meta-testing... 2025-04-03 10:38:47 | [pearl_trainer] epoch #471 | Saving snapshot... 2025-04-03 10:38:48 | [pearl_trainer] epoch #471 | Saved 2025-04-03 10:38:48 | [pearl_trainer] epoch #471 | Time 76204.67 s 2025-04-03 10:38:48 | [pearl_trainer] epoch #471 | EpochTime 162.95 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -85.3715 MetaTest/Average/AverageReturn -85.3715 MetaTest/Average/Iteration 471 MetaTest/Average/MaxReturn -82.7586 MetaTest/Average/MinReturn -90.4086 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.56264 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -85.3715 MetaTest/__unnamed_task__/AverageReturn -85.3715 MetaTest/__unnamed_task__/Iteration 471 MetaTest/__unnamed_task__/MaxReturn -82.7586 MetaTest/__unnamed_task__/MinReturn -90.4086 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.56264 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 770200 ------------------------------------------------- ------------ 2025-04-03 10:39:12 | [pearl_trainer] epoch #472 | Training... 2025-04-03 10:40:39 | [pearl_trainer] epoch #472 | Evaluating... 2025-04-03 10:40:39 | [pearl_trainer] epoch #472 | Sampling for adapation and meta-testing... 2025-04-03 10:41:34 | [pearl_trainer] epoch #472 | Finished meta-testing... 2025-04-03 10:41:34 | [pearl_trainer] epoch #472 | Saving snapshot... 2025-04-03 10:41:35 | [pearl_trainer] epoch #472 | Saved 2025-04-03 10:41:35 | [pearl_trainer] epoch #472 | Time 76371.61 s 2025-04-03 10:41:35 | [pearl_trainer] epoch #472 | EpochTime 166.94 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -93.7477 MetaTest/Average/AverageReturn -93.7477 MetaTest/Average/Iteration 472 MetaTest/Average/MaxReturn -78.9532 MetaTest/Average/MinReturn -108.931 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.2414 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.7477 MetaTest/__unnamed_task__/AverageReturn -93.7477 MetaTest/__unnamed_task__/Iteration 472 MetaTest/__unnamed_task__/MaxReturn -78.9532 MetaTest/__unnamed_task__/MinReturn -108.931 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.2414 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 771800 ------------------------------------------------- ----------- 2025-04-03 10:41:59 | [pearl_trainer] epoch #473 | Training... 2025-04-03 10:43:26 | [pearl_trainer] epoch #473 | Evaluating... 2025-04-03 10:43:26 | [pearl_trainer] epoch #473 | Sampling for adapation and meta-testing... 2025-04-03 10:44:11 | [pearl_trainer] epoch #473 | Finished meta-testing... 2025-04-03 10:44:11 | [pearl_trainer] epoch #473 | Saving snapshot... 2025-04-03 10:44:13 | [pearl_trainer] epoch #473 | Saved 2025-04-03 10:44:13 | [pearl_trainer] epoch #473 | Time 76528.93 s 2025-04-03 10:44:13 | [pearl_trainer] epoch #473 | EpochTime 157.32 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -85.1044 MetaTest/Average/AverageReturn -85.1044 MetaTest/Average/Iteration 473 MetaTest/Average/MaxReturn -81.724 MetaTest/Average/MinReturn -87.7482 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 2.51391 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -85.1044 MetaTest/__unnamed_task__/AverageReturn -85.1044 MetaTest/__unnamed_task__/Iteration 473 MetaTest/__unnamed_task__/MaxReturn -81.724 MetaTest/__unnamed_task__/MinReturn -87.7482 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 2.51391 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 773400 ------------------------------------------------- ------------ 2025-04-03 10:44:35 | [pearl_trainer] epoch #474 | Training... 2025-04-03 10:46:08 | [pearl_trainer] epoch #474 | Evaluating... 2025-04-03 10:46:08 | [pearl_trainer] epoch #474 | Sampling for adapation and meta-testing... 2025-04-03 10:46:59 | [pearl_trainer] epoch #474 | Finished meta-testing... 2025-04-03 10:46:59 | [pearl_trainer] epoch #474 | Saving snapshot... 2025-04-03 10:47:00 | [pearl_trainer] epoch #474 | Saved 2025-04-03 10:47:00 | [pearl_trainer] epoch #474 | Time 76695.86 s 2025-04-03 10:47:00 | [pearl_trainer] epoch #474 | EpochTime 166.92 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -114.493 MetaTest/Average/AverageReturn -114.493 MetaTest/Average/Iteration 474 MetaTest/Average/MaxReturn -88.3859 MetaTest/Average/MinReturn -137.463 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 20.158 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -114.493 MetaTest/__unnamed_task__/AverageReturn -114.493 MetaTest/__unnamed_task__/Iteration 474 MetaTest/__unnamed_task__/MaxReturn -88.3859 MetaTest/__unnamed_task__/MinReturn -137.463 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 20.158 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 775000 ------------------------------------------------- ----------- 2025-04-03 10:47:22 | [pearl_trainer] epoch #475 | Training... 