2025-04-03 16:28:49 | [pearl_trainer] Logging to /home/h2khalil/MetaRL-Assistive-Robotics/data/local/experiment/pearl_trainer_4 2025-04-03 16:28:56 | [pearl_trainer] Obtaining samples... 2025-04-03 16:51:56 | [pearl_trainer] epoch #0 | Training... 2025-04-03 16:55:09 | [pearl_trainer] epoch #0 | Evaluating... 2025-04-03 16:55:09 | [pearl_trainer] epoch #0 | Sampling for adapation and meta-testing... 2025-04-03 17:01:38 | [pearl_trainer] epoch #0 | Finished meta-testing... 2025-04-03 17:01:38 | [pearl_trainer] epoch #0 | Saving snapshot... 2025-04-03 17:01:40 | [pearl_trainer] epoch #0 | Saved 2025-04-03 17:01:40 | [pearl_trainer] epoch #0 | Time 1963.30 s 2025-04-03 17:01:40 | [pearl_trainer] epoch #0 | EpochTime 1963.30 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -71.6521 MetaTest/Average/AverageReturn -71.6521 MetaTest/Average/Iteration 0 MetaTest/Average/MaxReturn -62.121 MetaTest/Average/MinReturn -86.5749 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 9.01241 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -71.6521 MetaTest/__unnamed_task__/AverageReturn -71.6521 MetaTest/__unnamed_task__/Iteration 0 MetaTest/__unnamed_task__/MaxReturn -62.121 MetaTest/__unnamed_task__/MinReturn -86.5749 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 9.01241 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 42000 ------------------------------------------------- ----------- 2025-04-03 17:02:48 | [pearl_trainer] epoch #1 | Training... 2025-04-03 17:06:16 | [pearl_trainer] epoch #1 | Evaluating... 2025-04-03 17:06:16 | [pearl_trainer] epoch #1 | Sampling for adapation and meta-testing... 2025-04-03 17:12:50 | [pearl_trainer] epoch #1 | Finished meta-testing... 2025-04-03 17:12:50 | [pearl_trainer] epoch #1 | Saving snapshot... 2025-04-03 17:12:51 | [pearl_trainer] epoch #1 | Saved 2025-04-03 17:12:51 | [pearl_trainer] epoch #1 | Time 2634.67 s 2025-04-03 17:12:51 | [pearl_trainer] epoch #1 | EpochTime 671.36 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -67.5921 MetaTest/Average/AverageReturn -67.5921 MetaTest/Average/Iteration 1 MetaTest/Average/MaxReturn -58.4369 MetaTest/Average/MinReturn -77.7331 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 7.0954 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -67.5921 MetaTest/__unnamed_task__/AverageReturn -67.5921 MetaTest/__unnamed_task__/Iteration 1 MetaTest/__unnamed_task__/MaxReturn -58.4369 MetaTest/__unnamed_task__/MinReturn -77.7331 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 7.0954 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 44000 ------------------------------------------------- ---------- 2025-04-03 17:13:59 | [pearl_trainer] epoch #2 | Training... 2025-04-03 17:17:14 | [pearl_trainer] epoch #2 | Evaluating... 2025-04-03 17:17:14 | [pearl_trainer] epoch #2 | Sampling for adapation and meta-testing... 2025-04-03 17:23:15 | [pearl_trainer] epoch #2 | Finished meta-testing... 2025-04-03 17:23:15 | [pearl_trainer] epoch #2 | Saving snapshot... 2025-04-03 17:23:17 | [pearl_trainer] epoch #2 | Saved 2025-04-03 17:23:17 | [pearl_trainer] epoch #2 | Time 3260.37 s 2025-04-03 17:23:17 | [pearl_trainer] epoch #2 | EpochTime 625.69 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -136.012 MetaTest/Average/AverageReturn -136.012 MetaTest/Average/Iteration 2 MetaTest/Average/MaxReturn -59.4788 MetaTest/Average/MinReturn -202.432 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 61.6012 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -136.012 MetaTest/__unnamed_task__/AverageReturn -136.012 MetaTest/__unnamed_task__/Iteration 2 MetaTest/__unnamed_task__/MaxReturn -59.4788 MetaTest/__unnamed_task__/MinReturn -202.432 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 61.6012 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 46000 ------------------------------------------------- ---------- 2025-04-03 17:24:23 | [pearl_trainer] epoch #3 | Training... 2025-04-03 17:27:57 | [pearl_trainer] epoch #3 | Evaluating... 2025-04-03 17:27:57 | [pearl_trainer] epoch #3 | Sampling for adapation and meta-testing... 2025-04-03 17:32:22 | [pearl_trainer] epoch #3 | Finished meta-testing... 2025-04-03 17:32:22 | [pearl_trainer] epoch #3 | Saving snapshot... 2025-04-03 17:32:23 | [pearl_trainer] epoch #3 | Saved 2025-04-03 17:32:23 | [pearl_trainer] epoch #3 | Time 3806.65 s 2025-04-03 17:32:23 | [pearl_trainer] epoch #3 | EpochTime 546.28 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -261.487 MetaTest/Average/AverageReturn -261.487 MetaTest/Average/Iteration 3 MetaTest/Average/MaxReturn -248.139 MetaTest/Average/MinReturn -269.255 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 9.20386 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -261.487 MetaTest/__unnamed_task__/AverageReturn -261.487 MetaTest/__unnamed_task__/Iteration 3 MetaTest/__unnamed_task__/MaxReturn -248.139 MetaTest/__unnamed_task__/MinReturn -269.255 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 9.20386 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 48000 ------------------------------------------------- ----------- 2025-04-03 17:33:10 | [pearl_trainer] epoch #4 | Training... 2025-04-03 17:36:28 | [pearl_trainer] epoch #4 | Evaluating... 2025-04-03 17:36:28 | [pearl_trainer] epoch #4 | Sampling for adapation and meta-testing... 2025-04-03 17:41:34 | [pearl_trainer] epoch #4 | Finished meta-testing... 2025-04-03 17:41:34 | [pearl_trainer] epoch #4 | Saving snapshot... 2025-04-03 17:41:35 | [pearl_trainer] epoch #4 | Saved 2025-04-03 17:41:35 | [pearl_trainer] epoch #4 | Time 4359.16 s 2025-04-03 17:41:35 | [pearl_trainer] epoch #4 | EpochTime 552.51 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -194.491 MetaTest/Average/AverageReturn -194.491 MetaTest/Average/Iteration 4 MetaTest/Average/MaxReturn -140.648 MetaTest/Average/MinReturn -226.916 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 29.8567 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -194.491 MetaTest/__unnamed_task__/AverageReturn -194.491 MetaTest/__unnamed_task__/Iteration 4 MetaTest/__unnamed_task__/MaxReturn -140.648 MetaTest/__unnamed_task__/MinReturn -226.916 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 29.8567 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 50000 ------------------------------------------------- ---------- 2025-04-03 17:42:27 | [pearl_trainer] epoch #5 | Training... 2025-04-03 17:45:49 | [pearl_trainer] epoch #5 | Evaluating... 2025-04-03 17:45:49 | [pearl_trainer] epoch #5 | Sampling for adapation and meta-testing... 2025-04-03 17:51:06 | [pearl_trainer] epoch #5 | Finished meta-testing... 2025-04-03 17:51:06 | [pearl_trainer] epoch #5 | Saving snapshot... 2025-04-03 17:51:07 | [pearl_trainer] epoch #5 | Saved 2025-04-03 17:51:07 | [pearl_trainer] epoch #5 | Time 4930.37 s 2025-04-03 17:51:07 | [pearl_trainer] epoch #5 | EpochTime 571.21 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -191.463 MetaTest/Average/AverageReturn -191.463 MetaTest/Average/Iteration 5 MetaTest/Average/MaxReturn -169.733 MetaTest/Average/MinReturn -209.811 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 13.3868 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -191.463 MetaTest/__unnamed_task__/AverageReturn -191.463 MetaTest/__unnamed_task__/Iteration 5 MetaTest/__unnamed_task__/MaxReturn -169.733 MetaTest/__unnamed_task__/MinReturn -209.811 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 13.3868 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 52000 ------------------------------------------------- ---------- 2025-04-03 17:52:08 | [pearl_trainer] epoch #6 | Training... 2025-04-03 17:55:26 | [pearl_trainer] epoch #6 | Evaluating... 2025-04-03 17:55:26 | [pearl_trainer] epoch #6 | Sampling for adapation and meta-testing... 2025-04-03 17:59:59 | [pearl_trainer] epoch #6 | Finished meta-testing... 2025-04-03 17:59:59 | [pearl_trainer] epoch #6 | Saving snapshot... 2025-04-03 18:00:00 | [pearl_trainer] epoch #6 | Saved 2025-04-03 18:00:00 | [pearl_trainer] epoch #6 | Time 5464.08 s 2025-04-03 18:00:00 | [pearl_trainer] epoch #6 | EpochTime 533.71 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -207.041 MetaTest/Average/AverageReturn -207.041 MetaTest/Average/Iteration 6 MetaTest/Average/MaxReturn -181.949 MetaTest/Average/MinReturn -234.646 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 20.7276 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -207.041 MetaTest/__unnamed_task__/AverageReturn -207.041 MetaTest/__unnamed_task__/Iteration 6 MetaTest/__unnamed_task__/MaxReturn -181.949 MetaTest/__unnamed_task__/MinReturn -234.646 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 20.7276 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 54000 ------------------------------------------------- ---------- 2025-04-03 18:00:49 | [pearl_trainer] epoch #7 | Training... 2025-04-03 18:04:12 | [pearl_trainer] epoch #7 | Evaluating... 2025-04-03 18:04:12 | [pearl_trainer] epoch #7 | Sampling for adapation and meta-testing... 2025-04-03 18:08:27 | [pearl_trainer] epoch #7 | Finished meta-testing... 2025-04-03 18:08:27 | [pearl_trainer] epoch #7 | Saving snapshot... 2025-04-03 18:08:29 | [pearl_trainer] epoch #7 | Saved 2025-04-03 18:08:29 | [pearl_trainer] epoch #7 | Time 5972.24 s 2025-04-03 18:08:29 | [pearl_trainer] epoch #7 | EpochTime 508.16 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -279.704 MetaTest/Average/AverageReturn -279.704 MetaTest/Average/Iteration 7 MetaTest/Average/MaxReturn -218.776 MetaTest/Average/MinReturn -340.712 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 48.4658 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -279.704 MetaTest/__unnamed_task__/AverageReturn -279.704 MetaTest/__unnamed_task__/Iteration 7 MetaTest/__unnamed_task__/MaxReturn -218.776 MetaTest/__unnamed_task__/MinReturn -340.712 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 48.4658 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 56000 ------------------------------------------------- ---------- 2025-04-03 18:09:14 | [pearl_trainer] epoch #8 | Training... 2025-04-03 18:12:33 | [pearl_trainer] epoch #8 | Evaluating... 2025-04-03 18:12:33 | [pearl_trainer] epoch #8 | Sampling for adapation and meta-testing... 2025-04-03 18:16:51 | [pearl_trainer] epoch #8 | Finished meta-testing... 2025-04-03 18:16:51 | [pearl_trainer] epoch #8 | Saving snapshot... 2025-04-03 18:16:52 | [pearl_trainer] epoch #8 | Saved 2025-04-03 18:16:52 | [pearl_trainer] epoch #8 | Time 6475.73 s 2025-04-03 18:16:52 | [pearl_trainer] epoch #8 | EpochTime 503.49 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -288.407 MetaTest/Average/AverageReturn -288.407 MetaTest/Average/Iteration 8 MetaTest/Average/MaxReturn -260.94 MetaTest/Average/MinReturn -303.811 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 15.4663 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -288.407 MetaTest/__unnamed_task__/AverageReturn -288.407 MetaTest/__unnamed_task__/Iteration 8 MetaTest/__unnamed_task__/MaxReturn -260.94 MetaTest/__unnamed_task__/MinReturn -303.811 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 15.4663 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 58000 ------------------------------------------------- ---------- 2025-04-03 18:17:39 | [pearl_trainer] epoch #9 | Training... 2025-04-03 18:21:01 | [pearl_trainer] epoch #9 | Evaluating... 2025-04-03 18:21:01 | [pearl_trainer] epoch #9 | Sampling for adapation and meta-testing... 2025-04-03 18:25:18 | [pearl_trainer] epoch #9 | Finished meta-testing... 2025-04-03 18:25:18 | [pearl_trainer] epoch #9 | Saving snapshot... 2025-04-03 18:25:19 | [pearl_trainer] epoch #9 | Saved 2025-04-03 18:25:19 | [pearl_trainer] epoch #9 | Time 6982.46 s 2025-04-03 18:25:19 | [pearl_trainer] epoch #9 | EpochTime 506.73 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -250.833 MetaTest/Average/AverageReturn -250.833 MetaTest/Average/Iteration 9 MetaTest/Average/MaxReturn -219.318 MetaTest/Average/MinReturn -281.384 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.2322 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -250.833 MetaTest/__unnamed_task__/AverageReturn -250.833 MetaTest/__unnamed_task__/Iteration 9 MetaTest/__unnamed_task__/MaxReturn -219.318 MetaTest/__unnamed_task__/MinReturn -281.384 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.2322 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 60000 ------------------------------------------------- ---------- 2025-04-03 18:26:05 | [pearl_trainer] epoch #10 | Training... 2025-04-03 18:29:22 | [pearl_trainer] epoch #10 | Evaluating... 2025-04-03 18:29:22 | [pearl_trainer] epoch #10 | Sampling for adapation and meta-testing... 2025-04-03 18:34:02 | [pearl_trainer] epoch #10 | Finished meta-testing... 2025-04-03 18:34:02 | [pearl_trainer] epoch #10 | Saving snapshot... 2025-04-03 18:34:04 | [pearl_trainer] epoch #10 | Saved 2025-04-03 18:34:04 | [pearl_trainer] epoch #10 | Time 7507.55 s 2025-04-03 18:34:04 | [pearl_trainer] epoch #10 | EpochTime 525.09 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -252.349 MetaTest/Average/AverageReturn -252.349 MetaTest/Average/Iteration 10 MetaTest/Average/MaxReturn -208.511 MetaTest/Average/MinReturn -292.689 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.6489 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -252.349 MetaTest/__unnamed_task__/AverageReturn -252.349 MetaTest/__unnamed_task__/Iteration 10 MetaTest/__unnamed_task__/MaxReturn -208.511 MetaTest/__unnamed_task__/MinReturn -292.689 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.6489 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 62000 ------------------------------------------------- ---------- 2025-04-03 18:34:54 | [pearl_trainer] epoch #11 | Training... 2025-04-03 18:38:10 | [pearl_trainer] epoch #11 | Evaluating... 2025-04-03 18:38:10 | [pearl_trainer] epoch #11 | Sampling for adapation and meta-testing... 2025-04-03 18:42:26 | [pearl_trainer] epoch #11 | Finished meta-testing... 2025-04-03 18:42:26 | [pearl_trainer] epoch #11 | Saving snapshot... 2025-04-03 18:42:28 | [pearl_trainer] epoch #11 | Saved 2025-04-03 18:42:28 | [pearl_trainer] epoch #11 | Time 8011.21 s 2025-04-03 18:42:28 | [pearl_trainer] epoch #11 | EpochTime 503.66 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -270.785 MetaTest/Average/AverageReturn -270.785 MetaTest/Average/Iteration 11 MetaTest/Average/MaxReturn -237.397 MetaTest/Average/MinReturn -316.099 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 28.1495 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -270.785 MetaTest/__unnamed_task__/AverageReturn -270.785 MetaTest/__unnamed_task__/Iteration 11 MetaTest/__unnamed_task__/MaxReturn -237.397 MetaTest/__unnamed_task__/MinReturn -316.099 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 28.1495 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 64000 ------------------------------------------------- ---------- 2025-04-03 18:43:14 | [pearl_trainer] epoch #12 | Training... 2025-04-03 18:46:31 | [pearl_trainer] epoch #12 | Evaluating... 2025-04-03 18:46:31 | [pearl_trainer] epoch #12 | Sampling for adapation and meta-testing... 2025-04-03 18:50:46 | [pearl_trainer] epoch #12 | Finished meta-testing... 2025-04-03 18:50:46 | [pearl_trainer] epoch #12 | Saving snapshot... 2025-04-03 18:50:47 | [pearl_trainer] epoch #12 | Saved 2025-04-03 18:50:47 | [pearl_trainer] epoch #12 | Time 8511.14 s 2025-04-03 18:50:47 | [pearl_trainer] epoch #12 | EpochTime 499.92 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -268.725 MetaTest/Average/AverageReturn -268.725 MetaTest/Average/Iteration 12 MetaTest/Average/MaxReturn -237.227 MetaTest/Average/MinReturn -299.168 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 24.3174 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -268.725 MetaTest/__unnamed_task__/AverageReturn -268.725 MetaTest/__unnamed_task__/Iteration 12 MetaTest/__unnamed_task__/MaxReturn -237.227 MetaTest/__unnamed_task__/MinReturn -299.168 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 24.3174 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 66000 ------------------------------------------------- ---------- 2025-04-03 18:51:33 | [pearl_trainer] epoch #13 | Training... 2025-04-03 18:54:56 | [pearl_trainer] epoch #13 | Evaluating... 2025-04-03 18:54:56 | [pearl_trainer] epoch #13 | Sampling for adapation and meta-testing... 2025-04-03 18:59:23 | [pearl_trainer] epoch #13 | Finished meta-testing... 2025-04-03 18:59:23 | [pearl_trainer] epoch #13 | Saving snapshot... 2025-04-03 18:59:24 | [pearl_trainer] epoch #13 | Saved 2025-04-03 18:59:24 | [pearl_trainer] epoch #13 | Time 9027.95 s 2025-04-03 18:59:24 | [pearl_trainer] epoch #13 | EpochTime 516.81 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -257.507 MetaTest/Average/AverageReturn -257.507 MetaTest/Average/Iteration 13 MetaTest/Average/MaxReturn -230.297 MetaTest/Average/MinReturn -293.381 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 23.5218 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -257.507 MetaTest/__unnamed_task__/AverageReturn -257.507 MetaTest/__unnamed_task__/Iteration 13 MetaTest/__unnamed_task__/MaxReturn -230.297 MetaTest/__unnamed_task__/MinReturn -293.381 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 23.5218 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 68000 ------------------------------------------------- ---------- 2025-04-03 19:00:09 | [pearl_trainer] epoch #14 | Training... 2025-04-03 19:03:28 | [pearl_trainer] epoch #14 | Evaluating... 2025-04-03 19:03:28 | [pearl_trainer] epoch #14 | Sampling for adapation and meta-testing... 2025-04-03 19:07:28 | [pearl_trainer] epoch #14 | Finished meta-testing... 2025-04-03 19:07:28 | [pearl_trainer] epoch #14 | Saving snapshot... 2025-04-03 19:07:29 | [pearl_trainer] epoch #14 | Saved 2025-04-03 19:07:29 | [pearl_trainer] epoch #14 | Time 9513.13 s 2025-04-03 19:07:29 | [pearl_trainer] epoch #14 | EpochTime 485.18 s ------------------------------------------------- --------- MetaTest/Average/AverageDiscountedReturn -269.438 MetaTest/Average/AverageReturn -269.438 MetaTest/Average/Iteration 14 MetaTest/Average/MaxReturn -193.359 MetaTest/Average/MinReturn -321.837 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 42.117 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -269.438 MetaTest/__unnamed_task__/AverageReturn -269.438 MetaTest/__unnamed_task__/Iteration 14 MetaTest/__unnamed_task__/MaxReturn -193.359 MetaTest/__unnamed_task__/MinReturn -321.837 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 42.117 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 70000 ------------------------------------------------- --------- 2025-04-03 19:08:09 | [pearl_trainer] epoch #15 | Training... 2025-04-03 19:11:00 | [pearl_trainer] epoch #15 | Evaluating... 2025-04-03 19:11:00 | [pearl_trainer] epoch #15 | Sampling for adapation and meta-testing... 2025-04-03 19:14:37 | [pearl_trainer] epoch #15 | Finished meta-testing... 2025-04-03 19:14:37 | [pearl_trainer] epoch #15 | Saving snapshot... 2025-04-03 19:14:38 | [pearl_trainer] epoch #15 | Saved 2025-04-03 19:14:38 | [pearl_trainer] epoch #15 | Time 9941.48 s 2025-04-03 19:14:38 | [pearl_trainer] epoch #15 | EpochTime 428.35 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -235.92 MetaTest/Average/AverageReturn -235.92 MetaTest/Average/Iteration 15 MetaTest/Average/MaxReturn -171.169 MetaTest/Average/MinReturn -330.774 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 56.1205 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -235.92 MetaTest/__unnamed_task__/AverageReturn -235.92 MetaTest/__unnamed_task__/Iteration 15 MetaTest/__unnamed_task__/MaxReturn -171.169 MetaTest/__unnamed_task__/MinReturn -330.774 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 56.1205 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 72000 ------------------------------------------------- ---------- 2025-04-03 19:15:20 | [pearl_trainer] epoch #16 | Training... 2025-04-03 19:18:10 | [pearl_trainer] epoch #16 | Evaluating... 2025-04-03 19:18:10 | [pearl_trainer] epoch #16 | Sampling for adapation and meta-testing... 2025-04-03 19:21:36 | [pearl_trainer] epoch #16 | Finished meta-testing... 2025-04-03 19:21:36 | [pearl_trainer] epoch #16 | Saving snapshot... 2025-04-03 19:21:37 | [pearl_trainer] epoch #16 | Saved 2025-04-03 19:21:37 | [pearl_trainer] epoch #16 | Time 10360.69 s 2025-04-03 19:21:37 | [pearl_trainer] epoch #16 | EpochTime 419.20 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -297.062 MetaTest/Average/AverageReturn -297.062 MetaTest/Average/Iteration 16 MetaTest/Average/MaxReturn -236.131 MetaTest/Average/MinReturn -333.01 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.3774 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -297.062 MetaTest/__unnamed_task__/AverageReturn -297.062 MetaTest/__unnamed_task__/Iteration 16 MetaTest/__unnamed_task__/MaxReturn -236.131 MetaTest/__unnamed_task__/MinReturn -333.01 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.3774 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 74000 ------------------------------------------------- ---------- 2025-04-03 19:22:15 | [pearl_trainer] epoch #17 | Training... 2025-04-03 19:24:51 | [pearl_trainer] epoch #17 | Evaluating... 2025-04-03 19:24:51 | [pearl_trainer] epoch #17 | Sampling for adapation and meta-testing... 2025-04-03 19:28:22 | [pearl_trainer] epoch #17 | Finished meta-testing... 2025-04-03 19:28:22 | [pearl_trainer] epoch #17 | Saving snapshot... 2025-04-03 19:28:23 | [pearl_trainer] epoch #17 | Saved 2025-04-03 19:28:23 | [pearl_trainer] epoch #17 | Time 10767.05 s 2025-04-03 19:28:23 | [pearl_trainer] epoch #17 | EpochTime 406.36 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -318.634 MetaTest/Average/AverageReturn -318.634 MetaTest/Average/Iteration 17 MetaTest/Average/MaxReturn -293.845 MetaTest/Average/MinReturn -345.689 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 18.8073 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -318.634 MetaTest/__unnamed_task__/AverageReturn -318.634 MetaTest/__unnamed_task__/Iteration 17 MetaTest/__unnamed_task__/MaxReturn -293.845 MetaTest/__unnamed_task__/MinReturn -345.689 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 18.8073 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 76000 ------------------------------------------------- ---------- 2025-04-03 19:29:03 | [pearl_trainer] epoch #18 | Training... 2025-04-03 19:31:42 | [pearl_trainer] epoch #18 | Evaluating... 2025-04-03 19:31:42 | [pearl_trainer] epoch #18 | Sampling for adapation and meta-testing... 2025-04-03 19:35:36 | [pearl_trainer] epoch #18 | Finished meta-testing... 2025-04-03 19:35:36 | [pearl_trainer] epoch #18 | Saving snapshot... 2025-04-03 19:35:37 | [pearl_trainer] epoch #18 | Saved 2025-04-03 19:35:37 | [pearl_trainer] epoch #18 | Time 11200.91 s 2025-04-03 19:35:37 | [pearl_trainer] epoch #18 | EpochTime 433.86 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -327.548 MetaTest/Average/AverageReturn -327.548 MetaTest/Average/Iteration 18 MetaTest/Average/MaxReturn -260.92 MetaTest/Average/MinReturn -391.904 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 48.5867 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -327.548 MetaTest/__unnamed_task__/AverageReturn -327.548 MetaTest/__unnamed_task__/Iteration 18 MetaTest/__unnamed_task__/MaxReturn -260.92 MetaTest/__unnamed_task__/MinReturn -391.904 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 48.5867 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 78000 ------------------------------------------------- ---------- 2025-04-03 19:36:17 | [pearl_trainer] epoch #19 | Training... 2025-04-03 19:38:55 | [pearl_trainer] epoch #19 | Evaluating... 2025-04-03 19:38:55 | [pearl_trainer] epoch #19 | Sampling for adapation and meta-testing... 2025-04-03 19:43:34 | [pearl_trainer] epoch #19 | Finished meta-testing... 2025-04-03 19:43:34 | [pearl_trainer] epoch #19 | Saving snapshot... 2025-04-03 19:43:35 | [pearl_trainer] epoch #19 | Saved 2025-04-03 19:43:35 | [pearl_trainer] epoch #19 | Time 11678.58 s 2025-04-03 19:43:35 | [pearl_trainer] epoch #19 | EpochTime 477.67 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -328.087 MetaTest/Average/AverageReturn -328.087 MetaTest/Average/Iteration 19 MetaTest/Average/MaxReturn -299.303 MetaTest/Average/MinReturn -347.864 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 17.3413 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -328.087 MetaTest/__unnamed_task__/AverageReturn -328.087 MetaTest/__unnamed_task__/Iteration 19 MetaTest/__unnamed_task__/MaxReturn -299.303 MetaTest/__unnamed_task__/MinReturn -347.864 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 17.3413 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 80000 ------------------------------------------------- ---------- 2025-04-03 19:44:30 | [pearl_trainer] epoch #20 | Training... 2025-04-03 19:47:51 | [pearl_trainer] epoch #20 | Evaluating... 2025-04-03 19:47:51 | [pearl_trainer] epoch #20 | Sampling for adapation and meta-testing... 2025-04-03 19:52:39 | [pearl_trainer] epoch #20 | Finished meta-testing... 2025-04-03 19:52:39 | [pearl_trainer] epoch #20 | Saving snapshot... 2025-04-03 19:52:41 | [pearl_trainer] epoch #20 | Saved 2025-04-03 19:52:41 | [pearl_trainer] epoch #20 | Time 12224.58 s 2025-04-03 19:52:41 | [pearl_trainer] epoch #20 | EpochTime 545.99 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -290.684 MetaTest/Average/AverageReturn -290.684 MetaTest/Average/Iteration 20 MetaTest/Average/MaxReturn -261.276 MetaTest/Average/MinReturn -329.746 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 23.3876 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -290.684 MetaTest/__unnamed_task__/AverageReturn -290.684 MetaTest/__unnamed_task__/Iteration 20 MetaTest/__unnamed_task__/MaxReturn -261.276 MetaTest/__unnamed_task__/MinReturn -329.746 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 23.3876 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 82000 ------------------------------------------------- ---------- 2025-04-03 19:53:29 | [pearl_trainer] epoch #21 | Training... 2025-04-03 19:56:42 | [pearl_trainer] epoch #21 | Evaluating... 2025-04-03 19:56:42 | [pearl_trainer] epoch #21 | Sampling for adapation and meta-testing... 2025-04-03 20:01:08 | [pearl_trainer] epoch #21 | Finished meta-testing... 2025-04-03 20:01:08 | [pearl_trainer] epoch #21 | Saving snapshot... 2025-04-03 20:01:09 | [pearl_trainer] epoch #21 | Saved 2025-04-03 20:01:09 | [pearl_trainer] epoch #21 | Time 12732.99 s 2025-04-03 20:01:09 | [pearl_trainer] epoch #21 | EpochTime 508.41 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -332.105 MetaTest/Average/AverageReturn -332.105 MetaTest/Average/Iteration 21 MetaTest/Average/MaxReturn -257.799 MetaTest/Average/MinReturn -373.982 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 40.3571 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -332.105 MetaTest/__unnamed_task__/AverageReturn -332.105 MetaTest/__unnamed_task__/Iteration 21 MetaTest/__unnamed_task__/MaxReturn -257.799 MetaTest/__unnamed_task__/MinReturn -373.982 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 40.3571 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 84000 ------------------------------------------------- ---------- 2025-04-03 20:01:55 | [pearl_trainer] epoch #22 | Training... 2025-04-03 20:05:11 | [pearl_trainer] epoch #22 | Evaluating... 2025-04-03 20:05:11 | [pearl_trainer] epoch #22 | Sampling for adapation and meta-testing... 2025-04-03 20:09:34 | [pearl_trainer] epoch #22 | Finished meta-testing... 2025-04-03 20:09:34 | [pearl_trainer] epoch #22 | Saving snapshot... 2025-04-03 20:09:36 | [pearl_trainer] epoch #22 | Saved 2025-04-03 20:09:36 | [pearl_trainer] epoch #22 | Time 13239.38 s 2025-04-03 20:09:36 | [pearl_trainer] epoch #22 | EpochTime 506.39 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -300.579 MetaTest/Average/AverageReturn -300.579 MetaTest/Average/Iteration 22 MetaTest/Average/MaxReturn -255.266 MetaTest/Average/MinReturn -351.858 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.3615 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -300.579 MetaTest/__unnamed_task__/AverageReturn -300.579 MetaTest/__unnamed_task__/Iteration 22 MetaTest/__unnamed_task__/MaxReturn -255.266 MetaTest/__unnamed_task__/MinReturn -351.858 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.3615 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 86000 ------------------------------------------------- ---------- 2025-04-03 20:10:24 | [pearl_trainer] epoch #23 | Training... 2025-04-03 20:13:37 | [pearl_trainer] epoch #23 | Evaluating... 2025-04-03 20:13:37 | [pearl_trainer] epoch #23 | Sampling for adapation and meta-testing... 2025-04-03 20:17:20 | [pearl_trainer] epoch #23 | Finished meta-testing... 2025-04-03 20:17:20 | [pearl_trainer] epoch #23 | Saving snapshot... 2025-04-03 20:17:21 | [pearl_trainer] epoch #23 | Saved 2025-04-03 20:17:21 | [pearl_trainer] epoch #23 | Time 13705.19 s 2025-04-03 20:17:21 | [pearl_trainer] epoch #23 | EpochTime 465.81 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -275.079 MetaTest/Average/AverageReturn -275.079 MetaTest/Average/Iteration 23 MetaTest/Average/MaxReturn -216.141 MetaTest/Average/MinReturn -316.915 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 38.5104 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -275.079 MetaTest/__unnamed_task__/AverageReturn -275.079 MetaTest/__unnamed_task__/Iteration 23 MetaTest/__unnamed_task__/MaxReturn -216.141 MetaTest/__unnamed_task__/MinReturn -316.915 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 38.5104 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 88000 ------------------------------------------------- ---------- 2025-04-03 20:18:01 | [pearl_trainer] epoch #24 | Training... 2025-04-03 20:21:21 | [pearl_trainer] epoch #24 | Evaluating... 2025-04-03 20:21:21 | [pearl_trainer] epoch #24 | Sampling for adapation and meta-testing... 2025-04-03 20:25:13 | [pearl_trainer] epoch #24 | Finished meta-testing... 2025-04-03 20:25:13 | [pearl_trainer] epoch #24 | Saving snapshot... 2025-04-03 20:25:14 | [pearl_trainer] epoch #24 | Saved 2025-04-03 20:25:14 | [pearl_trainer] epoch #24 | Time 14177.80 s 2025-04-03 20:25:14 | [pearl_trainer] epoch #24 | EpochTime 472.61 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -284.37 MetaTest/Average/AverageReturn -284.37 MetaTest/Average/Iteration 24 MetaTest/Average/MaxReturn -200.433 MetaTest/Average/MinReturn -348.261 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 67.5021 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -284.37 MetaTest/__unnamed_task__/AverageReturn -284.37 MetaTest/__unnamed_task__/Iteration 24 MetaTest/__unnamed_task__/MaxReturn -200.433 MetaTest/__unnamed_task__/MinReturn -348.261 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 67.5021 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 90000 ------------------------------------------------- ---------- 2025-04-03 20:25:55 | [pearl_trainer] epoch #25 | Training... 2025-04-03 20:28:34 | [pearl_trainer] epoch #25 | Evaluating... 2025-04-03 20:28:34 | [pearl_trainer] epoch #25 | Sampling for adapation and meta-testing... 2025-04-03 20:32:11 | [pearl_trainer] epoch #25 | Finished meta-testing... 2025-04-03 20:32:11 | [pearl_trainer] epoch #25 | Saving snapshot... 2025-04-03 20:32:12 | [pearl_trainer] epoch #25 | Saved 2025-04-03 20:32:12 | [pearl_trainer] epoch #25 | Time 14596.17 s 2025-04-03 20:32:12 | [pearl_trainer] epoch #25 | EpochTime 418.37 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -287.16 MetaTest/Average/AverageReturn -287.16 MetaTest/Average/Iteration 25 MetaTest/Average/MaxReturn -203.037 MetaTest/Average/MinReturn -330.369 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 45.7154 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -287.16 MetaTest/__unnamed_task__/AverageReturn -287.16 MetaTest/__unnamed_task__/Iteration 25 MetaTest/__unnamed_task__/MaxReturn -203.037 MetaTest/__unnamed_task__/MinReturn -330.369 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 45.7154 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 92000 ------------------------------------------------- ---------- 2025-04-03 20:32:54 | [pearl_trainer] epoch #26 | Training... 2025-04-03 20:35:51 | [pearl_trainer] epoch #26 | Evaluating... 2025-04-03 20:35:51 | [pearl_trainer] epoch #26 | Sampling for adapation and meta-testing... 2025-04-03 20:39:35 | [pearl_trainer] epoch #26 | Finished meta-testing... 2025-04-03 20:39:35 | [pearl_trainer] epoch #26 | Saving snapshot... 2025-04-03 20:39:36 | [pearl_trainer] epoch #26 | Saved 2025-04-03 20:39:36 | [pearl_trainer] epoch #26 | Time 15039.74 s 2025-04-03 20:39:36 | [pearl_trainer] epoch #26 | EpochTime 443.56 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -308.512 MetaTest/Average/AverageReturn -308.512 MetaTest/Average/Iteration 26 MetaTest/Average/MaxReturn -242.191 MetaTest/Average/MinReturn -363.54 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 39.7483 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -308.512 MetaTest/__unnamed_task__/AverageReturn -308.512 MetaTest/__unnamed_task__/Iteration 26 MetaTest/__unnamed_task__/MaxReturn -242.191 MetaTest/__unnamed_task__/MinReturn -363.54 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 39.7483 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 94000 ------------------------------------------------- ---------- 2025-04-03 20:40:16 | [pearl_trainer] epoch #27 | Training... 2025-04-03 20:42:58 | [pearl_trainer] epoch #27 | Evaluating... 2025-04-03 20:42:58 | [pearl_trainer] epoch #27 | Sampling for adapation and meta-testing... 2025-04-03 20:47:11 | [pearl_trainer] epoch #27 | Finished meta-testing... 2025-04-03 20:47:11 | [pearl_trainer] epoch #27 | Saving snapshot... 2025-04-03 20:47:12 | [pearl_trainer] epoch #27 | Saved 2025-04-03 20:47:12 | [pearl_trainer] epoch #27 | Time 15495.90 s 2025-04-03 20:47:12 | [pearl_trainer] epoch #27 | EpochTime 456.16 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -272.132 MetaTest/Average/AverageReturn -272.132 MetaTest/Average/Iteration 27 MetaTest/Average/MaxReturn -209.173 MetaTest/Average/MinReturn -320.682 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 40.6442 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -272.132 MetaTest/__unnamed_task__/AverageReturn -272.132 MetaTest/__unnamed_task__/Iteration 27 MetaTest/__unnamed_task__/MaxReturn -209.173 MetaTest/__unnamed_task__/MinReturn -320.682 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 40.6442 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 96000 ------------------------------------------------- ---------- 2025-04-03 20:47:53 | [pearl_trainer] epoch #28 | Training... 2025-04-03 20:51:06 | [pearl_trainer] epoch #28 | Evaluating... 2025-04-03 20:51:06 | [pearl_trainer] epoch #28 | Sampling for adapation and meta-testing... 2025-04-03 20:55:31 | [pearl_trainer] epoch #28 | Finished meta-testing... 2025-04-03 20:55:31 | [pearl_trainer] epoch #28 | Saving snapshot... 2025-04-03 20:55:32 | [pearl_trainer] epoch #28 | Saved 2025-04-03 20:55:32 | [pearl_trainer] epoch #28 | Time 15995.86 s 2025-04-03 20:55:32 | [pearl_trainer] epoch #28 | EpochTime 499.96 s ------------------------------------------------- --------- MetaTest/Average/AverageDiscountedReturn -275.484 MetaTest/Average/AverageReturn -275.484 MetaTest/Average/Iteration 28 MetaTest/Average/MaxReturn -249.48 MetaTest/Average/MinReturn -306.423 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 19.52 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -275.484 MetaTest/__unnamed_task__/AverageReturn -275.484 MetaTest/__unnamed_task__/Iteration 28 MetaTest/__unnamed_task__/MaxReturn -249.48 MetaTest/__unnamed_task__/MinReturn -306.423 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 19.52 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 98000 ------------------------------------------------- --------- 2025-04-03 20:56:12 | [pearl_trainer] epoch #29 | Training... 2025-04-03 20:58:56 | [pearl_trainer] epoch #29 | Evaluating... 2025-04-03 20:58:56 | [pearl_trainer] epoch #29 | Sampling for adapation and meta-testing... 2025-04-03 21:02:41 | [pearl_trainer] epoch #29 | Finished meta-testing... 2025-04-03 21:02:41 | [pearl_trainer] epoch #29 | Saving snapshot... 2025-04-03 21:02:42 | [pearl_trainer] epoch #29 | Saved 2025-04-03 21:02:42 | [pearl_trainer] epoch #29 | Time 16425.69 s 2025-04-03 21:02:42 | [pearl_trainer] epoch #29 | EpochTime 429.84 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -290.315 MetaTest/Average/AverageReturn -290.315 MetaTest/Average/Iteration 29 MetaTest/Average/MaxReturn -219.038 MetaTest/Average/MinReturn -401.55 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 62.0525 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -290.315 MetaTest/__unnamed_task__/AverageReturn -290.315 MetaTest/__unnamed_task__/Iteration 29 MetaTest/__unnamed_task__/MaxReturn -219.038 MetaTest/__unnamed_task__/MinReturn -401.55 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 62.0525 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 100000 ------------------------------------------------- ----------- 2025-04-03 21:03:25 | [pearl_trainer] epoch #30 | Training... 2025-04-03 21:06:19 | [pearl_trainer] epoch #30 | Evaluating... 2025-04-03 21:06:19 | [pearl_trainer] epoch #30 | Sampling for adapation and meta-testing... 2025-04-03 21:10:48 | [pearl_trainer] epoch #30 | Finished meta-testing... 2025-04-03 21:10:48 | [pearl_trainer] epoch #30 | Saving snapshot... 2025-04-03 21:10:50 | [pearl_trainer] epoch #30 | Saved 2025-04-03 21:10:50 | [pearl_trainer] epoch #30 | Time 16913.33 s 2025-04-03 21:10:50 | [pearl_trainer] epoch #30 | EpochTime 487.63 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -274.344 MetaTest/Average/AverageReturn -274.344 MetaTest/Average/Iteration 30 MetaTest/Average/MaxReturn -244.356 MetaTest/Average/MinReturn -313.085 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.2761 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -274.344 MetaTest/__unnamed_task__/AverageReturn -274.344 MetaTest/__unnamed_task__/Iteration 30 MetaTest/__unnamed_task__/MaxReturn -244.356 MetaTest/__unnamed_task__/MinReturn -313.085 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.2761 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 102000 ------------------------------------------------- ----------- 2025-04-03 21:11:31 | [pearl_trainer] epoch #31 | Training... 2025-04-03 21:14:08 | [pearl_trainer] epoch #31 | Evaluating... 2025-04-03 21:14:08 | [pearl_trainer] epoch #31 | Sampling for adapation and meta-testing... 2025-04-03 21:18:15 | [pearl_trainer] epoch #31 | Finished meta-testing... 2025-04-03 21:18:15 | [pearl_trainer] epoch #31 | Saving snapshot... 2025-04-03 21:18:16 | [pearl_trainer] epoch #31 | Saved 2025-04-03 21:18:16 | [pearl_trainer] epoch #31 | Time 17359.30 s 2025-04-03 21:18:16 | [pearl_trainer] epoch #31 | EpochTime 445.97 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -238.764 MetaTest/Average/AverageReturn -238.764 MetaTest/Average/Iteration 31 MetaTest/Average/MaxReturn -183.812 MetaTest/Average/MinReturn -298.397 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 38.8437 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -238.764 MetaTest/__unnamed_task__/AverageReturn -238.764 MetaTest/__unnamed_task__/Iteration 31 MetaTest/__unnamed_task__/MaxReturn -183.812 MetaTest/__unnamed_task__/MinReturn -298.397 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 38.8437 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 104000 ------------------------------------------------- ----------- 2025-04-03 21:19:01 | [pearl_trainer] epoch #32 | Training... 2025-04-03 21:22:12 | [pearl_trainer] epoch #32 | Evaluating... 2025-04-03 21:22:12 | [pearl_trainer] epoch #32 | Sampling for adapation and meta-testing... 2025-04-03 21:26:46 | [pearl_trainer] epoch #32 | Finished meta-testing... 2025-04-03 21:26:46 | [pearl_trainer] epoch #32 | Saving snapshot... 2025-04-03 21:26:47 | [pearl_trainer] epoch #32 | Saved 2025-04-03 21:26:47 | [pearl_trainer] epoch #32 | Time 17870.92 s 2025-04-03 21:26:47 | [pearl_trainer] epoch #32 | EpochTime 511.63 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -288.627 MetaTest/Average/AverageReturn -288.627 MetaTest/Average/Iteration 32 MetaTest/Average/MaxReturn -232.402 MetaTest/Average/MinReturn -344.213 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 38.0516 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -288.627 MetaTest/__unnamed_task__/AverageReturn -288.627 MetaTest/__unnamed_task__/Iteration 32 MetaTest/__unnamed_task__/MaxReturn -232.402 MetaTest/__unnamed_task__/MinReturn -344.213 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 38.0516 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 106000 ------------------------------------------------- ----------- 2025-04-03 21:27:34 | [pearl_trainer] epoch #33 | Training... 2025-04-03 21:30:21 | [pearl_trainer] epoch #33 | Evaluating... 2025-04-03 21:30:21 | [pearl_trainer] epoch #33 | Sampling for adapation and meta-testing... 2025-04-03 21:33:58 | [pearl_trainer] epoch #33 | Finished meta-testing... 2025-04-03 21:33:58 | [pearl_trainer] epoch #33 | Saving snapshot... 2025-04-03 21:33:59 | [pearl_trainer] epoch #33 | Saved 2025-04-03 21:33:59 | [pearl_trainer] epoch #33 | Time 18303.06 s 2025-04-03 21:33:59 | [pearl_trainer] epoch #33 | EpochTime 432.13 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -314.678 MetaTest/Average/AverageReturn -314.678 MetaTest/Average/Iteration 33 MetaTest/Average/MaxReturn -280.453 MetaTest/Average/MinReturn -333.88 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 18.1541 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -314.678 MetaTest/__unnamed_task__/AverageReturn -314.678 MetaTest/__unnamed_task__/Iteration 33 MetaTest/__unnamed_task__/MaxReturn -280.453 MetaTest/__unnamed_task__/MinReturn -333.88 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 18.1541 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 108000 ------------------------------------------------- ----------- 2025-04-03 21:34:40 | [pearl_trainer] epoch #34 | Training... 2025-04-03 21:37:22 | [pearl_trainer] epoch #34 | Evaluating... 2025-04-03 21:37:22 | [pearl_trainer] epoch #34 | Sampling for adapation and meta-testing... 2025-04-03 21:41:00 | [pearl_trainer] epoch #34 | Finished meta-testing... 2025-04-03 21:41:00 | [pearl_trainer] epoch #34 | Saving snapshot... 2025-04-03 21:41:01 | [pearl_trainer] epoch #34 | Saved 2025-04-03 21:41:01 | [pearl_trainer] epoch #34 | Time 18724.81 s 2025-04-03 21:41:01 | [pearl_trainer] epoch #34 | EpochTime 421.75 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -298.593 MetaTest/Average/AverageReturn -298.593 MetaTest/Average/Iteration 34 MetaTest/Average/MaxReturn -262.276 MetaTest/Average/MinReturn -318.468 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 20.3695 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -298.593 MetaTest/__unnamed_task__/AverageReturn -298.593 MetaTest/__unnamed_task__/Iteration 34 MetaTest/__unnamed_task__/MaxReturn -262.276 MetaTest/__unnamed_task__/MinReturn -318.468 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 20.3695 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 110000 ------------------------------------------------- ----------- 2025-04-03 21:41:42 | [pearl_trainer] epoch #35 | Training... 2025-04-03 21:44:19 | [pearl_trainer] epoch #35 | Evaluating... 2025-04-03 21:44:19 | [pearl_trainer] epoch #35 | Sampling for adapation and meta-testing... 2025-04-03 21:48:00 | [pearl_trainer] epoch #35 | Finished meta-testing... 2025-04-03 21:48:00 | [pearl_trainer] epoch #35 | Saving snapshot... 2025-04-03 21:48:01 | [pearl_trainer] epoch #35 | Saved 2025-04-03 21:48:01 | [pearl_trainer] epoch #35 | Time 19144.72 s 2025-04-03 21:48:01 | [pearl_trainer] epoch #35 | EpochTime 419.91 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -269.324 MetaTest/Average/AverageReturn -269.324 MetaTest/Average/Iteration 35 MetaTest/Average/MaxReturn -255.635 MetaTest/Average/MinReturn -287.441 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 11.7607 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -269.324 MetaTest/__unnamed_task__/AverageReturn -269.324 MetaTest/__unnamed_task__/Iteration 35 MetaTest/__unnamed_task__/MaxReturn -255.635 MetaTest/__unnamed_task__/MinReturn -287.441 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 11.7607 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 112000 ------------------------------------------------- ----------- 2025-04-03 21:48:44 | [pearl_trainer] epoch #36 | Training... 2025-04-03 21:51:23 | [pearl_trainer] epoch #36 | Evaluating... 2025-04-03 21:51:23 | [pearl_trainer] epoch #36 | Sampling for adapation and meta-testing... 2025-04-03 21:55:05 | [pearl_trainer] epoch #36 | Finished meta-testing... 2025-04-03 21:55:05 | [pearl_trainer] epoch #36 | Saving snapshot... 2025-04-03 21:55:06 | [pearl_trainer] epoch #36 | Saved 2025-04-03 21:55:06 | [pearl_trainer] epoch #36 | Time 19569.57 s 2025-04-03 21:55:06 | [pearl_trainer] epoch #36 | EpochTime 424.85 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -275.674 MetaTest/Average/AverageReturn -275.674 MetaTest/Average/Iteration 36 MetaTest/Average/MaxReturn -239.166 MetaTest/Average/MinReturn -297.939 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 23.8881 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -275.674 MetaTest/__unnamed_task__/AverageReturn -275.674 MetaTest/__unnamed_task__/Iteration 36 MetaTest/__unnamed_task__/MaxReturn -239.166 MetaTest/__unnamed_task__/MinReturn -297.939 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 23.8881 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 114000 ------------------------------------------------- ----------- 2025-04-03 21:55:45 | [pearl_trainer] epoch #37 | Training... 2025-04-03 21:58:26 | [pearl_trainer] epoch #37 | Evaluating... 2025-04-03 21:58:26 | [pearl_trainer] epoch #37 | Sampling for adapation and meta-testing... 2025-04-03 22:01:57 | [pearl_trainer] epoch #37 | Finished meta-testing... 2025-04-03 22:01:57 | [pearl_trainer] epoch #37 | Saving snapshot... 2025-04-03 22:01:58 | [pearl_trainer] epoch #37 | Saved 2025-04-03 22:01:58 | [pearl_trainer] epoch #37 | Time 19982.01 s 2025-04-03 22:01:58 | [pearl_trainer] epoch #37 | EpochTime 412.44 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -242.493 MetaTest/Average/AverageReturn -242.493 MetaTest/Average/Iteration 37 MetaTest/Average/MaxReturn -211.168 MetaTest/Average/MinReturn -283.583 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.82 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -242.493 MetaTest/__unnamed_task__/AverageReturn -242.493 MetaTest/__unnamed_task__/Iteration 37 MetaTest/__unnamed_task__/MaxReturn -211.168 MetaTest/__unnamed_task__/MinReturn -283.583 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.82 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 116000 ------------------------------------------------- ---------- 2025-04-03 22:02:36 | [pearl_trainer] epoch #38 | Training... 2025-04-03 22:05:20 | [pearl_trainer] epoch #38 | Evaluating... 2025-04-03 22:05:20 | [pearl_trainer] epoch #38 | Sampling for adapation and meta-testing... 2025-04-03 22:08:47 | [pearl_trainer] epoch #38 | Finished meta-testing... 2025-04-03 22:08:47 | [pearl_trainer] epoch #38 | Saving snapshot... 2025-04-03 22:08:48 | [pearl_trainer] epoch #38 | Saved 2025-04-03 22:08:48 | [pearl_trainer] epoch #38 | Time 20391.69 s 2025-04-03 22:08:48 | [pearl_trainer] epoch #38 | EpochTime 409.68 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -257.461 MetaTest/Average/AverageReturn -257.461 MetaTest/Average/Iteration 38 MetaTest/Average/MaxReturn -237.853 MetaTest/Average/MinReturn -295.31 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 22.6153 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -257.461 MetaTest/__unnamed_task__/AverageReturn -257.461 MetaTest/__unnamed_task__/Iteration 38 MetaTest/__unnamed_task__/MaxReturn -237.853 MetaTest/__unnamed_task__/MinReturn -295.31 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 22.6153 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 118000 ------------------------------------------------- ----------- 2025-04-03 22:09:26 | [pearl_trainer] epoch #39 | Training... 2025-04-03 22:12:25 | [pearl_trainer] epoch #39 | Evaluating... 2025-04-03 22:12:25 | [pearl_trainer] epoch #39 | Sampling for adapation and meta-testing... 2025-04-03 22:16:22 | [pearl_trainer] epoch #39 | Finished meta-testing... 2025-04-03 22:16:22 | [pearl_trainer] epoch #39 | Saving snapshot... 2025-04-03 22:16:23 | [pearl_trainer] epoch #39 | Saved 2025-04-03 22:16:23 | [pearl_trainer] epoch #39 | Time 20846.96 s 2025-04-03 22:16:23 | [pearl_trainer] epoch #39 | EpochTime 455.26 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -272.935 MetaTest/Average/AverageReturn -272.935 MetaTest/Average/Iteration 39 MetaTest/Average/MaxReturn -257.308 MetaTest/Average/MinReturn -288.736 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 10.8879 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -272.935 MetaTest/__unnamed_task__/AverageReturn -272.935 MetaTest/__unnamed_task__/Iteration 39 MetaTest/__unnamed_task__/MaxReturn -257.308 MetaTest/__unnamed_task__/MinReturn -288.736 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 10.8879 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 120000 ------------------------------------------------- ----------- 2025-04-03 22:17:04 | [pearl_trainer] epoch #40 | Training... 2025-04-03 22:20:29 | [pearl_trainer] epoch #40 | Evaluating... 2025-04-03 22:20:29 | [pearl_trainer] epoch #40 | Sampling for adapation and meta-testing... 2025-04-03 22:24:50 | [pearl_trainer] epoch #40 | Finished meta-testing... 2025-04-03 22:24:50 | [pearl_trainer] epoch #40 | Saving snapshot... 2025-04-03 22:24:52 | [pearl_trainer] epoch #40 | Saved 2025-04-03 22:24:52 | [pearl_trainer] epoch #40 | Time 21355.20 s 2025-04-03 22:24:52 | [pearl_trainer] epoch #40 | EpochTime 508.23 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -273.433 MetaTest/Average/AverageReturn -273.433 MetaTest/Average/Iteration 40 MetaTest/Average/MaxReturn -252.831 MetaTest/Average/MinReturn -304.282 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 17.3702 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -273.433 MetaTest/__unnamed_task__/AverageReturn -273.433 MetaTest/__unnamed_task__/Iteration 40 MetaTest/__unnamed_task__/MaxReturn -252.831 MetaTest/__unnamed_task__/MinReturn -304.282 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 17.3702 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 122000 ------------------------------------------------- ----------- 2025-04-03 22:25:37 | [pearl_trainer] epoch #41 | Training... 2025-04-03 22:29:03 | [pearl_trainer] epoch #41 | Evaluating... 2025-04-03 22:29:03 | [pearl_trainer] epoch #41 | Sampling for adapation and meta-testing... 2025-04-03 22:33:22 | [pearl_trainer] epoch #41 | Finished meta-testing... 2025-04-03 22:33:22 | [pearl_trainer] epoch #41 | Saving snapshot... 2025-04-03 22:33:24 | [pearl_trainer] epoch #41 | Saved 2025-04-03 22:33:24 | [pearl_trainer] epoch #41 | Time 21867.48 s 2025-04-03 22:33:24 | [pearl_trainer] epoch #41 | EpochTime 512.28 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -282.273 MetaTest/Average/AverageReturn -282.273 MetaTest/Average/Iteration 41 MetaTest/Average/MaxReturn -267.609 MetaTest/Average/MinReturn -296.868 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 10.2742 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -282.273 MetaTest/__unnamed_task__/AverageReturn -282.273 MetaTest/__unnamed_task__/Iteration 41 MetaTest/__unnamed_task__/MaxReturn -267.609 MetaTest/__unnamed_task__/MinReturn -296.868 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 10.2742 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 124000 ------------------------------------------------- ----------- 2025-04-03 22:34:09 | [pearl_trainer] epoch #42 | Training... 2025-04-03 22:37:27 | [pearl_trainer] epoch #42 | Evaluating... 2025-04-03 22:37:27 | [pearl_trainer] epoch #42 | Sampling for adapation and meta-testing... 2025-04-03 22:41:54 | [pearl_trainer] epoch #42 | Finished meta-testing... 2025-04-03 22:41:54 | [pearl_trainer] epoch #42 | Saving snapshot... 2025-04-03 22:41:55 | [pearl_trainer] epoch #42 | Saved 2025-04-03 22:41:55 | [pearl_trainer] epoch #42 | Time 22378.44 s 2025-04-03 22:41:55 | [pearl_trainer] epoch #42 | EpochTime 510.96 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -343.554 MetaTest/Average/AverageReturn -343.554 MetaTest/Average/Iteration 42 MetaTest/Average/MaxReturn -288.29 MetaTest/Average/MinReturn -406.848 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 41.1933 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -343.554 MetaTest/__unnamed_task__/AverageReturn -343.554 MetaTest/__unnamed_task__/Iteration 42 MetaTest/__unnamed_task__/MaxReturn -288.29 MetaTest/__unnamed_task__/MinReturn -406.848 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 41.1933 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 126000 ------------------------------------------------- ----------- 2025-04-03 22:42:43 | [pearl_trainer] epoch #43 | Training... 2025-04-03 22:45:29 | [pearl_trainer] epoch #43 | Evaluating... 2025-04-03 22:45:29 | [pearl_trainer] epoch #43 | Sampling for adapation and meta-testing... 2025-04-03 22:50:23 | [pearl_trainer] epoch #43 | Finished meta-testing... 2025-04-03 22:50:23 | [pearl_trainer] epoch #43 | Saving snapshot... 2025-04-03 22:50:25 | [pearl_trainer] epoch #43 | Saved 2025-04-03 22:50:25 | [pearl_trainer] epoch #43 | Time 22888.20 s 2025-04-03 22:50:25 | [pearl_trainer] epoch #43 | EpochTime 509.76 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -409.313 MetaTest/Average/AverageReturn -409.313 MetaTest/Average/Iteration 43 MetaTest/Average/MaxReturn -365.389 MetaTest/Average/MinReturn -464.846 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 33.3414 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -409.313 MetaTest/__unnamed_task__/AverageReturn -409.313 MetaTest/__unnamed_task__/Iteration 43 MetaTest/__unnamed_task__/MaxReturn -365.389 MetaTest/__unnamed_task__/MinReturn -464.846 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 33.3414 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 128000 ------------------------------------------------- ----------- 2025-04-03 22:51:13 | [pearl_trainer] epoch #44 | Training... 2025-04-03 22:54:16 | [pearl_trainer] epoch #44 | Evaluating... 2025-04-03 22:54:16 | [pearl_trainer] epoch #44 | Sampling for adapation and meta-testing... 2025-04-03 22:59:40 | [pearl_trainer] epoch #44 | Finished meta-testing... 2025-04-03 22:59:40 | [pearl_trainer] epoch #44 | Saving snapshot... 2025-04-03 22:59:41 | [pearl_trainer] epoch #44 | Saved 2025-04-03 22:59:41 | [pearl_trainer] epoch #44 | Time 23444.41 s 2025-04-03 22:59:41 | [pearl_trainer] epoch #44 | EpochTime 556.20 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -393.034 MetaTest/Average/AverageReturn -393.034 MetaTest/Average/Iteration 44 MetaTest/Average/MaxReturn -345.707 MetaTest/Average/MinReturn -468.864 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 44.5741 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -393.034 MetaTest/__unnamed_task__/AverageReturn -393.034 MetaTest/__unnamed_task__/Iteration 44 MetaTest/__unnamed_task__/MaxReturn -345.707 MetaTest/__unnamed_task__/MinReturn -468.864 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 44.5741 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 130000 ------------------------------------------------- ----------- 2025-04-03 23:00:36 | [pearl_trainer] epoch #45 | Training... 2025-04-03 23:03:52 | [pearl_trainer] epoch #45 | Evaluating... 2025-04-03 23:03:52 | [pearl_trainer] epoch #45 | Sampling for adapation and meta-testing... 2025-04-03 23:09:14 | [pearl_trainer] epoch #45 | Finished meta-testing... 2025-04-03 23:09:14 | [pearl_trainer] epoch #45 | Saving snapshot... 2025-04-03 23:09:16 | [pearl_trainer] epoch #45 | Saved 2025-04-03 23:09:16 | [pearl_trainer] epoch #45 | Time 24019.28 s 2025-04-03 23:09:16 | [pearl_trainer] epoch #45 | EpochTime 574.87 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -346.542 MetaTest/Average/AverageReturn -346.542 MetaTest/Average/Iteration 45 MetaTest/Average/MaxReturn -270.891 MetaTest/Average/MinReturn -378.753 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 40.7554 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -346.542 MetaTest/__unnamed_task__/AverageReturn -346.542 MetaTest/__unnamed_task__/Iteration 45 MetaTest/__unnamed_task__/MaxReturn -270.891 MetaTest/__unnamed_task__/MinReturn -378.753 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 40.7554 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 132000 ------------------------------------------------- ----------- 2025-04-03 23:10:12 | [pearl_trainer] epoch #46 | Training... 2025-04-03 23:13:26 | [pearl_trainer] epoch #46 | Evaluating... 2025-04-03 23:13:26 | [pearl_trainer] epoch #46 | Sampling for adapation and meta-testing... 2025-04-03 23:18:21 | [pearl_trainer] epoch #46 | Finished meta-testing... 2025-04-03 23:18:21 | [pearl_trainer] epoch #46 | Saving snapshot... 2025-04-03 23:18:22 | [pearl_trainer] epoch #46 | Saved 2025-04-03 23:18:22 | [pearl_trainer] epoch #46 | Time 24565.47 s 2025-04-03 23:18:22 | [pearl_trainer] epoch #46 | EpochTime 546.19 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -266.371 MetaTest/Average/AverageReturn -266.371 MetaTest/Average/Iteration 46 MetaTest/Average/MaxReturn -216.023 MetaTest/Average/MinReturn -315.592 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.7997 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -266.371 MetaTest/__unnamed_task__/AverageReturn -266.371 MetaTest/__unnamed_task__/Iteration 46 MetaTest/__unnamed_task__/MaxReturn -216.023 MetaTest/__unnamed_task__/MinReturn -315.592 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.7997 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 134000 ------------------------------------------------- ----------- 2025-04-03 23:19:17 | [pearl_trainer] epoch #47 | Training... 2025-04-03 23:22:29 | [pearl_trainer] epoch #47 | Evaluating... 2025-04-03 23:22:29 | [pearl_trainer] epoch #47 | Sampling for adapation and meta-testing... 2025-04-03 23:27:21 | [pearl_trainer] epoch #47 | Finished meta-testing... 2025-04-03 23:27:21 | [pearl_trainer] epoch #47 | Saving snapshot... 2025-04-03 23:27:22 | [pearl_trainer] epoch #47 | Saved 2025-04-03 23:27:22 | [pearl_trainer] epoch #47 | Time 25106.05 s 2025-04-03 23:27:22 | [pearl_trainer] epoch #47 | EpochTime 540.57 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -310.814 MetaTest/Average/AverageReturn -310.814 MetaTest/Average/Iteration 47 MetaTest/Average/MaxReturn -246.627 MetaTest/Average/MinReturn -371.996 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 50.2911 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -310.814 MetaTest/__unnamed_task__/AverageReturn -310.814 MetaTest/__unnamed_task__/Iteration 47 MetaTest/__unnamed_task__/MaxReturn -246.627 MetaTest/__unnamed_task__/MinReturn -371.996 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 50.2911 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 136000 ------------------------------------------------- ----------- 2025-04-03 23:28:12 | [pearl_trainer] epoch #48 | Training... 2025-04-03 23:31:25 | [pearl_trainer] epoch #48 | Evaluating... 2025-04-03 23:31:25 | [pearl_trainer] epoch #48 | Sampling for adapation and meta-testing... 2025-04-03 23:36:30 | [pearl_trainer] epoch #48 | Finished meta-testing... 2025-04-03 23:36:30 | [pearl_trainer] epoch #48 | Saving snapshot... 2025-04-03 23:36:32 | [pearl_trainer] epoch #48 | Saved 2025-04-03 23:36:32 | [pearl_trainer] epoch #48 | Time 25655.22 s 2025-04-03 23:36:32 | [pearl_trainer] epoch #48 | EpochTime 549.17 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -280.552 MetaTest/Average/AverageReturn -280.552 MetaTest/Average/Iteration 48 MetaTest/Average/MaxReturn -227.85 MetaTest/Average/MinReturn -366.674 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 57.5585 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -280.552 MetaTest/__unnamed_task__/AverageReturn -280.552 MetaTest/__unnamed_task__/Iteration 48 MetaTest/__unnamed_task__/MaxReturn -227.85 MetaTest/__unnamed_task__/MinReturn -366.674 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 57.5585 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 138000 ------------------------------------------------- ----------- 2025-04-03 23:37:23 | [pearl_trainer] epoch #49 | Training... 2025-04-03 23:40:37 | [pearl_trainer] epoch #49 | Evaluating... 2025-04-03 23:40:37 | [pearl_trainer] epoch #49 | Sampling for adapation and meta-testing... 2025-04-03 23:45:27 | [pearl_trainer] epoch #49 | Finished meta-testing... 2025-04-03 23:45:27 | [pearl_trainer] epoch #49 | Saving snapshot... 2025-04-03 23:45:29 | [pearl_trainer] epoch #49 | Saved 2025-04-03 23:45:29 | [pearl_trainer] epoch #49 | Time 26192.57 s 2025-04-03 23:45:29 | [pearl_trainer] epoch #49 | EpochTime 537.35 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -291.205 MetaTest/Average/AverageReturn -291.205 MetaTest/Average/Iteration 49 MetaTest/Average/MaxReturn -194.863 MetaTest/Average/MinReturn -357.308 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 59.1798 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -291.205 MetaTest/__unnamed_task__/AverageReturn -291.205 MetaTest/__unnamed_task__/Iteration 49 MetaTest/__unnamed_task__/MaxReturn -194.863 MetaTest/__unnamed_task__/MinReturn -357.308 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 59.1798 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 140000 ------------------------------------------------- ----------- 2025-04-03 23:46:23 | [pearl_trainer] epoch #50 | Training... 2025-04-03 23:49:37 | [pearl_trainer] epoch #50 | Evaluating... 2025-04-03 23:49:37 | [pearl_trainer] epoch #50 | Sampling for adapation and meta-testing... 2025-04-03 23:54:26 | [pearl_trainer] epoch #50 | Finished meta-testing... 2025-04-03 23:54:26 | [pearl_trainer] epoch #50 | Saving snapshot... 2025-04-03 23:54:28 | [pearl_trainer] epoch #50 | Saved 2025-04-03 23:54:28 | [pearl_trainer] epoch #50 | Time 26731.23 s 2025-04-03 23:54:28 | [pearl_trainer] epoch #50 | EpochTime 538.66 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -280.282 MetaTest/Average/AverageReturn -280.282 MetaTest/Average/Iteration 50 MetaTest/Average/MaxReturn -236.655 MetaTest/Average/MinReturn -315.854 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.3363 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -280.282 MetaTest/__unnamed_task__/AverageReturn -280.282 MetaTest/__unnamed_task__/Iteration 50 MetaTest/__unnamed_task__/MaxReturn -236.655 MetaTest/__unnamed_task__/MinReturn -315.854 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.3363 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 142000 ------------------------------------------------- ----------- 2025-04-03 23:55:19 | [pearl_trainer] epoch #51 | Training... 2025-04-03 23:58:34 | [pearl_trainer] epoch #51 | Evaluating... 2025-04-03 23:58:34 | [pearl_trainer] epoch #51 | Sampling for adapation and meta-testing... 2025-04-04 00:03:18 | [pearl_trainer] epoch #51 | Finished meta-testing... 2025-04-04 00:03:18 | [pearl_trainer] epoch #51 | Saving snapshot... 2025-04-04 00:03:19 | [pearl_trainer] epoch #51 | Saved 2025-04-04 00:03:19 | [pearl_trainer] epoch #51 | Time 27262.77 s 2025-04-04 00:03:19 | [pearl_trainer] epoch #51 | EpochTime 531.54 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -277.236 MetaTest/Average/AverageReturn -277.236 MetaTest/Average/Iteration 51 MetaTest/Average/MaxReturn -242.418 MetaTest/Average/MinReturn -323.117 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 33.1211 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -277.236 MetaTest/__unnamed_task__/AverageReturn -277.236 MetaTest/__unnamed_task__/Iteration 51 MetaTest/__unnamed_task__/MaxReturn -242.418 MetaTest/__unnamed_task__/MinReturn -323.117 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 33.1211 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 144000 ------------------------------------------------- ----------- 2025-04-04 00:04:10 | [pearl_trainer] epoch #52 | Training... 2025-04-04 00:07:33 | [pearl_trainer] epoch #52 | Evaluating... 2025-04-04 00:07:33 | [pearl_trainer] epoch #52 | Sampling for adapation and meta-testing... 2025-04-04 00:12:12 | [pearl_trainer] epoch #52 | Finished meta-testing... 2025-04-04 00:12:12 | [pearl_trainer] epoch #52 | Saving snapshot... 2025-04-04 00:12:13 | [pearl_trainer] epoch #52 | Saved 2025-04-04 00:12:13 | [pearl_trainer] epoch #52 | Time 27796.88 s 2025-04-04 00:12:13 | [pearl_trainer] epoch #52 | EpochTime 534.11 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -310.227 MetaTest/Average/AverageReturn -310.227 MetaTest/Average/Iteration 52 MetaTest/Average/MaxReturn -247.816 MetaTest/Average/MinReturn -386.109 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 49.156 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -310.227 MetaTest/__unnamed_task__/AverageReturn -310.227 MetaTest/__unnamed_task__/Iteration 52 MetaTest/__unnamed_task__/MaxReturn -247.816 MetaTest/__unnamed_task__/MinReturn -386.109 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 49.156 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 146000 ------------------------------------------------- ---------- 2025-04-04 00:13:06 | [pearl_trainer] epoch #53 | Training... 2025-04-04 00:16:18 | [pearl_trainer] epoch #53 | Evaluating... 2025-04-04 00:16:18 | [pearl_trainer] epoch #53 | Sampling for adapation and meta-testing... 2025-04-04 00:20:56 | [pearl_trainer] epoch #53 | Finished meta-testing... 2025-04-04 00:20:57 | [pearl_trainer] epoch #53 | Saving snapshot... 2025-04-04 00:20:58 | [pearl_trainer] epoch #53 | Saved 2025-04-04 00:20:58 | [pearl_trainer] epoch #53 | Time 28321.64 s 2025-04-04 00:20:58 | [pearl_trainer] epoch #53 | EpochTime 524.76 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -311.172 MetaTest/Average/AverageReturn -311.172 MetaTest/Average/Iteration 53 MetaTest/Average/MaxReturn -258.304 MetaTest/Average/MinReturn -406.972 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 57.599 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -311.172 MetaTest/__unnamed_task__/AverageReturn -311.172 MetaTest/__unnamed_task__/Iteration 53 MetaTest/__unnamed_task__/MaxReturn -258.304 MetaTest/__unnamed_task__/MinReturn -406.972 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 57.599 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 148000 ------------------------------------------------- ---------- 2025-04-04 00:21:48 | [pearl_trainer] epoch #54 | Training... 2025-04-04 00:24:57 | [pearl_trainer] epoch #54 | Evaluating... 2025-04-04 00:24:57 | [pearl_trainer] epoch #54 | Sampling for adapation and meta-testing... 2025-04-04 00:29:28 | [pearl_trainer] epoch #54 | Finished meta-testing... 2025-04-04 00:29:28 | [pearl_trainer] epoch #54 | Saving snapshot... 2025-04-04 00:29:30 | [pearl_trainer] epoch #54 | Saved 2025-04-04 00:29:30 | [pearl_trainer] epoch #54 | Time 28833.32 s 2025-04-04 00:29:30 | [pearl_trainer] epoch #54 | EpochTime 511.67 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -300.377 MetaTest/Average/AverageReturn -300.377 MetaTest/Average/Iteration 54 MetaTest/Average/MaxReturn -210.563 MetaTest/Average/MinReturn -384.622 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 59.305 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -300.377 MetaTest/__unnamed_task__/AverageReturn -300.377 MetaTest/__unnamed_task__/Iteration 54 MetaTest/__unnamed_task__/MaxReturn -210.563 MetaTest/__unnamed_task__/MinReturn -384.622 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 59.305 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 150000 ------------------------------------------------- ---------- 2025-04-04 00:30:21 | [pearl_trainer] epoch #55 | Training... 2025-04-04 00:33:35 | [pearl_trainer] epoch #55 | Evaluating... 2025-04-04 00:33:35 | [pearl_trainer] epoch #55 | Sampling for adapation and meta-testing... 2025-04-04 00:38:25 | [pearl_trainer] epoch #55 | Finished meta-testing... 2025-04-04 00:38:25 | [pearl_trainer] epoch #55 | Saving snapshot... 2025-04-04 00:38:27 | [pearl_trainer] epoch #55 | Saved 2025-04-04 00:38:27 | [pearl_trainer] epoch #55 | Time 29370.36 s 2025-04-04 00:38:27 | [pearl_trainer] epoch #55 | EpochTime 537.05 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -292.651 MetaTest/Average/AverageReturn -292.651 MetaTest/Average/Iteration 55 MetaTest/Average/MaxReturn -253.658 MetaTest/Average/MinReturn -316.306 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 21.9704 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -292.651 MetaTest/__unnamed_task__/AverageReturn -292.651 MetaTest/__unnamed_task__/Iteration 55 MetaTest/__unnamed_task__/MaxReturn -253.658 MetaTest/__unnamed_task__/MinReturn -316.306 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 21.9704 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 152000 ------------------------------------------------- ----------- 2025-04-04 00:39:18 | [pearl_trainer] epoch #56 | Training... 2025-04-04 00:42:30 | [pearl_trainer] epoch #56 | Evaluating... 2025-04-04 00:42:30 | [pearl_trainer] epoch #56 | Sampling for adapation and meta-testing... 2025-04-04 00:47:16 | [pearl_trainer] epoch #56 | Finished meta-testing... 2025-04-04 00:47:16 | [pearl_trainer] epoch #56 | Saving snapshot... 2025-04-04 00:47:17 | [pearl_trainer] epoch #56 | Saved 2025-04-04 00:47:17 | [pearl_trainer] epoch #56 | Time 29901.16 s 2025-04-04 00:47:17 | [pearl_trainer] epoch #56 | EpochTime 530.79 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -263.427 MetaTest/Average/AverageReturn -263.427 MetaTest/Average/Iteration 56 MetaTest/Average/MaxReturn -211.587 MetaTest/Average/MinReturn -336.097 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 46.9043 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -263.427 MetaTest/__unnamed_task__/AverageReturn -263.427 MetaTest/__unnamed_task__/Iteration 56 MetaTest/__unnamed_task__/MaxReturn -211.587 MetaTest/__unnamed_task__/MinReturn -336.097 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 46.9043 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 154000 ------------------------------------------------- ----------- 2025-04-04 00:48:10 | [pearl_trainer] epoch #57 | Training... 2025-04-04 00:51:22 | [pearl_trainer] epoch #57 | Evaluating... 2025-04-04 00:51:22 | [pearl_trainer] epoch #57 | Sampling for adapation and meta-testing... 2025-04-04 00:56:05 | [pearl_trainer] epoch #57 | Finished meta-testing... 2025-04-04 00:56:05 | [pearl_trainer] epoch #57 | Saving snapshot... 2025-04-04 00:56:07 | [pearl_trainer] epoch #57 | Saved 2025-04-04 00:56:07 | [pearl_trainer] epoch #57 | Time 30430.66 s 2025-04-04 00:56:07 | [pearl_trainer] epoch #57 | EpochTime 529.50 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -329.192 MetaTest/Average/AverageReturn -329.192 MetaTest/Average/Iteration 57 MetaTest/Average/MaxReturn -231.236 MetaTest/Average/MinReturn -421.034 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 65.544 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -329.192 MetaTest/__unnamed_task__/AverageReturn -329.192 MetaTest/__unnamed_task__/Iteration 57 MetaTest/__unnamed_task__/MaxReturn -231.236 MetaTest/__unnamed_task__/MinReturn -421.034 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 65.544 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 156000 ------------------------------------------------- ---------- 2025-04-04 00:56:58 | [pearl_trainer] epoch #58 | Training... 2025-04-04 01:00:11 | [pearl_trainer] epoch #58 | Evaluating... 2025-04-04 01:00:11 | [pearl_trainer] epoch #58 | Sampling for adapation and meta-testing... 2025-04-04 01:04:45 | [pearl_trainer] epoch #58 | Finished meta-testing... 2025-04-04 01:04:45 | [pearl_trainer] epoch #58 | Saving snapshot... 2025-04-04 01:04:46 | [pearl_trainer] epoch #58 | Saved 2025-04-04 01:04:46 | [pearl_trainer] epoch #58 | Time 30949.65 s 2025-04-04 01:04:46 | [pearl_trainer] epoch #58 | EpochTime 518.99 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -332.37 MetaTest/Average/AverageReturn -332.37 MetaTest/Average/Iteration 58 MetaTest/Average/MaxReturn -247.267 MetaTest/Average/MinReturn -426.777 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 59.4016 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -332.37 MetaTest/__unnamed_task__/AverageReturn -332.37 MetaTest/__unnamed_task__/Iteration 58 MetaTest/__unnamed_task__/MaxReturn -247.267 MetaTest/__unnamed_task__/MinReturn -426.777 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 59.4016 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 158000 ------------------------------------------------- ----------- 2025-04-04 01:05:36 | [pearl_trainer] epoch #59 | Training... 2025-04-04 01:08:47 | [pearl_trainer] epoch #59 | Evaluating... 2025-04-04 01:08:47 | [pearl_trainer] epoch #59 | Sampling for adapation and meta-testing... 2025-04-04 01:13:32 | [pearl_trainer] epoch #59 | Finished meta-testing... 2025-04-04 01:13:32 | [pearl_trainer] epoch #59 | Saving snapshot... 2025-04-04 01:13:34 | [pearl_trainer] epoch #59 | Saved 2025-04-04 01:13:34 | [pearl_trainer] epoch #59 | Time 31477.32 s 2025-04-04 01:13:34 | [pearl_trainer] epoch #59 | EpochTime 527.67 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -250.315 MetaTest/Average/AverageReturn -250.315 MetaTest/Average/Iteration 59 MetaTest/Average/MaxReturn -227.529 MetaTest/Average/MinReturn -263.114 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 14.6573 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -250.315 MetaTest/__unnamed_task__/AverageReturn -250.315 MetaTest/__unnamed_task__/Iteration 59 MetaTest/__unnamed_task__/MaxReturn -227.529 MetaTest/__unnamed_task__/MinReturn -263.114 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 14.6573 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 160000 ------------------------------------------------- ----------- 2025-04-04 01:14:21 | [pearl_trainer] epoch #60 | Training... 2025-04-04 01:17:37 | [pearl_trainer] epoch #60 | Evaluating... 2025-04-04 01:17:37 | [pearl_trainer] epoch #60 | Sampling for adapation and meta-testing... 2025-04-04 01:22:21 | [pearl_trainer] epoch #60 | Finished meta-testing... 2025-04-04 01:22:21 | [pearl_trainer] epoch #60 | Saving snapshot... 2025-04-04 01:22:23 | [pearl_trainer] epoch #60 | Saved 2025-04-04 01:22:23 | [pearl_trainer] epoch #60 | Time 32006.30 s 2025-04-04 01:22:23 | [pearl_trainer] epoch #60 | EpochTime 528.98 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -345.153 MetaTest/Average/AverageReturn -345.153 MetaTest/Average/Iteration 60 MetaTest/Average/MaxReturn -301.161 MetaTest/Average/MinReturn -384.056 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 28.0135 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -345.153 MetaTest/__unnamed_task__/AverageReturn -345.153 MetaTest/__unnamed_task__/Iteration 60 MetaTest/__unnamed_task__/MaxReturn -301.161 MetaTest/__unnamed_task__/MinReturn -384.056 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 28.0135 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 162000 ------------------------------------------------- ----------- 2025-04-04 01:23:10 | [pearl_trainer] epoch #61 | Training... 2025-04-04 01:25:39 | [pearl_trainer] epoch #61 | Evaluating... 2025-04-04 01:25:39 | [pearl_trainer] epoch #61 | Sampling for adapation and meta-testing... 2025-04-04 01:29:25 | [pearl_trainer] epoch #61 | Finished meta-testing... 2025-04-04 01:29:25 | [pearl_trainer] epoch #61 | Saving snapshot... 2025-04-04 01:29:26 | [pearl_trainer] epoch #61 | Saved 2025-04-04 01:29:26 | [pearl_trainer] epoch #61 | Time 32429.76 s 2025-04-04 01:29:26 | [pearl_trainer] epoch #61 | EpochTime 423.46 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -326.836 MetaTest/Average/AverageReturn -326.836 MetaTest/Average/Iteration 61 MetaTest/Average/MaxReturn -249.197 MetaTest/Average/MinReturn -407.447 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 62.6605 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -326.836 MetaTest/__unnamed_task__/AverageReturn -326.836 MetaTest/__unnamed_task__/Iteration 61 MetaTest/__unnamed_task__/MaxReturn -249.197 MetaTest/__unnamed_task__/MinReturn -407.447 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 62.6605 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 164000 ------------------------------------------------- ----------- 2025-04-04 01:30:09 | [pearl_trainer] epoch #62 | Training... 2025-04-04 01:32:45 | [pearl_trainer] epoch #62 | Evaluating... 2025-04-04 01:32:45 | [pearl_trainer] epoch #62 | Sampling for adapation and meta-testing... 2025-04-04 01:36:58 | [pearl_trainer] epoch #62 | Finished meta-testing... 2025-04-04 01:36:58 | [pearl_trainer] epoch #62 | Saving snapshot... 