2025-04-03 10:48:45 | [pearl_trainer] epoch #475 | Evaluating... 2025-04-03 10:48:45 | [pearl_trainer] epoch #475 | Sampling for adapation and meta-testing... 2025-04-03 10:49:35 | [pearl_trainer] epoch #475 | Finished meta-testing... 2025-04-03 10:49:35 | [pearl_trainer] epoch #475 | Saving snapshot... 2025-04-03 10:49:36 | [pearl_trainer] epoch #475 | Saved 2025-04-03 10:49:36 | [pearl_trainer] epoch #475 | Time 76852.48 s 2025-04-03 10:49:36 | [pearl_trainer] epoch #475 | EpochTime 156.62 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -120.502 MetaTest/Average/AverageReturn -120.502 MetaTest/Average/Iteration 475 MetaTest/Average/MaxReturn -115.52 MetaTest/Average/MinReturn -128.753 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.87638 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -120.502 MetaTest/__unnamed_task__/AverageReturn -120.502 MetaTest/__unnamed_task__/Iteration 475 MetaTest/__unnamed_task__/MaxReturn -115.52 MetaTest/__unnamed_task__/MinReturn -128.753 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.87638 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 776600 ------------------------------------------------- ------------ 2025-04-03 10:50:01 | [pearl_trainer] epoch #476 | Training... 2025-04-03 10:51:27 | [pearl_trainer] epoch #476 | Evaluating... 2025-04-03 10:51:27 | [pearl_trainer] epoch #476 | Sampling for adapation and meta-testing... 2025-04-03 10:52:16 | [pearl_trainer] epoch #476 | Finished meta-testing... 2025-04-03 10:52:16 | [pearl_trainer] epoch #476 | Saving snapshot... 2025-04-03 10:52:17 | [pearl_trainer] epoch #476 | Saved 2025-04-03 10:52:17 | [pearl_trainer] epoch #476 | Time 77013.33 s 2025-04-03 10:52:17 | [pearl_trainer] epoch #476 | EpochTime 160.85 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -114.918 MetaTest/Average/AverageReturn -114.918 MetaTest/Average/Iteration 476 MetaTest/Average/MaxReturn -107.074 MetaTest/Average/MinReturn -123.153 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.57015 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -114.918 MetaTest/__unnamed_task__/AverageReturn -114.918 MetaTest/__unnamed_task__/Iteration 476 MetaTest/__unnamed_task__/MaxReturn -107.074 MetaTest/__unnamed_task__/MinReturn -123.153 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.57015 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 778200 ------------------------------------------------- ------------ 2025-04-03 10:52:42 | [pearl_trainer] epoch #477 | Training... 2025-04-03 10:54:12 | [pearl_trainer] epoch #477 | Evaluating... 2025-04-03 10:54:12 | [pearl_trainer] epoch #477 | Sampling for adapation and meta-testing... 2025-04-03 10:54:59 | [pearl_trainer] epoch #477 | Finished meta-testing... 2025-04-03 10:54:59 | [pearl_trainer] epoch #477 | Saving snapshot... 2025-04-03 10:55:00 | [pearl_trainer] epoch #477 | Saved 2025-04-03 10:55:00 | [pearl_trainer] epoch #477 | Time 77176.11 s 2025-04-03 10:55:00 | [pearl_trainer] epoch #477 | EpochTime 162.78 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -150.67 MetaTest/Average/AverageReturn -150.67 MetaTest/Average/Iteration 477 MetaTest/Average/MaxReturn -149.194 MetaTest/Average/MinReturn -152.297 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 1.27152 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -150.67 MetaTest/__unnamed_task__/AverageReturn -150.67 MetaTest/__unnamed_task__/Iteration 477 MetaTest/__unnamed_task__/MaxReturn -149.194 MetaTest/__unnamed_task__/MinReturn -152.297 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 1.27152 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 779800 ------------------------------------------------- ------------ 2025-04-03 10:55:22 | [pearl_trainer] epoch #478 | Training... 2025-04-03 10:56:49 | [pearl_trainer] epoch #478 | Evaluating... 2025-04-03 10:56:49 | [pearl_trainer] epoch #478 | Sampling for adapation and meta-testing... 2025-04-03 10:57:38 | [pearl_trainer] epoch #478 | Finished meta-testing... 2025-04-03 10:57:38 | [pearl_trainer] epoch #478 | Saving snapshot... 2025-04-03 10:57:40 | [pearl_trainer] epoch #478 | Saved 2025-04-03 10:57:40 | [pearl_trainer] epoch #478 | Time 77336.05 s 2025-04-03 10:57:40 | [pearl_trainer] epoch #478 | EpochTime 159.94 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -124.862 MetaTest/Average/AverageReturn -124.862 MetaTest/Average/Iteration 478 MetaTest/Average/MaxReturn -108.866 MetaTest/Average/MinReturn -140.121 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.7705 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -124.862 MetaTest/__unnamed_task__/AverageReturn -124.862 MetaTest/__unnamed_task__/Iteration 478 MetaTest/__unnamed_task__/MaxReturn -108.866 MetaTest/__unnamed_task__/MinReturn -140.121 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.7705 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 781400 ------------------------------------------------- ----------- 2025-04-03 10:58:03 | [pearl_trainer] epoch #479 | Training... 2025-04-03 10:59:27 | [pearl_trainer] epoch #479 | Evaluating... 2025-04-03 10:59:27 | [pearl_trainer] epoch #479 | Sampling for adapation and meta-testing... 2025-04-03 11:00:18 | [pearl_trainer] epoch #479 | Finished meta-testing... 2025-04-03 11:00:18 | [pearl_trainer] epoch #479 | Saving snapshot... 2025-04-03 11:00:19 | [pearl_trainer] epoch #479 | Saved 2025-04-03 11:00:19 | [pearl_trainer] epoch #479 | Time 77495.58 s 2025-04-03 11:00:19 | [pearl_trainer] epoch #479 | EpochTime 159.52 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -125.78 MetaTest/Average/AverageReturn -125.78 MetaTest/Average/Iteration 479 MetaTest/Average/MaxReturn -114.191 MetaTest/Average/MinReturn -131.586 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.19458 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -125.78 MetaTest/__unnamed_task__/AverageReturn -125.78 MetaTest/__unnamed_task__/Iteration 479 MetaTest/__unnamed_task__/MaxReturn -114.191 MetaTest/__unnamed_task__/MinReturn -131.586 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.19458 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 783000 ------------------------------------------------- ------------ 2025-04-03 11:00:44 | [pearl_trainer] epoch #480 | Training... 2025-04-03 11:02:20 | [pearl_trainer] epoch #480 | Evaluating... 2025-04-03 11:02:20 | [pearl_trainer] epoch #480 | Sampling for adapation and meta-testing... 2025-04-03 11:03:08 | [pearl_trainer] epoch #480 | Finished meta-testing... 2025-04-03 11:03:08 | [pearl_trainer] epoch #480 | Saving snapshot... 2025-04-03 11:03:09 | [pearl_trainer] epoch #480 | Saved 2025-04-03 11:03:09 | [pearl_trainer] epoch #480 | Time 77665.19 s 2025-04-03 11:03:09 | [pearl_trainer] epoch #480 | EpochTime 169.60 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -105.771 MetaTest/Average/AverageReturn -105.771 MetaTest/Average/Iteration 480 MetaTest/Average/MaxReturn -96.9242 MetaTest/Average/MinReturn -117.577 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.68728 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -105.771 MetaTest/__unnamed_task__/AverageReturn -105.771 MetaTest/__unnamed_task__/Iteration 480 MetaTest/__unnamed_task__/MaxReturn -96.9242 MetaTest/__unnamed_task__/MinReturn -117.577 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.68728 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 784600 ------------------------------------------------- ------------ 2025-04-03 11:03:33 | [pearl_trainer] epoch #481 | Training... 2025-04-03 11:04:57 | [pearl_trainer] epoch #481 | Evaluating... 2025-04-03 11:04:57 | [pearl_trainer] epoch #481 | Sampling for adapation and meta-testing... 2025-04-03 11:05:50 | [pearl_trainer] epoch #481 | Finished meta-testing... 2025-04-03 11:05:50 | [pearl_trainer] epoch #481 | Saving snapshot... 2025-04-03 11:05:51 | [pearl_trainer] epoch #481 | Saved 2025-04-03 11:05:51 | [pearl_trainer] epoch #481 | Time 77827.62 s 2025-04-03 11:05:51 | [pearl_trainer] epoch #481 | EpochTime 162.44 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -117.92 MetaTest/Average/AverageReturn -117.92 MetaTest/Average/Iteration 481 MetaTest/Average/MaxReturn -103.183 MetaTest/Average/MinReturn -142.435 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 17.4525 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -117.92 MetaTest/__unnamed_task__/AverageReturn -117.92 MetaTest/__unnamed_task__/Iteration 481 MetaTest/__unnamed_task__/MaxReturn -103.183 MetaTest/__unnamed_task__/MinReturn -142.435 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 17.4525 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 786200 ------------------------------------------------- ----------- 2025-04-03 11:06:16 | [pearl_trainer] epoch #482 | Training... 