2025-04-04 01:36:59 | [pearl_trainer] epoch #62 | Saved 2025-04-04 01:36:59 | [pearl_trainer] epoch #62 | Time 32882.59 s 2025-04-04 01:36:59 | [pearl_trainer] epoch #62 | EpochTime 452.83 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -320.617 MetaTest/Average/AverageReturn -320.617 MetaTest/Average/Iteration 62 MetaTest/Average/MaxReturn -220.851 MetaTest/Average/MinReturn -421.761 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 64.0996 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -320.617 MetaTest/__unnamed_task__/AverageReturn -320.617 MetaTest/__unnamed_task__/Iteration 62 MetaTest/__unnamed_task__/MaxReturn -220.851 MetaTest/__unnamed_task__/MinReturn -421.761 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 64.0996 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 166000 ------------------------------------------------- ----------- 2025-04-04 01:37:42 | [pearl_trainer] epoch #63 | Training... 2025-04-04 01:40:21 | [pearl_trainer] epoch #63 | Evaluating... 2025-04-04 01:40:21 | [pearl_trainer] epoch #63 | Sampling for adapation and meta-testing... 2025-04-04 01:44:24 | [pearl_trainer] epoch #63 | Finished meta-testing... 2025-04-04 01:44:24 | [pearl_trainer] epoch #63 | Saving snapshot... 2025-04-04 01:44:25 | [pearl_trainer] epoch #63 | Saved 2025-04-04 01:44:25 | [pearl_trainer] epoch #63 | Time 33329.15 s 2025-04-04 01:44:25 | [pearl_trainer] epoch #63 | EpochTime 446.55 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -269.188 MetaTest/Average/AverageReturn -269.188 MetaTest/Average/Iteration 63 MetaTest/Average/MaxReturn -252.022 MetaTest/Average/MinReturn -306.343 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 19.3734 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -269.188 MetaTest/__unnamed_task__/AverageReturn -269.188 MetaTest/__unnamed_task__/Iteration 63 MetaTest/__unnamed_task__/MaxReturn -252.022 MetaTest/__unnamed_task__/MinReturn -306.343 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 19.3734 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 168000 ------------------------------------------------- ----------- 2025-04-04 01:45:14 | [pearl_trainer] epoch #64 | Training... 2025-04-04 01:48:06 | [pearl_trainer] epoch #64 | Evaluating... 2025-04-04 01:48:06 | [pearl_trainer] epoch #64 | Sampling for adapation and meta-testing... 2025-04-04 01:52:01 | [pearl_trainer] epoch #64 | Finished meta-testing... 2025-04-04 01:52:01 | [pearl_trainer] epoch #64 | Saving snapshot... 2025-04-04 01:52:03 | [pearl_trainer] epoch #64 | Saved 2025-04-04 01:52:03 | [pearl_trainer] epoch #64 | Time 33786.24 s 2025-04-04 01:52:03 | [pearl_trainer] epoch #64 | EpochTime 457.09 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -267.675 MetaTest/Average/AverageReturn -267.675 MetaTest/Average/Iteration 64 MetaTest/Average/MaxReturn -215.272 MetaTest/Average/MinReturn -365.031 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 51.0412 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -267.675 MetaTest/__unnamed_task__/AverageReturn -267.675 MetaTest/__unnamed_task__/Iteration 64 MetaTest/__unnamed_task__/MaxReturn -215.272 MetaTest/__unnamed_task__/MinReturn -365.031 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 51.0412 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 170000 ------------------------------------------------- ----------- 2025-04-04 01:52:47 | [pearl_trainer] epoch #65 | Training... 2025-04-04 01:55:22 | [pearl_trainer] epoch #65 | Evaluating... 2025-04-04 01:55:22 | [pearl_trainer] epoch #65 | Sampling for adapation and meta-testing... 2025-04-04 01:59:00 | [pearl_trainer] epoch #65 | Finished meta-testing... 2025-04-04 01:59:00 | [pearl_trainer] epoch #65 | Saving snapshot... 2025-04-04 01:59:01 | [pearl_trainer] epoch #65 | Saved 2025-04-04 01:59:01 | [pearl_trainer] epoch #65 | Time 34204.86 s 2025-04-04 01:59:01 | [pearl_trainer] epoch #65 | EpochTime 418.61 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -291.108 MetaTest/Average/AverageReturn -291.108 MetaTest/Average/Iteration 65 MetaTest/Average/MaxReturn -226.842 MetaTest/Average/MinReturn -367.165 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 48.6103 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -291.108 MetaTest/__unnamed_task__/AverageReturn -291.108 MetaTest/__unnamed_task__/Iteration 65 MetaTest/__unnamed_task__/MaxReturn -226.842 MetaTest/__unnamed_task__/MinReturn -367.165 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 48.6103 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 172000 ------------------------------------------------- ----------- 2025-04-04 01:59:39 | [pearl_trainer] epoch #66 | Training... 2025-04-04 02:02:17 | [pearl_trainer] epoch #66 | Evaluating... 2025-04-04 02:02:17 | [pearl_trainer] epoch #66 | Sampling for adapation and meta-testing... 2025-04-04 02:05:56 | [pearl_trainer] epoch #66 | Finished meta-testing... 2025-04-04 02:05:56 | [pearl_trainer] epoch #66 | Saving snapshot... 2025-04-04 02:05:57 | [pearl_trainer] epoch #66 | Saved 2025-04-04 02:05:57 | [pearl_trainer] epoch #66 | Time 34621.04 s 2025-04-04 02:05:57 | [pearl_trainer] epoch #66 | EpochTime 416.18 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -330.012 MetaTest/Average/AverageReturn -330.012 MetaTest/Average/Iteration 66 MetaTest/Average/MaxReturn -220.538 MetaTest/Average/MinReturn -404.555 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 66.392 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -330.012 MetaTest/__unnamed_task__/AverageReturn -330.012 MetaTest/__unnamed_task__/Iteration 66 MetaTest/__unnamed_task__/MaxReturn -220.538 MetaTest/__unnamed_task__/MinReturn -404.555 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 66.392 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 174000 ------------------------------------------------- ---------- 2025-04-04 02:06:38 | [pearl_trainer] epoch #67 | Training... 2025-04-04 02:09:15 | [pearl_trainer] epoch #67 | Evaluating... 2025-04-04 02:09:15 | [pearl_trainer] epoch #67 | Sampling for adapation and meta-testing... 2025-04-04 02:13:10 | [pearl_trainer] epoch #67 | Finished meta-testing... 2025-04-04 02:13:10 | [pearl_trainer] epoch #67 | Saving snapshot... 2025-04-04 02:13:11 | [pearl_trainer] epoch #67 | Saved 2025-04-04 02:13:11 | [pearl_trainer] epoch #67 | Time 35054.62 s 2025-04-04 02:13:11 | [pearl_trainer] epoch #67 | EpochTime 433.58 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -338.731 MetaTest/Average/AverageReturn -338.731 MetaTest/Average/Iteration 67 MetaTest/Average/MaxReturn -270.442 MetaTest/Average/MinReturn -404.619 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 46.914 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -338.731 MetaTest/__unnamed_task__/AverageReturn -338.731 MetaTest/__unnamed_task__/Iteration 67 MetaTest/__unnamed_task__/MaxReturn -270.442 MetaTest/__unnamed_task__/MinReturn -404.619 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 46.914 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 176000 ------------------------------------------------- ---------- 2025-04-04 02:13:51 | [pearl_trainer] epoch #68 | Training... 2025-04-04 02:16:31 | [pearl_trainer] epoch #68 | Evaluating... 2025-04-04 02:16:31 | [pearl_trainer] epoch #68 | Sampling for adapation and meta-testing... 2025-04-04 02:20:37 | [pearl_trainer] epoch #68 | Finished meta-testing... 2025-04-04 02:20:37 | [pearl_trainer] epoch #68 | Saving snapshot... 2025-04-04 02:20:38 | [pearl_trainer] epoch #68 | Saved 2025-04-04 02:20:38 | [pearl_trainer] epoch #68 | Time 35501.81 s 2025-04-04 02:20:38 | [pearl_trainer] epoch #68 | EpochTime 447.18 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -308.515 MetaTest/Average/AverageReturn -308.515 MetaTest/Average/Iteration 68 MetaTest/Average/MaxReturn -276.017 MetaTest/Average/MinReturn -333.04 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 20.5689 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -308.515 MetaTest/__unnamed_task__/AverageReturn -308.515 MetaTest/__unnamed_task__/Iteration 68 MetaTest/__unnamed_task__/MaxReturn -276.017 MetaTest/__unnamed_task__/MinReturn -333.04 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 20.5689 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 178000 ------------------------------------------------- ----------- 2025-04-04 02:21:21 | [pearl_trainer] epoch #69 | Training... 2025-04-04 02:23:56 | [pearl_trainer] epoch #69 | Evaluating... 2025-04-04 02:23:56 | [pearl_trainer] epoch #69 | Sampling for adapation and meta-testing... 2025-04-04 02:28:03 | [pearl_trainer] epoch #69 | Finished meta-testing... 2025-04-04 02:28:03 | [pearl_trainer] epoch #69 | Saving snapshot... 2025-04-04 02:28:04 | [pearl_trainer] epoch #69 | Saved 2025-04-04 02:28:04 | [pearl_trainer] epoch #69 | Time 35947.91 s 2025-04-04 02:28:04 | [pearl_trainer] epoch #69 | EpochTime 446.11 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -315.454 MetaTest/Average/AverageReturn -315.454 MetaTest/Average/Iteration 69 MetaTest/Average/MaxReturn -205.539 MetaTest/Average/MinReturn -399.507 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 64.7598 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -315.454 MetaTest/__unnamed_task__/AverageReturn -315.454 MetaTest/__unnamed_task__/Iteration 69 MetaTest/__unnamed_task__/MaxReturn -205.539 MetaTest/__unnamed_task__/MinReturn -399.507 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 64.7598 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 180000 ------------------------------------------------- ----------- 2025-04-04 02:28:47 | [pearl_trainer] epoch #70 | Training... 2025-04-04 02:31:31 | [pearl_trainer] epoch #70 | Evaluating... 2025-04-04 02:31:31 | [pearl_trainer] epoch #70 | Sampling for adapation and meta-testing... 2025-04-04 02:35:44 | [pearl_trainer] epoch #70 | Finished meta-testing... 2025-04-04 02:35:44 | [pearl_trainer] epoch #70 | Saving snapshot... 2025-04-04 02:35:45 | [pearl_trainer] epoch #70 | Saved 2025-04-04 02:35:45 | [pearl_trainer] epoch #70 | Time 36408.78 s 2025-04-04 02:35:45 | [pearl_trainer] epoch #70 | EpochTime 460.86 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -342.3 MetaTest/Average/AverageReturn -342.3 MetaTest/Average/Iteration 70 MetaTest/Average/MaxReturn -303.897 MetaTest/Average/MinReturn -374.056 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.1811 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -342.3 MetaTest/__unnamed_task__/AverageReturn -342.3 MetaTest/__unnamed_task__/Iteration 70 MetaTest/__unnamed_task__/MaxReturn -303.897 MetaTest/__unnamed_task__/MinReturn -374.056 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.1811 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 182000 ------------------------------------------------- ----------- 2025-04-04 02:36:29 | [pearl_trainer] epoch #71 | Training... 2025-04-04 02:39:08 | [pearl_trainer] epoch #71 | Evaluating... 2025-04-04 02:39:08 | [pearl_trainer] epoch #71 | Sampling for adapation and meta-testing... 2025-04-04 02:43:13 | [pearl_trainer] epoch #71 | Finished meta-testing... 2025-04-04 02:43:13 | [pearl_trainer] epoch #71 | Saving snapshot... 2025-04-04 02:43:14 | [pearl_trainer] epoch #71 | Saved 2025-04-04 02:43:14 | [pearl_trainer] epoch #71 | Time 36858.03 s 2025-04-04 02:43:14 | [pearl_trainer] epoch #71 | EpochTime 449.25 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -321.964 MetaTest/Average/AverageReturn -321.964 MetaTest/Average/Iteration 71 MetaTest/Average/MaxReturn -265.529 MetaTest/Average/MinReturn -371.065 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 35.6341 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -321.964 MetaTest/__unnamed_task__/AverageReturn -321.964 MetaTest/__unnamed_task__/Iteration 71 MetaTest/__unnamed_task__/MaxReturn -265.529 MetaTest/__unnamed_task__/MinReturn -371.065 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 35.6341 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 184000 ------------------------------------------------- ----------- 2025-04-04 02:43:59 | [pearl_trainer] epoch #72 | Training... 2025-04-04 02:46:39 | [pearl_trainer] epoch #72 | Evaluating... 2025-04-04 02:46:39 | [pearl_trainer] epoch #72 | Sampling for adapation and meta-testing... 2025-04-04 02:50:36 | [pearl_trainer] epoch #72 | Finished meta-testing... 2025-04-04 02:50:36 | [pearl_trainer] epoch #72 | Saving snapshot... 2025-04-04 02:50:38 | [pearl_trainer] epoch #72 | Saved 2025-04-04 02:50:38 | [pearl_trainer] epoch #72 | Time 37301.26 s 2025-04-04 02:50:38 | [pearl_trainer] epoch #72 | EpochTime 443.23 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -302.788 MetaTest/Average/AverageReturn -302.788 MetaTest/Average/Iteration 72 MetaTest/Average/MaxReturn -201.101 MetaTest/Average/MinReturn -392.57 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 63.1262 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -302.788 MetaTest/__unnamed_task__/AverageReturn -302.788 MetaTest/__unnamed_task__/Iteration 72 MetaTest/__unnamed_task__/MaxReturn -201.101 MetaTest/__unnamed_task__/MinReturn -392.57 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 63.1262 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 186000 ------------------------------------------------- ----------- 2025-04-04 02:51:21 | [pearl_trainer] epoch #73 | Training... 2025-04-04 02:53:58 | [pearl_trainer] epoch #73 | Evaluating... 2025-04-04 02:53:58 | [pearl_trainer] epoch #73 | Sampling for adapation and meta-testing... 2025-04-04 02:57:56 | [pearl_trainer] epoch #73 | Finished meta-testing... 2025-04-04 02:57:56 | [pearl_trainer] epoch #73 | Saving snapshot... 2025-04-04 02:57:57 | [pearl_trainer] epoch #73 | Saved 2025-04-04 02:57:57 | [pearl_trainer] epoch #73 | Time 37740.55 s 2025-04-04 02:57:57 | [pearl_trainer] epoch #73 | EpochTime 439.28 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -354.63 MetaTest/Average/AverageReturn -354.63 MetaTest/Average/Iteration 73 MetaTest/Average/MaxReturn -293.469 MetaTest/Average/MinReturn -419.344 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 48.1616 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -354.63 MetaTest/__unnamed_task__/AverageReturn -354.63 MetaTest/__unnamed_task__/Iteration 73 MetaTest/__unnamed_task__/MaxReturn -293.469 MetaTest/__unnamed_task__/MinReturn -419.344 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 48.1616 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 188000 ------------------------------------------------- ----------- 2025-04-04 02:58:39 | [pearl_trainer] epoch #74 | Training... 2025-04-04 03:01:28 | [pearl_trainer] epoch #74 | Evaluating... 2025-04-04 03:01:28 | [pearl_trainer] epoch #74 | Sampling for adapation and meta-testing... 2025-04-04 03:05:16 | [pearl_trainer] epoch #74 | Finished meta-testing... 2025-04-04 03:05:16 | [pearl_trainer] epoch #74 | Saving snapshot... 2025-04-04 03:05:17 | [pearl_trainer] epoch #74 | Saved 2025-04-04 03:05:17 | [pearl_trainer] epoch #74 | Time 38180.61 s 2025-04-04 03:05:17 | [pearl_trainer] epoch #74 | EpochTime 440.06 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -330.711 MetaTest/Average/AverageReturn -330.711 MetaTest/Average/Iteration 74 MetaTest/Average/MaxReturn -265.271 MetaTest/Average/MinReturn -441.122 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 63.0188 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -330.711 MetaTest/__unnamed_task__/AverageReturn -330.711 MetaTest/__unnamed_task__/Iteration 74 MetaTest/__unnamed_task__/MaxReturn -265.271 MetaTest/__unnamed_task__/MinReturn -441.122 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 63.0188 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 190000 ------------------------------------------------- ----------- 2025-04-04 03:05:57 | [pearl_trainer] epoch #75 | Training... 2025-04-04 03:08:52 | [pearl_trainer] epoch #75 | Evaluating... 2025-04-04 03:08:52 | [pearl_trainer] epoch #75 | Sampling for adapation and meta-testing... 2025-04-04 03:12:45 | [pearl_trainer] epoch #75 | Finished meta-testing... 2025-04-04 03:12:45 | [pearl_trainer] epoch #75 | Saving snapshot... 2025-04-04 03:12:46 | [pearl_trainer] epoch #75 | Saved 2025-04-04 03:12:46 | [pearl_trainer] epoch #75 | Time 38629.99 s 2025-04-04 03:12:46 | [pearl_trainer] epoch #75 | EpochTime 449.38 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -313.067 MetaTest/Average/AverageReturn -313.067 MetaTest/Average/Iteration 75 MetaTest/Average/MaxReturn -253.647 MetaTest/Average/MinReturn -362.867 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 39.3281 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -313.067 MetaTest/__unnamed_task__/AverageReturn -313.067 MetaTest/__unnamed_task__/Iteration 75 MetaTest/__unnamed_task__/MaxReturn -253.647 MetaTest/__unnamed_task__/MinReturn -362.867 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 39.3281 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 192000 ------------------------------------------------- ----------- 2025-04-04 03:13:30 | [pearl_trainer] epoch #76 | Training... 2025-04-04 03:16:05 | [pearl_trainer] epoch #76 | Evaluating... 2025-04-04 03:16:05 | [pearl_trainer] epoch #76 | Sampling for adapation and meta-testing... 2025-04-04 03:19:56 | [pearl_trainer] epoch #76 | Finished meta-testing... 2025-04-04 03:19:56 | [pearl_trainer] epoch #76 | Saving snapshot... 2025-04-04 03:19:57 | [pearl_trainer] epoch #76 | Saved 2025-04-04 03:19:57 | [pearl_trainer] epoch #76 | Time 39061.13 s 2025-04-04 03:19:57 | [pearl_trainer] epoch #76 | EpochTime 431.14 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -314.2 MetaTest/Average/AverageReturn -314.2 MetaTest/Average/Iteration 76 MetaTest/Average/MaxReturn -238.373 MetaTest/Average/MinReturn -405.566 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 74.9506 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -314.2 MetaTest/__unnamed_task__/AverageReturn -314.2 MetaTest/__unnamed_task__/Iteration 76 MetaTest/__unnamed_task__/MaxReturn -238.373 MetaTest/__unnamed_task__/MinReturn -405.566 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 74.9506 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 194000 ------------------------------------------------- ----------- 2025-04-04 03:20:38 | [pearl_trainer] epoch #77 | Training... 2025-04-04 03:23:07 | [pearl_trainer] epoch #77 | Evaluating... 2025-04-04 03:23:07 | [pearl_trainer] epoch #77 | Sampling for adapation and meta-testing... 2025-04-04 03:26:54 | [pearl_trainer] epoch #77 | Finished meta-testing... 2025-04-04 03:26:54 | [pearl_trainer] epoch #77 | Saving snapshot... 2025-04-04 03:26:56 | [pearl_trainer] epoch #77 | Saved 2025-04-04 03:26:56 | [pearl_trainer] epoch #77 | Time 39479.20 s 2025-04-04 03:26:56 | [pearl_trainer] epoch #77 | EpochTime 418.07 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -358.284 MetaTest/Average/AverageReturn -358.284 MetaTest/Average/Iteration 77 MetaTest/Average/MaxReturn -311.091 MetaTest/Average/MinReturn -408.062 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.2033 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -358.284 MetaTest/__unnamed_task__/AverageReturn -358.284 MetaTest/__unnamed_task__/Iteration 77 MetaTest/__unnamed_task__/MaxReturn -311.091 MetaTest/__unnamed_task__/MinReturn -408.062 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.2033 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 196000 ------------------------------------------------- ----------- 2025-04-04 03:27:38 | [pearl_trainer] epoch #78 | Training... 2025-04-04 03:30:18 | [pearl_trainer] epoch #78 | Evaluating... 2025-04-04 03:30:18 | [pearl_trainer] epoch #78 | Sampling for adapation and meta-testing... 2025-04-04 03:34:04 | [pearl_trainer] epoch #78 | Finished meta-testing... 2025-04-04 03:34:04 | [pearl_trainer] epoch #78 | Saving snapshot... 2025-04-04 03:34:06 | [pearl_trainer] epoch #78 | Saved 2025-04-04 03:34:06 | [pearl_trainer] epoch #78 | Time 39909.42 s 2025-04-04 03:34:06 | [pearl_trainer] epoch #78 | EpochTime 430.21 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -304.862 MetaTest/Average/AverageReturn -304.862 MetaTest/Average/Iteration 78 MetaTest/Average/MaxReturn -274.442 MetaTest/Average/MinReturn -370.243 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 34.7618 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -304.862 MetaTest/__unnamed_task__/AverageReturn -304.862 MetaTest/__unnamed_task__/Iteration 78 MetaTest/__unnamed_task__/MaxReturn -274.442 MetaTest/__unnamed_task__/MinReturn -370.243 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 34.7618 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 198000 ------------------------------------------------- ----------- 2025-04-04 03:34:44 | [pearl_trainer] epoch #79 | Training... 2025-04-04 03:37:21 | [pearl_trainer] epoch #79 | Evaluating... 2025-04-04 03:37:21 | [pearl_trainer] epoch #79 | Sampling for adapation and meta-testing... 2025-04-04 03:40:57 | [pearl_trainer] epoch #79 | Finished meta-testing... 2025-04-04 03:40:57 | [pearl_trainer] epoch #79 | Saving snapshot... 2025-04-04 03:40:58 | [pearl_trainer] epoch #79 | Saved 2025-04-04 03:40:58 | [pearl_trainer] epoch #79 | Time 40321.31 s 2025-04-04 03:40:58 | [pearl_trainer] epoch #79 | EpochTime 411.89 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -357.12 MetaTest/Average/AverageReturn -357.12 MetaTest/Average/Iteration 79 MetaTest/Average/MaxReturn -325.241 MetaTest/Average/MinReturn -388.482 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 21.5147 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -357.12 MetaTest/__unnamed_task__/AverageReturn -357.12 MetaTest/__unnamed_task__/Iteration 79 MetaTest/__unnamed_task__/MaxReturn -325.241 MetaTest/__unnamed_task__/MinReturn -388.482 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 21.5147 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 200000 ------------------------------------------------- ----------- 2025-04-04 03:41:43 | [pearl_trainer] epoch #80 | Training... 2025-04-04 03:44:17 | [pearl_trainer] epoch #80 | Evaluating... 2025-04-04 03:44:17 | [pearl_trainer] epoch #80 | Sampling for adapation and meta-testing... 2025-04-04 03:48:00 | [pearl_trainer] epoch #80 | Finished meta-testing... 2025-04-04 03:48:00 | [pearl_trainer] epoch #80 | Saving snapshot... 2025-04-04 03:48:02 | [pearl_trainer] epoch #80 | Saved 2025-04-04 03:48:02 | [pearl_trainer] epoch #80 | Time 40745.32 s 2025-04-04 03:48:02 | [pearl_trainer] epoch #80 | EpochTime 424.01 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -301.768 MetaTest/Average/AverageReturn -301.768 MetaTest/Average/Iteration 80 MetaTest/Average/MaxReturn -189.906 MetaTest/Average/MinReturn -376.332 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 69.8289 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -301.768 MetaTest/__unnamed_task__/AverageReturn -301.768 MetaTest/__unnamed_task__/Iteration 80 MetaTest/__unnamed_task__/MaxReturn -189.906 MetaTest/__unnamed_task__/MinReturn -376.332 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 69.8289 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 202000 ------------------------------------------------- ----------- 2025-04-04 03:48:40 | [pearl_trainer] epoch #81 | Training... 2025-04-04 03:51:15 | [pearl_trainer] epoch #81 | Evaluating... 2025-04-04 03:51:15 | [pearl_trainer] epoch #81 | Sampling for adapation and meta-testing... 2025-04-04 03:54:54 | [pearl_trainer] epoch #81 | Finished meta-testing... 2025-04-04 03:54:54 | [pearl_trainer] epoch #81 | Saving snapshot... 2025-04-04 03:54:55 | [pearl_trainer] epoch #81 | Saved 2025-04-04 03:54:55 | [pearl_trainer] epoch #81 | Time 41158.38 s 2025-04-04 03:54:55 | [pearl_trainer] epoch #81 | EpochTime 413.06 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -334.86 MetaTest/Average/AverageReturn -334.86 MetaTest/Average/Iteration 81 MetaTest/Average/MaxReturn -209.121 MetaTest/Average/MinReturn -472.101 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 92.9982 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -334.86 MetaTest/__unnamed_task__/AverageReturn -334.86 MetaTest/__unnamed_task__/Iteration 81 MetaTest/__unnamed_task__/MaxReturn -209.121 MetaTest/__unnamed_task__/MinReturn -472.101 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 92.9982 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 204000 ------------------------------------------------- ----------- 2025-04-04 03:55:37 | [pearl_trainer] epoch #82 | Training... 2025-04-04 03:58:30 | [pearl_trainer] epoch #82 | Evaluating... 2025-04-04 03:58:30 | [pearl_trainer] epoch #82 | Sampling for adapation and meta-testing... 2025-04-04 04:02:04 | [pearl_trainer] epoch #82 | Finished meta-testing... 2025-04-04 04:02:04 | [pearl_trainer] epoch #82 | Saving snapshot... 2025-04-04 04:02:06 | [pearl_trainer] epoch #82 | Saved 2025-04-04 04:02:06 | [pearl_trainer] epoch #82 | Time 41589.42 s 2025-04-04 04:02:06 | [pearl_trainer] epoch #82 | EpochTime 431.04 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -324.005 MetaTest/Average/AverageReturn -324.005 MetaTest/Average/Iteration 82 MetaTest/Average/MaxReturn -216.024 MetaTest/Average/MinReturn -403.824 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 79.4421 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -324.005 MetaTest/__unnamed_task__/AverageReturn -324.005 MetaTest/__unnamed_task__/Iteration 82 MetaTest/__unnamed_task__/MaxReturn -216.024 MetaTest/__unnamed_task__/MinReturn -403.824 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 79.4421 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 206000 ------------------------------------------------- ----------- 2025-04-04 04:02:44 | [pearl_trainer] epoch #83 | Training... 2025-04-04 04:05:32 | [pearl_trainer] epoch #83 | Evaluating... 2025-04-04 04:05:32 | [pearl_trainer] epoch #83 | Sampling for adapation and meta-testing... 2025-04-04 04:09:13 | [pearl_trainer] epoch #83 | Finished meta-testing... 2025-04-04 04:09:13 | [pearl_trainer] epoch #83 | Saving snapshot... 2025-04-04 04:09:14 | [pearl_trainer] epoch #83 | Saved 2025-04-04 04:09:14 | [pearl_trainer] epoch #83 | Time 42017.84 s 2025-04-04 04:09:14 | [pearl_trainer] epoch #83 | EpochTime 428.41 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -368.999 MetaTest/Average/AverageReturn -368.999 MetaTest/Average/Iteration 83 MetaTest/Average/MaxReturn -329.624 MetaTest/Average/MinReturn -424.837 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 34.3057 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -368.999 MetaTest/__unnamed_task__/AverageReturn -368.999 MetaTest/__unnamed_task__/Iteration 83 MetaTest/__unnamed_task__/MaxReturn -329.624 MetaTest/__unnamed_task__/MinReturn -424.837 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 34.3057 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 208000 ------------------------------------------------- ----------- 2025-04-04 04:09:54 | [pearl_trainer] epoch #84 | Training... 2025-04-04 04:12:20 | [pearl_trainer] epoch #84 | Evaluating... 2025-04-04 04:12:20 | [pearl_trainer] epoch #84 | Sampling for adapation and meta-testing... 2025-04-04 04:16:04 | [pearl_trainer] epoch #84 | Finished meta-testing... 2025-04-04 04:16:04 | [pearl_trainer] epoch #84 | Saving snapshot... 2025-04-04 04:16:05 | [pearl_trainer] epoch #84 | Saved 2025-04-04 04:16:05 | [pearl_trainer] epoch #84 | Time 42429.09 s 2025-04-04 04:16:05 | [pearl_trainer] epoch #84 | EpochTime 411.25 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -350.501 MetaTest/Average/AverageReturn -350.501 MetaTest/Average/Iteration 84 MetaTest/Average/MaxReturn -325.214 MetaTest/Average/MinReturn -384.473 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 20.5247 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -350.501 MetaTest/__unnamed_task__/AverageReturn -350.501 MetaTest/__unnamed_task__/Iteration 84 MetaTest/__unnamed_task__/MaxReturn -325.214 MetaTest/__unnamed_task__/MinReturn -384.473 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 20.5247 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 210000 ------------------------------------------------- ----------- 2025-04-04 04:16:44 | [pearl_trainer] epoch #85 | Training... 2025-04-04 04:19:23 | [pearl_trainer] epoch #85 | Evaluating... 2025-04-04 04:19:23 | [pearl_trainer] epoch #85 | Sampling for adapation and meta-testing... 2025-04-04 04:23:00 | [pearl_trainer] epoch #85 | Finished meta-testing... 2025-04-04 04:23:00 | [pearl_trainer] epoch #85 | Saving snapshot... 2025-04-04 04:23:01 | [pearl_trainer] epoch #85 | Saved 2025-04-04 04:23:01 | [pearl_trainer] epoch #85 | Time 42844.76 s 2025-04-04 04:23:01 | [pearl_trainer] epoch #85 | EpochTime 415.67 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -337.029 MetaTest/Average/AverageReturn -337.029 MetaTest/Average/Iteration 85 MetaTest/Average/MaxReturn -250.625 MetaTest/Average/MinReturn -387.623 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 51.4465 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -337.029 MetaTest/__unnamed_task__/AverageReturn -337.029 MetaTest/__unnamed_task__/Iteration 85 MetaTest/__unnamed_task__/MaxReturn -250.625 MetaTest/__unnamed_task__/MinReturn -387.623 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 51.4465 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 212000 ------------------------------------------------- ----------- 2025-04-04 04:23:39 | [pearl_trainer] epoch #86 | Training... 2025-04-04 04:26:13 | [pearl_trainer] epoch #86 | Evaluating... 2025-04-04 04:26:13 | [pearl_trainer] epoch #86 | Sampling for adapation and meta-testing... 2025-04-04 04:29:54 | [pearl_trainer] epoch #86 | Finished meta-testing... 2025-04-04 04:29:54 | [pearl_trainer] epoch #86 | Saving snapshot... 2025-04-04 04:29:55 | [pearl_trainer] epoch #86 | Saved 2025-04-04 04:29:55 | [pearl_trainer] epoch #86 | Time 43259.11 s 2025-04-04 04:29:55 | [pearl_trainer] epoch #86 | EpochTime 414.35 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -324.473 MetaTest/Average/AverageReturn -324.473 MetaTest/Average/Iteration 86 MetaTest/Average/MaxReturn -204.762 MetaTest/Average/MinReturn -385.061 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 66.3867 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -324.473 MetaTest/__unnamed_task__/AverageReturn -324.473 MetaTest/__unnamed_task__/Iteration 86 MetaTest/__unnamed_task__/MaxReturn -204.762 MetaTest/__unnamed_task__/MinReturn -385.061 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 66.3867 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 214000 ------------------------------------------------- ----------- 2025-04-04 04:30:36 | [pearl_trainer] epoch #87 | Training... 2025-04-04 04:33:15 | [pearl_trainer] epoch #87 | Evaluating... 2025-04-04 04:33:15 | [pearl_trainer] epoch #87 | Sampling for adapation and meta-testing... 2025-04-04 04:37:03 | [pearl_trainer] epoch #87 | Finished meta-testing... 2025-04-04 04:37:03 | [pearl_trainer] epoch #87 | Saving snapshot... 2025-04-04 04:37:04 | [pearl_trainer] epoch #87 | Saved 2025-04-04 04:37:04 | [pearl_trainer] epoch #87 | Time 43687.41 s 2025-04-04 04:37:04 | [pearl_trainer] epoch #87 | EpochTime 428.30 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -310.855 MetaTest/Average/AverageReturn -310.855 MetaTest/Average/Iteration 87 MetaTest/Average/MaxReturn -242.369 MetaTest/Average/MinReturn -367.555 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 43.8036 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -310.855 MetaTest/__unnamed_task__/AverageReturn -310.855 MetaTest/__unnamed_task__/Iteration 87 MetaTest/__unnamed_task__/MaxReturn -242.369 MetaTest/__unnamed_task__/MinReturn -367.555 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 43.8036 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 216000 ------------------------------------------------- ----------- 2025-04-04 04:37:45 | [pearl_trainer] epoch #88 | Training... 2025-04-04 04:40:24 | [pearl_trainer] epoch #88 | Evaluating... 2025-04-04 04:40:24 | [pearl_trainer] epoch #88 | Sampling for adapation and meta-testing... 2025-04-04 04:44:17 | [pearl_trainer] epoch #88 | Finished meta-testing... 2025-04-04 04:44:17 | [pearl_trainer] epoch #88 | Saving snapshot... 2025-04-04 04:44:19 | [pearl_trainer] epoch #88 | Saved 2025-04-04 04:44:19 | [pearl_trainer] epoch #88 | Time 44122.20 s 2025-04-04 04:44:19 | [pearl_trainer] epoch #88 | EpochTime 434.78 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -288.813 MetaTest/Average/AverageReturn -288.813 MetaTest/Average/Iteration 88 MetaTest/Average/MaxReturn -249.78 MetaTest/Average/MinReturn -334.1 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 32.8155 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -288.813 MetaTest/__unnamed_task__/AverageReturn -288.813 MetaTest/__unnamed_task__/Iteration 88 MetaTest/__unnamed_task__/MaxReturn -249.78 MetaTest/__unnamed_task__/MinReturn -334.1 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 32.8155 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 218000 ------------------------------------------------- ----------- 2025-04-04 04:45:02 | [pearl_trainer] epoch #89 | Training... 2025-04-04 04:47:38 | [pearl_trainer] epoch #89 | Evaluating... 2025-04-04 04:47:38 | [pearl_trainer] epoch #89 | Sampling for adapation and meta-testing... 2025-04-04 04:51:49 | [pearl_trainer] epoch #89 | Finished meta-testing... 2025-04-04 04:51:49 | [pearl_trainer] epoch #89 | Saving snapshot... 2025-04-04 04:51:50 | [pearl_trainer] epoch #89 | Saved 2025-04-04 04:51:50 | [pearl_trainer] epoch #89 | Time 44573.93 s 2025-04-04 04:51:50 | [pearl_trainer] epoch #89 | EpochTime 451.73 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -297.152 MetaTest/Average/AverageReturn -297.152 MetaTest/Average/Iteration 89 MetaTest/Average/MaxReturn -245.055 MetaTest/Average/MinReturn -333.751 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 32.7229 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -297.152 MetaTest/__unnamed_task__/AverageReturn -297.152 MetaTest/__unnamed_task__/Iteration 89 MetaTest/__unnamed_task__/MaxReturn -245.055 MetaTest/__unnamed_task__/MinReturn -333.751 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 32.7229 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 220000 ------------------------------------------------- ----------- 2025-04-04 04:52:36 | [pearl_trainer] epoch #90 | Training... 2025-04-04 04:55:08 | [pearl_trainer] epoch #90 | Evaluating... 2025-04-04 04:55:08 | [pearl_trainer] epoch #90 | Sampling for adapation and meta-testing... 2025-04-04 04:58:59 | [pearl_trainer] epoch #90 | Finished meta-testing... 2025-04-04 04:58:59 | [pearl_trainer] epoch #90 | Saving snapshot... 2025-04-04 04:59:00 | [pearl_trainer] epoch #90 | Saved 2025-04-04 04:59:00 | [pearl_trainer] epoch #90 | Time 45003.79 s 2025-04-04 04:59:00 | [pearl_trainer] epoch #90 | EpochTime 429.87 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -306.883 MetaTest/Average/AverageReturn -306.883 MetaTest/Average/Iteration 90 MetaTest/Average/MaxReturn -291.234 MetaTest/Average/MinReturn -328.679 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 14.7691 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -306.883 MetaTest/__unnamed_task__/AverageReturn -306.883 MetaTest/__unnamed_task__/Iteration 90 MetaTest/__unnamed_task__/MaxReturn -291.234 MetaTest/__unnamed_task__/MinReturn -328.679 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 14.7691 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 222000 ------------------------------------------------- ----------- 2025-04-04 04:59:46 | [pearl_trainer] epoch #91 | Training... 2025-04-04 05:02:17 | [pearl_trainer] epoch #91 | Evaluating... 2025-04-04 05:02:17 | [pearl_trainer] epoch #91 | Sampling for adapation and meta-testing... 2025-04-04 05:06:19 | [pearl_trainer] epoch #91 | Finished meta-testing... 2025-04-04 05:06:19 | [pearl_trainer] epoch #91 | Saving snapshot... 2025-04-04 05:06:20 | [pearl_trainer] epoch #91 | Saved 2025-04-04 05:06:20 | [pearl_trainer] epoch #91 | Time 45444.10 s 2025-04-04 05:06:20 | [pearl_trainer] epoch #91 | EpochTime 440.30 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -299.31 MetaTest/Average/AverageReturn -299.31 MetaTest/Average/Iteration 91 MetaTest/Average/MaxReturn -218.006 MetaTest/Average/MinReturn -371.676 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 52.9216 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -299.31 MetaTest/__unnamed_task__/AverageReturn -299.31 MetaTest/__unnamed_task__/Iteration 91 MetaTest/__unnamed_task__/MaxReturn -218.006 MetaTest/__unnamed_task__/MinReturn -371.676 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 52.9216 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 224000 ------------------------------------------------- ----------- 2025-04-04 05:07:03 | [pearl_trainer] epoch #92 | Training... 2025-04-04 05:09:29 | [pearl_trainer] epoch #92 | Evaluating... 2025-04-04 05:09:29 | [pearl_trainer] epoch #92 | Sampling for adapation and meta-testing... 2025-04-04 05:13:24 | [pearl_trainer] epoch #92 | Finished meta-testing... 2025-04-04 05:13:24 | [pearl_trainer] epoch #92 | Saving snapshot... 2025-04-04 05:13:26 | [pearl_trainer] epoch #92 | Saved 2025-04-04 05:13:26 | [pearl_trainer] epoch #92 | Time 45869.39 s 2025-04-04 05:13:26 | [pearl_trainer] epoch #92 | EpochTime 425.28 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -270.351 MetaTest/Average/AverageReturn -270.351 MetaTest/Average/Iteration 92 MetaTest/Average/MaxReturn -231.41 MetaTest/Average/MinReturn -352.13 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 42.178 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -270.351 MetaTest/__unnamed_task__/AverageReturn -270.351 MetaTest/__unnamed_task__/Iteration 92 MetaTest/__unnamed_task__/MaxReturn -231.41 MetaTest/__unnamed_task__/MinReturn -352.13 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 42.178 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 226000 ------------------------------------------------- ---------- 2025-04-04 05:14:11 | [pearl_trainer] epoch #93 | Training... 2025-04-04 05:16:48 | [pearl_trainer] epoch #93 | Evaluating... 2025-04-04 05:16:48 | [pearl_trainer] epoch #93 | Sampling for adapation and meta-testing... 2025-04-04 05:20:47 | [pearl_trainer] epoch #93 | Finished meta-testing... 2025-04-04 05:20:47 | [pearl_trainer] epoch #93 | Saving snapshot... 2025-04-04 05:20:48 | [pearl_trainer] epoch #93 | Saved 2025-04-04 05:20:48 | [pearl_trainer] epoch #93 | Time 46311.42 s 2025-04-04 05:20:48 | [pearl_trainer] epoch #93 | EpochTime 442.03 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -300.207 MetaTest/Average/AverageReturn -300.207 MetaTest/Average/Iteration 93 MetaTest/Average/MaxReturn -238.114 MetaTest/Average/MinReturn -349.68 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 44.5526 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -300.207 MetaTest/__unnamed_task__/AverageReturn -300.207 MetaTest/__unnamed_task__/Iteration 93 MetaTest/__unnamed_task__/MaxReturn -238.114 MetaTest/__unnamed_task__/MinReturn -349.68 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 44.5526 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 228000 ------------------------------------------------- ----------- 2025-04-04 05:21:29 | [pearl_trainer] epoch #94 | Training... 2025-04-04 05:24:19 | [pearl_trainer] epoch #94 | Evaluating... 2025-04-04 05:24:19 | [pearl_trainer] epoch #94 | Sampling for adapation and meta-testing... 2025-04-04 05:28:09 | [pearl_trainer] epoch #94 | Finished meta-testing... 2025-04-04 05:28:09 | [pearl_trainer] epoch #94 | Saving snapshot... 2025-04-04 05:28:10 | [pearl_trainer] epoch #94 | Saved 2025-04-04 05:28:10 | [pearl_trainer] epoch #94 | Time 46754.16 s 2025-04-04 05:28:10 | [pearl_trainer] epoch #94 | EpochTime 442.74 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -325.362 MetaTest/Average/AverageReturn -325.362 MetaTest/Average/Iteration 94 MetaTest/Average/MaxReturn -268.117 MetaTest/Average/MinReturn -348.921 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 30.3554 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -325.362 MetaTest/__unnamed_task__/AverageReturn -325.362 MetaTest/__unnamed_task__/Iteration 94 MetaTest/__unnamed_task__/MaxReturn -268.117 MetaTest/__unnamed_task__/MinReturn -348.921 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 30.3554 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 230000 ------------------------------------------------- ----------- 2025-04-04 05:28:50 | [pearl_trainer] epoch #95 | Training... 2025-04-04 05:31:34 | [pearl_trainer] epoch #95 | Evaluating... 2025-04-04 05:31:34 | [pearl_trainer] epoch #95 | Sampling for adapation and meta-testing... 2025-04-04 05:35:29 | [pearl_trainer] epoch #95 | Finished meta-testing... 2025-04-04 05:35:29 | [pearl_trainer] epoch #95 | Saving snapshot... 2025-04-04 05:35:30 | [pearl_trainer] epoch #95 | Saved 2025-04-04 05:35:30 | [pearl_trainer] epoch #95 | Time 47193.90 s 2025-04-04 05:35:30 | [pearl_trainer] epoch #95 | EpochTime 439.74 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -336.579 MetaTest/Average/AverageReturn -336.579 MetaTest/Average/Iteration 95 MetaTest/Average/MaxReturn -316.394 MetaTest/Average/MinReturn -354.798 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 16.0364 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -336.579 MetaTest/__unnamed_task__/AverageReturn -336.579 MetaTest/__unnamed_task__/Iteration 95 MetaTest/__unnamed_task__/MaxReturn -316.394 MetaTest/__unnamed_task__/MinReturn -354.798 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 16.0364 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 232000 ------------------------------------------------- ----------- 2025-04-04 05:36:12 | [pearl_trainer] epoch #96 | Training... 2025-04-04 05:38:42 | [pearl_trainer] epoch #96 | Evaluating... 2025-04-04 05:38:42 | [pearl_trainer] epoch #96 | Sampling for adapation and meta-testing... 2025-04-04 05:42:26 | [pearl_trainer] epoch #96 | Finished meta-testing... 2025-04-04 05:42:26 | [pearl_trainer] epoch #96 | Saving snapshot... 2025-04-04 05:42:28 | [pearl_trainer] epoch #96 | Saved 2025-04-04 05:42:28 | [pearl_trainer] epoch #96 | Time 47611.20 s 2025-04-04 05:42:28 | [pearl_trainer] epoch #96 | EpochTime 417.30 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -277.568 MetaTest/Average/AverageReturn -277.568 MetaTest/Average/Iteration 96 MetaTest/Average/MaxReturn -225.626 MetaTest/Average/MinReturn -310.611 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 30.5317 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -277.568 MetaTest/__unnamed_task__/AverageReturn -277.568 MetaTest/__unnamed_task__/Iteration 96 MetaTest/__unnamed_task__/MaxReturn -225.626 MetaTest/__unnamed_task__/MinReturn -310.611 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 30.5317 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 234000 ------------------------------------------------- ----------- 2025-04-04 05:43:10 | [pearl_trainer] epoch #97 | Training... 2025-04-04 05:45:51 | [pearl_trainer] epoch #97 | Evaluating... 2025-04-04 05:45:51 | [pearl_trainer] epoch #97 | Sampling for adapation and meta-testing... 2025-04-04 05:49:52 | [pearl_trainer] epoch #97 | Finished meta-testing... 2025-04-04 05:49:52 | [pearl_trainer] epoch #97 | Saving snapshot... 2025-04-04 05:49:53 | [pearl_trainer] epoch #97 | Saved 2025-04-04 05:49:53 | [pearl_trainer] epoch #97 | Time 48056.69 s 2025-04-04 05:49:53 | [pearl_trainer] epoch #97 | EpochTime 445.49 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -331.805 MetaTest/Average/AverageReturn -331.805 MetaTest/Average/Iteration 97 MetaTest/Average/MaxReturn -290.963 MetaTest/Average/MinReturn -376.321 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 28.5923 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -331.805 MetaTest/__unnamed_task__/AverageReturn -331.805 MetaTest/__unnamed_task__/Iteration 97 MetaTest/__unnamed_task__/MaxReturn -290.963 MetaTest/__unnamed_task__/MinReturn -376.321 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 28.5923 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 236000 ------------------------------------------------- ----------- 2025-04-04 05:50:35 | [pearl_trainer] epoch #98 | Training... 2025-04-04 05:53:15 | [pearl_trainer] epoch #98 | Evaluating... 2025-04-04 05:53:15 | [pearl_trainer] epoch #98 | Sampling for adapation and meta-testing... 2025-04-04 05:57:30 | [pearl_trainer] epoch #98 | Finished meta-testing... 2025-04-04 05:57:30 | [pearl_trainer] epoch #98 | Saving snapshot... 2025-04-04 05:57:32 | [pearl_trainer] epoch #98 | Saved 2025-04-04 05:57:32 | [pearl_trainer] epoch #98 | Time 48515.35 s 2025-04-04 05:57:32 | [pearl_trainer] epoch #98 | EpochTime 458.66 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -285.532 MetaTest/Average/AverageReturn -285.532 MetaTest/Average/Iteration 98 MetaTest/Average/MaxReturn -155.603 MetaTest/Average/MinReturn -433.266 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 88.7152 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -285.532 MetaTest/__unnamed_task__/AverageReturn -285.532 MetaTest/__unnamed_task__/Iteration 98 MetaTest/__unnamed_task__/MaxReturn -155.603 MetaTest/__unnamed_task__/MinReturn -433.266 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 88.7152 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 238000 ------------------------------------------------- ----------- 2025-04-04 05:58:16 | [pearl_trainer] epoch #99 | Training... 2025-04-04 06:00:54 | [pearl_trainer] epoch #99 | Evaluating... 2025-04-04 06:00:54 | [pearl_trainer] epoch #99 | Sampling for adapation and meta-testing... 2025-04-04 06:05:04 | [pearl_trainer] epoch #99 | Finished meta-testing... 2025-04-04 06:05:04 | [pearl_trainer] epoch #99 | Saving snapshot... 2025-04-04 06:05:05 | [pearl_trainer] epoch #99 | Saved 2025-04-04 06:05:05 | [pearl_trainer] epoch #99 | Time 48969.06 s 2025-04-04 06:05:05 | [pearl_trainer] epoch #99 | EpochTime 453.71 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -294.718 MetaTest/Average/AverageReturn -294.718 MetaTest/Average/Iteration 99 MetaTest/Average/MaxReturn -221.307 MetaTest/Average/MinReturn -378.771 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 55.8616 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -294.718 MetaTest/__unnamed_task__/AverageReturn -294.718 MetaTest/__unnamed_task__/Iteration 99 MetaTest/__unnamed_task__/MaxReturn -221.307 MetaTest/__unnamed_task__/MinReturn -378.771 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 55.8616 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 240000 ------------------------------------------------- ----------- 2025-04-04 06:05:51 | [pearl_trainer] epoch #100 | Training... 2025-04-04 06:08:31 | [pearl_trainer] epoch #100 | Evaluating... 2025-04-04 06:08:31 | [pearl_trainer] epoch #100 | Sampling for adapation and meta-testing... 2025-04-04 06:12:28 | [pearl_trainer] epoch #100 | Finished meta-testing... 2025-04-04 06:12:28 | [pearl_trainer] epoch #100 | Saving snapshot... 2025-04-04 06:12:29 | [pearl_trainer] epoch #100 | Saved 2025-04-04 06:12:29 | [pearl_trainer] epoch #100 | Time 49413.03 s 2025-04-04 06:12:29 | [pearl_trainer] epoch #100 | EpochTime 443.97 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -312.365 MetaTest/Average/AverageReturn -312.365 MetaTest/Average/Iteration 100 MetaTest/Average/MaxReturn -278.4 MetaTest/Average/MinReturn -339.081 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 22.246 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -312.365 MetaTest/__unnamed_task__/AverageReturn -312.365 MetaTest/__unnamed_task__/Iteration 100 MetaTest/__unnamed_task__/MaxReturn -278.4 MetaTest/__unnamed_task__/MinReturn -339.081 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 22.246 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 242000 ------------------------------------------------- ---------- 2025-04-04 06:13:11 | [pearl_trainer] epoch #101 | Training... 2025-04-04 06:15:51 | [pearl_trainer] epoch #101 | Evaluating... 2025-04-04 06:15:51 | [pearl_trainer] epoch #101 | Sampling for adapation and meta-testing... 2025-04-04 06:19:39 | [pearl_trainer] epoch #101 | Finished meta-testing... 2025-04-04 06:19:39 | [pearl_trainer] epoch #101 | Saving snapshot... 2025-04-04 06:19:41 | [pearl_trainer] epoch #101 | Saved 2025-04-04 06:19:41 | [pearl_trainer] epoch #101 | Time 49844.31 s 2025-04-04 06:19:41 | [pearl_trainer] epoch #101 | EpochTime 431.28 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -317.53 MetaTest/Average/AverageReturn -317.53 MetaTest/Average/Iteration 101 MetaTest/Average/MaxReturn -264.555 MetaTest/Average/MinReturn -374.763 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.0128 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -317.53 MetaTest/__unnamed_task__/AverageReturn -317.53 MetaTest/__unnamed_task__/Iteration 101 MetaTest/__unnamed_task__/MaxReturn -264.555 MetaTest/__unnamed_task__/MinReturn -374.763 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.0128 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 244000 ------------------------------------------------- ----------- 2025-04-04 06:20:26 | [pearl_trainer] epoch #102 | Training... 2025-04-04 06:23:04 | [pearl_trainer] epoch #102 | Evaluating... 2025-04-04 06:23:04 | [pearl_trainer] epoch #102 | Sampling for adapation and meta-testing... 2025-04-04 06:27:01 | [pearl_trainer] epoch #102 | Finished meta-testing... 2025-04-04 06:27:01 | [pearl_trainer] epoch #102 | Saving snapshot... 2025-04-04 06:27:02 | [pearl_trainer] epoch #102 | Saved 2025-04-04 06:27:02 | [pearl_trainer] epoch #102 | Time 50285.71 s 2025-04-04 06:27:02 | [pearl_trainer] epoch #102 | EpochTime 441.39 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -250.219 MetaTest/Average/AverageReturn -250.219 MetaTest/Average/Iteration 102 MetaTest/Average/MaxReturn -226.035 MetaTest/Average/MinReturn -278.482 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 20.1664 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -250.219 MetaTest/__unnamed_task__/AverageReturn -250.219 MetaTest/__unnamed_task__/Iteration 102 MetaTest/__unnamed_task__/MaxReturn -226.035 MetaTest/__unnamed_task__/MinReturn -278.482 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 20.1664 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 246000 ------------------------------------------------- ----------- 2025-04-04 06:27:46 | [pearl_trainer] epoch #103 | Training... 2025-04-04 06:30:30 | [pearl_trainer] epoch #103 | Evaluating... 2025-04-04 06:30:30 | [pearl_trainer] epoch #103 | Sampling for adapation and meta-testing... 2025-04-04 06:34:24 | [pearl_trainer] epoch #103 | Finished meta-testing... 2025-04-04 06:34:24 | [pearl_trainer] epoch #103 | Saving snapshot... 2025-04-04 06:34:25 | [pearl_trainer] epoch #103 | Saved 2025-04-04 06:34:25 | [pearl_trainer] epoch #103 | Time 50728.45 s 2025-04-04 06:34:25 | [pearl_trainer] epoch #103 | EpochTime 442.75 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -314.207 MetaTest/Average/AverageReturn -314.207 MetaTest/Average/Iteration 103 MetaTest/Average/MaxReturn -291.071 MetaTest/Average/MinReturn -354.954 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 22.9532 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -314.207 MetaTest/__unnamed_task__/AverageReturn -314.207 MetaTest/__unnamed_task__/Iteration 103 MetaTest/__unnamed_task__/MaxReturn -291.071 MetaTest/__unnamed_task__/MinReturn -354.954 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 22.9532 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 248000 ------------------------------------------------- ----------- 2025-04-04 06:35:12 | [pearl_trainer] epoch #104 | Training... 2025-04-04 06:37:57 | [pearl_trainer] epoch #104 | Evaluating... 2025-04-04 06:37:57 | [pearl_trainer] epoch #104 | Sampling for adapation and meta-testing... 2025-04-04 06:41:49 | [pearl_trainer] epoch #104 | Finished meta-testing... 2025-04-04 06:41:49 | [pearl_trainer] epoch #104 | Saving snapshot... 2025-04-04 06:41:50 | [pearl_trainer] epoch #104 | Saved 2025-04-04 06:41:50 | [pearl_trainer] epoch #104 | Time 51174.11 s 2025-04-04 06:41:50 | [pearl_trainer] epoch #104 | EpochTime 445.65 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -291.907 MetaTest/Average/AverageReturn -291.907 MetaTest/Average/Iteration 104 MetaTest/Average/MaxReturn -240.572 MetaTest/Average/MinReturn -341.456 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 32.3652 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -291.907 MetaTest/__unnamed_task__/AverageReturn -291.907 MetaTest/__unnamed_task__/Iteration 104 MetaTest/__unnamed_task__/MaxReturn -240.572 MetaTest/__unnamed_task__/MinReturn -341.456 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 32.3652 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 250000 ------------------------------------------------- ----------- 2025-04-04 06:42:33 | [pearl_trainer] epoch #105 | Training... 2025-04-04 06:45:24 | [pearl_trainer] epoch #105 | Evaluating... 2025-04-04 06:45:24 | [pearl_trainer] epoch #105 | Sampling for adapation and meta-testing... 2025-04-04 06:49:21 | [pearl_trainer] epoch #105 | Finished meta-testing... 2025-04-04 06:49:21 | [pearl_trainer] epoch #105 | Saving snapshot... 2025-04-04 06:49:23 | [pearl_trainer] epoch #105 | Saved 2025-04-04 06:49:23 | [pearl_trainer] epoch #105 | Time 51626.29 s 2025-04-04 06:49:23 | [pearl_trainer] epoch #105 | EpochTime 452.18 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -354.428 MetaTest/Average/AverageReturn -354.428 MetaTest/Average/Iteration 105 MetaTest/Average/MaxReturn -295.796 MetaTest/Average/MinReturn -409.474 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 39.1486 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -354.428 MetaTest/__unnamed_task__/AverageReturn -354.428 MetaTest/__unnamed_task__/Iteration 105 MetaTest/__unnamed_task__/MaxReturn -295.796 MetaTest/__unnamed_task__/MinReturn -409.474 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 39.1486 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 252000 ------------------------------------------------- ----------- 2025-04-04 06:50:04 | [pearl_trainer] epoch #106 | Training... 2025-04-04 06:53:01 | [pearl_trainer] epoch #106 | Evaluating... 2025-04-04 06:53:01 | [pearl_trainer] epoch #106 | Sampling for adapation and meta-testing... 2025-04-04 06:56:56 | [pearl_trainer] epoch #106 | Finished meta-testing... 2025-04-04 06:56:56 | [pearl_trainer] epoch #106 | Saving snapshot... 2025-04-04 06:56:57 | [pearl_trainer] epoch #106 | Saved 2025-04-04 06:56:57 | [pearl_trainer] epoch #106 | Time 52080.33 s 2025-04-04 06:56:57 | [pearl_trainer] epoch #106 | EpochTime 454.03 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -296.615 MetaTest/Average/AverageReturn -296.615 MetaTest/Average/Iteration 106 MetaTest/Average/MaxReturn -261.423 MetaTest/Average/MinReturn -322.323 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 20.6003 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -296.615 MetaTest/__unnamed_task__/AverageReturn -296.615 MetaTest/__unnamed_task__/Iteration 106 MetaTest/__unnamed_task__/MaxReturn -261.423 MetaTest/__unnamed_task__/MinReturn -322.323 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 20.6003 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 254000 ------------------------------------------------- ----------- 2025-04-04 06:57:37 | [pearl_trainer] epoch #107 | Training... 2025-04-04 07:00:28 | [pearl_trainer] epoch #107 | Evaluating... 2025-04-04 07:00:28 | [pearl_trainer] epoch #107 | Sampling for adapation and meta-testing... 2025-04-04 07:04:29 | [pearl_trainer] epoch #107 | Finished meta-testing... 2025-04-04 07:04:29 | [pearl_trainer] epoch #107 | Saving snapshot... 2025-04-04 07:04:30 | [pearl_trainer] epoch #107 | Saved 2025-04-04 07:04:30 | [pearl_trainer] epoch #107 | Time 52533.64 s 2025-04-04 07:04:30 | [pearl_trainer] epoch #107 | EpochTime 453.31 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -246.225 MetaTest/Average/AverageReturn -246.225 MetaTest/Average/Iteration 107 MetaTest/Average/MaxReturn -194.657 MetaTest/Average/MinReturn -288.756 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.5093 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -246.225 MetaTest/__unnamed_task__/AverageReturn -246.225 MetaTest/__unnamed_task__/Iteration 107 MetaTest/__unnamed_task__/MaxReturn -194.657 MetaTest/__unnamed_task__/MinReturn -288.756 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.5093 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 256000 ------------------------------------------------- ----------- 2025-04-04 07:05:14 | [pearl_trainer] epoch #108 | Training... 2025-04-04 07:08:13 | [pearl_trainer] epoch #108 | Evaluating... 2025-04-04 07:08:13 | [pearl_trainer] epoch #108 | Sampling for adapation and meta-testing... 2025-04-04 07:12:15 | [pearl_trainer] epoch #108 | Finished meta-testing... 2025-04-04 07:12:15 | [pearl_trainer] epoch #108 | Saving snapshot... 2025-04-04 07:12:16 | [pearl_trainer] epoch #108 | Saved 2025-04-04 07:12:16 | [pearl_trainer] epoch #108 | Time 53000.18 s 2025-04-04 07:12:16 | [pearl_trainer] epoch #108 | EpochTime 466.53 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -318.379 MetaTest/Average/AverageReturn -318.379 MetaTest/Average/Iteration 108 MetaTest/Average/MaxReturn -217.604 MetaTest/Average/MinReturn -367.313 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 53.1489 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -318.379 MetaTest/__unnamed_task__/AverageReturn -318.379 MetaTest/__unnamed_task__/Iteration 108 MetaTest/__unnamed_task__/MaxReturn -217.604 MetaTest/__unnamed_task__/MinReturn -367.313 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 53.1489 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 258000 ------------------------------------------------- ----------- 2025-04-04 07:13:08 | [pearl_trainer] epoch #109 | Training... 2025-04-04 07:15:52 | [pearl_trainer] epoch #109 | Evaluating... 2025-04-04 07:15:52 | [pearl_trainer] epoch #109 | Sampling for adapation and meta-testing... 2025-04-04 07:20:03 | [pearl_trainer] epoch #109 | Finished meta-testing... 2025-04-04 07:20:03 | [pearl_trainer] epoch #109 | Saving snapshot... 2025-04-04 07:20:05 | [pearl_trainer] epoch #109 | Saved 2025-04-04 07:20:05 | [pearl_trainer] epoch #109 | Time 53468.31 s 2025-04-04 07:20:05 | [pearl_trainer] epoch #109 | EpochTime 468.13 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -291.483 MetaTest/Average/AverageReturn -291.483 MetaTest/Average/Iteration 109 MetaTest/Average/MaxReturn -169.967 MetaTest/Average/MinReturn -369.726 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 71.5883 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -291.483 MetaTest/__unnamed_task__/AverageReturn -291.483 MetaTest/__unnamed_task__/Iteration 109 MetaTest/__unnamed_task__/MaxReturn -169.967 MetaTest/__unnamed_task__/MinReturn -369.726 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 71.5883 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 260000 ------------------------------------------------- ----------- 2025-04-04 07:20:49 | [pearl_trainer] epoch #110 | Training... 2025-04-04 07:23:29 | [pearl_trainer] epoch #110 | Evaluating... 2025-04-04 07:23:29 | [pearl_trainer] epoch #110 | Sampling for adapation and meta-testing... 2025-04-04 07:27:53 | [pearl_trainer] epoch #110 | Finished meta-testing... 2025-04-04 07:27:53 | [pearl_trainer] epoch #110 | Saving snapshot... 2025-04-04 07:27:54 | [pearl_trainer] epoch #110 | Saved 2025-04-04 07:27:54 | [pearl_trainer] epoch #110 | Time 53937.73 s 2025-04-04 07:27:54 | [pearl_trainer] epoch #110 | EpochTime 469.42 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -287.479 MetaTest/Average/AverageReturn -287.479 MetaTest/Average/Iteration 110 MetaTest/Average/MaxReturn -186.762 MetaTest/Average/MinReturn -353.394 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 55.1499 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -287.479 MetaTest/__unnamed_task__/AverageReturn -287.479 MetaTest/__unnamed_task__/Iteration 110 MetaTest/__unnamed_task__/MaxReturn -186.762 MetaTest/__unnamed_task__/MinReturn -353.394 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 55.1499 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 262000 ------------------------------------------------- ----------- 2025-04-04 07:28:40 | [pearl_trainer] epoch #111 | Training... 2025-04-04 07:31:18 | [pearl_trainer] epoch #111 | Evaluating... 2025-04-04 07:31:18 | [pearl_trainer] epoch #111 | Sampling for adapation and meta-testing... 2025-04-04 07:35:53 | [pearl_trainer] epoch #111 | Finished meta-testing... 2025-04-04 07:35:53 | [pearl_trainer] epoch #111 | Saving snapshot... 2025-04-04 07:35:54 | [pearl_trainer] epoch #111 | Saved 2025-04-04 07:35:54 | [pearl_trainer] epoch #111 | Time 54417.77 s 2025-04-04 07:35:54 | [pearl_trainer] epoch #111 | EpochTime 480.04 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -315.902 MetaTest/Average/AverageReturn -315.902 MetaTest/Average/Iteration 111 MetaTest/Average/MaxReturn -259 MetaTest/Average/MinReturn -360.195 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 41.1018 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -315.902 MetaTest/__unnamed_task__/AverageReturn -315.902 MetaTest/__unnamed_task__/Iteration 111 MetaTest/__unnamed_task__/MaxReturn -259 MetaTest/__unnamed_task__/MinReturn -360.195 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 41.1018 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 264000 ------------------------------------------------- ----------- 2025-04-04 07:36:44 | [pearl_trainer] epoch #112 | Training... 2025-04-04 07:39:20 | [pearl_trainer] epoch #112 | Evaluating... 2025-04-04 07:39:20 | [pearl_trainer] epoch #112 | Sampling for adapation and meta-testing... 2025-04-04 07:43:41 | [pearl_trainer] epoch #112 | Finished meta-testing... 2025-04-04 07:43:41 | [pearl_trainer] epoch #112 | Saving snapshot... 2025-04-04 07:43:42 | [pearl_trainer] epoch #112 | Saved 2025-04-04 07:43:42 | [pearl_trainer] epoch #112 | Time 54885.88 s 2025-04-04 07:43:42 | [pearl_trainer] epoch #112 | EpochTime 468.11 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -308.225 MetaTest/Average/AverageReturn -308.225 MetaTest/Average/Iteration 112 MetaTest/Average/MaxReturn -259.778 MetaTest/Average/MinReturn -375.736 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 42.5584 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -308.225 MetaTest/__unnamed_task__/AverageReturn -308.225 MetaTest/__unnamed_task__/Iteration 112 MetaTest/__unnamed_task__/MaxReturn -259.778 MetaTest/__unnamed_task__/MinReturn -375.736 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 42.5584 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 266000 ------------------------------------------------- ----------- 2025-04-04 07:44:31 | [pearl_trainer] epoch #113 | Training... 2025-04-04 07:47:01 | [pearl_trainer] epoch #113 | Evaluating... 2025-04-04 07:47:01 | [pearl_trainer] epoch #113 | Sampling for adapation and meta-testing... 2025-04-04 07:51:26 | [pearl_trainer] epoch #113 | Finished meta-testing... 2025-04-04 07:51:26 | [pearl_trainer] epoch #113 | Saving snapshot... 2025-04-04 07:51:28 | [pearl_trainer] epoch #113 | Saved 2025-04-04 07:51:28 | [pearl_trainer] epoch #113 | Time 55351.35 s 2025-04-04 07:51:28 | [pearl_trainer] epoch #113 | EpochTime 465.47 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -337.229 MetaTest/Average/AverageReturn -337.229 MetaTest/Average/Iteration 113 MetaTest/Average/MaxReturn -286.467 MetaTest/Average/MinReturn -376.211 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 30.7407 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -337.229 MetaTest/__unnamed_task__/AverageReturn -337.229 MetaTest/__unnamed_task__/Iteration 113 MetaTest/__unnamed_task__/MaxReturn -286.467 MetaTest/__unnamed_task__/MinReturn -376.211 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 30.7407 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 268000 ------------------------------------------------- ----------- 2025-04-04 07:52:14 | [pearl_trainer] epoch #114 | Training... 2025-04-04 07:54:48 | [pearl_trainer] epoch #114 | Evaluating... 2025-04-04 07:54:48 | [pearl_trainer] epoch #114 | Sampling for adapation and meta-testing... 2025-04-04 07:59:13 | [pearl_trainer] epoch #114 | Finished meta-testing... 2025-04-04 07:59:13 | [pearl_trainer] epoch #114 | Saving snapshot... 2025-04-04 07:59:14 | [pearl_trainer] epoch #114 | Saved 2025-04-04 07:59:14 | [pearl_trainer] epoch #114 | Time 55817.78 s 2025-04-04 07:59:14 | [pearl_trainer] epoch #114 | EpochTime 466.43 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -299.683 MetaTest/Average/AverageReturn -299.683 MetaTest/Average/Iteration 114 MetaTest/Average/MaxReturn -202.14 MetaTest/Average/MinReturn -401.133 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 64.0746 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -299.683 MetaTest/__unnamed_task__/AverageReturn -299.683 MetaTest/__unnamed_task__/Iteration 114 MetaTest/__unnamed_task__/MaxReturn -202.14 MetaTest/__unnamed_task__/MinReturn -401.133 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 64.0746 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 270000 ------------------------------------------------- ----------- 2025-04-04 08:00:05 | [pearl_trainer] epoch #115 | Training... 2025-04-04 08:02:46 | [pearl_trainer] epoch #115 | Evaluating... 2025-04-04 08:02:46 | [pearl_trainer] epoch #115 | Sampling for adapation and meta-testing... 2025-04-04 08:06:53 | [pearl_trainer] epoch #115 | Finished meta-testing... 2025-04-04 08:06:53 | [pearl_trainer] epoch #115 | Saving snapshot... 2025-04-04 08:06:55 | [pearl_trainer] epoch #115 | Saved 2025-04-04 08:06:55 | [pearl_trainer] epoch #115 | Time 56278.27 s 2025-04-04 08:06:55 | [pearl_trainer] epoch #115 | EpochTime 460.48 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -287.273 MetaTest/Average/AverageReturn -287.273 MetaTest/Average/Iteration 115 MetaTest/Average/MaxReturn -263.799 MetaTest/Average/MinReturn -321.473 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 22.3426 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -287.273 MetaTest/__unnamed_task__/AverageReturn -287.273 MetaTest/__unnamed_task__/Iteration 115 MetaTest/__unnamed_task__/MaxReturn -263.799 MetaTest/__unnamed_task__/MinReturn -321.473 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 22.3426 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 272000 ------------------------------------------------- ----------- 2025-04-04 08:07:38 | [pearl_trainer] epoch #116 | Training... 2025-04-04 08:10:39 | [pearl_trainer] epoch #116 | Evaluating... 2025-04-04 08:10:39 | [pearl_trainer] epoch #116 | Sampling for adapation and meta-testing... 2025-04-04 08:14:32 | [pearl_trainer] epoch #116 | Finished meta-testing... 2025-04-04 08:14:32 | [pearl_trainer] epoch #116 | Saving snapshot... 2025-04-04 08:14:33 | [pearl_trainer] epoch #116 | Saved 2025-04-04 08:14:33 | [pearl_trainer] epoch #116 | Time 56736.83 s 2025-04-04 08:14:33 | [pearl_trainer] epoch #116 | EpochTime 458.56 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -326.313 MetaTest/Average/AverageReturn -326.313 MetaTest/Average/Iteration 116 MetaTest/Average/MaxReturn -284.048 MetaTest/Average/MinReturn -363.219 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.9409 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -326.313 MetaTest/__unnamed_task__/AverageReturn -326.313 MetaTest/__unnamed_task__/Iteration 116 MetaTest/__unnamed_task__/MaxReturn -284.048 MetaTest/__unnamed_task__/MinReturn -363.219 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.9409 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 274000 ------------------------------------------------- ----------- 2025-04-04 08:15:17 | [pearl_trainer] epoch #117 | Training... 2025-04-04 08:18:00 | [pearl_trainer] epoch #117 | Evaluating... 2025-04-04 08:18:00 | [pearl_trainer] epoch #117 | Sampling for adapation and meta-testing... 2025-04-04 08:22:09 | [pearl_trainer] epoch #117 | Finished meta-testing... 2025-04-04 08:22:09 | [pearl_trainer] epoch #117 | Saving snapshot... 2025-04-04 08:22:10 | [pearl_trainer] epoch #117 | Saved 2025-04-04 08:22:10 | [pearl_trainer] epoch #117 | Time 57193.79 s 2025-04-04 08:22:10 | [pearl_trainer] epoch #117 | EpochTime 456.96 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -276.685 MetaTest/Average/AverageReturn -276.685 MetaTest/Average/Iteration 117 MetaTest/Average/MaxReturn -249.409 MetaTest/Average/MinReturn -301.765 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 21.6499 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -276.685 MetaTest/__unnamed_task__/AverageReturn -276.685 MetaTest/__unnamed_task__/Iteration 117 MetaTest/__unnamed_task__/MaxReturn -249.409 MetaTest/__unnamed_task__/MinReturn -301.765 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 21.6499 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 276000 ------------------------------------------------- ----------- 2025-04-04 08:22:56 | [pearl_trainer] epoch #118 | Training... 2025-04-04 08:25:40 | [pearl_trainer] epoch #118 | Evaluating... 2025-04-04 08:25:40 | [pearl_trainer] epoch #118 | Sampling for adapation and meta-testing... 2025-04-04 08:29:43 | [pearl_trainer] epoch #118 | Finished meta-testing... 2025-04-04 08:29:43 | [pearl_trainer] epoch #118 | Saving snapshot... 2025-04-04 08:29:44 | [pearl_trainer] epoch #118 | Saved 2025-04-04 08:29:44 | [pearl_trainer] epoch #118 | Time 57647.63 s 2025-04-04 08:29:44 | [pearl_trainer] epoch #118 | EpochTime 453.84 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -302.068 MetaTest/Average/AverageReturn -302.068 MetaTest/Average/Iteration 118 MetaTest/Average/MaxReturn -253.471 MetaTest/Average/MinReturn -324.443 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 25.1561 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -302.068 MetaTest/__unnamed_task__/AverageReturn -302.068 MetaTest/__unnamed_task__/Iteration 118 MetaTest/__unnamed_task__/MaxReturn -253.471 MetaTest/__unnamed_task__/MinReturn -324.443 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 25.1561 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 278000 ------------------------------------------------- ----------- 2025-04-04 08:30:30 | [pearl_trainer] epoch #119 | Training... 2025-04-04 08:33:32 | [pearl_trainer] epoch #119 | Evaluating... 2025-04-04 08:33:32 | [pearl_trainer] epoch #119 | Sampling for adapation and meta-testing... 2025-04-04 08:37:33 | [pearl_trainer] epoch #119 | Finished meta-testing... 2025-04-04 08:37:33 | [pearl_trainer] epoch #119 | Saving snapshot... 2025-04-04 08:37:34 | [pearl_trainer] epoch #119 | Saved 2025-04-04 08:37:34 | [pearl_trainer] epoch #119 | Time 58118.15 s 2025-04-04 08:37:34 | [pearl_trainer] epoch #119 | EpochTime 470.51 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -265.98 MetaTest/Average/AverageReturn -265.98 MetaTest/Average/Iteration 119 MetaTest/Average/MaxReturn -170.199 MetaTest/Average/MinReturn -353.441 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 59.0755 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -265.98 MetaTest/__unnamed_task__/AverageReturn -265.98 MetaTest/__unnamed_task__/Iteration 119 MetaTest/__unnamed_task__/MaxReturn -170.199 MetaTest/__unnamed_task__/MinReturn -353.441 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 59.0755 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 280000 ------------------------------------------------- ----------- 2025-04-04 08:38:18 | [pearl_trainer] epoch #120 | Training... 2025-04-04 08:41:12 | [pearl_trainer] epoch #120 | Evaluating... 2025-04-04 08:41:12 | [pearl_trainer] epoch #120 | Sampling for adapation and meta-testing... 2025-04-04 08:44:55 | [pearl_trainer] epoch #120 | Finished meta-testing... 2025-04-04 08:44:55 | [pearl_trainer] epoch #120 | Saving snapshot... 2025-04-04 08:44:56 | [pearl_trainer] epoch #120 | Saved 2025-04-04 08:44:56 | [pearl_trainer] epoch #120 | Time 58560.07 s 2025-04-04 08:44:56 | [pearl_trainer] epoch #120 | EpochTime 441.92 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -271.524 MetaTest/Average/AverageReturn -271.524 MetaTest/Average/Iteration 120 MetaTest/Average/MaxReturn -231.346 MetaTest/Average/MinReturn -343.497 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 43.2574 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -271.524 MetaTest/__unnamed_task__/AverageReturn -271.524 MetaTest/__unnamed_task__/Iteration 120 MetaTest/__unnamed_task__/MaxReturn -231.346 MetaTest/__unnamed_task__/MinReturn -343.497 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 43.2574 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 282000 ------------------------------------------------- ----------- 2025-04-04 08:45:41 | [pearl_trainer] epoch #121 | Training... 2025-04-04 08:48:21 | [pearl_trainer] epoch #121 | Evaluating... 2025-04-04 08:48:21 | [pearl_trainer] epoch #121 | Sampling for adapation and meta-testing... 2025-04-04 08:52:11 | [pearl_trainer] epoch #121 | Finished meta-testing... 2025-04-04 08:52:11 | [pearl_trainer] epoch #121 | Saving snapshot... 2025-04-04 08:52:12 | [pearl_trainer] epoch #121 | Saved 2025-04-04 08:52:12 | [pearl_trainer] epoch #121 | Time 58996.11 s 2025-04-04 08:52:12 | [pearl_trainer] epoch #121 | EpochTime 436.03 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -245.602 MetaTest/Average/AverageReturn -245.602 MetaTest/Average/Iteration 121 MetaTest/Average/MaxReturn -201.191 MetaTest/Average/MinReturn -281.785 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 29.9947 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -245.602 MetaTest/__unnamed_task__/AverageReturn -245.602 MetaTest/__unnamed_task__/Iteration 121 MetaTest/__unnamed_task__/MaxReturn -201.191 MetaTest/__unnamed_task__/MinReturn -281.785 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 29.9947 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 284000 ------------------------------------------------- ----------- 2025-04-04 08:52:53 | [pearl_trainer] epoch #122 | Training... 2025-04-04 08:55:40 | [pearl_trainer] epoch #122 | Evaluating... 2025-04-04 08:55:40 | [pearl_trainer] epoch #122 | Sampling for adapation and meta-testing... 2025-04-04 08:59:26 | [pearl_trainer] epoch #122 | Finished meta-testing... 2025-04-04 08:59:26 | [pearl_trainer] epoch #122 | Saving snapshot... 2025-04-04 08:59:28 | [pearl_trainer] epoch #122 | Saved 2025-04-04 08:59:28 | [pearl_trainer] epoch #122 | Time 59431.25 s 2025-04-04 08:59:28 | [pearl_trainer] epoch #122 | EpochTime 435.14 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -316.934 MetaTest/Average/AverageReturn -316.934 MetaTest/Average/Iteration 122 MetaTest/Average/MaxReturn -277.311 MetaTest/Average/MinReturn -354.243 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.3438 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -316.934 MetaTest/__unnamed_task__/AverageReturn -316.934 MetaTest/__unnamed_task__/Iteration 122 MetaTest/__unnamed_task__/MaxReturn -277.311 MetaTest/__unnamed_task__/MinReturn -354.243 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.3438 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 286000 ------------------------------------------------- ----------- 2025-04-04 09:00:08 | [pearl_trainer] epoch #123 | Training... 2025-04-04 09:02:48 | [pearl_trainer] epoch #123 | Evaluating... 2025-04-04 09:02:48 | [pearl_trainer] epoch #123 | Sampling for adapation and meta-testing... 2025-04-04 09:06:29 | [pearl_trainer] epoch #123 | Finished meta-testing... 2025-04-04 09:06:29 | [pearl_trainer] epoch #123 | Saving snapshot... 2025-04-04 09:06:30 | [pearl_trainer] epoch #123 | Saved 2025-04-04 09:06:30 | [pearl_trainer] epoch #123 | Time 59853.71 s 2025-04-04 09:06:30 | [pearl_trainer] epoch #123 | EpochTime 422.46 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -294.708 MetaTest/Average/AverageReturn -294.708 MetaTest/Average/Iteration 123 MetaTest/Average/MaxReturn -219.294 MetaTest/Average/MinReturn -366.959 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 46.7916 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -294.708 MetaTest/__unnamed_task__/AverageReturn -294.708 MetaTest/__unnamed_task__/Iteration 123 MetaTest/__unnamed_task__/MaxReturn -219.294 MetaTest/__unnamed_task__/MinReturn -366.959 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 46.7916 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 288000 ------------------------------------------------- ----------- 2025-04-04 09:07:11 | [pearl_trainer] epoch #124 | Training... 2025-04-04 09:09:51 | [pearl_trainer] epoch #124 | Evaluating... 2025-04-04 09:09:51 | [pearl_trainer] epoch #124 | Sampling for adapation and meta-testing... 2025-04-04 09:13:29 | [pearl_trainer] epoch #124 | Finished meta-testing... 2025-04-04 09:13:29 | [pearl_trainer] epoch #124 | Saving snapshot... 2025-04-04 09:13:31 | [pearl_trainer] epoch #124 | Saved 2025-04-04 09:13:31 | [pearl_trainer] epoch #124 | Time 60274.39 s 2025-04-04 09:13:31 | [pearl_trainer] epoch #124 | EpochTime 420.68 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -297.591 MetaTest/Average/AverageReturn -297.591 MetaTest/Average/Iteration 124 MetaTest/Average/MaxReturn -280.443 MetaTest/Average/MinReturn -329.379 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 19.1617 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -297.591 MetaTest/__unnamed_task__/AverageReturn -297.591 MetaTest/__unnamed_task__/Iteration 124 MetaTest/__unnamed_task__/MaxReturn -280.443 MetaTest/__unnamed_task__/MinReturn -329.379 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 19.1617 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 290000 ------------------------------------------------- ----------- 2025-04-04 09:14:10 | [pearl_trainer] epoch #125 | Training... 2025-04-04 09:16:50 | [pearl_trainer] epoch #125 | Evaluating... 2025-04-04 09:16:50 | [pearl_trainer] epoch #125 | Sampling for adapation and meta-testing... 2025-04-04 09:20:29 | [pearl_trainer] epoch #125 | Finished meta-testing... 2025-04-04 09:20:29 | [pearl_trainer] epoch #125 | Saving snapshot... 2025-04-04 09:20:30 | [pearl_trainer] epoch #125 | Saved 2025-04-04 09:20:30 | [pearl_trainer] epoch #125 | Time 60693.52 s 2025-04-04 09:20:30 | [pearl_trainer] epoch #125 | EpochTime 419.13 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -258.595 MetaTest/Average/AverageReturn -258.595 MetaTest/Average/Iteration 125 MetaTest/Average/MaxReturn -164.614 MetaTest/Average/MinReturn -305.812 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 53.1117 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -258.595 MetaTest/__unnamed_task__/AverageReturn -258.595 MetaTest/__unnamed_task__/Iteration 125 MetaTest/__unnamed_task__/MaxReturn -164.614 MetaTest/__unnamed_task__/MinReturn -305.812 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 53.1117 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 292000 ------------------------------------------------- ----------- 2025-04-04 09:21:09 | [pearl_trainer] epoch #126 | Training... 2025-04-04 09:23:34 | [pearl_trainer] epoch #126 | Evaluating... 2025-04-04 09:23:34 | [pearl_trainer] epoch #126 | Sampling for adapation and meta-testing... 2025-04-04 09:27:15 | [pearl_trainer] epoch #126 | Finished meta-testing... 2025-04-04 09:27:15 | [pearl_trainer] epoch #126 | Saving snapshot... 2025-04-04 09:27:16 | [pearl_trainer] epoch #126 | Saved 2025-04-04 09:27:16 | [pearl_trainer] epoch #126 | Time 61099.99 s 2025-04-04 09:27:16 | [pearl_trainer] epoch #126 | EpochTime 406.46 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -257.99 MetaTest/Average/AverageReturn -257.99 MetaTest/Average/Iteration 126 MetaTest/Average/MaxReturn -238.357 MetaTest/Average/MinReturn -288.547 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 17.0559 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -257.99 MetaTest/__unnamed_task__/AverageReturn -257.99 MetaTest/__unnamed_task__/Iteration 126 MetaTest/__unnamed_task__/MaxReturn -238.357 MetaTest/__unnamed_task__/MinReturn -288.547 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 17.0559 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 294000 ------------------------------------------------- ----------- 2025-04-04 09:27:56 | [pearl_trainer] epoch #127 | Training... 2025-04-04 09:30:33 | [pearl_trainer] epoch #127 | Evaluating... 2025-04-04 09:30:33 | [pearl_trainer] epoch #127 | Sampling for adapation and meta-testing... 2025-04-04 09:34:18 | [pearl_trainer] epoch #127 | Finished meta-testing... 2025-04-04 09:34:18 | [pearl_trainer] epoch #127 | Saving snapshot... 2025-04-04 09:34:19 | [pearl_trainer] epoch #127 | Saved 2025-04-04 09:34:19 | [pearl_trainer] epoch #127 | Time 61522.62 s 2025-04-04 09:34:19 | [pearl_trainer] epoch #127 | EpochTime 422.64 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -228.386 MetaTest/Average/AverageReturn -228.386 MetaTest/Average/Iteration 127 MetaTest/Average/MaxReturn -200.99 MetaTest/Average/MinReturn -294.378 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 34.4055 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -228.386 MetaTest/__unnamed_task__/AverageReturn -228.386 MetaTest/__unnamed_task__/Iteration 127 MetaTest/__unnamed_task__/MaxReturn -200.99 MetaTest/__unnamed_task__/MinReturn -294.378 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 34.4055 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 296000 ------------------------------------------------- ----------- 2025-04-04 09:34:59 | [pearl_trainer] epoch #128 | Training... 2025-04-04 09:37:32 | [pearl_trainer] epoch #128 | Evaluating... 2025-04-04 09:37:32 | [pearl_trainer] epoch #128 | Sampling for adapation and meta-testing... 2025-04-04 09:41:19 | [pearl_trainer] epoch #128 | Finished meta-testing... 2025-04-04 09:41:19 | [pearl_trainer] epoch #128 | Saving snapshot... 2025-04-04 09:41:21 | [pearl_trainer] epoch #128 | Saved 2025-04-04 09:41:21 | [pearl_trainer] epoch #128 | Time 61944.29 s 2025-04-04 09:41:21 | [pearl_trainer] epoch #128 | EpochTime 421.66 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -293.807 MetaTest/Average/AverageReturn -293.807 MetaTest/Average/Iteration 128 MetaTest/Average/MaxReturn -218.439 MetaTest/Average/MinReturn -363.094 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 50.1192 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -293.807 MetaTest/__unnamed_task__/AverageReturn -293.807 MetaTest/__unnamed_task__/Iteration 128 MetaTest/__unnamed_task__/MaxReturn -218.439 MetaTest/__unnamed_task__/MinReturn -363.094 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 50.1192 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 298000 ------------------------------------------------- ----------- 2025-04-04 09:42:03 | [pearl_trainer] epoch #129 | Training... 2025-04-04 09:44:41 | [pearl_trainer] epoch #129 | Evaluating... 2025-04-04 09:44:41 | [pearl_trainer] epoch #129 | Sampling for adapation and meta-testing... 2025-04-04 09:48:27 | [pearl_trainer] epoch #129 | Finished meta-testing... 2025-04-04 09:48:27 | [pearl_trainer] epoch #129 | Saving snapshot... 2025-04-04 09:48:28 | [pearl_trainer] epoch #129 | Saved 2025-04-04 09:48:28 | [pearl_trainer] epoch #129 | Time 62372.03 s 2025-04-04 09:48:28 | [pearl_trainer] epoch #129 | EpochTime 427.74 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -310.445 MetaTest/Average/AverageReturn -310.445 MetaTest/Average/Iteration 129 MetaTest/Average/MaxReturn -268.425 MetaTest/Average/MinReturn -338.318 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 23.8471 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -310.445 MetaTest/__unnamed_task__/AverageReturn -310.445 MetaTest/__unnamed_task__/Iteration 129 MetaTest/__unnamed_task__/MaxReturn -268.425 MetaTest/__unnamed_task__/MinReturn -338.318 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 23.8471 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 300000 ------------------------------------------------- ----------- 2025-04-04 09:49:09 | [pearl_trainer] epoch #130 | Training... 2025-04-04 09:52:09 | [pearl_trainer] epoch #130 | Evaluating... 2025-04-04 09:52:09 | [pearl_trainer] epoch #130 | Sampling for adapation and meta-testing... 2025-04-04 09:56:01 | [pearl_trainer] epoch #130 | Finished meta-testing... 2025-04-04 09:56:01 | [pearl_trainer] epoch #130 | Saving snapshot... 2025-04-04 09:56:02 | [pearl_trainer] epoch #130 | Saved 2025-04-04 09:56:02 | [pearl_trainer] epoch #130 | Time 62825.60 s 2025-04-04 09:56:02 | [pearl_trainer] epoch #130 | EpochTime 453.56 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -323.099 MetaTest/Average/AverageReturn -323.099 MetaTest/Average/Iteration 130 MetaTest/Average/MaxReturn -264.244 MetaTest/Average/MinReturn -376.334 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.9978 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -323.099 MetaTest/__unnamed_task__/AverageReturn -323.099 MetaTest/__unnamed_task__/Iteration 130 MetaTest/__unnamed_task__/MaxReturn -264.244 MetaTest/__unnamed_task__/MinReturn -376.334 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.9978 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 302000 ------------------------------------------------- ----------- 2025-04-04 09:56:42 | [pearl_trainer] epoch #131 | Training... 2025-04-04 09:59:39 | [pearl_trainer] epoch #131 | Evaluating... 2025-04-04 09:59:39 | [pearl_trainer] epoch #131 | Sampling for adapation and meta-testing... 2025-04-04 10:03:23 | [pearl_trainer] epoch #131 | Finished meta-testing... 2025-04-04 10:03:23 | [pearl_trainer] epoch #131 | Saving snapshot... 2025-04-04 10:03:24 | [pearl_trainer] epoch #131 | Saved 2025-04-04 10:03:24 | [pearl_trainer] epoch #131 | Time 63268.12 s 2025-04-04 10:03:24 | [pearl_trainer] epoch #131 | EpochTime 442.52 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -302.621 MetaTest/Average/AverageReturn -302.621 MetaTest/Average/Iteration 131 MetaTest/Average/MaxReturn -286.48 MetaTest/Average/MinReturn -334.814 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 17.2556 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -302.621 MetaTest/__unnamed_task__/AverageReturn -302.621 MetaTest/__unnamed_task__/Iteration 131 MetaTest/__unnamed_task__/MaxReturn -286.48 MetaTest/__unnamed_task__/MinReturn -334.814 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 17.2556 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 304000 ------------------------------------------------- ----------- 2025-04-04 10:04:02 | [pearl_trainer] epoch #132 | Training... 2025-04-04 10:07:03 | [pearl_trainer] epoch #132 | Evaluating... 2025-04-04 10:07:03 | [pearl_trainer] epoch #132 | Sampling for adapation and meta-testing... 2025-04-04 10:10:52 | [pearl_trainer] epoch #132 | Finished meta-testing... 2025-04-04 10:10:52 | [pearl_trainer] epoch #132 | Saving snapshot... 2025-04-04 10:10:53 | [pearl_trainer] epoch #132 | Saved 2025-04-04 10:10:53 | [pearl_trainer] epoch #132 | Time 63716.93 s 2025-04-04 10:10:53 | [pearl_trainer] epoch #132 | EpochTime 448.81 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -304.235 MetaTest/Average/AverageReturn -304.235 MetaTest/Average/Iteration 132 MetaTest/Average/MaxReturn -216.126 MetaTest/Average/MinReturn -355.64 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 57.8692 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -304.235 MetaTest/__unnamed_task__/AverageReturn -304.235 MetaTest/__unnamed_task__/Iteration 132 MetaTest/__unnamed_task__/MaxReturn -216.126 MetaTest/__unnamed_task__/MinReturn -355.64 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 57.8692 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 306000 ------------------------------------------------- ----------- 2025-04-04 10:11:34 | [pearl_trainer] epoch #133 | Training... 2025-04-04 10:14:30 | [pearl_trainer] epoch #133 | Evaluating... 2025-04-04 10:14:30 | [pearl_trainer] epoch #133 | Sampling for adapation and meta-testing... 2025-04-04 10:18:15 | [pearl_trainer] epoch #133 | Finished meta-testing... 2025-04-04 10:18:15 | [pearl_trainer] epoch #133 | Saving snapshot... 2025-04-04 10:18:16 | [pearl_trainer] epoch #133 | Saved 2025-04-04 10:18:16 | [pearl_trainer] epoch #133 | Time 64159.68 s 2025-04-04 10:18:16 | [pearl_trainer] epoch #133 | EpochTime 442.75 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -339.591 MetaTest/Average/AverageReturn -339.591 MetaTest/Average/Iteration 133 MetaTest/Average/MaxReturn -262.052 MetaTest/Average/MinReturn -417.427 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 53.7391 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -339.591 MetaTest/__unnamed_task__/AverageReturn -339.591 MetaTest/__unnamed_task__/Iteration 133 MetaTest/__unnamed_task__/MaxReturn -262.052 MetaTest/__unnamed_task__/MinReturn -417.427 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 53.7391 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 308000 ------------------------------------------------- ----------- 2025-04-04 10:18:58 | [pearl_trainer] epoch #134 | Training... 2025-04-04 10:21:58 | [pearl_trainer] epoch #134 | Evaluating... 2025-04-04 10:21:58 | [pearl_trainer] epoch #134 | Sampling for adapation and meta-testing... 2025-04-04 10:25:50 | [pearl_trainer] epoch #134 | Finished meta-testing... 2025-04-04 10:25:50 | [pearl_trainer] epoch #134 | Saving snapshot... 2025-04-04 10:25:51 | [pearl_trainer] epoch #134 | Saved 2025-04-04 10:25:51 | [pearl_trainer] epoch #134 | Time 64614.71 s 2025-04-04 10:25:51 | [pearl_trainer] epoch #134 | EpochTime 455.02 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -318.013 MetaTest/Average/AverageReturn -318.013 MetaTest/Average/Iteration 134 MetaTest/Average/MaxReturn -274.631 MetaTest/Average/MinReturn -349.774 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 33.6605 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -318.013 MetaTest/__unnamed_task__/AverageReturn -318.013 MetaTest/__unnamed_task__/Iteration 134 MetaTest/__unnamed_task__/MaxReturn -274.631 MetaTest/__unnamed_task__/MinReturn -349.774 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 33.6605 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 310000 ------------------------------------------------- ----------- 2025-04-04 10:26:30 | [pearl_trainer] epoch #135 | Training... 2025-04-04 10:29:15 | [pearl_trainer] epoch #135 | Evaluating... 2025-04-04 10:29:15 | [pearl_trainer] epoch #135 | Sampling for adapation and meta-testing... 2025-04-04 10:33:04 | [pearl_trainer] epoch #135 | Finished meta-testing... 2025-04-04 10:33:04 | [pearl_trainer] epoch #135 | Saving snapshot... 2025-04-04 10:33:06 | [pearl_trainer] epoch #135 | Saved 2025-04-04 10:33:06 | [pearl_trainer] epoch #135 | Time 65049.24 s 2025-04-04 10:33:06 | [pearl_trainer] epoch #135 | EpochTime 434.54 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -343.628 MetaTest/Average/AverageReturn -343.628 MetaTest/Average/Iteration 135 MetaTest/Average/MaxReturn -276.043 MetaTest/Average/MinReturn -385.12 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.1797 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -343.628 MetaTest/__unnamed_task__/AverageReturn -343.628 MetaTest/__unnamed_task__/Iteration 135 MetaTest/__unnamed_task__/MaxReturn -276.043 MetaTest/__unnamed_task__/MinReturn -385.12 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.1797 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 312000 ------------------------------------------------- ----------- 2025-04-04 10:33:47 | [pearl_trainer] epoch #136 | Training... 2025-04-04 10:36:26 | [pearl_trainer] epoch #136 | Evaluating... 2025-04-04 10:36:26 | [pearl_trainer] epoch #136 | Sampling for adapation and meta-testing... 2025-04-04 10:40:29 | [pearl_trainer] epoch #136 | Finished meta-testing... 2025-04-04 10:40:29 | [pearl_trainer] epoch #136 | Saving snapshot... 2025-04-04 10:40:30 | [pearl_trainer] epoch #136 | Saved 2025-04-04 10:40:30 | [pearl_trainer] epoch #136 | Time 65493.81 s 2025-04-04 10:40:30 | [pearl_trainer] epoch #136 | EpochTime 444.57 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -309.135 MetaTest/Average/AverageReturn -309.135 MetaTest/Average/Iteration 136 MetaTest/Average/MaxReturn -226.341 MetaTest/Average/MinReturn -363.608 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 46.6769 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -309.135 MetaTest/__unnamed_task__/AverageReturn -309.135 MetaTest/__unnamed_task__/Iteration 136 MetaTest/__unnamed_task__/MaxReturn -226.341 MetaTest/__unnamed_task__/MinReturn -363.608 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 46.6769 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 314000 ------------------------------------------------- ----------- 2025-04-04 10:41:13 | [pearl_trainer] epoch #137 | Training... 2025-04-04 10:43:53 | [pearl_trainer] epoch #137 | Evaluating... 2025-04-04 10:43:53 | [pearl_trainer] epoch #137 | Sampling for adapation and meta-testing... 2025-04-04 10:47:58 | [pearl_trainer] epoch #137 | Finished meta-testing... 2025-04-04 10:47:58 | [pearl_trainer] epoch #137 | Saving snapshot... 2025-04-04 10:47:59 | [pearl_trainer] epoch #137 | Saved 2025-04-04 10:47:59 | [pearl_trainer] epoch #137 | Time 65942.82 s 2025-04-04 10:47:59 | [pearl_trainer] epoch #137 | EpochTime 449.00 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -314.167 MetaTest/Average/AverageReturn -314.167 MetaTest/Average/Iteration 137 MetaTest/Average/MaxReturn -261.497 MetaTest/Average/MinReturn -375.033 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.5482 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -314.167 MetaTest/__unnamed_task__/AverageReturn -314.167 MetaTest/__unnamed_task__/Iteration 137 MetaTest/__unnamed_task__/MaxReturn -261.497 MetaTest/__unnamed_task__/MinReturn -375.033 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.5482 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 316000 ------------------------------------------------- ----------- 2025-04-04 10:48:42 | [pearl_trainer] epoch #138 | Training... 2025-04-04 10:51:23 | [pearl_trainer] epoch #138 | Evaluating... 2025-04-04 10:51:23 | [pearl_trainer] epoch #138 | Sampling for adapation and meta-testing... 2025-04-04 10:55:44 | [pearl_trainer] epoch #138 | Finished meta-testing... 2025-04-04 10:55:44 | [pearl_trainer] epoch #138 | Saving snapshot... 2025-04-04 10:55:45 | [pearl_trainer] epoch #138 | Saved 2025-04-04 10:55:45 | [pearl_trainer] epoch #138 | Time 66408.44 s 2025-04-04 10:55:45 | [pearl_trainer] epoch #138 | EpochTime 465.62 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -265.015 MetaTest/Average/AverageReturn -265.015 MetaTest/Average/Iteration 138 MetaTest/Average/MaxReturn -156.259 MetaTest/Average/MinReturn -371.894 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 70.8651 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -265.015 MetaTest/__unnamed_task__/AverageReturn -265.015 MetaTest/__unnamed_task__/Iteration 138 MetaTest/__unnamed_task__/MaxReturn -156.259 MetaTest/__unnamed_task__/MinReturn -371.894 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 70.8651 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 318000 ------------------------------------------------- ----------- 2025-04-04 10:56:30 | [pearl_trainer] epoch #139 | Training... 2025-04-04 10:59:07 | [pearl_trainer] epoch #139 | Evaluating... 2025-04-04 10:59:07 | [pearl_trainer] epoch #139 | Sampling for adapation and meta-testing... 2025-04-04 11:03:34 | [pearl_trainer] epoch #139 | Finished meta-testing... 2025-04-04 11:03:34 | [pearl_trainer] epoch #139 | Saving snapshot... 2025-04-04 11:03:35 | [pearl_trainer] epoch #139 | Saved 2025-04-04 11:03:35 | [pearl_trainer] epoch #139 | Time 66878.94 s 2025-04-04 11:03:35 | [pearl_trainer] epoch #139 | EpochTime 470.50 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -285.776 MetaTest/Average/AverageReturn -285.776 MetaTest/Average/Iteration 139 MetaTest/Average/MaxReturn -210.609 MetaTest/Average/MinReturn -336.461 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 49.2707 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -285.776 MetaTest/__unnamed_task__/AverageReturn -285.776 MetaTest/__unnamed_task__/Iteration 139 MetaTest/__unnamed_task__/MaxReturn -210.609 MetaTest/__unnamed_task__/MinReturn -336.461 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 49.2707 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 320000 ------------------------------------------------- ----------- 2025-04-04 11:04:23 | [pearl_trainer] epoch #140 | Training... 2025-04-04 11:07:09 | [pearl_trainer] epoch #140 | Evaluating... 2025-04-04 11:07:09 | [pearl_trainer] epoch #140 | Sampling for adapation and meta-testing... 2025-04-04 11:11:46 | [pearl_trainer] epoch #140 | Finished meta-testing... 2025-04-04 11:11:46 | [pearl_trainer] epoch #140 | Saving snapshot... 2025-04-04 11:11:47 | [pearl_trainer] epoch #140 | Saved 2025-04-04 11:11:47 | [pearl_trainer] epoch #140 | Time 67370.79 s 2025-04-04 11:11:47 | [pearl_trainer] epoch #140 | EpochTime 491.84 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -250.348 MetaTest/Average/AverageReturn -250.348 MetaTest/Average/Iteration 140 MetaTest/Average/MaxReturn -164.367 MetaTest/Average/MinReturn -312.216 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 49.6385 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -250.348 MetaTest/__unnamed_task__/AverageReturn -250.348 MetaTest/__unnamed_task__/Iteration 140 MetaTest/__unnamed_task__/MaxReturn -164.367 MetaTest/__unnamed_task__/MinReturn -312.216 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 49.6385 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 322000 ------------------------------------------------- ----------- 2025-04-04 11:12:36 | [pearl_trainer] epoch #141 | Training... 2025-04-04 11:15:18 | [pearl_trainer] epoch #141 | Evaluating... 2025-04-04 11:15:18 | [pearl_trainer] epoch #141 | Sampling for adapation and meta-testing... 2025-04-04 11:19:29 | [pearl_trainer] epoch #141 | Finished meta-testing... 2025-04-04 11:19:29 | [pearl_trainer] epoch #141 | Saving snapshot... 2025-04-04 11:19:30 | [pearl_trainer] epoch #141 | Saved 2025-04-04 11:19:30 | [pearl_trainer] epoch #141 | Time 67833.51 s 2025-04-04 11:19:30 | [pearl_trainer] epoch #141 | EpochTime 462.72 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -253.441 MetaTest/Average/AverageReturn -253.441 MetaTest/Average/Iteration 141 MetaTest/Average/MaxReturn -132.508 MetaTest/Average/MinReturn -321.542 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 63.8265 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -253.441 MetaTest/__unnamed_task__/AverageReturn -253.441 MetaTest/__unnamed_task__/Iteration 141 MetaTest/__unnamed_task__/MaxReturn -132.508 MetaTest/__unnamed_task__/MinReturn -321.542 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 63.8265 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 324000 ------------------------------------------------- ----------- 2025-04-04 11:20:16 | [pearl_trainer] epoch #142 | Training... 2025-04-04 11:23:09 | [pearl_trainer] epoch #142 | Evaluating... 2025-04-04 11:23:09 | [pearl_trainer] epoch #142 | Sampling for adapation and meta-testing... 2025-04-04 11:27:27 | [pearl_trainer] epoch #142 | Finished meta-testing... 2025-04-04 11:27:27 | [pearl_trainer] epoch #142 | Saving snapshot... 2025-04-04 11:27:28 | [pearl_trainer] epoch #142 | Saved 2025-04-04 11:27:28 | [pearl_trainer] epoch #142 | Time 68311.91 s 2025-04-04 11:27:28 | [pearl_trainer] epoch #142 | EpochTime 478.40 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -248.537 MetaTest/Average/AverageReturn -248.537 MetaTest/Average/Iteration 142 MetaTest/Average/MaxReturn -212.678 MetaTest/Average/MinReturn -300.1 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 28.6691 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -248.537 MetaTest/__unnamed_task__/AverageReturn -248.537 MetaTest/__unnamed_task__/Iteration 142 MetaTest/__unnamed_task__/MaxReturn -212.678 MetaTest/__unnamed_task__/MinReturn -300.1 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 28.6691 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 326000 ------------------------------------------------- ----------- 2025-04-04 11:28:20 | [pearl_trainer] epoch #143 | Training... 2025-04-04 11:31:00 | [pearl_trainer] epoch #143 | Evaluating... 2025-04-04 11:31:00 | [pearl_trainer] epoch #143 | Sampling for adapation and meta-testing... 2025-04-04 11:35:11 | [pearl_trainer] epoch #143 | Finished meta-testing... 2025-04-04 11:35:11 | [pearl_trainer] epoch #143 | Saving snapshot... 2025-04-04 11:35:12 | [pearl_trainer] epoch #143 | Saved 2025-04-04 11:35:12 | [pearl_trainer] epoch #143 | Time 68775.96 s 2025-04-04 11:35:12 | [pearl_trainer] epoch #143 | EpochTime 464.06 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -294.852 MetaTest/Average/AverageReturn -294.852 MetaTest/Average/Iteration 143 MetaTest/Average/MaxReturn -234.887 MetaTest/Average/MinReturn -349.572 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 45.5452 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -294.852 MetaTest/__unnamed_task__/AverageReturn -294.852 MetaTest/__unnamed_task__/Iteration 143 MetaTest/__unnamed_task__/MaxReturn -234.887 MetaTest/__unnamed_task__/MinReturn -349.572 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 45.5452 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 328000 ------------------------------------------------- ----------- 2025-04-04 11:35:55 | [pearl_trainer] epoch #144 | Training... 2025-04-04 11:38:35 | [pearl_trainer] epoch #144 | Evaluating... 2025-04-04 11:38:35 | [pearl_trainer] epoch #144 | Sampling for adapation and meta-testing... 2025-04-04 11:42:46 | [pearl_trainer] epoch #144 | Finished meta-testing... 2025-04-04 11:42:46 | [pearl_trainer] epoch #144 | Saving snapshot... 2025-04-04 11:42:47 | [pearl_trainer] epoch #144 | Saved 2025-04-04 11:42:47 | [pearl_trainer] epoch #144 | Time 69230.83 s 2025-04-04 11:42:47 | [pearl_trainer] epoch #144 | EpochTime 454.86 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -269.663 MetaTest/Average/AverageReturn -269.663 MetaTest/Average/Iteration 144 MetaTest/Average/MaxReturn -232.432 MetaTest/Average/MinReturn -311.127 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 27.7633 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -269.663 MetaTest/__unnamed_task__/AverageReturn -269.663 MetaTest/__unnamed_task__/Iteration 144 MetaTest/__unnamed_task__/MaxReturn -232.432 MetaTest/__unnamed_task__/MinReturn -311.127 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 27.7633 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 330000 ------------------------------------------------- ----------- 2025-04-04 11:43:32 | [pearl_trainer] epoch #145 | Training... 2025-04-04 11:46:11 | [pearl_trainer] epoch #145 | Evaluating... 2025-04-04 11:46:11 | [pearl_trainer] epoch #145 | Sampling for adapation and meta-testing... 2025-04-04 11:50:19 | [pearl_trainer] epoch #145 | Finished meta-testing... 2025-04-04 11:50:19 | [pearl_trainer] epoch #145 | Saving snapshot... 2025-04-04 11:50:20 | [pearl_trainer] epoch #145 | Saved 2025-04-04 11:50:20 | [pearl_trainer] epoch #145 | Time 69683.42 s 2025-04-04 11:50:20 | [pearl_trainer] epoch #145 | EpochTime 452.59 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -220.745 MetaTest/Average/AverageReturn -220.745 MetaTest/Average/Iteration 145 MetaTest/Average/MaxReturn -192.25 MetaTest/Average/MinReturn -242.551 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 22.7111 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -220.745 MetaTest/__unnamed_task__/AverageReturn -220.745 MetaTest/__unnamed_task__/Iteration 145 MetaTest/__unnamed_task__/MaxReturn -192.25 MetaTest/__unnamed_task__/MinReturn -242.551 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 22.7111 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 332000 ------------------------------------------------- ----------- 2025-04-04 11:51:07 | [pearl_trainer] epoch #146 | Training... 2025-04-04 11:53:45 | [pearl_trainer] epoch #146 | Evaluating... 2025-04-04 11:53:45 | [pearl_trainer] epoch #146 | Sampling for adapation and meta-testing... 2025-04-04 11:58:03 | [pearl_trainer] epoch #146 | Finished meta-testing... 2025-04-04 11:58:03 | [pearl_trainer] epoch #146 | Saving snapshot... 2025-04-04 11:58:04 | [pearl_trainer] epoch #146 | Saved 2025-04-04 11:58:04 | [pearl_trainer] epoch #146 | Time 70147.72 s 2025-04-04 11:58:04 | [pearl_trainer] epoch #146 | EpochTime 464.30 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -238.811 MetaTest/Average/AverageReturn -238.811 MetaTest/Average/Iteration 146 MetaTest/Average/MaxReturn -220.466 MetaTest/Average/MinReturn -273.184 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 18.1085 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -238.811 MetaTest/__unnamed_task__/AverageReturn -238.811 MetaTest/__unnamed_task__/Iteration 146 MetaTest/__unnamed_task__/MaxReturn -220.466 MetaTest/__unnamed_task__/MinReturn -273.184 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 18.1085 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 334000 ------------------------------------------------- ----------- 2025-04-04 11:58:47 | [pearl_trainer] epoch #147 | Training... 2025-04-04 12:01:28 | [pearl_trainer] epoch #147 | Evaluating... 2025-04-04 12:01:28 | [pearl_trainer] epoch #147 | Sampling for adapation and meta-testing... 2025-04-04 12:05:39 | [pearl_trainer] epoch #147 | Finished meta-testing... 2025-04-04 12:05:39 | [pearl_trainer] epoch #147 | Saving snapshot... 2025-04-04 12:05:40 | [pearl_trainer] epoch #147 | Saved 2025-04-04 12:05:40 | [pearl_trainer] epoch #147 | Time 70603.46 s 2025-04-04 12:05:40 | [pearl_trainer] epoch #147 | EpochTime 455.73 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -235.666 MetaTest/Average/AverageReturn -235.666 MetaTest/Average/Iteration 147 MetaTest/Average/MaxReturn -200.674 MetaTest/Average/MinReturn -274.116 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 23.6751 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -235.666 MetaTest/__unnamed_task__/AverageReturn -235.666 MetaTest/__unnamed_task__/Iteration 147 MetaTest/__unnamed_task__/MaxReturn -200.674 MetaTest/__unnamed_task__/MinReturn -274.116 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 23.6751 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 336000 ------------------------------------------------- ----------- 2025-04-04 12:06:28 | [pearl_trainer] epoch #148 | Training... 2025-04-04 12:09:08 | [pearl_trainer] epoch #148 | Evaluating... 2025-04-04 12:09:08 | [pearl_trainer] epoch #148 | Sampling for adapation and meta-testing... 2025-04-04 12:13:13 | [pearl_trainer] epoch #148 | Finished meta-testing... 2025-04-04 12:13:13 | [pearl_trainer] epoch #148 | Saving snapshot... 2025-04-04 12:13:15 | [pearl_trainer] epoch #148 | Saved 2025-04-04 12:13:15 | [pearl_trainer] epoch #148 | Time 71058.53 s 2025-04-04 12:13:15 | [pearl_trainer] epoch #148 | EpochTime 455.07 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -244.924 MetaTest/Average/AverageReturn -244.924 MetaTest/Average/Iteration 148 MetaTest/Average/MaxReturn -130.666 MetaTest/Average/MinReturn -297.736 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 66.8013 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -244.924 MetaTest/__unnamed_task__/AverageReturn -244.924 MetaTest/__unnamed_task__/Iteration 148 MetaTest/__unnamed_task__/MaxReturn -130.666 MetaTest/__unnamed_task__/MinReturn -297.736 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 66.8013 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 338000 ------------------------------------------------- ----------- 2025-04-04 12:14:02 | [pearl_trainer] epoch #149 | Training... 2025-04-04 12:16:42 | [pearl_trainer] epoch #149 | Evaluating... 2025-04-04 12:16:42 | [pearl_trainer] epoch #149 | Sampling for adapation and meta-testing... 2025-04-04 12:20:32 | [pearl_trainer] epoch #149 | Finished meta-testing... 2025-04-04 12:20:32 | [pearl_trainer] epoch #149 | Saving snapshot... 2025-04-04 12:20:33 | [pearl_trainer] epoch #149 | Saved 2025-04-04 12:20:33 | [pearl_trainer] epoch #149 | Time 71496.35 s 2025-04-04 12:20:33 | [pearl_trainer] epoch #149 | EpochTime 437.82 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -272.4 MetaTest/Average/AverageReturn -272.4 MetaTest/Average/Iteration 149 MetaTest/Average/MaxReturn -246.309 MetaTest/Average/MinReturn -320.157 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 27.0728 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -272.4 MetaTest/__unnamed_task__/AverageReturn -272.4 MetaTest/__unnamed_task__/Iteration 149 MetaTest/__unnamed_task__/MaxReturn -246.309 MetaTest/__unnamed_task__/MinReturn -320.157 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 27.0728 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 340000 ------------------------------------------------- ----------- 2025-04-04 12:21:15 | [pearl_trainer] epoch #150 | Training... 2025-04-04 12:23:55 | [pearl_trainer] epoch #150 | Evaluating... 2025-04-04 12:23:55 | [pearl_trainer] epoch #150 | Sampling for adapation and meta-testing... 2025-04-04 12:28:00 | [pearl_trainer] epoch #150 | Finished meta-testing... 2025-04-04 12:28:00 | [pearl_trainer] epoch #150 | Saving snapshot... 2025-04-04 12:28:01 | [pearl_trainer] epoch #150 | Saved 2025-04-04 12:28:01 | [pearl_trainer] epoch #150 | Time 71944.76 s 2025-04-04 12:28:01 | [pearl_trainer] epoch #150 | EpochTime 448.41 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -306.261 MetaTest/Average/AverageReturn -306.261 MetaTest/Average/Iteration 150 MetaTest/Average/MaxReturn -273.199 MetaTest/Average/MinReturn -328.983 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 21.3502 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -306.261 MetaTest/__unnamed_task__/AverageReturn -306.261 MetaTest/__unnamed_task__/Iteration 150 MetaTest/__unnamed_task__/MaxReturn -273.199 MetaTest/__unnamed_task__/MinReturn -328.983 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 21.3502 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 342000 ------------------------------------------------- ----------- 2025-04-04 12:28:44 | [pearl_trainer] epoch #151 | Training... 2025-04-04 12:31:15 | [pearl_trainer] epoch #151 | Evaluating... 2025-04-04 12:31:15 | [pearl_trainer] epoch #151 | Sampling for adapation and meta-testing... 2025-04-04 12:35:14 | [pearl_trainer] epoch #151 | Finished meta-testing... 2025-04-04 12:35:14 | [pearl_trainer] epoch #151 | Saving snapshot... 2025-04-04 12:35:15 | [pearl_trainer] epoch #151 | Saved 2025-04-04 12:35:15 | [pearl_trainer] epoch #151 | Time 72378.66 s 2025-04-04 12:35:15 | [pearl_trainer] epoch #151 | EpochTime 433.90 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -331.28 MetaTest/Average/AverageReturn -331.28 MetaTest/Average/Iteration 151 MetaTest/Average/MaxReturn -241.26 MetaTest/Average/MinReturn -409.745 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 53.613 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -331.28 MetaTest/__unnamed_task__/AverageReturn -331.28 MetaTest/__unnamed_task__/Iteration 151 MetaTest/__unnamed_task__/MaxReturn -241.26 MetaTest/__unnamed_task__/MinReturn -409.745 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 53.613 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 344000 ------------------------------------------------- ---------- 2025-04-04 12:35:59 | [pearl_trainer] epoch #152 | Training... 2025-04-04 12:38:35 | [pearl_trainer] epoch #152 | Evaluating... 2025-04-04 12:38:35 | [pearl_trainer] epoch #152 | Sampling for adapation and meta-testing... 2025-04-04 12:42:23 | [pearl_trainer] epoch #152 | Finished meta-testing... 2025-04-04 12:42:23 | [pearl_trainer] epoch #152 | Saving snapshot... 2025-04-04 12:42:25 | [pearl_trainer] epoch #152 | Saved 2025-04-04 12:42:25 | [pearl_trainer] epoch #152 | Time 72808.25 s 2025-04-04 12:42:25 | [pearl_trainer] epoch #152 | EpochTime 429.59 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -303.088 MetaTest/Average/AverageReturn -303.088 MetaTest/Average/Iteration 152 MetaTest/Average/MaxReturn -278.721 MetaTest/Average/MinReturn -339.153 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 19.7913 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -303.088 MetaTest/__unnamed_task__/AverageReturn -303.088 MetaTest/__unnamed_task__/Iteration 152 MetaTest/__unnamed_task__/MaxReturn -278.721 MetaTest/__unnamed_task__/MinReturn -339.153 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 19.7913 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 346000 ------------------------------------------------- ----------- 2025-04-04 12:43:07 | [pearl_trainer] epoch #153 | Training... 2025-04-04 12:45:51 | [pearl_trainer] epoch #153 | Evaluating... 2025-04-04 12:45:51 | [pearl_trainer] epoch #153 | Sampling for adapation and meta-testing... 2025-04-04 12:49:47 | [pearl_trainer] epoch #153 | Finished meta-testing... 2025-04-04 12:49:47 | [pearl_trainer] epoch #153 | Saving snapshot... 2025-04-04 12:49:49 | [pearl_trainer] epoch #153 | Saved 2025-04-04 12:49:49 | [pearl_trainer] epoch #153 | Time 73252.31 s 2025-04-04 12:49:49 | [pearl_trainer] epoch #153 | EpochTime 444.06 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -317.292 MetaTest/Average/AverageReturn -317.292 MetaTest/Average/Iteration 153 MetaTest/Average/MaxReturn -280.991 MetaTest/Average/MinReturn -344.253 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 23.4929 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -317.292 MetaTest/__unnamed_task__/AverageReturn -317.292 MetaTest/__unnamed_task__/Iteration 153 MetaTest/__unnamed_task__/MaxReturn -280.991 MetaTest/__unnamed_task__/MinReturn -344.253 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 23.4929 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 348000 ------------------------------------------------- ----------- 2025-04-04 12:50:29 | [pearl_trainer] epoch #154 | Training... 2025-04-04 12:53:09 | [pearl_trainer] epoch #154 | Evaluating... 2025-04-04 12:53:09 | [pearl_trainer] epoch #154 | Sampling for adapation and meta-testing... 2025-04-04 12:57:21 | [pearl_trainer] epoch #154 | Finished meta-testing... 2025-04-04 12:57:21 | [pearl_trainer] epoch #154 | Saving snapshot... 2025-04-04 12:57:22 | [pearl_trainer] epoch #154 | Saved 2025-04-04 12:57:22 | [pearl_trainer] epoch #154 | Time 73705.98 s 2025-04-04 12:57:22 | [pearl_trainer] epoch #154 | EpochTime 453.67 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -268.801 MetaTest/Average/AverageReturn -268.801 MetaTest/Average/Iteration 154 MetaTest/Average/MaxReturn -241.676 MetaTest/Average/MinReturn -299.344 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 23.0956 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -268.801 MetaTest/__unnamed_task__/AverageReturn -268.801 MetaTest/__unnamed_task__/Iteration 154 MetaTest/__unnamed_task__/MaxReturn -241.676 MetaTest/__unnamed_task__/MinReturn -299.344 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 23.0956 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 350000 ------------------------------------------------- ----------- 2025-04-04 12:58:07 | [pearl_trainer] epoch #155 | Training... 2025-04-04 13:00:52 | [pearl_trainer] epoch #155 | Evaluating... 2025-04-04 13:00:52 | [pearl_trainer] epoch #155 | Sampling for adapation and meta-testing... 2025-04-04 13:04:50 | [pearl_trainer] epoch #155 | Finished meta-testing... 2025-04-04 13:04:50 | [pearl_trainer] epoch #155 | Saving snapshot... 2025-04-04 13:04:51 | [pearl_trainer] epoch #155 | Saved 2025-04-04 13:04:51 | [pearl_trainer] epoch #155 | Time 74154.91 s 2025-04-04 13:04:51 | [pearl_trainer] epoch #155 | EpochTime 448.92 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -303.847 MetaTest/Average/AverageReturn -303.847 MetaTest/Average/Iteration 155 MetaTest/Average/MaxReturn -236.396 MetaTest/Average/MinReturn -363.598 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 45.9335 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -303.847 MetaTest/__unnamed_task__/AverageReturn -303.847 MetaTest/__unnamed_task__/Iteration 155 MetaTest/__unnamed_task__/MaxReturn -236.396 MetaTest/__unnamed_task__/MinReturn -363.598 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 45.9335 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 352000 ------------------------------------------------- ----------- 2025-04-04 13:05:37 | [pearl_trainer] epoch #156 | Training... 2025-04-04 13:08:13 | [pearl_trainer] epoch #156 | Evaluating... 2025-04-04 13:08:13 | [pearl_trainer] epoch #156 | Sampling for adapation and meta-testing... 2025-04-04 13:12:20 | [pearl_trainer] epoch #156 | Finished meta-testing... 2025-04-04 13:12:20 | [pearl_trainer] epoch #156 | Saving snapshot... 2025-04-04 13:12:21 | [pearl_trainer] epoch #156 | Saved 2025-04-04 13:12:21 | [pearl_trainer] epoch #156 | Time 74604.75 s 2025-04-04 13:12:21 | [pearl_trainer] epoch #156 | EpochTime 449.84 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -246.237 MetaTest/Average/AverageReturn -246.237 MetaTest/Average/Iteration 156 MetaTest/Average/MaxReturn -211.86 MetaTest/Average/MinReturn -276.972 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 24.2084 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -246.237 MetaTest/__unnamed_task__/AverageReturn -246.237 MetaTest/__unnamed_task__/Iteration 156 MetaTest/__unnamed_task__/MaxReturn -211.86 MetaTest/__unnamed_task__/MinReturn -276.972 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 24.2084 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 354000 ------------------------------------------------- ----------- 2025-04-04 13:13:05 | [pearl_trainer] epoch #157 | Training... 2025-04-04 13:15:50 | [pearl_trainer] epoch #157 | Evaluating... 2025-04-04 13:15:50 | [pearl_trainer] epoch #157 | Sampling for adapation and meta-testing... 2025-04-04 13:20:17 | [pearl_trainer] epoch #157 | Finished meta-testing... 2025-04-04 13:20:17 | [pearl_trainer] epoch #157 | Saving snapshot... 2025-04-04 13:20:18 | [pearl_trainer] epoch #157 | Saved 2025-04-04 13:20:18 | [pearl_trainer] epoch #157 | Time 75082.09 s 2025-04-04 13:20:18 | [pearl_trainer] epoch #157 | EpochTime 477.34 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -257.011 MetaTest/Average/AverageReturn -257.011 MetaTest/Average/Iteration 157 MetaTest/Average/MaxReturn -195.67 MetaTest/Average/MinReturn -313.048 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.6953 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -257.011 MetaTest/__unnamed_task__/AverageReturn -257.011 MetaTest/__unnamed_task__/Iteration 157 MetaTest/__unnamed_task__/MaxReturn -195.67 MetaTest/__unnamed_task__/MinReturn -313.048 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.6953 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 356000 ------------------------------------------------- ----------- 2025-04-04 13:21:02 | [pearl_trainer] epoch #158 | Training... 2025-04-04 13:23:41 | [pearl_trainer] epoch #158 | Evaluating... 2025-04-04 13:23:41 | [pearl_trainer] epoch #158 | Sampling for adapation and meta-testing... 2025-04-04 13:28:10 | [pearl_trainer] epoch #158 | Finished meta-testing... 2025-04-04 13:28:10 | [pearl_trainer] epoch #158 | Saving snapshot... 2025-04-04 13:28:11 | [pearl_trainer] epoch #158 | Saved 2025-04-04 13:28:11 | [pearl_trainer] epoch #158 | Time 75554.77 s 2025-04-04 13:28:11 | [pearl_trainer] epoch #158 | EpochTime 472.68 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -276.74 MetaTest/Average/AverageReturn -276.74 MetaTest/Average/Iteration 158 MetaTest/Average/MaxReturn -213.43 MetaTest/Average/MinReturn -330.684 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 46.2599 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -276.74 MetaTest/__unnamed_task__/AverageReturn -276.74 MetaTest/__unnamed_task__/Iteration 158 MetaTest/__unnamed_task__/MaxReturn -213.43 MetaTest/__unnamed_task__/MinReturn -330.684 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 46.2599 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 358000 ------------------------------------------------- ----------- 2025-04-04 13:29:00 | [pearl_trainer] epoch #159 | Training... 2025-04-04 13:31:40 | [pearl_trainer] epoch #159 | Evaluating... 2025-04-04 13:31:40 | [pearl_trainer] epoch #159 | Sampling for adapation and meta-testing... 2025-04-04 13:36:17 | [pearl_trainer] epoch #159 | Finished meta-testing... 2025-04-04 13:36:17 | [pearl_trainer] epoch #159 | Saving snapshot... 2025-04-04 13:36:18 | [pearl_trainer] epoch #159 | Saved 2025-04-04 13:36:18 | [pearl_trainer] epoch #159 | Time 76041.63 s 2025-04-04 13:36:18 | [pearl_trainer] epoch #159 | EpochTime 486.86 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -294.785 MetaTest/Average/AverageReturn -294.785 MetaTest/Average/Iteration 159 MetaTest/Average/MaxReturn -274.36 MetaTest/Average/MinReturn -328.455 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 18.6125 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -294.785 MetaTest/__unnamed_task__/AverageReturn -294.785 MetaTest/__unnamed_task__/Iteration 159 MetaTest/__unnamed_task__/MaxReturn -274.36 MetaTest/__unnamed_task__/MinReturn -328.455 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 18.6125 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 360000 ------------------------------------------------- ----------- 2025-04-04 13:37:07 | [pearl_trainer] epoch #160 | Training... 2025-04-04 13:39:48 | [pearl_trainer] epoch #160 | Evaluating... 2025-04-04 13:39:48 | [pearl_trainer] epoch #160 | Sampling for adapation and meta-testing... 2025-04-04 13:44:38 | [pearl_trainer] epoch #160 | Finished meta-testing... 2025-04-04 13:44:38 | [pearl_trainer] epoch #160 | Saving snapshot... 2025-04-04 13:44:39 | [pearl_trainer] epoch #160 | Saved 2025-04-04 13:44:39 | [pearl_trainer] epoch #160 | Time 76542.61 s 2025-04-04 13:44:39 | [pearl_trainer] epoch #160 | EpochTime 500.98 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -275.32 MetaTest/Average/AverageReturn -275.32 MetaTest/Average/Iteration 160 MetaTest/Average/MaxReturn -246.521 MetaTest/Average/MinReturn -322.139 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.383 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -275.32 MetaTest/__unnamed_task__/AverageReturn -275.32 MetaTest/__unnamed_task__/Iteration 160 MetaTest/__unnamed_task__/MaxReturn -246.521 MetaTest/__unnamed_task__/MinReturn -322.139 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.383 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 362000 ------------------------------------------------- ---------- 2025-04-04 13:45:29 | [pearl_trainer] epoch #161 | Training... 2025-04-04 13:48:09 | [pearl_trainer] epoch #161 | Evaluating... 2025-04-04 13:48:09 | [pearl_trainer] epoch #161 | Sampling for adapation and meta-testing... 2025-04-04 13:52:23 | [pearl_trainer] epoch #161 | Finished meta-testing... 2025-04-04 13:52:23 | [pearl_trainer] epoch #161 | Saving snapshot... 2025-04-04 13:52:24 | [pearl_trainer] epoch #161 | Saved 2025-04-04 13:52:24 | [pearl_trainer] epoch #161 | Time 77007.80 s 2025-04-04 13:52:24 | [pearl_trainer] epoch #161 | EpochTime 465.18 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -270.832 MetaTest/Average/AverageReturn -270.832 MetaTest/Average/Iteration 161 MetaTest/Average/MaxReturn -241.56 MetaTest/Average/MinReturn -298.265 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 22.9109 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -270.832 MetaTest/__unnamed_task__/AverageReturn -270.832 MetaTest/__unnamed_task__/Iteration 161 MetaTest/__unnamed_task__/MaxReturn -241.56 MetaTest/__unnamed_task__/MinReturn -298.265 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 22.9109 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 364000 ------------------------------------------------- ----------- 2025-04-04 13:53:14 | [pearl_trainer] epoch #162 | Training... 2025-04-04 13:55:54 | [pearl_trainer] epoch #162 | Evaluating... 2025-04-04 13:55:54 | [pearl_trainer] epoch #162 | Sampling for adapation and meta-testing... 2025-04-04 14:00:01 | [pearl_trainer] epoch #162 | Finished meta-testing... 2025-04-04 14:00:01 | [pearl_trainer] epoch #162 | Saving snapshot... 2025-04-04 14:00:02 | [pearl_trainer] epoch #162 | Saved 2025-04-04 14:00:02 | [pearl_trainer] epoch #162 | Time 77465.85 s 2025-04-04 14:00:02 | [pearl_trainer] epoch #162 | EpochTime 458.05 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -306.917 MetaTest/Average/AverageReturn -306.917 MetaTest/Average/Iteration 162 MetaTest/Average/MaxReturn -227.586 MetaTest/Average/MinReturn -367.016 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 48.2743 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -306.917 MetaTest/__unnamed_task__/AverageReturn -306.917 MetaTest/__unnamed_task__/Iteration 162 MetaTest/__unnamed_task__/MaxReturn -227.586 MetaTest/__unnamed_task__/MinReturn -367.016 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 48.2743 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 366000 ------------------------------------------------- ----------- 2025-04-04 14:00:48 | [pearl_trainer] epoch #163 | Training... 2025-04-04 14:03:47 | [pearl_trainer] epoch #163 | Evaluating... 2025-04-04 14:03:47 | [pearl_trainer] epoch #163 | Sampling for adapation and meta-testing... 2025-04-04 14:08:06 | [pearl_trainer] epoch #163 | Finished meta-testing... 2025-04-04 14:08:06 | [pearl_trainer] epoch #163 | Saving snapshot... 2025-04-04 14:08:07 | [pearl_trainer] epoch #163 | Saved 2025-04-04 14:08:07 | [pearl_trainer] epoch #163 | Time 77950.90 s 2025-04-04 14:08:07 | [pearl_trainer] epoch #163 | EpochTime 485.05 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -270.508 MetaTest/Average/AverageReturn -270.508 MetaTest/Average/Iteration 163 MetaTest/Average/MaxReturn -227.312 MetaTest/Average/MinReturn -372.36 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 52.7141 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -270.508 MetaTest/__unnamed_task__/AverageReturn -270.508 MetaTest/__unnamed_task__/Iteration 163 MetaTest/__unnamed_task__/MaxReturn -227.312 MetaTest/__unnamed_task__/MinReturn -372.36 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 52.7141 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 368000 ------------------------------------------------- ----------- 2025-04-04 14:08:51 | [pearl_trainer] epoch #164 | Training... 2025-04-04 14:11:41 | [pearl_trainer] epoch #164 | Evaluating... 2025-04-04 14:11:41 | [pearl_trainer] epoch #164 | Sampling for adapation and meta-testing... 2025-04-04 14:15:52 | [pearl_trainer] epoch #164 | Finished meta-testing... 2025-04-04 14:15:52 | [pearl_trainer] epoch #164 | Saving snapshot... 2025-04-04 14:15:53 | [pearl_trainer] epoch #164 | Saved 2025-04-04 14:15:53 | [pearl_trainer] epoch #164 | Time 78417.10 s 2025-04-04 14:15:53 | [pearl_trainer] epoch #164 | EpochTime 466.20 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -259.96 MetaTest/Average/AverageReturn -259.96 MetaTest/Average/Iteration 164 MetaTest/Average/MaxReturn -232.054 MetaTest/Average/MinReturn -271.513 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 14.4039 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -259.96 MetaTest/__unnamed_task__/AverageReturn -259.96 MetaTest/__unnamed_task__/Iteration 164 MetaTest/__unnamed_task__/MaxReturn -232.054 MetaTest/__unnamed_task__/MinReturn -271.513 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 14.4039 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 370000 ------------------------------------------------- ----------- 2025-04-04 14:16:42 | [pearl_trainer] epoch #165 | Training... 2025-04-04 14:19:22 | [pearl_trainer] epoch #165 | Evaluating... 2025-04-04 14:19:22 | [pearl_trainer] epoch #165 | Sampling for adapation and meta-testing... 2025-04-04 14:24:08 | [pearl_trainer] epoch #165 | Finished meta-testing... 2025-04-04 14:24:08 | [pearl_trainer] epoch #165 | Saving snapshot... 2025-04-04 14:24:09 | [pearl_trainer] epoch #165 | Saved 2025-04-04 14:24:09 | [pearl_trainer] epoch #165 | Time 78912.43 s 2025-04-04 14:24:09 | [pearl_trainer] epoch #165 | EpochTime 495.32 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -213.36 MetaTest/Average/AverageReturn -213.36 MetaTest/Average/Iteration 165 MetaTest/Average/MaxReturn -114.317 MetaTest/Average/MinReturn -302.399 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 75.6007 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -213.36 MetaTest/__unnamed_task__/AverageReturn -213.36 MetaTest/__unnamed_task__/Iteration 165 MetaTest/__unnamed_task__/MaxReturn -114.317 MetaTest/__unnamed_task__/MinReturn -302.399 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 75.6007 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 372000 ------------------------------------------------- ----------- 2025-04-04 14:24:54 | [pearl_trainer] epoch #166 | Training... 2025-04-04 14:27:54 | [pearl_trainer] epoch #166 | Evaluating... 2025-04-04 14:27:54 | [pearl_trainer] epoch #166 | Sampling for adapation and meta-testing... 2025-04-04 14:32:33 | [pearl_trainer] epoch #166 | Finished meta-testing... 2025-04-04 14:32:33 | [pearl_trainer] epoch #166 | Saving snapshot... 2025-04-04 14:32:34 | [pearl_trainer] epoch #166 | Saved 2025-04-04 14:32:34 | [pearl_trainer] epoch #166 | Time 79417.45 s 2025-04-04 14:32:34 | [pearl_trainer] epoch #166 | EpochTime 505.02 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -234.408 MetaTest/Average/AverageReturn -234.408 MetaTest/Average/Iteration 166 MetaTest/Average/MaxReturn -160.557 MetaTest/Average/MinReturn -322.935 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 55.2174 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -234.408 MetaTest/__unnamed_task__/AverageReturn -234.408 MetaTest/__unnamed_task__/Iteration 166 MetaTest/__unnamed_task__/MaxReturn -160.557 MetaTest/__unnamed_task__/MinReturn -322.935 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 55.2174 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 374000 ------------------------------------------------- ----------- 2025-04-04 14:33:20 | [pearl_trainer] epoch #167 | Training... 2025-04-04 14:36:04 | [pearl_trainer] epoch #167 | Evaluating... 2025-04-04 14:36:04 | [pearl_trainer] epoch #167 | Sampling for adapation and meta-testing... 2025-04-04 14:40:03 | [pearl_trainer] epoch #167 | Finished meta-testing... 2025-04-04 14:40:03 | [pearl_trainer] epoch #167 | Saving snapshot... 2025-04-04 14:40:05 | [pearl_trainer] epoch #167 | Saved 2025-04-04 14:40:05 | [pearl_trainer] epoch #167 | Time 79868.23 s 2025-04-04 14:40:05 | [pearl_trainer] epoch #167 | EpochTime 450.78 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -245.963 MetaTest/Average/AverageReturn -245.963 MetaTest/Average/Iteration 167 MetaTest/Average/MaxReturn -226.264 MetaTest/Average/MinReturn -272.923 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 16.136 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -245.963 MetaTest/__unnamed_task__/AverageReturn -245.963 MetaTest/__unnamed_task__/Iteration 167 MetaTest/__unnamed_task__/MaxReturn -226.264 MetaTest/__unnamed_task__/MinReturn -272.923 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 16.136 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 376000 ------------------------------------------------- ---------- 2025-04-04 14:40:51 | [pearl_trainer] epoch #168 | Training... 2025-04-04 14:43:31 | [pearl_trainer] epoch #168 | Evaluating... 2025-04-04 14:43:31 | [pearl_trainer] epoch #168 | Sampling for adapation and meta-testing... 2025-04-04 14:47:23 | [pearl_trainer] epoch #168 | Finished meta-testing... 2025-04-04 14:47:23 | [pearl_trainer] epoch #168 | Saving snapshot... 2025-04-04 14:47:24 | [pearl_trainer] epoch #168 | Saved 2025-04-04 14:47:24 | [pearl_trainer] epoch #168 | Time 80307.88 s 2025-04-04 14:47:24 | [pearl_trainer] epoch #168 | EpochTime 439.64 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -225.876 MetaTest/Average/AverageReturn -225.876 MetaTest/Average/Iteration 168 MetaTest/Average/MaxReturn -209.209 MetaTest/Average/MinReturn -241.347 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 11.4217 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -225.876 MetaTest/__unnamed_task__/AverageReturn -225.876 MetaTest/__unnamed_task__/Iteration 168 MetaTest/__unnamed_task__/MaxReturn -209.209 MetaTest/__unnamed_task__/MinReturn -241.347 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 11.4217 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 378000 ------------------------------------------------- ----------- 2025-04-04 14:48:11 | [pearl_trainer] epoch #169 | Training... 2025-04-04 14:51:01 | [pearl_trainer] epoch #169 | Evaluating... 2025-04-04 14:51:01 | [pearl_trainer] epoch #169 | Sampling for adapation and meta-testing... 2025-04-04 14:55:14 | [pearl_trainer] epoch #169 | Finished meta-testing... 2025-04-04 14:55:14 | [pearl_trainer] epoch #169 | Saving snapshot... 2025-04-04 14:55:16 | [pearl_trainer] epoch #169 | Saved 2025-04-04 14:55:16 | [pearl_trainer] epoch #169 | Time 80779.46 s 2025-04-04 14:55:16 | [pearl_trainer] epoch #169 | EpochTime 471.58 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -232.873 MetaTest/Average/AverageReturn -232.873 MetaTest/Average/Iteration 169 MetaTest/Average/MaxReturn -217.966 MetaTest/Average/MinReturn -253.456 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 15.5612 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -232.873 MetaTest/__unnamed_task__/AverageReturn -232.873 MetaTest/__unnamed_task__/Iteration 169 MetaTest/__unnamed_task__/MaxReturn -217.966 MetaTest/__unnamed_task__/MinReturn -253.456 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 15.5612 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 380000 ------------------------------------------------- ----------- 2025-04-04 14:55:59 | [pearl_trainer] epoch #170 | Training... 2025-04-04 14:58:42 | [pearl_trainer] epoch #170 | Evaluating... 2025-04-04 14:58:42 | [pearl_trainer] epoch #170 | Sampling for adapation and meta-testing... 2025-04-04 15:02:55 | [pearl_trainer] epoch #170 | Finished meta-testing... 2025-04-04 15:02:55 | [pearl_trainer] epoch #170 | Saving snapshot... 2025-04-04 15:02:56 | [pearl_trainer] epoch #170 | Saved 2025-04-04 15:02:56 | [pearl_trainer] epoch #170 | Time 81239.51 s 2025-04-04 15:02:56 | [pearl_trainer] epoch #170 | EpochTime 460.05 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -219.709 MetaTest/Average/AverageReturn -219.709 MetaTest/Average/Iteration 170 MetaTest/Average/MaxReturn -170.661 MetaTest/Average/MinReturn -252.436 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 29.6258 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -219.709 MetaTest/__unnamed_task__/AverageReturn -219.709 MetaTest/__unnamed_task__/Iteration 170 MetaTest/__unnamed_task__/MaxReturn -170.661 MetaTest/__unnamed_task__/MinReturn -252.436 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 29.6258 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 382000 ------------------------------------------------- ----------- 2025-04-04 15:03:46 | [pearl_trainer] epoch #171 | Training... 2025-04-04 15:06:23 | [pearl_trainer] epoch #171 | Evaluating... 2025-04-04 15:06:23 | [pearl_trainer] epoch #171 | Sampling for adapation and meta-testing... 2025-04-04 15:10:50 | [pearl_trainer] epoch #171 | Finished meta-testing... 2025-04-04 15:10:50 | [pearl_trainer] epoch #171 | Saving snapshot... 2025-04-04 15:10:51 | [pearl_trainer] epoch #171 | Saved 2025-04-04 15:10:51 | [pearl_trainer] epoch #171 | Time 81715.01 s 2025-04-04 15:10:51 | [pearl_trainer] epoch #171 | EpochTime 475.49 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -240.579 MetaTest/Average/AverageReturn -240.579 MetaTest/Average/Iteration 171 MetaTest/Average/MaxReturn -203.472 MetaTest/Average/MinReturn -279.054 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 29.298 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -240.579 MetaTest/__unnamed_task__/AverageReturn -240.579 MetaTest/__unnamed_task__/Iteration 171 MetaTest/__unnamed_task__/MaxReturn -203.472 MetaTest/__unnamed_task__/MinReturn -279.054 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 29.298 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 384000 ------------------------------------------------- ---------- 2025-04-04 15:11:37 | [pearl_trainer] epoch #172 | Training... 2025-04-04 15:14:15 | [pearl_trainer] epoch #172 | Evaluating... 2025-04-04 15:14:15 | [pearl_trainer] epoch #172 | Sampling for adapation and meta-testing... 2025-04-04 15:18:44 | [pearl_trainer] epoch #172 | Finished meta-testing... 2025-04-04 15:18:44 | [pearl_trainer] epoch #172 | Saving snapshot... 2025-04-04 15:18:45 | [pearl_trainer] epoch #172 | Saved 2025-04-04 15:18:45 | [pearl_trainer] epoch #172 | Time 82188.66 s 2025-04-04 15:18:45 | [pearl_trainer] epoch #172 | EpochTime 473.65 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -220.525 MetaTest/Average/AverageReturn -220.525 MetaTest/Average/Iteration 172 MetaTest/Average/MaxReturn -186.427 MetaTest/Average/MinReturn -263.038 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 25.7828 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -220.525 MetaTest/__unnamed_task__/AverageReturn -220.525 MetaTest/__unnamed_task__/Iteration 172 MetaTest/__unnamed_task__/MaxReturn -186.427 MetaTest/__unnamed_task__/MinReturn -263.038 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 25.7828 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 386000 ------------------------------------------------- ----------- 2025-04-04 15:19:29 | [pearl_trainer] epoch #173 | Training... 2025-04-04 15:22:09 | [pearl_trainer] epoch #173 | Evaluating... 2025-04-04 15:22:09 | [pearl_trainer] epoch #173 | Sampling for adapation and meta-testing... 2025-04-04 15:26:37 | [pearl_trainer] epoch #173 | Finished meta-testing... 2025-04-04 15:26:37 | [pearl_trainer] epoch #173 | Saving snapshot... 2025-04-04 15:26:38 | [pearl_trainer] epoch #173 | Saved 2025-04-04 15:26:38 | [pearl_trainer] epoch #173 | Time 82661.65 s 2025-04-04 15:26:38 | [pearl_trainer] epoch #173 | EpochTime 472.99 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -249.729 MetaTest/Average/AverageReturn -249.729 MetaTest/Average/Iteration 173 MetaTest/Average/MaxReturn -204.035 MetaTest/Average/MinReturn -308.839 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 40.2081 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -249.729 MetaTest/__unnamed_task__/AverageReturn -249.729 MetaTest/__unnamed_task__/Iteration 173 MetaTest/__unnamed_task__/MaxReturn -204.035 MetaTest/__unnamed_task__/MinReturn -308.839 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 40.2081 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 388000 ------------------------------------------------- ----------- 2025-04-04 15:27:25 | [pearl_trainer] epoch #174 | Training... 2025-04-04 15:30:04 | [pearl_trainer] epoch #174 | Evaluating... 2025-04-04 15:30:04 | [pearl_trainer] epoch #174 | Sampling for adapation and meta-testing... 2025-04-04 15:34:43 | [pearl_trainer] epoch #174 | Finished meta-testing... 2025-04-04 15:34:43 | [pearl_trainer] epoch #174 | Saving snapshot... 2025-04-04 15:34:44 | [pearl_trainer] epoch #174 | Saved 2025-04-04 15:34:44 | [pearl_trainer] epoch #174 | Time 83148.13 s 2025-04-04 15:34:44 | [pearl_trainer] epoch #174 | EpochTime 486.47 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -254.286 MetaTest/Average/AverageReturn -254.286 MetaTest/Average/Iteration 174 MetaTest/Average/MaxReturn -206.806 MetaTest/Average/MinReturn -273.2 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 24.7706 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -254.286 MetaTest/__unnamed_task__/AverageReturn -254.286 MetaTest/__unnamed_task__/Iteration 174 MetaTest/__unnamed_task__/MaxReturn -206.806 MetaTest/__unnamed_task__/MinReturn -273.2 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 24.7706 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 390000 ------------------------------------------------- ----------- 2025-04-04 15:35:35 | [pearl_trainer] epoch #175 | Training... 2025-04-04 15:38:15 | [pearl_trainer] epoch #175 | Evaluating... 2025-04-04 15:38:15 | [pearl_trainer] epoch #175 | Sampling for adapation and meta-testing... 2025-04-04 15:42:46 | [pearl_trainer] epoch #175 | Finished meta-testing... 2025-04-04 15:42:46 | [pearl_trainer] epoch #175 | Saving snapshot... 2025-04-04 15:42:48 | [pearl_trainer] epoch #175 | Saved 2025-04-04 15:42:48 | [pearl_trainer] epoch #175 | Time 83631.36 s 2025-04-04 15:42:48 | [pearl_trainer] epoch #175 | EpochTime 483.22 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -220.356 MetaTest/Average/AverageReturn -220.356 MetaTest/Average/Iteration 175 MetaTest/Average/MaxReturn -183.339 MetaTest/Average/MinReturn -283.957 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.5382 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -220.356 MetaTest/__unnamed_task__/AverageReturn -220.356 MetaTest/__unnamed_task__/Iteration 175 MetaTest/__unnamed_task__/MaxReturn -183.339 MetaTest/__unnamed_task__/MinReturn -283.957 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.5382 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 392000 ------------------------------------------------- ----------- 2025-04-04 15:43:37 | [pearl_trainer] epoch #176 | Training... 2025-04-04 15:46:20 | [pearl_trainer] epoch #176 | Evaluating... 2025-04-04 15:46:20 | [pearl_trainer] epoch #176 | Sampling for adapation and meta-testing... 2025-04-04 15:50:50 | [pearl_trainer] epoch #176 | Finished meta-testing... 2025-04-04 15:50:50 | [pearl_trainer] epoch #176 | Saving snapshot... 2025-04-04 15:50:51 | [pearl_trainer] epoch #176 | Saved 2025-04-04 15:50:51 | [pearl_trainer] epoch #176 | Time 84114.34 s 2025-04-04 15:50:51 | [pearl_trainer] epoch #176 | EpochTime 482.98 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -207.789 MetaTest/Average/AverageReturn -207.789 MetaTest/Average/Iteration 176 MetaTest/Average/MaxReturn -145.564 MetaTest/Average/MinReturn -258.831 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 41.6581 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -207.789 MetaTest/__unnamed_task__/AverageReturn -207.789 MetaTest/__unnamed_task__/Iteration 176 MetaTest/__unnamed_task__/MaxReturn -145.564 MetaTest/__unnamed_task__/MinReturn -258.831 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 41.6581 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 394000 ------------------------------------------------- ----------- 2025-04-04 15:51:36 | [pearl_trainer] epoch #177 | Training... 2025-04-04 15:54:11 | [pearl_trainer] epoch #177 | Evaluating... 2025-04-04 15:54:11 | [pearl_trainer] epoch #177 | Sampling for adapation and meta-testing... 2025-04-04 15:58:40 | [pearl_trainer] epoch #177 | Finished meta-testing... 2025-04-04 15:58:40 | [pearl_trainer] epoch #177 | Saving snapshot... 2025-04-04 15:58:42 | [pearl_trainer] epoch #177 | Saved 2025-04-04 15:58:42 | [pearl_trainer] epoch #177 | Time 84585.37 s 2025-04-04 15:58:42 | [pearl_trainer] epoch #177 | EpochTime 471.03 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -215.164 MetaTest/Average/AverageReturn -215.164 MetaTest/Average/Iteration 177 MetaTest/Average/MaxReturn -144.363 MetaTest/Average/MinReturn -262.864 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 45.0908 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -215.164 MetaTest/__unnamed_task__/AverageReturn -215.164 MetaTest/__unnamed_task__/Iteration 177 MetaTest/__unnamed_task__/MaxReturn -144.363 MetaTest/__unnamed_task__/MinReturn -262.864 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 45.0908 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 396000 ------------------------------------------------- ----------- 2025-04-04 15:59:28 | [pearl_trainer] epoch #178 | Training... 2025-04-04 16:02:19 | [pearl_trainer] epoch #178 | Evaluating... 2025-04-04 16:02:19 | [pearl_trainer] epoch #178 | Sampling for adapation and meta-testing... 2025-04-04 16:06:49 | [pearl_trainer] epoch #178 | Finished meta-testing... 2025-04-04 16:06:49 | [pearl_trainer] epoch #178 | Saving snapshot... 2025-04-04 16:06:50 | [pearl_trainer] epoch #178 | Saved 2025-04-04 16:06:50 | [pearl_trainer] epoch #178 | Time 85073.54 s 2025-04-04 16:06:50 | [pearl_trainer] epoch #178 | EpochTime 488.16 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -236.318 MetaTest/Average/AverageReturn -236.318 MetaTest/Average/Iteration 178 MetaTest/Average/MaxReturn -207.014 MetaTest/Average/MinReturn -338.422 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 51.155 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -236.318 MetaTest/__unnamed_task__/AverageReturn -236.318 MetaTest/__unnamed_task__/Iteration 178 MetaTest/__unnamed_task__/MaxReturn -207.014 MetaTest/__unnamed_task__/MinReturn -338.422 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 51.155 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 398000 ------------------------------------------------- ---------- 2025-04-04 16:07:36 | [pearl_trainer] epoch #179 | Training... 2025-04-04 16:10:16 | [pearl_trainer] epoch #179 | Evaluating... 2025-04-04 16:10:16 | [pearl_trainer] epoch #179 | Sampling for adapation and meta-testing... 2025-04-04 16:14:45 | [pearl_trainer] epoch #179 | Finished meta-testing... 2025-04-04 16:14:45 | [pearl_trainer] epoch #179 | Saving snapshot... 2025-04-04 16:14:46 | [pearl_trainer] epoch #179 | Saved 2025-04-04 16:14:46 | [pearl_trainer] epoch #179 | Time 85549.85 s 2025-04-04 16:14:46 | [pearl_trainer] epoch #179 | EpochTime 476.31 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -250.335 MetaTest/Average/AverageReturn -250.335 MetaTest/Average/Iteration 179 MetaTest/Average/MaxReturn -203.772 MetaTest/Average/MinReturn -305.485 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.361 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -250.335 MetaTest/__unnamed_task__/AverageReturn -250.335 MetaTest/__unnamed_task__/Iteration 179 MetaTest/__unnamed_task__/MaxReturn -203.772 MetaTest/__unnamed_task__/MinReturn -305.485 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.361 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 400000 ------------------------------------------------- ---------- 2025-04-04 16:15:35 | [pearl_trainer] epoch #180 | Training... 2025-04-04 16:18:19 | [pearl_trainer] epoch #180 | Evaluating... 2025-04-04 16:18:19 | [pearl_trainer] epoch #180 | Sampling for adapation and meta-testing... 2025-04-04 16:22:52 | [pearl_trainer] epoch #180 | Finished meta-testing... 2025-04-04 16:22:52 | [pearl_trainer] epoch #180 | Saving snapshot... 2025-04-04 16:22:53 | [pearl_trainer] epoch #180 | Saved 2025-04-04 16:22:53 | [pearl_trainer] epoch #180 | Time 86036.60 s 2025-04-04 16:22:53 | [pearl_trainer] epoch #180 | EpochTime 486.75 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -222.426 MetaTest/Average/AverageReturn -222.426 MetaTest/Average/Iteration 180 MetaTest/Average/MaxReturn -141.657 MetaTest/Average/MinReturn -282.84 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 52.8464 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -222.426 MetaTest/__unnamed_task__/AverageReturn -222.426 MetaTest/__unnamed_task__/Iteration 180 MetaTest/__unnamed_task__/MaxReturn -141.657 MetaTest/__unnamed_task__/MinReturn -282.84 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 52.8464 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 402000 ------------------------------------------------- ----------- 2025-04-04 16:23:43 | [pearl_trainer] epoch #181 | Training... 2025-04-04 16:26:18 | [pearl_trainer] epoch #181 | Evaluating... 2025-04-04 16:26:18 | [pearl_trainer] epoch #181 | Sampling for adapation and meta-testing... 2025-04-04 16:31:00 | [pearl_trainer] epoch #181 | Finished meta-testing... 2025-04-04 16:31:00 | [pearl_trainer] epoch #181 | Saving snapshot... 2025-04-04 16:31:02 | [pearl_trainer] epoch #181 | Saved 2025-04-04 16:31:02 | [pearl_trainer] epoch #181 | Time 86525.46 s 2025-04-04 16:31:02 | [pearl_trainer] epoch #181 | EpochTime 488.86 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -214.464 MetaTest/Average/AverageReturn -214.464 MetaTest/Average/Iteration 181 MetaTest/Average/MaxReturn -170.716 MetaTest/Average/MinReturn -305.012 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 46.6891 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -214.464 MetaTest/__unnamed_task__/AverageReturn -214.464 MetaTest/__unnamed_task__/Iteration 181 MetaTest/__unnamed_task__/MaxReturn -170.716 MetaTest/__unnamed_task__/MinReturn -305.012 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 46.6891 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 404000 ------------------------------------------------- ----------- 2025-04-04 16:31:50 | [pearl_trainer] epoch #182 | Training... 2025-04-04 16:34:26 | [pearl_trainer] epoch #182 | Evaluating... 2025-04-04 16:34:26 | [pearl_trainer] epoch #182 | Sampling for adapation and meta-testing... 2025-04-04 16:39:10 | [pearl_trainer] epoch #182 | Finished meta-testing... 2025-04-04 16:39:10 | [pearl_trainer] epoch #182 | Saving snapshot... 2025-04-04 16:39:12 | [pearl_trainer] epoch #182 | Saved 2025-04-04 16:39:12 | [pearl_trainer] epoch #182 | Time 87015.26 s 2025-04-04 16:39:12 | [pearl_trainer] epoch #182 | EpochTime 489.80 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -209.488 MetaTest/Average/AverageReturn -209.488 MetaTest/Average/Iteration 182 MetaTest/Average/MaxReturn -191.355 MetaTest/Average/MinReturn -223.239 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 10.2424 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -209.488 MetaTest/__unnamed_task__/AverageReturn -209.488 MetaTest/__unnamed_task__/Iteration 182 MetaTest/__unnamed_task__/MaxReturn -191.355 MetaTest/__unnamed_task__/MinReturn -223.239 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 10.2424 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 406000 ------------------------------------------------- ----------- 2025-04-04 16:40:00 | [pearl_trainer] epoch #183 | Training... 2025-04-04 16:42:31 | [pearl_trainer] epoch #183 | Evaluating... 2025-04-04 16:42:31 | [pearl_trainer] epoch #183 | Sampling for adapation and meta-testing... 2025-04-04 16:47:01 | [pearl_trainer] epoch #183 | Finished meta-testing... 2025-04-04 16:47:01 | [pearl_trainer] epoch #183 | Saving snapshot... 2025-04-04 16:47:02 | [pearl_trainer] epoch #183 | Saved 2025-04-04 16:47:02 | [pearl_trainer] epoch #183 | Time 87486.12 s 2025-04-04 16:47:02 | [pearl_trainer] epoch #183 | EpochTime 470.86 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -195.041 MetaTest/Average/AverageReturn -195.041 MetaTest/Average/Iteration 183 MetaTest/Average/MaxReturn -159.082 MetaTest/Average/MinReturn -216.577 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 19.9021 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -195.041 MetaTest/__unnamed_task__/AverageReturn -195.041 MetaTest/__unnamed_task__/Iteration 183 MetaTest/__unnamed_task__/MaxReturn -159.082 MetaTest/__unnamed_task__/MinReturn -216.577 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 19.9021 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 408000 ------------------------------------------------- ----------- 2025-04-04 16:47:53 | [pearl_trainer] epoch #184 | Training... 2025-04-04 16:50:35 | [pearl_trainer] epoch #184 | Evaluating... 2025-04-04 16:50:35 | [pearl_trainer] epoch #184 | Sampling for adapation and meta-testing... 2025-04-04 16:55:16 | [pearl_trainer] epoch #184 | Finished meta-testing... 2025-04-04 16:55:16 | [pearl_trainer] epoch #184 | Saving snapshot... 2025-04-04 16:55:17 | [pearl_trainer] epoch #184 | Saved 2025-04-04 16:55:17 | [pearl_trainer] epoch #184 | Time 87980.65 s 2025-04-04 16:55:17 | [pearl_trainer] epoch #184 | EpochTime 494.52 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -239.754 MetaTest/Average/AverageReturn -239.754 MetaTest/Average/Iteration 184 MetaTest/Average/MaxReturn -181.675 MetaTest/Average/MinReturn -322.755 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 56.6655 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -239.754 MetaTest/__unnamed_task__/AverageReturn -239.754 MetaTest/__unnamed_task__/Iteration 184 MetaTest/__unnamed_task__/MaxReturn -181.675 MetaTest/__unnamed_task__/MinReturn -322.755 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 56.6655 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 410000 ------------------------------------------------- ----------- 2025-04-04 16:56:09 | [pearl_trainer] epoch #185 | Training... 2025-04-04 16:58:49 | [pearl_trainer] epoch #185 | Evaluating... 2025-04-04 16:58:49 | [pearl_trainer] epoch #185 | Sampling for adapation and meta-testing... 2025-04-04 17:03:16 | [pearl_trainer] epoch #185 | Finished meta-testing... 2025-04-04 17:03:16 | [pearl_trainer] epoch #185 | Saving snapshot... 2025-04-04 17:03:17 | [pearl_trainer] epoch #185 | Saved 2025-04-04 17:03:17 | [pearl_trainer] epoch #185 | Time 88460.91 s 2025-04-04 17:03:17 | [pearl_trainer] epoch #185 | EpochTime 480.26 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -272.763 MetaTest/Average/AverageReturn -272.763 MetaTest/Average/Iteration 185 MetaTest/Average/MaxReturn -113.446 MetaTest/Average/MinReturn -355.14 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 86.7627 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -272.763 MetaTest/__unnamed_task__/AverageReturn -272.763 MetaTest/__unnamed_task__/Iteration 185 MetaTest/__unnamed_task__/MaxReturn -113.446 MetaTest/__unnamed_task__/MinReturn -355.14 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 86.7627 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 412000 ------------------------------------------------- ----------- 2025-04-04 17:04:07 | [pearl_trainer] epoch #186 | Training... 2025-04-04 17:06:52 | [pearl_trainer] epoch #186 | Evaluating... 2025-04-04 17:06:52 | [pearl_trainer] epoch #186 | Sampling for adapation and meta-testing... 2025-04-04 17:11:11 | [pearl_trainer] epoch #186 | Finished meta-testing... 2025-04-04 17:11:11 | [pearl_trainer] epoch #186 | Saving snapshot... 