2025-04-03 11:07:44 | [pearl_trainer] epoch #482 | Evaluating... 2025-04-03 11:07:44 | [pearl_trainer] epoch #482 | Sampling for adapation and meta-testing... 2025-04-03 11:08:30 | [pearl_trainer] epoch #482 | Finished meta-testing... 2025-04-03 11:08:30 | [pearl_trainer] epoch #482 | Saving snapshot... 2025-04-03 11:08:31 | [pearl_trainer] epoch #482 | Saved 2025-04-03 11:08:31 | [pearl_trainer] epoch #482 | Time 77986.78 s 2025-04-03 11:08:31 | [pearl_trainer] epoch #482 | EpochTime 159.15 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -100.487 MetaTest/Average/AverageReturn -100.487 MetaTest/Average/Iteration 482 MetaTest/Average/MaxReturn -92.0197 MetaTest/Average/MinReturn -110.845 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 7.80104 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -100.487 MetaTest/__unnamed_task__/AverageReturn -100.487 MetaTest/__unnamed_task__/Iteration 482 MetaTest/__unnamed_task__/MaxReturn -92.0197 MetaTest/__unnamed_task__/MinReturn -110.845 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 7.80104 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 787800 ------------------------------------------------- ------------ 2025-04-03 11:08:54 | [pearl_trainer] epoch #483 | Training... 2025-04-03 11:10:31 | [pearl_trainer] epoch #483 | Evaluating... 2025-04-03 11:10:31 | [pearl_trainer] epoch #483 | Sampling for adapation and meta-testing... 2025-04-03 11:11:16 | [pearl_trainer] epoch #483 | Finished meta-testing... 2025-04-03 11:11:16 | [pearl_trainer] epoch #483 | Saving snapshot... 2025-04-03 11:11:18 | [pearl_trainer] epoch #483 | Saved 2025-04-03 11:11:18 | [pearl_trainer] epoch #483 | Time 78153.91 s 2025-04-03 11:11:18 | [pearl_trainer] epoch #483 | EpochTime 167.13 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -107.356 MetaTest/Average/AverageReturn -107.356 MetaTest/Average/Iteration 483 MetaTest/Average/MaxReturn -86.1559 MetaTest/Average/MinReturn -122.01 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 15.3519 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -107.356 MetaTest/__unnamed_task__/AverageReturn -107.356 MetaTest/__unnamed_task__/Iteration 483 MetaTest/__unnamed_task__/MaxReturn -86.1559 MetaTest/__unnamed_task__/MinReturn -122.01 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 15.3519 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 789400 ------------------------------------------------- ----------- 2025-04-03 11:11:40 | [pearl_trainer] epoch #484 | Training... 2025-04-03 11:13:12 | [pearl_trainer] epoch #484 | Evaluating... 2025-04-03 11:13:12 | [pearl_trainer] epoch #484 | Sampling for adapation and meta-testing... 2025-04-03 11:14:07 | [pearl_trainer] epoch #484 | Finished meta-testing... 2025-04-03 11:14:07 | [pearl_trainer] epoch #484 | Saving snapshot... 2025-04-03 11:14:08 | [pearl_trainer] epoch #484 | Saved 2025-04-03 11:14:08 | [pearl_trainer] epoch #484 | Time 78324.48 s 2025-04-03 11:14:08 | [pearl_trainer] epoch #484 | EpochTime 170.57 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -102.49 MetaTest/Average/AverageReturn -102.49 MetaTest/Average/Iteration 484 MetaTest/Average/MaxReturn -99.3304 MetaTest/Average/MinReturn -107.008 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.27807 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -102.49 MetaTest/__unnamed_task__/AverageReturn -102.49 MetaTest/__unnamed_task__/Iteration 484 MetaTest/__unnamed_task__/MaxReturn -99.3304 MetaTest/__unnamed_task__/MinReturn -107.008 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.27807 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 791000 ------------------------------------------------- ------------ 2025-04-03 11:14:30 | [pearl_trainer] epoch #485 | Training... 2025-04-03 11:15:58 | [pearl_trainer] epoch #485 | Evaluating... 2025-04-03 11:15:58 | [pearl_trainer] epoch #485 | Sampling for adapation and meta-testing... 2025-04-03 11:16:45 | [pearl_trainer] epoch #485 | Finished meta-testing... 2025-04-03 11:16:45 | [pearl_trainer] epoch #485 | Saving snapshot... 