2025-04-04 17:11:12 | [pearl_trainer] epoch #186 | Saved 2025-04-04 17:11:12 | [pearl_trainer] epoch #186 | Time 88936.09 s 2025-04-04 17:11:12 | [pearl_trainer] epoch #186 | EpochTime 475.18 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -272.488 MetaTest/Average/AverageReturn -272.488 MetaTest/Average/Iteration 186 MetaTest/Average/MaxReturn -173.085 MetaTest/Average/MinReturn -338.81 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 66.619 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -272.488 MetaTest/__unnamed_task__/AverageReturn -272.488 MetaTest/__unnamed_task__/Iteration 186 MetaTest/__unnamed_task__/MaxReturn -173.085 MetaTest/__unnamed_task__/MinReturn -338.81 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 66.619 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 414000 ------------------------------------------------- ---------- 2025-04-04 17:12:02 | [pearl_trainer] epoch #187 | Training... 2025-04-04 17:14:41 | [pearl_trainer] epoch #187 | Evaluating... 2025-04-04 17:14:41 | [pearl_trainer] epoch #187 | Sampling for adapation and meta-testing... 2025-04-04 17:18:56 | [pearl_trainer] epoch #187 | Finished meta-testing... 2025-04-04 17:18:56 | [pearl_trainer] epoch #187 | Saving snapshot... 2025-04-04 17:18:57 | [pearl_trainer] epoch #187 | Saved 2025-04-04 17:18:57 | [pearl_trainer] epoch #187 | Time 89401.17 s 2025-04-04 17:18:57 | [pearl_trainer] epoch #187 | EpochTime 465.07 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -250.588 MetaTest/Average/AverageReturn -250.588 MetaTest/Average/Iteration 187 MetaTest/Average/MaxReturn -227.761 MetaTest/Average/MinReturn -280.804 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 20.3768 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -250.588 MetaTest/__unnamed_task__/AverageReturn -250.588 MetaTest/__unnamed_task__/Iteration 187 MetaTest/__unnamed_task__/MaxReturn -227.761 MetaTest/__unnamed_task__/MinReturn -280.804 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 20.3768 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 416000 ------------------------------------------------- ----------- 2025-04-04 17:19:40 | [pearl_trainer] epoch #188 | Training... 2025-04-04 17:22:24 | [pearl_trainer] epoch #188 | Evaluating... 2025-04-04 17:22:24 | [pearl_trainer] epoch #188 | Sampling for adapation and meta-testing... 2025-04-04 17:26:34 | [pearl_trainer] epoch #188 | Finished meta-testing... 2025-04-04 17:26:34 | [pearl_trainer] epoch #188 | Saving snapshot... 2025-04-04 17:26:35 | [pearl_trainer] epoch #188 | Saved 2025-04-04 17:26:35 | [pearl_trainer] epoch #188 | Time 89858.93 s 2025-04-04 17:26:35 | [pearl_trainer] epoch #188 | EpochTime 457.76 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -286.657 MetaTest/Average/AverageReturn -286.657 MetaTest/Average/Iteration 188 MetaTest/Average/MaxReturn -254.745 MetaTest/Average/MinReturn -333.937 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 29.4686 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -286.657 MetaTest/__unnamed_task__/AverageReturn -286.657 MetaTest/__unnamed_task__/Iteration 188 MetaTest/__unnamed_task__/MaxReturn -254.745 MetaTest/__unnamed_task__/MinReturn -333.937 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 29.4686 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 418000 ------------------------------------------------- ----------- 2025-04-04 17:27:19 | [pearl_trainer] epoch #189 | Training... 2025-04-04 17:30:00 | [pearl_trainer] epoch #189 | Evaluating... 2025-04-04 17:30:00 | [pearl_trainer] epoch #189 | Sampling for adapation and meta-testing... 2025-04-04 17:34:08 | [pearl_trainer] epoch #189 | Finished meta-testing... 2025-04-04 17:34:08 | [pearl_trainer] epoch #189 | Saving snapshot... 2025-04-04 17:34:09 | [pearl_trainer] epoch #189 | Saved 2025-04-04 17:34:09 | [pearl_trainer] epoch #189 | Time 90312.74 s 2025-04-04 17:34:09 | [pearl_trainer] epoch #189 | EpochTime 453.80 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -262.368 MetaTest/Average/AverageReturn -262.368 MetaTest/Average/Iteration 189 MetaTest/Average/MaxReturn -219.224 MetaTest/Average/MinReturn -331.254 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 38.4889 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -262.368 MetaTest/__unnamed_task__/AverageReturn -262.368 MetaTest/__unnamed_task__/Iteration 189 MetaTest/__unnamed_task__/MaxReturn -219.224 MetaTest/__unnamed_task__/MinReturn -331.254 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 38.4889 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 420000 ------------------------------------------------- ----------- 2025-04-04 17:34:54 | [pearl_trainer] epoch #190 | Training... 2025-04-04 17:37:34 | [pearl_trainer] epoch #190 | Evaluating... 2025-04-04 17:37:34 | [pearl_trainer] epoch #190 | Sampling for adapation and meta-testing... 2025-04-04 17:41:40 | [pearl_trainer] epoch #190 | Finished meta-testing... 2025-04-04 17:41:40 | [pearl_trainer] epoch #190 | Saving snapshot... 2025-04-04 17:41:42 | [pearl_trainer] epoch #190 | Saved 2025-04-04 17:41:42 | [pearl_trainer] epoch #190 | Time 90765.42 s 2025-04-04 17:41:42 | [pearl_trainer] epoch #190 | EpochTime 452.68 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -295.712 MetaTest/Average/AverageReturn -295.712 MetaTest/Average/Iteration 190 MetaTest/Average/MaxReturn -225.661 MetaTest/Average/MinReturn -366.816 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 52.0192 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -295.712 MetaTest/__unnamed_task__/AverageReturn -295.712 MetaTest/__unnamed_task__/Iteration 190 MetaTest/__unnamed_task__/MaxReturn -225.661 MetaTest/__unnamed_task__/MinReturn -366.816 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 52.0192 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 422000 ------------------------------------------------- ----------- 2025-04-04 17:42:25 | [pearl_trainer] epoch #191 | Training... 2025-04-04 17:45:09 | [pearl_trainer] epoch #191 | Evaluating... 2025-04-04 17:45:09 | [pearl_trainer] epoch #191 | Sampling for adapation and meta-testing... 2025-04-04 17:49:43 | [pearl_trainer] epoch #191 | Finished meta-testing... 2025-04-04 17:49:43 | [pearl_trainer] epoch #191 | Saving snapshot... 2025-04-04 17:49:44 | [pearl_trainer] epoch #191 | Saved 2025-04-04 17:49:44 | [pearl_trainer] epoch #191 | Time 91247.51 s 2025-04-04 17:49:44 | [pearl_trainer] epoch #191 | EpochTime 482.10 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -287.796 MetaTest/Average/AverageReturn -287.796 MetaTest/Average/Iteration 191 MetaTest/Average/MaxReturn -252.475 MetaTest/Average/MinReturn -337.235 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 35.7098 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -287.796 MetaTest/__unnamed_task__/AverageReturn -287.796 MetaTest/__unnamed_task__/Iteration 191 MetaTest/__unnamed_task__/MaxReturn -252.475 MetaTest/__unnamed_task__/MinReturn -337.235 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 35.7098 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 424000 ------------------------------------------------- ----------- 2025-04-04 17:50:32 | [pearl_trainer] epoch #192 | Training... 2025-04-04 17:53:11 | [pearl_trainer] epoch #192 | Evaluating... 2025-04-04 17:53:11 | [pearl_trainer] epoch #192 | Sampling for adapation and meta-testing... 2025-04-04 17:57:24 | [pearl_trainer] epoch #192 | Finished meta-testing... 2025-04-04 17:57:24 | [pearl_trainer] epoch #192 | Saving snapshot... 2025-04-04 17:57:25 | [pearl_trainer] epoch #192 | Saved 2025-04-04 17:57:25 | [pearl_trainer] epoch #192 | Time 91709.14 s 2025-04-04 17:57:25 | [pearl_trainer] epoch #192 | EpochTime 461.62 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -298.327 MetaTest/Average/AverageReturn -298.327 MetaTest/Average/Iteration 192 MetaTest/Average/MaxReturn -268.278 MetaTest/Average/MinReturn -339.532 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 30.8737 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -298.327 MetaTest/__unnamed_task__/AverageReturn -298.327 MetaTest/__unnamed_task__/Iteration 192 MetaTest/__unnamed_task__/MaxReturn -268.278 MetaTest/__unnamed_task__/MinReturn -339.532 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 30.8737 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 426000 ------------------------------------------------- ----------- 2025-04-04 17:58:12 | [pearl_trainer] epoch #193 | Training... 2025-04-04 18:01:14 | [pearl_trainer] epoch #193 | Evaluating... 2025-04-04 18:01:14 | [pearl_trainer] epoch #193 | Sampling for adapation and meta-testing... 2025-04-04 18:05:33 | [pearl_trainer] epoch #193 | Finished meta-testing... 2025-04-04 18:05:33 | [pearl_trainer] epoch #193 | Saving snapshot... 2025-04-04 18:05:34 | [pearl_trainer] epoch #193 | Saved 2025-04-04 18:05:34 | [pearl_trainer] epoch #193 | Time 92197.76 s 2025-04-04 18:05:34 | [pearl_trainer] epoch #193 | EpochTime 488.62 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -265.849 MetaTest/Average/AverageReturn -265.849 MetaTest/Average/Iteration 193 MetaTest/Average/MaxReturn -186.909 MetaTest/Average/MinReturn -339.59 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 53.576 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -265.849 MetaTest/__unnamed_task__/AverageReturn -265.849 MetaTest/__unnamed_task__/Iteration 193 MetaTest/__unnamed_task__/MaxReturn -186.909 MetaTest/__unnamed_task__/MinReturn -339.59 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 53.576 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 428000 ------------------------------------------------- ---------- 2025-04-04 18:06:23 | [pearl_trainer] epoch #194 | Training... 2025-04-04 18:09:21 | [pearl_trainer] epoch #194 | Evaluating... 2025-04-04 18:09:21 | [pearl_trainer] epoch #194 | Sampling for adapation and meta-testing... 2025-04-04 18:13:32 | [pearl_trainer] epoch #194 | Finished meta-testing... 2025-04-04 18:13:32 | [pearl_trainer] epoch #194 | Saving snapshot... 2025-04-04 18:13:33 | [pearl_trainer] epoch #194 | Saved 2025-04-04 18:13:33 | [pearl_trainer] epoch #194 | Time 92676.90 s 2025-04-04 18:13:33 | [pearl_trainer] epoch #194 | EpochTime 479.14 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -290.347 MetaTest/Average/AverageReturn -290.347 MetaTest/Average/Iteration 194 MetaTest/Average/MaxReturn -258.783 MetaTest/Average/MinReturn -369.023 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 41.148 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -290.347 MetaTest/__unnamed_task__/AverageReturn -290.347 MetaTest/__unnamed_task__/Iteration 194 MetaTest/__unnamed_task__/MaxReturn -258.783 MetaTest/__unnamed_task__/MinReturn -369.023 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 41.148 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 430000 ------------------------------------------------- ---------- 2025-04-04 18:14:21 | [pearl_trainer] epoch #195 | Training... 2025-04-04 18:17:10 | [pearl_trainer] epoch #195 | Evaluating... 2025-04-04 18:17:10 | [pearl_trainer] epoch #195 | Sampling for adapation and meta-testing... 2025-04-04 18:21:37 | [pearl_trainer] epoch #195 | Finished meta-testing... 2025-04-04 18:21:37 | [pearl_trainer] epoch #195 | Saving snapshot... 2025-04-04 18:21:38 | [pearl_trainer] epoch #195 | Saved 2025-04-04 18:21:38 | [pearl_trainer] epoch #195 | Time 93161.77 s 2025-04-04 18:21:38 | [pearl_trainer] epoch #195 | EpochTime 484.87 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -239.804 MetaTest/Average/AverageReturn -239.804 MetaTest/Average/Iteration 195 MetaTest/Average/MaxReturn -160.306 MetaTest/Average/MinReturn -325.616 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 60.878 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -239.804 MetaTest/__unnamed_task__/AverageReturn -239.804 MetaTest/__unnamed_task__/Iteration 195 MetaTest/__unnamed_task__/MaxReturn -160.306 MetaTest/__unnamed_task__/MinReturn -325.616 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 60.878 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 432000 ------------------------------------------------- ---------- 2025-04-04 18:22:27 | [pearl_trainer] epoch #196 | Training... 2025-04-04 18:25:07 | [pearl_trainer] epoch #196 | Evaluating... 2025-04-04 18:25:07 | [pearl_trainer] epoch #196 | Sampling for adapation and meta-testing... 2025-04-04 18:29:41 | [pearl_trainer] epoch #196 | Finished meta-testing... 2025-04-04 18:29:41 | [pearl_trainer] epoch #196 | Saving snapshot... 2025-04-04 18:29:43 | [pearl_trainer] epoch #196 | Saved 2025-04-04 18:29:43 | [pearl_trainer] epoch #196 | Time 93646.62 s 2025-04-04 18:29:43 | [pearl_trainer] epoch #196 | EpochTime 484.84 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -227.827 MetaTest/Average/AverageReturn -227.827 MetaTest/Average/Iteration 196 MetaTest/Average/MaxReturn -126.998 MetaTest/Average/MinReturn -312.728 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 65.8652 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -227.827 MetaTest/__unnamed_task__/AverageReturn -227.827 MetaTest/__unnamed_task__/Iteration 196 MetaTest/__unnamed_task__/MaxReturn -126.998 MetaTest/__unnamed_task__/MinReturn -312.728 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 65.8652 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 434000 ------------------------------------------------- ----------- 2025-04-04 18:30:33 | [pearl_trainer] epoch #197 | Training... 2025-04-04 18:33:16 | [pearl_trainer] epoch #197 | Evaluating... 2025-04-04 18:33:16 | [pearl_trainer] epoch #197 | Sampling for adapation and meta-testing... 2025-04-04 18:37:50 | [pearl_trainer] epoch #197 | Finished meta-testing... 2025-04-04 18:37:50 | [pearl_trainer] epoch #197 | Saving snapshot... 2025-04-04 18:37:52 | [pearl_trainer] epoch #197 | Saved 2025-04-04 18:37:52 | [pearl_trainer] epoch #197 | Time 94135.27 s 2025-04-04 18:37:52 | [pearl_trainer] epoch #197 | EpochTime 488.65 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -240.769 MetaTest/Average/AverageReturn -240.769 MetaTest/Average/Iteration 197 MetaTest/Average/MaxReturn -162.955 MetaTest/Average/MinReturn -305.013 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 47.3575 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -240.769 MetaTest/__unnamed_task__/AverageReturn -240.769 MetaTest/__unnamed_task__/Iteration 197 MetaTest/__unnamed_task__/MaxReturn -162.955 MetaTest/__unnamed_task__/MinReturn -305.013 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 47.3575 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 436000 ------------------------------------------------- ----------- 2025-04-04 18:38:37 | [pearl_trainer] epoch #198 | Training... 2025-04-04 18:41:18 | [pearl_trainer] epoch #198 | Evaluating... 2025-04-04 18:41:18 | [pearl_trainer] epoch #198 | Sampling for adapation and meta-testing... 2025-04-04 18:45:43 | [pearl_trainer] epoch #198 | Finished meta-testing... 2025-04-04 18:45:43 | [pearl_trainer] epoch #198 | Saving snapshot... 2025-04-04 18:45:44 | [pearl_trainer] epoch #198 | Saved 2025-04-04 18:45:44 | [pearl_trainer] epoch #198 | Time 94608.19 s 2025-04-04 18:45:44 | [pearl_trainer] epoch #198 | EpochTime 472.92 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -272.905 MetaTest/Average/AverageReturn -272.905 MetaTest/Average/Iteration 198 MetaTest/Average/MaxReturn -236.115 MetaTest/Average/MinReturn -311.639 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 30.6592 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -272.905 MetaTest/__unnamed_task__/AverageReturn -272.905 MetaTest/__unnamed_task__/Iteration 198 MetaTest/__unnamed_task__/MaxReturn -236.115 MetaTest/__unnamed_task__/MinReturn -311.639 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 30.6592 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 438000 ------------------------------------------------- ----------- 2025-04-04 18:46:28 | [pearl_trainer] epoch #199 | Training... 2025-04-04 18:49:10 | [pearl_trainer] epoch #199 | Evaluating... 2025-04-04 18:49:10 | [pearl_trainer] epoch #199 | Sampling for adapation and meta-testing... 2025-04-04 18:53:35 | [pearl_trainer] epoch #199 | Finished meta-testing... 2025-04-04 18:53:35 | [pearl_trainer] epoch #199 | Saving snapshot... 2025-04-04 18:53:37 | [pearl_trainer] epoch #199 | Saved 2025-04-04 18:53:37 | [pearl_trainer] epoch #199 | Time 95080.23 s 2025-04-04 18:53:37 | [pearl_trainer] epoch #199 | EpochTime 472.04 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -266.006 MetaTest/Average/AverageReturn -266.006 MetaTest/Average/Iteration 199 MetaTest/Average/MaxReturn -224.524 MetaTest/Average/MinReturn -313.763 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.417 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -266.006 MetaTest/__unnamed_task__/AverageReturn -266.006 MetaTest/__unnamed_task__/Iteration 199 MetaTest/__unnamed_task__/MaxReturn -224.524 MetaTest/__unnamed_task__/MinReturn -313.763 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.417 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 440000 ------------------------------------------------- ---------- 2025-04-04 18:54:24 | [pearl_trainer] epoch #200 | Training... 2025-04-04 18:57:04 | [pearl_trainer] epoch #200 | Evaluating... 2025-04-04 18:57:04 | [pearl_trainer] epoch #200 | Sampling for adapation and meta-testing... 2025-04-04 19:01:13 | [pearl_trainer] epoch #200 | Finished meta-testing... 2025-04-04 19:01:13 | [pearl_trainer] epoch #200 | Saving snapshot... 2025-04-04 19:01:15 | [pearl_trainer] epoch #200 | Saved 2025-04-04 19:01:15 | [pearl_trainer] epoch #200 | Time 95538.47 s 2025-04-04 19:01:15 | [pearl_trainer] epoch #200 | EpochTime 458.24 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -269.414 MetaTest/Average/AverageReturn -269.414 MetaTest/Average/Iteration 200 MetaTest/Average/MaxReturn -195.897 MetaTest/Average/MinReturn -395.029 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 70.2931 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -269.414 MetaTest/__unnamed_task__/AverageReturn -269.414 MetaTest/__unnamed_task__/Iteration 200 MetaTest/__unnamed_task__/MaxReturn -195.897 MetaTest/__unnamed_task__/MinReturn -395.029 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 70.2931 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 442000 ------------------------------------------------- ----------- 2025-04-04 19:02:01 | [pearl_trainer] epoch #201 | Training... 2025-04-04 19:04:46 | [pearl_trainer] epoch #201 | Evaluating... 2025-04-04 19:04:46 | [pearl_trainer] epoch #201 | Sampling for adapation and meta-testing... 2025-04-04 19:09:02 | [pearl_trainer] epoch #201 | Finished meta-testing... 2025-04-04 19:09:02 | [pearl_trainer] epoch #201 | Saving snapshot... 2025-04-04 19:09:04 | [pearl_trainer] epoch #201 | Saved 2025-04-04 19:09:04 | [pearl_trainer] epoch #201 | Time 96007.23 s 2025-04-04 19:09:04 | [pearl_trainer] epoch #201 | EpochTime 468.76 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -228.809 MetaTest/Average/AverageReturn -228.809 MetaTest/Average/Iteration 201 MetaTest/Average/MaxReturn -203.775 MetaTest/Average/MinReturn -271.732 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.9026 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -228.809 MetaTest/__unnamed_task__/AverageReturn -228.809 MetaTest/__unnamed_task__/Iteration 201 MetaTest/__unnamed_task__/MaxReturn -203.775 MetaTest/__unnamed_task__/MinReturn -271.732 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.9026 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 444000 ------------------------------------------------- ----------- 2025-04-04 19:09:51 | [pearl_trainer] epoch #202 | Training... 2025-04-04 19:12:28 | [pearl_trainer] epoch #202 | Evaluating... 2025-04-04 19:12:28 | [pearl_trainer] epoch #202 | Sampling for adapation and meta-testing... 2025-04-04 19:17:06 | [pearl_trainer] epoch #202 | Finished meta-testing... 2025-04-04 19:17:06 | [pearl_trainer] epoch #202 | Saving snapshot... 2025-04-04 19:17:07 | [pearl_trainer] epoch #202 | Saved 2025-04-04 19:17:07 | [pearl_trainer] epoch #202 | Time 96491.18 s 2025-04-04 19:17:07 | [pearl_trainer] epoch #202 | EpochTime 483.94 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -245.183 MetaTest/Average/AverageReturn -245.183 MetaTest/Average/Iteration 202 MetaTest/Average/MaxReturn -146.522 MetaTest/Average/MinReturn -376.368 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 80.6616 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -245.183 MetaTest/__unnamed_task__/AverageReturn -245.183 MetaTest/__unnamed_task__/Iteration 202 MetaTest/__unnamed_task__/MaxReturn -146.522 MetaTest/__unnamed_task__/MinReturn -376.368 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 80.6616 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 446000 ------------------------------------------------- ----------- 2025-04-04 19:17:55 | [pearl_trainer] epoch #203 | Training... 2025-04-04 19:20:25 | [pearl_trainer] epoch #203 | Evaluating... 2025-04-04 19:20:25 | [pearl_trainer] epoch #203 | Sampling for adapation and meta-testing... 2025-04-04 19:25:06 | [pearl_trainer] epoch #203 | Finished meta-testing... 2025-04-04 19:25:06 | [pearl_trainer] epoch #203 | Saving snapshot... 2025-04-04 19:25:07 | [pearl_trainer] epoch #203 | Saved 2025-04-04 19:25:07 | [pearl_trainer] epoch #203 | Time 96970.94 s 2025-04-04 19:25:07 | [pearl_trainer] epoch #203 | EpochTime 479.76 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -221.17 MetaTest/Average/AverageReturn -221.17 MetaTest/Average/Iteration 203 MetaTest/Average/MaxReturn -137.329 MetaTest/Average/MinReturn -289.015 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 57.1668 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -221.17 MetaTest/__unnamed_task__/AverageReturn -221.17 MetaTest/__unnamed_task__/Iteration 203 MetaTest/__unnamed_task__/MaxReturn -137.329 MetaTest/__unnamed_task__/MinReturn -289.015 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 57.1668 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 448000 ------------------------------------------------- ----------- 2025-04-04 19:25:58 | [pearl_trainer] epoch #204 | Training... 2025-04-04 19:28:36 | [pearl_trainer] epoch #204 | Evaluating... 2025-04-04 19:28:36 | [pearl_trainer] epoch #204 | Sampling for adapation and meta-testing... 2025-04-04 19:33:04 | [pearl_trainer] epoch #204 | Finished meta-testing... 2025-04-04 19:33:04 | [pearl_trainer] epoch #204 | Saving snapshot... 2025-04-04 19:33:05 | [pearl_trainer] epoch #204 | Saved 2025-04-04 19:33:05 | [pearl_trainer] epoch #204 | Time 97449.07 s 2025-04-04 19:33:05 | [pearl_trainer] epoch #204 | EpochTime 478.12 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -215.816 MetaTest/Average/AverageReturn -215.816 MetaTest/Average/Iteration 204 MetaTest/Average/MaxReturn -117.264 MetaTest/Average/MinReturn -270.001 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 52.1936 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -215.816 MetaTest/__unnamed_task__/AverageReturn -215.816 MetaTest/__unnamed_task__/Iteration 204 MetaTest/__unnamed_task__/MaxReturn -117.264 MetaTest/__unnamed_task__/MinReturn -270.001 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 52.1936 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 450000 ------------------------------------------------- ----------- 2025-04-04 19:33:50 | [pearl_trainer] epoch #205 | Training... 2025-04-04 19:36:27 | [pearl_trainer] epoch #205 | Evaluating... 2025-04-04 19:36:27 | [pearl_trainer] epoch #205 | Sampling for adapation and meta-testing... 2025-04-04 19:40:34 | [pearl_trainer] epoch #205 | Finished meta-testing... 2025-04-04 19:40:34 | [pearl_trainer] epoch #205 | Saving snapshot... 2025-04-04 19:40:35 | [pearl_trainer] epoch #205 | Saved 2025-04-04 19:40:35 | [pearl_trainer] epoch #205 | Time 97898.64 s 2025-04-04 19:40:35 | [pearl_trainer] epoch #205 | EpochTime 449.57 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -271.026 MetaTest/Average/AverageReturn -271.026 MetaTest/Average/Iteration 205 MetaTest/Average/MaxReturn -233.438 MetaTest/Average/MinReturn -354.248 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 43.9985 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -271.026 MetaTest/__unnamed_task__/AverageReturn -271.026 MetaTest/__unnamed_task__/Iteration 205 MetaTest/__unnamed_task__/MaxReturn -233.438 MetaTest/__unnamed_task__/MinReturn -354.248 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 43.9985 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 452000 ------------------------------------------------- ----------- 2025-04-04 19:41:18 | [pearl_trainer] epoch #206 | Training... 2025-04-04 19:43:58 | [pearl_trainer] epoch #206 | Evaluating... 2025-04-04 19:43:58 | [pearl_trainer] epoch #206 | Sampling for adapation and meta-testing... 2025-04-04 19:47:49 | [pearl_trainer] epoch #206 | Finished meta-testing... 2025-04-04 19:47:49 | [pearl_trainer] epoch #206 | Saving snapshot... 2025-04-04 19:47:50 | [pearl_trainer] epoch #206 | Saved 2025-04-04 19:47:50 | [pearl_trainer] epoch #206 | Time 98334.11 s 2025-04-04 19:47:50 | [pearl_trainer] epoch #206 | EpochTime 435.47 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -248.702 MetaTest/Average/AverageReturn -248.702 MetaTest/Average/Iteration 206 MetaTest/Average/MaxReturn -205.773 MetaTest/Average/MinReturn -305.134 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 40.2365 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -248.702 MetaTest/__unnamed_task__/AverageReturn -248.702 MetaTest/__unnamed_task__/Iteration 206 MetaTest/__unnamed_task__/MaxReturn -205.773 MetaTest/__unnamed_task__/MinReturn -305.134 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 40.2365 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 454000 ------------------------------------------------- ----------- 2025-04-04 19:48:36 | [pearl_trainer] epoch #207 | Training... 2025-04-04 19:51:16 | [pearl_trainer] epoch #207 | Evaluating... 2025-04-04 19:51:16 | [pearl_trainer] epoch #207 | Sampling for adapation and meta-testing... 2025-04-04 19:55:13 | [pearl_trainer] epoch #207 | Finished meta-testing... 2025-04-04 19:55:13 | [pearl_trainer] epoch #207 | Saving snapshot... 2025-04-04 19:55:14 | [pearl_trainer] epoch #207 | Saved 2025-04-04 19:55:14 | [pearl_trainer] epoch #207 | Time 98777.48 s 2025-04-04 19:55:14 | [pearl_trainer] epoch #207 | EpochTime 443.36 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -247.623 MetaTest/Average/AverageReturn -247.623 MetaTest/Average/Iteration 207 MetaTest/Average/MaxReturn -200.541 MetaTest/Average/MinReturn -308.703 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 42.0671 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -247.623 MetaTest/__unnamed_task__/AverageReturn -247.623 MetaTest/__unnamed_task__/Iteration 207 MetaTest/__unnamed_task__/MaxReturn -200.541 MetaTest/__unnamed_task__/MinReturn -308.703 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 42.0671 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 456000 ------------------------------------------------- ----------- 2025-04-04 19:56:00 | [pearl_trainer] epoch #208 | Training... 2025-04-04 19:58:35 | [pearl_trainer] epoch #208 | Evaluating... 2025-04-04 19:58:35 | [pearl_trainer] epoch #208 | Sampling for adapation and meta-testing... 2025-04-04 20:02:38 | [pearl_trainer] epoch #208 | Finished meta-testing... 2025-04-04 20:02:38 | [pearl_trainer] epoch #208 | Saving snapshot... 2025-04-04 20:02:39 | [pearl_trainer] epoch #208 | Saved 2025-04-04 20:02:39 | [pearl_trainer] epoch #208 | Time 99223.19 s 2025-04-04 20:02:39 | [pearl_trainer] epoch #208 | EpochTime 445.71 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -249.565 MetaTest/Average/AverageReturn -249.565 MetaTest/Average/Iteration 208 MetaTest/Average/MaxReturn -211.194 MetaTest/Average/MinReturn -375.522 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 63.3488 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -249.565 MetaTest/__unnamed_task__/AverageReturn -249.565 MetaTest/__unnamed_task__/Iteration 208 MetaTest/__unnamed_task__/MaxReturn -211.194 MetaTest/__unnamed_task__/MinReturn -375.522 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 63.3488 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 458000 ------------------------------------------------- ----------- 2025-04-04 20:03:26 | [pearl_trainer] epoch #209 | Training... 2025-04-04 20:06:10 | [pearl_trainer] epoch #209 | Evaluating... 2025-04-04 20:06:10 | [pearl_trainer] epoch #209 | Sampling for adapation and meta-testing... 2025-04-04 20:10:06 | [pearl_trainer] epoch #209 | Finished meta-testing... 2025-04-04 20:10:06 | [pearl_trainer] epoch #209 | Saving snapshot... 2025-04-04 20:10:07 | [pearl_trainer] epoch #209 | Saved 2025-04-04 20:10:07 | [pearl_trainer] epoch #209 | Time 99670.81 s 2025-04-04 20:10:07 | [pearl_trainer] epoch #209 | EpochTime 447.62 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -272.705 MetaTest/Average/AverageReturn -272.705 MetaTest/Average/Iteration 209 MetaTest/Average/MaxReturn -236.948 MetaTest/Average/MinReturn -299.63 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.014 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -272.705 MetaTest/__unnamed_task__/AverageReturn -272.705 MetaTest/__unnamed_task__/Iteration 209 MetaTest/__unnamed_task__/MaxReturn -236.948 MetaTest/__unnamed_task__/MinReturn -299.63 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.014 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 460000 ------------------------------------------------- ---------- 2025-04-04 20:10:54 | [pearl_trainer] epoch #210 | Training... 2025-04-04 20:13:34 | [pearl_trainer] epoch #210 | Evaluating... 2025-04-04 20:13:34 | [pearl_trainer] epoch #210 | Sampling for adapation and meta-testing... 2025-04-04 20:17:48 | [pearl_trainer] epoch #210 | Finished meta-testing... 2025-04-04 20:17:48 | [pearl_trainer] epoch #210 | Saving snapshot... 2025-04-04 20:17:49 | [pearl_trainer] epoch #210 | Saved 2025-04-04 20:17:49 | [pearl_trainer] epoch #210 | Time 100132.64 s 2025-04-04 20:17:49 | [pearl_trainer] epoch #210 | EpochTime 461.83 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -232.072 MetaTest/Average/AverageReturn -232.072 MetaTest/Average/Iteration 210 MetaTest/Average/MaxReturn -148.49 MetaTest/Average/MinReturn -288.683 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 47.8805 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -232.072 MetaTest/__unnamed_task__/AverageReturn -232.072 MetaTest/__unnamed_task__/Iteration 210 MetaTest/__unnamed_task__/MaxReturn -148.49 MetaTest/__unnamed_task__/MinReturn -288.683 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 47.8805 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 462000 ------------------------------------------------- ----------- 2025-04-04 20:18:34 | [pearl_trainer] epoch #211 | Training... 2025-04-04 20:21:19 | [pearl_trainer] epoch #211 | Evaluating... 2025-04-04 20:21:19 | [pearl_trainer] epoch #211 | Sampling for adapation and meta-testing... 2025-04-04 20:25:24 | [pearl_trainer] epoch #211 | Finished meta-testing... 2025-04-04 20:25:24 | [pearl_trainer] epoch #211 | Saving snapshot... 2025-04-04 20:25:26 | [pearl_trainer] epoch #211 | Saved 2025-04-04 20:25:26 | [pearl_trainer] epoch #211 | Time 100589.28 s 2025-04-04 20:25:26 | [pearl_trainer] epoch #211 | EpochTime 456.63 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -248.048 MetaTest/Average/AverageReturn -248.048 MetaTest/Average/Iteration 211 MetaTest/Average/MaxReturn -184.615 MetaTest/Average/MinReturn -287.069 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.9453 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -248.048 MetaTest/__unnamed_task__/AverageReturn -248.048 MetaTest/__unnamed_task__/Iteration 211 MetaTest/__unnamed_task__/MaxReturn -184.615 MetaTest/__unnamed_task__/MinReturn -287.069 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.9453 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 464000 ------------------------------------------------- ----------- 2025-04-04 20:26:12 | [pearl_trainer] epoch #212 | Training... 2025-04-04 20:28:52 | [pearl_trainer] epoch #212 | Evaluating... 2025-04-04 20:28:52 | [pearl_trainer] epoch #212 | Sampling for adapation and meta-testing... 2025-04-04 20:33:22 | [pearl_trainer] epoch #212 | Finished meta-testing... 2025-04-04 20:33:22 | [pearl_trainer] epoch #212 | Saving snapshot... 2025-04-04 20:33:23 | [pearl_trainer] epoch #212 | Saved 2025-04-04 20:33:23 | [pearl_trainer] epoch #212 | Time 101067.03 s 2025-04-04 20:33:23 | [pearl_trainer] epoch #212 | EpochTime 477.75 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -233.157 MetaTest/Average/AverageReturn -233.157 MetaTest/Average/Iteration 212 MetaTest/Average/MaxReturn -162.95 MetaTest/Average/MinReturn -267.157 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.892 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -233.157 MetaTest/__unnamed_task__/AverageReturn -233.157 MetaTest/__unnamed_task__/Iteration 212 MetaTest/__unnamed_task__/MaxReturn -162.95 MetaTest/__unnamed_task__/MinReturn -267.157 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.892 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 466000 ------------------------------------------------- ---------- 2025-04-04 20:34:15 | [pearl_trainer] epoch #213 | Training... 2025-04-04 20:37:00 | [pearl_trainer] epoch #213 | Evaluating... 2025-04-04 20:37:00 | [pearl_trainer] epoch #213 | Sampling for adapation and meta-testing... 2025-04-04 20:41:37 | [pearl_trainer] epoch #213 | Finished meta-testing... 2025-04-04 20:41:37 | [pearl_trainer] epoch #213 | Saving snapshot... 2025-04-04 20:41:38 | [pearl_trainer] epoch #213 | Saved 2025-04-04 20:41:38 | [pearl_trainer] epoch #213 | Time 101561.51 s 2025-04-04 20:41:38 | [pearl_trainer] epoch #213 | EpochTime 494.48 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -231.187 MetaTest/Average/AverageReturn -231.187 MetaTest/Average/Iteration 213 MetaTest/Average/MaxReturn -123.14 MetaTest/Average/MinReturn -286.504 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 57.8124 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -231.187 MetaTest/__unnamed_task__/AverageReturn -231.187 MetaTest/__unnamed_task__/Iteration 213 MetaTest/__unnamed_task__/MaxReturn -123.14 MetaTest/__unnamed_task__/MinReturn -286.504 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 57.8124 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 468000 ------------------------------------------------- ----------- 2025-04-04 20:42:28 | [pearl_trainer] epoch #214 | Training... 2025-04-04 20:45:09 | [pearl_trainer] epoch #214 | Evaluating... 2025-04-04 20:45:09 | [pearl_trainer] epoch #214 | Sampling for adapation and meta-testing... 2025-04-04 20:49:28 | [pearl_trainer] epoch #214 | Finished meta-testing... 2025-04-04 20:49:28 | [pearl_trainer] epoch #214 | Saving snapshot... 2025-04-04 20:49:30 | [pearl_trainer] epoch #214 | Saved 2025-04-04 20:49:30 | [pearl_trainer] epoch #214 | Time 102033.55 s 2025-04-04 20:49:30 | [pearl_trainer] epoch #214 | EpochTime 472.04 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -283.695 MetaTest/Average/AverageReturn -283.695 MetaTest/Average/Iteration 214 MetaTest/Average/MaxReturn -240.221 MetaTest/Average/MinReturn -327.273 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 32.2818 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -283.695 MetaTest/__unnamed_task__/AverageReturn -283.695 MetaTest/__unnamed_task__/Iteration 214 MetaTest/__unnamed_task__/MaxReturn -240.221 MetaTest/__unnamed_task__/MinReturn -327.273 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 32.2818 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 470000 ------------------------------------------------- ----------- 2025-04-04 20:50:19 | [pearl_trainer] epoch #215 | Training... 2025-04-04 20:53:04 | [pearl_trainer] epoch #215 | Evaluating... 2025-04-04 20:53:04 | [pearl_trainer] epoch #215 | Sampling for adapation and meta-testing... 2025-04-04 20:57:21 | [pearl_trainer] epoch #215 | Finished meta-testing... 2025-04-04 20:57:21 | [pearl_trainer] epoch #215 | Saving snapshot... 2025-04-04 20:57:22 | [pearl_trainer] epoch #215 | Saved 2025-04-04 20:57:22 | [pearl_trainer] epoch #215 | Time 102505.57 s 2025-04-04 20:57:22 | [pearl_trainer] epoch #215 | EpochTime 472.02 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -270.456 MetaTest/Average/AverageReturn -270.456 MetaTest/Average/Iteration 215 MetaTest/Average/MaxReturn -198.136 MetaTest/Average/MinReturn -331.6 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 50.4894 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -270.456 MetaTest/__unnamed_task__/AverageReturn -270.456 MetaTest/__unnamed_task__/Iteration 215 MetaTest/__unnamed_task__/MaxReturn -198.136 MetaTest/__unnamed_task__/MinReturn -331.6 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 50.4894 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 472000 ------------------------------------------------- ----------- 2025-04-04 20:58:08 | [pearl_trainer] epoch #216 | Training... 2025-04-04 21:00:48 | [pearl_trainer] epoch #216 | Evaluating... 2025-04-04 21:00:48 | [pearl_trainer] epoch #216 | Sampling for adapation and meta-testing... 2025-04-04 21:05:21 | [pearl_trainer] epoch #216 | Finished meta-testing... 2025-04-04 21:05:21 | [pearl_trainer] epoch #216 | Saving snapshot... 2025-04-04 21:05:23 | [pearl_trainer] epoch #216 | Saved 2025-04-04 21:05:23 | [pearl_trainer] epoch #216 | Time 102986.24 s 2025-04-04 21:05:23 | [pearl_trainer] epoch #216 | EpochTime 480.67 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -194.363 MetaTest/Average/AverageReturn -194.363 MetaTest/Average/Iteration 216 MetaTest/Average/MaxReturn -164.989 MetaTest/Average/MinReturn -244.789 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 29.4185 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -194.363 MetaTest/__unnamed_task__/AverageReturn -194.363 MetaTest/__unnamed_task__/Iteration 216 MetaTest/__unnamed_task__/MaxReturn -164.989 MetaTest/__unnamed_task__/MinReturn -244.789 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 29.4185 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 474000 ------------------------------------------------- ----------- 2025-04-04 21:06:13 | [pearl_trainer] epoch #217 | Training... 2025-04-04 21:08:53 | [pearl_trainer] epoch #217 | Evaluating... 2025-04-04 21:08:53 | [pearl_trainer] epoch #217 | Sampling for adapation and meta-testing... 2025-04-04 21:13:36 | [pearl_trainer] epoch #217 | Finished meta-testing... 2025-04-04 21:13:36 | [pearl_trainer] epoch #217 | Saving snapshot... 2025-04-04 21:13:37 | [pearl_trainer] epoch #217 | Saved 2025-04-04 21:13:37 | [pearl_trainer] epoch #217 | Time 103480.75 s 2025-04-04 21:13:37 | [pearl_trainer] epoch #217 | EpochTime 494.50 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -244.658 MetaTest/Average/AverageReturn -244.658 MetaTest/Average/Iteration 217 MetaTest/Average/MaxReturn -189.381 MetaTest/Average/MinReturn -361.714 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 60.9793 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -244.658 MetaTest/__unnamed_task__/AverageReturn -244.658 MetaTest/__unnamed_task__/Iteration 217 MetaTest/__unnamed_task__/MaxReturn -189.381 MetaTest/__unnamed_task__/MinReturn -361.714 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 60.9793 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 476000 ------------------------------------------------- ----------- 2025-04-04 21:14:27 | [pearl_trainer] epoch #218 | Training... 2025-04-04 21:17:10 | [pearl_trainer] epoch #218 | Evaluating... 2025-04-04 21:17:10 | [pearl_trainer] epoch #218 | Sampling for adapation and meta-testing... 2025-04-04 21:21:58 | [pearl_trainer] epoch #218 | Finished meta-testing... 2025-04-04 21:21:58 | [pearl_trainer] epoch #218 | Saving snapshot... 2025-04-04 21:21:59 | [pearl_trainer] epoch #218 | Saved 2025-04-04 21:21:59 | [pearl_trainer] epoch #218 | Time 103982.94 s 2025-04-04 21:21:59 | [pearl_trainer] epoch #218 | EpochTime 502.19 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -181.419 MetaTest/Average/AverageReturn -181.419 MetaTest/Average/Iteration 218 MetaTest/Average/MaxReturn -138.29 MetaTest/Average/MinReturn -245.187 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 41.7672 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -181.419 MetaTest/__unnamed_task__/AverageReturn -181.419 MetaTest/__unnamed_task__/Iteration 218 MetaTest/__unnamed_task__/MaxReturn -138.29 MetaTest/__unnamed_task__/MinReturn -245.187 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 41.7672 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 478000 ------------------------------------------------- ----------- 2025-04-04 21:22:49 | [pearl_trainer] epoch #219 | Training... 2025-04-04 21:25:33 | [pearl_trainer] epoch #219 | Evaluating... 2025-04-04 21:25:33 | [pearl_trainer] epoch #219 | Sampling for adapation and meta-testing... 2025-04-04 21:30:14 | [pearl_trainer] epoch #219 | Finished meta-testing... 2025-04-04 21:30:14 | [pearl_trainer] epoch #219 | Saving snapshot... 2025-04-04 21:30:15 | [pearl_trainer] epoch #219 | Saved 2025-04-04 21:30:15 | [pearl_trainer] epoch #219 | Time 104478.95 s 2025-04-04 21:30:15 | [pearl_trainer] epoch #219 | EpochTime 496.01 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -180.987 MetaTest/Average/AverageReturn -180.987 MetaTest/Average/Iteration 219 MetaTest/Average/MaxReturn -131.316 MetaTest/Average/MinReturn -225.576 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 41.7967 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -180.987 MetaTest/__unnamed_task__/AverageReturn -180.987 MetaTest/__unnamed_task__/Iteration 219 MetaTest/__unnamed_task__/MaxReturn -131.316 MetaTest/__unnamed_task__/MinReturn -225.576 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 41.7967 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 480000 ------------------------------------------------- ----------- 2025-04-04 21:31:03 | [pearl_trainer] epoch #220 | Training... 2025-04-04 21:33:39 | [pearl_trainer] epoch #220 | Evaluating... 2025-04-04 21:33:39 | [pearl_trainer] epoch #220 | Sampling for adapation and meta-testing... 2025-04-04 21:38:21 | [pearl_trainer] epoch #220 | Finished meta-testing... 2025-04-04 21:38:21 | [pearl_trainer] epoch #220 | Saving snapshot... 2025-04-04 21:38:23 | [pearl_trainer] epoch #220 | Saved 2025-04-04 21:38:23 | [pearl_trainer] epoch #220 | Time 104966.43 s 2025-04-04 21:38:23 | [pearl_trainer] epoch #220 | EpochTime 487.48 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -142.168 MetaTest/Average/AverageReturn -142.168 MetaTest/Average/Iteration 220 MetaTest/Average/MaxReturn -76.1441 MetaTest/Average/MinReturn -174.157 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 35.8226 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -142.168 MetaTest/__unnamed_task__/AverageReturn -142.168 MetaTest/__unnamed_task__/Iteration 220 MetaTest/__unnamed_task__/MaxReturn -76.1441 MetaTest/__unnamed_task__/MinReturn -174.157 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 35.8226 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 482000 ------------------------------------------------- ----------- 2025-04-04 21:39:16 | [pearl_trainer] epoch #221 | Training... 2025-04-04 21:41:56 | [pearl_trainer] epoch #221 | Evaluating... 2025-04-04 21:41:56 | [pearl_trainer] epoch #221 | Sampling for adapation and meta-testing... 2025-04-04 21:46:42 | [pearl_trainer] epoch #221 | Finished meta-testing... 2025-04-04 21:46:42 | [pearl_trainer] epoch #221 | Saving snapshot... 2025-04-04 21:46:43 | [pearl_trainer] epoch #221 | Saved 2025-04-04 21:46:43 | [pearl_trainer] epoch #221 | Time 105467.12 s 2025-04-04 21:46:43 | [pearl_trainer] epoch #221 | EpochTime 500.69 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -188.954 MetaTest/Average/AverageReturn -188.954 MetaTest/Average/Iteration 221 MetaTest/Average/MaxReturn -76.7533 MetaTest/Average/MinReturn -243.446 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 60.6316 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -188.954 MetaTest/__unnamed_task__/AverageReturn -188.954 MetaTest/__unnamed_task__/Iteration 221 MetaTest/__unnamed_task__/MaxReturn -76.7533 MetaTest/__unnamed_task__/MinReturn -243.446 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 60.6316 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 484000 ------------------------------------------------- ----------- 2025-04-04 21:47:32 | [pearl_trainer] epoch #222 | Training... 2025-04-04 21:50:15 | [pearl_trainer] epoch #222 | Evaluating... 2025-04-04 21:50:15 | [pearl_trainer] epoch #222 | Sampling for adapation and meta-testing... 2025-04-04 21:54:56 | [pearl_trainer] epoch #222 | Finished meta-testing... 2025-04-04 21:54:56 | [pearl_trainer] epoch #222 | Saving snapshot... 2025-04-04 21:54:57 | [pearl_trainer] epoch #222 | Saved 2025-04-04 21:54:57 | [pearl_trainer] epoch #222 | Time 105960.70 s 2025-04-04 21:54:57 | [pearl_trainer] epoch #222 | EpochTime 493.58 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -231.758 MetaTest/Average/AverageReturn -231.758 MetaTest/Average/Iteration 222 MetaTest/Average/MaxReturn -138.967 MetaTest/Average/MinReturn -317.797 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 59.9232 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -231.758 MetaTest/__unnamed_task__/AverageReturn -231.758 MetaTest/__unnamed_task__/Iteration 222 MetaTest/__unnamed_task__/MaxReturn -138.967 MetaTest/__unnamed_task__/MinReturn -317.797 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 59.9232 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 486000 ------------------------------------------------- ----------- 2025-04-04 21:55:49 | [pearl_trainer] epoch #223 | Training... 2025-04-04 21:58:35 | [pearl_trainer] epoch #223 | Evaluating... 2025-04-04 21:58:35 | [pearl_trainer] epoch #223 | Sampling for adapation and meta-testing... 2025-04-04 22:03:12 | [pearl_trainer] epoch #223 | Finished meta-testing... 2025-04-04 22:03:12 | [pearl_trainer] epoch #223 | Saving snapshot... 2025-04-04 22:03:13 | [pearl_trainer] epoch #223 | Saved 2025-04-04 22:03:13 | [pearl_trainer] epoch #223 | Time 106456.67 s 2025-04-04 22:03:13 | [pearl_trainer] epoch #223 | EpochTime 495.96 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -196.628 MetaTest/Average/AverageReturn -196.628 MetaTest/Average/Iteration 223 MetaTest/Average/MaxReturn -160.906 MetaTest/Average/MinReturn -239.632 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 25.3234 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -196.628 MetaTest/__unnamed_task__/AverageReturn -196.628 MetaTest/__unnamed_task__/Iteration 223 MetaTest/__unnamed_task__/MaxReturn -160.906 MetaTest/__unnamed_task__/MinReturn -239.632 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 25.3234 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 488000 ------------------------------------------------- ----------- 2025-04-04 22:04:05 | [pearl_trainer] epoch #224 | Training... 2025-04-04 22:06:45 | [pearl_trainer] epoch #224 | Evaluating... 2025-04-04 22:06:45 | [pearl_trainer] epoch #224 | Sampling for adapation and meta-testing... 2025-04-04 22:11:30 | [pearl_trainer] epoch #224 | Finished meta-testing... 2025-04-04 22:11:30 | [pearl_trainer] epoch #224 | Saving snapshot... 2025-04-04 22:11:32 | [pearl_trainer] epoch #224 | Saved 2025-04-04 22:11:32 | [pearl_trainer] epoch #224 | Time 106955.22 s 2025-04-04 22:11:32 | [pearl_trainer] epoch #224 | EpochTime 498.55 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -216.936 MetaTest/Average/AverageReturn -216.936 MetaTest/Average/Iteration 224 MetaTest/Average/MaxReturn -115.447 MetaTest/Average/MinReturn -297.665 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 61.7365 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -216.936 MetaTest/__unnamed_task__/AverageReturn -216.936 MetaTest/__unnamed_task__/Iteration 224 MetaTest/__unnamed_task__/MaxReturn -115.447 MetaTest/__unnamed_task__/MinReturn -297.665 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 61.7365 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 490000 ------------------------------------------------- ----------- 2025-04-04 22:12:18 | [pearl_trainer] epoch #225 | Training... 2025-04-04 22:14:59 | [pearl_trainer] epoch #225 | Evaluating... 2025-04-04 22:14:59 | [pearl_trainer] epoch #225 | Sampling for adapation and meta-testing... 2025-04-04 22:19:37 | [pearl_trainer] epoch #225 | Finished meta-testing... 2025-04-04 22:19:37 | [pearl_trainer] epoch #225 | Saving snapshot... 2025-04-04 22:19:38 | [pearl_trainer] epoch #225 | Saved 2025-04-04 22:19:38 | [pearl_trainer] epoch #225 | Time 107441.37 s 2025-04-04 22:19:38 | [pearl_trainer] epoch #225 | EpochTime 486.15 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -259.698 MetaTest/Average/AverageReturn -259.698 MetaTest/Average/Iteration 225 MetaTest/Average/MaxReturn -184.737 MetaTest/Average/MinReturn -323.72 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 53.6165 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -259.698 MetaTest/__unnamed_task__/AverageReturn -259.698 MetaTest/__unnamed_task__/Iteration 225 MetaTest/__unnamed_task__/MaxReturn -184.737 MetaTest/__unnamed_task__/MinReturn -323.72 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 53.6165 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 492000 ------------------------------------------------- ----------- 2025-04-04 22:20:28 | [pearl_trainer] epoch #226 | Training... 2025-04-04 22:23:08 | [pearl_trainer] epoch #226 | Evaluating... 2025-04-04 22:23:08 | [pearl_trainer] epoch #226 | Sampling for adapation and meta-testing... 2025-04-04 22:27:28 | [pearl_trainer] epoch #226 | Finished meta-testing... 2025-04-04 22:27:28 | [pearl_trainer] epoch #226 | Saving snapshot... 2025-04-04 22:27:29 | [pearl_trainer] epoch #226 | Saved 2025-04-04 22:27:29 | [pearl_trainer] epoch #226 | Time 107912.76 s 2025-04-04 22:27:29 | [pearl_trainer] epoch #226 | EpochTime 471.39 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -238.2 MetaTest/Average/AverageReturn -238.2 MetaTest/Average/Iteration 226 MetaTest/Average/MaxReturn -217.657 MetaTest/Average/MinReturn -266.581 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 18.3045 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -238.2 MetaTest/__unnamed_task__/AverageReturn -238.2 MetaTest/__unnamed_task__/Iteration 226 MetaTest/__unnamed_task__/MaxReturn -217.657 MetaTest/__unnamed_task__/MinReturn -266.581 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 18.3045 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 494000 ------------------------------------------------- ----------- 2025-04-04 22:28:18 | [pearl_trainer] epoch #227 | Training... 2025-04-04 22:31:03 | [pearl_trainer] epoch #227 | Evaluating... 2025-04-04 22:31:03 | [pearl_trainer] epoch #227 | Sampling for adapation and meta-testing... 2025-04-04 22:35:22 | [pearl_trainer] epoch #227 | Finished meta-testing... 2025-04-04 22:35:22 | [pearl_trainer] epoch #227 | Saving snapshot... 2025-04-04 22:35:23 | [pearl_trainer] epoch #227 | Saved 2025-04-04 22:35:23 | [pearl_trainer] epoch #227 | Time 108386.78 s 2025-04-04 22:35:23 | [pearl_trainer] epoch #227 | EpochTime 474.01 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -242.971 MetaTest/Average/AverageReturn -242.971 MetaTest/Average/Iteration 227 MetaTest/Average/MaxReturn -191.043 MetaTest/Average/MinReturn -292.412 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 38.6419 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -242.971 MetaTest/__unnamed_task__/AverageReturn -242.971 MetaTest/__unnamed_task__/Iteration 227 MetaTest/__unnamed_task__/MaxReturn -191.043 MetaTest/__unnamed_task__/MinReturn -292.412 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 38.6419 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 496000 ------------------------------------------------- ----------- 2025-04-04 22:36:09 | [pearl_trainer] epoch #228 | Training... 2025-04-04 22:38:51 | [pearl_trainer] epoch #228 | Evaluating... 2025-04-04 22:38:51 | [pearl_trainer] epoch #228 | Sampling for adapation and meta-testing... 2025-04-04 22:43:16 | [pearl_trainer] epoch #228 | Finished meta-testing... 2025-04-04 22:43:16 | [pearl_trainer] epoch #228 | Saving snapshot... 2025-04-04 22:43:18 | [pearl_trainer] epoch #228 | Saved 2025-04-04 22:43:18 | [pearl_trainer] epoch #228 | Time 108861.27 s 2025-04-04 22:43:18 | [pearl_trainer] epoch #228 | EpochTime 474.49 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -237.966 MetaTest/Average/AverageReturn -237.966 MetaTest/Average/Iteration 228 MetaTest/Average/MaxReturn -199.676 MetaTest/Average/MinReturn -266.878 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.463 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -237.966 MetaTest/__unnamed_task__/AverageReturn -237.966 MetaTest/__unnamed_task__/Iteration 228 MetaTest/__unnamed_task__/MaxReturn -199.676 MetaTest/__unnamed_task__/MinReturn -266.878 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.463 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 498000 ------------------------------------------------- ---------- 2025-04-04 22:44:06 | [pearl_trainer] epoch #229 | Training... 2025-04-04 22:46:52 | [pearl_trainer] epoch #229 | Evaluating... 2025-04-04 22:46:52 | [pearl_trainer] epoch #229 | Sampling for adapation and meta-testing... 2025-04-04 22:51:29 | [pearl_trainer] epoch #229 | Finished meta-testing... 2025-04-04 22:51:29 | [pearl_trainer] epoch #229 | Saving snapshot... 2025-04-04 22:51:30 | [pearl_trainer] epoch #229 | Saved 2025-04-04 22:51:30 | [pearl_trainer] epoch #229 | Time 109353.46 s 2025-04-04 22:51:30 | [pearl_trainer] epoch #229 | EpochTime 492.19 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -185.203 MetaTest/Average/AverageReturn -185.203 MetaTest/Average/Iteration 229 MetaTest/Average/MaxReturn -133.514 MetaTest/Average/MinReturn -258.592 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 48.6294 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -185.203 MetaTest/__unnamed_task__/AverageReturn -185.203 MetaTest/__unnamed_task__/Iteration 229 MetaTest/__unnamed_task__/MaxReturn -133.514 MetaTest/__unnamed_task__/MinReturn -258.592 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 48.6294 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 500000 ------------------------------------------------- ----------- 2025-04-04 22:52:20 | [pearl_trainer] epoch #230 | Training... 2025-04-04 22:55:03 | [pearl_trainer] epoch #230 | Evaluating... 2025-04-04 22:55:03 | [pearl_trainer] epoch #230 | Sampling for adapation and meta-testing... 2025-04-04 22:59:28 | [pearl_trainer] epoch #230 | Finished meta-testing... 2025-04-04 22:59:28 | [pearl_trainer] epoch #230 | Saving snapshot... 2025-04-04 22:59:29 | [pearl_trainer] epoch #230 | Saved 2025-04-04 22:59:29 | [pearl_trainer] epoch #230 | Time 109833.03 s 2025-04-04 22:59:29 | [pearl_trainer] epoch #230 | EpochTime 479.57 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -241.621 MetaTest/Average/AverageReturn -241.621 MetaTest/Average/Iteration 230 MetaTest/Average/MaxReturn -204.635 MetaTest/Average/MinReturn -275.372 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.5161 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -241.621 MetaTest/__unnamed_task__/AverageReturn -241.621 MetaTest/__unnamed_task__/Iteration 230 MetaTest/__unnamed_task__/MaxReturn -204.635 MetaTest/__unnamed_task__/MinReturn -275.372 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.5161 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 502000 ------------------------------------------------- ----------- 2025-04-04 23:00:15 | [pearl_trainer] epoch #231 | Training... 2025-04-04 23:02:55 | [pearl_trainer] epoch #231 | Evaluating... 2025-04-04 23:02:55 | [pearl_trainer] epoch #231 | Sampling for adapation and meta-testing... 2025-04-04 23:07:15 | [pearl_trainer] epoch #231 | Finished meta-testing... 2025-04-04 23:07:15 | [pearl_trainer] epoch #231 | Saving snapshot... 2025-04-04 23:07:16 | [pearl_trainer] epoch #231 | Saved 2025-04-04 23:07:16 | [pearl_trainer] epoch #231 | Time 110299.54 s 2025-04-04 23:07:16 | [pearl_trainer] epoch #231 | EpochTime 466.51 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -202.5 MetaTest/Average/AverageReturn -202.5 MetaTest/Average/Iteration 231 MetaTest/Average/MaxReturn -128.795 MetaTest/Average/MinReturn -283.945 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 50.6697 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -202.5 MetaTest/__unnamed_task__/AverageReturn -202.5 MetaTest/__unnamed_task__/Iteration 231 MetaTest/__unnamed_task__/MaxReturn -128.795 MetaTest/__unnamed_task__/MinReturn -283.945 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 50.6697 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 504000 ------------------------------------------------- ----------- 2025-04-04 23:08:03 | [pearl_trainer] epoch #232 | Training... 2025-04-04 23:10:47 | [pearl_trainer] epoch #232 | Evaluating... 2025-04-04 23:10:47 | [pearl_trainer] epoch #232 | Sampling for adapation and meta-testing... 2025-04-04 23:15:20 | [pearl_trainer] epoch #232 | Finished meta-testing... 2025-04-04 23:15:20 | [pearl_trainer] epoch #232 | Saving snapshot... 2025-04-04 23:15:21 | [pearl_trainer] epoch #232 | Saved 2025-04-04 23:15:21 | [pearl_trainer] epoch #232 | Time 110784.70 s 2025-04-04 23:15:21 | [pearl_trainer] epoch #232 | EpochTime 485.15 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -238.846 MetaTest/Average/AverageReturn -238.846 MetaTest/Average/Iteration 232 MetaTest/Average/MaxReturn -183.844 MetaTest/Average/MinReturn -347.948 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 57.3026 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -238.846 MetaTest/__unnamed_task__/AverageReturn -238.846 MetaTest/__unnamed_task__/Iteration 232 MetaTest/__unnamed_task__/MaxReturn -183.844 MetaTest/__unnamed_task__/MinReturn -347.948 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 57.3026 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 506000 ------------------------------------------------- ----------- 2025-04-04 23:16:04 | [pearl_trainer] epoch #233 | Training... 2025-04-04 23:18:44 | [pearl_trainer] epoch #233 | Evaluating... 2025-04-04 23:18:44 | [pearl_trainer] epoch #233 | Sampling for adapation and meta-testing... 2025-04-04 23:23:00 | [pearl_trainer] epoch #233 | Finished meta-testing... 2025-04-04 23:23:00 | [pearl_trainer] epoch #233 | Saving snapshot... 2025-04-04 23:23:01 | [pearl_trainer] epoch #233 | Saved 2025-04-04 23:23:01 | [pearl_trainer] epoch #233 | Time 111244.99 s 2025-04-04 23:23:01 | [pearl_trainer] epoch #233 | EpochTime 460.29 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -188.933 MetaTest/Average/AverageReturn -188.933 MetaTest/Average/Iteration 233 MetaTest/Average/MaxReturn -93.4972 MetaTest/Average/MinReturn -250.993 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 52.3405 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -188.933 MetaTest/__unnamed_task__/AverageReturn -188.933 MetaTest/__unnamed_task__/Iteration 233 MetaTest/__unnamed_task__/MaxReturn -93.4972 MetaTest/__unnamed_task__/MinReturn -250.993 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 52.3405 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 508000 ------------------------------------------------- ----------- 2025-04-04 23:23:48 | [pearl_trainer] epoch #234 | Training... 2025-04-04 23:26:23 | [pearl_trainer] epoch #234 | Evaluating... 2025-04-04 23:26:23 | [pearl_trainer] epoch #234 | Sampling for adapation and meta-testing... 2025-04-04 23:31:00 | [pearl_trainer] epoch #234 | Finished meta-testing... 2025-04-04 23:31:00 | [pearl_trainer] epoch #234 | Saving snapshot... 2025-04-04 23:31:01 | [pearl_trainer] epoch #234 | Saved 2025-04-04 23:31:01 | [pearl_trainer] epoch #234 | Time 111725.08 s 2025-04-04 23:31:01 | [pearl_trainer] epoch #234 | EpochTime 480.09 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -204.648 MetaTest/Average/AverageReturn -204.648 MetaTest/Average/Iteration 234 MetaTest/Average/MaxReturn -173.06 MetaTest/Average/MinReturn -276.781 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 38.9178 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -204.648 MetaTest/__unnamed_task__/AverageReturn -204.648 MetaTest/__unnamed_task__/Iteration 234 MetaTest/__unnamed_task__/MaxReturn -173.06 MetaTest/__unnamed_task__/MinReturn -276.781 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 38.9178 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 510000 ------------------------------------------------- ----------- 2025-04-04 23:31:51 | [pearl_trainer] epoch #235 | Training... 2025-04-04 23:34:32 | [pearl_trainer] epoch #235 | Evaluating... 2025-04-04 23:34:32 | [pearl_trainer] epoch #235 | Sampling for adapation and meta-testing... 2025-04-04 23:39:02 | [pearl_trainer] epoch #235 | Finished meta-testing... 2025-04-04 23:39:02 | [pearl_trainer] epoch #235 | Saving snapshot... 2025-04-04 23:39:04 | [pearl_trainer] epoch #235 | Saved 2025-04-04 23:39:04 | [pearl_trainer] epoch #235 | Time 112207.29 s 2025-04-04 23:39:04 | [pearl_trainer] epoch #235 | EpochTime 482.21 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -191.298 MetaTest/Average/AverageReturn -191.298 MetaTest/Average/Iteration 235 MetaTest/Average/MaxReturn -142.949 MetaTest/Average/MinReturn -238.67 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.2993 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -191.298 MetaTest/__unnamed_task__/AverageReturn -191.298 MetaTest/__unnamed_task__/Iteration 235 MetaTest/__unnamed_task__/MaxReturn -142.949 MetaTest/__unnamed_task__/MinReturn -238.67 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.2993 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 512000 ------------------------------------------------- ----------- 2025-04-04 23:39:52 | [pearl_trainer] epoch #236 | Training... 2025-04-04 23:42:36 | [pearl_trainer] epoch #236 | Evaluating... 2025-04-04 23:42:36 | [pearl_trainer] epoch #236 | Sampling for adapation and meta-testing... 2025-04-04 23:47:18 | [pearl_trainer] epoch #236 | Finished meta-testing... 2025-04-04 23:47:18 | [pearl_trainer] epoch #236 | Saving snapshot... 2025-04-04 23:47:19 | [pearl_trainer] epoch #236 | Saved 2025-04-04 23:47:19 | [pearl_trainer] epoch #236 | Time 112702.82 s 2025-04-04 23:47:19 | [pearl_trainer] epoch #236 | EpochTime 495.53 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -228.576 MetaTest/Average/AverageReturn -228.576 MetaTest/Average/Iteration 236 MetaTest/Average/MaxReturn -144.68 MetaTest/Average/MinReturn -328.314 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 58.9945 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -228.576 MetaTest/__unnamed_task__/AverageReturn -228.576 MetaTest/__unnamed_task__/Iteration 236 MetaTest/__unnamed_task__/MaxReturn -144.68 MetaTest/__unnamed_task__/MinReturn -328.314 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 58.9945 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 514000 ------------------------------------------------- ----------- 2025-04-04 23:48:11 | [pearl_trainer] epoch #237 | Training... 2025-04-04 23:50:54 | [pearl_trainer] epoch #237 | Evaluating... 2025-04-04 23:50:54 | [pearl_trainer] epoch #237 | Sampling for adapation and meta-testing... 2025-04-04 23:55:17 | [pearl_trainer] epoch #237 | Finished meta-testing... 2025-04-04 23:55:17 | [pearl_trainer] epoch #237 | Saving snapshot... 2025-04-04 23:55:18 | [pearl_trainer] epoch #237 | Saved 2025-04-04 23:55:18 | [pearl_trainer] epoch #237 | Time 113181.84 s 2025-04-04 23:55:18 | [pearl_trainer] epoch #237 | EpochTime 479.01 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -222.491 MetaTest/Average/AverageReturn -222.491 MetaTest/Average/Iteration 237 MetaTest/Average/MaxReturn -84.6831 MetaTest/Average/MinReturn -352 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 85.9313 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -222.491 MetaTest/__unnamed_task__/AverageReturn -222.491 MetaTest/__unnamed_task__/Iteration 237 MetaTest/__unnamed_task__/MaxReturn -84.6831 MetaTest/__unnamed_task__/MinReturn -352 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 85.9313 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 516000 ------------------------------------------------- ----------- 2025-04-04 23:56:07 | [pearl_trainer] epoch #238 | Training... 2025-04-04 23:58:47 | [pearl_trainer] epoch #238 | Evaluating... 2025-04-04 23:58:47 | [pearl_trainer] epoch #238 | Sampling for adapation and meta-testing... 2025-04-05 00:03:06 | [pearl_trainer] epoch #238 | Finished meta-testing... 2025-04-05 00:03:06 | [pearl_trainer] epoch #238 | Saving snapshot... 2025-04-05 00:03:07 | [pearl_trainer] epoch #238 | Saved 2025-04-05 00:03:07 | [pearl_trainer] epoch #238 | Time 113651.09 s 2025-04-05 00:03:07 | [pearl_trainer] epoch #238 | EpochTime 469.25 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -236.353 MetaTest/Average/AverageReturn -236.353 MetaTest/Average/Iteration 238 MetaTest/Average/MaxReturn -215.189 MetaTest/Average/MinReturn -249.02 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 12.2935 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -236.353 MetaTest/__unnamed_task__/AverageReturn -236.353 MetaTest/__unnamed_task__/Iteration 238 MetaTest/__unnamed_task__/MaxReturn -215.189 MetaTest/__unnamed_task__/MinReturn -249.02 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 12.2935 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 518000 ------------------------------------------------- ----------- 2025-04-05 00:03:50 | [pearl_trainer] epoch #239 | Training... 2025-04-05 00:06:35 | [pearl_trainer] epoch #239 | Evaluating... 2025-04-05 00:06:35 | [pearl_trainer] epoch #239 | Sampling for adapation and meta-testing... 2025-04-05 00:10:28 | [pearl_trainer] epoch #239 | Finished meta-testing... 2025-04-05 00:10:28 | [pearl_trainer] epoch #239 | Saving snapshot... 2025-04-05 00:10:30 | [pearl_trainer] epoch #239 | Saved 2025-04-05 00:10:30 | [pearl_trainer] epoch #239 | Time 114093.26 s 2025-04-05 00:10:30 | [pearl_trainer] epoch #239 | EpochTime 442.16 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -305.011 MetaTest/Average/AverageReturn -305.011 MetaTest/Average/Iteration 239 MetaTest/Average/MaxReturn -258.599 MetaTest/Average/MinReturn -359.337 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.1173 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -305.011 MetaTest/__unnamed_task__/AverageReturn -305.011 MetaTest/__unnamed_task__/Iteration 239 MetaTest/__unnamed_task__/MaxReturn -258.599 MetaTest/__unnamed_task__/MinReturn -359.337 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.1173 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 520000 ------------------------------------------------- ----------- 2025-04-05 00:11:11 | [pearl_trainer] epoch #240 | Training... 2025-04-05 00:13:41 | [pearl_trainer] epoch #240 | Evaluating... 2025-04-05 00:13:41 | [pearl_trainer] epoch #240 | Sampling for adapation and meta-testing... 2025-04-05 00:17:28 | [pearl_trainer] epoch #240 | Finished meta-testing... 2025-04-05 00:17:28 | [pearl_trainer] epoch #240 | Saving snapshot... 2025-04-05 00:17:29 | [pearl_trainer] epoch #240 | Saved 2025-04-05 00:17:29 | [pearl_trainer] epoch #240 | Time 114513.10 s 2025-04-05 00:17:29 | [pearl_trainer] epoch #240 | EpochTime 419.84 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -299.462 MetaTest/Average/AverageReturn -299.462 MetaTest/Average/Iteration 240 MetaTest/Average/MaxReturn -247.204 MetaTest/Average/MinReturn -356.301 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 42.6113 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -299.462 MetaTest/__unnamed_task__/AverageReturn -299.462 MetaTest/__unnamed_task__/Iteration 240 MetaTest/__unnamed_task__/MaxReturn -247.204 MetaTest/__unnamed_task__/MinReturn -356.301 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 42.6113 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 522000 ------------------------------------------------- ----------- 2025-04-05 00:18:19 | [pearl_trainer] epoch #241 | Training... 2025-04-05 00:21:03 | [pearl_trainer] epoch #241 | Evaluating... 2025-04-05 00:21:03 | [pearl_trainer] epoch #241 | Sampling for adapation and meta-testing... 2025-04-05 00:24:57 | [pearl_trainer] epoch #241 | Finished meta-testing... 2025-04-05 00:24:57 | [pearl_trainer] epoch #241 | Saving snapshot... 2025-04-05 00:24:58 | [pearl_trainer] epoch #241 | Saved 2025-04-05 00:24:58 | [pearl_trainer] epoch #241 | Time 114961.58 s 2025-04-05 00:24:58 | [pearl_trainer] epoch #241 | EpochTime 448.48 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -262.196 MetaTest/Average/AverageReturn -262.196 MetaTest/Average/Iteration 241 MetaTest/Average/MaxReturn -198.54 MetaTest/Average/MinReturn -333.739 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 46.6624 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -262.196 MetaTest/__unnamed_task__/AverageReturn -262.196 MetaTest/__unnamed_task__/Iteration 241 MetaTest/__unnamed_task__/MaxReturn -198.54 MetaTest/__unnamed_task__/MinReturn -333.739 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 46.6624 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 524000 ------------------------------------------------- ----------- 2025-04-05 00:25:44 | [pearl_trainer] epoch #242 | Training... 2025-04-05 00:28:18 | [pearl_trainer] epoch #242 | Evaluating... 2025-04-05 00:28:18 | [pearl_trainer] epoch #242 | Sampling for adapation and meta-testing... 2025-04-05 00:32:13 | [pearl_trainer] epoch #242 | Finished meta-testing... 2025-04-05 00:32:13 | [pearl_trainer] epoch #242 | Saving snapshot... 2025-04-05 00:32:14 | [pearl_trainer] epoch #242 | Saved 2025-04-05 00:32:14 | [pearl_trainer] epoch #242 | Time 115398.04 s 2025-04-05 00:32:14 | [pearl_trainer] epoch #242 | EpochTime 436.46 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -281.331 MetaTest/Average/AverageReturn -281.331 MetaTest/Average/Iteration 242 MetaTest/Average/MaxReturn -209.338 MetaTest/Average/MinReturn -325.781 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 39.7081 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -281.331 MetaTest/__unnamed_task__/AverageReturn -281.331 MetaTest/__unnamed_task__/Iteration 242 MetaTest/__unnamed_task__/MaxReturn -209.338 MetaTest/__unnamed_task__/MinReturn -325.781 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 39.7081 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 526000 ------------------------------------------------- ----------- 2025-04-05 00:32:58 | [pearl_trainer] epoch #243 | Training... 2025-04-05 00:35:35 | [pearl_trainer] epoch #243 | Evaluating... 2025-04-05 00:35:35 | [pearl_trainer] epoch #243 | Sampling for adapation and meta-testing... 2025-04-05 00:39:40 | [pearl_trainer] epoch #243 | Finished meta-testing... 2025-04-05 00:39:40 | [pearl_trainer] epoch #243 | Saving snapshot... 2025-04-05 00:39:41 | [pearl_trainer] epoch #243 | Saved 2025-04-05 00:39:41 | [pearl_trainer] epoch #243 | Time 115844.70 s 2025-04-05 00:39:41 | [pearl_trainer] epoch #243 | EpochTime 446.66 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -264.943 MetaTest/Average/AverageReturn -264.943 MetaTest/Average/Iteration 243 MetaTest/Average/MaxReturn -235.715 MetaTest/Average/MinReturn -297.701 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 23.6059 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -264.943 MetaTest/__unnamed_task__/AverageReturn -264.943 MetaTest/__unnamed_task__/Iteration 243 MetaTest/__unnamed_task__/MaxReturn -235.715 MetaTest/__unnamed_task__/MinReturn -297.701 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 23.6059 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 528000 ------------------------------------------------- ----------- 2025-04-05 00:40:26 | [pearl_trainer] epoch #244 | Training... 2025-04-05 00:43:06 | [pearl_trainer] epoch #244 | Evaluating... 2025-04-05 00:43:06 | [pearl_trainer] epoch #244 | Sampling for adapation and meta-testing... 2025-04-05 00:47:36 | [pearl_trainer] epoch #244 | Finished meta-testing... 2025-04-05 00:47:36 | [pearl_trainer] epoch #244 | Saving snapshot... 2025-04-05 00:47:38 | [pearl_trainer] epoch #244 | Saved 2025-04-05 00:47:38 | [pearl_trainer] epoch #244 | Time 116321.19 s 2025-04-05 00:47:38 | [pearl_trainer] epoch #244 | EpochTime 476.49 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -235.035 MetaTest/Average/AverageReturn -235.035 MetaTest/Average/Iteration 244 MetaTest/Average/MaxReturn -161.317 MetaTest/Average/MinReturn -285.876 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 45.3995 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -235.035 MetaTest/__unnamed_task__/AverageReturn -235.035 MetaTest/__unnamed_task__/Iteration 244 MetaTest/__unnamed_task__/MaxReturn -161.317 MetaTest/__unnamed_task__/MinReturn -285.876 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 45.3995 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 530000 ------------------------------------------------- ----------- 2025-04-05 00:48:25 | [pearl_trainer] epoch #245 | Training... 2025-04-05 00:51:12 | [pearl_trainer] epoch #245 | Evaluating... 2025-04-05 00:51:12 | [pearl_trainer] epoch #245 | Sampling for adapation and meta-testing... 2025-04-05 00:55:40 | [pearl_trainer] epoch #245 | Finished meta-testing... 2025-04-05 00:55:40 | [pearl_trainer] epoch #245 | Saving snapshot... 2025-04-05 00:55:41 | [pearl_trainer] epoch #245 | Saved 2025-04-05 00:55:41 | [pearl_trainer] epoch #245 | Time 116804.52 s 2025-04-05 00:55:41 | [pearl_trainer] epoch #245 | EpochTime 483.32 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -244.152 MetaTest/Average/AverageReturn -244.152 MetaTest/Average/Iteration 245 MetaTest/Average/MaxReturn -188.983 MetaTest/Average/MinReturn -288.988 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 40.3449 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -244.152 MetaTest/__unnamed_task__/AverageReturn -244.152 MetaTest/__unnamed_task__/Iteration 245 MetaTest/__unnamed_task__/MaxReturn -188.983 MetaTest/__unnamed_task__/MinReturn -288.988 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 40.3449 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 532000 ------------------------------------------------- ----------- 2025-04-05 00:56:27 | [pearl_trainer] epoch #246 | Training... 2025-04-05 00:59:10 | [pearl_trainer] epoch #246 | Evaluating... 2025-04-05 00:59:10 | [pearl_trainer] epoch #246 | Sampling for adapation and meta-testing... 2025-04-05 01:03:23 | [pearl_trainer] epoch #246 | Finished meta-testing... 2025-04-05 01:03:23 | [pearl_trainer] epoch #246 | Saving snapshot... 2025-04-05 01:03:25 | [pearl_trainer] epoch #246 | Saved 2025-04-05 01:03:25 | [pearl_trainer] epoch #246 | Time 117268.52 s 2025-04-05 01:03:25 | [pearl_trainer] epoch #246 | EpochTime 464.00 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -249.051 MetaTest/Average/AverageReturn -249.051 MetaTest/Average/Iteration 246 MetaTest/Average/MaxReturn -234.872 MetaTest/Average/MinReturn -264.108 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 10.7962 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -249.051 MetaTest/__unnamed_task__/AverageReturn -249.051 MetaTest/__unnamed_task__/Iteration 246 MetaTest/__unnamed_task__/MaxReturn -234.872 MetaTest/__unnamed_task__/MinReturn -264.108 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 10.7962 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 534000 ------------------------------------------------- ----------- 2025-04-05 01:04:11 | [pearl_trainer] epoch #247 | Training... 2025-04-05 01:06:56 | [pearl_trainer] epoch #247 | Evaluating... 2025-04-05 01:06:56 | [pearl_trainer] epoch #247 | Sampling for adapation and meta-testing... 2025-04-05 01:10:52 | [pearl_trainer] epoch #247 | Finished meta-testing... 2025-04-05 01:10:52 | [pearl_trainer] epoch #247 | Saving snapshot... 2025-04-05 01:10:53 | [pearl_trainer] epoch #247 | Saved 2025-04-05 01:10:53 | [pearl_trainer] epoch #247 | Time 117716.57 s 2025-04-05 01:10:53 | [pearl_trainer] epoch #247 | EpochTime 448.04 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -295.857 MetaTest/Average/AverageReturn -295.857 MetaTest/Average/Iteration 247 MetaTest/Average/MaxReturn -232.575 MetaTest/Average/MinReturn -343.512 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.1002 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -295.857 MetaTest/__unnamed_task__/AverageReturn -295.857 MetaTest/__unnamed_task__/Iteration 247 MetaTest/__unnamed_task__/MaxReturn -232.575 MetaTest/__unnamed_task__/MinReturn -343.512 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.1002 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 536000 ------------------------------------------------- ----------- 2025-04-05 01:11:38 | [pearl_trainer] epoch #248 | Training... 2025-04-05 01:14:17 | [pearl_trainer] epoch #248 | Evaluating... 2025-04-05 01:14:17 | [pearl_trainer] epoch #248 | Sampling for adapation and meta-testing... 2025-04-05 01:18:12 | [pearl_trainer] epoch #248 | Finished meta-testing... 2025-04-05 01:18:12 | [pearl_trainer] epoch #248 | Saving snapshot... 2025-04-05 01:18:14 | [pearl_trainer] epoch #248 | Saved 2025-04-05 01:18:14 | [pearl_trainer] epoch #248 | Time 118157.35 s 2025-04-05 01:18:14 | [pearl_trainer] epoch #248 | EpochTime 440.78 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -242.844 MetaTest/Average/AverageReturn -242.844 MetaTest/Average/Iteration 248 MetaTest/Average/MaxReturn -140.483 MetaTest/Average/MinReturn -319.82 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 63.5495 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -242.844 MetaTest/__unnamed_task__/AverageReturn -242.844 MetaTest/__unnamed_task__/Iteration 248 MetaTest/__unnamed_task__/MaxReturn -140.483 MetaTest/__unnamed_task__/MinReturn -319.82 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 63.5495 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 538000 ------------------------------------------------- ----------- 2025-04-05 01:18:59 | [pearl_trainer] epoch #249 | Training... 2025-04-05 01:21:42 | [pearl_trainer] epoch #249 | Evaluating... 2025-04-05 01:21:42 | [pearl_trainer] epoch #249 | Sampling for adapation and meta-testing... 2025-04-05 01:25:47 | [pearl_trainer] epoch #249 | Finished meta-testing... 2025-04-05 01:25:47 | [pearl_trainer] epoch #249 | Saving snapshot... 2025-04-05 01:25:49 | [pearl_trainer] epoch #249 | Saved 2025-04-05 01:25:49 | [pearl_trainer] epoch #249 | Time 118612.29 s 2025-04-05 01:25:49 | [pearl_trainer] epoch #249 | EpochTime 454.94 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -289.909 MetaTest/Average/AverageReturn -289.909 MetaTest/Average/Iteration 249 MetaTest/Average/MaxReturn -270.963 MetaTest/Average/MinReturn -314.53 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 18.743 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -289.909 MetaTest/__unnamed_task__/AverageReturn -289.909 MetaTest/__unnamed_task__/Iteration 249 MetaTest/__unnamed_task__/MaxReturn -270.963 MetaTest/__unnamed_task__/MinReturn -314.53 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 18.743 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 540000 ------------------------------------------------- ---------- 2025-04-05 01:26:35 | [pearl_trainer] epoch #250 | Training... 2025-04-05 01:29:18 | [pearl_trainer] epoch #250 | Evaluating... 2025-04-05 01:29:18 | [pearl_trainer] epoch #250 | Sampling for adapation and meta-testing... 2025-04-05 01:33:14 | [pearl_trainer] epoch #250 | Finished meta-testing... 2025-04-05 01:33:14 | [pearl_trainer] epoch #250 | Saving snapshot... 2025-04-05 01:33:15 | [pearl_trainer] epoch #250 | Saved 2025-04-05 01:33:15 | [pearl_trainer] epoch #250 | Time 119059.16 s 2025-04-05 01:33:15 | [pearl_trainer] epoch #250 | EpochTime 446.87 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -289.163 MetaTest/Average/AverageReturn -289.163 MetaTest/Average/Iteration 250 MetaTest/Average/MaxReturn -243.931 MetaTest/Average/MinReturn -378.14 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 48.995 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -289.163 MetaTest/__unnamed_task__/AverageReturn -289.163 MetaTest/__unnamed_task__/Iteration 250 MetaTest/__unnamed_task__/MaxReturn -243.931 MetaTest/__unnamed_task__/MinReturn -378.14 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 48.995 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 542000 ------------------------------------------------- ---------- 2025-04-05 01:34:01 | [pearl_trainer] epoch #251 | Training... 2025-04-05 01:36:45 | [pearl_trainer] epoch #251 | Evaluating... 2025-04-05 01:36:45 | [pearl_trainer] epoch #251 | Sampling for adapation and meta-testing... 2025-04-05 01:40:53 | [pearl_trainer] epoch #251 | Finished meta-testing... 2025-04-05 01:40:53 | [pearl_trainer] epoch #251 | Saving snapshot... 2025-04-05 01:40:54 | [pearl_trainer] epoch #251 | Saved 2025-04-05 01:40:54 | [pearl_trainer] epoch #251 | Time 119517.83 s 2025-04-05 01:40:54 | [pearl_trainer] epoch #251 | EpochTime 458.67 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -325.509 MetaTest/Average/AverageReturn -325.509 MetaTest/Average/Iteration 251 MetaTest/Average/MaxReturn -280.223 MetaTest/Average/MinReturn -377.763 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.7787 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -325.509 MetaTest/__unnamed_task__/AverageReturn -325.509 MetaTest/__unnamed_task__/Iteration 251 MetaTest/__unnamed_task__/MaxReturn -280.223 MetaTest/__unnamed_task__/MinReturn -377.763 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.7787 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 544000 ------------------------------------------------- ----------- 2025-04-05 01:41:40 | [pearl_trainer] epoch #252 | Training... 2025-04-05 01:44:24 | [pearl_trainer] epoch #252 | Evaluating... 2025-04-05 01:44:24 | [pearl_trainer] epoch #252 | Sampling for adapation and meta-testing... 2025-04-05 01:48:15 | [pearl_trainer] epoch #252 | Finished meta-testing... 2025-04-05 01:48:15 | [pearl_trainer] epoch #252 | Saving snapshot... 2025-04-05 01:48:17 | [pearl_trainer] epoch #252 | Saved 2025-04-05 01:48:17 | [pearl_trainer] epoch #252 | Time 119960.50 s 2025-04-05 01:48:17 | [pearl_trainer] epoch #252 | EpochTime 442.67 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -324.472 MetaTest/Average/AverageReturn -324.472 MetaTest/Average/Iteration 252 MetaTest/Average/MaxReturn -285.872 MetaTest/Average/MinReturn -351.784 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 24.9571 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -324.472 MetaTest/__unnamed_task__/AverageReturn -324.472 MetaTest/__unnamed_task__/Iteration 252 MetaTest/__unnamed_task__/MaxReturn -285.872 MetaTest/__unnamed_task__/MinReturn -351.784 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 24.9571 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 546000 ------------------------------------------------- ----------- 2025-04-05 01:48:59 | [pearl_trainer] epoch #253 | Training... 2025-04-05 01:51:36 | [pearl_trainer] epoch #253 | Evaluating... 2025-04-05 01:51:36 | [pearl_trainer] epoch #253 | Sampling for adapation and meta-testing... 2025-04-05 01:55:36 | [pearl_trainer] epoch #253 | Finished meta-testing... 2025-04-05 01:55:36 | [pearl_trainer] epoch #253 | Saving snapshot... 2025-04-05 01:55:37 | [pearl_trainer] epoch #253 | Saved 2025-04-05 01:55:37 | [pearl_trainer] epoch #253 | Time 120400.98 s 2025-04-05 01:55:37 | [pearl_trainer] epoch #253 | EpochTime 440.48 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -295.223 MetaTest/Average/AverageReturn -295.223 MetaTest/Average/Iteration 253 MetaTest/Average/MaxReturn -258.187 MetaTest/Average/MinReturn -356.249 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 41.4052 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -295.223 MetaTest/__unnamed_task__/AverageReturn -295.223 MetaTest/__unnamed_task__/Iteration 253 MetaTest/__unnamed_task__/MaxReturn -258.187 MetaTest/__unnamed_task__/MinReturn -356.249 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 41.4052 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 548000 ------------------------------------------------- ----------- 2025-04-05 01:56:20 | [pearl_trainer] epoch #254 | Training... 2025-04-05 01:59:03 | [pearl_trainer] epoch #254 | Evaluating... 2025-04-05 01:59:03 | [pearl_trainer] epoch #254 | Sampling for adapation and meta-testing... 2025-04-05 02:02:53 | [pearl_trainer] epoch #254 | Finished meta-testing... 2025-04-05 02:02:53 | [pearl_trainer] epoch #254 | Saving snapshot... 2025-04-05 02:02:55 | [pearl_trainer] epoch #254 | Saved 2025-04-05 02:02:55 | [pearl_trainer] epoch #254 | Time 120838.24 s 2025-04-05 02:02:55 | [pearl_trainer] epoch #254 | EpochTime 437.27 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -274.643 MetaTest/Average/AverageReturn -274.643 MetaTest/Average/Iteration 254 MetaTest/Average/MaxReturn -219.07 MetaTest/Average/MinReturn -376.221 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 57.9036 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -274.643 MetaTest/__unnamed_task__/AverageReturn -274.643 MetaTest/__unnamed_task__/Iteration 254 MetaTest/__unnamed_task__/MaxReturn -219.07 MetaTest/__unnamed_task__/MinReturn -376.221 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 57.9036 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 550000 ------------------------------------------------- ----------- 2025-04-05 02:03:38 | [pearl_trainer] epoch #255 | Training... 2025-04-05 02:06:18 | [pearl_trainer] epoch #255 | Evaluating... 2025-04-05 02:06:18 | [pearl_trainer] epoch #255 | Sampling for adapation and meta-testing... 2025-04-05 02:10:22 | [pearl_trainer] epoch #255 | Finished meta-testing... 2025-04-05 02:10:22 | [pearl_trainer] epoch #255 | Saving snapshot... 2025-04-05 02:10:24 | [pearl_trainer] epoch #255 | Saved 2025-04-05 02:10:24 | [pearl_trainer] epoch #255 | Time 121287.33 s 2025-04-05 02:10:24 | [pearl_trainer] epoch #255 | EpochTime 449.08 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -247.23 MetaTest/Average/AverageReturn -247.23 MetaTest/Average/Iteration 255 MetaTest/Average/MaxReturn -221.315 MetaTest/Average/MinReturn -264.758 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 15.4459 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -247.23 MetaTest/__unnamed_task__/AverageReturn -247.23 MetaTest/__unnamed_task__/Iteration 255 MetaTest/__unnamed_task__/MaxReturn -221.315 MetaTest/__unnamed_task__/MinReturn -264.758 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 15.4459 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 552000 ------------------------------------------------- ----------- 2025-04-05 02:11:09 | [pearl_trainer] epoch #256 | Training... 2025-04-05 02:13:54 | [pearl_trainer] epoch #256 | Evaluating... 2025-04-05 02:13:54 | [pearl_trainer] epoch #256 | Sampling for adapation and meta-testing... 2025-04-05 02:18:05 | [pearl_trainer] epoch #256 | Finished meta-testing... 2025-04-05 02:18:05 | [pearl_trainer] epoch #256 | Saving snapshot... 2025-04-05 02:18:06 | [pearl_trainer] epoch #256 | Saved 2025-04-05 02:18:06 | [pearl_trainer] epoch #256 | Time 121749.66 s 2025-04-05 02:18:06 | [pearl_trainer] epoch #256 | EpochTime 462.32 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -288.013 MetaTest/Average/AverageReturn -288.013 MetaTest/Average/Iteration 256 MetaTest/Average/MaxReturn -257.482 MetaTest/Average/MinReturn -323.314 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 27.9303 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -288.013 MetaTest/__unnamed_task__/AverageReturn -288.013 MetaTest/__unnamed_task__/Iteration 256 MetaTest/__unnamed_task__/MaxReturn -257.482 MetaTest/__unnamed_task__/MinReturn -323.314 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 27.9303 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 554000 ------------------------------------------------- ----------- 2025-04-05 02:18:53 | [pearl_trainer] epoch #257 | Training... 2025-04-05 02:21:34 | [pearl_trainer] epoch #257 | Evaluating... 2025-04-05 02:21:34 | [pearl_trainer] epoch #257 | Sampling for adapation and meta-testing... 2025-04-05 02:25:57 | [pearl_trainer] epoch #257 | Finished meta-testing... 2025-04-05 02:25:57 | [pearl_trainer] epoch #257 | Saving snapshot... 2025-04-05 02:25:58 | [pearl_trainer] epoch #257 | Saved 2025-04-05 02:25:58 | [pearl_trainer] epoch #257 | Time 122221.98 s 2025-04-05 02:25:58 | [pearl_trainer] epoch #257 | EpochTime 472.32 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -224.609 MetaTest/Average/AverageReturn -224.609 MetaTest/Average/Iteration 257 MetaTest/Average/MaxReturn -165.734 MetaTest/Average/MinReturn -338.324 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 60.1569 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -224.609 MetaTest/__unnamed_task__/AverageReturn -224.609 MetaTest/__unnamed_task__/Iteration 257 MetaTest/__unnamed_task__/MaxReturn -165.734 MetaTest/__unnamed_task__/MinReturn -338.324 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 60.1569 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 556000 ------------------------------------------------- ----------- 2025-04-05 02:26:45 | [pearl_trainer] epoch #258 | Training... 2025-04-05 02:29:29 | [pearl_trainer] epoch #258 | Evaluating... 2025-04-05 02:29:29 | [pearl_trainer] epoch #258 | Sampling for adapation and meta-testing... 2025-04-05 02:34:31 | [pearl_trainer] epoch #258 | Finished meta-testing... 2025-04-05 02:34:31 | [pearl_trainer] epoch #258 | Saving snapshot... 2025-04-05 02:34:32 | [pearl_trainer] epoch #258 | Saved 2025-04-05 02:34:32 | [pearl_trainer] epoch #258 | Time 122736.13 s 2025-04-05 02:34:32 | [pearl_trainer] epoch #258 | EpochTime 514.15 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -218.477 MetaTest/Average/AverageReturn -218.477 MetaTest/Average/Iteration 258 MetaTest/Average/MaxReturn -167.148 MetaTest/Average/MinReturn -266.707 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.64 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -218.477 MetaTest/__unnamed_task__/AverageReturn -218.477 MetaTest/__unnamed_task__/Iteration 258 MetaTest/__unnamed_task__/MaxReturn -167.148 MetaTest/__unnamed_task__/MinReturn -266.707 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.64 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 558000 ------------------------------------------------- ---------- 2025-04-05 02:35:22 | [pearl_trainer] epoch #259 | Training... 2025-04-05 02:38:03 | [pearl_trainer] epoch #259 | Evaluating... 2025-04-05 02:38:03 | [pearl_trainer] epoch #259 | Sampling for adapation and meta-testing... 2025-04-05 02:42:59 | [pearl_trainer] epoch #259 | Finished meta-testing... 2025-04-05 02:42:59 | [pearl_trainer] epoch #259 | Saving snapshot... 2025-04-05 02:43:00 | [pearl_trainer] epoch #259 | Saved 2025-04-05 02:43:00 | [pearl_trainer] epoch #259 | Time 123243.65 s 2025-04-05 02:43:00 | [pearl_trainer] epoch #259 | EpochTime 507.52 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -183.203 MetaTest/Average/AverageReturn -183.203 MetaTest/Average/Iteration 259 MetaTest/Average/MaxReturn -116.76 MetaTest/Average/MinReturn -298.185 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 64.7501 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -183.203 MetaTest/__unnamed_task__/AverageReturn -183.203 MetaTest/__unnamed_task__/Iteration 259 MetaTest/__unnamed_task__/MaxReturn -116.76 MetaTest/__unnamed_task__/MinReturn -298.185 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 64.7501 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 560000 ------------------------------------------------- ----------- 2025-04-05 02:43:57 | [pearl_trainer] epoch #260 | Training... 2025-04-05 02:46:55 | [pearl_trainer] epoch #260 | Evaluating... 2025-04-05 02:46:55 | [pearl_trainer] epoch #260 | Sampling for adapation and meta-testing... 2025-04-05 02:51:53 | [pearl_trainer] epoch #260 | Finished meta-testing... 2025-04-05 02:51:53 | [pearl_trainer] epoch #260 | Saving snapshot... 2025-04-05 02:51:55 | [pearl_trainer] epoch #260 | Saved 2025-04-05 02:51:55 | [pearl_trainer] epoch #260 | Time 123778.22 s 2025-04-05 02:51:55 | [pearl_trainer] epoch #260 | EpochTime 534.56 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -202.066 MetaTest/Average/AverageReturn -202.066 MetaTest/Average/Iteration 260 MetaTest/Average/MaxReturn -141.577 MetaTest/Average/MinReturn -262.758 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 44.3895 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -202.066 MetaTest/__unnamed_task__/AverageReturn -202.066 MetaTest/__unnamed_task__/Iteration 260 MetaTest/__unnamed_task__/MaxReturn -141.577 MetaTest/__unnamed_task__/MinReturn -262.758 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 44.3895 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 562000 ------------------------------------------------- ----------- 2025-04-05 02:52:43 | [pearl_trainer] epoch #261 | Training... 2025-04-05 02:55:41 | [pearl_trainer] epoch #261 | Evaluating... 2025-04-05 02:55:41 | [pearl_trainer] epoch #261 | Sampling for adapation and meta-testing... 2025-04-05 03:00:13 | [pearl_trainer] epoch #261 | Finished meta-testing... 2025-04-05 03:00:13 | [pearl_trainer] epoch #261 | Saving snapshot... 2025-04-05 03:00:14 | [pearl_trainer] epoch #261 | Saved 2025-04-05 03:00:14 | [pearl_trainer] epoch #261 | Time 124277.77 s 2025-04-05 03:00:14 | [pearl_trainer] epoch #261 | EpochTime 499.56 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -269.331 MetaTest/Average/AverageReturn -269.331 MetaTest/Average/Iteration 261 MetaTest/Average/MaxReturn -142.688 MetaTest/Average/MinReturn -360.207 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 76.9077 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -269.331 MetaTest/__unnamed_task__/AverageReturn -269.331 MetaTest/__unnamed_task__/Iteration 261 MetaTest/__unnamed_task__/MaxReturn -142.688 MetaTest/__unnamed_task__/MinReturn -360.207 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 76.9077 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 564000 ------------------------------------------------- ----------- 2025-04-05 03:01:02 | [pearl_trainer] epoch #262 | Training... 2025-04-05 03:03:40 | [pearl_trainer] epoch #262 | Evaluating... 2025-04-05 03:03:40 | [pearl_trainer] epoch #262 | Sampling for adapation and meta-testing... 2025-04-05 03:08:05 | [pearl_trainer] epoch #262 | Finished meta-testing... 2025-04-05 03:08:05 | [pearl_trainer] epoch #262 | Saving snapshot... 2025-04-05 03:08:06 | [pearl_trainer] epoch #262 | Saved 2025-04-05 03:08:06 | [pearl_trainer] epoch #262 | Time 124749.56 s 2025-04-05 03:08:06 | [pearl_trainer] epoch #262 | EpochTime 471.79 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -274.219 MetaTest/Average/AverageReturn -274.219 MetaTest/Average/Iteration 262 MetaTest/Average/MaxReturn -245.31 MetaTest/Average/MinReturn -302.9 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 22.5987 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -274.219 MetaTest/__unnamed_task__/AverageReturn -274.219 MetaTest/__unnamed_task__/Iteration 262 MetaTest/__unnamed_task__/MaxReturn -245.31 MetaTest/__unnamed_task__/MinReturn -302.9 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 22.5987 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 566000 ------------------------------------------------- ----------- 2025-04-05 03:08:52 | [pearl_trainer] epoch #263 | Training... 2025-04-05 03:11:35 | [pearl_trainer] epoch #263 | Evaluating... 2025-04-05 03:11:35 | [pearl_trainer] epoch #263 | Sampling for adapation and meta-testing... 2025-04-05 03:15:38 | [pearl_trainer] epoch #263 | Finished meta-testing... 2025-04-05 03:15:38 | [pearl_trainer] epoch #263 | Saving snapshot... 2025-04-05 03:15:39 | [pearl_trainer] epoch #263 | Saved 2025-04-05 03:15:39 | [pearl_trainer] epoch #263 | Time 125202.84 s 2025-04-05 03:15:39 | [pearl_trainer] epoch #263 | EpochTime 453.28 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -274.084 MetaTest/Average/AverageReturn -274.084 MetaTest/Average/Iteration 263 MetaTest/Average/MaxReturn -134.48 MetaTest/Average/MinReturn -359.14 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 76.9453 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -274.084 MetaTest/__unnamed_task__/AverageReturn -274.084 MetaTest/__unnamed_task__/Iteration 263 MetaTest/__unnamed_task__/MaxReturn -134.48 MetaTest/__unnamed_task__/MinReturn -359.14 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 76.9453 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 568000 ------------------------------------------------- ----------- 2025-04-05 03:16:25 | [pearl_trainer] epoch #264 | Training... 2025-04-05 03:19:22 | [pearl_trainer] epoch #264 | Evaluating... 2025-04-05 03:19:22 | [pearl_trainer] epoch #264 | Sampling for adapation and meta-testing... 2025-04-05 03:23:45 | [pearl_trainer] epoch #264 | Finished meta-testing... 2025-04-05 03:23:45 | [pearl_trainer] epoch #264 | Saving snapshot... 2025-04-05 03:23:47 | [pearl_trainer] epoch #264 | Saved 2025-04-05 03:23:47 | [pearl_trainer] epoch #264 | Time 125690.22 s 2025-04-05 03:23:47 | [pearl_trainer] epoch #264 | EpochTime 487.37 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -220.222 MetaTest/Average/AverageReturn -220.222 MetaTest/Average/Iteration 264 MetaTest/Average/MaxReturn -195.979 MetaTest/Average/MinReturn -241.563 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 16.4317 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -220.222 MetaTest/__unnamed_task__/AverageReturn -220.222 MetaTest/__unnamed_task__/Iteration 264 MetaTest/__unnamed_task__/MaxReturn -195.979 MetaTest/__unnamed_task__/MinReturn -241.563 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 16.4317 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 570000 ------------------------------------------------- ----------- 2025-04-05 03:24:38 | [pearl_trainer] epoch #265 | Training... 2025-04-05 03:27:42 | [pearl_trainer] epoch #265 | Evaluating... 2025-04-05 03:27:42 | [pearl_trainer] epoch #265 | Sampling for adapation and meta-testing... 2025-04-05 03:32:14 | [pearl_trainer] epoch #265 | Finished meta-testing... 2025-04-05 03:32:14 | [pearl_trainer] epoch #265 | Saving snapshot... 2025-04-05 03:32:16 | [pearl_trainer] epoch #265 | Saved 2025-04-05 03:32:16 | [pearl_trainer] epoch #265 | Time 126199.26 s 2025-04-05 03:32:16 | [pearl_trainer] epoch #265 | EpochTime 509.04 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -267.689 MetaTest/Average/AverageReturn -267.689 MetaTest/Average/Iteration 265 MetaTest/Average/MaxReturn -178.502 MetaTest/Average/MinReturn -326.22 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 58.8361 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -267.689 MetaTest/__unnamed_task__/AverageReturn -267.689 MetaTest/__unnamed_task__/Iteration 265 MetaTest/__unnamed_task__/MaxReturn -178.502 MetaTest/__unnamed_task__/MinReturn -326.22 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 58.8361 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 572000 ------------------------------------------------- ----------- 2025-04-05 03:33:06 | [pearl_trainer] epoch #266 | Training... 2025-04-05 03:36:10 | [pearl_trainer] epoch #266 | Evaluating... 2025-04-05 03:36:10 | [pearl_trainer] epoch #266 | Sampling for adapation and meta-testing... 2025-04-05 03:40:56 | [pearl_trainer] epoch #266 | Finished meta-testing... 2025-04-05 03:40:56 | [pearl_trainer] epoch #266 | Saving snapshot... 2025-04-05 03:40:57 | [pearl_trainer] epoch #266 | Saved 2025-04-05 03:40:57 | [pearl_trainer] epoch #266 | Time 126721.09 s 2025-04-05 03:40:57 | [pearl_trainer] epoch #266 | EpochTime 521.83 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -187.062 MetaTest/Average/AverageReturn -187.062 MetaTest/Average/Iteration 266 MetaTest/Average/MaxReturn -92.5817 MetaTest/Average/MinReturn -230.666 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 49.9075 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -187.062 MetaTest/__unnamed_task__/AverageReturn -187.062 MetaTest/__unnamed_task__/Iteration 266 MetaTest/__unnamed_task__/MaxReturn -92.5817 MetaTest/__unnamed_task__/MinReturn -230.666 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 49.9075 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 574000 ------------------------------------------------- ----------- 2025-04-05 03:41:46 | [pearl_trainer] epoch #267 | Training... 2025-04-05 03:44:45 | [pearl_trainer] epoch #267 | Evaluating... 2025-04-05 03:44:45 | [pearl_trainer] epoch #267 | Sampling for adapation and meta-testing... 2025-04-05 03:49:24 | [pearl_trainer] epoch #267 | Finished meta-testing... 2025-04-05 03:49:24 | [pearl_trainer] epoch #267 | Saving snapshot... 2025-04-05 03:49:26 | [pearl_trainer] epoch #267 | Saved 2025-04-05 03:49:26 | [pearl_trainer] epoch #267 | Time 127229.63 s 2025-04-05 03:49:26 | [pearl_trainer] epoch #267 | EpochTime 508.53 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -168.671 MetaTest/Average/AverageReturn -168.671 MetaTest/Average/Iteration 267 MetaTest/Average/MaxReturn -114.077 MetaTest/Average/MinReturn -230.606 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 48.8981 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -168.671 MetaTest/__unnamed_task__/AverageReturn -168.671 MetaTest/__unnamed_task__/Iteration 267 MetaTest/__unnamed_task__/MaxReturn -114.077 MetaTest/__unnamed_task__/MinReturn -230.606 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 48.8981 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 576000 ------------------------------------------------- ----------- 2025-04-05 03:50:12 | [pearl_trainer] epoch #268 | Training... 2025-04-05 03:52:49 | [pearl_trainer] epoch #268 | Evaluating... 2025-04-05 03:52:49 | [pearl_trainer] epoch #268 | Sampling for adapation and meta-testing... 2025-04-05 03:57:22 | [pearl_trainer] epoch #268 | Finished meta-testing... 2025-04-05 03:57:22 | [pearl_trainer] epoch #268 | Saving snapshot... 2025-04-05 03:57:23 | [pearl_trainer] epoch #268 | Saved 2025-04-05 03:57:23 | [pearl_trainer] epoch #268 | Time 127706.82 s 2025-04-05 03:57:23 | [pearl_trainer] epoch #268 | EpochTime 477.19 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -225.739 MetaTest/Average/AverageReturn -225.739 MetaTest/Average/Iteration 268 MetaTest/Average/MaxReturn -173.194 MetaTest/Average/MinReturn -283.88 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.7679 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -225.739 MetaTest/__unnamed_task__/AverageReturn -225.739 MetaTest/__unnamed_task__/Iteration 268 MetaTest/__unnamed_task__/MaxReturn -173.194 MetaTest/__unnamed_task__/MinReturn -283.88 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.7679 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 578000 ------------------------------------------------- ----------- 2025-04-05 03:58:11 | [pearl_trainer] epoch #269 | Training... 2025-04-05 04:00:54 | [pearl_trainer] epoch #269 | Evaluating... 2025-04-05 04:00:54 | [pearl_trainer] epoch #269 | Sampling for adapation and meta-testing... 2025-04-05 04:05:28 | [pearl_trainer] epoch #269 | Finished meta-testing... 2025-04-05 04:05:28 | [pearl_trainer] epoch #269 | Saving snapshot... 2025-04-05 04:05:29 | [pearl_trainer] epoch #269 | Saved 2025-04-05 04:05:29 | [pearl_trainer] epoch #269 | Time 128192.77 s 2025-04-05 04:05:29 | [pearl_trainer] epoch #269 | EpochTime 485.95 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -226.916 MetaTest/Average/AverageReturn -226.916 MetaTest/Average/Iteration 269 MetaTest/Average/MaxReturn -131.277 MetaTest/Average/MinReturn -284.86 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 50.9922 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -226.916 MetaTest/__unnamed_task__/AverageReturn -226.916 MetaTest/__unnamed_task__/Iteration 269 MetaTest/__unnamed_task__/MaxReturn -131.277 MetaTest/__unnamed_task__/MinReturn -284.86 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 50.9922 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 580000 ------------------------------------------------- ----------- 2025-04-05 04:06:15 | [pearl_trainer] epoch #270 | Training... 2025-04-05 04:08:59 | [pearl_trainer] epoch #270 | Evaluating... 2025-04-05 04:08:59 | [pearl_trainer] epoch #270 | Sampling for adapation and meta-testing... 2025-04-05 04:13:33 | [pearl_trainer] epoch #270 | Finished meta-testing... 2025-04-05 04:13:33 | [pearl_trainer] epoch #270 | Saving snapshot... 2025-04-05 04:13:34 | [pearl_trainer] epoch #270 | Saved 2025-04-05 04:13:34 | [pearl_trainer] epoch #270 | Time 128677.70 s 2025-04-05 04:13:34 | [pearl_trainer] epoch #270 | EpochTime 484.93 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -227.555 MetaTest/Average/AverageReturn -227.555 MetaTest/Average/Iteration 270 MetaTest/Average/MaxReturn -167.244 MetaTest/Average/MinReturn -340.829 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 62.3366 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -227.555 MetaTest/__unnamed_task__/AverageReturn -227.555 MetaTest/__unnamed_task__/Iteration 270 MetaTest/__unnamed_task__/MaxReturn -167.244 MetaTest/__unnamed_task__/MinReturn -340.829 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 62.3366 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 582000 ------------------------------------------------- ----------- 2025-04-05 04:14:24 | [pearl_trainer] epoch #271 | Training... 2025-04-05 04:17:08 | [pearl_trainer] epoch #271 | Evaluating... 2025-04-05 04:17:08 | [pearl_trainer] epoch #271 | Sampling for adapation and meta-testing... 2025-04-05 04:21:27 | [pearl_trainer] epoch #271 | Finished meta-testing... 2025-04-05 04:21:27 | [pearl_trainer] epoch #271 | Saving snapshot... 2025-04-05 04:21:28 | [pearl_trainer] epoch #271 | Saved 2025-04-05 04:21:28 | [pearl_trainer] epoch #271 | Time 129151.69 s 2025-04-05 04:21:28 | [pearl_trainer] epoch #271 | EpochTime 473.99 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -262.037 MetaTest/Average/AverageReturn -262.037 MetaTest/Average/Iteration 271 MetaTest/Average/MaxReturn -222.69 MetaTest/Average/MinReturn -286.738 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 22.4748 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -262.037 MetaTest/__unnamed_task__/AverageReturn -262.037 MetaTest/__unnamed_task__/Iteration 271 MetaTest/__unnamed_task__/MaxReturn -222.69 MetaTest/__unnamed_task__/MinReturn -286.738 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 22.4748 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 584000 ------------------------------------------------- ----------- 2025-04-05 04:22:14 | [pearl_trainer] epoch #272 | Training... 2025-04-05 04:24:56 | [pearl_trainer] epoch #272 | Evaluating... 2025-04-05 04:24:56 | [pearl_trainer] epoch #272 | Sampling for adapation and meta-testing... 2025-04-05 04:29:08 | [pearl_trainer] epoch #272 | Finished meta-testing... 2025-04-05 04:29:08 | [pearl_trainer] epoch #272 | Saving snapshot... 2025-04-05 04:29:09 | [pearl_trainer] epoch #272 | Saved 2025-04-05 04:29:09 | [pearl_trainer] epoch #272 | Time 129612.72 s 2025-04-05 04:29:09 | [pearl_trainer] epoch #272 | EpochTime 461.02 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -254.028 MetaTest/Average/AverageReturn -254.028 MetaTest/Average/Iteration 272 MetaTest/Average/MaxReturn -201.76 MetaTest/Average/MinReturn -299.348 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 34.0469 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -254.028 MetaTest/__unnamed_task__/AverageReturn -254.028 MetaTest/__unnamed_task__/Iteration 272 MetaTest/__unnamed_task__/MaxReturn -201.76 MetaTest/__unnamed_task__/MinReturn -299.348 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 34.0469 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 586000 ------------------------------------------------- ----------- 2025-04-05 04:29:51 | [pearl_trainer] epoch #273 | Training... 2025-04-05 04:32:32 | [pearl_trainer] epoch #273 | Evaluating... 2025-04-05 04:32:32 | [pearl_trainer] epoch #273 | Sampling for adapation and meta-testing... 2025-04-05 04:36:59 | [pearl_trainer] epoch #273 | Finished meta-testing... 2025-04-05 04:36:59 | [pearl_trainer] epoch #273 | Saving snapshot... 2025-04-05 04:37:01 | [pearl_trainer] epoch #273 | Saved 2025-04-05 04:37:01 | [pearl_trainer] epoch #273 | Time 130084.39 s 2025-04-05 04:37:01 | [pearl_trainer] epoch #273 | EpochTime 471.67 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -252.649 MetaTest/Average/AverageReturn -252.649 MetaTest/Average/Iteration 273 MetaTest/Average/MaxReturn -196.154 MetaTest/Average/MinReturn -301.743 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 34.7632 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -252.649 MetaTest/__unnamed_task__/AverageReturn -252.649 MetaTest/__unnamed_task__/Iteration 273 MetaTest/__unnamed_task__/MaxReturn -196.154 MetaTest/__unnamed_task__/MinReturn -301.743 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 34.7632 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 588000 ------------------------------------------------- ----------- 2025-04-05 04:37:48 | [pearl_trainer] epoch #274 | Training... 2025-04-05 04:40:33 | [pearl_trainer] epoch #274 | Evaluating... 2025-04-05 04:40:33 | [pearl_trainer] epoch #274 | Sampling for adapation and meta-testing... 2025-04-05 04:44:56 | [pearl_trainer] epoch #274 | Finished meta-testing... 2025-04-05 04:44:56 | [pearl_trainer] epoch #274 | Saving snapshot... 2025-04-05 04:44:57 | [pearl_trainer] epoch #274 | Saved 2025-04-05 04:44:57 | [pearl_trainer] epoch #274 | Time 130560.38 s 2025-04-05 04:44:57 | [pearl_trainer] epoch #274 | EpochTime 475.99 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -238.486 MetaTest/Average/AverageReturn -238.486 MetaTest/Average/Iteration 274 MetaTest/Average/MaxReturn -154.984 MetaTest/Average/MinReturn -317.39 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 55.1724 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -238.486 MetaTest/__unnamed_task__/AverageReturn -238.486 MetaTest/__unnamed_task__/Iteration 274 MetaTest/__unnamed_task__/MaxReturn -154.984 MetaTest/__unnamed_task__/MinReturn -317.39 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 55.1724 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 590000 ------------------------------------------------- ----------- 2025-04-05 04:45:47 | [pearl_trainer] epoch #275 | Training... 2025-04-05 04:48:31 | [pearl_trainer] epoch #275 | Evaluating... 2025-04-05 04:48:31 | [pearl_trainer] epoch #275 | Sampling for adapation and meta-testing... 2025-04-05 04:52:48 | [pearl_trainer] epoch #275 | Finished meta-testing... 2025-04-05 04:52:48 | [pearl_trainer] epoch #275 | Saving snapshot... 2025-04-05 04:52:50 | [pearl_trainer] epoch #275 | Saved 2025-04-05 04:52:50 | [pearl_trainer] epoch #275 | Time 131033.35 s 2025-04-05 04:52:50 | [pearl_trainer] epoch #275 | EpochTime 472.97 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -281.117 MetaTest/Average/AverageReturn -281.117 MetaTest/Average/Iteration 275 MetaTest/Average/MaxReturn -236.549 MetaTest/Average/MinReturn -338.649 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 38.2291 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -281.117 MetaTest/__unnamed_task__/AverageReturn -281.117 MetaTest/__unnamed_task__/Iteration 275 MetaTest/__unnamed_task__/MaxReturn -236.549 MetaTest/__unnamed_task__/MinReturn -338.649 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 38.2291 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 592000 ------------------------------------------------- ----------- 2025-04-05 04:53:39 | [pearl_trainer] epoch #276 | Training... 2025-04-05 04:56:22 | [pearl_trainer] epoch #276 | Evaluating... 2025-04-05 04:56:22 | [pearl_trainer] epoch #276 | Sampling for adapation and meta-testing... 2025-04-05 05:00:45 | [pearl_trainer] epoch #276 | Finished meta-testing... 2025-04-05 05:00:45 | [pearl_trainer] epoch #276 | Saving snapshot... 2025-04-05 05:00:46 | [pearl_trainer] epoch #276 | Saved 2025-04-05 05:00:46 | [pearl_trainer] epoch #276 | Time 131509.86 s 2025-04-05 05:00:46 | [pearl_trainer] epoch #276 | EpochTime 476.51 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -197.59 MetaTest/Average/AverageReturn -197.59 MetaTest/Average/Iteration 276 MetaTest/Average/MaxReturn -87.6275 MetaTest/Average/MinReturn -275.831 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 64.0757 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -197.59 MetaTest/__unnamed_task__/AverageReturn -197.59 MetaTest/__unnamed_task__/Iteration 276 MetaTest/__unnamed_task__/MaxReturn -87.6275 MetaTest/__unnamed_task__/MinReturn -275.831 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 64.0757 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 594000 ------------------------------------------------- ----------- 2025-04-05 05:01:35 | [pearl_trainer] epoch #277 | Training... 2025-04-05 05:04:16 | [pearl_trainer] epoch #277 | Evaluating... 2025-04-05 05:04:16 | [pearl_trainer] epoch #277 | Sampling for adapation and meta-testing... 2025-04-05 05:08:43 | [pearl_trainer] epoch #277 | Finished meta-testing... 2025-04-05 05:08:43 | [pearl_trainer] epoch #277 | Saving snapshot... 2025-04-05 05:08:44 | [pearl_trainer] epoch #277 | Saved 2025-04-05 05:08:44 | [pearl_trainer] epoch #277 | Time 131987.66 s 2025-04-05 05:08:44 | [pearl_trainer] epoch #277 | EpochTime 477.80 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -272.447 MetaTest/Average/AverageReturn -272.447 MetaTest/Average/Iteration 277 MetaTest/Average/MaxReturn -198.553 MetaTest/Average/MinReturn -348.688 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 57.2984 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -272.447 MetaTest/__unnamed_task__/AverageReturn -272.447 MetaTest/__unnamed_task__/Iteration 277 MetaTest/__unnamed_task__/MaxReturn -198.553 MetaTest/__unnamed_task__/MinReturn -348.688 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 57.2984 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 596000 ------------------------------------------------- ----------- 2025-04-05 05:09:35 | [pearl_trainer] epoch #278 | Training... 2025-04-05 05:12:16 | [pearl_trainer] epoch #278 | Evaluating... 2025-04-05 05:12:16 | [pearl_trainer] epoch #278 | Sampling for adapation and meta-testing... 2025-04-05 05:16:31 | [pearl_trainer] epoch #278 | Finished meta-testing... 2025-04-05 05:16:31 | [pearl_trainer] epoch #278 | Saving snapshot... 2025-04-05 05:16:32 | [pearl_trainer] epoch #278 | Saved 2025-04-05 05:16:32 | [pearl_trainer] epoch #278 | Time 132455.95 s 2025-04-05 05:16:32 | [pearl_trainer] epoch #278 | EpochTime 468.29 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -244.615 MetaTest/Average/AverageReturn -244.615 MetaTest/Average/Iteration 278 MetaTest/Average/MaxReturn -207.443 MetaTest/Average/MinReturn -313.166 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.3145 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -244.615 MetaTest/__unnamed_task__/AverageReturn -244.615 MetaTest/__unnamed_task__/Iteration 278 MetaTest/__unnamed_task__/MaxReturn -207.443 MetaTest/__unnamed_task__/MinReturn -313.166 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.3145 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 598000 ------------------------------------------------- ----------- 2025-04-05 05:17:20 | [pearl_trainer] epoch #279 | Training... 2025-04-05 05:20:02 | [pearl_trainer] epoch #279 | Evaluating... 2025-04-05 05:20:02 | [pearl_trainer] epoch #279 | Sampling for adapation and meta-testing... 2025-04-05 05:24:23 | [pearl_trainer] epoch #279 | Finished meta-testing... 2025-04-05 05:24:23 | [pearl_trainer] epoch #279 | Saving snapshot... 2025-04-05 05:24:25 | [pearl_trainer] epoch #279 | Saved 2025-04-05 05:24:25 | [pearl_trainer] epoch #279 | Time 132928.47 s 2025-04-05 05:24:25 | [pearl_trainer] epoch #279 | EpochTime 472.52 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -280.338 MetaTest/Average/AverageReturn -280.338 MetaTest/Average/Iteration 279 MetaTest/Average/MaxReturn -184.063 MetaTest/Average/MinReturn -350.748 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 57.1803 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -280.338 MetaTest/__unnamed_task__/AverageReturn -280.338 MetaTest/__unnamed_task__/Iteration 279 MetaTest/__unnamed_task__/MaxReturn -184.063 MetaTest/__unnamed_task__/MinReturn -350.748 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 57.1803 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 600000 ------------------------------------------------- ----------- 2025-04-05 05:25:10 | [pearl_trainer] epoch #280 | Training... 2025-04-05 05:27:56 | [pearl_trainer] epoch #280 | Evaluating... 2025-04-05 05:27:56 | [pearl_trainer] epoch #280 | Sampling for adapation and meta-testing... 2025-04-05 05:32:08 | [pearl_trainer] epoch #280 | Finished meta-testing... 2025-04-05 05:32:08 | [pearl_trainer] epoch #280 | Saving snapshot... 2025-04-05 05:32:09 | [pearl_trainer] epoch #280 | Saved 2025-04-05 05:32:09 | [pearl_trainer] epoch #280 | Time 133392.48 s 2025-04-05 05:32:09 | [pearl_trainer] epoch #280 | EpochTime 464.01 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -248 MetaTest/Average/AverageReturn -248 MetaTest/Average/Iteration 280 MetaTest/Average/MaxReturn -109.465 MetaTest/Average/MinReturn -329.633 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 75.6156 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -248 MetaTest/__unnamed_task__/AverageReturn -248 MetaTest/__unnamed_task__/Iteration 280 MetaTest/__unnamed_task__/MaxReturn -109.465 MetaTest/__unnamed_task__/MinReturn -329.633 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 75.6156 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 602000 ------------------------------------------------- ----------- 2025-04-05 05:32:57 | [pearl_trainer] epoch #281 | Training... 2025-04-05 05:35:40 | [pearl_trainer] epoch #281 | Evaluating... 2025-04-05 05:35:40 | [pearl_trainer] epoch #281 | Sampling for adapation and meta-testing... 2025-04-05 05:39:47 | [pearl_trainer] epoch #281 | Finished meta-testing... 2025-04-05 05:39:47 | [pearl_trainer] epoch #281 | Saving snapshot... 2025-04-05 05:39:49 | [pearl_trainer] epoch #281 | Saved 2025-04-05 05:39:49 | [pearl_trainer] epoch #281 | Time 133852.54 s 2025-04-05 05:39:49 | [pearl_trainer] epoch #281 | EpochTime 460.06 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -260.973 MetaTest/Average/AverageReturn -260.973 MetaTest/Average/Iteration 281 MetaTest/Average/MaxReturn -195.245 MetaTest/Average/MinReturn -322.596 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 44.1922 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -260.973 MetaTest/__unnamed_task__/AverageReturn -260.973 MetaTest/__unnamed_task__/Iteration 281 MetaTest/__unnamed_task__/MaxReturn -195.245 MetaTest/__unnamed_task__/MinReturn -322.596 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 44.1922 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 604000 ------------------------------------------------- ----------- 2025-04-05 05:40:37 | [pearl_trainer] epoch #282 | Training... 2025-04-05 05:43:29 | [pearl_trainer] epoch #282 | Evaluating... 2025-04-05 05:43:29 | [pearl_trainer] epoch #282 | Sampling for adapation and meta-testing... 2025-04-05 05:47:37 | [pearl_trainer] epoch #282 | Finished meta-testing... 2025-04-05 05:47:37 | [pearl_trainer] epoch #282 | Saving snapshot... 2025-04-05 05:47:38 | [pearl_trainer] epoch #282 | Saved 2025-04-05 05:47:38 | [pearl_trainer] epoch #282 | Time 134321.59 s 2025-04-05 05:47:38 | [pearl_trainer] epoch #282 | EpochTime 469.04 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -283.625 MetaTest/Average/AverageReturn -283.625 MetaTest/Average/Iteration 282 MetaTest/Average/MaxReturn -263.135 MetaTest/Average/MinReturn -325.829 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 22.1163 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -283.625 MetaTest/__unnamed_task__/AverageReturn -283.625 MetaTest/__unnamed_task__/Iteration 282 MetaTest/__unnamed_task__/MaxReturn -263.135 MetaTest/__unnamed_task__/MinReturn -325.829 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 22.1163 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 606000 ------------------------------------------------- ----------- 2025-04-05 05:48:25 | [pearl_trainer] epoch #283 | Training... 2025-04-05 05:51:32 | [pearl_trainer] epoch #283 | Evaluating... 2025-04-05 05:51:32 | [pearl_trainer] epoch #283 | Sampling for adapation and meta-testing... 2025-04-05 05:55:43 | [pearl_trainer] epoch #283 | Finished meta-testing... 2025-04-05 05:55:43 | [pearl_trainer] epoch #283 | Saving snapshot... 2025-04-05 05:55:44 | [pearl_trainer] epoch #283 | Saved 2025-04-05 05:55:44 | [pearl_trainer] epoch #283 | Time 134807.87 s 2025-04-05 05:55:44 | [pearl_trainer] epoch #283 | EpochTime 486.28 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -308.861 MetaTest/Average/AverageReturn -308.861 MetaTest/Average/Iteration 283 MetaTest/Average/MaxReturn -260.221 MetaTest/Average/MinReturn -327.625 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 24.9744 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -308.861 MetaTest/__unnamed_task__/AverageReturn -308.861 MetaTest/__unnamed_task__/Iteration 283 MetaTest/__unnamed_task__/MaxReturn -260.221 MetaTest/__unnamed_task__/MinReturn -327.625 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 24.9744 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 608000 ------------------------------------------------- ----------- 2025-04-05 05:56:29 | [pearl_trainer] epoch #284 | Training... 2025-04-05 05:59:35 | [pearl_trainer] epoch #284 | Evaluating... 2025-04-05 05:59:35 | [pearl_trainer] epoch #284 | Sampling for adapation and meta-testing... 2025-04-05 06:03:58 | [pearl_trainer] epoch #284 | Finished meta-testing... 2025-04-05 06:03:58 | [pearl_trainer] epoch #284 | Saving snapshot... 2025-04-05 06:03:59 | [pearl_trainer] epoch #284 | Saved 2025-04-05 06:03:59 | [pearl_trainer] epoch #284 | Time 135302.99 s 2025-04-05 06:03:59 | [pearl_trainer] epoch #284 | EpochTime 495.12 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -273.339 MetaTest/Average/AverageReturn -273.339 MetaTest/Average/Iteration 284 MetaTest/Average/MaxReturn -244.561 MetaTest/Average/MinReturn -309.995 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.3697 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -273.339 MetaTest/__unnamed_task__/AverageReturn -273.339 MetaTest/__unnamed_task__/Iteration 284 MetaTest/__unnamed_task__/MaxReturn -244.561 MetaTest/__unnamed_task__/MinReturn -309.995 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.3697 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 610000 ------------------------------------------------- ----------- 2025-04-05 06:04:45 | [pearl_trainer] epoch #285 | Training... 2025-04-05 06:07:25 | [pearl_trainer] epoch #285 | Evaluating... 2025-04-05 06:07:25 | [pearl_trainer] epoch #285 | Sampling for adapation and meta-testing... 2025-04-05 06:11:39 | [pearl_trainer] epoch #285 | Finished meta-testing... 2025-04-05 06:11:39 | [pearl_trainer] epoch #285 | Saving snapshot... 2025-04-05 06:11:41 | [pearl_trainer] epoch #285 | Saved 2025-04-05 06:11:41 | [pearl_trainer] epoch #285 | Time 135764.22 s 2025-04-05 06:11:41 | [pearl_trainer] epoch #285 | EpochTime 461.22 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -272.101 MetaTest/Average/AverageReturn -272.101 MetaTest/Average/Iteration 285 MetaTest/Average/MaxReturn -249.946 MetaTest/Average/MinReturn -315.431 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 25.9688 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -272.101 MetaTest/__unnamed_task__/AverageReturn -272.101 MetaTest/__unnamed_task__/Iteration 285 MetaTest/__unnamed_task__/MaxReturn -249.946 MetaTest/__unnamed_task__/MinReturn -315.431 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 25.9688 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 612000 ------------------------------------------------- ----------- 2025-04-05 06:12:25 | [pearl_trainer] epoch #286 | Training... 2025-04-05 06:15:08 | [pearl_trainer] epoch #286 | Evaluating... 2025-04-05 06:15:08 | [pearl_trainer] epoch #286 | Sampling for adapation and meta-testing... 2025-04-05 06:19:24 | [pearl_trainer] epoch #286 | Finished meta-testing... 2025-04-05 06:19:24 | [pearl_trainer] epoch #286 | Saving snapshot... 2025-04-05 06:19:25 | [pearl_trainer] epoch #286 | Saved 2025-04-05 06:19:25 | [pearl_trainer] epoch #286 | Time 136229.08 s 2025-04-05 06:19:25 | [pearl_trainer] epoch #286 | EpochTime 464.87 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -271.202 MetaTest/Average/AverageReturn -271.202 MetaTest/Average/Iteration 286 MetaTest/Average/MaxReturn -203.747 MetaTest/Average/MinReturn -332.423 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 44.4384 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -271.202 MetaTest/__unnamed_task__/AverageReturn -271.202 MetaTest/__unnamed_task__/Iteration 286 MetaTest/__unnamed_task__/MaxReturn -203.747 MetaTest/__unnamed_task__/MinReturn -332.423 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 44.4384 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 614000 ------------------------------------------------- ----------- 2025-04-05 06:20:10 | [pearl_trainer] epoch #287 | Training... 2025-04-05 06:23:09 | [pearl_trainer] epoch #287 | Evaluating... 2025-04-05 06:23:09 | [pearl_trainer] epoch #287 | Sampling for adapation and meta-testing... 2025-04-05 06:27:43 | [pearl_trainer] epoch #287 | Finished meta-testing... 2025-04-05 06:27:43 | [pearl_trainer] epoch #287 | Saving snapshot... 2025-04-05 06:27:45 | [pearl_trainer] epoch #287 | Saved 2025-04-05 06:27:45 | [pearl_trainer] epoch #287 | Time 136728.49 s 2025-04-05 06:27:45 | [pearl_trainer] epoch #287 | EpochTime 499.40 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -287.002 MetaTest/Average/AverageReturn -287.002 MetaTest/Average/Iteration 287 MetaTest/Average/MaxReturn -226.541 MetaTest/Average/MinReturn -358.697 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 45.2751 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -287.002 MetaTest/__unnamed_task__/AverageReturn -287.002 MetaTest/__unnamed_task__/Iteration 287 MetaTest/__unnamed_task__/MaxReturn -226.541 MetaTest/__unnamed_task__/MinReturn -358.697 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 45.2751 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 616000 ------------------------------------------------- ----------- 2025-04-05 06:28:27 | [pearl_trainer] epoch #288 | Training... 2025-04-05 06:31:12 | [pearl_trainer] epoch #288 | Evaluating... 2025-04-05 06:31:12 | [pearl_trainer] epoch #288 | Sampling for adapation and meta-testing... 2025-04-05 06:35:39 | [pearl_trainer] epoch #288 | Finished meta-testing... 2025-04-05 06:35:39 | [pearl_trainer] epoch #288 | Saving snapshot... 2025-04-05 06:35:40 | [pearl_trainer] epoch #288 | Saved 2025-04-05 06:35:40 | [pearl_trainer] epoch #288 | Time 137203.51 s 2025-04-05 06:35:40 | [pearl_trainer] epoch #288 | EpochTime 475.02 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -263.459 MetaTest/Average/AverageReturn -263.459 MetaTest/Average/Iteration 288 MetaTest/Average/MaxReturn -246.962 MetaTest/Average/MinReturn -293.901 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 18.4582 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -263.459 MetaTest/__unnamed_task__/AverageReturn -263.459 MetaTest/__unnamed_task__/Iteration 288 MetaTest/__unnamed_task__/MaxReturn -246.962 MetaTest/__unnamed_task__/MinReturn -293.901 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 18.4582 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 618000 ------------------------------------------------- ----------- 2025-04-05 06:36:32 | [pearl_trainer] epoch #289 | Training... 2025-04-05 06:39:15 | [pearl_trainer] epoch #289 | Evaluating... 2025-04-05 06:39:15 | [pearl_trainer] epoch #289 | Sampling for adapation and meta-testing... 2025-04-05 06:43:35 | [pearl_trainer] epoch #289 | Finished meta-testing... 2025-04-05 06:43:35 | [pearl_trainer] epoch #289 | Saving snapshot... 2025-04-05 06:43:37 | [pearl_trainer] epoch #289 | Saved 2025-04-05 06:43:37 | [pearl_trainer] epoch #289 | Time 137680.43 s 2025-04-05 06:43:37 | [pearl_trainer] epoch #289 | EpochTime 476.91 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -262.523 MetaTest/Average/AverageReturn -262.523 MetaTest/Average/Iteration 289 MetaTest/Average/MaxReturn -188.463 MetaTest/Average/MinReturn -346.655 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 54.9646 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -262.523 MetaTest/__unnamed_task__/AverageReturn -262.523 MetaTest/__unnamed_task__/Iteration 289 MetaTest/__unnamed_task__/MaxReturn -188.463 MetaTest/__unnamed_task__/MinReturn -346.655 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 54.9646 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 620000 ------------------------------------------------- ----------- 2025-04-05 06:44:29 | [pearl_trainer] epoch #290 | Training... 2025-04-05 06:47:13 | [pearl_trainer] epoch #290 | Evaluating... 2025-04-05 06:47:13 | [pearl_trainer] epoch #290 | Sampling for adapation and meta-testing... 2025-04-05 06:51:44 | [pearl_trainer] epoch #290 | Finished meta-testing... 2025-04-05 06:51:44 | [pearl_trainer] epoch #290 | Saving snapshot... 2025-04-05 06:51:45 | [pearl_trainer] epoch #290 | Saved 2025-04-05 06:51:45 | [pearl_trainer] epoch #290 | Time 138169.11 s 2025-04-05 06:51:45 | [pearl_trainer] epoch #290 | EpochTime 488.69 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -255.198 MetaTest/Average/AverageReturn -255.198 MetaTest/Average/Iteration 290 MetaTest/Average/MaxReturn -210.364 MetaTest/Average/MinReturn -317.406 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 34.6159 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -255.198 MetaTest/__unnamed_task__/AverageReturn -255.198 MetaTest/__unnamed_task__/Iteration 290 MetaTest/__unnamed_task__/MaxReturn -210.364 MetaTest/__unnamed_task__/MinReturn -317.406 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 34.6159 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 622000 ------------------------------------------------- ----------- 2025-04-05 06:52:32 | [pearl_trainer] epoch #291 | Training... 2025-04-05 06:55:08 | [pearl_trainer] epoch #291 | Evaluating... 2025-04-05 06:55:08 | [pearl_trainer] epoch #291 | Sampling for adapation and meta-testing... 2025-04-05 06:59:36 | [pearl_trainer] epoch #291 | Finished meta-testing... 2025-04-05 06:59:36 | [pearl_trainer] epoch #291 | Saving snapshot... 2025-04-05 06:59:38 | [pearl_trainer] epoch #291 | Saved 2025-04-05 06:59:38 | [pearl_trainer] epoch #291 | Time 138641.26 s 2025-04-05 06:59:38 | [pearl_trainer] epoch #291 | EpochTime 472.14 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -263.55 MetaTest/Average/AverageReturn -263.55 MetaTest/Average/Iteration 291 MetaTest/Average/MaxReturn -227.406 MetaTest/Average/MinReturn -305.151 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.6522 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -263.55 MetaTest/__unnamed_task__/AverageReturn -263.55 MetaTest/__unnamed_task__/Iteration 291 MetaTest/__unnamed_task__/MaxReturn -227.406 MetaTest/__unnamed_task__/MinReturn -305.151 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.6522 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 624000 ------------------------------------------------- ----------- 2025-04-05 07:00:27 | [pearl_trainer] epoch #292 | Training... 2025-04-05 07:03:04 | [pearl_trainer] epoch #292 | Evaluating... 2025-04-05 07:03:04 | [pearl_trainer] epoch #292 | Sampling for adapation and meta-testing... 2025-04-05 07:07:37 | [pearl_trainer] epoch #292 | Finished meta-testing... 2025-04-05 07:07:37 | [pearl_trainer] epoch #292 | Saving snapshot... 2025-04-05 07:07:39 | [pearl_trainer] epoch #292 | Saved 2025-04-05 07:07:39 | [pearl_trainer] epoch #292 | Time 139122.24 s 2025-04-05 07:07:39 | [pearl_trainer] epoch #292 | EpochTime 480.98 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -258.377 MetaTest/Average/AverageReturn -258.377 MetaTest/Average/Iteration 292 MetaTest/Average/MaxReturn -233.331 MetaTest/Average/MinReturn -314.144 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 29.2786 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -258.377 MetaTest/__unnamed_task__/AverageReturn -258.377 MetaTest/__unnamed_task__/Iteration 292 MetaTest/__unnamed_task__/MaxReturn -233.331 MetaTest/__unnamed_task__/MinReturn -314.144 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 29.2786 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 626000 ------------------------------------------------- ----------- 2025-04-05 07:08:26 | [pearl_trainer] epoch #293 | Training... 2025-04-05 07:11:08 | [pearl_trainer] epoch #293 | Evaluating... 2025-04-05 07:11:08 | [pearl_trainer] epoch #293 | Sampling for adapation and meta-testing... 2025-04-05 07:15:31 | [pearl_trainer] epoch #293 | Finished meta-testing... 2025-04-05 07:15:31 | [pearl_trainer] epoch #293 | Saving snapshot... 2025-04-05 07:15:32 | [pearl_trainer] epoch #293 | Saved 2025-04-05 07:15:32 | [pearl_trainer] epoch #293 | Time 139595.95 s 2025-04-05 07:15:32 | [pearl_trainer] epoch #293 | EpochTime 473.70 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -255.301 MetaTest/Average/AverageReturn -255.301 MetaTest/Average/Iteration 293 MetaTest/Average/MaxReturn -209.169 MetaTest/Average/MinReturn -335.329 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 46.1435 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -255.301 MetaTest/__unnamed_task__/AverageReturn -255.301 MetaTest/__unnamed_task__/Iteration 293 MetaTest/__unnamed_task__/MaxReturn -209.169 MetaTest/__unnamed_task__/MinReturn -335.329 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 46.1435 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 628000 ------------------------------------------------- ----------- 2025-04-05 07:16:17 | [pearl_trainer] epoch #294 | Training... 2025-04-05 07:19:00 | [pearl_trainer] epoch #294 | Evaluating... 2025-04-05 07:19:00 | [pearl_trainer] epoch #294 | Sampling for adapation and meta-testing... 2025-04-05 07:23:13 | [pearl_trainer] epoch #294 | Finished meta-testing... 2025-04-05 07:23:13 | [pearl_trainer] epoch #294 | Saving snapshot... 2025-04-05 07:23:15 | [pearl_trainer] epoch #294 | Saved 2025-04-05 07:23:15 | [pearl_trainer] epoch #294 | Time 140058.21 s 2025-04-05 07:23:15 | [pearl_trainer] epoch #294 | EpochTime 462.26 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -248.036 MetaTest/Average/AverageReturn -248.036 MetaTest/Average/Iteration 294 MetaTest/Average/MaxReturn -193.184 MetaTest/Average/MinReturn -327.217 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 49.5986 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -248.036 MetaTest/__unnamed_task__/AverageReturn -248.036 MetaTest/__unnamed_task__/Iteration 294 MetaTest/__unnamed_task__/MaxReturn -193.184 MetaTest/__unnamed_task__/MinReturn -327.217 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 49.5986 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 630000 ------------------------------------------------- ----------- 2025-04-05 07:24:02 | [pearl_trainer] epoch #295 | Training... 2025-04-05 07:26:46 | [pearl_trainer] epoch #295 | Evaluating... 2025-04-05 07:26:46 | [pearl_trainer] epoch #295 | Sampling for adapation and meta-testing... 2025-04-05 07:31:04 | [pearl_trainer] epoch #295 | Finished meta-testing... 2025-04-05 07:31:04 | [pearl_trainer] epoch #295 | Saving snapshot... 2025-04-05 07:31:05 | [pearl_trainer] epoch #295 | Saved 2025-04-05 07:31:05 | [pearl_trainer] epoch #295 | Time 140528.48 s 2025-04-05 07:31:05 | [pearl_trainer] epoch #295 | EpochTime 470.28 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -271.756 MetaTest/Average/AverageReturn -271.756 MetaTest/Average/Iteration 295 MetaTest/Average/MaxReturn -226.689 MetaTest/Average/MinReturn -329.384 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 34.5412 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -271.756 MetaTest/__unnamed_task__/AverageReturn -271.756 MetaTest/__unnamed_task__/Iteration 295 MetaTest/__unnamed_task__/MaxReturn -226.689 MetaTest/__unnamed_task__/MinReturn -329.384 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 34.5412 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 632000 ------------------------------------------------- ----------- 2025-04-05 07:31:58 | [pearl_trainer] epoch #296 | Training... 2025-04-05 07:34:42 | [pearl_trainer] epoch #296 | Evaluating... 2025-04-05 07:34:42 | [pearl_trainer] epoch #296 | Sampling for adapation and meta-testing... 2025-04-05 07:38:58 | [pearl_trainer] epoch #296 | Finished meta-testing... 2025-04-05 07:38:58 | [pearl_trainer] epoch #296 | Saving snapshot... 2025-04-05 07:38:59 | [pearl_trainer] epoch #296 | Saved 2025-04-05 07:38:59 | [pearl_trainer] epoch #296 | Time 141002.80 s 2025-04-05 07:38:59 | [pearl_trainer] epoch #296 | EpochTime 474.31 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -263.919 MetaTest/Average/AverageReturn -263.919 MetaTest/Average/Iteration 296 MetaTest/Average/MaxReturn -233.66 MetaTest/Average/MinReturn -329.496 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 34.0057 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -263.919 MetaTest/__unnamed_task__/AverageReturn -263.919 MetaTest/__unnamed_task__/Iteration 296 MetaTest/__unnamed_task__/MaxReturn -233.66 MetaTest/__unnamed_task__/MinReturn -329.496 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 34.0057 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 634000 ------------------------------------------------- ----------- 2025-04-05 07:39:51 | [pearl_trainer] epoch #297 | Training... 2025-04-05 07:42:35 | [pearl_trainer] epoch #297 | Evaluating... 2025-04-05 07:42:35 | [pearl_trainer] epoch #297 | Sampling for adapation and meta-testing... 2025-04-05 07:46:59 | [pearl_trainer] epoch #297 | Finished meta-testing... 2025-04-05 07:46:59 | [pearl_trainer] epoch #297 | Saving snapshot... 2025-04-05 07:47:00 | [pearl_trainer] epoch #297 | Saved 2025-04-05 07:47:00 | [pearl_trainer] epoch #297 | Time 141484.15 s 2025-04-05 07:47:00 | [pearl_trainer] epoch #297 | EpochTime 481.35 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -326.931 MetaTest/Average/AverageReturn -326.931 MetaTest/Average/Iteration 297 MetaTest/Average/MaxReturn -292.713 MetaTest/Average/MinReturn -369.995 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 30.1467 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -326.931 MetaTest/__unnamed_task__/AverageReturn -326.931 MetaTest/__unnamed_task__/Iteration 297 MetaTest/__unnamed_task__/MaxReturn -292.713 MetaTest/__unnamed_task__/MinReturn -369.995 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 30.1467 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 636000 ------------------------------------------------- ----------- 2025-04-05 07:47:44 | [pearl_trainer] epoch #298 | Training... 2025-04-05 07:50:27 | [pearl_trainer] epoch #298 | Evaluating... 2025-04-05 07:50:27 | [pearl_trainer] epoch #298 | Sampling for adapation and meta-testing... 2025-04-05 07:54:43 | [pearl_trainer] epoch #298 | Finished meta-testing... 2025-04-05 07:54:43 | [pearl_trainer] epoch #298 | Saving snapshot... 2025-04-05 07:54:44 | [pearl_trainer] epoch #298 | Saved 2025-04-05 07:54:44 | [pearl_trainer] epoch #298 | Time 141947.86 s 2025-04-05 07:54:44 | [pearl_trainer] epoch #298 | EpochTime 463.71 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -270.692 MetaTest/Average/AverageReturn -270.692 MetaTest/Average/Iteration 298 MetaTest/Average/MaxReturn -170.56 MetaTest/Average/MinReturn -318.474 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 53.7905 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -270.692 MetaTest/__unnamed_task__/AverageReturn -270.692 MetaTest/__unnamed_task__/Iteration 298 MetaTest/__unnamed_task__/MaxReturn -170.56 MetaTest/__unnamed_task__/MinReturn -318.474 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 53.7905 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 638000 ------------------------------------------------- ----------- 2025-04-05 07:55:29 | [pearl_trainer] epoch #299 | Training... 2025-04-05 07:58:13 | [pearl_trainer] epoch #299 | Evaluating... 2025-04-05 07:58:13 | [pearl_trainer] epoch #299 | Sampling for adapation and meta-testing... 2025-04-05 08:02:32 | [pearl_trainer] epoch #299 | Finished meta-testing... 2025-04-05 08:02:32 | [pearl_trainer] epoch #299 | Saving snapshot... 2025-04-05 08:02:33 | [pearl_trainer] epoch #299 | Saved 2025-04-05 08:02:33 | [pearl_trainer] epoch #299 | Time 142416.86 s 2025-04-05 08:02:33 | [pearl_trainer] epoch #299 | EpochTime 469.00 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -257.453 MetaTest/Average/AverageReturn -257.453 MetaTest/Average/Iteration 299 MetaTest/Average/MaxReturn -161.772 MetaTest/Average/MinReturn -303.148 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 51.3287 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -257.453 MetaTest/__unnamed_task__/AverageReturn -257.453 MetaTest/__unnamed_task__/Iteration 299 MetaTest/__unnamed_task__/MaxReturn -161.772 MetaTest/__unnamed_task__/MinReturn -303.148 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 51.3287 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 640000 ------------------------------------------------- ----------- 2025-04-05 08:03:19 | [pearl_trainer] epoch #300 | Training... 2025-04-05 08:05:51 | [pearl_trainer] epoch #300 | Evaluating... 2025-04-05 08:05:51 | [pearl_trainer] epoch #300 | Sampling for adapation and meta-testing... 2025-04-05 08:10:06 | [pearl_trainer] epoch #300 | Finished meta-testing... 2025-04-05 08:10:06 | [pearl_trainer] epoch #300 | Saving snapshot... 2025-04-05 08:10:07 | [pearl_trainer] epoch #300 | Saved 2025-04-05 08:10:07 | [pearl_trainer] epoch #300 | Time 142871.10 s 2025-04-05 08:10:07 | [pearl_trainer] epoch #300 | EpochTime 454.24 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -233.399 MetaTest/Average/AverageReturn -233.399 MetaTest/Average/Iteration 300 MetaTest/Average/MaxReturn -204.979 MetaTest/Average/MinReturn -271.233 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 24.8881 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -233.399 MetaTest/__unnamed_task__/AverageReturn -233.399 MetaTest/__unnamed_task__/Iteration 300 MetaTest/__unnamed_task__/MaxReturn -204.979 MetaTest/__unnamed_task__/MinReturn -271.233 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 24.8881 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 642000 ------------------------------------------------- ----------- 2025-04-05 08:10:55 | [pearl_trainer] epoch #301 | Training... 2025-04-05 08:13:35 | [pearl_trainer] epoch #301 | Evaluating... 2025-04-05 08:13:35 | [pearl_trainer] epoch #301 | Sampling for adapation and meta-testing... 2025-04-05 08:17:53 | [pearl_trainer] epoch #301 | Finished meta-testing... 2025-04-05 08:17:53 | [pearl_trainer] epoch #301 | Saving snapshot... 2025-04-05 08:17:54 | [pearl_trainer] epoch #301 | Saved 2025-04-05 08:17:54 | [pearl_trainer] epoch #301 | Time 143338.19 s 2025-04-05 08:17:54 | [pearl_trainer] epoch #301 | EpochTime 467.08 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -268.77 MetaTest/Average/AverageReturn -268.77 MetaTest/Average/Iteration 301 MetaTest/Average/MaxReturn -165.238 MetaTest/Average/MinReturn -441.793 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 106.802 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -268.77 MetaTest/__unnamed_task__/AverageReturn -268.77 MetaTest/__unnamed_task__/Iteration 301 MetaTest/__unnamed_task__/MaxReturn -165.238 MetaTest/__unnamed_task__/MinReturn -441.793 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 106.802 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 644000 ------------------------------------------------- ---------- 2025-04-05 08:18:45 | [pearl_trainer] epoch #302 | Training... 2025-04-05 08:21:26 | [pearl_trainer] epoch #302 | Evaluating... 2025-04-05 08:21:26 | [pearl_trainer] epoch #302 | Sampling for adapation and meta-testing... 2025-04-05 08:25:34 | [pearl_trainer] epoch #302 | Finished meta-testing... 2025-04-05 08:25:34 | [pearl_trainer] epoch #302 | Saving snapshot... 2025-04-05 08:25:35 | [pearl_trainer] epoch #302 | Saved 2025-04-05 08:25:35 | [pearl_trainer] epoch #302 | Time 143798.83 s 2025-04-05 08:25:35 | [pearl_trainer] epoch #302 | EpochTime 460.65 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -263.373 MetaTest/Average/AverageReturn -263.373 MetaTest/Average/Iteration 302 MetaTest/Average/MaxReturn -218.771 MetaTest/Average/MinReturn -297.184 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 30.134 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -263.373 MetaTest/__unnamed_task__/AverageReturn -263.373 MetaTest/__unnamed_task__/Iteration 302 MetaTest/__unnamed_task__/MaxReturn -218.771 MetaTest/__unnamed_task__/MinReturn -297.184 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 30.134 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 646000 ------------------------------------------------- ---------- 2025-04-05 08:26:19 | [pearl_trainer] epoch #303 | Training... 2025-04-05 08:29:03 | [pearl_trainer] epoch #303 | Evaluating... 2025-04-05 08:29:03 | [pearl_trainer] epoch #303 | Sampling for adapation and meta-testing... 2025-04-05 08:33:08 | [pearl_trainer] epoch #303 | Finished meta-testing... 2025-04-05 08:33:08 | [pearl_trainer] epoch #303 | Saving snapshot... 2025-04-05 08:33:09 | [pearl_trainer] epoch #303 | Saved 2025-04-05 08:33:09 | [pearl_trainer] epoch #303 | Time 144252.54 s 2025-04-05 08:33:09 | [pearl_trainer] epoch #303 | EpochTime 453.71 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -237.329 MetaTest/Average/AverageReturn -237.329 MetaTest/Average/Iteration 303 MetaTest/Average/MaxReturn -165.192 MetaTest/Average/MinReturn -307.125 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 53.3769 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -237.329 MetaTest/__unnamed_task__/AverageReturn -237.329 MetaTest/__unnamed_task__/Iteration 303 MetaTest/__unnamed_task__/MaxReturn -165.192 MetaTest/__unnamed_task__/MinReturn -307.125 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 53.3769 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 648000 ------------------------------------------------- ----------- 2025-04-05 08:33:55 | [pearl_trainer] epoch #304 | Training... 2025-04-05 08:36:36 | [pearl_trainer] epoch #304 | Evaluating... 2025-04-05 08:36:36 | [pearl_trainer] epoch #304 | Sampling for adapation and meta-testing... 2025-04-05 08:40:41 | [pearl_trainer] epoch #304 | Finished meta-testing... 2025-04-05 08:40:41 | [pearl_trainer] epoch #304 | Saving snapshot... 2025-04-05 08:40:42 | [pearl_trainer] epoch #304 | Saved 2025-04-05 08:40:42 | [pearl_trainer] epoch #304 | Time 144706.19 s 2025-04-05 08:40:42 | [pearl_trainer] epoch #304 | EpochTime 453.65 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -307.607 MetaTest/Average/AverageReturn -307.607 MetaTest/Average/Iteration 304 MetaTest/Average/MaxReturn -264.24 MetaTest/Average/MinReturn -370.072 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.8977 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -307.607 MetaTest/__unnamed_task__/AverageReturn -307.607 MetaTest/__unnamed_task__/Iteration 304 MetaTest/__unnamed_task__/MaxReturn -264.24 MetaTest/__unnamed_task__/MinReturn -370.072 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.8977 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 650000 ------------------------------------------------- ----------- 2025-04-05 08:41:28 | [pearl_trainer] epoch #305 | Training... 2025-04-05 08:44:10 | [pearl_trainer] epoch #305 | Evaluating... 2025-04-05 08:44:10 | [pearl_trainer] epoch #305 | Sampling for adapation and meta-testing... 2025-04-05 08:48:05 | [pearl_trainer] epoch #305 | Finished meta-testing... 2025-04-05 08:48:05 | [pearl_trainer] epoch #305 | Saving snapshot... 2025-04-05 08:48:06 | [pearl_trainer] epoch #305 | Saved 2025-04-05 08:48:06 | [pearl_trainer] epoch #305 | Time 145149.44 s 2025-04-05 08:48:06 | [pearl_trainer] epoch #305 | EpochTime 443.24 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -289.835 MetaTest/Average/AverageReturn -289.835 MetaTest/Average/Iteration 305 MetaTest/Average/MaxReturn -219.196 MetaTest/Average/MinReturn -369.573 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 63.2538 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -289.835 MetaTest/__unnamed_task__/AverageReturn -289.835 MetaTest/__unnamed_task__/Iteration 305 MetaTest/__unnamed_task__/MaxReturn -219.196 MetaTest/__unnamed_task__/MinReturn -369.573 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 63.2538 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 652000 ------------------------------------------------- ----------- 2025-04-05 08:48:48 | [pearl_trainer] epoch #306 | Training... 2025-04-05 08:51:29 | [pearl_trainer] epoch #306 | Evaluating... 2025-04-05 08:51:29 | [pearl_trainer] epoch #306 | Sampling for adapation and meta-testing... 2025-04-05 08:55:24 | [pearl_trainer] epoch #306 | Finished meta-testing... 2025-04-05 08:55:24 | [pearl_trainer] epoch #306 | Saving snapshot... 2025-04-05 08:55:25 | [pearl_trainer] epoch #306 | Saved 2025-04-05 08:55:25 | [pearl_trainer] epoch #306 | Time 145589.04 s 2025-04-05 08:55:25 | [pearl_trainer] epoch #306 | EpochTime 439.60 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -275.643 MetaTest/Average/AverageReturn -275.643 MetaTest/Average/Iteration 306 MetaTest/Average/MaxReturn -189.5 MetaTest/Average/MinReturn -355.366 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 58.1558 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -275.643 MetaTest/__unnamed_task__/AverageReturn -275.643 MetaTest/__unnamed_task__/Iteration 306 MetaTest/__unnamed_task__/MaxReturn -189.5 MetaTest/__unnamed_task__/MinReturn -355.366 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 58.1558 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 654000 ------------------------------------------------- ----------- 2025-04-05 08:56:11 | [pearl_trainer] epoch #307 | Training... 2025-04-05 08:58:55 | [pearl_trainer] epoch #307 | Evaluating... 2025-04-05 08:58:55 | [pearl_trainer] epoch #307 | Sampling for adapation and meta-testing... 2025-04-05 09:02:55 | [pearl_trainer] epoch #307 | Finished meta-testing... 2025-04-05 09:02:55 | [pearl_trainer] epoch #307 | Saving snapshot... 2025-04-05 09:02:57 | [pearl_trainer] epoch #307 | Saved 2025-04-05 09:02:57 | [pearl_trainer] epoch #307 | Time 146040.26 s 2025-04-05 09:02:57 | [pearl_trainer] epoch #307 | EpochTime 451.22 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -264.081 MetaTest/Average/AverageReturn -264.081 MetaTest/Average/Iteration 307 MetaTest/Average/MaxReturn -190.798 MetaTest/Average/MinReturn -340.245 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 53.3946 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -264.081 MetaTest/__unnamed_task__/AverageReturn -264.081 MetaTest/__unnamed_task__/Iteration 307 MetaTest/__unnamed_task__/MaxReturn -190.798 MetaTest/__unnamed_task__/MinReturn -340.245 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 53.3946 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 656000 ------------------------------------------------- ----------- 2025-04-05 09:03:38 | [pearl_trainer] epoch #308 | Training... 2025-04-05 09:06:19 | [pearl_trainer] epoch #308 | Evaluating... 2025-04-05 09:06:19 | [pearl_trainer] epoch #308 | Sampling for adapation and meta-testing... 2025-04-05 09:10:16 | [pearl_trainer] epoch #308 | Finished meta-testing... 2025-04-05 09:10:16 | [pearl_trainer] epoch #308 | Saving snapshot... 2025-04-05 09:10:17 | [pearl_trainer] epoch #308 | Saved 2025-04-05 09:10:17 | [pearl_trainer] epoch #308 | Time 146481.06 s 2025-04-05 09:10:17 | [pearl_trainer] epoch #308 | EpochTime 440.79 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -275.245 MetaTest/Average/AverageReturn -275.245 MetaTest/Average/Iteration 308 MetaTest/Average/MaxReturn -197.232 MetaTest/Average/MinReturn -360.048 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 61.1722 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -275.245 MetaTest/__unnamed_task__/AverageReturn -275.245 MetaTest/__unnamed_task__/Iteration 308 MetaTest/__unnamed_task__/MaxReturn -197.232 MetaTest/__unnamed_task__/MinReturn -360.048 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 61.1722 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 658000 ------------------------------------------------- ----------- 2025-04-05 09:11:03 | [pearl_trainer] epoch #309 | Training... 2025-04-05 09:14:02 | [pearl_trainer] epoch #309 | Evaluating... 2025-04-05 09:14:02 | [pearl_trainer] epoch #309 | Sampling for adapation and meta-testing... 2025-04-05 09:18:01 | [pearl_trainer] epoch #309 | Finished meta-testing... 2025-04-05 09:18:01 | [pearl_trainer] epoch #309 | Saving snapshot... 2025-04-05 09:18:02 | [pearl_trainer] epoch #309 | Saved 2025-04-05 09:18:02 | [pearl_trainer] epoch #309 | Time 146945.62 s 2025-04-05 09:18:02 | [pearl_trainer] epoch #309 | EpochTime 464.56 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -286.502 MetaTest/Average/AverageReturn -286.502 MetaTest/Average/Iteration 309 MetaTest/Average/MaxReturn -236.33 MetaTest/Average/MinReturn -347.247 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 38.6395 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -286.502 MetaTest/__unnamed_task__/AverageReturn -286.502 MetaTest/__unnamed_task__/Iteration 309 MetaTest/__unnamed_task__/MaxReturn -236.33 MetaTest/__unnamed_task__/MinReturn -347.247 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 38.6395 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 660000 ------------------------------------------------- ----------- 2025-04-05 09:18:48 | [pearl_trainer] epoch #310 | Training... 2025-04-05 09:21:31 | [pearl_trainer] epoch #310 | Evaluating... 