2025-04-03 11:16:46 | [pearl_trainer] epoch #485 | Saved 2025-04-03 11:16:46 | [pearl_trainer] epoch #485 | Time 78482.18 s 2025-04-03 11:16:46 | [pearl_trainer] epoch #485 | EpochTime 157.70 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -92.0264 MetaTest/Average/AverageReturn -92.0264 MetaTest/Average/Iteration 485 MetaTest/Average/MaxReturn -87.7203 MetaTest/Average/MinReturn -97.0388 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 3.83693 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -92.0264 MetaTest/__unnamed_task__/AverageReturn -92.0264 MetaTest/__unnamed_task__/Iteration 485 MetaTest/__unnamed_task__/MaxReturn -87.7203 MetaTest/__unnamed_task__/MinReturn -97.0388 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 3.83693 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 792600 ------------------------------------------------- ------------ 2025-04-03 11:17:09 | [pearl_trainer] epoch #486 | Training... 2025-04-03 11:18:44 | [pearl_trainer] epoch #486 | Evaluating... 2025-04-03 11:18:44 | [pearl_trainer] epoch #486 | Sampling for adapation and meta-testing... 2025-04-03 11:19:30 | [pearl_trainer] epoch #486 | Finished meta-testing... 2025-04-03 11:19:30 | [pearl_trainer] epoch #486 | Saving snapshot... 2025-04-03 11:19:31 | [pearl_trainer] epoch #486 | Saved 2025-04-03 11:19:31 | [pearl_trainer] epoch #486 | Time 78647.28 s 2025-04-03 11:19:31 | [pearl_trainer] epoch #486 | EpochTime 165.09 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -95.82 MetaTest/Average/AverageReturn -95.82 MetaTest/Average/Iteration 486 MetaTest/Average/MaxReturn -86.7203 MetaTest/Average/MinReturn -110.043 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 10.1876 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.82 MetaTest/__unnamed_task__/AverageReturn -95.82 MetaTest/__unnamed_task__/Iteration 486 MetaTest/__unnamed_task__/MaxReturn -86.7203 MetaTest/__unnamed_task__/MinReturn -110.043 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 10.1876 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 794200 ------------------------------------------------- ----------- 2025-04-03 11:19:53 | [pearl_trainer] epoch #487 | Training... 2025-04-03 11:21:20 | [pearl_trainer] epoch #487 | Evaluating... 2025-04-03 11:21:20 | [pearl_trainer] epoch #487 | Sampling for adapation and meta-testing... 2025-04-03 11:22:15 | [pearl_trainer] epoch #487 | Finished meta-testing... 2025-04-03 11:22:15 | [pearl_trainer] epoch #487 | Saving snapshot... 2025-04-03 11:22:16 | [pearl_trainer] epoch #487 | Saved 2025-04-03 11:22:16 | [pearl_trainer] epoch #487 | Time 78811.95 s 2025-04-03 11:22:16 | [pearl_trainer] epoch #487 | EpochTime 164.67 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.8035 MetaTest/Average/AverageReturn -93.8035 MetaTest/Average/Iteration 487 MetaTest/Average/MaxReturn -87.1797 MetaTest/Average/MinReturn -106.723 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 9.13663 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.8035 MetaTest/__unnamed_task__/AverageReturn -93.8035 MetaTest/__unnamed_task__/Iteration 487 MetaTest/__unnamed_task__/MaxReturn -87.1797 MetaTest/__unnamed_task__/MinReturn -106.723 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 9.13663 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 795800 ------------------------------------------------- ------------ 2025-04-03 11:22:38 | [pearl_trainer] epoch #488 | Training... 2025-04-03 11:23:59 | [pearl_trainer] epoch #488 | Evaluating... 2025-04-03 11:23:59 | [pearl_trainer] epoch #488 | Sampling for adapation and meta-testing... 2025-04-03 11:24:47 | [pearl_trainer] epoch #488 | Finished meta-testing... 2025-04-03 11:24:47 | [pearl_trainer] epoch #488 | Saving snapshot... 2025-04-03 11:24:48 | [pearl_trainer] epoch #488 | Saved 2025-04-03 11:24:48 | [pearl_trainer] epoch #488 | Time 78964.55 s 2025-04-03 11:24:48 | [pearl_trainer] epoch #488 | EpochTime 152.60 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -93.797 MetaTest/Average/AverageReturn -93.797 MetaTest/Average/Iteration 488 MetaTest/Average/MaxReturn -85.5658 MetaTest/Average/MinReturn -105.142 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.28941 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -93.797 MetaTest/__unnamed_task__/AverageReturn -93.797 MetaTest/__unnamed_task__/Iteration 488 MetaTest/__unnamed_task__/MaxReturn -85.5658 MetaTest/__unnamed_task__/MinReturn -105.142 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.28941 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 797400 ------------------------------------------------- ------------ 2025-04-03 11:25:15 | [pearl_trainer] epoch #489 | Training... 2025-04-03 11:26:46 | [pearl_trainer] epoch #489 | Evaluating... 2025-04-03 11:26:46 | [pearl_trainer] epoch #489 | Sampling for adapation and meta-testing... 2025-04-03 11:27:33 | [pearl_trainer] epoch #489 | Finished meta-testing... 