2025-04-05 09:21:31 | [pearl_trainer] epoch #310 | Sampling for adapation and meta-testing... 2025-04-05 09:25:26 | [pearl_trainer] epoch #310 | Finished meta-testing... 2025-04-05 09:25:26 | [pearl_trainer] epoch #310 | Saving snapshot... 2025-04-05 09:25:28 | [pearl_trainer] epoch #310 | Saved 2025-04-05 09:25:28 | [pearl_trainer] epoch #310 | Time 147391.27 s 2025-04-05 09:25:28 | [pearl_trainer] epoch #310 | EpochTime 445.65 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -322.919 MetaTest/Average/AverageReturn -322.919 MetaTest/Average/Iteration 310 MetaTest/Average/MaxReturn -256.415 MetaTest/Average/MinReturn -367.859 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 41.1441 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -322.919 MetaTest/__unnamed_task__/AverageReturn -322.919 MetaTest/__unnamed_task__/Iteration 310 MetaTest/__unnamed_task__/MaxReturn -256.415 MetaTest/__unnamed_task__/MinReturn -367.859 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 41.1441 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 662000 ------------------------------------------------- ----------- 2025-04-05 09:26:12 | [pearl_trainer] epoch #311 | Training... 2025-04-05 09:29:00 | [pearl_trainer] epoch #311 | Evaluating... 2025-04-05 09:29:00 | [pearl_trainer] epoch #311 | Sampling for adapation and meta-testing... 2025-04-05 09:33:06 | [pearl_trainer] epoch #311 | Finished meta-testing... 2025-04-05 09:33:06 | [pearl_trainer] epoch #311 | Saving snapshot... 2025-04-05 09:33:07 | [pearl_trainer] epoch #311 | Saved 2025-04-05 09:33:07 | [pearl_trainer] epoch #311 | Time 147850.44 s 2025-04-05 09:33:07 | [pearl_trainer] epoch #311 | EpochTime 459.17 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -262.997 MetaTest/Average/AverageReturn -262.997 MetaTest/Average/Iteration 311 MetaTest/Average/MaxReturn -228.298 MetaTest/Average/MinReturn -312.795 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.6837 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -262.997 MetaTest/__unnamed_task__/AverageReturn -262.997 MetaTest/__unnamed_task__/Iteration 311 MetaTest/__unnamed_task__/MaxReturn -228.298 MetaTest/__unnamed_task__/MinReturn -312.795 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.6837 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 664000 ------------------------------------------------- ----------- 2025-04-05 09:33:51 | [pearl_trainer] epoch #312 | Training... 2025-04-05 09:36:37 | [pearl_trainer] epoch #312 | Evaluating... 2025-04-05 09:36:37 | [pearl_trainer] epoch #312 | Sampling for adapation and meta-testing... 2025-04-05 09:40:33 | [pearl_trainer] epoch #312 | Finished meta-testing... 2025-04-05 09:40:33 | [pearl_trainer] epoch #312 | Saving snapshot... 2025-04-05 09:40:35 | [pearl_trainer] epoch #312 | Saved 2025-04-05 09:40:35 | [pearl_trainer] epoch #312 | Time 148298.61 s 2025-04-05 09:40:35 | [pearl_trainer] epoch #312 | EpochTime 448.16 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -307.06 MetaTest/Average/AverageReturn -307.06 MetaTest/Average/Iteration 312 MetaTest/Average/MaxReturn -270.739 MetaTest/Average/MinReturn -351.944 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.6039 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -307.06 MetaTest/__unnamed_task__/AverageReturn -307.06 MetaTest/__unnamed_task__/Iteration 312 MetaTest/__unnamed_task__/MaxReturn -270.739 MetaTest/__unnamed_task__/MinReturn -351.944 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.6039 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 666000 ------------------------------------------------- ----------- 2025-04-05 09:41:20 | [pearl_trainer] epoch #313 | Training... 2025-04-05 09:44:06 | [pearl_trainer] epoch #313 | Evaluating... 2025-04-05 09:44:06 | [pearl_trainer] epoch #313 | Sampling for adapation and meta-testing... 2025-04-05 09:48:05 | [pearl_trainer] epoch #313 | Finished meta-testing... 2025-04-05 09:48:05 | [pearl_trainer] epoch #313 | Saving snapshot... 2025-04-05 09:48:06 | [pearl_trainer] epoch #313 | Saved 2025-04-05 09:48:06 | [pearl_trainer] epoch #313 | Time 148749.77 s 2025-04-05 09:48:06 | [pearl_trainer] epoch #313 | EpochTime 451.16 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -270.785 MetaTest/Average/AverageReturn -270.785 MetaTest/Average/Iteration 313 MetaTest/Average/MaxReturn -189.515 MetaTest/Average/MinReturn -371.379 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 60.2725 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -270.785 MetaTest/__unnamed_task__/AverageReturn -270.785 MetaTest/__unnamed_task__/Iteration 313 MetaTest/__unnamed_task__/MaxReturn -189.515 MetaTest/__unnamed_task__/MinReturn -371.379 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 60.2725 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 668000 ------------------------------------------------- ----------- 2025-04-05 09:48:52 | [pearl_trainer] epoch #314 | Training... 2025-04-05 09:51:35 | [pearl_trainer] epoch #314 | Evaluating... 2025-04-05 09:51:35 | [pearl_trainer] epoch #314 | Sampling for adapation and meta-testing... 2025-04-05 09:55:35 | [pearl_trainer] epoch #314 | Finished meta-testing... 2025-04-05 09:55:35 | [pearl_trainer] epoch #314 | Saving snapshot... 2025-04-05 09:55:36 | [pearl_trainer] epoch #314 | Saved 2025-04-05 09:55:36 | [pearl_trainer] epoch #314 | Time 149199.73 s 2025-04-05 09:55:36 | [pearl_trainer] epoch #314 | EpochTime 449.96 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -328.885 MetaTest/Average/AverageReturn -328.885 MetaTest/Average/Iteration 314 MetaTest/Average/MaxReturn -284.72 MetaTest/Average/MinReturn -413.14 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 49.7519 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -328.885 MetaTest/__unnamed_task__/AverageReturn -328.885 MetaTest/__unnamed_task__/Iteration 314 MetaTest/__unnamed_task__/MaxReturn -284.72 MetaTest/__unnamed_task__/MinReturn -413.14 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 49.7519 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 670000 ------------------------------------------------- ----------- 2025-04-05 09:56:21 | [pearl_trainer] epoch #315 | Training... 2025-04-05 09:59:06 | [pearl_trainer] epoch #315 | Evaluating... 2025-04-05 09:59:06 | [pearl_trainer] epoch #315 | Sampling for adapation and meta-testing... 2025-04-05 10:03:15 | [pearl_trainer] epoch #315 | Finished meta-testing... 2025-04-05 10:03:15 | [pearl_trainer] epoch #315 | Saving snapshot... 2025-04-05 10:03:16 | [pearl_trainer] epoch #315 | Saved 2025-04-05 10:03:16 | [pearl_trainer] epoch #315 | Time 149659.63 s 2025-04-05 10:03:16 | [pearl_trainer] epoch #315 | EpochTime 459.90 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -266.282 MetaTest/Average/AverageReturn -266.282 MetaTest/Average/Iteration 315 MetaTest/Average/MaxReturn -246.363 MetaTest/Average/MinReturn -287.567 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 14.5199 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -266.282 MetaTest/__unnamed_task__/AverageReturn -266.282 MetaTest/__unnamed_task__/Iteration 315 MetaTest/__unnamed_task__/MaxReturn -246.363 MetaTest/__unnamed_task__/MinReturn -287.567 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 14.5199 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 672000 ------------------------------------------------- ----------- 2025-04-05 10:04:03 | [pearl_trainer] epoch #316 | Training... 2025-04-05 10:06:47 | [pearl_trainer] epoch #316 | Evaluating... 2025-04-05 10:06:47 | [pearl_trainer] epoch #316 | Sampling for adapation and meta-testing... 2025-04-05 10:10:47 | [pearl_trainer] epoch #316 | Finished meta-testing... 2025-04-05 10:10:47 | [pearl_trainer] epoch #316 | Saving snapshot... 2025-04-05 10:10:48 | [pearl_trainer] epoch #316 | Saved 2025-04-05 10:10:48 | [pearl_trainer] epoch #316 | Time 150111.35 s 2025-04-05 10:10:48 | [pearl_trainer] epoch #316 | EpochTime 451.72 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -300.538 MetaTest/Average/AverageReturn -300.538 MetaTest/Average/Iteration 316 MetaTest/Average/MaxReturn -232.159 MetaTest/Average/MinReturn -402.367 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 56.2079 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -300.538 MetaTest/__unnamed_task__/AverageReturn -300.538 MetaTest/__unnamed_task__/Iteration 316 MetaTest/__unnamed_task__/MaxReturn -232.159 MetaTest/__unnamed_task__/MinReturn -402.367 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 56.2079 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 674000 ------------------------------------------------- ----------- 2025-04-05 10:11:28 | [pearl_trainer] epoch #317 | Training... 2025-04-05 10:14:09 | [pearl_trainer] epoch #317 | Evaluating... 2025-04-05 10:14:09 | [pearl_trainer] epoch #317 | Sampling for adapation and meta-testing... 2025-04-05 10:18:15 | [pearl_trainer] epoch #317 | Finished meta-testing... 2025-04-05 10:18:15 | [pearl_trainer] epoch #317 | Saving snapshot... 2025-04-05 10:18:16 | [pearl_trainer] epoch #317 | Saved 2025-04-05 10:18:16 | [pearl_trainer] epoch #317 | Time 150559.65 s 2025-04-05 10:18:16 | [pearl_trainer] epoch #317 | EpochTime 448.30 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -313.765 MetaTest/Average/AverageReturn -313.765 MetaTest/Average/Iteration 317 MetaTest/Average/MaxReturn -264.408 MetaTest/Average/MinReturn -333.741 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.2593 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -313.765 MetaTest/__unnamed_task__/AverageReturn -313.765 MetaTest/__unnamed_task__/Iteration 317 MetaTest/__unnamed_task__/MaxReturn -264.408 MetaTest/__unnamed_task__/MinReturn -333.741 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.2593 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 676000 ------------------------------------------------- ----------- 2025-04-05 10:19:01 | [pearl_trainer] epoch #318 | Training... 2025-04-05 10:21:45 | [pearl_trainer] epoch #318 | Evaluating... 2025-04-05 10:21:45 | [pearl_trainer] epoch #318 | Sampling for adapation and meta-testing... 2025-04-05 10:26:02 | [pearl_trainer] epoch #318 | Finished meta-testing... 2025-04-05 10:26:02 | [pearl_trainer] epoch #318 | Saving snapshot... 2025-04-05 10:26:03 | [pearl_trainer] epoch #318 | Saved 2025-04-05 10:26:03 | [pearl_trainer] epoch #318 | Time 151026.99 s 2025-04-05 10:26:03 | [pearl_trainer] epoch #318 | EpochTime 467.34 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -299.619 MetaTest/Average/AverageReturn -299.619 MetaTest/Average/Iteration 318 MetaTest/Average/MaxReturn -213.692 MetaTest/Average/MinReturn -407.04 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 61.8637 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -299.619 MetaTest/__unnamed_task__/AverageReturn -299.619 MetaTest/__unnamed_task__/Iteration 318 MetaTest/__unnamed_task__/MaxReturn -213.692 MetaTest/__unnamed_task__/MinReturn -407.04 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 61.8637 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 678000 ------------------------------------------------- ----------- 2025-04-05 10:26:50 | [pearl_trainer] epoch #319 | Training... 2025-04-05 10:29:34 | [pearl_trainer] epoch #319 | Evaluating... 2025-04-05 10:29:34 | [pearl_trainer] epoch #319 | Sampling for adapation and meta-testing... 2025-04-05 10:33:52 | [pearl_trainer] epoch #319 | Finished meta-testing... 2025-04-05 10:33:52 | [pearl_trainer] epoch #319 | Saving snapshot... 2025-04-05 10:33:54 | [pearl_trainer] epoch #319 | Saved 2025-04-05 10:33:54 | [pearl_trainer] epoch #319 | Time 151497.25 s 2025-04-05 10:33:54 | [pearl_trainer] epoch #319 | EpochTime 470.26 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -308.161 MetaTest/Average/AverageReturn -308.161 MetaTest/Average/Iteration 319 MetaTest/Average/MaxReturn -153.416 MetaTest/Average/MinReturn -435.719 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 96.9389 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -308.161 MetaTest/__unnamed_task__/AverageReturn -308.161 MetaTest/__unnamed_task__/Iteration 319 MetaTest/__unnamed_task__/MaxReturn -153.416 MetaTest/__unnamed_task__/MinReturn -435.719 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 96.9389 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 680000 ------------------------------------------------- ----------- 2025-04-05 10:34:38 | [pearl_trainer] epoch #320 | Training... 2025-04-05 10:37:23 | [pearl_trainer] epoch #320 | Evaluating... 2025-04-05 10:37:23 | [pearl_trainer] epoch #320 | Sampling for adapation and meta-testing... 2025-04-05 10:41:42 | [pearl_trainer] epoch #320 | Finished meta-testing... 2025-04-05 10:41:42 | [pearl_trainer] epoch #320 | Saving snapshot... 2025-04-05 10:41:43 | [pearl_trainer] epoch #320 | Saved 2025-04-05 10:41:43 | [pearl_trainer] epoch #320 | Time 151966.77 s 2025-04-05 10:41:43 | [pearl_trainer] epoch #320 | EpochTime 469.51 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -284.185 MetaTest/Average/AverageReturn -284.185 MetaTest/Average/Iteration 320 MetaTest/Average/MaxReturn -218.158 MetaTest/Average/MinReturn -320.51 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.8508 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -284.185 MetaTest/__unnamed_task__/AverageReturn -284.185 MetaTest/__unnamed_task__/Iteration 320 MetaTest/__unnamed_task__/MaxReturn -218.158 MetaTest/__unnamed_task__/MinReturn -320.51 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.8508 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 682000 ------------------------------------------------- ----------- 2025-04-05 10:42:26 | [pearl_trainer] epoch #321 | Training... 2025-04-05 10:45:06 | [pearl_trainer] epoch #321 | Evaluating... 2025-04-05 10:45:06 | [pearl_trainer] epoch #321 | Sampling for adapation and meta-testing... 2025-04-05 10:49:23 | [pearl_trainer] epoch #321 | Finished meta-testing... 2025-04-05 10:49:23 | [pearl_trainer] epoch #321 | Saving snapshot... 2025-04-05 10:49:25 | [pearl_trainer] epoch #321 | Saved 2025-04-05 10:49:25 | [pearl_trainer] epoch #321 | Time 152428.44 s 2025-04-05 10:49:25 | [pearl_trainer] epoch #321 | EpochTime 461.66 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -282.862 MetaTest/Average/AverageReturn -282.862 MetaTest/Average/Iteration 321 MetaTest/Average/MaxReturn -227.141 MetaTest/Average/MinReturn -344.5 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 39.1121 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -282.862 MetaTest/__unnamed_task__/AverageReturn -282.862 MetaTest/__unnamed_task__/Iteration 321 MetaTest/__unnamed_task__/MaxReturn -227.141 MetaTest/__unnamed_task__/MinReturn -344.5 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 39.1121 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 684000 ------------------------------------------------- ----------- 2025-04-05 10:50:11 | [pearl_trainer] epoch #322 | Training... 2025-04-05 10:53:00 | [pearl_trainer] epoch #322 | Evaluating... 2025-04-05 10:53:00 | [pearl_trainer] epoch #322 | Sampling for adapation and meta-testing... 2025-04-05 10:57:16 | [pearl_trainer] epoch #322 | Finished meta-testing... 2025-04-05 10:57:16 | [pearl_trainer] epoch #322 | Saving snapshot... 2025-04-05 10:57:17 | [pearl_trainer] epoch #322 | Saved 2025-04-05 10:57:17 | [pearl_trainer] epoch #322 | Time 152900.37 s 2025-04-05 10:57:17 | [pearl_trainer] epoch #322 | EpochTime 471.94 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -266.146 MetaTest/Average/AverageReturn -266.146 MetaTest/Average/Iteration 322 MetaTest/Average/MaxReturn -185.885 MetaTest/Average/MinReturn -339.253 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 53.2759 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -266.146 MetaTest/__unnamed_task__/AverageReturn -266.146 MetaTest/__unnamed_task__/Iteration 322 MetaTest/__unnamed_task__/MaxReturn -185.885 MetaTest/__unnamed_task__/MinReturn -339.253 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 53.2759 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 686000 ------------------------------------------------- ----------- 2025-04-05 10:58:04 | [pearl_trainer] epoch #323 | Training... 2025-04-05 11:00:42 | [pearl_trainer] epoch #323 | Evaluating... 2025-04-05 11:00:42 | [pearl_trainer] epoch #323 | Sampling for adapation and meta-testing... 2025-04-05 11:05:10 | [pearl_trainer] epoch #323 | Finished meta-testing... 2025-04-05 11:05:10 | [pearl_trainer] epoch #323 | Saving snapshot... 2025-04-05 11:05:11 | [pearl_trainer] epoch #323 | Saved 2025-04-05 11:05:11 | [pearl_trainer] epoch #323 | Time 153375.10 s 2025-04-05 11:05:11 | [pearl_trainer] epoch #323 | EpochTime 474.72 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -188.962 MetaTest/Average/AverageReturn -188.962 MetaTest/Average/Iteration 323 MetaTest/Average/MaxReturn -139.181 MetaTest/Average/MinReturn -301.553 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 58.9076 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -188.962 MetaTest/__unnamed_task__/AverageReturn -188.962 MetaTest/__unnamed_task__/Iteration 323 MetaTest/__unnamed_task__/MaxReturn -139.181 MetaTest/__unnamed_task__/MinReturn -301.553 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 58.9076 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 688000 ------------------------------------------------- ----------- 2025-04-05 11:05:59 | [pearl_trainer] epoch #324 | Training... 2025-04-05 11:08:45 | [pearl_trainer] epoch #324 | Evaluating... 2025-04-05 11:08:45 | [pearl_trainer] epoch #324 | Sampling for adapation and meta-testing... 2025-04-05 11:13:30 | [pearl_trainer] epoch #324 | Finished meta-testing... 2025-04-05 11:13:30 | [pearl_trainer] epoch #324 | Saving snapshot... 2025-04-05 11:13:31 | [pearl_trainer] epoch #324 | Saved 2025-04-05 11:13:31 | [pearl_trainer] epoch #324 | Time 153874.73 s 2025-04-05 11:13:31 | [pearl_trainer] epoch #324 | EpochTime 499.63 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -224.507 MetaTest/Average/AverageReturn -224.507 MetaTest/Average/Iteration 324 MetaTest/Average/MaxReturn -155.081 MetaTest/Average/MinReturn -287.446 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 52.3136 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -224.507 MetaTest/__unnamed_task__/AverageReturn -224.507 MetaTest/__unnamed_task__/Iteration 324 MetaTest/__unnamed_task__/MaxReturn -155.081 MetaTest/__unnamed_task__/MinReturn -287.446 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 52.3136 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 690000 ------------------------------------------------- ----------- 2025-04-05 11:14:22 | [pearl_trainer] epoch #325 | Training... 2025-04-05 11:17:05 | [pearl_trainer] epoch #325 | Evaluating... 2025-04-05 11:17:05 | [pearl_trainer] epoch #325 | Sampling for adapation and meta-testing... 2025-04-05 11:21:55 | [pearl_trainer] epoch #325 | Finished meta-testing... 2025-04-05 11:21:55 | [pearl_trainer] epoch #325 | Saving snapshot... 2025-04-05 11:21:57 | [pearl_trainer] epoch #325 | Saved 2025-04-05 11:21:57 | [pearl_trainer] epoch #325 | Time 154380.26 s 2025-04-05 11:21:57 | [pearl_trainer] epoch #325 | EpochTime 505.53 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -179.351 MetaTest/Average/AverageReturn -179.351 MetaTest/Average/Iteration 325 MetaTest/Average/MaxReturn -94.8789 MetaTest/Average/MinReturn -279.877 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 61.0848 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -179.351 MetaTest/__unnamed_task__/AverageReturn -179.351 MetaTest/__unnamed_task__/Iteration 325 MetaTest/__unnamed_task__/MaxReturn -94.8789 MetaTest/__unnamed_task__/MinReturn -279.877 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 61.0848 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 692000 ------------------------------------------------- ----------- 2025-04-05 11:22:49 | [pearl_trainer] epoch #326 | Training... 2025-04-05 11:25:21 | [pearl_trainer] epoch #326 | Evaluating... 2025-04-05 11:25:21 | [pearl_trainer] epoch #326 | Sampling for adapation and meta-testing... 2025-04-05 11:29:57 | [pearl_trainer] epoch #326 | Finished meta-testing... 2025-04-05 11:29:57 | [pearl_trainer] epoch #326 | Saving snapshot... 2025-04-05 11:29:59 | [pearl_trainer] epoch #326 | Saved 2025-04-05 11:29:59 | [pearl_trainer] epoch #326 | Time 154862.33 s 2025-04-05 11:29:59 | [pearl_trainer] epoch #326 | EpochTime 482.06 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -194.162 MetaTest/Average/AverageReturn -194.162 MetaTest/Average/Iteration 326 MetaTest/Average/MaxReturn -98.6792 MetaTest/Average/MinReturn -286.901 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 65.5703 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -194.162 MetaTest/__unnamed_task__/AverageReturn -194.162 MetaTest/__unnamed_task__/Iteration 326 MetaTest/__unnamed_task__/MaxReturn -98.6792 MetaTest/__unnamed_task__/MinReturn -286.901 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 65.5703 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 694000 ------------------------------------------------- ----------- 2025-04-05 11:30:50 | [pearl_trainer] epoch #327 | Training... 2025-04-05 11:33:30 | [pearl_trainer] epoch #327 | Evaluating... 2025-04-05 11:33:30 | [pearl_trainer] epoch #327 | Sampling for adapation and meta-testing... 2025-04-05 11:38:04 | [pearl_trainer] epoch #327 | Finished meta-testing... 2025-04-05 11:38:04 | [pearl_trainer] epoch #327 | Saving snapshot... 2025-04-05 11:38:06 | [pearl_trainer] epoch #327 | Saved 2025-04-05 11:38:06 | [pearl_trainer] epoch #327 | Time 155349.61 s 2025-04-05 11:38:06 | [pearl_trainer] epoch #327 | EpochTime 487.29 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -244.423 MetaTest/Average/AverageReturn -244.423 MetaTest/Average/Iteration 327 MetaTest/Average/MaxReturn -117.893 MetaTest/Average/MinReturn -320.544 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 69.2596 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -244.423 MetaTest/__unnamed_task__/AverageReturn -244.423 MetaTest/__unnamed_task__/Iteration 327 MetaTest/__unnamed_task__/MaxReturn -117.893 MetaTest/__unnamed_task__/MinReturn -320.544 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 69.2596 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 696000 ------------------------------------------------- ----------- 2025-04-05 11:38:58 | [pearl_trainer] epoch #328 | Training... 2025-04-05 11:42:03 | [pearl_trainer] epoch #328 | Evaluating... 2025-04-05 11:42:03 | [pearl_trainer] epoch #328 | Sampling for adapation and meta-testing... 2025-04-05 11:46:45 | [pearl_trainer] epoch #328 | Finished meta-testing... 2025-04-05 11:46:45 | [pearl_trainer] epoch #328 | Saving snapshot... 2025-04-05 11:46:47 | [pearl_trainer] epoch #328 | Saved 2025-04-05 11:46:47 | [pearl_trainer] epoch #328 | Time 155870.35 s 2025-04-05 11:46:47 | [pearl_trainer] epoch #328 | EpochTime 520.73 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -202.394 MetaTest/Average/AverageReturn -202.394 MetaTest/Average/Iteration 328 MetaTest/Average/MaxReturn -148.733 MetaTest/Average/MinReturn -259.906 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 41.6366 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -202.394 MetaTest/__unnamed_task__/AverageReturn -202.394 MetaTest/__unnamed_task__/Iteration 328 MetaTest/__unnamed_task__/MaxReturn -148.733 MetaTest/__unnamed_task__/MinReturn -259.906 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 41.6366 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 698000 ------------------------------------------------- ----------- 2025-04-05 11:47:34 | [pearl_trainer] epoch #329 | Training... 2025-04-05 11:50:37 | [pearl_trainer] epoch #329 | Evaluating... 2025-04-05 11:50:37 | [pearl_trainer] epoch #329 | Sampling for adapation and meta-testing... 2025-04-05 11:55:10 | [pearl_trainer] epoch #329 | Finished meta-testing... 2025-04-05 11:55:10 | [pearl_trainer] epoch #329 | Saving snapshot... 2025-04-05 11:55:12 | [pearl_trainer] epoch #329 | Saved 2025-04-05 11:55:12 | [pearl_trainer] epoch #329 | Time 156375.42 s 2025-04-05 11:55:12 | [pearl_trainer] epoch #329 | EpochTime 505.07 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -265.728 MetaTest/Average/AverageReturn -265.728 MetaTest/Average/Iteration 329 MetaTest/Average/MaxReturn -225.288 MetaTest/Average/MinReturn -313.647 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 34.3037 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -265.728 MetaTest/__unnamed_task__/AverageReturn -265.728 MetaTest/__unnamed_task__/Iteration 329 MetaTest/__unnamed_task__/MaxReturn -225.288 MetaTest/__unnamed_task__/MinReturn -313.647 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 34.3037 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 700000 ------------------------------------------------- ----------- 2025-04-05 11:55:59 | [pearl_trainer] epoch #330 | Training... 2025-04-05 11:59:04 | [pearl_trainer] epoch #330 | Evaluating... 2025-04-05 11:59:04 | [pearl_trainer] epoch #330 | Sampling for adapation and meta-testing... 2025-04-05 12:03:20 | [pearl_trainer] epoch #330 | Finished meta-testing... 2025-04-05 12:03:20 | [pearl_trainer] epoch #330 | Saving snapshot... 2025-04-05 12:03:21 | [pearl_trainer] epoch #330 | Saved 2025-04-05 12:03:21 | [pearl_trainer] epoch #330 | Time 156865.06 s 2025-04-05 12:03:21 | [pearl_trainer] epoch #330 | EpochTime 489.64 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -272.422 MetaTest/Average/AverageReturn -272.422 MetaTest/Average/Iteration 330 MetaTest/Average/MaxReturn -223.581 MetaTest/Average/MinReturn -338.853 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 42.4045 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -272.422 MetaTest/__unnamed_task__/AverageReturn -272.422 MetaTest/__unnamed_task__/Iteration 330 MetaTest/__unnamed_task__/MaxReturn -223.581 MetaTest/__unnamed_task__/MinReturn -338.853 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 42.4045 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 702000 ------------------------------------------------- ----------- 2025-04-05 12:04:04 | [pearl_trainer] epoch #331 | Training... 2025-04-05 12:06:59 | [pearl_trainer] epoch #331 | Evaluating... 2025-04-05 12:06:59 | [pearl_trainer] epoch #331 | Sampling for adapation and meta-testing... 2025-04-05 12:10:59 | [pearl_trainer] epoch #331 | Finished meta-testing... 2025-04-05 12:10:59 | [pearl_trainer] epoch #331 | Saving snapshot... 2025-04-05 12:11:00 | [pearl_trainer] epoch #331 | Saved 2025-04-05 12:11:00 | [pearl_trainer] epoch #331 | Time 157324.07 s 2025-04-05 12:11:00 | [pearl_trainer] epoch #331 | EpochTime 459.00 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -288.642 MetaTest/Average/AverageReturn -288.642 MetaTest/Average/Iteration 331 MetaTest/Average/MaxReturn -249.436 MetaTest/Average/MinReturn -314.031 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 23.6898 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -288.642 MetaTest/__unnamed_task__/AverageReturn -288.642 MetaTest/__unnamed_task__/Iteration 331 MetaTest/__unnamed_task__/MaxReturn -249.436 MetaTest/__unnamed_task__/MinReturn -314.031 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 23.6898 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 704000 ------------------------------------------------- ----------- 2025-04-05 12:11:49 | [pearl_trainer] epoch #332 | Training... 2025-04-05 12:14:41 | [pearl_trainer] epoch #332 | Evaluating... 2025-04-05 12:14:41 | [pearl_trainer] epoch #332 | Sampling for adapation and meta-testing... 2025-04-05 12:19:20 | [pearl_trainer] epoch #332 | Finished meta-testing... 2025-04-05 12:19:20 | [pearl_trainer] epoch #332 | Saving snapshot... 2025-04-05 12:19:21 | [pearl_trainer] epoch #332 | Saved 2025-04-05 12:19:21 | [pearl_trainer] epoch #332 | Time 157825.09 s 2025-04-05 12:19:21 | [pearl_trainer] epoch #332 | EpochTime 501.02 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -202.759 MetaTest/Average/AverageReturn -202.759 MetaTest/Average/Iteration 332 MetaTest/Average/MaxReturn -173.782 MetaTest/Average/MinReturn -259.747 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 29.7211 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -202.759 MetaTest/__unnamed_task__/AverageReturn -202.759 MetaTest/__unnamed_task__/Iteration 332 MetaTest/__unnamed_task__/MaxReturn -173.782 MetaTest/__unnamed_task__/MinReturn -259.747 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 29.7211 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 706000 ------------------------------------------------- ----------- 2025-04-05 12:20:11 | [pearl_trainer] epoch #333 | Training... 2025-04-05 12:23:16 | [pearl_trainer] epoch #333 | Evaluating... 2025-04-05 12:23:16 | [pearl_trainer] epoch #333 | Sampling for adapation and meta-testing... 2025-04-05 12:28:15 | [pearl_trainer] epoch #333 | Finished meta-testing... 2025-04-05 12:28:15 | [pearl_trainer] epoch #333 | Saving snapshot... 2025-04-05 12:28:17 | [pearl_trainer] epoch #333 | Saved 2025-04-05 12:28:17 | [pearl_trainer] epoch #333 | Time 158360.21 s 2025-04-05 12:28:17 | [pearl_trainer] epoch #333 | EpochTime 535.13 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -202.405 MetaTest/Average/AverageReturn -202.405 MetaTest/Average/Iteration 333 MetaTest/Average/MaxReturn -101.31 MetaTest/Average/MinReturn -283.215 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 64.9627 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -202.405 MetaTest/__unnamed_task__/AverageReturn -202.405 MetaTest/__unnamed_task__/Iteration 333 MetaTest/__unnamed_task__/MaxReturn -101.31 MetaTest/__unnamed_task__/MinReturn -283.215 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 64.9627 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 708000 ------------------------------------------------- ----------- 2025-04-05 12:29:09 | [pearl_trainer] epoch #334 | Training... 2025-04-05 12:31:55 | [pearl_trainer] epoch #334 | Evaluating... 2025-04-05 12:31:55 | [pearl_trainer] epoch #334 | Sampling for adapation and meta-testing... 2025-04-05 12:36:45 | [pearl_trainer] epoch #334 | Finished meta-testing... 2025-04-05 12:36:45 | [pearl_trainer] epoch #334 | Saving snapshot... 2025-04-05 12:36:46 | [pearl_trainer] epoch #334 | Saved 2025-04-05 12:36:46 | [pearl_trainer] epoch #334 | Time 158869.52 s 2025-04-05 12:36:46 | [pearl_trainer] epoch #334 | EpochTime 509.30 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -283.109 MetaTest/Average/AverageReturn -283.109 MetaTest/Average/Iteration 334 MetaTest/Average/MaxReturn -191.381 MetaTest/Average/MinReturn -370.063 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 57.2124 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -283.109 MetaTest/__unnamed_task__/AverageReturn -283.109 MetaTest/__unnamed_task__/Iteration 334 MetaTest/__unnamed_task__/MaxReturn -191.381 MetaTest/__unnamed_task__/MinReturn -370.063 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 57.2124 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 710000 ------------------------------------------------- ----------- 2025-04-05 12:37:39 | [pearl_trainer] epoch #335 | Training... 2025-04-05 12:40:36 | [pearl_trainer] epoch #335 | Evaluating... 2025-04-05 12:40:36 | [pearl_trainer] epoch #335 | Sampling for adapation and meta-testing... 2025-04-05 12:45:31 | [pearl_trainer] epoch #335 | Finished meta-testing... 2025-04-05 12:45:31 | [pearl_trainer] epoch #335 | Saving snapshot... 2025-04-05 12:45:33 | [pearl_trainer] epoch #335 | Saved 2025-04-05 12:45:33 | [pearl_trainer] epoch #335 | Time 159396.32 s 2025-04-05 12:45:33 | [pearl_trainer] epoch #335 | EpochTime 526.80 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -193.713 MetaTest/Average/AverageReturn -193.713 MetaTest/Average/Iteration 335 MetaTest/Average/MaxReturn -151.031 MetaTest/Average/MinReturn -214.36 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 22.9449 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -193.713 MetaTest/__unnamed_task__/AverageReturn -193.713 MetaTest/__unnamed_task__/Iteration 335 MetaTest/__unnamed_task__/MaxReturn -151.031 MetaTest/__unnamed_task__/MinReturn -214.36 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 22.9449 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 712000 ------------------------------------------------- ----------- 2025-04-05 12:46:25 | [pearl_trainer] epoch #336 | Training... 2025-04-05 12:49:12 | [pearl_trainer] epoch #336 | Evaluating... 2025-04-05 12:49:12 | [pearl_trainer] epoch #336 | Sampling for adapation and meta-testing... 2025-04-05 12:53:41 | [pearl_trainer] epoch #336 | Finished meta-testing... 2025-04-05 12:53:41 | [pearl_trainer] epoch #336 | Saving snapshot... 2025-04-05 12:53:42 | [pearl_trainer] epoch #336 | Saved 2025-04-05 12:53:42 | [pearl_trainer] epoch #336 | Time 159885.98 s 2025-04-05 12:53:42 | [pearl_trainer] epoch #336 | EpochTime 489.66 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -241.032 MetaTest/Average/AverageReturn -241.032 MetaTest/Average/Iteration 336 MetaTest/Average/MaxReturn -139.867 MetaTest/Average/MinReturn -312.841 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 56.6757 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -241.032 MetaTest/__unnamed_task__/AverageReturn -241.032 MetaTest/__unnamed_task__/Iteration 336 MetaTest/__unnamed_task__/MaxReturn -139.867 MetaTest/__unnamed_task__/MinReturn -312.841 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 56.6757 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 714000 ------------------------------------------------- ----------- 2025-04-05 12:54:32 | [pearl_trainer] epoch #337 | Training... 2025-04-05 12:57:18 | [pearl_trainer] epoch #337 | Evaluating... 2025-04-05 12:57:18 | [pearl_trainer] epoch #337 | Sampling for adapation and meta-testing... 2025-04-05 13:01:42 | [pearl_trainer] epoch #337 | Finished meta-testing... 2025-04-05 13:01:42 | [pearl_trainer] epoch #337 | Saving snapshot... 2025-04-05 13:01:43 | [pearl_trainer] epoch #337 | Saved 2025-04-05 13:01:43 | [pearl_trainer] epoch #337 | Time 160366.68 s 2025-04-05 13:01:43 | [pearl_trainer] epoch #337 | EpochTime 480.70 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -242.822 MetaTest/Average/AverageReturn -242.822 MetaTest/Average/Iteration 337 MetaTest/Average/MaxReturn -186.959 MetaTest/Average/MinReturn -281.895 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.2867 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -242.822 MetaTest/__unnamed_task__/AverageReturn -242.822 MetaTest/__unnamed_task__/Iteration 337 MetaTest/__unnamed_task__/MaxReturn -186.959 MetaTest/__unnamed_task__/MinReturn -281.895 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.2867 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 716000 ------------------------------------------------- ----------- 2025-04-05 13:02:25 | [pearl_trainer] epoch #338 | Training... 2025-04-05 13:05:14 | [pearl_trainer] epoch #338 | Evaluating... 2025-04-05 13:05:14 | [pearl_trainer] epoch #338 | Sampling for adapation and meta-testing... 2025-04-05 13:09:29 | [pearl_trainer] epoch #338 | Finished meta-testing... 2025-04-05 13:09:29 | [pearl_trainer] epoch #338 | Saving snapshot... 2025-04-05 13:09:30 | [pearl_trainer] epoch #338 | Saved 2025-04-05 13:09:30 | [pearl_trainer] epoch #338 | Time 160833.99 s 2025-04-05 13:09:30 | [pearl_trainer] epoch #338 | EpochTime 467.31 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -263.962 MetaTest/Average/AverageReturn -263.962 MetaTest/Average/Iteration 338 MetaTest/Average/MaxReturn -205.628 MetaTest/Average/MinReturn -380.163 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 68.3291 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -263.962 MetaTest/__unnamed_task__/AverageReturn -263.962 MetaTest/__unnamed_task__/Iteration 338 MetaTest/__unnamed_task__/MaxReturn -205.628 MetaTest/__unnamed_task__/MinReturn -380.163 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 68.3291 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 718000 ------------------------------------------------- ----------- 2025-04-05 13:10:17 | [pearl_trainer] epoch #339 | Training... 2025-04-05 13:13:01 | [pearl_trainer] epoch #339 | Evaluating... 2025-04-05 13:13:01 | [pearl_trainer] epoch #339 | Sampling for adapation and meta-testing... 2025-04-05 13:17:08 | [pearl_trainer] epoch #339 | Finished meta-testing... 2025-04-05 13:17:08 | [pearl_trainer] epoch #339 | Saving snapshot... 2025-04-05 13:17:09 | [pearl_trainer] epoch #339 | Saved 2025-04-05 13:17:09 | [pearl_trainer] epoch #339 | Time 161292.66 s 2025-04-05 13:17:09 | [pearl_trainer] epoch #339 | EpochTime 458.67 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -275.943 MetaTest/Average/AverageReturn -275.943 MetaTest/Average/Iteration 339 MetaTest/Average/MaxReturn -246.521 MetaTest/Average/MinReturn -344.713 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 35.4476 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -275.943 MetaTest/__unnamed_task__/AverageReturn -275.943 MetaTest/__unnamed_task__/Iteration 339 MetaTest/__unnamed_task__/MaxReturn -246.521 MetaTest/__unnamed_task__/MinReturn -344.713 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 35.4476 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 720000 ------------------------------------------------- ----------- 2025-04-05 13:17:54 | [pearl_trainer] epoch #340 | Training... 2025-04-05 13:20:37 | [pearl_trainer] epoch #340 | Evaluating... 2025-04-05 13:20:37 | [pearl_trainer] epoch #340 | Sampling for adapation and meta-testing... 2025-04-05 13:24:35 | [pearl_trainer] epoch #340 | Finished meta-testing... 2025-04-05 13:24:35 | [pearl_trainer] epoch #340 | Saving snapshot... 2025-04-05 13:24:37 | [pearl_trainer] epoch #340 | Saved 2025-04-05 13:24:37 | [pearl_trainer] epoch #340 | Time 161740.22 s 2025-04-05 13:24:37 | [pearl_trainer] epoch #340 | EpochTime 447.55 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -284.25 MetaTest/Average/AverageReturn -284.25 MetaTest/Average/Iteration 340 MetaTest/Average/MaxReturn -208.651 MetaTest/Average/MinReturn -334.78 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 49.4191 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -284.25 MetaTest/__unnamed_task__/AverageReturn -284.25 MetaTest/__unnamed_task__/Iteration 340 MetaTest/__unnamed_task__/MaxReturn -208.651 MetaTest/__unnamed_task__/MinReturn -334.78 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 49.4191 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 722000 ------------------------------------------------- ----------- 2025-04-05 13:25:20 | [pearl_trainer] epoch #341 | Training... 2025-04-05 13:28:05 | [pearl_trainer] epoch #341 | Evaluating... 2025-04-05 13:28:05 | [pearl_trainer] epoch #341 | Sampling for adapation and meta-testing... 2025-04-05 13:32:10 | [pearl_trainer] epoch #341 | Finished meta-testing... 2025-04-05 13:32:10 | [pearl_trainer] epoch #341 | Saving snapshot... 2025-04-05 13:32:11 | [pearl_trainer] epoch #341 | Saved 2025-04-05 13:32:11 | [pearl_trainer] epoch #341 | Time 162194.77 s 2025-04-05 13:32:11 | [pearl_trainer] epoch #341 | EpochTime 454.55 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -335.015 MetaTest/Average/AverageReturn -335.015 MetaTest/Average/Iteration 341 MetaTest/Average/MaxReturn -264.497 MetaTest/Average/MinReturn -407.533 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 45.9561 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -335.015 MetaTest/__unnamed_task__/AverageReturn -335.015 MetaTest/__unnamed_task__/Iteration 341 MetaTest/__unnamed_task__/MaxReturn -264.497 MetaTest/__unnamed_task__/MinReturn -407.533 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 45.9561 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 724000 ------------------------------------------------- ----------- 2025-04-05 13:32:54 | [pearl_trainer] epoch #342 | Training... 2025-04-05 13:36:03 | [pearl_trainer] epoch #342 | Evaluating... 2025-04-05 13:36:03 | [pearl_trainer] epoch #342 | Sampling for adapation and meta-testing... 2025-04-05 13:40:01 | [pearl_trainer] epoch #342 | Finished meta-testing... 2025-04-05 13:40:01 | [pearl_trainer] epoch #342 | Saving snapshot... 2025-04-05 13:40:03 | [pearl_trainer] epoch #342 | Saved 2025-04-05 13:40:03 | [pearl_trainer] epoch #342 | Time 162666.40 s 2025-04-05 13:40:03 | [pearl_trainer] epoch #342 | EpochTime 471.62 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -305.799 MetaTest/Average/AverageReturn -305.799 MetaTest/Average/Iteration 342 MetaTest/Average/MaxReturn -273.722 MetaTest/Average/MinReturn -361.977 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.7309 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -305.799 MetaTest/__unnamed_task__/AverageReturn -305.799 MetaTest/__unnamed_task__/Iteration 342 MetaTest/__unnamed_task__/MaxReturn -273.722 MetaTest/__unnamed_task__/MinReturn -361.977 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.7309 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 726000 ------------------------------------------------- ----------- 2025-04-05 13:40:46 | [pearl_trainer] epoch #343 | Training... 2025-04-05 13:43:51 | [pearl_trainer] epoch #343 | Evaluating... 2025-04-05 13:43:51 | [pearl_trainer] epoch #343 | Sampling for adapation and meta-testing... 2025-04-05 13:47:53 | [pearl_trainer] epoch #343 | Finished meta-testing... 2025-04-05 13:47:53 | [pearl_trainer] epoch #343 | Saving snapshot... 2025-04-05 13:47:54 | [pearl_trainer] epoch #343 | Saved 2025-04-05 13:47:54 | [pearl_trainer] epoch #343 | Time 163137.87 s 2025-04-05 13:47:54 | [pearl_trainer] epoch #343 | EpochTime 471.47 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -251.105 MetaTest/Average/AverageReturn -251.105 MetaTest/Average/Iteration 343 MetaTest/Average/MaxReturn -233.051 MetaTest/Average/MinReturn -279.417 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 15.2768 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -251.105 MetaTest/__unnamed_task__/AverageReturn -251.105 MetaTest/__unnamed_task__/Iteration 343 MetaTest/__unnamed_task__/MaxReturn -233.051 MetaTest/__unnamed_task__/MinReturn -279.417 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 15.2768 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 728000 ------------------------------------------------- ----------- 2025-04-05 13:48:44 | [pearl_trainer] epoch #344 | Training... 2025-04-05 13:51:48 | [pearl_trainer] epoch #344 | Evaluating... 2025-04-05 13:51:48 | [pearl_trainer] epoch #344 | Sampling for adapation and meta-testing... 2025-04-05 13:55:57 | [pearl_trainer] epoch #344 | Finished meta-testing... 2025-04-05 13:55:57 | [pearl_trainer] epoch #344 | Saving snapshot... 2025-04-05 13:55:58 | [pearl_trainer] epoch #344 | Saved 2025-04-05 13:55:58 | [pearl_trainer] epoch #344 | Time 163621.66 s 2025-04-05 13:55:58 | [pearl_trainer] epoch #344 | EpochTime 483.78 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -243.136 MetaTest/Average/AverageReturn -243.136 MetaTest/Average/Iteration 344 MetaTest/Average/MaxReturn -197.883 MetaTest/Average/MinReturn -304.361 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.8004 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -243.136 MetaTest/__unnamed_task__/AverageReturn -243.136 MetaTest/__unnamed_task__/Iteration 344 MetaTest/__unnamed_task__/MaxReturn -197.883 MetaTest/__unnamed_task__/MinReturn -304.361 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.8004 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 730000 ------------------------------------------------- ----------- 2025-04-05 13:56:44 | [pearl_trainer] epoch #345 | Training... 2025-04-05 13:59:50 | [pearl_trainer] epoch #345 | Evaluating... 2025-04-05 13:59:50 | [pearl_trainer] epoch #345 | Sampling for adapation and meta-testing... 2025-04-05 14:04:04 | [pearl_trainer] epoch #345 | Finished meta-testing... 2025-04-05 14:04:04 | [pearl_trainer] epoch #345 | Saving snapshot... 2025-04-05 14:04:05 | [pearl_trainer] epoch #345 | Saved 2025-04-05 14:04:05 | [pearl_trainer] epoch #345 | Time 164108.60 s 2025-04-05 14:04:05 | [pearl_trainer] epoch #345 | EpochTime 486.94 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -239.309 MetaTest/Average/AverageReturn -239.309 MetaTest/Average/Iteration 345 MetaTest/Average/MaxReturn -203.39 MetaTest/Average/MinReturn -293.364 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 29.5146 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -239.309 MetaTest/__unnamed_task__/AverageReturn -239.309 MetaTest/__unnamed_task__/Iteration 345 MetaTest/__unnamed_task__/MaxReturn -203.39 MetaTest/__unnamed_task__/MinReturn -293.364 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 29.5146 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 732000 ------------------------------------------------- ----------- 2025-04-05 14:04:50 | [pearl_trainer] epoch #346 | Training... 2025-04-05 14:07:28 | [pearl_trainer] epoch #346 | Evaluating... 2025-04-05 14:07:28 | [pearl_trainer] epoch #346 | Sampling for adapation and meta-testing... 2025-04-05 14:11:44 | [pearl_trainer] epoch #346 | Finished meta-testing... 2025-04-05 14:11:44 | [pearl_trainer] epoch #346 | Saving snapshot... 2025-04-05 14:11:46 | [pearl_trainer] epoch #346 | Saved 2025-04-05 14:11:46 | [pearl_trainer] epoch #346 | Time 164569.59 s 2025-04-05 14:11:46 | [pearl_trainer] epoch #346 | EpochTime 460.99 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -292.702 MetaTest/Average/AverageReturn -292.702 MetaTest/Average/Iteration 346 MetaTest/Average/MaxReturn -210.648 MetaTest/Average/MinReturn -364.643 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 53.7831 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -292.702 MetaTest/__unnamed_task__/AverageReturn -292.702 MetaTest/__unnamed_task__/Iteration 346 MetaTest/__unnamed_task__/MaxReturn -210.648 MetaTest/__unnamed_task__/MinReturn -364.643 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 53.7831 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 734000 ------------------------------------------------- ----------- 2025-04-05 14:12:32 | [pearl_trainer] epoch #347 | Training... 2025-04-05 14:15:16 | [pearl_trainer] epoch #347 | Evaluating... 2025-04-05 14:15:16 | [pearl_trainer] epoch #347 | Sampling for adapation and meta-testing... 2025-04-05 14:19:35 | [pearl_trainer] epoch #347 | Finished meta-testing... 2025-04-05 14:19:35 | [pearl_trainer] epoch #347 | Saving snapshot... 2025-04-05 14:19:36 | [pearl_trainer] epoch #347 | Saved 2025-04-05 14:19:36 | [pearl_trainer] epoch #347 | Time 165039.92 s 2025-04-05 14:19:36 | [pearl_trainer] epoch #347 | EpochTime 470.33 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -251.176 MetaTest/Average/AverageReturn -251.176 MetaTest/Average/Iteration 347 MetaTest/Average/MaxReturn -156.629 MetaTest/Average/MinReturn -372.545 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 76.4556 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -251.176 MetaTest/__unnamed_task__/AverageReturn -251.176 MetaTest/__unnamed_task__/Iteration 347 MetaTest/__unnamed_task__/MaxReturn -156.629 MetaTest/__unnamed_task__/MinReturn -372.545 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 76.4556 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 736000 ------------------------------------------------- ----------- 2025-04-05 14:20:18 | [pearl_trainer] epoch #348 | Training... 2025-04-05 14:23:16 | [pearl_trainer] epoch #348 | Evaluating... 2025-04-05 14:23:16 | [pearl_trainer] epoch #348 | Sampling for adapation and meta-testing... 2025-04-05 14:27:32 | [pearl_trainer] epoch #348 | Finished meta-testing... 2025-04-05 14:27:32 | [pearl_trainer] epoch #348 | Saving snapshot... 2025-04-05 14:27:33 | [pearl_trainer] epoch #348 | Saved 2025-04-05 14:27:33 | [pearl_trainer] epoch #348 | Time 165517.00 s 2025-04-05 14:27:33 | [pearl_trainer] epoch #348 | EpochTime 477.07 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -253.557 MetaTest/Average/AverageReturn -253.557 MetaTest/Average/Iteration 348 MetaTest/Average/MaxReturn -239.042 MetaTest/Average/MinReturn -278.863 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 14.8746 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -253.557 MetaTest/__unnamed_task__/AverageReturn -253.557 MetaTest/__unnamed_task__/Iteration 348 MetaTest/__unnamed_task__/MaxReturn -239.042 MetaTest/__unnamed_task__/MinReturn -278.863 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 14.8746 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 738000 ------------------------------------------------- ----------- 2025-04-05 14:28:23 | [pearl_trainer] epoch #349 | Training... 2025-04-05 14:31:30 | [pearl_trainer] epoch #349 | Evaluating... 2025-04-05 14:31:30 | [pearl_trainer] epoch #349 | Sampling for adapation and meta-testing... 2025-04-05 14:35:45 | [pearl_trainer] epoch #349 | Finished meta-testing... 2025-04-05 14:35:45 | [pearl_trainer] epoch #349 | Saving snapshot... 2025-04-05 14:35:46 | [pearl_trainer] epoch #349 | Saved 2025-04-05 14:35:46 | [pearl_trainer] epoch #349 | Time 166009.95 s 2025-04-05 14:35:46 | [pearl_trainer] epoch #349 | EpochTime 492.94 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -284.352 MetaTest/Average/AverageReturn -284.352 MetaTest/Average/Iteration 349 MetaTest/Average/MaxReturn -239.693 MetaTest/Average/MinReturn -322.164 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 30.0154 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -284.352 MetaTest/__unnamed_task__/AverageReturn -284.352 MetaTest/__unnamed_task__/Iteration 349 MetaTest/__unnamed_task__/MaxReturn -239.693 MetaTest/__unnamed_task__/MinReturn -322.164 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 30.0154 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 740000 ------------------------------------------------- ----------- 2025-04-05 14:36:31 | [pearl_trainer] epoch #350 | Training... 2025-04-05 14:39:33 | [pearl_trainer] epoch #350 | Evaluating... 2025-04-05 14:39:33 | [pearl_trainer] epoch #350 | Sampling for adapation and meta-testing... 2025-04-05 14:43:46 | [pearl_trainer] epoch #350 | Finished meta-testing... 2025-04-05 14:43:46 | [pearl_trainer] epoch #350 | Saving snapshot... 2025-04-05 14:43:47 | [pearl_trainer] epoch #350 | Saved 2025-04-05 14:43:47 | [pearl_trainer] epoch #350 | Time 166490.81 s 2025-04-05 14:43:47 | [pearl_trainer] epoch #350 | EpochTime 480.86 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -223.075 MetaTest/Average/AverageReturn -223.075 MetaTest/Average/Iteration 350 MetaTest/Average/MaxReturn -121.297 MetaTest/Average/MinReturn -337.409 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 76.9338 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -223.075 MetaTest/__unnamed_task__/AverageReturn -223.075 MetaTest/__unnamed_task__/Iteration 350 MetaTest/__unnamed_task__/MaxReturn -121.297 MetaTest/__unnamed_task__/MinReturn -337.409 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 76.9338 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 742000 ------------------------------------------------- ----------- 2025-04-05 14:44:34 | [pearl_trainer] epoch #351 | Training... 2025-04-05 14:47:41 | [pearl_trainer] epoch #351 | Evaluating... 2025-04-05 14:47:41 | [pearl_trainer] epoch #351 | Sampling for adapation and meta-testing... 2025-04-05 14:52:06 | [pearl_trainer] epoch #351 | Finished meta-testing... 2025-04-05 14:52:06 | [pearl_trainer] epoch #351 | Saving snapshot... 2025-04-05 14:52:08 | [pearl_trainer] epoch #351 | Saved 2025-04-05 14:52:08 | [pearl_trainer] epoch #351 | Time 166991.24 s 2025-04-05 14:52:08 | [pearl_trainer] epoch #351 | EpochTime 500.43 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -254.968 MetaTest/Average/AverageReturn -254.968 MetaTest/Average/Iteration 351 MetaTest/Average/MaxReturn -146.296 MetaTest/Average/MinReturn -352.813 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 65.9486 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -254.968 MetaTest/__unnamed_task__/AverageReturn -254.968 MetaTest/__unnamed_task__/Iteration 351 MetaTest/__unnamed_task__/MaxReturn -146.296 MetaTest/__unnamed_task__/MinReturn -352.813 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 65.9486 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 744000 ------------------------------------------------- ----------- 2025-04-05 14:52:56 | [pearl_trainer] epoch #352 | Training... 2025-04-05 14:55:53 | [pearl_trainer] epoch #352 | Evaluating... 2025-04-05 14:55:53 | [pearl_trainer] epoch #352 | Sampling for adapation and meta-testing... 2025-04-05 15:00:24 | [pearl_trainer] epoch #352 | Finished meta-testing... 2025-04-05 15:00:24 | [pearl_trainer] epoch #352 | Saving snapshot... 2025-04-05 15:00:26 | [pearl_trainer] epoch #352 | Saved 2025-04-05 15:00:26 | [pearl_trainer] epoch #352 | Time 167489.29 s 2025-04-05 15:00:26 | [pearl_trainer] epoch #352 | EpochTime 498.05 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -238.655 MetaTest/Average/AverageReturn -238.655 MetaTest/Average/Iteration 352 MetaTest/Average/MaxReturn -221.111 MetaTest/Average/MinReturn -273.727 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 18.8257 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -238.655 MetaTest/__unnamed_task__/AverageReturn -238.655 MetaTest/__unnamed_task__/Iteration 352 MetaTest/__unnamed_task__/MaxReturn -221.111 MetaTest/__unnamed_task__/MinReturn -273.727 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 18.8257 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 746000 ------------------------------------------------- ----------- 2025-04-05 15:01:14 | [pearl_trainer] epoch #353 | Training... 2025-04-05 15:03:58 | [pearl_trainer] epoch #353 | Evaluating... 2025-04-05 15:03:58 | [pearl_trainer] epoch #353 | Sampling for adapation and meta-testing... 2025-04-05 15:08:32 | [pearl_trainer] epoch #353 | Finished meta-testing... 2025-04-05 15:08:32 | [pearl_trainer] epoch #353 | Saving snapshot... 2025-04-05 15:08:33 | [pearl_trainer] epoch #353 | Saved 2025-04-05 15:08:33 | [pearl_trainer] epoch #353 | Time 167976.69 s 2025-04-05 15:08:33 | [pearl_trainer] epoch #353 | EpochTime 487.40 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -205.635 MetaTest/Average/AverageReturn -205.635 MetaTest/Average/Iteration 353 MetaTest/Average/MaxReturn -157.876 MetaTest/Average/MinReturn -265.272 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.1602 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -205.635 MetaTest/__unnamed_task__/AverageReturn -205.635 MetaTest/__unnamed_task__/Iteration 353 MetaTest/__unnamed_task__/MaxReturn -157.876 MetaTest/__unnamed_task__/MinReturn -265.272 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.1602 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 748000 ------------------------------------------------- ----------- 2025-04-05 15:09:24 | [pearl_trainer] epoch #354 | Training... 2025-04-05 15:12:08 | [pearl_trainer] epoch #354 | Evaluating... 2025-04-05 15:12:08 | [pearl_trainer] epoch #354 | Sampling for adapation and meta-testing... 2025-04-05 15:16:38 | [pearl_trainer] epoch #354 | Finished meta-testing... 2025-04-05 15:16:38 | [pearl_trainer] epoch #354 | Saving snapshot... 2025-04-05 15:16:40 | [pearl_trainer] epoch #354 | Saved 2025-04-05 15:16:40 | [pearl_trainer] epoch #354 | Time 168463.41 s 2025-04-05 15:16:40 | [pearl_trainer] epoch #354 | EpochTime 486.72 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -202.171 MetaTest/Average/AverageReturn -202.171 MetaTest/Average/Iteration 354 MetaTest/Average/MaxReturn -113.047 MetaTest/Average/MinReturn -287.883 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 65.5293 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -202.171 MetaTest/__unnamed_task__/AverageReturn -202.171 MetaTest/__unnamed_task__/Iteration 354 MetaTest/__unnamed_task__/MaxReturn -113.047 MetaTest/__unnamed_task__/MinReturn -287.883 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 65.5293 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 750000 ------------------------------------------------- ----------- 2025-04-05 15:17:28 | [pearl_trainer] epoch #355 | Training... 2025-04-05 15:20:12 | [pearl_trainer] epoch #355 | Evaluating... 2025-04-05 15:20:12 | [pearl_trainer] epoch #355 | Sampling for adapation and meta-testing... 2025-04-05 15:24:47 | [pearl_trainer] epoch #355 | Finished meta-testing... 2025-04-05 15:24:47 | [pearl_trainer] epoch #355 | Saving snapshot... 2025-04-05 15:24:48 | [pearl_trainer] epoch #355 | Saved 2025-04-05 15:24:48 | [pearl_trainer] epoch #355 | Time 168951.36 s 2025-04-05 15:24:48 | [pearl_trainer] epoch #355 | EpochTime 487.95 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -324.075 MetaTest/Average/AverageReturn -324.075 MetaTest/Average/Iteration 355 MetaTest/Average/MaxReturn -251.625 MetaTest/Average/MinReturn -348.454 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.4662 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -324.075 MetaTest/__unnamed_task__/AverageReturn -324.075 MetaTest/__unnamed_task__/Iteration 355 MetaTest/__unnamed_task__/MaxReturn -251.625 MetaTest/__unnamed_task__/MinReturn -348.454 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.4662 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 752000 ------------------------------------------------- ----------- 2025-04-05 15:25:35 | [pearl_trainer] epoch #356 | Training... 2025-04-05 15:28:19 | [pearl_trainer] epoch #356 | Evaluating... 2025-04-05 15:28:19 | [pearl_trainer] epoch #356 | Sampling for adapation and meta-testing... 2025-04-05 15:32:52 | [pearl_trainer] epoch #356 | Finished meta-testing... 2025-04-05 15:32:52 | [pearl_trainer] epoch #356 | Saving snapshot... 2025-04-05 15:32:53 | [pearl_trainer] epoch #356 | Saved 2025-04-05 15:32:53 | [pearl_trainer] epoch #356 | Time 169437.13 s 2025-04-05 15:32:53 | [pearl_trainer] epoch #356 | EpochTime 485.77 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -332.918 MetaTest/Average/AverageReturn -332.918 MetaTest/Average/Iteration 356 MetaTest/Average/MaxReturn -259.563 MetaTest/Average/MinReturn -374.49 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 45.8766 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -332.918 MetaTest/__unnamed_task__/AverageReturn -332.918 MetaTest/__unnamed_task__/Iteration 356 MetaTest/__unnamed_task__/MaxReturn -259.563 MetaTest/__unnamed_task__/MinReturn -374.49 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 45.8766 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 754000 ------------------------------------------------- ----------- 2025-04-05 15:33:39 | [pearl_trainer] epoch #357 | Training... 2025-04-05 15:36:23 | [pearl_trainer] epoch #357 | Evaluating... 2025-04-05 15:36:23 | [pearl_trainer] epoch #357 | Sampling for adapation and meta-testing... 2025-04-05 15:40:56 | [pearl_trainer] epoch #357 | Finished meta-testing... 2025-04-05 15:40:56 | [pearl_trainer] epoch #357 | Saving snapshot... 2025-04-05 15:40:57 | [pearl_trainer] epoch #357 | Saved 2025-04-05 15:40:57 | [pearl_trainer] epoch #357 | Time 169920.83 s 2025-04-05 15:40:57 | [pearl_trainer] epoch #357 | EpochTime 483.69 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -278.627 MetaTest/Average/AverageReturn -278.627 MetaTest/Average/Iteration 357 MetaTest/Average/MaxReturn -212.062 MetaTest/Average/MinReturn -361.197 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 61.0622 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -278.627 MetaTest/__unnamed_task__/AverageReturn -278.627 MetaTest/__unnamed_task__/Iteration 357 MetaTest/__unnamed_task__/MaxReturn -212.062 MetaTest/__unnamed_task__/MinReturn -361.197 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 61.0622 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 756000 ------------------------------------------------- ----------- 2025-04-05 15:41:47 | [pearl_trainer] epoch #358 | Training... 2025-04-05 15:44:31 | [pearl_trainer] epoch #358 | Evaluating... 2025-04-05 15:44:31 | [pearl_trainer] epoch #358 | Sampling for adapation and meta-testing... 2025-04-05 15:49:08 | [pearl_trainer] epoch #358 | Finished meta-testing... 2025-04-05 15:49:08 | [pearl_trainer] epoch #358 | Saving snapshot... 2025-04-05 15:49:10 | [pearl_trainer] epoch #358 | Saved 2025-04-05 15:49:10 | [pearl_trainer] epoch #358 | Time 170413.23 s 2025-04-05 15:49:10 | [pearl_trainer] epoch #358 | EpochTime 492.40 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -238.627 MetaTest/Average/AverageReturn -238.627 MetaTest/Average/Iteration 358 MetaTest/Average/MaxReturn -163.529 MetaTest/Average/MinReturn -318.205 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 50.2416 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -238.627 MetaTest/__unnamed_task__/AverageReturn -238.627 MetaTest/__unnamed_task__/Iteration 358 MetaTest/__unnamed_task__/MaxReturn -163.529 MetaTest/__unnamed_task__/MinReturn -318.205 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 50.2416 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 758000 ------------------------------------------------- ----------- 2025-04-05 15:49:57 | [pearl_trainer] epoch #359 | Training... 2025-04-05 15:52:41 | [pearl_trainer] epoch #359 | Evaluating... 2025-04-05 15:52:41 | [pearl_trainer] epoch #359 | Sampling for adapation and meta-testing... 2025-04-05 15:57:29 | [pearl_trainer] epoch #359 | Finished meta-testing... 2025-04-05 15:57:29 | [pearl_trainer] epoch #359 | Saving snapshot... 2025-04-05 15:57:31 | [pearl_trainer] epoch #359 | Saved 2025-04-05 15:57:31 | [pearl_trainer] epoch #359 | Time 170914.29 s 2025-04-05 15:57:31 | [pearl_trainer] epoch #359 | EpochTime 501.05 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -190.496 MetaTest/Average/AverageReturn -190.496 MetaTest/Average/Iteration 359 MetaTest/Average/MaxReturn -138.761 MetaTest/Average/MinReturn -251.298 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 43.9057 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -190.496 MetaTest/__unnamed_task__/AverageReturn -190.496 MetaTest/__unnamed_task__/Iteration 359 MetaTest/__unnamed_task__/MaxReturn -138.761 MetaTest/__unnamed_task__/MinReturn -251.298 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 43.9057 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 760000 ------------------------------------------------- ----------- 2025-04-05 15:58:18 | [pearl_trainer] epoch #360 | Training... 2025-04-05 16:01:07 | [pearl_trainer] epoch #360 | Evaluating... 2025-04-05 16:01:07 | [pearl_trainer] epoch #360 | Sampling for adapation and meta-testing... 2025-04-05 16:06:06 | [pearl_trainer] epoch #360 | Finished meta-testing... 2025-04-05 16:06:06 | [pearl_trainer] epoch #360 | Saving snapshot... 2025-04-05 16:06:07 | [pearl_trainer] epoch #360 | Saved 2025-04-05 16:06:07 | [pearl_trainer] epoch #360 | Time 171430.95 s 2025-04-05 16:06:07 | [pearl_trainer] epoch #360 | EpochTime 516.66 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -198.653 MetaTest/Average/AverageReturn -198.653 MetaTest/Average/Iteration 360 MetaTest/Average/MaxReturn -134.022 MetaTest/Average/MinReturn -268.558 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 53.8795 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -198.653 MetaTest/__unnamed_task__/AverageReturn -198.653 MetaTest/__unnamed_task__/Iteration 360 MetaTest/__unnamed_task__/MaxReturn -134.022 MetaTest/__unnamed_task__/MinReturn -268.558 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 53.8795 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 762000 ------------------------------------------------- ----------- 2025-04-05 16:06:59 | [pearl_trainer] epoch #361 | Training... 2025-04-05 16:09:38 | [pearl_trainer] epoch #361 | Evaluating... 2025-04-05 16:09:38 | [pearl_trainer] epoch #361 | Sampling for adapation and meta-testing... 2025-04-05 16:14:32 | [pearl_trainer] epoch #361 | Finished meta-testing... 2025-04-05 16:14:32 | [pearl_trainer] epoch #361 | Saving snapshot... 2025-04-05 16:14:33 | [pearl_trainer] epoch #361 | Saved 2025-04-05 16:14:33 | [pearl_trainer] epoch #361 | Time 171936.66 s 2025-04-05 16:14:33 | [pearl_trainer] epoch #361 | EpochTime 505.71 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -224.397 MetaTest/Average/AverageReturn -224.397 MetaTest/Average/Iteration 361 MetaTest/Average/MaxReturn -145.814 MetaTest/Average/MinReturn -360.382 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 74.3373 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -224.397 MetaTest/__unnamed_task__/AverageReturn -224.397 MetaTest/__unnamed_task__/Iteration 361 MetaTest/__unnamed_task__/MaxReturn -145.814 MetaTest/__unnamed_task__/MinReturn -360.382 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 74.3373 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 764000 ------------------------------------------------- ----------- 2025-04-05 16:15:22 | [pearl_trainer] epoch #362 | Training... 2025-04-05 16:17:58 | [pearl_trainer] epoch #362 | Evaluating... 2025-04-05 16:17:58 | [pearl_trainer] epoch #362 | Sampling for adapation and meta-testing... 2025-04-05 16:23:09 | [pearl_trainer] epoch #362 | Finished meta-testing... 2025-04-05 16:23:09 | [pearl_trainer] epoch #362 | Saving snapshot... 2025-04-05 16:23:10 | [pearl_trainer] epoch #362 | Saved 2025-04-05 16:23:10 | [pearl_trainer] epoch #362 | Time 172454.13 s 2025-04-05 16:23:10 | [pearl_trainer] epoch #362 | EpochTime 517.46 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -237.048 MetaTest/Average/AverageReturn -237.048 MetaTest/Average/Iteration 362 MetaTest/Average/MaxReturn -166.013 MetaTest/Average/MinReturn -334.801 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 61.6713 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -237.048 MetaTest/__unnamed_task__/AverageReturn -237.048 MetaTest/__unnamed_task__/Iteration 362 MetaTest/__unnamed_task__/MaxReturn -166.013 MetaTest/__unnamed_task__/MinReturn -334.801 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 61.6713 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 766000 ------------------------------------------------- ----------- 2025-04-05 16:24:07 | [pearl_trainer] epoch #363 | Training... 2025-04-05 16:26:50 | [pearl_trainer] epoch #363 | Evaluating... 2025-04-05 16:26:50 | [pearl_trainer] epoch #363 | Sampling for adapation and meta-testing... 2025-04-05 16:31:54 | [pearl_trainer] epoch #363 | Finished meta-testing... 2025-04-05 16:31:54 | [pearl_trainer] epoch #363 | Saving snapshot... 2025-04-05 16:31:55 | [pearl_trainer] epoch #363 | Saved 2025-04-05 16:31:55 | [pearl_trainer] epoch #363 | Time 172978.63 s 2025-04-05 16:31:55 | [pearl_trainer] epoch #363 | EpochTime 524.51 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -188.784 MetaTest/Average/AverageReturn -188.784 MetaTest/Average/Iteration 363 MetaTest/Average/MaxReturn -85.1703 MetaTest/Average/MinReturn -266.933 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 65.4077 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -188.784 MetaTest/__unnamed_task__/AverageReturn -188.784 MetaTest/__unnamed_task__/Iteration 363 MetaTest/__unnamed_task__/MaxReturn -85.1703 MetaTest/__unnamed_task__/MinReturn -266.933 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 65.4077 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 768000 ------------------------------------------------- ----------- 2025-04-05 16:32:48 | [pearl_trainer] epoch #364 | Training... 2025-04-05 16:35:30 | [pearl_trainer] epoch #364 | Evaluating... 2025-04-05 16:35:30 | [pearl_trainer] epoch #364 | Sampling for adapation and meta-testing... 2025-04-05 16:40:36 | [pearl_trainer] epoch #364 | Finished meta-testing... 2025-04-05 16:40:36 | [pearl_trainer] epoch #364 | Saving snapshot... 2025-04-05 16:40:38 | [pearl_trainer] epoch #364 | Saved 2025-04-05 16:40:38 | [pearl_trainer] epoch #364 | Time 173501.33 s 2025-04-05 16:40:38 | [pearl_trainer] epoch #364 | EpochTime 522.69 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -226.573 MetaTest/Average/AverageReturn -226.573 MetaTest/Average/Iteration 364 MetaTest/Average/MaxReturn -206.495 MetaTest/Average/MinReturn -256.679 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 18.6245 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -226.573 MetaTest/__unnamed_task__/AverageReturn -226.573 MetaTest/__unnamed_task__/Iteration 364 MetaTest/__unnamed_task__/MaxReturn -206.495 MetaTest/__unnamed_task__/MinReturn -256.679 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 18.6245 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 770000 ------------------------------------------------- ----------- 2025-04-05 16:41:32 | [pearl_trainer] epoch #365 | Training... 2025-04-05 16:44:14 | [pearl_trainer] epoch #365 | Evaluating... 2025-04-05 16:44:14 | [pearl_trainer] epoch #365 | Sampling for adapation and meta-testing... 2025-04-05 16:49:10 | [pearl_trainer] epoch #365 | Finished meta-testing... 2025-04-05 16:49:10 | [pearl_trainer] epoch #365 | Saving snapshot... 2025-04-05 16:49:12 | [pearl_trainer] epoch #365 | Saved 2025-04-05 16:49:12 | [pearl_trainer] epoch #365 | Time 174015.29 s 2025-04-05 16:49:12 | [pearl_trainer] epoch #365 | EpochTime 513.96 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -237.822 MetaTest/Average/AverageReturn -237.822 MetaTest/Average/Iteration 365 MetaTest/Average/MaxReturn -89.9909 MetaTest/Average/MinReturn -292.971 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 76.1832 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -237.822 MetaTest/__unnamed_task__/AverageReturn -237.822 MetaTest/__unnamed_task__/Iteration 365 MetaTest/__unnamed_task__/MaxReturn -89.9909 MetaTest/__unnamed_task__/MinReturn -292.971 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 76.1832 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 772000 ------------------------------------------------- ----------- 2025-04-05 16:50:04 | [pearl_trainer] epoch #366 | Training... 2025-04-05 16:52:43 | [pearl_trainer] epoch #366 | Evaluating... 2025-04-05 16:52:43 | [pearl_trainer] epoch #366 | Sampling for adapation and meta-testing... 2025-04-05 16:57:36 | [pearl_trainer] epoch #366 | Finished meta-testing... 2025-04-05 16:57:36 | [pearl_trainer] epoch #366 | Saving snapshot... 2025-04-05 16:57:37 | [pearl_trainer] epoch #366 | Saved 2025-04-05 16:57:37 | [pearl_trainer] epoch #366 | Time 174520.85 s 2025-04-05 16:57:37 | [pearl_trainer] epoch #366 | EpochTime 505.56 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -274.105 MetaTest/Average/AverageReturn -274.105 MetaTest/Average/Iteration 366 MetaTest/Average/MaxReturn -238.132 MetaTest/Average/MinReturn -332.845 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.4652 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -274.105 MetaTest/__unnamed_task__/AverageReturn -274.105 MetaTest/__unnamed_task__/Iteration 366 MetaTest/__unnamed_task__/MaxReturn -238.132 MetaTest/__unnamed_task__/MinReturn -332.845 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.4652 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 774000 ------------------------------------------------- ----------- 2025-04-05 16:58:32 | [pearl_trainer] epoch #367 | Training... 2025-04-05 17:01:16 | [pearl_trainer] epoch #367 | Evaluating... 2025-04-05 17:01:16 | [pearl_trainer] epoch #367 | Sampling for adapation and meta-testing... 2025-04-05 17:06:11 | [pearl_trainer] epoch #367 | Finished meta-testing... 2025-04-05 17:06:11 | [pearl_trainer] epoch #367 | Saving snapshot... 2025-04-05 17:06:12 | [pearl_trainer] epoch #367 | Saved 2025-04-05 17:06:12 | [pearl_trainer] epoch #367 | Time 175036.07 s 2025-04-05 17:06:12 | [pearl_trainer] epoch #367 | EpochTime 515.22 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -219.895 MetaTest/Average/AverageReturn -219.895 MetaTest/Average/Iteration 367 MetaTest/Average/MaxReturn -116.122 MetaTest/Average/MinReturn -275.207 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 59.8464 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -219.895 MetaTest/__unnamed_task__/AverageReturn -219.895 MetaTest/__unnamed_task__/Iteration 367 MetaTest/__unnamed_task__/MaxReturn -116.122 MetaTest/__unnamed_task__/MinReturn -275.207 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 59.8464 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 776000 ------------------------------------------------- ----------- 2025-04-05 17:07:06 | [pearl_trainer] epoch #368 | Training... 2025-04-05 17:09:52 | [pearl_trainer] epoch #368 | Evaluating... 2025-04-05 17:09:52 | [pearl_trainer] epoch #368 | Sampling for adapation and meta-testing... 2025-04-05 17:14:37 | [pearl_trainer] epoch #368 | Finished meta-testing... 2025-04-05 17:14:37 | [pearl_trainer] epoch #368 | Saving snapshot... 2025-04-05 17:14:39 | [pearl_trainer] epoch #368 | Saved 2025-04-05 17:14:39 | [pearl_trainer] epoch #368 | Time 175542.63 s 2025-04-05 17:14:39 | [pearl_trainer] epoch #368 | EpochTime 506.55 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -264.502 MetaTest/Average/AverageReturn -264.502 MetaTest/Average/Iteration 368 MetaTest/Average/MaxReturn -214.085 MetaTest/Average/MinReturn -298.779 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 30.1332 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -264.502 MetaTest/__unnamed_task__/AverageReturn -264.502 MetaTest/__unnamed_task__/Iteration 368 MetaTest/__unnamed_task__/MaxReturn -214.085 MetaTest/__unnamed_task__/MinReturn -298.779 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 30.1332 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 778000 ------------------------------------------------- ----------- 2025-04-05 17:15:29 | [pearl_trainer] epoch #369 | Training... 2025-04-05 17:18:28 | [pearl_trainer] epoch #369 | Evaluating... 2025-04-05 17:18:28 | [pearl_trainer] epoch #369 | Sampling for adapation and meta-testing... 2025-04-05 17:23:18 | [pearl_trainer] epoch #369 | Finished meta-testing... 2025-04-05 17:23:18 | [pearl_trainer] epoch #369 | Saving snapshot... 2025-04-05 17:23:19 | [pearl_trainer] epoch #369 | Saved 2025-04-05 17:23:19 | [pearl_trainer] epoch #369 | Time 176062.61 s 2025-04-05 17:23:19 | [pearl_trainer] epoch #369 | EpochTime 519.98 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -232.298 MetaTest/Average/AverageReturn -232.298 MetaTest/Average/Iteration 369 MetaTest/Average/MaxReturn -123.267 MetaTest/Average/MinReturn -270.905 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 54.9257 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -232.298 MetaTest/__unnamed_task__/AverageReturn -232.298 MetaTest/__unnamed_task__/Iteration 369 MetaTest/__unnamed_task__/MaxReturn -123.267 MetaTest/__unnamed_task__/MinReturn -270.905 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 54.9257 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 780000 ------------------------------------------------- ----------- 2025-04-05 17:24:12 | [pearl_trainer] epoch #370 | Training... 2025-04-05 17:26:53 | [pearl_trainer] epoch #370 | Evaluating... 2025-04-05 17:26:53 | [pearl_trainer] epoch #370 | Sampling for adapation and meta-testing... 2025-04-05 17:31:40 | [pearl_trainer] epoch #370 | Finished meta-testing... 2025-04-05 17:31:40 | [pearl_trainer] epoch #370 | Saving snapshot... 2025-04-05 17:31:42 | [pearl_trainer] epoch #370 | Saved 2025-04-05 17:31:42 | [pearl_trainer] epoch #370 | Time 176565.33 s 2025-04-05 17:31:42 | [pearl_trainer] epoch #370 | EpochTime 502.72 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -235.725 MetaTest/Average/AverageReturn -235.725 MetaTest/Average/Iteration 370 MetaTest/Average/MaxReturn -173.349 MetaTest/Average/MinReturn -310.281 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 43.9219 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -235.725 MetaTest/__unnamed_task__/AverageReturn -235.725 MetaTest/__unnamed_task__/Iteration 370 MetaTest/__unnamed_task__/MaxReturn -173.349 MetaTest/__unnamed_task__/MinReturn -310.281 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 43.9219 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 782000 ------------------------------------------------- ----------- 2025-04-05 17:32:35 | [pearl_trainer] epoch #371 | Training... 2025-04-05 17:35:23 | [pearl_trainer] epoch #371 | Evaluating... 2025-04-05 17:35:23 | [pearl_trainer] epoch #371 | Sampling for adapation and meta-testing... 2025-04-05 17:40:15 | [pearl_trainer] epoch #371 | Finished meta-testing... 2025-04-05 17:40:15 | [pearl_trainer] epoch #371 | Saving snapshot... 2025-04-05 17:40:17 | [pearl_trainer] epoch #371 | Saved 2025-04-05 17:40:17 | [pearl_trainer] epoch #371 | Time 177080.40 s 2025-04-05 17:40:17 | [pearl_trainer] epoch #371 | EpochTime 515.07 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -271.775 MetaTest/Average/AverageReturn -271.775 MetaTest/Average/Iteration 371 MetaTest/Average/MaxReturn -244.712 MetaTest/Average/MinReturn -318.109 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 27.249 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -271.775 MetaTest/__unnamed_task__/AverageReturn -271.775 MetaTest/__unnamed_task__/Iteration 371 MetaTest/__unnamed_task__/MaxReturn -244.712 MetaTest/__unnamed_task__/MinReturn -318.109 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 27.249 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 784000 ------------------------------------------------- ---------- 2025-04-05 17:41:05 | [pearl_trainer] epoch #372 | Training... 