2025-04-03 11:27:33 | [pearl_trainer] epoch #489 | Saving snapshot... 2025-04-03 11:27:34 | [pearl_trainer] epoch #489 | Saved 2025-04-03 11:27:34 | [pearl_trainer] epoch #489 | Time 79130.20 s 2025-04-03 11:27:34 | [pearl_trainer] epoch #489 | EpochTime 165.65 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -87.9433 MetaTest/Average/AverageReturn -87.9433 MetaTest/Average/Iteration 489 MetaTest/Average/MaxReturn -81.8199 MetaTest/Average/MinReturn -91.4029 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.34203 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -87.9433 MetaTest/__unnamed_task__/AverageReturn -87.9433 MetaTest/__unnamed_task__/Iteration 489 MetaTest/__unnamed_task__/MaxReturn -81.8199 MetaTest/__unnamed_task__/MinReturn -91.4029 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.34203 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 799000 ------------------------------------------------- ------------ 2025-04-03 11:27:58 | [pearl_trainer] epoch #490 | Training... 2025-04-03 11:29:29 | [pearl_trainer] epoch #490 | Evaluating... 2025-04-03 11:29:29 | [pearl_trainer] epoch #490 | Sampling for adapation and meta-testing... 2025-04-03 11:30:24 | [pearl_trainer] epoch #490 | Finished meta-testing... 2025-04-03 11:30:24 | [pearl_trainer] epoch #490 | Saving snapshot... 2025-04-03 11:30:25 | [pearl_trainer] epoch #490 | Saved 2025-04-03 11:30:25 | [pearl_trainer] epoch #490 | Time 79301.62 s 2025-04-03 11:30:25 | [pearl_trainer] epoch #490 | EpochTime 171.42 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -85.5722 MetaTest/Average/AverageReturn -85.5722 MetaTest/Average/Iteration 490 MetaTest/Average/MaxReturn -84.954 MetaTest/Average/MinReturn -86.044 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 0.456879 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -85.5722 MetaTest/__unnamed_task__/AverageReturn -85.5722 MetaTest/__unnamed_task__/Iteration 490 MetaTest/__unnamed_task__/MaxReturn -84.954 MetaTest/__unnamed_task__/MinReturn -86.044 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 0.456879 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 800600 ------------------------------------------------- ------------- 2025-04-03 11:30:49 | [pearl_trainer] epoch #491 | Training... 2025-04-03 11:32:18 | [pearl_trainer] epoch #491 | Evaluating... 2025-04-03 11:32:18 | [pearl_trainer] epoch #491 | Sampling for adapation and meta-testing... 2025-04-03 11:33:09 | [pearl_trainer] epoch #491 | Finished meta-testing... 2025-04-03 11:33:09 | [pearl_trainer] epoch #491 | Saving snapshot... 2025-04-03 11:33:10 | [pearl_trainer] epoch #491 | Saved 2025-04-03 11:33:10 | [pearl_trainer] epoch #491 | Time 79466.45 s 2025-04-03 11:33:10 | [pearl_trainer] epoch #491 | EpochTime 164.83 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -95.35 MetaTest/Average/AverageReturn -95.35 MetaTest/Average/Iteration 491 MetaTest/Average/MaxReturn -77.2483 MetaTest/Average/MinReturn -121.113 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 18.7093 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -95.35 MetaTest/__unnamed_task__/AverageReturn -95.35 MetaTest/__unnamed_task__/Iteration 491 MetaTest/__unnamed_task__/MaxReturn -77.2483 MetaTest/__unnamed_task__/MinReturn -121.113 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 18.7093 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 802200 ------------------------------------------------- ----------- 2025-04-03 11:33:34 | [pearl_trainer] epoch #492 | Training... 2025-04-03 11:35:00 | [pearl_trainer] epoch #492 | Evaluating... 2025-04-03 11:35:00 | [pearl_trainer] epoch #492 | Sampling for adapation and meta-testing... 2025-04-03 11:35:49 | [pearl_trainer] epoch #492 | Finished meta-testing... 2025-04-03 11:35:49 | [pearl_trainer] epoch #492 | Saving snapshot... 2025-04-03 11:35:50 | [pearl_trainer] epoch #492 | Saved 2025-04-03 11:35:50 | [pearl_trainer] epoch #492 | Time 79626.26 s 2025-04-03 11:35:50 | [pearl_trainer] epoch #492 | EpochTime 159.80 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -106.514 MetaTest/Average/AverageReturn -106.514 MetaTest/Average/Iteration 492 MetaTest/Average/MaxReturn -95.5334 MetaTest/Average/MinReturn -126.343 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 14.0481 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -106.514 MetaTest/__unnamed_task__/AverageReturn -106.514 MetaTest/__unnamed_task__/Iteration 492 MetaTest/__unnamed_task__/MaxReturn -95.5334 MetaTest/__unnamed_task__/MinReturn -126.343 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 14.0481 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 803800 ------------------------------------------------- ----------- 2025-04-03 11:36:14 | [pearl_trainer] epoch #493 | Training... 2025-04-03 11:37:42 | [pearl_trainer] epoch #493 | Evaluating... 2025-04-03 11:37:42 | [pearl_trainer] epoch #493 | Sampling for adapation and meta-testing... 2025-04-03 11:38:30 | [pearl_trainer] epoch #493 | Finished meta-testing... 2025-04-03 11:38:30 | [pearl_trainer] epoch #493 | Saving snapshot... 2025-04-03 11:38:31 | [pearl_trainer] epoch #493 | Saved 2025-04-03 11:38:31 | [pearl_trainer] epoch #493 | Time 79787.28 s 2025-04-03 11:38:31 | [pearl_trainer] epoch #493 | EpochTime 161.02 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -121.563 MetaTest/Average/AverageReturn -121.563 MetaTest/Average/Iteration 493 MetaTest/Average/MaxReturn -113.368 MetaTest/Average/MinReturn -126.647 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.85048 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -121.563 MetaTest/__unnamed_task__/AverageReturn -121.563 MetaTest/__unnamed_task__/Iteration 493 MetaTest/__unnamed_task__/MaxReturn -113.368 MetaTest/__unnamed_task__/MinReturn -126.647 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.85048 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 805400 ------------------------------------------------- ------------ 2025-04-03 11:38:53 | [pearl_trainer] epoch #494 | Training... 2025-04-03 11:40:24 | [pearl_trainer] epoch #494 | Evaluating... 2025-04-03 11:40:24 | [pearl_trainer] epoch #494 | Sampling for adapation and meta-testing... 2025-04-03 11:41:12 | [pearl_trainer] epoch #494 | Finished meta-testing... 2025-04-03 11:41:12 | [pearl_trainer] epoch #494 | Saving snapshot... 2025-04-03 11:41:13 | [pearl_trainer] epoch #494 | Saved 2025-04-03 11:41:13 | [pearl_trainer] epoch #494 | Time 79949.52 s 2025-04-03 11:41:13 | [pearl_trainer] epoch #494 | EpochTime 162.25 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -125.392 MetaTest/Average/AverageReturn -125.392 MetaTest/Average/Iteration 494 MetaTest/Average/MaxReturn -120.197 MetaTest/Average/MinReturn -130.322 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 4.13762 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -125.392 MetaTest/__unnamed_task__/AverageReturn -125.392 MetaTest/__unnamed_task__/Iteration 494 MetaTest/__unnamed_task__/MaxReturn -120.197 MetaTest/__unnamed_task__/MinReturn -130.322 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 4.13762 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 807000 ------------------------------------------------- ------------ 2025-04-03 11:41:36 | [pearl_trainer] epoch #495 | Training... 2025-04-03 11:43:08 | [pearl_trainer] epoch #495 | Evaluating... 2025-04-03 11:43:08 | [pearl_trainer] epoch #495 | Sampling for adapation and meta-testing... 2025-04-03 11:43:55 | [pearl_trainer] epoch #495 | Finished meta-testing... 2025-04-03 11:43:55 | [pearl_trainer] epoch #495 | Saving snapshot... 2025-04-03 11:43:56 | [pearl_trainer] epoch #495 | Saved 2025-04-03 11:43:56 | [pearl_trainer] epoch #495 | Time 80112.27 s 2025-04-03 11:43:56 | [pearl_trainer] epoch #495 | EpochTime 162.74 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -107.533 MetaTest/Average/AverageReturn -107.533 MetaTest/Average/Iteration 495 MetaTest/Average/MaxReturn -100.473 MetaTest/Average/MinReturn -115.81 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 6.32022 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -107.533 MetaTest/__unnamed_task__/AverageReturn -107.533 MetaTest/__unnamed_task__/Iteration 495 MetaTest/__unnamed_task__/MaxReturn -100.473 MetaTest/__unnamed_task__/MinReturn -115.81 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 6.32022 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 808600 ------------------------------------------------- ------------ 2025-04-03 11:44:18 | [pearl_trainer] epoch #496 | Training... 2025-04-03 11:45:48 | [pearl_trainer] epoch #496 | Evaluating... 2025-04-03 11:45:48 | [pearl_trainer] epoch #496 | Sampling for adapation and meta-testing... 2025-04-03 11:46:40 | [pearl_trainer] epoch #496 | Finished meta-testing... 2025-04-03 11:46:40 | [pearl_trainer] epoch #496 | Saving snapshot... 