2025-04-05 17:43:49 | [pearl_trainer] epoch #372 | Evaluating... 2025-04-05 17:43:49 | [pearl_trainer] epoch #372 | Sampling for adapation and meta-testing... 2025-04-05 17:48:44 | [pearl_trainer] epoch #372 | Finished meta-testing... 2025-04-05 17:48:44 | [pearl_trainer] epoch #372 | Saving snapshot... 2025-04-05 17:48:46 | [pearl_trainer] epoch #372 | Saved 2025-04-05 17:48:46 | [pearl_trainer] epoch #372 | Time 177589.53 s 2025-04-05 17:48:46 | [pearl_trainer] epoch #372 | EpochTime 509.12 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -254.285 MetaTest/Average/AverageReturn -254.285 MetaTest/Average/Iteration 372 MetaTest/Average/MaxReturn -189.537 MetaTest/Average/MinReturn -330.113 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 45.6164 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -254.285 MetaTest/__unnamed_task__/AverageReturn -254.285 MetaTest/__unnamed_task__/Iteration 372 MetaTest/__unnamed_task__/MaxReturn -189.537 MetaTest/__unnamed_task__/MinReturn -330.113 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 45.6164 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 786000 ------------------------------------------------- ----------- 2025-04-05 17:49:37 | [pearl_trainer] epoch #373 | Training... 2025-04-05 17:52:26 | [pearl_trainer] epoch #373 | Evaluating... 2025-04-05 17:52:26 | [pearl_trainer] epoch #373 | Sampling for adapation and meta-testing... 2025-04-05 17:57:10 | [pearl_trainer] epoch #373 | Finished meta-testing... 2025-04-05 17:57:10 | [pearl_trainer] epoch #373 | Saving snapshot... 2025-04-05 17:57:12 | [pearl_trainer] epoch #373 | Saved 2025-04-05 17:57:12 | [pearl_trainer] epoch #373 | Time 178095.39 s 2025-04-05 17:57:12 | [pearl_trainer] epoch #373 | EpochTime 505.87 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -252.936 MetaTest/Average/AverageReturn -252.936 MetaTest/Average/Iteration 373 MetaTest/Average/MaxReturn -207.293 MetaTest/Average/MinReturn -296.476 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 35.4831 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -252.936 MetaTest/__unnamed_task__/AverageReturn -252.936 MetaTest/__unnamed_task__/Iteration 373 MetaTest/__unnamed_task__/MaxReturn -207.293 MetaTest/__unnamed_task__/MinReturn -296.476 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 35.4831 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 788000 ------------------------------------------------- ----------- 2025-04-05 17:58:07 | [pearl_trainer] epoch #374 | Training... 2025-04-05 18:00:49 | [pearl_trainer] epoch #374 | Evaluating... 2025-04-05 18:00:49 | [pearl_trainer] epoch #374 | Sampling for adapation and meta-testing... 2025-04-05 18:05:35 | [pearl_trainer] epoch #374 | Finished meta-testing... 2025-04-05 18:05:35 | [pearl_trainer] epoch #374 | Saving snapshot... 2025-04-05 18:05:37 | [pearl_trainer] epoch #374 | Saved 2025-04-05 18:05:37 | [pearl_trainer] epoch #374 | Time 178600.74 s 2025-04-05 18:05:37 | [pearl_trainer] epoch #374 | EpochTime 505.34 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -270.608 MetaTest/Average/AverageReturn -270.608 MetaTest/Average/Iteration 374 MetaTest/Average/MaxReturn -218.325 MetaTest/Average/MinReturn -327.336 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 37.4412 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -270.608 MetaTest/__unnamed_task__/AverageReturn -270.608 MetaTest/__unnamed_task__/Iteration 374 MetaTest/__unnamed_task__/MaxReturn -218.325 MetaTest/__unnamed_task__/MinReturn -327.336 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 37.4412 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 790000 ------------------------------------------------- ----------- 2025-04-05 18:06:31 | [pearl_trainer] epoch #375 | Training... 2025-04-05 18:09:22 | [pearl_trainer] epoch #375 | Evaluating... 2025-04-05 18:09:22 | [pearl_trainer] epoch #375 | Sampling for adapation and meta-testing... 2025-04-05 18:14:01 | [pearl_trainer] epoch #375 | Finished meta-testing... 2025-04-05 18:14:01 | [pearl_trainer] epoch #375 | Saving snapshot... 2025-04-05 18:14:02 | [pearl_trainer] epoch #375 | Saved 2025-04-05 18:14:02 | [pearl_trainer] epoch #375 | Time 179106.12 s 2025-04-05 18:14:02 | [pearl_trainer] epoch #375 | EpochTime 505.38 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -222.537 MetaTest/Average/AverageReturn -222.537 MetaTest/Average/Iteration 375 MetaTest/Average/MaxReturn -127.431 MetaTest/Average/MinReturn -315.776 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 71.4167 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -222.537 MetaTest/__unnamed_task__/AverageReturn -222.537 MetaTest/__unnamed_task__/Iteration 375 MetaTest/__unnamed_task__/MaxReturn -127.431 MetaTest/__unnamed_task__/MinReturn -315.776 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 71.4167 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 792000 ------------------------------------------------- ----------- 2025-04-05 18:14:57 | [pearl_trainer] epoch #376 | Training... 2025-04-05 18:17:43 | [pearl_trainer] epoch #376 | Evaluating... 2025-04-05 18:17:43 | [pearl_trainer] epoch #376 | Sampling for adapation and meta-testing... 2025-04-05 18:22:23 | [pearl_trainer] epoch #376 | Finished meta-testing... 2025-04-05 18:22:23 | [pearl_trainer] epoch #376 | Saving snapshot... 2025-04-05 18:22:25 | [pearl_trainer] epoch #376 | Saved 2025-04-05 18:22:25 | [pearl_trainer] epoch #376 | Time 179608.57 s 2025-04-05 18:22:25 | [pearl_trainer] epoch #376 | EpochTime 502.45 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -264.39 MetaTest/Average/AverageReturn -264.39 MetaTest/Average/Iteration 376 MetaTest/Average/MaxReturn -229.618 MetaTest/Average/MinReturn -318.747 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 30.1243 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -264.39 MetaTest/__unnamed_task__/AverageReturn -264.39 MetaTest/__unnamed_task__/Iteration 376 MetaTest/__unnamed_task__/MaxReturn -229.618 MetaTest/__unnamed_task__/MinReturn -318.747 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 30.1243 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 794000 ------------------------------------------------- ----------- 2025-04-05 18:23:13 | [pearl_trainer] epoch #377 | Training... 2025-04-05 18:25:59 | [pearl_trainer] epoch #377 | Evaluating... 2025-04-05 18:25:59 | [pearl_trainer] epoch #377 | Sampling for adapation and meta-testing... 2025-04-05 18:30:33 | [pearl_trainer] epoch #377 | Finished meta-testing... 2025-04-05 18:30:33 | [pearl_trainer] epoch #377 | Saving snapshot... 2025-04-05 18:30:35 | [pearl_trainer] epoch #377 | Saved 2025-04-05 18:30:35 | [pearl_trainer] epoch #377 | Time 180098.31 s 2025-04-05 18:30:35 | [pearl_trainer] epoch #377 | EpochTime 489.74 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -212.282 MetaTest/Average/AverageReturn -212.282 MetaTest/Average/Iteration 377 MetaTest/Average/MaxReturn -116.195 MetaTest/Average/MinReturn -277.4 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 57.6065 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -212.282 MetaTest/__unnamed_task__/AverageReturn -212.282 MetaTest/__unnamed_task__/Iteration 377 MetaTest/__unnamed_task__/MaxReturn -116.195 MetaTest/__unnamed_task__/MinReturn -277.4 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 57.6065 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 796000 ------------------------------------------------- ----------- 2025-04-05 18:31:27 | [pearl_trainer] epoch #378 | Training... 2025-04-05 18:34:09 | [pearl_trainer] epoch #378 | Evaluating... 2025-04-05 18:34:09 | [pearl_trainer] epoch #378 | Sampling for adapation and meta-testing... 2025-04-05 18:38:46 | [pearl_trainer] epoch #378 | Finished meta-testing... 2025-04-05 18:38:46 | [pearl_trainer] epoch #378 | Saving snapshot... 2025-04-05 18:38:48 | [pearl_trainer] epoch #378 | Saved 2025-04-05 18:38:48 | [pearl_trainer] epoch #378 | Time 180591.32 s 2025-04-05 18:38:48 | [pearl_trainer] epoch #378 | EpochTime 493.01 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -255.079 MetaTest/Average/AverageReturn -255.079 MetaTest/Average/Iteration 378 MetaTest/Average/MaxReturn -219.41 MetaTest/Average/MinReturn -279.4 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 21.9824 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -255.079 MetaTest/__unnamed_task__/AverageReturn -255.079 MetaTest/__unnamed_task__/Iteration 378 MetaTest/__unnamed_task__/MaxReturn -219.41 MetaTest/__unnamed_task__/MinReturn -279.4 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 21.9824 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 798000 ------------------------------------------------- ----------- 2025-04-05 18:39:41 | [pearl_trainer] epoch #379 | Training... 2025-04-05 18:42:22 | [pearl_trainer] epoch #379 | Evaluating... 2025-04-05 18:42:22 | [pearl_trainer] epoch #379 | Sampling for adapation and meta-testing... 2025-04-05 18:46:50 | [pearl_trainer] epoch #379 | Finished meta-testing... 2025-04-05 18:46:50 | [pearl_trainer] epoch #379 | Saving snapshot... 2025-04-05 18:46:51 | [pearl_trainer] epoch #379 | Saved 2025-04-05 18:46:51 | [pearl_trainer] epoch #379 | Time 181075.10 s 2025-04-05 18:46:51 | [pearl_trainer] epoch #379 | EpochTime 483.77 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -197.184 MetaTest/Average/AverageReturn -197.184 MetaTest/Average/Iteration 379 MetaTest/Average/MaxReturn -151.706 MetaTest/Average/MinReturn -228.71 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 28.9752 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -197.184 MetaTest/__unnamed_task__/AverageReturn -197.184 MetaTest/__unnamed_task__/Iteration 379 MetaTest/__unnamed_task__/MaxReturn -151.706 MetaTest/__unnamed_task__/MinReturn -228.71 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 28.9752 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 800000 ------------------------------------------------- ----------- 2025-04-05 18:47:43 | [pearl_trainer] epoch #380 | Training... 2025-04-05 18:50:26 | [pearl_trainer] epoch #380 | Evaluating... 2025-04-05 18:50:26 | [pearl_trainer] epoch #380 | Sampling for adapation and meta-testing... 2025-04-05 18:54:55 | [pearl_trainer] epoch #380 | Finished meta-testing... 2025-04-05 18:54:55 | [pearl_trainer] epoch #380 | Saving snapshot... 2025-04-05 18:54:57 | [pearl_trainer] epoch #380 | Saved 2025-04-05 18:54:57 | [pearl_trainer] epoch #380 | Time 181560.24 s 2025-04-05 18:54:57 | [pearl_trainer] epoch #380 | EpochTime 485.15 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -224.378 MetaTest/Average/AverageReturn -224.378 MetaTest/Average/Iteration 380 MetaTest/Average/MaxReturn -154.229 MetaTest/Average/MinReturn -289.12 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 47.8715 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -224.378 MetaTest/__unnamed_task__/AverageReturn -224.378 MetaTest/__unnamed_task__/Iteration 380 MetaTest/__unnamed_task__/MaxReturn -154.229 MetaTest/__unnamed_task__/MinReturn -289.12 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 47.8715 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 802000 ------------------------------------------------- ----------- 2025-04-05 18:55:42 | [pearl_trainer] epoch #381 | Training... 2025-04-05 18:58:30 | [pearl_trainer] epoch #381 | Evaluating... 2025-04-05 18:58:30 | [pearl_trainer] epoch #381 | Sampling for adapation and meta-testing... 2025-04-05 19:03:01 | [pearl_trainer] epoch #381 | Finished meta-testing... 2025-04-05 19:03:01 | [pearl_trainer] epoch #381 | Saving snapshot... 2025-04-05 19:03:03 | [pearl_trainer] epoch #381 | Saved 2025-04-05 19:03:03 | [pearl_trainer] epoch #381 | Time 182046.34 s 2025-04-05 19:03:03 | [pearl_trainer] epoch #381 | EpochTime 486.10 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -246.03 MetaTest/Average/AverageReturn -246.03 MetaTest/Average/Iteration 381 MetaTest/Average/MaxReturn -140.636 MetaTest/Average/MinReturn -310.733 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 59.6956 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -246.03 MetaTest/__unnamed_task__/AverageReturn -246.03 MetaTest/__unnamed_task__/Iteration 381 MetaTest/__unnamed_task__/MaxReturn -140.636 MetaTest/__unnamed_task__/MinReturn -310.733 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 59.6956 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 804000 ------------------------------------------------- ----------- 2025-04-05 19:03:53 | [pearl_trainer] epoch #382 | Training... 2025-04-05 19:06:33 | [pearl_trainer] epoch #382 | Evaluating... 2025-04-05 19:06:33 | [pearl_trainer] epoch #382 | Sampling for adapation and meta-testing... 2025-04-05 19:11:13 | [pearl_trainer] epoch #382 | Finished meta-testing... 2025-04-05 19:11:13 | [pearl_trainer] epoch #382 | Saving snapshot... 2025-04-05 19:11:15 | [pearl_trainer] epoch #382 | Saved 2025-04-05 19:11:15 | [pearl_trainer] epoch #382 | Time 182538.52 s 2025-04-05 19:11:15 | [pearl_trainer] epoch #382 | EpochTime 492.18 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -240.733 MetaTest/Average/AverageReturn -240.733 MetaTest/Average/Iteration 382 MetaTest/Average/MaxReturn -204.819 MetaTest/Average/MinReturn -295.121 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.0295 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -240.733 MetaTest/__unnamed_task__/AverageReturn -240.733 MetaTest/__unnamed_task__/Iteration 382 MetaTest/__unnamed_task__/MaxReturn -204.819 MetaTest/__unnamed_task__/MinReturn -295.121 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.0295 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 806000 ------------------------------------------------- ----------- 2025-04-05 19:12:05 | [pearl_trainer] epoch #383 | Training... 2025-04-05 19:14:52 | [pearl_trainer] epoch #383 | Evaluating... 2025-04-05 19:14:52 | [pearl_trainer] epoch #383 | Sampling for adapation and meta-testing... 2025-04-05 19:19:31 | [pearl_trainer] epoch #383 | Finished meta-testing... 2025-04-05 19:19:31 | [pearl_trainer] epoch #383 | Saving snapshot... 2025-04-05 19:19:32 | [pearl_trainer] epoch #383 | Saved 2025-04-05 19:19:32 | [pearl_trainer] epoch #383 | Time 183036.06 s 2025-04-05 19:19:32 | [pearl_trainer] epoch #383 | EpochTime 497.54 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -241.418 MetaTest/Average/AverageReturn -241.418 MetaTest/Average/Iteration 383 MetaTest/Average/MaxReturn -187.055 MetaTest/Average/MinReturn -284.237 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 34.6209 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -241.418 MetaTest/__unnamed_task__/AverageReturn -241.418 MetaTest/__unnamed_task__/Iteration 383 MetaTest/__unnamed_task__/MaxReturn -187.055 MetaTest/__unnamed_task__/MinReturn -284.237 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 34.6209 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 808000 ------------------------------------------------- ----------- 2025-04-05 19:20:25 | [pearl_trainer] epoch #384 | Training... 2025-04-05 19:23:19 | [pearl_trainer] epoch #384 | Evaluating... 2025-04-05 19:23:19 | [pearl_trainer] epoch #384 | Sampling for adapation and meta-testing... 2025-04-05 19:27:54 | [pearl_trainer] epoch #384 | Finished meta-testing... 2025-04-05 19:27:54 | [pearl_trainer] epoch #384 | Saving snapshot... 2025-04-05 19:27:55 | [pearl_trainer] epoch #384 | Saved 2025-04-05 19:27:55 | [pearl_trainer] epoch #384 | Time 183538.99 s 2025-04-05 19:27:55 | [pearl_trainer] epoch #384 | EpochTime 502.93 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -199.936 MetaTest/Average/AverageReturn -199.936 MetaTest/Average/Iteration 384 MetaTest/Average/MaxReturn -104.5 MetaTest/Average/MinReturn -282.139 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 72.5695 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -199.936 MetaTest/__unnamed_task__/AverageReturn -199.936 MetaTest/__unnamed_task__/Iteration 384 MetaTest/__unnamed_task__/MaxReturn -104.5 MetaTest/__unnamed_task__/MinReturn -282.139 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 72.5695 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 810000 ------------------------------------------------- ----------- 2025-04-05 19:28:47 | [pearl_trainer] epoch #385 | Training... 2025-04-05 19:31:42 | [pearl_trainer] epoch #385 | Evaluating... 2025-04-05 19:31:42 | [pearl_trainer] epoch #385 | Sampling for adapation and meta-testing... 2025-04-05 19:36:23 | [pearl_trainer] epoch #385 | Finished meta-testing... 2025-04-05 19:36:23 | [pearl_trainer] epoch #385 | Saving snapshot... 2025-04-05 19:36:25 | [pearl_trainer] epoch #385 | Saved 2025-04-05 19:36:25 | [pearl_trainer] epoch #385 | Time 184048.20 s 2025-04-05 19:36:25 | [pearl_trainer] epoch #385 | EpochTime 509.20 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -231.691 MetaTest/Average/AverageReturn -231.691 MetaTest/Average/Iteration 385 MetaTest/Average/MaxReturn -77.4745 MetaTest/Average/MinReturn -328.467 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 86.2621 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -231.691 MetaTest/__unnamed_task__/AverageReturn -231.691 MetaTest/__unnamed_task__/Iteration 385 MetaTest/__unnamed_task__/MaxReturn -77.4745 MetaTest/__unnamed_task__/MinReturn -328.467 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 86.2621 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 812000 ------------------------------------------------- ----------- 2025-04-05 19:37:11 | [pearl_trainer] epoch #386 | Training... 2025-04-05 19:40:01 | [pearl_trainer] epoch #386 | Evaluating... 2025-04-05 19:40:01 | [pearl_trainer] epoch #386 | Sampling for adapation and meta-testing... 2025-04-05 19:44:46 | [pearl_trainer] epoch #386 | Finished meta-testing... 2025-04-05 19:44:46 | [pearl_trainer] epoch #386 | Saving snapshot... 2025-04-05 19:44:47 | [pearl_trainer] epoch #386 | Saved 2025-04-05 19:44:47 | [pearl_trainer] epoch #386 | Time 184551.13 s 2025-04-05 19:44:47 | [pearl_trainer] epoch #386 | EpochTime 502.93 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -237.333 MetaTest/Average/AverageReturn -237.333 MetaTest/Average/Iteration 386 MetaTest/Average/MaxReturn -193.94 MetaTest/Average/MinReturn -271.769 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 30.3896 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -237.333 MetaTest/__unnamed_task__/AverageReturn -237.333 MetaTest/__unnamed_task__/Iteration 386 MetaTest/__unnamed_task__/MaxReturn -193.94 MetaTest/__unnamed_task__/MinReturn -271.769 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 30.3896 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 814000 ------------------------------------------------- ----------- 2025-04-05 19:45:39 | [pearl_trainer] epoch #387 | Training... 2025-04-05 19:48:31 | [pearl_trainer] epoch #387 | Evaluating... 2025-04-05 19:48:31 | [pearl_trainer] epoch #387 | Sampling for adapation and meta-testing... 2025-04-05 19:53:16 | [pearl_trainer] epoch #387 | Finished meta-testing... 2025-04-05 19:53:16 | [pearl_trainer] epoch #387 | Saving snapshot... 2025-04-05 19:53:18 | [pearl_trainer] epoch #387 | Saved 2025-04-05 19:53:18 | [pearl_trainer] epoch #387 | Time 185061.76 s 2025-04-05 19:53:18 | [pearl_trainer] epoch #387 | EpochTime 510.63 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -295.978 MetaTest/Average/AverageReturn -295.978 MetaTest/Average/Iteration 387 MetaTest/Average/MaxReturn -229.117 MetaTest/Average/MinReturn -365.882 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 55.8574 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -295.978 MetaTest/__unnamed_task__/AverageReturn -295.978 MetaTest/__unnamed_task__/Iteration 387 MetaTest/__unnamed_task__/MaxReturn -229.117 MetaTest/__unnamed_task__/MinReturn -365.882 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 55.8574 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 816000 ------------------------------------------------- ----------- 2025-04-05 19:54:10 | [pearl_trainer] epoch #388 | Training... 2025-04-05 19:57:05 | [pearl_trainer] epoch #388 | Evaluating... 2025-04-05 19:57:05 | [pearl_trainer] epoch #388 | Sampling for adapation and meta-testing... 2025-04-05 20:01:46 | [pearl_trainer] epoch #388 | Finished meta-testing... 2025-04-05 20:01:46 | [pearl_trainer] epoch #388 | Saving snapshot... 2025-04-05 20:01:47 | [pearl_trainer] epoch #388 | Saved 2025-04-05 20:01:47 | [pearl_trainer] epoch #388 | Time 185570.98 s 2025-04-05 20:01:47 | [pearl_trainer] epoch #388 | EpochTime 509.23 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -275.648 MetaTest/Average/AverageReturn -275.648 MetaTest/Average/Iteration 388 MetaTest/Average/MaxReturn -216.052 MetaTest/Average/MinReturn -311.271 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 32.0082 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -275.648 MetaTest/__unnamed_task__/AverageReturn -275.648 MetaTest/__unnamed_task__/Iteration 388 MetaTest/__unnamed_task__/MaxReturn -216.052 MetaTest/__unnamed_task__/MinReturn -311.271 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 32.0082 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 818000 ------------------------------------------------- ----------- 2025-04-05 20:02:39 | [pearl_trainer] epoch #389 | Training... 2025-04-05 20:05:22 | [pearl_trainer] epoch #389 | Evaluating... 2025-04-05 20:05:22 | [pearl_trainer] epoch #389 | Sampling for adapation and meta-testing... 2025-04-05 20:10:06 | [pearl_trainer] epoch #389 | Finished meta-testing... 2025-04-05 20:10:06 | [pearl_trainer] epoch #389 | Saving snapshot... 2025-04-05 20:10:08 | [pearl_trainer] epoch #389 | Saved 2025-04-05 20:10:08 | [pearl_trainer] epoch #389 | Time 186071.51 s 2025-04-05 20:10:08 | [pearl_trainer] epoch #389 | EpochTime 500.52 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -242.78 MetaTest/Average/AverageReturn -242.78 MetaTest/Average/Iteration 389 MetaTest/Average/MaxReturn -211.074 MetaTest/Average/MinReturn -290.042 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 28.768 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -242.78 MetaTest/__unnamed_task__/AverageReturn -242.78 MetaTest/__unnamed_task__/Iteration 389 MetaTest/__unnamed_task__/MaxReturn -211.074 MetaTest/__unnamed_task__/MinReturn -290.042 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 28.768 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 820000 ------------------------------------------------- ---------- 2025-04-05 20:10:58 | [pearl_trainer] epoch #390 | Training... 2025-04-05 20:13:41 | [pearl_trainer] epoch #390 | Evaluating... 2025-04-05 20:13:41 | [pearl_trainer] epoch #390 | Sampling for adapation and meta-testing... 2025-04-05 20:18:15 | [pearl_trainer] epoch #390 | Finished meta-testing... 2025-04-05 20:18:15 | [pearl_trainer] epoch #390 | Saving snapshot... 2025-04-05 20:18:17 | [pearl_trainer] epoch #390 | Saved 2025-04-05 20:18:17 | [pearl_trainer] epoch #390 | Time 186560.25 s 2025-04-05 20:18:17 | [pearl_trainer] epoch #390 | EpochTime 488.74 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -275.442 MetaTest/Average/AverageReturn -275.442 MetaTest/Average/Iteration 390 MetaTest/Average/MaxReturn -229.424 MetaTest/Average/MinReturn -328.913 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 40.9882 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -275.442 MetaTest/__unnamed_task__/AverageReturn -275.442 MetaTest/__unnamed_task__/Iteration 390 MetaTest/__unnamed_task__/MaxReturn -229.424 MetaTest/__unnamed_task__/MinReturn -328.913 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 40.9882 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 822000 ------------------------------------------------- ----------- 2025-04-05 20:19:10 | [pearl_trainer] epoch #391 | Training... 2025-04-05 20:21:55 | [pearl_trainer] epoch #391 | Evaluating... 2025-04-05 20:21:55 | [pearl_trainer] epoch #391 | Sampling for adapation and meta-testing... 2025-04-05 20:26:24 | [pearl_trainer] epoch #391 | Finished meta-testing... 2025-04-05 20:26:24 | [pearl_trainer] epoch #391 | Saving snapshot... 2025-04-05 20:26:26 | [pearl_trainer] epoch #391 | Saved 2025-04-05 20:26:26 | [pearl_trainer] epoch #391 | Time 187049.83 s 2025-04-05 20:26:26 | [pearl_trainer] epoch #391 | EpochTime 489.58 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -264.221 MetaTest/Average/AverageReturn -264.221 MetaTest/Average/Iteration 391 MetaTest/Average/MaxReturn -226.496 MetaTest/Average/MinReturn -293.854 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.1645 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -264.221 MetaTest/__unnamed_task__/AverageReturn -264.221 MetaTest/__unnamed_task__/Iteration 391 MetaTest/__unnamed_task__/MaxReturn -226.496 MetaTest/__unnamed_task__/MinReturn -293.854 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.1645 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 824000 ------------------------------------------------- ----------- 2025-04-05 20:27:18 | [pearl_trainer] epoch #392 | Training... 2025-04-05 20:30:01 | [pearl_trainer] epoch #392 | Evaluating... 2025-04-05 20:30:01 | [pearl_trainer] epoch #392 | Sampling for adapation and meta-testing... 2025-04-05 20:34:53 | [pearl_trainer] epoch #392 | Finished meta-testing... 2025-04-05 20:34:53 | [pearl_trainer] epoch #392 | Saving snapshot... 2025-04-05 20:34:54 | [pearl_trainer] epoch #392 | Saved 2025-04-05 20:34:54 | [pearl_trainer] epoch #392 | Time 187557.52 s 2025-04-05 20:34:54 | [pearl_trainer] epoch #392 | EpochTime 507.69 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -261.988 MetaTest/Average/AverageReturn -261.988 MetaTest/Average/Iteration 392 MetaTest/Average/MaxReturn -131.87 MetaTest/Average/MinReturn -308.706 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 66.7445 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -261.988 MetaTest/__unnamed_task__/AverageReturn -261.988 MetaTest/__unnamed_task__/Iteration 392 MetaTest/__unnamed_task__/MaxReturn -131.87 MetaTest/__unnamed_task__/MinReturn -308.706 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 66.7445 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 826000 ------------------------------------------------- ----------- 2025-04-05 20:35:45 | [pearl_trainer] epoch #393 | Training... 2025-04-05 20:38:32 | [pearl_trainer] epoch #393 | Evaluating... 2025-04-05 20:38:32 | [pearl_trainer] epoch #393 | Sampling for adapation and meta-testing... 2025-04-05 20:43:17 | [pearl_trainer] epoch #393 | Finished meta-testing... 2025-04-05 20:43:17 | [pearl_trainer] epoch #393 | Saving snapshot... 2025-04-05 20:43:19 | [pearl_trainer] epoch #393 | Saved 2025-04-05 20:43:19 | [pearl_trainer] epoch #393 | Time 188062.68 s 2025-04-05 20:43:19 | [pearl_trainer] epoch #393 | EpochTime 505.16 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -307.579 MetaTest/Average/AverageReturn -307.579 MetaTest/Average/Iteration 393 MetaTest/Average/MaxReturn -227.998 MetaTest/Average/MinReturn -361.287 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 48.1291 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -307.579 MetaTest/__unnamed_task__/AverageReturn -307.579 MetaTest/__unnamed_task__/Iteration 393 MetaTest/__unnamed_task__/MaxReturn -227.998 MetaTest/__unnamed_task__/MinReturn -361.287 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 48.1291 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 828000 ------------------------------------------------- ----------- 2025-04-05 20:44:06 | [pearl_trainer] epoch #394 | Training... 2025-04-05 20:46:49 | [pearl_trainer] epoch #394 | Evaluating... 2025-04-05 20:46:49 | [pearl_trainer] epoch #394 | Sampling for adapation and meta-testing... 2025-04-05 20:51:31 | [pearl_trainer] epoch #394 | Finished meta-testing... 2025-04-05 20:51:31 | [pearl_trainer] epoch #394 | Saving snapshot... 2025-04-05 20:51:32 | [pearl_trainer] epoch #394 | Saved 2025-04-05 20:51:32 | [pearl_trainer] epoch #394 | Time 188555.87 s 2025-04-05 20:51:32 | [pearl_trainer] epoch #394 | EpochTime 493.19 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -263.812 MetaTest/Average/AverageReturn -263.812 MetaTest/Average/Iteration 394 MetaTest/Average/MaxReturn -232.453 MetaTest/Average/MinReturn -310.769 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 33.4458 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -263.812 MetaTest/__unnamed_task__/AverageReturn -263.812 MetaTest/__unnamed_task__/Iteration 394 MetaTest/__unnamed_task__/MaxReturn -232.453 MetaTest/__unnamed_task__/MinReturn -310.769 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 33.4458 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 830000 ------------------------------------------------- ----------- 2025-04-05 20:52:20 | [pearl_trainer] epoch #395 | Training... 2025-04-05 20:55:01 | [pearl_trainer] epoch #395 | Evaluating... 2025-04-05 20:55:01 | [pearl_trainer] epoch #395 | Sampling for adapation and meta-testing... 2025-04-05 20:59:23 | [pearl_trainer] epoch #395 | Finished meta-testing... 2025-04-05 20:59:23 | [pearl_trainer] epoch #395 | Saving snapshot... 2025-04-05 20:59:25 | [pearl_trainer] epoch #395 | Saved 2025-04-05 20:59:25 | [pearl_trainer] epoch #395 | Time 189028.28 s 2025-04-05 20:59:25 | [pearl_trainer] epoch #395 | EpochTime 472.41 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -251.265 MetaTest/Average/AverageReturn -251.265 MetaTest/Average/Iteration 395 MetaTest/Average/MaxReturn -210.321 MetaTest/Average/MinReturn -295.871 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 32.644 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -251.265 MetaTest/__unnamed_task__/AverageReturn -251.265 MetaTest/__unnamed_task__/Iteration 395 MetaTest/__unnamed_task__/MaxReturn -210.321 MetaTest/__unnamed_task__/MinReturn -295.871 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 32.644 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 832000 ------------------------------------------------- ---------- 2025-04-05 21:00:18 | [pearl_trainer] epoch #396 | Training... 2025-04-05 21:03:12 | [pearl_trainer] epoch #396 | Evaluating... 2025-04-05 21:03:12 | [pearl_trainer] epoch #396 | Sampling for adapation and meta-testing... 2025-04-05 21:07:30 | [pearl_trainer] epoch #396 | Finished meta-testing... 2025-04-05 21:07:30 | [pearl_trainer] epoch #396 | Saving snapshot... 2025-04-05 21:07:31 | [pearl_trainer] epoch #396 | Saved 2025-04-05 21:07:31 | [pearl_trainer] epoch #396 | Time 189515.00 s 2025-04-05 21:07:31 | [pearl_trainer] epoch #396 | EpochTime 486.72 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -279.023 MetaTest/Average/AverageReturn -279.023 MetaTest/Average/Iteration 396 MetaTest/Average/MaxReturn -228.978 MetaTest/Average/MinReturn -315.852 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 34.0838 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -279.023 MetaTest/__unnamed_task__/AverageReturn -279.023 MetaTest/__unnamed_task__/Iteration 396 MetaTest/__unnamed_task__/MaxReturn -228.978 MetaTest/__unnamed_task__/MinReturn -315.852 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 34.0838 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 834000 ------------------------------------------------- ----------- 2025-04-05 21:08:19 | [pearl_trainer] epoch #397 | Training... 2025-04-05 21:11:18 | [pearl_trainer] epoch #397 | Evaluating... 2025-04-05 21:11:18 | [pearl_trainer] epoch #397 | Sampling for adapation and meta-testing... 2025-04-05 21:15:59 | [pearl_trainer] epoch #397 | Finished meta-testing... 2025-04-05 21:15:59 | [pearl_trainer] epoch #397 | Saving snapshot... 2025-04-05 21:16:00 | [pearl_trainer] epoch #397 | Saved 2025-04-05 21:16:00 | [pearl_trainer] epoch #397 | Time 190024.08 s 2025-04-05 21:16:00 | [pearl_trainer] epoch #397 | EpochTime 509.09 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -235.936 MetaTest/Average/AverageReturn -235.936 MetaTest/Average/Iteration 397 MetaTest/Average/MaxReturn -143.676 MetaTest/Average/MinReturn -310.025 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 57.9478 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -235.936 MetaTest/__unnamed_task__/AverageReturn -235.936 MetaTest/__unnamed_task__/Iteration 397 MetaTest/__unnamed_task__/MaxReturn -143.676 MetaTest/__unnamed_task__/MinReturn -310.025 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 57.9478 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 836000 ------------------------------------------------- ----------- 2025-04-05 21:16:55 | [pearl_trainer] epoch #398 | Training... 2025-04-05 21:19:59 | [pearl_trainer] epoch #398 | Evaluating... 2025-04-05 21:19:59 | [pearl_trainer] epoch #398 | Sampling for adapation and meta-testing... 2025-04-05 21:24:46 | [pearl_trainer] epoch #398 | Finished meta-testing... 2025-04-05 21:24:46 | [pearl_trainer] epoch #398 | Saving snapshot... 2025-04-05 21:24:47 | [pearl_trainer] epoch #398 | Saved 2025-04-05 21:24:47 | [pearl_trainer] epoch #398 | Time 190550.47 s 2025-04-05 21:24:47 | [pearl_trainer] epoch #398 | EpochTime 526.38 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -226.507 MetaTest/Average/AverageReturn -226.507 MetaTest/Average/Iteration 398 MetaTest/Average/MaxReturn -167.47 MetaTest/Average/MinReturn -257.259 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 32.5966 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -226.507 MetaTest/__unnamed_task__/AverageReturn -226.507 MetaTest/__unnamed_task__/Iteration 398 MetaTest/__unnamed_task__/MaxReturn -167.47 MetaTest/__unnamed_task__/MinReturn -257.259 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 32.5966 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 838000 ------------------------------------------------- ----------- 2025-04-05 21:25:39 | [pearl_trainer] epoch #399 | Training... 2025-04-05 21:28:33 | [pearl_trainer] epoch #399 | Evaluating... 2025-04-05 21:28:33 | [pearl_trainer] epoch #399 | Sampling for adapation and meta-testing... 2025-04-05 21:33:11 | [pearl_trainer] epoch #399 | Finished meta-testing... 2025-04-05 21:33:11 | [pearl_trainer] epoch #399 | Saving snapshot... 2025-04-05 21:33:13 | [pearl_trainer] epoch #399 | Saved 2025-04-05 21:33:13 | [pearl_trainer] epoch #399 | Time 191056.33 s 2025-04-05 21:33:13 | [pearl_trainer] epoch #399 | EpochTime 505.85 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -222.736 MetaTest/Average/AverageReturn -222.736 MetaTest/Average/Iteration 399 MetaTest/Average/MaxReturn -189.093 MetaTest/Average/MinReturn -256.947 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 25.1382 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -222.736 MetaTest/__unnamed_task__/AverageReturn -222.736 MetaTest/__unnamed_task__/Iteration 399 MetaTest/__unnamed_task__/MaxReturn -189.093 MetaTest/__unnamed_task__/MinReturn -256.947 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 25.1382 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 840000 ------------------------------------------------- ----------- 2025-04-05 21:34:08 | [pearl_trainer] epoch #400 | Training... 2025-04-05 21:37:13 | [pearl_trainer] epoch #400 | Evaluating... 2025-04-05 21:37:13 | [pearl_trainer] epoch #400 | Sampling for adapation and meta-testing... 2025-04-05 21:42:04 | [pearl_trainer] epoch #400 | Finished meta-testing... 2025-04-05 21:42:04 | [pearl_trainer] epoch #400 | Saving snapshot... 2025-04-05 21:42:06 | [pearl_trainer] epoch #400 | Saved 2025-04-05 21:42:06 | [pearl_trainer] epoch #400 | Time 191589.20 s 2025-04-05 21:42:06 | [pearl_trainer] epoch #400 | EpochTime 532.88 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -290.71 MetaTest/Average/AverageReturn -290.71 MetaTest/Average/Iteration 400 MetaTest/Average/MaxReturn -262.373 MetaTest/Average/MinReturn -315.763 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 22.4919 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -290.71 MetaTest/__unnamed_task__/AverageReturn -290.71 MetaTest/__unnamed_task__/Iteration 400 MetaTest/__unnamed_task__/MaxReturn -262.373 MetaTest/__unnamed_task__/MinReturn -315.763 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 22.4919 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 842000 ------------------------------------------------- ----------- 2025-04-05 21:42:56 | [pearl_trainer] epoch #401 | Training... 2025-04-05 21:45:45 | [pearl_trainer] epoch #401 | Evaluating... 2025-04-05 21:45:45 | [pearl_trainer] epoch #401 | Sampling for adapation and meta-testing... 2025-04-05 21:50:36 | [pearl_trainer] epoch #401 | Finished meta-testing... 2025-04-05 21:50:36 | [pearl_trainer] epoch #401 | Saving snapshot... 2025-04-05 21:50:38 | [pearl_trainer] epoch #401 | Saved 2025-04-05 21:50:38 | [pearl_trainer] epoch #401 | Time 192101.44 s 2025-04-05 21:50:38 | [pearl_trainer] epoch #401 | EpochTime 512.23 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -282.696 MetaTest/Average/AverageReturn -282.696 MetaTest/Average/Iteration 401 MetaTest/Average/MaxReturn -247.804 MetaTest/Average/MinReturn -341.199 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 32.1921 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -282.696 MetaTest/__unnamed_task__/AverageReturn -282.696 MetaTest/__unnamed_task__/Iteration 401 MetaTest/__unnamed_task__/MaxReturn -247.804 MetaTest/__unnamed_task__/MinReturn -341.199 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 32.1921 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 844000 ------------------------------------------------- ----------- 2025-04-05 21:51:30 | [pearl_trainer] epoch #402 | Training... 2025-04-05 21:54:18 | [pearl_trainer] epoch #402 | Evaluating... 2025-04-05 21:54:18 | [pearl_trainer] epoch #402 | Sampling for adapation and meta-testing... 2025-04-05 21:58:52 | [pearl_trainer] epoch #402 | Finished meta-testing... 2025-04-05 21:58:52 | [pearl_trainer] epoch #402 | Saving snapshot... 2025-04-05 21:58:53 | [pearl_trainer] epoch #402 | Saved 2025-04-05 21:58:53 | [pearl_trainer] epoch #402 | Time 192597.02 s 2025-04-05 21:58:53 | [pearl_trainer] epoch #402 | EpochTime 495.59 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -245.474 MetaTest/Average/AverageReturn -245.474 MetaTest/Average/Iteration 402 MetaTest/Average/MaxReturn -175.564 MetaTest/Average/MinReturn -341.76 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 54.3506 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -245.474 MetaTest/__unnamed_task__/AverageReturn -245.474 MetaTest/__unnamed_task__/Iteration 402 MetaTest/__unnamed_task__/MaxReturn -175.564 MetaTest/__unnamed_task__/MinReturn -341.76 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 54.3506 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 846000 ------------------------------------------------- ----------- 2025-04-05 21:59:45 | [pearl_trainer] epoch #403 | Training... 2025-04-05 22:02:27 | [pearl_trainer] epoch #403 | Evaluating... 2025-04-05 22:02:27 | [pearl_trainer] epoch #403 | Sampling for adapation and meta-testing... 2025-04-05 22:07:13 | [pearl_trainer] epoch #403 | Finished meta-testing... 2025-04-05 22:07:13 | [pearl_trainer] epoch #403 | Saving snapshot... 2025-04-05 22:07:14 | [pearl_trainer] epoch #403 | Saved 2025-04-05 22:07:14 | [pearl_trainer] epoch #403 | Time 193097.96 s 2025-04-05 22:07:14 | [pearl_trainer] epoch #403 | EpochTime 500.94 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -241.648 MetaTest/Average/AverageReturn -241.648 MetaTest/Average/Iteration 403 MetaTest/Average/MaxReturn -119.281 MetaTest/Average/MinReturn -309.563 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 65.3779 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -241.648 MetaTest/__unnamed_task__/AverageReturn -241.648 MetaTest/__unnamed_task__/Iteration 403 MetaTest/__unnamed_task__/MaxReturn -119.281 MetaTest/__unnamed_task__/MinReturn -309.563 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 65.3779 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 848000 ------------------------------------------------- ----------- 2025-04-05 22:08:10 | [pearl_trainer] epoch #404 | Training... 2025-04-05 22:11:08 | [pearl_trainer] epoch #404 | Evaluating... 2025-04-05 22:11:08 | [pearl_trainer] epoch #404 | Sampling for adapation and meta-testing... 2025-04-05 22:15:56 | [pearl_trainer] epoch #404 | Finished meta-testing... 2025-04-05 22:15:56 | [pearl_trainer] epoch #404 | Saving snapshot... 2025-04-05 22:15:57 | [pearl_trainer] epoch #404 | Saved 2025-04-05 22:15:57 | [pearl_trainer] epoch #404 | Time 193621.19 s 2025-04-05 22:15:57 | [pearl_trainer] epoch #404 | EpochTime 523.23 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -257.499 MetaTest/Average/AverageReturn -257.499 MetaTest/Average/Iteration 404 MetaTest/Average/MaxReturn -135.214 MetaTest/Average/MinReturn -335.464 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 70.425 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -257.499 MetaTest/__unnamed_task__/AverageReturn -257.499 MetaTest/__unnamed_task__/Iteration 404 MetaTest/__unnamed_task__/MaxReturn -135.214 MetaTest/__unnamed_task__/MinReturn -335.464 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 70.425 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 850000 ------------------------------------------------- ---------- 2025-04-05 22:16:50 | [pearl_trainer] epoch #405 | Training... 2025-04-05 22:19:32 | [pearl_trainer] epoch #405 | Evaluating... 2025-04-05 22:19:32 | [pearl_trainer] epoch #405 | Sampling for adapation and meta-testing... 2025-04-05 22:24:18 | [pearl_trainer] epoch #405 | Finished meta-testing... 2025-04-05 22:24:18 | [pearl_trainer] epoch #405 | Saving snapshot... 2025-04-05 22:24:20 | [pearl_trainer] epoch #405 | Saved 2025-04-05 22:24:20 | [pearl_trainer] epoch #405 | Time 194123.54 s 2025-04-05 22:24:20 | [pearl_trainer] epoch #405 | EpochTime 502.34 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -193.353 MetaTest/Average/AverageReturn -193.353 MetaTest/Average/Iteration 405 MetaTest/Average/MaxReturn -109.349 MetaTest/Average/MinReturn -292.183 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 71.4716 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -193.353 MetaTest/__unnamed_task__/AverageReturn -193.353 MetaTest/__unnamed_task__/Iteration 405 MetaTest/__unnamed_task__/MaxReturn -109.349 MetaTest/__unnamed_task__/MinReturn -292.183 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 71.4716 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 852000 ------------------------------------------------- ----------- 2025-04-05 22:25:11 | [pearl_trainer] epoch #406 | Training... 2025-04-05 22:27:56 | [pearl_trainer] epoch #406 | Evaluating... 2025-04-05 22:27:56 | [pearl_trainer] epoch #406 | Sampling for adapation and meta-testing... 2025-04-05 22:32:42 | [pearl_trainer] epoch #406 | Finished meta-testing... 2025-04-05 22:32:42 | [pearl_trainer] epoch #406 | Saving snapshot... 2025-04-05 22:32:43 | [pearl_trainer] epoch #406 | Saved 2025-04-05 22:32:43 | [pearl_trainer] epoch #406 | Time 194626.89 s 2025-04-05 22:32:43 | [pearl_trainer] epoch #406 | EpochTime 503.35 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -233.72 MetaTest/Average/AverageReturn -233.72 MetaTest/Average/Iteration 406 MetaTest/Average/MaxReturn -173.142 MetaTest/Average/MinReturn -304.415 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 45.6882 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -233.72 MetaTest/__unnamed_task__/AverageReturn -233.72 MetaTest/__unnamed_task__/Iteration 406 MetaTest/__unnamed_task__/MaxReturn -173.142 MetaTest/__unnamed_task__/MinReturn -304.415 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 45.6882 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 854000 ------------------------------------------------- ----------- 2025-04-05 22:33:31 | [pearl_trainer] epoch #407 | Training... 2025-04-05 22:36:16 | [pearl_trainer] epoch #407 | Evaluating... 2025-04-05 22:36:16 | [pearl_trainer] epoch #407 | Sampling for adapation and meta-testing... 2025-04-05 22:41:11 | [pearl_trainer] epoch #407 | Finished meta-testing... 2025-04-05 22:41:11 | [pearl_trainer] epoch #407 | Saving snapshot... 2025-04-05 22:41:12 | [pearl_trainer] epoch #407 | Saved 2025-04-05 22:41:12 | [pearl_trainer] epoch #407 | Time 195135.91 s 2025-04-05 22:41:12 | [pearl_trainer] epoch #407 | EpochTime 509.02 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -233.66 MetaTest/Average/AverageReturn -233.66 MetaTest/Average/Iteration 407 MetaTest/Average/MaxReturn -117.713 MetaTest/Average/MinReturn -291.187 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 61.895 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -233.66 MetaTest/__unnamed_task__/AverageReturn -233.66 MetaTest/__unnamed_task__/Iteration 407 MetaTest/__unnamed_task__/MaxReturn -117.713 MetaTest/__unnamed_task__/MinReturn -291.187 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 61.895 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 856000 ------------------------------------------------- ---------- 2025-04-05 22:42:04 | [pearl_trainer] epoch #408 | Training... 2025-04-05 22:44:48 | [pearl_trainer] epoch #408 | Evaluating... 2025-04-05 22:44:48 | [pearl_trainer] epoch #408 | Sampling for adapation and meta-testing... 2025-04-05 22:49:20 | [pearl_trainer] epoch #408 | Finished meta-testing... 2025-04-05 22:49:20 | [pearl_trainer] epoch #408 | Saving snapshot... 2025-04-05 22:49:22 | [pearl_trainer] epoch #408 | Saved 2025-04-05 22:49:22 | [pearl_trainer] epoch #408 | Time 195625.42 s 2025-04-05 22:49:22 | [pearl_trainer] epoch #408 | EpochTime 489.51 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -256.935 MetaTest/Average/AverageReturn -256.935 MetaTest/Average/Iteration 408 MetaTest/Average/MaxReturn -174.596 MetaTest/Average/MinReturn -323.014 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 62.0569 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -256.935 MetaTest/__unnamed_task__/AverageReturn -256.935 MetaTest/__unnamed_task__/Iteration 408 MetaTest/__unnamed_task__/MaxReturn -174.596 MetaTest/__unnamed_task__/MinReturn -323.014 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 62.0569 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 858000 ------------------------------------------------- ----------- 2025-04-05 22:50:12 | [pearl_trainer] epoch #409 | Training... 2025-04-05 22:53:01 | [pearl_trainer] epoch #409 | Evaluating... 2025-04-05 22:53:01 | [pearl_trainer] epoch #409 | Sampling for adapation and meta-testing... 2025-04-05 22:57:17 | [pearl_trainer] epoch #409 | Finished meta-testing... 2025-04-05 22:57:17 | [pearl_trainer] epoch #409 | Saving snapshot... 2025-04-05 22:57:19 | [pearl_trainer] epoch #409 | Saved 2025-04-05 22:57:19 | [pearl_trainer] epoch #409 | Time 196102.31 s 2025-04-05 22:57:19 | [pearl_trainer] epoch #409 | EpochTime 476.88 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -293.746 MetaTest/Average/AverageReturn -293.746 MetaTest/Average/Iteration 409 MetaTest/Average/MaxReturn -244.794 MetaTest/Average/MinReturn -340.55 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.5668 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -293.746 MetaTest/__unnamed_task__/AverageReturn -293.746 MetaTest/__unnamed_task__/Iteration 409 MetaTest/__unnamed_task__/MaxReturn -244.794 MetaTest/__unnamed_task__/MinReturn -340.55 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.5668 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 860000 ------------------------------------------------- ----------- 2025-04-05 22:58:07 | [pearl_trainer] epoch #410 | Training... 2025-04-05 23:00:53 | [pearl_trainer] epoch #410 | Evaluating... 2025-04-05 23:00:53 | [pearl_trainer] epoch #410 | Sampling for adapation and meta-testing... 2025-04-05 23:05:14 | [pearl_trainer] epoch #410 | Finished meta-testing... 2025-04-05 23:05:14 | [pearl_trainer] epoch #410 | Saving snapshot... 2025-04-05 23:05:16 | [pearl_trainer] epoch #410 | Saved 2025-04-05 23:05:16 | [pearl_trainer] epoch #410 | Time 196579.22 s 2025-04-05 23:05:16 | [pearl_trainer] epoch #410 | EpochTime 476.92 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -288.578 MetaTest/Average/AverageReturn -288.578 MetaTest/Average/Iteration 410 MetaTest/Average/MaxReturn -201.22 MetaTest/Average/MinReturn -362.39 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 51.8337 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -288.578 MetaTest/__unnamed_task__/AverageReturn -288.578 MetaTest/__unnamed_task__/Iteration 410 MetaTest/__unnamed_task__/MaxReturn -201.22 MetaTest/__unnamed_task__/MinReturn -362.39 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 51.8337 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 862000 ------------------------------------------------- ----------- 2025-04-05 23:06:00 | [pearl_trainer] epoch #411 | Training... 2025-04-05 23:09:06 | [pearl_trainer] epoch #411 | Evaluating... 2025-04-05 23:09:06 | [pearl_trainer] epoch #411 | Sampling for adapation and meta-testing... 2025-04-05 23:13:23 | [pearl_trainer] epoch #411 | Finished meta-testing... 2025-04-05 23:13:23 | [pearl_trainer] epoch #411 | Saving snapshot... 2025-04-05 23:13:24 | [pearl_trainer] epoch #411 | Saved 2025-04-05 23:13:24 | [pearl_trainer] epoch #411 | Time 197068.18 s 2025-04-05 23:13:24 | [pearl_trainer] epoch #411 | EpochTime 488.95 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -279.056 MetaTest/Average/AverageReturn -279.056 MetaTest/Average/Iteration 411 MetaTest/Average/MaxReturn -178.656 MetaTest/Average/MinReturn -324.993 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 56.0219 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -279.056 MetaTest/__unnamed_task__/AverageReturn -279.056 MetaTest/__unnamed_task__/Iteration 411 MetaTest/__unnamed_task__/MaxReturn -178.656 MetaTest/__unnamed_task__/MinReturn -324.993 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 56.0219 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 864000 ------------------------------------------------- ----------- 2025-04-05 23:14:12 | [pearl_trainer] epoch #412 | Training... 2025-04-05 23:17:14 | [pearl_trainer] epoch #412 | Evaluating... 2025-04-05 23:17:14 | [pearl_trainer] epoch #412 | Sampling for adapation and meta-testing... 2025-04-05 23:21:26 | [pearl_trainer] epoch #412 | Finished meta-testing... 2025-04-05 23:21:26 | [pearl_trainer] epoch #412 | Saving snapshot... 2025-04-05 23:21:28 | [pearl_trainer] epoch #412 | Saved 2025-04-05 23:21:28 | [pearl_trainer] epoch #412 | Time 197551.39 s 2025-04-05 23:21:28 | [pearl_trainer] epoch #412 | EpochTime 483.21 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -319.607 MetaTest/Average/AverageReturn -319.607 MetaTest/Average/Iteration 412 MetaTest/Average/MaxReturn -280.974 MetaTest/Average/MinReturn -356.728 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 24.3332 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -319.607 MetaTest/__unnamed_task__/AverageReturn -319.607 MetaTest/__unnamed_task__/Iteration 412 MetaTest/__unnamed_task__/MaxReturn -280.974 MetaTest/__unnamed_task__/MinReturn -356.728 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 24.3332 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 866000 ------------------------------------------------- ----------- 2025-04-05 23:22:10 | [pearl_trainer] epoch #413 | Training... 2025-04-05 23:24:56 | [pearl_trainer] epoch #413 | Evaluating... 2025-04-05 23:24:56 | [pearl_trainer] epoch #413 | Sampling for adapation and meta-testing... 2025-04-05 23:28:55 | [pearl_trainer] epoch #413 | Finished meta-testing... 2025-04-05 23:28:55 | [pearl_trainer] epoch #413 | Saving snapshot... 2025-04-05 23:28:56 | [pearl_trainer] epoch #413 | Saved 2025-04-05 23:28:56 | [pearl_trainer] epoch #413 | Time 197999.85 s 2025-04-05 23:28:56 | [pearl_trainer] epoch #413 | EpochTime 448.46 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -263.937 MetaTest/Average/AverageReturn -263.937 MetaTest/Average/Iteration 413 MetaTest/Average/MaxReturn -219.176 MetaTest/Average/MinReturn -282.64 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 23.42 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -263.937 MetaTest/__unnamed_task__/AverageReturn -263.937 MetaTest/__unnamed_task__/Iteration 413 MetaTest/__unnamed_task__/MaxReturn -219.176 MetaTest/__unnamed_task__/MinReturn -282.64 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 23.42 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 868000 ------------------------------------------------- ---------- 2025-04-05 23:29:40 | [pearl_trainer] epoch #414 | Training... 2025-04-05 23:32:22 | [pearl_trainer] epoch #414 | Evaluating... 2025-04-05 23:32:22 | [pearl_trainer] epoch #414 | Sampling for adapation and meta-testing... 2025-04-05 23:36:33 | [pearl_trainer] epoch #414 | Finished meta-testing... 2025-04-05 23:36:33 | [pearl_trainer] epoch #414 | Saving snapshot... 2025-04-05 23:36:35 | [pearl_trainer] epoch #414 | Saved 2025-04-05 23:36:35 | [pearl_trainer] epoch #414 | Time 198458.39 s 2025-04-05 23:36:35 | [pearl_trainer] epoch #414 | EpochTime 458.54 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -292.695 MetaTest/Average/AverageReturn -292.695 MetaTest/Average/Iteration 414 MetaTest/Average/MaxReturn -217.63 MetaTest/Average/MinReturn -388.002 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 55.4437 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -292.695 MetaTest/__unnamed_task__/AverageReturn -292.695 MetaTest/__unnamed_task__/Iteration 414 MetaTest/__unnamed_task__/MaxReturn -217.63 MetaTest/__unnamed_task__/MinReturn -388.002 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 55.4437 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 870000 ------------------------------------------------- ----------- 2025-04-05 23:37:18 | [pearl_trainer] epoch #415 | Training... 2025-04-05 23:40:01 | [pearl_trainer] epoch #415 | Evaluating... 2025-04-05 23:40:01 | [pearl_trainer] epoch #415 | Sampling for adapation and meta-testing... 2025-04-05 23:43:58 | [pearl_trainer] epoch #415 | Finished meta-testing... 2025-04-05 23:43:58 | [pearl_trainer] epoch #415 | Saving snapshot... 2025-04-05 23:43:59 | [pearl_trainer] epoch #415 | Saved 2025-04-05 23:43:59 | [pearl_trainer] epoch #415 | Time 198903.13 s 2025-04-05 23:43:59 | [pearl_trainer] epoch #415 | EpochTime 444.74 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -277.122 MetaTest/Average/AverageReturn -277.122 MetaTest/Average/Iteration 415 MetaTest/Average/MaxReturn -210.558 MetaTest/Average/MinReturn -336.807 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 45.2491 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -277.122 MetaTest/__unnamed_task__/AverageReturn -277.122 MetaTest/__unnamed_task__/Iteration 415 MetaTest/__unnamed_task__/MaxReturn -210.558 MetaTest/__unnamed_task__/MinReturn -336.807 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 45.2491 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 872000 ------------------------------------------------- ----------- 2025-04-05 23:44:44 | [pearl_trainer] epoch #416 | Training... 2025-04-05 23:47:31 | [pearl_trainer] epoch #416 | Evaluating... 2025-04-05 23:47:31 | [pearl_trainer] epoch #416 | Sampling for adapation and meta-testing... 2025-04-05 23:51:28 | [pearl_trainer] epoch #416 | Finished meta-testing... 2025-04-05 23:51:28 | [pearl_trainer] epoch #416 | Saving snapshot... 2025-04-05 23:51:29 | [pearl_trainer] epoch #416 | Saved 2025-04-05 23:51:29 | [pearl_trainer] epoch #416 | Time 199352.79 s 2025-04-05 23:51:29 | [pearl_trainer] epoch #416 | EpochTime 449.66 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -270.486 MetaTest/Average/AverageReturn -270.486 MetaTest/Average/Iteration 416 MetaTest/Average/MaxReturn -254.79 MetaTest/Average/MinReturn -293.989 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 13.608 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -270.486 MetaTest/__unnamed_task__/AverageReturn -270.486 MetaTest/__unnamed_task__/Iteration 416 MetaTest/__unnamed_task__/MaxReturn -254.79 MetaTest/__unnamed_task__/MinReturn -293.989 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 13.608 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 874000 ------------------------------------------------- ---------- 2025-04-05 23:52:16 | [pearl_trainer] epoch #417 | Training... 2025-04-05 23:55:03 | [pearl_trainer] epoch #417 | Evaluating... 2025-04-05 23:55:03 | [pearl_trainer] epoch #417 | Sampling for adapation and meta-testing... 2025-04-05 23:59:19 | [pearl_trainer] epoch #417 | Finished meta-testing... 2025-04-05 23:59:19 | [pearl_trainer] epoch #417 | Saving snapshot... 2025-04-05 23:59:20 | [pearl_trainer] epoch #417 | Saved 2025-04-05 23:59:20 | [pearl_trainer] epoch #417 | Time 199823.96 s 2025-04-05 23:59:20 | [pearl_trainer] epoch #417 | EpochTime 471.17 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -301.301 MetaTest/Average/AverageReturn -301.301 MetaTest/Average/Iteration 417 MetaTest/Average/MaxReturn -271.194 MetaTest/Average/MinReturn -329.859 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 18.7141 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -301.301 MetaTest/__unnamed_task__/AverageReturn -301.301 MetaTest/__unnamed_task__/Iteration 417 MetaTest/__unnamed_task__/MaxReturn -271.194 MetaTest/__unnamed_task__/MinReturn -329.859 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 18.7141 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 876000 ------------------------------------------------- ----------- 2025-04-06 00:00:05 | [pearl_trainer] epoch #418 | Training... 2025-04-06 00:02:50 | [pearl_trainer] epoch #418 | Evaluating... 2025-04-06 00:02:50 | [pearl_trainer] epoch #418 | Sampling for adapation and meta-testing... 2025-04-06 00:06:58 | [pearl_trainer] epoch #418 | Finished meta-testing... 2025-04-06 00:06:58 | [pearl_trainer] epoch #418 | Saving snapshot... 2025-04-06 00:06:59 | [pearl_trainer] epoch #418 | Saved 2025-04-06 00:06:59 | [pearl_trainer] epoch #418 | Time 200282.66 s 2025-04-06 00:06:59 | [pearl_trainer] epoch #418 | EpochTime 458.69 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -275.266 MetaTest/Average/AverageReturn -275.266 MetaTest/Average/Iteration 418 MetaTest/Average/MaxReturn -253.066 MetaTest/Average/MinReturn -320.374 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 23.3213 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -275.266 MetaTest/__unnamed_task__/AverageReturn -275.266 MetaTest/__unnamed_task__/Iteration 418 MetaTest/__unnamed_task__/MaxReturn -253.066 MetaTest/__unnamed_task__/MinReturn -320.374 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 23.3213 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 878000 ------------------------------------------------- ----------- 2025-04-06 00:07:42 | [pearl_trainer] epoch #419 | Training... 2025-04-06 00:10:41 | [pearl_trainer] epoch #419 | Evaluating... 2025-04-06 00:10:41 | [pearl_trainer] epoch #419 | Sampling for adapation and meta-testing... 2025-04-06 00:14:55 | [pearl_trainer] epoch #419 | Finished meta-testing... 2025-04-06 00:14:55 | [pearl_trainer] epoch #419 | Saving snapshot... 2025-04-06 00:14:57 | [pearl_trainer] epoch #419 | Saved 2025-04-06 00:14:57 | [pearl_trainer] epoch #419 | Time 200760.55 s 2025-04-06 00:14:57 | [pearl_trainer] epoch #419 | EpochTime 477.89 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -276.242 MetaTest/Average/AverageReturn -276.242 MetaTest/Average/Iteration 419 MetaTest/Average/MaxReturn -243.15 MetaTest/Average/MinReturn -297.25 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 20.4762 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -276.242 MetaTest/__unnamed_task__/AverageReturn -276.242 MetaTest/__unnamed_task__/Iteration 419 MetaTest/__unnamed_task__/MaxReturn -243.15 MetaTest/__unnamed_task__/MinReturn -297.25 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 20.4762 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 880000 ------------------------------------------------- ----------- 2025-04-06 00:15:46 | [pearl_trainer] epoch #420 | Training... 2025-04-06 00:18:38 | [pearl_trainer] epoch #420 | Evaluating... 2025-04-06 00:18:38 | [pearl_trainer] epoch #420 | Sampling for adapation and meta-testing... 2025-04-06 00:23:14 | [pearl_trainer] epoch #420 | Finished meta-testing... 2025-04-06 00:23:14 | [pearl_trainer] epoch #420 | Saving snapshot... 2025-04-06 00:23:15 | [pearl_trainer] epoch #420 | Saved 2025-04-06 00:23:15 | [pearl_trainer] epoch #420 | Time 201258.86 s 2025-04-06 00:23:15 | [pearl_trainer] epoch #420 | EpochTime 498.31 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -242.399 MetaTest/Average/AverageReturn -242.399 MetaTest/Average/Iteration 420 MetaTest/Average/MaxReturn -186.597 MetaTest/Average/MinReturn -330.808 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 48.6299 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -242.399 MetaTest/__unnamed_task__/AverageReturn -242.399 MetaTest/__unnamed_task__/Iteration 420 MetaTest/__unnamed_task__/MaxReturn -186.597 MetaTest/__unnamed_task__/MinReturn -330.808 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 48.6299 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 882000 ------------------------------------------------- ----------- 2025-04-06 00:23:59 | [pearl_trainer] epoch #421 | Training... 2025-04-06 00:27:03 | [pearl_trainer] epoch #421 | Evaluating... 2025-04-06 00:27:03 | [pearl_trainer] epoch #421 | Sampling for adapation and meta-testing... 2025-04-06 00:31:39 | [pearl_trainer] epoch #421 | Finished meta-testing... 2025-04-06 00:31:39 | [pearl_trainer] epoch #421 | Saving snapshot... 2025-04-06 00:31:40 | [pearl_trainer] epoch #421 | Saved 2025-04-06 00:31:40 | [pearl_trainer] epoch #421 | Time 201763.69 s 2025-04-06 00:31:40 | [pearl_trainer] epoch #421 | EpochTime 504.83 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -265.978 MetaTest/Average/AverageReturn -265.978 MetaTest/Average/Iteration 421 MetaTest/Average/MaxReturn -182.248 MetaTest/Average/MinReturn -365.074 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 60.8632 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -265.978 MetaTest/__unnamed_task__/AverageReturn -265.978 MetaTest/__unnamed_task__/Iteration 421 MetaTest/__unnamed_task__/MaxReturn -182.248 MetaTest/__unnamed_task__/MinReturn -365.074 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 60.8632 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 884000 ------------------------------------------------- ----------- 2025-04-06 00:32:32 | [pearl_trainer] epoch #422 | Training... 2025-04-06 00:35:06 | [pearl_trainer] epoch #422 | Evaluating... 2025-04-06 00:35:06 | [pearl_trainer] epoch #422 | Sampling for adapation and meta-testing... 2025-04-06 00:39:36 | [pearl_trainer] epoch #422 | Finished meta-testing... 2025-04-06 00:39:36 | [pearl_trainer] epoch #422 | Saving snapshot... 2025-04-06 00:39:37 | [pearl_trainer] epoch #422 | Saved 2025-04-06 00:39:37 | [pearl_trainer] epoch #422 | Time 202240.53 s 2025-04-06 00:39:37 | [pearl_trainer] epoch #422 | EpochTime 476.83 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -238.853 MetaTest/Average/AverageReturn -238.853 MetaTest/Average/Iteration 422 MetaTest/Average/MaxReturn -117.794 MetaTest/Average/MinReturn -337.732 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 79.8752 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -238.853 MetaTest/__unnamed_task__/AverageReturn -238.853 MetaTest/__unnamed_task__/Iteration 422 MetaTest/__unnamed_task__/MaxReturn -117.794 MetaTest/__unnamed_task__/MinReturn -337.732 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 79.8752 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 886000 ------------------------------------------------- ----------- 2025-04-06 00:40:26 | [pearl_trainer] epoch #423 | Training... 2025-04-06 00:43:04 | [pearl_trainer] epoch #423 | Evaluating... 2025-04-06 00:43:04 | [pearl_trainer] epoch #423 | Sampling for adapation and meta-testing... 2025-04-06 00:47:38 | [pearl_trainer] epoch #423 | Finished meta-testing... 2025-04-06 00:47:38 | [pearl_trainer] epoch #423 | Saving snapshot... 2025-04-06 00:47:39 | [pearl_trainer] epoch #423 | Saved 2025-04-06 00:47:39 | [pearl_trainer] epoch #423 | Time 202722.52 s 2025-04-06 00:47:39 | [pearl_trainer] epoch #423 | EpochTime 481.99 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -231.713 MetaTest/Average/AverageReturn -231.713 MetaTest/Average/Iteration 423 MetaTest/Average/MaxReturn -185.404 MetaTest/Average/MinReturn -308.054 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 43.3149 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -231.713 MetaTest/__unnamed_task__/AverageReturn -231.713 MetaTest/__unnamed_task__/Iteration 423 MetaTest/__unnamed_task__/MaxReturn -185.404 MetaTest/__unnamed_task__/MinReturn -308.054 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 43.3149 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 888000 ------------------------------------------------- ----------- 2025-04-06 00:48:29 | [pearl_trainer] epoch #424 | Training... 2025-04-06 00:51:04 | [pearl_trainer] epoch #424 | Evaluating... 2025-04-06 00:51:04 | [pearl_trainer] epoch #424 | Sampling for adapation and meta-testing... 2025-04-06 00:55:36 | [pearl_trainer] epoch #424 | Finished meta-testing... 2025-04-06 00:55:36 | [pearl_trainer] epoch #424 | Saving snapshot... 2025-04-06 00:55:37 | [pearl_trainer] epoch #424 | Saved 2025-04-06 00:55:37 | [pearl_trainer] epoch #424 | Time 203200.89 s 2025-04-06 00:55:37 | [pearl_trainer] epoch #424 | EpochTime 478.37 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -264.815 MetaTest/Average/AverageReturn -264.815 MetaTest/Average/Iteration 424 MetaTest/Average/MaxReturn -137.656 MetaTest/Average/MinReturn -332.731 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 69.4856 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -264.815 MetaTest/__unnamed_task__/AverageReturn -264.815 MetaTest/__unnamed_task__/Iteration 424 MetaTest/__unnamed_task__/MaxReturn -137.656 MetaTest/__unnamed_task__/MinReturn -332.731 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 69.4856 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 890000 ------------------------------------------------- ----------- 2025-04-06 00:56:26 | [pearl_trainer] epoch #425 | Training... 2025-04-06 00:59:08 | [pearl_trainer] epoch #425 | Evaluating... 2025-04-06 00:59:08 | [pearl_trainer] epoch #425 | Sampling for adapation and meta-testing... 2025-04-06 01:03:38 | [pearl_trainer] epoch #425 | Finished meta-testing... 2025-04-06 01:03:38 | [pearl_trainer] epoch #425 | Saving snapshot... 2025-04-06 01:03:39 | [pearl_trainer] epoch #425 | Saved 2025-04-06 01:03:39 | [pearl_trainer] epoch #425 | Time 203683.00 s 2025-04-06 01:03:39 | [pearl_trainer] epoch #425 | EpochTime 482.11 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -210.668 MetaTest/Average/AverageReturn -210.668 MetaTest/Average/Iteration 425 MetaTest/Average/MaxReturn -184.791 MetaTest/Average/MinReturn -237.888 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 18.1326 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -210.668 MetaTest/__unnamed_task__/AverageReturn -210.668 MetaTest/__unnamed_task__/Iteration 425 MetaTest/__unnamed_task__/MaxReturn -184.791 MetaTest/__unnamed_task__/MinReturn -237.888 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 18.1326 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 892000 ------------------------------------------------- ----------- 2025-04-06 01:04:28 | [pearl_trainer] epoch #426 | Training... 2025-04-06 01:07:37 | [pearl_trainer] epoch #426 | Evaluating... 2025-04-06 01:07:37 | [pearl_trainer] epoch #426 | Sampling for adapation and meta-testing... 2025-04-06 01:12:04 | [pearl_trainer] epoch #426 | Finished meta-testing... 2025-04-06 01:12:04 | [pearl_trainer] epoch #426 | Saving snapshot... 2025-04-06 01:12:05 | [pearl_trainer] epoch #426 | Saved 2025-04-06 01:12:05 | [pearl_trainer] epoch #426 | Time 204188.91 s 2025-04-06 01:12:05 | [pearl_trainer] epoch #426 | EpochTime 505.91 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -261.007 MetaTest/Average/AverageReturn -261.007 MetaTest/Average/Iteration 426 MetaTest/Average/MaxReturn -209.97 MetaTest/Average/MinReturn -300.864 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.0036 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -261.007 MetaTest/__unnamed_task__/AverageReturn -261.007 MetaTest/__unnamed_task__/Iteration 426 MetaTest/__unnamed_task__/MaxReturn -209.97 MetaTest/__unnamed_task__/MinReturn -300.864 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.0036 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 894000 ------------------------------------------------- ----------- 2025-04-06 01:12:53 | [pearl_trainer] epoch #427 | Training... 2025-04-06 01:15:50 | [pearl_trainer] epoch #427 | Evaluating... 2025-04-06 01:15:50 | [pearl_trainer] epoch #427 | Sampling for adapation and meta-testing... 2025-04-06 01:20:30 | [pearl_trainer] epoch #427 | Finished meta-testing... 2025-04-06 01:20:30 | [pearl_trainer] epoch #427 | Saving snapshot... 2025-04-06 01:20:31 | [pearl_trainer] epoch #427 | Saved 2025-04-06 01:20:31 | [pearl_trainer] epoch #427 | Time 204694.41 s 2025-04-06 01:20:31 | [pearl_trainer] epoch #427 | EpochTime 505.50 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -222.134 MetaTest/Average/AverageReturn -222.134 MetaTest/Average/Iteration 427 MetaTest/Average/MaxReturn -164.552 MetaTest/Average/MinReturn -266.884 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 44.8166 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -222.134 MetaTest/__unnamed_task__/AverageReturn -222.134 MetaTest/__unnamed_task__/Iteration 427 MetaTest/__unnamed_task__/MaxReturn -164.552 MetaTest/__unnamed_task__/MinReturn -266.884 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 44.8166 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 896000 ------------------------------------------------- ----------- 2025-04-06 01:21:21 | [pearl_trainer] epoch #428 | Training... 2025-04-06 01:24:06 | [pearl_trainer] epoch #428 | Evaluating... 2025-04-06 01:24:06 | [pearl_trainer] epoch #428 | Sampling for adapation and meta-testing... 2025-04-06 01:28:53 | [pearl_trainer] epoch #428 | Finished meta-testing... 2025-04-06 01:28:53 | [pearl_trainer] epoch #428 | Saving snapshot... 2025-04-06 01:28:54 | [pearl_trainer] epoch #428 | Saved 2025-04-06 01:28:54 | [pearl_trainer] epoch #428 | Time 205197.44 s 2025-04-06 01:28:54 | [pearl_trainer] epoch #428 | EpochTime 503.03 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -251.617 MetaTest/Average/AverageReturn -251.617 MetaTest/Average/Iteration 428 MetaTest/Average/MaxReturn -169.668 MetaTest/Average/MinReturn -341.446 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 64.7055 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -251.617 MetaTest/__unnamed_task__/AverageReturn -251.617 MetaTest/__unnamed_task__/Iteration 428 MetaTest/__unnamed_task__/MaxReturn -169.668 MetaTest/__unnamed_task__/MinReturn -341.446 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 64.7055 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 898000 ------------------------------------------------- ----------- 2025-04-06 01:29:48 | [pearl_trainer] epoch #429 | Training... 2025-04-06 01:32:29 | [pearl_trainer] epoch #429 | Evaluating... 2025-04-06 01:32:29 | [pearl_trainer] epoch #429 | Sampling for adapation and meta-testing... 2025-04-06 01:37:12 | [pearl_trainer] epoch #429 | Finished meta-testing... 2025-04-06 01:37:12 | [pearl_trainer] epoch #429 | Saving snapshot... 2025-04-06 01:37:13 | [pearl_trainer] epoch #429 | Saved 2025-04-06 01:37:13 | [pearl_trainer] epoch #429 | Time 205696.92 s 2025-04-06 01:37:13 | [pearl_trainer] epoch #429 | EpochTime 499.47 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -211.141 MetaTest/Average/AverageReturn -211.141 MetaTest/Average/Iteration 429 MetaTest/Average/MaxReturn -136.443 MetaTest/Average/MinReturn -335.755 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 69.3433 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -211.141 MetaTest/__unnamed_task__/AverageReturn -211.141 MetaTest/__unnamed_task__/Iteration 429 MetaTest/__unnamed_task__/MaxReturn -136.443 MetaTest/__unnamed_task__/MinReturn -335.755 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 69.3433 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 900000 ------------------------------------------------- ----------- 2025-04-06 01:38:03 | [pearl_trainer] epoch #430 | Training... 2025-04-06 01:40:45 | [pearl_trainer] epoch #430 | Evaluating... 2025-04-06 01:40:45 | [pearl_trainer] epoch #430 | Sampling for adapation and meta-testing... 2025-04-06 01:45:21 | [pearl_trainer] epoch #430 | Finished meta-testing... 2025-04-06 01:45:21 | [pearl_trainer] epoch #430 | Saving snapshot... 2025-04-06 01:45:22 | [pearl_trainer] epoch #430 | Saved 2025-04-06 01:45:22 | [pearl_trainer] epoch #430 | Time 206185.93 s 2025-04-06 01:45:22 | [pearl_trainer] epoch #430 | EpochTime 489.02 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -218.259 MetaTest/Average/AverageReturn -218.259 MetaTest/Average/Iteration 430 MetaTest/Average/MaxReturn -153.609 MetaTest/Average/MinReturn -264.882 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 41.1116 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -218.259 MetaTest/__unnamed_task__/AverageReturn -218.259 MetaTest/__unnamed_task__/Iteration 430 MetaTest/__unnamed_task__/MaxReturn -153.609 MetaTest/__unnamed_task__/MinReturn -264.882 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 41.1116 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 902000 ------------------------------------------------- ----------- 2025-04-06 01:46:11 | [pearl_trainer] epoch #431 | Training... 2025-04-06 01:48:53 | [pearl_trainer] epoch #431 | Evaluating... 2025-04-06 01:48:53 | [pearl_trainer] epoch #431 | Sampling for adapation and meta-testing... 2025-04-06 01:53:35 | [pearl_trainer] epoch #431 | Finished meta-testing... 2025-04-06 01:53:35 | [pearl_trainer] epoch #431 | Saving snapshot... 2025-04-06 01:53:37 | [pearl_trainer] epoch #431 | Saved 2025-04-06 01:53:37 | [pearl_trainer] epoch #431 | Time 206680.36 s 2025-04-06 01:53:37 | [pearl_trainer] epoch #431 | EpochTime 494.43 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -248.693 MetaTest/Average/AverageReturn -248.693 MetaTest/Average/Iteration 431 MetaTest/Average/MaxReturn -197.12 MetaTest/Average/MinReturn -297.591 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 38.4331 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -248.693 MetaTest/__unnamed_task__/AverageReturn -248.693 MetaTest/__unnamed_task__/Iteration 431 MetaTest/__unnamed_task__/MaxReturn -197.12 MetaTest/__unnamed_task__/MinReturn -297.591 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 38.4331 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 904000 ------------------------------------------------- ----------- 2025-04-06 01:54:25 | [pearl_trainer] epoch #432 | Training... 2025-04-06 01:57:20 | [pearl_trainer] epoch #432 | Evaluating... 2025-04-06 01:57:20 | [pearl_trainer] epoch #432 | Sampling for adapation and meta-testing... 2025-04-06 02:02:04 | [pearl_trainer] epoch #432 | Finished meta-testing... 2025-04-06 02:02:04 | [pearl_trainer] epoch #432 | Saving snapshot... 2025-04-06 02:02:06 | [pearl_trainer] epoch #432 | Saved 2025-04-06 02:02:06 | [pearl_trainer] epoch #432 | Time 207189.35 s 2025-04-06 02:02:06 | [pearl_trainer] epoch #432 | EpochTime 508.99 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -264.69 MetaTest/Average/AverageReturn -264.69 MetaTest/Average/Iteration 432 MetaTest/Average/MaxReturn -190.952 MetaTest/Average/MinReturn -362.402 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 63.2392 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -264.69 MetaTest/__unnamed_task__/AverageReturn -264.69 MetaTest/__unnamed_task__/Iteration 432 MetaTest/__unnamed_task__/MaxReturn -190.952 MetaTest/__unnamed_task__/MinReturn -362.402 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 63.2392 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 906000 ------------------------------------------------- ----------- 2025-04-06 02:02:56 | [pearl_trainer] epoch #433 | Training... 2025-04-06 02:06:02 | [pearl_trainer] epoch #433 | Evaluating... 2025-04-06 02:06:02 | [pearl_trainer] epoch #433 | Sampling for adapation and meta-testing... 2025-04-06 02:10:52 | [pearl_trainer] epoch #433 | Finished meta-testing... 2025-04-06 02:10:52 | [pearl_trainer] epoch #433 | Saving snapshot... 2025-04-06 02:10:53 | [pearl_trainer] epoch #433 | Saved 2025-04-06 02:10:53 | [pearl_trainer] epoch #433 | Time 207716.93 s 2025-04-06 02:10:53 | [pearl_trainer] epoch #433 | EpochTime 527.58 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -201.106 MetaTest/Average/AverageReturn -201.106 MetaTest/Average/Iteration 433 MetaTest/Average/MaxReturn -131.027 MetaTest/Average/MinReturn -290.554 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 63.9593 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -201.106 MetaTest/__unnamed_task__/AverageReturn -201.106 MetaTest/__unnamed_task__/Iteration 433 MetaTest/__unnamed_task__/MaxReturn -131.027 MetaTest/__unnamed_task__/MinReturn -290.554 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 63.9593 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 908000 ------------------------------------------------- ----------- 2025-04-06 02:11:41 | [pearl_trainer] epoch #434 | Training... 