2025-04-03 11:46:42 | [pearl_trainer] epoch #496 | Saved 2025-04-03 11:46:42 | [pearl_trainer] epoch #496 | Time 80277.91 s 2025-04-03 11:46:42 | [pearl_trainer] epoch #496 | EpochTime 165.63 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -115.66 MetaTest/Average/AverageReturn -115.66 MetaTest/Average/Iteration 496 MetaTest/Average/MaxReturn -100.628 MetaTest/Average/MinReturn -130.504 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 12.1974 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -115.66 MetaTest/__unnamed_task__/AverageReturn -115.66 MetaTest/__unnamed_task__/Iteration 496 MetaTest/__unnamed_task__/MaxReturn -100.628 MetaTest/__unnamed_task__/MinReturn -130.504 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 12.1974 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 810200 ------------------------------------------------- ----------- 2025-04-03 11:47:04 | [pearl_trainer] epoch #497 | Training... 2025-04-03 11:48:28 | [pearl_trainer] epoch #497 | Evaluating... 2025-04-03 11:48:28 | [pearl_trainer] epoch #497 | Sampling for adapation and meta-testing... 2025-04-03 11:49:21 | [pearl_trainer] epoch #497 | Finished meta-testing... 2025-04-03 11:49:21 | [pearl_trainer] epoch #497 | Saving snapshot... 2025-04-03 11:49:22 | [pearl_trainer] epoch #497 | Saved 2025-04-03 11:49:22 | [pearl_trainer] epoch #497 | Time 80438.24 s 2025-04-03 11:49:22 | [pearl_trainer] epoch #497 | EpochTime 160.33 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -100.14 MetaTest/Average/AverageReturn -100.14 MetaTest/Average/Iteration 497 MetaTest/Average/MaxReturn -92.1569 MetaTest/Average/MinReturn -105.694 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.78746 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -100.14 MetaTest/__unnamed_task__/AverageReturn -100.14 MetaTest/__unnamed_task__/Iteration 497 MetaTest/__unnamed_task__/MaxReturn -92.1569 MetaTest/__unnamed_task__/MinReturn -105.694 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.78746 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 811800 ------------------------------------------------- ------------ 2025-04-03 11:49:46 | [pearl_trainer] epoch #498 | Training... 2025-04-03 11:51:11 | [pearl_trainer] epoch #498 | Evaluating... 2025-04-03 11:51:11 | [pearl_trainer] epoch #498 | Sampling for adapation and meta-testing... 2025-04-03 11:51:57 | [pearl_trainer] epoch #498 | Finished meta-testing... 2025-04-03 11:51:57 | [pearl_trainer] epoch #498 | Saving snapshot... 2025-04-03 11:51:59 | [pearl_trainer] epoch #498 | Saved 2025-04-03 11:51:59 | [pearl_trainer] epoch #498 | Time 80594.76 s 2025-04-03 11:51:59 | [pearl_trainer] epoch #498 | EpochTime 156.52 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -115.135 MetaTest/Average/AverageReturn -115.135 MetaTest/Average/Iteration 498 MetaTest/Average/MaxReturn -108.853 MetaTest/Average/MinReturn -122.79 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 5.77177 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -115.135 MetaTest/__unnamed_task__/AverageReturn -115.135 MetaTest/__unnamed_task__/Iteration 498 MetaTest/__unnamed_task__/MaxReturn -108.853 MetaTest/__unnamed_task__/MinReturn -122.79 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 5.77177 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 813400 ------------------------------------------------- ------------ 2025-04-03 11:52:23 | [pearl_trainer] epoch #499 | Training... 2025-04-03 11:53:52 | [pearl_trainer] epoch #499 | Evaluating... 2025-04-03 11:53:52 | [pearl_trainer] epoch #499 | Sampling for adapation and meta-testing... 2025-04-03 11:54:39 | [pearl_trainer] epoch #499 | Finished meta-testing... 2025-04-03 11:54:39 | [pearl_trainer] epoch #499 | Saving snapshot... 2025-04-03 11:54:41 | [pearl_trainer] epoch #499 | Saved 2025-04-03 11:54:41 | [pearl_trainer] epoch #499 | Time 80756.79 s 2025-04-03 11:54:41 | [pearl_trainer] epoch #499 | EpochTime 162.03 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -103.539 MetaTest/Average/AverageReturn -103.539 MetaTest/Average/Iteration 499 MetaTest/Average/MaxReturn -93.4883 MetaTest/Average/MinReturn -113.263 MetaTest/Average/NumEpisodes 3 MetaTest/Average/StdReturn 8.07646 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -103.539 MetaTest/__unnamed_task__/AverageReturn -103.539 MetaTest/__unnamed_task__/Iteration 499 MetaTest/__unnamed_task__/MaxReturn -93.4883 MetaTest/__unnamed_task__/MinReturn -113.263 MetaTest/__unnamed_task__/NumEpisodes 3 MetaTest/__unnamed_task__/StdReturn 8.07646 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 815000 ------------------------------------------------- ------------