2025-04-06 02:14:25 | [pearl_trainer] epoch #434 | Evaluating... 2025-04-06 02:14:25 | [pearl_trainer] epoch #434 | Sampling for adapation and meta-testing... 2025-04-06 02:19:08 | [pearl_trainer] epoch #434 | Finished meta-testing... 2025-04-06 02:19:08 | [pearl_trainer] epoch #434 | Saving snapshot... 2025-04-06 02:19:10 | [pearl_trainer] epoch #434 | Saved 2025-04-06 02:19:10 | [pearl_trainer] epoch #434 | Time 208213.32 s 2025-04-06 02:19:10 | [pearl_trainer] epoch #434 | EpochTime 496.39 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -247.678 MetaTest/Average/AverageReturn -247.678 MetaTest/Average/Iteration 434 MetaTest/Average/MaxReturn -181.857 MetaTest/Average/MinReturn -288.475 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 43.0801 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -247.678 MetaTest/__unnamed_task__/AverageReturn -247.678 MetaTest/__unnamed_task__/Iteration 434 MetaTest/__unnamed_task__/MaxReturn -181.857 MetaTest/__unnamed_task__/MinReturn -288.475 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 43.0801 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 910000 ------------------------------------------------- ----------- 2025-04-06 02:19:54 | [pearl_trainer] epoch #435 | Training... 2025-04-06 02:22:38 | [pearl_trainer] epoch #435 | Evaluating... 2025-04-06 02:22:38 | [pearl_trainer] epoch #435 | Sampling for adapation and meta-testing... 2025-04-06 02:27:13 | [pearl_trainer] epoch #435 | Finished meta-testing... 2025-04-06 02:27:13 | [pearl_trainer] epoch #435 | Saving snapshot... 2025-04-06 02:27:14 | [pearl_trainer] epoch #435 | Saved 2025-04-06 02:27:14 | [pearl_trainer] epoch #435 | Time 208698.03 s 2025-04-06 02:27:14 | [pearl_trainer] epoch #435 | EpochTime 484.70 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -213.66 MetaTest/Average/AverageReturn -213.66 MetaTest/Average/Iteration 435 MetaTest/Average/MaxReturn -124.943 MetaTest/Average/MinReturn -316.294 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 74.4096 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -213.66 MetaTest/__unnamed_task__/AverageReturn -213.66 MetaTest/__unnamed_task__/Iteration 435 MetaTest/__unnamed_task__/MaxReturn -124.943 MetaTest/__unnamed_task__/MinReturn -316.294 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 74.4096 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 912000 ------------------------------------------------- ----------- 2025-04-06 02:28:03 | [pearl_trainer] epoch #436 | Training... 2025-04-06 02:30:47 | [pearl_trainer] epoch #436 | Evaluating... 2025-04-06 02:30:47 | [pearl_trainer] epoch #436 | Sampling for adapation and meta-testing... 2025-04-06 02:35:29 | [pearl_trainer] epoch #436 | Finished meta-testing... 2025-04-06 02:35:29 | [pearl_trainer] epoch #436 | Saving snapshot... 2025-04-06 02:35:30 | [pearl_trainer] epoch #436 | Saved 2025-04-06 02:35:30 | [pearl_trainer] epoch #436 | Time 209193.74 s 2025-04-06 02:35:30 | [pearl_trainer] epoch #436 | EpochTime 495.71 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -226.547 MetaTest/Average/AverageReturn -226.547 MetaTest/Average/Iteration 436 MetaTest/Average/MaxReturn -154.256 MetaTest/Average/MinReturn -267.474 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 50.3792 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -226.547 MetaTest/__unnamed_task__/AverageReturn -226.547 MetaTest/__unnamed_task__/Iteration 436 MetaTest/__unnamed_task__/MaxReturn -154.256 MetaTest/__unnamed_task__/MinReturn -267.474 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 50.3792 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 914000 ------------------------------------------------- ----------- 2025-04-06 02:36:20 | [pearl_trainer] epoch #437 | Training... 2025-04-06 02:39:27 | [pearl_trainer] epoch #437 | Evaluating... 2025-04-06 02:39:27 | [pearl_trainer] epoch #437 | Sampling for adapation and meta-testing... 2025-04-06 02:44:02 | [pearl_trainer] epoch #437 | Finished meta-testing... 2025-04-06 02:44:02 | [pearl_trainer] epoch #437 | Saving snapshot... 2025-04-06 02:44:03 | [pearl_trainer] epoch #437 | Saved 2025-04-06 02:44:03 | [pearl_trainer] epoch #437 | Time 209706.99 s 2025-04-06 02:44:03 | [pearl_trainer] epoch #437 | EpochTime 513.25 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -261.082 MetaTest/Average/AverageReturn -261.082 MetaTest/Average/Iteration 437 MetaTest/Average/MaxReturn -209.97 MetaTest/Average/MinReturn -320.93 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 41.9263 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -261.082 MetaTest/__unnamed_task__/AverageReturn -261.082 MetaTest/__unnamed_task__/Iteration 437 MetaTest/__unnamed_task__/MaxReturn -209.97 MetaTest/__unnamed_task__/MinReturn -320.93 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 41.9263 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 916000 ------------------------------------------------- ----------- 2025-04-06 02:44:51 | [pearl_trainer] epoch #438 | Training... 2025-04-06 02:47:55 | [pearl_trainer] epoch #438 | Evaluating... 2025-04-06 02:47:55 | [pearl_trainer] epoch #438 | Sampling for adapation and meta-testing... 2025-04-06 02:52:21 | [pearl_trainer] epoch #438 | Finished meta-testing... 2025-04-06 02:52:21 | [pearl_trainer] epoch #438 | Saving snapshot... 2025-04-06 02:52:23 | [pearl_trainer] epoch #438 | Saved 2025-04-06 02:52:23 | [pearl_trainer] epoch #438 | Time 210207.05 s 2025-04-06 02:52:23 | [pearl_trainer] epoch #438 | EpochTime 500.06 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -244.752 MetaTest/Average/AverageReturn -244.752 MetaTest/Average/Iteration 438 MetaTest/Average/MaxReturn -228.455 MetaTest/Average/MinReturn -275.376 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 16.1184 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -244.752 MetaTest/__unnamed_task__/AverageReturn -244.752 MetaTest/__unnamed_task__/Iteration 438 MetaTest/__unnamed_task__/MaxReturn -228.455 MetaTest/__unnamed_task__/MinReturn -275.376 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 16.1184 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 918000 ------------------------------------------------- ----------- 2025-04-06 02:53:15 | [pearl_trainer] epoch #439 | Training... 2025-04-06 02:57:10 | [pearl_trainer] epoch #439 | Evaluating... 2025-04-06 02:57:10 | [pearl_trainer] epoch #439 | Sampling for adapation and meta-testing... 2025-04-06 03:07:44 | [pearl_trainer] epoch #439 | Finished meta-testing... 2025-04-06 03:07:44 | [pearl_trainer] epoch #439 | Saving snapshot... 2025-04-06 03:07:46 | [pearl_trainer] epoch #439 | Saved 2025-04-06 03:07:46 | [pearl_trainer] epoch #439 | Time 211130.07 s 2025-04-06 03:07:46 | [pearl_trainer] epoch #439 | EpochTime 923.01 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -288.288 MetaTest/Average/AverageReturn -288.288 MetaTest/Average/Iteration 439 MetaTest/Average/MaxReturn -206.1 MetaTest/Average/MinReturn -395.261 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 61.1662 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -288.288 MetaTest/__unnamed_task__/AverageReturn -288.288 MetaTest/__unnamed_task__/Iteration 439 MetaTest/__unnamed_task__/MaxReturn -206.1 MetaTest/__unnamed_task__/MinReturn -395.261 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 61.1662 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 920000 ------------------------------------------------- ----------- 2025-04-06 03:09:49 | [pearl_trainer] epoch #440 | Training... 2025-04-06 03:13:40 | [pearl_trainer] epoch #440 | Evaluating... 2025-04-06 03:13:40 | [pearl_trainer] epoch #440 | Sampling for adapation and meta-testing... 2025-04-06 03:17:41 | [pearl_trainer] epoch #440 | Finished meta-testing... 2025-04-06 03:17:41 | [pearl_trainer] epoch #440 | Saving snapshot... 2025-04-06 03:17:42 | [pearl_trainer] epoch #440 | Saved 2025-04-06 03:17:42 | [pearl_trainer] epoch #440 | Time 211725.75 s 2025-04-06 03:17:42 | [pearl_trainer] epoch #440 | EpochTime 595.68 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -282.804 MetaTest/Average/AverageReturn -282.804 MetaTest/Average/Iteration 440 MetaTest/Average/MaxReturn -230.426 MetaTest/Average/MinReturn -313.462 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 27.9095 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -282.804 MetaTest/__unnamed_task__/AverageReturn -282.804 MetaTest/__unnamed_task__/Iteration 440 MetaTest/__unnamed_task__/MaxReturn -230.426 MetaTest/__unnamed_task__/MinReturn -313.462 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 27.9095 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 922000 ------------------------------------------------- ----------- 2025-04-06 03:18:26 | [pearl_trainer] epoch #441 | Training... 2025-04-06 03:21:14 | [pearl_trainer] epoch #441 | Evaluating... 2025-04-06 03:21:14 | [pearl_trainer] epoch #441 | Sampling for adapation and meta-testing... 2025-04-06 03:25:42 | [pearl_trainer] epoch #441 | Finished meta-testing... 2025-04-06 03:25:42 | [pearl_trainer] epoch #441 | Saving snapshot... 2025-04-06 03:25:44 | [pearl_trainer] epoch #441 | Saved 2025-04-06 03:25:44 | [pearl_trainer] epoch #441 | Time 212207.31 s 2025-04-06 03:25:44 | [pearl_trainer] epoch #441 | EpochTime 481.56 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -270.298 MetaTest/Average/AverageReturn -270.298 MetaTest/Average/Iteration 441 MetaTest/Average/MaxReturn -230.183 MetaTest/Average/MinReturn -303.39 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.0109 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -270.298 MetaTest/__unnamed_task__/AverageReturn -270.298 MetaTest/__unnamed_task__/Iteration 441 MetaTest/__unnamed_task__/MaxReturn -230.183 MetaTest/__unnamed_task__/MinReturn -303.39 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.0109 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 924000 ------------------------------------------------- ----------- 2025-04-06 03:26:33 | [pearl_trainer] epoch #442 | Training... 2025-04-06 03:29:14 | [pearl_trainer] epoch #442 | Evaluating... 2025-04-06 03:29:14 | [pearl_trainer] epoch #442 | Sampling for adapation and meta-testing... 2025-04-06 03:33:42 | [pearl_trainer] epoch #442 | Finished meta-testing... 2025-04-06 03:33:42 | [pearl_trainer] epoch #442 | Saving snapshot... 2025-04-06 03:33:44 | [pearl_trainer] epoch #442 | Saved 2025-04-06 03:33:44 | [pearl_trainer] epoch #442 | Time 212687.19 s 2025-04-06 03:33:44 | [pearl_trainer] epoch #442 | EpochTime 479.88 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -260.87 MetaTest/Average/AverageReturn -260.87 MetaTest/Average/Iteration 442 MetaTest/Average/MaxReturn -181.592 MetaTest/Average/MinReturn -332.365 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 64.6861 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -260.87 MetaTest/__unnamed_task__/AverageReturn -260.87 MetaTest/__unnamed_task__/Iteration 442 MetaTest/__unnamed_task__/MaxReturn -181.592 MetaTest/__unnamed_task__/MinReturn -332.365 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 64.6861 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 926000 ------------------------------------------------- ----------- 2025-04-06 03:34:32 | [pearl_trainer] epoch #443 | Training... 2025-04-06 03:37:20 | [pearl_trainer] epoch #443 | Evaluating... 2025-04-06 03:37:20 | [pearl_trainer] epoch #443 | Sampling for adapation and meta-testing... 2025-04-06 03:41:41 | [pearl_trainer] epoch #443 | Finished meta-testing... 2025-04-06 03:41:41 | [pearl_trainer] epoch #443 | Saving snapshot... 2025-04-06 03:41:42 | [pearl_trainer] epoch #443 | Saved 2025-04-06 03:41:42 | [pearl_trainer] epoch #443 | Time 213165.40 s 2025-04-06 03:41:42 | [pearl_trainer] epoch #443 | EpochTime 478.20 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -282.828 MetaTest/Average/AverageReturn -282.828 MetaTest/Average/Iteration 443 MetaTest/Average/MaxReturn -174.439 MetaTest/Average/MinReturn -386.178 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 74.81 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -282.828 MetaTest/__unnamed_task__/AverageReturn -282.828 MetaTest/__unnamed_task__/Iteration 443 MetaTest/__unnamed_task__/MaxReturn -174.439 MetaTest/__unnamed_task__/MinReturn -386.178 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 74.81 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 928000 ------------------------------------------------- ---------- 2025-04-06 03:42:25 | [pearl_trainer] epoch #444 | Training... 2025-04-06 03:45:09 | [pearl_trainer] epoch #444 | Evaluating... 2025-04-06 03:45:09 | [pearl_trainer] epoch #444 | Sampling for adapation and meta-testing... 2025-04-06 03:49:19 | [pearl_trainer] epoch #444 | Finished meta-testing... 2025-04-06 03:49:19 | [pearl_trainer] epoch #444 | Saving snapshot... 2025-04-06 03:49:21 | [pearl_trainer] epoch #444 | Saved 2025-04-06 03:49:21 | [pearl_trainer] epoch #444 | Time 213624.27 s 2025-04-06 03:49:21 | [pearl_trainer] epoch #444 | EpochTime 458.87 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -277.605 MetaTest/Average/AverageReturn -277.605 MetaTest/Average/Iteration 444 MetaTest/Average/MaxReturn -216.974 MetaTest/Average/MinReturn -378.446 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 55.1851 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -277.605 MetaTest/__unnamed_task__/AverageReturn -277.605 MetaTest/__unnamed_task__/Iteration 444 MetaTest/__unnamed_task__/MaxReturn -216.974 MetaTest/__unnamed_task__/MinReturn -378.446 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 55.1851 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 930000 ------------------------------------------------- ----------- 2025-04-06 03:50:07 | [pearl_trainer] epoch #445 | Training... 2025-04-06 03:52:55 | [pearl_trainer] epoch #445 | Evaluating... 2025-04-06 03:52:55 | [pearl_trainer] epoch #445 | Sampling for adapation and meta-testing... 2025-04-06 03:57:09 | [pearl_trainer] epoch #445 | Finished meta-testing... 2025-04-06 03:57:09 | [pearl_trainer] epoch #445 | Saving snapshot... 2025-04-06 03:57:11 | [pearl_trainer] epoch #445 | Saved 2025-04-06 03:57:11 | [pearl_trainer] epoch #445 | Time 214094.24 s 2025-04-06 03:57:11 | [pearl_trainer] epoch #445 | EpochTime 469.96 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -343.501 MetaTest/Average/AverageReturn -343.501 MetaTest/Average/Iteration 445 MetaTest/Average/MaxReturn -309.031 MetaTest/Average/MinReturn -399.805 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.1854 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -343.501 MetaTest/__unnamed_task__/AverageReturn -343.501 MetaTest/__unnamed_task__/Iteration 445 MetaTest/__unnamed_task__/MaxReturn -309.031 MetaTest/__unnamed_task__/MinReturn -399.805 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.1854 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 932000 ------------------------------------------------- ----------- 2025-04-06 03:58:00 | [pearl_trainer] epoch #446 | Training... 2025-04-06 04:00:46 | [pearl_trainer] epoch #446 | Evaluating... 2025-04-06 04:00:46 | [pearl_trainer] epoch #446 | Sampling for adapation and meta-testing... 2025-04-06 04:04:59 | [pearl_trainer] epoch #446 | Finished meta-testing... 2025-04-06 04:04:59 | [pearl_trainer] epoch #446 | Saving snapshot... 2025-04-06 04:05:01 | [pearl_trainer] epoch #446 | Saved 2025-04-06 04:05:01 | [pearl_trainer] epoch #446 | Time 214564.28 s 2025-04-06 04:05:01 | [pearl_trainer] epoch #446 | EpochTime 470.04 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -274.539 MetaTest/Average/AverageReturn -274.539 MetaTest/Average/Iteration 446 MetaTest/Average/MaxReturn -234.569 MetaTest/Average/MinReturn -357.028 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 43.2246 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -274.539 MetaTest/__unnamed_task__/AverageReturn -274.539 MetaTest/__unnamed_task__/Iteration 446 MetaTest/__unnamed_task__/MaxReturn -234.569 MetaTest/__unnamed_task__/MinReturn -357.028 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 43.2246 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 934000 ------------------------------------------------- ----------- 2025-04-06 04:05:47 | [pearl_trainer] epoch #447 | Training... 2025-04-06 04:08:36 | [pearl_trainer] epoch #447 | Evaluating... 2025-04-06 04:08:36 | [pearl_trainer] epoch #447 | Sampling for adapation and meta-testing... 2025-04-06 04:12:51 | [pearl_trainer] epoch #447 | Finished meta-testing... 2025-04-06 04:12:51 | [pearl_trainer] epoch #447 | Saving snapshot... 2025-04-06 04:12:52 | [pearl_trainer] epoch #447 | Saved 2025-04-06 04:12:52 | [pearl_trainer] epoch #447 | Time 215035.47 s 2025-04-06 04:12:52 | [pearl_trainer] epoch #447 | EpochTime 471.19 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -275.601 MetaTest/Average/AverageReturn -275.601 MetaTest/Average/Iteration 447 MetaTest/Average/MaxReturn -190.578 MetaTest/Average/MinReturn -359.547 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 55.0621 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -275.601 MetaTest/__unnamed_task__/AverageReturn -275.601 MetaTest/__unnamed_task__/Iteration 447 MetaTest/__unnamed_task__/MaxReturn -190.578 MetaTest/__unnamed_task__/MinReturn -359.547 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 55.0621 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 936000 ------------------------------------------------- ----------- 2025-04-06 04:13:37 | [pearl_trainer] epoch #448 | Training... 2025-04-06 04:16:08 | [pearl_trainer] epoch #448 | Evaluating... 2025-04-06 04:16:08 | [pearl_trainer] epoch #448 | Sampling for adapation and meta-testing... 2025-04-06 04:20:37 | [pearl_trainer] epoch #448 | Finished meta-testing... 2025-04-06 04:20:37 | [pearl_trainer] epoch #448 | Saving snapshot... 2025-04-06 04:20:38 | [pearl_trainer] epoch #448 | Saved 2025-04-06 04:20:38 | [pearl_trainer] epoch #448 | Time 215501.98 s 2025-04-06 04:20:38 | [pearl_trainer] epoch #448 | EpochTime 466.51 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -297.462 MetaTest/Average/AverageReturn -297.462 MetaTest/Average/Iteration 448 MetaTest/Average/MaxReturn -254.18 MetaTest/Average/MinReturn -330.863 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 28.5152 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -297.462 MetaTest/__unnamed_task__/AverageReturn -297.462 MetaTest/__unnamed_task__/Iteration 448 MetaTest/__unnamed_task__/MaxReturn -254.18 MetaTest/__unnamed_task__/MinReturn -330.863 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 28.5152 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 938000 ------------------------------------------------- ----------- 2025-04-06 04:21:27 | [pearl_trainer] epoch #449 | Training... 2025-04-06 04:23:59 | [pearl_trainer] epoch #449 | Evaluating... 2025-04-06 04:23:59 | [pearl_trainer] epoch #449 | Sampling for adapation and meta-testing... 2025-04-06 04:28:25 | [pearl_trainer] epoch #449 | Finished meta-testing... 2025-04-06 04:28:25 | [pearl_trainer] epoch #449 | Saving snapshot... 2025-04-06 04:28:27 | [pearl_trainer] epoch #449 | Saved 2025-04-06 04:28:27 | [pearl_trainer] epoch #449 | Time 215970.32 s 2025-04-06 04:28:27 | [pearl_trainer] epoch #449 | EpochTime 468.34 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -249.246 MetaTest/Average/AverageReturn -249.246 MetaTest/Average/Iteration 449 MetaTest/Average/MaxReturn -207.496 MetaTest/Average/MinReturn -288.291 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 32.7586 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -249.246 MetaTest/__unnamed_task__/AverageReturn -249.246 MetaTest/__unnamed_task__/Iteration 449 MetaTest/__unnamed_task__/MaxReturn -207.496 MetaTest/__unnamed_task__/MinReturn -288.291 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 32.7586 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 940000 ------------------------------------------------- ----------- 2025-04-06 04:29:10 | [pearl_trainer] epoch #450 | Training... 2025-04-06 04:31:47 | [pearl_trainer] epoch #450 | Evaluating... 2025-04-06 04:31:47 | [pearl_trainer] epoch #450 | Sampling for adapation and meta-testing... 2025-04-06 04:35:58 | [pearl_trainer] epoch #450 | Finished meta-testing... 2025-04-06 04:35:58 | [pearl_trainer] epoch #450 | Saving snapshot... 2025-04-06 04:35:59 | [pearl_trainer] epoch #450 | Saved 2025-04-06 04:35:59 | [pearl_trainer] epoch #450 | Time 216422.91 s 2025-04-06 04:35:59 | [pearl_trainer] epoch #450 | EpochTime 452.58 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -309.754 MetaTest/Average/AverageReturn -309.754 MetaTest/Average/Iteration 450 MetaTest/Average/MaxReturn -223.922 MetaTest/Average/MinReturn -364.3 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 47.6738 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -309.754 MetaTest/__unnamed_task__/AverageReturn -309.754 MetaTest/__unnamed_task__/Iteration 450 MetaTest/__unnamed_task__/MaxReturn -223.922 MetaTest/__unnamed_task__/MinReturn -364.3 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 47.6738 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 942000 ------------------------------------------------- ----------- 2025-04-06 04:36:49 | [pearl_trainer] epoch #451 | Training... 2025-04-06 04:39:39 | [pearl_trainer] epoch #451 | Evaluating... 2025-04-06 04:39:39 | [pearl_trainer] epoch #451 | Sampling for adapation and meta-testing... 2025-04-06 04:43:47 | [pearl_trainer] epoch #451 | Finished meta-testing... 2025-04-06 04:43:47 | [pearl_trainer] epoch #451 | Saving snapshot... 2025-04-06 04:43:49 | [pearl_trainer] epoch #451 | Saved 2025-04-06 04:43:49 | [pearl_trainer] epoch #451 | Time 216892.23 s 2025-04-06 04:43:49 | [pearl_trainer] epoch #451 | EpochTime 469.33 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -285.346 MetaTest/Average/AverageReturn -285.346 MetaTest/Average/Iteration 451 MetaTest/Average/MaxReturn -233.079 MetaTest/Average/MinReturn -347.824 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 40.3271 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -285.346 MetaTest/__unnamed_task__/AverageReturn -285.346 MetaTest/__unnamed_task__/Iteration 451 MetaTest/__unnamed_task__/MaxReturn -233.079 MetaTest/__unnamed_task__/MinReturn -347.824 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 40.3271 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 944000 ------------------------------------------------- ----------- 2025-04-06 04:44:31 | [pearl_trainer] epoch #452 | Training... 2025-04-06 04:47:17 | [pearl_trainer] epoch #452 | Evaluating... 2025-04-06 04:47:17 | [pearl_trainer] epoch #452 | Sampling for adapation and meta-testing... 2025-04-06 04:51:34 | [pearl_trainer] epoch #452 | Finished meta-testing... 2025-04-06 04:51:34 | [pearl_trainer] epoch #452 | Saving snapshot... 2025-04-06 04:51:36 | [pearl_trainer] epoch #452 | Saved 2025-04-06 04:51:36 | [pearl_trainer] epoch #452 | Time 217359.54 s 2025-04-06 04:51:36 | [pearl_trainer] epoch #452 | EpochTime 467.30 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -307.661 MetaTest/Average/AverageReturn -307.661 MetaTest/Average/Iteration 452 MetaTest/Average/MaxReturn -218.313 MetaTest/Average/MinReturn -384.126 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 55.7692 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -307.661 MetaTest/__unnamed_task__/AverageReturn -307.661 MetaTest/__unnamed_task__/Iteration 452 MetaTest/__unnamed_task__/MaxReturn -218.313 MetaTest/__unnamed_task__/MinReturn -384.126 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 55.7692 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 946000 ------------------------------------------------- ----------- 2025-04-06 04:52:22 | [pearl_trainer] epoch #453 | Training... 2025-04-06 04:55:30 | [pearl_trainer] epoch #453 | Evaluating... 2025-04-06 04:55:30 | [pearl_trainer] epoch #453 | Sampling for adapation and meta-testing... 2025-04-06 04:59:52 | [pearl_trainer] epoch #453 | Finished meta-testing... 2025-04-06 04:59:52 | [pearl_trainer] epoch #453 | Saving snapshot... 2025-04-06 04:59:53 | [pearl_trainer] epoch #453 | Saved 2025-04-06 04:59:53 | [pearl_trainer] epoch #453 | Time 217856.86 s 2025-04-06 04:59:53 | [pearl_trainer] epoch #453 | EpochTime 497.32 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -258.291 MetaTest/Average/AverageReturn -258.291 MetaTest/Average/Iteration 453 MetaTest/Average/MaxReturn -164.612 MetaTest/Average/MinReturn -329.651 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 59.5754 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -258.291 MetaTest/__unnamed_task__/AverageReturn -258.291 MetaTest/__unnamed_task__/Iteration 453 MetaTest/__unnamed_task__/MaxReturn -164.612 MetaTest/__unnamed_task__/MinReturn -329.651 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 59.5754 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 948000 ------------------------------------------------- ----------- 2025-04-06 05:00:42 | [pearl_trainer] epoch #454 | Training... 2025-04-06 05:03:41 | [pearl_trainer] epoch #454 | Evaluating... 2025-04-06 05:03:41 | [pearl_trainer] epoch #454 | Sampling for adapation and meta-testing... 2025-04-06 05:08:12 | [pearl_trainer] epoch #454 | Finished meta-testing... 2025-04-06 05:08:12 | [pearl_trainer] epoch #454 | Saving snapshot... 2025-04-06 05:08:13 | [pearl_trainer] epoch #454 | Saved 2025-04-06 05:08:13 | [pearl_trainer] epoch #454 | Time 218356.66 s 2025-04-06 05:08:13 | [pearl_trainer] epoch #454 | EpochTime 499.80 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -252.755 MetaTest/Average/AverageReturn -252.755 MetaTest/Average/Iteration 454 MetaTest/Average/MaxReturn -156.335 MetaTest/Average/MinReturn -383.742 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 79.3073 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -252.755 MetaTest/__unnamed_task__/AverageReturn -252.755 MetaTest/__unnamed_task__/Iteration 454 MetaTest/__unnamed_task__/MaxReturn -156.335 MetaTest/__unnamed_task__/MinReturn -383.742 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 79.3073 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 950000 ------------------------------------------------- ----------- 2025-04-06 05:09:00 | [pearl_trainer] epoch #455 | Training... 2025-04-06 05:12:01 | [pearl_trainer] epoch #455 | Evaluating... 2025-04-06 05:12:01 | [pearl_trainer] epoch #455 | Sampling for adapation and meta-testing... 2025-04-06 05:16:34 | [pearl_trainer] epoch #455 | Finished meta-testing... 2025-04-06 05:16:34 | [pearl_trainer] epoch #455 | Saving snapshot... 2025-04-06 05:16:36 | [pearl_trainer] epoch #455 | Saved 2025-04-06 05:16:36 | [pearl_trainer] epoch #455 | Time 218859.36 s 2025-04-06 05:16:36 | [pearl_trainer] epoch #455 | EpochTime 502.70 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -185.709 MetaTest/Average/AverageReturn -185.709 MetaTest/Average/Iteration 455 MetaTest/Average/MaxReturn -103.048 MetaTest/Average/MinReturn -244.837 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 46.0655 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -185.709 MetaTest/__unnamed_task__/AverageReturn -185.709 MetaTest/__unnamed_task__/Iteration 455 MetaTest/__unnamed_task__/MaxReturn -103.048 MetaTest/__unnamed_task__/MinReturn -244.837 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 46.0655 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 952000 ------------------------------------------------- ----------- 2025-04-06 05:17:25 | [pearl_trainer] epoch #456 | Training... 2025-04-06 05:20:24 | [pearl_trainer] epoch #456 | Evaluating... 2025-04-06 05:20:24 | [pearl_trainer] epoch #456 | Sampling for adapation and meta-testing... 2025-04-06 05:24:57 | [pearl_trainer] epoch #456 | Finished meta-testing... 2025-04-06 05:24:57 | [pearl_trainer] epoch #456 | Saving snapshot... 2025-04-06 05:24:59 | [pearl_trainer] epoch #456 | Saved 2025-04-06 05:24:59 | [pearl_trainer] epoch #456 | Time 219362.34 s 2025-04-06 05:24:59 | [pearl_trainer] epoch #456 | EpochTime 502.97 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -235.428 MetaTest/Average/AverageReturn -235.428 MetaTest/Average/Iteration 456 MetaTest/Average/MaxReturn -163.462 MetaTest/Average/MinReturn -307.666 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 49.6017 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -235.428 MetaTest/__unnamed_task__/AverageReturn -235.428 MetaTest/__unnamed_task__/Iteration 456 MetaTest/__unnamed_task__/MaxReturn -163.462 MetaTest/__unnamed_task__/MinReturn -307.666 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 49.6017 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 954000 ------------------------------------------------- ----------- 2025-04-06 05:25:47 | [pearl_trainer] epoch #457 | Training... 2025-04-06 05:28:31 | [pearl_trainer] epoch #457 | Evaluating... 2025-04-06 05:28:31 | [pearl_trainer] epoch #457 | Sampling for adapation and meta-testing... 2025-04-06 05:32:51 | [pearl_trainer] epoch #457 | Finished meta-testing... 2025-04-06 05:32:51 | [pearl_trainer] epoch #457 | Saving snapshot... 2025-04-06 05:32:53 | [pearl_trainer] epoch #457 | Saved 2025-04-06 05:32:53 | [pearl_trainer] epoch #457 | Time 219836.20 s 2025-04-06 05:32:53 | [pearl_trainer] epoch #457 | EpochTime 473.86 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -215.703 MetaTest/Average/AverageReturn -215.703 MetaTest/Average/Iteration 457 MetaTest/Average/MaxReturn -161.111 MetaTest/Average/MinReturn -257.399 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 32.0271 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -215.703 MetaTest/__unnamed_task__/AverageReturn -215.703 MetaTest/__unnamed_task__/Iteration 457 MetaTest/__unnamed_task__/MaxReturn -161.111 MetaTest/__unnamed_task__/MinReturn -257.399 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 32.0271 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 956000 ------------------------------------------------- ----------- 2025-04-06 05:33:40 | [pearl_trainer] epoch #458 | Training... 2025-04-06 05:36:27 | [pearl_trainer] epoch #458 | Evaluating... 2025-04-06 05:36:27 | [pearl_trainer] epoch #458 | Sampling for adapation and meta-testing... 2025-04-06 05:40:49 | [pearl_trainer] epoch #458 | Finished meta-testing... 2025-04-06 05:40:49 | [pearl_trainer] epoch #458 | Saving snapshot... 2025-04-06 05:40:51 | [pearl_trainer] epoch #458 | Saved 2025-04-06 05:40:51 | [pearl_trainer] epoch #458 | Time 220314.26 s 2025-04-06 05:40:51 | [pearl_trainer] epoch #458 | EpochTime 478.06 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -233.001 MetaTest/Average/AverageReturn -233.001 MetaTest/Average/Iteration 458 MetaTest/Average/MaxReturn -190.146 MetaTest/Average/MinReturn -260.878 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 27.242 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -233.001 MetaTest/__unnamed_task__/AverageReturn -233.001 MetaTest/__unnamed_task__/Iteration 458 MetaTest/__unnamed_task__/MaxReturn -190.146 MetaTest/__unnamed_task__/MinReturn -260.878 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 27.242 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 958000 ------------------------------------------------- ---------- 2025-04-06 05:41:41 | [pearl_trainer] epoch #459 | Training... 2025-04-06 05:44:27 | [pearl_trainer] epoch #459 | Evaluating... 2025-04-06 05:44:27 | [pearl_trainer] epoch #459 | Sampling for adapation and meta-testing... 2025-04-06 05:49:09 | [pearl_trainer] epoch #459 | Finished meta-testing... 2025-04-06 05:49:09 | [pearl_trainer] epoch #459 | Saving snapshot... 2025-04-06 05:49:11 | [pearl_trainer] epoch #459 | Saved 2025-04-06 05:49:11 | [pearl_trainer] epoch #459 | Time 220814.30 s 2025-04-06 05:49:11 | [pearl_trainer] epoch #459 | EpochTime 500.04 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -229.311 MetaTest/Average/AverageReturn -229.311 MetaTest/Average/Iteration 459 MetaTest/Average/MaxReturn -190.726 MetaTest/Average/MinReturn -262.011 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 27.1733 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -229.311 MetaTest/__unnamed_task__/AverageReturn -229.311 MetaTest/__unnamed_task__/Iteration 459 MetaTest/__unnamed_task__/MaxReturn -190.726 MetaTest/__unnamed_task__/MinReturn -262.011 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 27.1733 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 960000 ------------------------------------------------- ----------- 2025-04-06 05:49:57 | [pearl_trainer] epoch #460 | Training... 2025-04-06 05:52:42 | [pearl_trainer] epoch #460 | Evaluating... 2025-04-06 05:52:42 | [pearl_trainer] epoch #460 | Sampling for adapation and meta-testing... 2025-04-06 05:57:23 | [pearl_trainer] epoch #460 | Finished meta-testing... 2025-04-06 05:57:23 | [pearl_trainer] epoch #460 | Saving snapshot... 2025-04-06 05:57:25 | [pearl_trainer] epoch #460 | Saved 2025-04-06 05:57:25 | [pearl_trainer] epoch #460 | Time 221308.24 s 2025-04-06 05:57:25 | [pearl_trainer] epoch #460 | EpochTime 493.93 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -278.648 MetaTest/Average/AverageReturn -278.648 MetaTest/Average/Iteration 460 MetaTest/Average/MaxReturn -251.655 MetaTest/Average/MinReturn -312.43 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 20.2186 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -278.648 MetaTest/__unnamed_task__/AverageReturn -278.648 MetaTest/__unnamed_task__/Iteration 460 MetaTest/__unnamed_task__/MaxReturn -251.655 MetaTest/__unnamed_task__/MinReturn -312.43 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 20.2186 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 962000 ------------------------------------------------- ----------- 2025-04-06 05:58:13 | [pearl_trainer] epoch #461 | Training... 2025-04-06 06:00:57 | [pearl_trainer] epoch #461 | Evaluating... 2025-04-06 06:00:57 | [pearl_trainer] epoch #461 | Sampling for adapation and meta-testing... 2025-04-06 06:05:16 | [pearl_trainer] epoch #461 | Finished meta-testing... 2025-04-06 06:05:16 | [pearl_trainer] epoch #461 | Saving snapshot... 2025-04-06 06:05:18 | [pearl_trainer] epoch #461 | Saved 2025-04-06 06:05:18 | [pearl_trainer] epoch #461 | Time 221781.32 s 2025-04-06 06:05:18 | [pearl_trainer] epoch #461 | EpochTime 473.09 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -223.871 MetaTest/Average/AverageReturn -223.871 MetaTest/Average/Iteration 461 MetaTest/Average/MaxReturn -176.226 MetaTest/Average/MinReturn -250.869 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 28.9233 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -223.871 MetaTest/__unnamed_task__/AverageReturn -223.871 MetaTest/__unnamed_task__/Iteration 461 MetaTest/__unnamed_task__/MaxReturn -176.226 MetaTest/__unnamed_task__/MinReturn -250.869 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 28.9233 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 964000 ------------------------------------------------- ----------- 2025-04-06 06:06:04 | [pearl_trainer] epoch #462 | Training... 2025-04-06 06:08:35 | [pearl_trainer] epoch #462 | Evaluating... 2025-04-06 06:08:35 | [pearl_trainer] epoch #462 | Sampling for adapation and meta-testing... 2025-04-06 06:12:53 | [pearl_trainer] epoch #462 | Finished meta-testing... 2025-04-06 06:12:53 | [pearl_trainer] epoch #462 | Saving snapshot... 2025-04-06 06:12:54 | [pearl_trainer] epoch #462 | Saved 2025-04-06 06:12:54 | [pearl_trainer] epoch #462 | Time 222238.13 s 2025-04-06 06:12:54 | [pearl_trainer] epoch #462 | EpochTime 456.80 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -283.914 MetaTest/Average/AverageReturn -283.914 MetaTest/Average/Iteration 462 MetaTest/Average/MaxReturn -222.887 MetaTest/Average/MinReturn -368.389 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 51.3136 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -283.914 MetaTest/__unnamed_task__/AverageReturn -283.914 MetaTest/__unnamed_task__/Iteration 462 MetaTest/__unnamed_task__/MaxReturn -222.887 MetaTest/__unnamed_task__/MinReturn -368.389 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 51.3136 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 966000 ------------------------------------------------- ----------- 2025-04-06 06:13:42 | [pearl_trainer] epoch #463 | Training... 2025-04-06 06:16:09 | [pearl_trainer] epoch #463 | Evaluating... 2025-04-06 06:16:09 | [pearl_trainer] epoch #463 | Sampling for adapation and meta-testing... 2025-04-06 06:20:29 | [pearl_trainer] epoch #463 | Finished meta-testing... 2025-04-06 06:20:29 | [pearl_trainer] epoch #463 | Saving snapshot... 2025-04-06 06:20:30 | [pearl_trainer] epoch #463 | Saved 2025-04-06 06:20:30 | [pearl_trainer] epoch #463 | Time 222693.81 s 2025-04-06 06:20:30 | [pearl_trainer] epoch #463 | EpochTime 455.68 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -296.551 MetaTest/Average/AverageReturn -296.551 MetaTest/Average/Iteration 463 MetaTest/Average/MaxReturn -277.134 MetaTest/Average/MinReturn -314.47 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 12.7873 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -296.551 MetaTest/__unnamed_task__/AverageReturn -296.551 MetaTest/__unnamed_task__/Iteration 463 MetaTest/__unnamed_task__/MaxReturn -277.134 MetaTest/__unnamed_task__/MinReturn -314.47 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 12.7873 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 968000 ------------------------------------------------- ----------- 2025-04-06 06:21:22 | [pearl_trainer] epoch #464 | Training... 2025-04-06 06:24:04 | [pearl_trainer] epoch #464 | Evaluating... 2025-04-06 06:24:04 | [pearl_trainer] epoch #464 | Sampling for adapation and meta-testing... 2025-04-06 06:28:27 | [pearl_trainer] epoch #464 | Finished meta-testing... 2025-04-06 06:28:27 | [pearl_trainer] epoch #464 | Saving snapshot... 2025-04-06 06:28:28 | [pearl_trainer] epoch #464 | Saved 2025-04-06 06:28:28 | [pearl_trainer] epoch #464 | Time 223172.17 s 2025-04-06 06:28:28 | [pearl_trainer] epoch #464 | EpochTime 478.36 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -285.023 MetaTest/Average/AverageReturn -285.023 MetaTest/Average/Iteration 464 MetaTest/Average/MaxReturn -225.262 MetaTest/Average/MinReturn -346.242 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 38.3022 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -285.023 MetaTest/__unnamed_task__/AverageReturn -285.023 MetaTest/__unnamed_task__/Iteration 464 MetaTest/__unnamed_task__/MaxReturn -225.262 MetaTest/__unnamed_task__/MinReturn -346.242 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 38.3022 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 970000 ------------------------------------------------- ----------- 2025-04-06 06:29:14 | [pearl_trainer] epoch #465 | Training... 2025-04-06 06:31:41 | [pearl_trainer] epoch #465 | Evaluating... 2025-04-06 06:31:41 | [pearl_trainer] epoch #465 | Sampling for adapation and meta-testing... 2025-04-06 06:36:09 | [pearl_trainer] epoch #465 | Finished meta-testing... 2025-04-06 06:36:09 | [pearl_trainer] epoch #465 | Saving snapshot... 2025-04-06 06:36:11 | [pearl_trainer] epoch #465 | Saved 2025-04-06 06:36:11 | [pearl_trainer] epoch #465 | Time 223634.20 s 2025-04-06 06:36:11 | [pearl_trainer] epoch #465 | EpochTime 462.03 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -294.989 MetaTest/Average/AverageReturn -294.989 MetaTest/Average/Iteration 465 MetaTest/Average/MaxReturn -231.727 MetaTest/Average/MinReturn -331.601 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 40.8289 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -294.989 MetaTest/__unnamed_task__/AverageReturn -294.989 MetaTest/__unnamed_task__/Iteration 465 MetaTest/__unnamed_task__/MaxReturn -231.727 MetaTest/__unnamed_task__/MinReturn -331.601 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 40.8289 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 972000 ------------------------------------------------- ----------- 2025-04-06 06:36:57 | [pearl_trainer] epoch #466 | Training... 2025-04-06 06:39:46 | [pearl_trainer] epoch #466 | Evaluating... 2025-04-06 06:39:46 | [pearl_trainer] epoch #466 | Sampling for adapation and meta-testing... 2025-04-06 06:44:09 | [pearl_trainer] epoch #466 | Finished meta-testing... 2025-04-06 06:44:09 | [pearl_trainer] epoch #466 | Saving snapshot... 2025-04-06 06:44:10 | [pearl_trainer] epoch #466 | Saved 2025-04-06 06:44:10 | [pearl_trainer] epoch #466 | Time 224114.09 s 2025-04-06 06:44:10 | [pearl_trainer] epoch #466 | EpochTime 479.88 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -302.732 MetaTest/Average/AverageReturn -302.732 MetaTest/Average/Iteration 466 MetaTest/Average/MaxReturn -274.807 MetaTest/Average/MinReturn -324.411 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 17.2268 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -302.732 MetaTest/__unnamed_task__/AverageReturn -302.732 MetaTest/__unnamed_task__/Iteration 466 MetaTest/__unnamed_task__/MaxReturn -274.807 MetaTest/__unnamed_task__/MinReturn -324.411 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 17.2268 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 974000 ------------------------------------------------- ----------- 2025-04-06 06:44:57 | [pearl_trainer] epoch #467 | Training... 2025-04-06 06:47:54 | [pearl_trainer] epoch #467 | Evaluating... 2025-04-06 06:47:54 | [pearl_trainer] epoch #467 | Sampling for adapation and meta-testing... 2025-04-06 06:52:08 | [pearl_trainer] epoch #467 | Finished meta-testing... 2025-04-06 06:52:08 | [pearl_trainer] epoch #467 | Saving snapshot... 2025-04-06 06:52:09 | [pearl_trainer] epoch #467 | Saved 2025-04-06 06:52:09 | [pearl_trainer] epoch #467 | Time 224592.85 s 2025-04-06 06:52:09 | [pearl_trainer] epoch #467 | EpochTime 478.76 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -281.259 MetaTest/Average/AverageReturn -281.259 MetaTest/Average/Iteration 467 MetaTest/Average/MaxReturn -197.114 MetaTest/Average/MinReturn -326.752 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 51.012 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -281.259 MetaTest/__unnamed_task__/AverageReturn -281.259 MetaTest/__unnamed_task__/Iteration 467 MetaTest/__unnamed_task__/MaxReturn -197.114 MetaTest/__unnamed_task__/MinReturn -326.752 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 51.012 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 976000 ------------------------------------------------- ---------- 2025-04-06 06:52:57 | [pearl_trainer] epoch #468 | Training... 2025-04-06 06:55:47 | [pearl_trainer] epoch #468 | Evaluating... 2025-04-06 06:55:47 | [pearl_trainer] epoch #468 | Sampling for adapation and meta-testing... 2025-04-06 07:00:07 | [pearl_trainer] epoch #468 | Finished meta-testing... 2025-04-06 07:00:07 | [pearl_trainer] epoch #468 | Saving snapshot... 2025-04-06 07:00:09 | [pearl_trainer] epoch #468 | Saved 2025-04-06 07:00:09 | [pearl_trainer] epoch #468 | Time 225072.29 s 2025-04-06 07:00:09 | [pearl_trainer] epoch #468 | EpochTime 479.44 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -316.349 MetaTest/Average/AverageReturn -316.349 MetaTest/Average/Iteration 468 MetaTest/Average/MaxReturn -274.865 MetaTest/Average/MinReturn -339.904 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 23.5125 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -316.349 MetaTest/__unnamed_task__/AverageReturn -316.349 MetaTest/__unnamed_task__/Iteration 468 MetaTest/__unnamed_task__/MaxReturn -274.865 MetaTest/__unnamed_task__/MinReturn -339.904 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 23.5125 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 978000 ------------------------------------------------- ----------- 2025-04-06 07:00:56 | [pearl_trainer] epoch #469 | Training... 2025-04-06 07:03:39 | [pearl_trainer] epoch #469 | Evaluating... 2025-04-06 07:03:39 | [pearl_trainer] epoch #469 | Sampling for adapation and meta-testing... 2025-04-06 07:07:59 | [pearl_trainer] epoch #469 | Finished meta-testing... 2025-04-06 07:07:59 | [pearl_trainer] epoch #469 | Saving snapshot... 2025-04-06 07:08:00 | [pearl_trainer] epoch #469 | Saved 2025-04-06 07:08:00 | [pearl_trainer] epoch #469 | Time 225544.01 s 2025-04-06 07:08:00 | [pearl_trainer] epoch #469 | EpochTime 471.71 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -272.49 MetaTest/Average/AverageReturn -272.49 MetaTest/Average/Iteration 469 MetaTest/Average/MaxReturn -237.096 MetaTest/Average/MinReturn -309.32 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.4082 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -272.49 MetaTest/__unnamed_task__/AverageReturn -272.49 MetaTest/__unnamed_task__/Iteration 469 MetaTest/__unnamed_task__/MaxReturn -237.096 MetaTest/__unnamed_task__/MinReturn -309.32 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.4082 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 980000 ------------------------------------------------- ----------- 2025-04-06 07:08:48 | [pearl_trainer] epoch #470 | Training... 2025-04-06 07:11:39 | [pearl_trainer] epoch #470 | Evaluating... 2025-04-06 07:11:39 | [pearl_trainer] epoch #470 | Sampling for adapation and meta-testing... 2025-04-06 07:15:45 | [pearl_trainer] epoch #470 | Finished meta-testing... 2025-04-06 07:15:45 | [pearl_trainer] epoch #470 | Saving snapshot... 2025-04-06 07:15:47 | [pearl_trainer] epoch #470 | Saved 2025-04-06 07:15:47 | [pearl_trainer] epoch #470 | Time 226010.25 s 2025-04-06 07:15:47 | [pearl_trainer] epoch #470 | EpochTime 466.24 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -282.611 MetaTest/Average/AverageReturn -282.611 MetaTest/Average/Iteration 470 MetaTest/Average/MaxReturn -188.161 MetaTest/Average/MinReturn -339.063 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 51.9697 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -282.611 MetaTest/__unnamed_task__/AverageReturn -282.611 MetaTest/__unnamed_task__/Iteration 470 MetaTest/__unnamed_task__/MaxReturn -188.161 MetaTest/__unnamed_task__/MinReturn -339.063 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 51.9697 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 982000 ------------------------------------------------- ----------- 2025-04-06 07:16:32 | [pearl_trainer] epoch #471 | Training... 2025-04-06 07:19:34 | [pearl_trainer] epoch #471 | Evaluating... 2025-04-06 07:19:34 | [pearl_trainer] epoch #471 | Sampling for adapation and meta-testing... 2025-04-06 07:23:39 | [pearl_trainer] epoch #471 | Finished meta-testing... 2025-04-06 07:23:39 | [pearl_trainer] epoch #471 | Saving snapshot... 2025-04-06 07:23:41 | [pearl_trainer] epoch #471 | Saved 2025-04-06 07:23:41 | [pearl_trainer] epoch #471 | Time 226484.43 s 2025-04-06 07:23:41 | [pearl_trainer] epoch #471 | EpochTime 474.18 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -313.287 MetaTest/Average/AverageReturn -313.287 MetaTest/Average/Iteration 471 MetaTest/Average/MaxReturn -256.61 MetaTest/Average/MinReturn -379.962 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 47.2983 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -313.287 MetaTest/__unnamed_task__/AverageReturn -313.287 MetaTest/__unnamed_task__/Iteration 471 MetaTest/__unnamed_task__/MaxReturn -256.61 MetaTest/__unnamed_task__/MinReturn -379.962 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 47.2983 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 984000 ------------------------------------------------- ----------- 2025-04-06 07:24:23 | [pearl_trainer] epoch #472 | Training... 2025-04-06 07:27:32 | [pearl_trainer] epoch #472 | Evaluating... 2025-04-06 07:27:32 | [pearl_trainer] epoch #472 | Sampling for adapation and meta-testing... 2025-04-06 07:31:48 | [pearl_trainer] epoch #472 | Finished meta-testing... 2025-04-06 07:31:48 | [pearl_trainer] epoch #472 | Saving snapshot... 2025-04-06 07:31:49 | [pearl_trainer] epoch #472 | Saved 2025-04-06 07:31:49 | [pearl_trainer] epoch #472 | Time 226972.64 s 2025-04-06 07:31:49 | [pearl_trainer] epoch #472 | EpochTime 488.21 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -255.247 MetaTest/Average/AverageReturn -255.247 MetaTest/Average/Iteration 472 MetaTest/Average/MaxReturn -177.77 MetaTest/Average/MinReturn -306.847 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 42.6179 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -255.247 MetaTest/__unnamed_task__/AverageReturn -255.247 MetaTest/__unnamed_task__/Iteration 472 MetaTest/__unnamed_task__/MaxReturn -177.77 MetaTest/__unnamed_task__/MinReturn -306.847 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 42.6179 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 986000 ------------------------------------------------- ----------- 2025-04-06 07:32:39 | [pearl_trainer] epoch #473 | Training... 2025-04-06 07:35:45 | [pearl_trainer] epoch #473 | Evaluating... 2025-04-06 07:35:45 | [pearl_trainer] epoch #473 | Sampling for adapation and meta-testing... 2025-04-06 07:39:53 | [pearl_trainer] epoch #473 | Finished meta-testing... 2025-04-06 07:39:53 | [pearl_trainer] epoch #473 | Saving snapshot... 2025-04-06 07:39:55 | [pearl_trainer] epoch #473 | Saved 2025-04-06 07:39:55 | [pearl_trainer] epoch #473 | Time 227458.27 s 2025-04-06 07:39:55 | [pearl_trainer] epoch #473 | EpochTime 485.63 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -269.465 MetaTest/Average/AverageReturn -269.465 MetaTest/Average/Iteration 473 MetaTest/Average/MaxReturn -193.594 MetaTest/Average/MinReturn -387.382 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 68.4006 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -269.465 MetaTest/__unnamed_task__/AverageReturn -269.465 MetaTest/__unnamed_task__/Iteration 473 MetaTest/__unnamed_task__/MaxReturn -193.594 MetaTest/__unnamed_task__/MinReturn -387.382 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 68.4006 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 988000 ------------------------------------------------- ----------- 2025-04-06 07:40:46 | [pearl_trainer] epoch #474 | Training... 2025-04-06 07:43:54 | [pearl_trainer] epoch #474 | Evaluating... 2025-04-06 07:43:54 | [pearl_trainer] epoch #474 | Sampling for adapation and meta-testing... 2025-04-06 07:48:57 | [pearl_trainer] epoch #474 | Finished meta-testing... 2025-04-06 07:48:57 | [pearl_trainer] epoch #474 | Saving snapshot... 2025-04-06 07:48:58 | [pearl_trainer] epoch #474 | Saved 2025-04-06 07:48:58 | [pearl_trainer] epoch #474 | Time 228002.16 s 2025-04-06 07:48:58 | [pearl_trainer] epoch #474 | EpochTime 543.89 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -201.095 MetaTest/Average/AverageReturn -201.095 MetaTest/Average/Iteration 474 MetaTest/Average/MaxReturn -165.026 MetaTest/Average/MinReturn -235.745 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 27.2286 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -201.095 MetaTest/__unnamed_task__/AverageReturn -201.095 MetaTest/__unnamed_task__/Iteration 474 MetaTest/__unnamed_task__/MaxReturn -165.026 MetaTest/__unnamed_task__/MinReturn -235.745 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 27.2286 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 990000 ------------------------------------------------- ----------- 2025-04-06 07:49:43 | [pearl_trainer] epoch #475 | Training... 2025-04-06 07:52:32 | [pearl_trainer] epoch #475 | Evaluating... 2025-04-06 07:52:32 | [pearl_trainer] epoch #475 | Sampling for adapation and meta-testing... 2025-04-06 07:57:25 | [pearl_trainer] epoch #475 | Finished meta-testing... 2025-04-06 07:57:25 | [pearl_trainer] epoch #475 | Saving snapshot... 2025-04-06 07:57:27 | [pearl_trainer] epoch #475 | Saved 2025-04-06 07:57:27 | [pearl_trainer] epoch #475 | Time 228510.69 s 2025-04-06 07:57:27 | [pearl_trainer] epoch #475 | EpochTime 508.53 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -182.672 MetaTest/Average/AverageReturn -182.672 MetaTest/Average/Iteration 475 MetaTest/Average/MaxReturn -125.258 MetaTest/Average/MinReturn -223.881 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 36.8104 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -182.672 MetaTest/__unnamed_task__/AverageReturn -182.672 MetaTest/__unnamed_task__/Iteration 475 MetaTest/__unnamed_task__/MaxReturn -125.258 MetaTest/__unnamed_task__/MinReturn -223.881 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 36.8104 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 992000 ------------------------------------------------- ----------- 2025-04-06 07:58:18 | [pearl_trainer] epoch #476 | Training... 2025-04-06 08:01:06 | [pearl_trainer] epoch #476 | Evaluating... 2025-04-06 08:01:06 | [pearl_trainer] epoch #476 | Sampling for adapation and meta-testing... 2025-04-06 08:05:57 | [pearl_trainer] epoch #476 | Finished meta-testing... 2025-04-06 08:05:57 | [pearl_trainer] epoch #476 | Saving snapshot... 2025-04-06 08:05:58 | [pearl_trainer] epoch #476 | Saved 2025-04-06 08:05:58 | [pearl_trainer] epoch #476 | Time 229021.52 s 2025-04-06 08:05:58 | [pearl_trainer] epoch #476 | EpochTime 510.83 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -189.317 MetaTest/Average/AverageReturn -189.317 MetaTest/Average/Iteration 476 MetaTest/Average/MaxReturn -141.991 MetaTest/Average/MinReturn -282.154 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 48.7006 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -189.317 MetaTest/__unnamed_task__/AverageReturn -189.317 MetaTest/__unnamed_task__/Iteration 476 MetaTest/__unnamed_task__/MaxReturn -141.991 MetaTest/__unnamed_task__/MinReturn -282.154 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 48.7006 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 994000 ------------------------------------------------- ----------- 2025-04-06 08:06:48 | [pearl_trainer] epoch #477 | Training... 2025-04-06 08:09:36 | [pearl_trainer] epoch #477 | Evaluating... 2025-04-06 08:09:36 | [pearl_trainer] epoch #477 | Sampling for adapation and meta-testing... 2025-04-06 08:14:30 | [pearl_trainer] epoch #477 | Finished meta-testing... 2025-04-06 08:14:30 | [pearl_trainer] epoch #477 | Saving snapshot... 2025-04-06 08:14:31 | [pearl_trainer] epoch #477 | Saved 2025-04-06 08:14:31 | [pearl_trainer] epoch #477 | Time 229534.80 s 2025-04-06 08:14:31 | [pearl_trainer] epoch #477 | EpochTime 513.28 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -153.897 MetaTest/Average/AverageReturn -153.897 MetaTest/Average/Iteration 477 MetaTest/Average/MaxReturn -100.866 MetaTest/Average/MinReturn -236.62 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 49.634 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -153.897 MetaTest/__unnamed_task__/AverageReturn -153.897 MetaTest/__unnamed_task__/Iteration 477 MetaTest/__unnamed_task__/MaxReturn -100.866 MetaTest/__unnamed_task__/MinReturn -236.62 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 49.634 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 996000 ------------------------------------------------- ---------- 2025-04-06 08:15:22 | [pearl_trainer] epoch #478 | Training... 2025-04-06 08:18:13 | [pearl_trainer] epoch #478 | Evaluating... 2025-04-06 08:18:13 | [pearl_trainer] epoch #478 | Sampling for adapation and meta-testing... 2025-04-06 08:22:58 | [pearl_trainer] epoch #478 | Finished meta-testing... 2025-04-06 08:22:58 | [pearl_trainer] epoch #478 | Saving snapshot... 2025-04-06 08:22:59 | [pearl_trainer] epoch #478 | Saved 2025-04-06 08:22:59 | [pearl_trainer] epoch #478 | Time 230042.72 s 2025-04-06 08:22:59 | [pearl_trainer] epoch #478 | EpochTime 507.93 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -152.049 MetaTest/Average/AverageReturn -152.049 MetaTest/Average/Iteration 478 MetaTest/Average/MaxReturn -104.648 MetaTest/Average/MinReturn -202.149 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 32.8671 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -152.049 MetaTest/__unnamed_task__/AverageReturn -152.049 MetaTest/__unnamed_task__/Iteration 478 MetaTest/__unnamed_task__/MaxReturn -104.648 MetaTest/__unnamed_task__/MinReturn -202.149 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 32.8671 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 998000 ------------------------------------------------- ----------- 2025-04-06 08:23:47 | [pearl_trainer] epoch #479 | Training... 2025-04-06 08:26:31 | [pearl_trainer] epoch #479 | Evaluating... 2025-04-06 08:26:31 | [pearl_trainer] epoch #479 | Sampling for adapation and meta-testing... 2025-04-06 08:30:51 | [pearl_trainer] epoch #479 | Finished meta-testing... 2025-04-06 08:30:51 | [pearl_trainer] epoch #479 | Saving snapshot... 2025-04-06 08:30:53 | [pearl_trainer] epoch #479 | Saved 2025-04-06 08:30:53 | [pearl_trainer] epoch #479 | Time 230516.45 s 2025-04-06 08:30:53 | [pearl_trainer] epoch #479 | EpochTime 473.72 s ------------------------------------------------- --------- MetaTest/Average/AverageDiscountedReturn -299.723 MetaTest/Average/AverageReturn -299.723 MetaTest/Average/Iteration 479 MetaTest/Average/MaxReturn -236.15 MetaTest/Average/MinReturn -370.839 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 47.2325 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -299.723 MetaTest/__unnamed_task__/AverageReturn -299.723 MetaTest/__unnamed_task__/Iteration 479 MetaTest/__unnamed_task__/MaxReturn -236.15 MetaTest/__unnamed_task__/MinReturn -370.839 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 47.2325 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1e+06 ------------------------------------------------- --------- 2025-04-06 08:31:39 | [pearl_trainer] epoch #480 | Training... 2025-04-06 08:34:29 | [pearl_trainer] epoch #480 | Evaluating... 2025-04-06 08:34:29 | [pearl_trainer] epoch #480 | Sampling for adapation and meta-testing... 2025-04-06 08:39:08 | [pearl_trainer] epoch #480 | Finished meta-testing... 2025-04-06 08:39:08 | [pearl_trainer] epoch #480 | Saving snapshot... 2025-04-06 08:39:09 | [pearl_trainer] epoch #480 | Saved 2025-04-06 08:39:09 | [pearl_trainer] epoch #480 | Time 231012.38 s 2025-04-06 08:39:09 | [pearl_trainer] epoch #480 | EpochTime 495.93 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -236.836 MetaTest/Average/AverageReturn -236.836 MetaTest/Average/Iteration 480 MetaTest/Average/MaxReturn -98.7432 MetaTest/Average/MinReturn -317.801 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 86.1842 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -236.836 MetaTest/__unnamed_task__/AverageReturn -236.836 MetaTest/__unnamed_task__/Iteration 480 MetaTest/__unnamed_task__/MaxReturn -98.7432 MetaTest/__unnamed_task__/MinReturn -317.801 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 86.1842 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.002e+06 ------------------------------------------------- ------------ 2025-04-06 08:39:53 | [pearl_trainer] epoch #481 | Training... 2025-04-06 08:42:52 | [pearl_trainer] epoch #481 | Evaluating... 2025-04-06 08:42:52 | [pearl_trainer] epoch #481 | Sampling for adapation and meta-testing... 2025-04-06 08:47:48 | [pearl_trainer] epoch #481 | Finished meta-testing... 2025-04-06 08:47:48 | [pearl_trainer] epoch #481 | Saving snapshot... 2025-04-06 08:47:50 | [pearl_trainer] epoch #481 | Saved 2025-04-06 08:47:50 | [pearl_trainer] epoch #481 | Time 231533.25 s 2025-04-06 08:47:50 | [pearl_trainer] epoch #481 | EpochTime 520.88 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -210.572 MetaTest/Average/AverageReturn -210.572 MetaTest/Average/Iteration 481 MetaTest/Average/MaxReturn -185.394 MetaTest/Average/MinReturn -229.989 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 17.7285 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -210.572 MetaTest/__unnamed_task__/AverageReturn -210.572 MetaTest/__unnamed_task__/Iteration 481 MetaTest/__unnamed_task__/MaxReturn -185.394 MetaTest/__unnamed_task__/MinReturn -229.989 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 17.7285 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.004e+06 ------------------------------------------------- ------------ 2025-04-06 08:48:40 | [pearl_trainer] epoch #482 | Training... 2025-04-06 08:51:28 | [pearl_trainer] epoch #482 | Evaluating... 2025-04-06 08:51:28 | [pearl_trainer] epoch #482 | Sampling for adapation and meta-testing... 2025-04-06 08:56:31 | [pearl_trainer] epoch #482 | Finished meta-testing... 2025-04-06 08:56:31 | [pearl_trainer] epoch #482 | Saving snapshot... 2025-04-06 08:56:32 | [pearl_trainer] epoch #482 | Saved 2025-04-06 08:56:32 | [pearl_trainer] epoch #482 | Time 232055.73 s 2025-04-06 08:56:32 | [pearl_trainer] epoch #482 | EpochTime 522.48 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -201.756 MetaTest/Average/AverageReturn -201.756 MetaTest/Average/Iteration 482 MetaTest/Average/MaxReturn -171.219 MetaTest/Average/MinReturn -266.195 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 34.2204 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -201.756 MetaTest/__unnamed_task__/AverageReturn -201.756 MetaTest/__unnamed_task__/Iteration 482 MetaTest/__unnamed_task__/MaxReturn -171.219 MetaTest/__unnamed_task__/MinReturn -266.195 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 34.2204 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.006e+06 ------------------------------------------------- ------------ 2025-04-06 08:57:22 | [pearl_trainer] epoch #483 | Training... 2025-04-06 09:00:17 | [pearl_trainer] epoch #483 | Evaluating... 2025-04-06 09:00:17 | [pearl_trainer] epoch #483 | Sampling for adapation and meta-testing... 2025-04-06 09:04:54 | [pearl_trainer] epoch #483 | Finished meta-testing... 2025-04-06 09:04:54 | [pearl_trainer] epoch #483 | Saving snapshot... 2025-04-06 09:04:55 | [pearl_trainer] epoch #483 | Saved 2025-04-06 09:04:55 | [pearl_trainer] epoch #483 | Time 232559.04 s 2025-04-06 09:04:55 | [pearl_trainer] epoch #483 | EpochTime 503.30 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -249.972 MetaTest/Average/AverageReturn -249.972 MetaTest/Average/Iteration 483 MetaTest/Average/MaxReturn -176.428 MetaTest/Average/MinReturn -308.167 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 52.0049 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -249.972 MetaTest/__unnamed_task__/AverageReturn -249.972 MetaTest/__unnamed_task__/Iteration 483 MetaTest/__unnamed_task__/MaxReturn -176.428 MetaTest/__unnamed_task__/MinReturn -308.167 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 52.0049 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.008e+06 ------------------------------------------------- ------------ 2025-04-06 09:05:47 | [pearl_trainer] epoch #484 | Training... 2025-04-06 09:08:31 | [pearl_trainer] epoch #484 | Evaluating... 2025-04-06 09:08:31 | [pearl_trainer] epoch #484 | Sampling for adapation and meta-testing... 2025-04-06 09:13:21 | [pearl_trainer] epoch #484 | Finished meta-testing... 2025-04-06 09:13:21 | [pearl_trainer] epoch #484 | Saving snapshot... 2025-04-06 09:13:22 | [pearl_trainer] epoch #484 | Saved 2025-04-06 09:13:22 | [pearl_trainer] epoch #484 | Time 233065.86 s 2025-04-06 09:13:22 | [pearl_trainer] epoch #484 | EpochTime 506.82 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -248.975 MetaTest/Average/AverageReturn -248.975 MetaTest/Average/Iteration 484 MetaTest/Average/MaxReturn -203.593 MetaTest/Average/MinReturn -275.656 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 26.3632 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -248.975 MetaTest/__unnamed_task__/AverageReturn -248.975 MetaTest/__unnamed_task__/Iteration 484 MetaTest/__unnamed_task__/MaxReturn -203.593 MetaTest/__unnamed_task__/MinReturn -275.656 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 26.3632 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.01e+06 ------------------------------------------------- ----------- 2025-04-06 09:14:15 | [pearl_trainer] epoch #485 | Training... 2025-04-06 09:17:01 | [pearl_trainer] epoch #485 | Evaluating... 2025-04-06 09:17:01 | [pearl_trainer] epoch #485 | Sampling for adapation and meta-testing... 2025-04-06 09:21:36 | [pearl_trainer] epoch #485 | Finished meta-testing... 2025-04-06 09:21:36 | [pearl_trainer] epoch #485 | Saving snapshot... 2025-04-06 09:21:37 | [pearl_trainer] epoch #485 | Saved 2025-04-06 09:21:37 | [pearl_trainer] epoch #485 | Time 233561.16 s 2025-04-06 09:21:37 | [pearl_trainer] epoch #485 | EpochTime 495.29 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -258.34 MetaTest/Average/AverageReturn -258.34 MetaTest/Average/Iteration 485 MetaTest/Average/MaxReturn -190.587 MetaTest/Average/MinReturn -306.277 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 44.8811 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -258.34 MetaTest/__unnamed_task__/AverageReturn -258.34 MetaTest/__unnamed_task__/Iteration 485 MetaTest/__unnamed_task__/MaxReturn -190.587 MetaTest/__unnamed_task__/MinReturn -306.277 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 44.8811 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.012e+06 ------------------------------------------------- ------------ 2025-04-06 09:22:27 | [pearl_trainer] epoch #486 | Training... 2025-04-06 09:25:13 | [pearl_trainer] epoch #486 | Evaluating... 2025-04-06 09:25:13 | [pearl_trainer] epoch #486 | Sampling for adapation and meta-testing... 2025-04-06 09:29:58 | [pearl_trainer] epoch #486 | Finished meta-testing... 2025-04-06 09:29:58 | [pearl_trainer] epoch #486 | Saving snapshot... 2025-04-06 09:29:59 | [pearl_trainer] epoch #486 | Saved 2025-04-06 09:29:59 | [pearl_trainer] epoch #486 | Time 234062.81 s 2025-04-06 09:29:59 | [pearl_trainer] epoch #486 | EpochTime 501.65 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -255.911 MetaTest/Average/AverageReturn -255.911 MetaTest/Average/Iteration 486 MetaTest/Average/MaxReturn -231.525 MetaTest/Average/MinReturn -322.517 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 33.9689 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -255.911 MetaTest/__unnamed_task__/AverageReturn -255.911 MetaTest/__unnamed_task__/Iteration 486 MetaTest/__unnamed_task__/MaxReturn -231.525 MetaTest/__unnamed_task__/MinReturn -322.517 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 33.9689 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.014e+06 ------------------------------------------------- ------------ 2025-04-06 09:30:48 | [pearl_trainer] epoch #487 | Training... 2025-04-06 09:33:33 | [pearl_trainer] epoch #487 | Evaluating... 2025-04-06 09:33:33 | [pearl_trainer] epoch #487 | Sampling for adapation and meta-testing... 2025-04-06 09:38:15 | [pearl_trainer] epoch #487 | Finished meta-testing... 2025-04-06 09:38:15 | [pearl_trainer] epoch #487 | Saving snapshot... 2025-04-06 09:38:16 | [pearl_trainer] epoch #487 | Saved 2025-04-06 09:38:16 | [pearl_trainer] epoch #487 | Time 234559.59 s 2025-04-06 09:38:16 | [pearl_trainer] epoch #487 | EpochTime 496.78 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -280.011 MetaTest/Average/AverageReturn -280.011 MetaTest/Average/Iteration 487 MetaTest/Average/MaxReturn -228.585 MetaTest/Average/MinReturn -333.499 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 42.749 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -280.011 MetaTest/__unnamed_task__/AverageReturn -280.011 MetaTest/__unnamed_task__/Iteration 487 MetaTest/__unnamed_task__/MaxReturn -228.585 MetaTest/__unnamed_task__/MinReturn -333.499 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 42.749 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.016e+06 ------------------------------------------------- ------------ 2025-04-06 09:39:06 | [pearl_trainer] epoch #488 | Training... 2025-04-06 09:41:53 | [pearl_trainer] epoch #488 | Evaluating... 2025-04-06 09:41:53 | [pearl_trainer] epoch #488 | Sampling for adapation and meta-testing... 2025-04-06 09:46:49 | [pearl_trainer] epoch #488 | Finished meta-testing... 2025-04-06 09:46:49 | [pearl_trainer] epoch #488 | Saving snapshot... 2025-04-06 09:46:50 | [pearl_trainer] epoch #488 | Saved 2025-04-06 09:46:50 | [pearl_trainer] epoch #488 | Time 235074.17 s 2025-04-06 09:46:50 | [pearl_trainer] epoch #488 | EpochTime 514.58 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -289.978 MetaTest/Average/AverageReturn -289.978 MetaTest/Average/Iteration 488 MetaTest/Average/MaxReturn -235.688 MetaTest/Average/MinReturn -318.717 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 31.8558 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -289.978 MetaTest/__unnamed_task__/AverageReturn -289.978 MetaTest/__unnamed_task__/Iteration 488 MetaTest/__unnamed_task__/MaxReturn -235.688 MetaTest/__unnamed_task__/MinReturn -318.717 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 31.8558 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.018e+06 ------------------------------------------------- ------------ 2025-04-06 09:47:43 | [pearl_trainer] epoch #489 | Training... 2025-04-06 09:50:31 | [pearl_trainer] epoch #489 | Evaluating... 2025-04-06 09:50:31 | [pearl_trainer] epoch #489 | Sampling for adapation and meta-testing... 2025-04-06 09:55:10 | [pearl_trainer] epoch #489 | Finished meta-testing... 2025-04-06 09:55:10 | [pearl_trainer] epoch #489 | Saving snapshot... 2025-04-06 09:55:11 | [pearl_trainer] epoch #489 | Saved 2025-04-06 09:55:11 | [pearl_trainer] epoch #489 | Time 235575.10 s 2025-04-06 09:55:11 | [pearl_trainer] epoch #489 | EpochTime 500.92 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -267.502 MetaTest/Average/AverageReturn -267.502 MetaTest/Average/Iteration 489 MetaTest/Average/MaxReturn -164.762 MetaTest/Average/MinReturn -374.114 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 79.1005 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -267.502 MetaTest/__unnamed_task__/AverageReturn -267.502 MetaTest/__unnamed_task__/Iteration 489 MetaTest/__unnamed_task__/MaxReturn -164.762 MetaTest/__unnamed_task__/MinReturn -374.114 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 79.1005 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.02e+06 ------------------------------------------------- ----------- 2025-04-06 09:55:59 | [pearl_trainer] epoch #490 | Training... 2025-04-06 09:58:42 | [pearl_trainer] epoch #490 | Evaluating... 2025-04-06 09:58:42 | [pearl_trainer] epoch #490 | Sampling for adapation and meta-testing... 2025-04-06 10:03:34 | [pearl_trainer] epoch #490 | Finished meta-testing... 2025-04-06 10:03:34 | [pearl_trainer] epoch #490 | Saving snapshot... 2025-04-06 10:03:35 | [pearl_trainer] epoch #490 | Saved 2025-04-06 10:03:35 | [pearl_trainer] epoch #490 | Time 236079.15 s 2025-04-06 10:03:35 | [pearl_trainer] epoch #490 | EpochTime 504.06 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -285.545 MetaTest/Average/AverageReturn -285.545 MetaTest/Average/Iteration 490 MetaTest/Average/MaxReturn -168.688 MetaTest/Average/MinReturn -368.077 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 73.385 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -285.545 MetaTest/__unnamed_task__/AverageReturn -285.545 MetaTest/__unnamed_task__/Iteration 490 MetaTest/__unnamed_task__/MaxReturn -168.688 MetaTest/__unnamed_task__/MinReturn -368.077 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 73.385 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.022e+06 ------------------------------------------------- ------------ 2025-04-06 10:04:22 | [pearl_trainer] epoch #491 | Training... 2025-04-06 10:07:20 | [pearl_trainer] epoch #491 | Evaluating... 2025-04-06 10:07:20 | [pearl_trainer] epoch #491 | Sampling for adapation and meta-testing... 2025-04-06 10:12:16 | [pearl_trainer] epoch #491 | Finished meta-testing... 2025-04-06 10:12:16 | [pearl_trainer] epoch #491 | Saving snapshot... 2025-04-06 10:12:17 | [pearl_trainer] epoch #491 | Saved 2025-04-06 10:12:17 | [pearl_trainer] epoch #491 | Time 236601.12 s 2025-04-06 10:12:17 | [pearl_trainer] epoch #491 | EpochTime 521.97 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -205.864 MetaTest/Average/AverageReturn -205.864 MetaTest/Average/Iteration 491 MetaTest/Average/MaxReturn -154.697 MetaTest/Average/MinReturn -255.835 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 32.5669 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -205.864 MetaTest/__unnamed_task__/AverageReturn -205.864 MetaTest/__unnamed_task__/Iteration 491 MetaTest/__unnamed_task__/MaxReturn -154.697 MetaTest/__unnamed_task__/MinReturn -255.835 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 32.5669 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.024e+06 ------------------------------------------------- ------------ 2025-04-06 10:13:06 | [pearl_trainer] epoch #492 | Training... 2025-04-06 10:15:51 | [pearl_trainer] epoch #492 | Evaluating... 2025-04-06 10:15:51 | [pearl_trainer] epoch #492 | Sampling for adapation and meta-testing... 2025-04-06 10:20:55 | [pearl_trainer] epoch #492 | Finished meta-testing... 2025-04-06 10:20:55 | [pearl_trainer] epoch #492 | Saving snapshot... 2025-04-06 10:20:56 | [pearl_trainer] epoch #492 | Saved 2025-04-06 10:20:56 | [pearl_trainer] epoch #492 | Time 237120.05 s 2025-04-06 10:20:56 | [pearl_trainer] epoch #492 | EpochTime 518.92 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -216.044 MetaTest/Average/AverageReturn -216.044 MetaTest/Average/Iteration 492 MetaTest/Average/MaxReturn -125.068 MetaTest/Average/MinReturn -283.737 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 56.7093 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -216.044 MetaTest/__unnamed_task__/AverageReturn -216.044 MetaTest/__unnamed_task__/Iteration 492 MetaTest/__unnamed_task__/MaxReturn -125.068 MetaTest/__unnamed_task__/MinReturn -283.737 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 56.7093 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.026e+06 ------------------------------------------------- ------------ 2025-04-06 10:21:48 | [pearl_trainer] epoch #493 | Training... 2025-04-06 10:24:57 | [pearl_trainer] epoch #493 | Evaluating... 2025-04-06 10:24:57 | [pearl_trainer] epoch #493 | Sampling for adapation and meta-testing... 2025-04-06 10:29:53 | [pearl_trainer] epoch #493 | Finished meta-testing... 2025-04-06 10:29:53 | [pearl_trainer] epoch #493 | Saving snapshot... 2025-04-06 10:29:54 | [pearl_trainer] epoch #493 | Saved 2025-04-06 10:29:54 | [pearl_trainer] epoch #493 | Time 237657.55 s 2025-04-06 10:29:54 | [pearl_trainer] epoch #493 | EpochTime 537.49 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -310.742 MetaTest/Average/AverageReturn -310.742 MetaTest/Average/Iteration 493 MetaTest/Average/MaxReturn -282.319 MetaTest/Average/MinReturn -340.407 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 24.1673 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -310.742 MetaTest/__unnamed_task__/AverageReturn -310.742 MetaTest/__unnamed_task__/Iteration 493 MetaTest/__unnamed_task__/MaxReturn -282.319 MetaTest/__unnamed_task__/MinReturn -340.407 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 24.1673 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.028e+06 ------------------------------------------------- ------------ 2025-04-06 10:30:44 | [pearl_trainer] epoch #494 | Training... 2025-04-06 10:33:51 | [pearl_trainer] epoch #494 | Evaluating... 2025-04-06 10:33:51 | [pearl_trainer] epoch #494 | Sampling for adapation and meta-testing... 2025-04-06 10:38:36 | [pearl_trainer] epoch #494 | Finished meta-testing... 2025-04-06 10:38:36 | [pearl_trainer] epoch #494 | Saving snapshot... 2025-04-06 10:38:38 | [pearl_trainer] epoch #494 | Saved 2025-04-06 10:38:38 | [pearl_trainer] epoch #494 | Time 238181.57 s 2025-04-06 10:38:38 | [pearl_trainer] epoch #494 | EpochTime 524.02 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -229.583 MetaTest/Average/AverageReturn -229.583 MetaTest/Average/Iteration 494 MetaTest/Average/MaxReturn -138.464 MetaTest/Average/MinReturn -283.376 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 56.8671 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -229.583 MetaTest/__unnamed_task__/AverageReturn -229.583 MetaTest/__unnamed_task__/Iteration 494 MetaTest/__unnamed_task__/MaxReturn -138.464 MetaTest/__unnamed_task__/MinReturn -283.376 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 56.8671 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.03e+06 ------------------------------------------------- ----------- 2025-04-06 10:39:28 | [pearl_trainer] epoch #495 | Training... 2025-04-06 10:42:17 | [pearl_trainer] epoch #495 | Evaluating... 2025-04-06 10:42:17 | [pearl_trainer] epoch #495 | Sampling for adapation and meta-testing... 2025-04-06 10:47:13 | [pearl_trainer] epoch #495 | Finished meta-testing... 2025-04-06 10:47:13 | [pearl_trainer] epoch #495 | Saving snapshot... 2025-04-06 10:47:15 | [pearl_trainer] epoch #495 | Saved 2025-04-06 10:47:15 | [pearl_trainer] epoch #495 | Time 238698.31 s 2025-04-06 10:47:15 | [pearl_trainer] epoch #495 | EpochTime 516.74 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -229.252 MetaTest/Average/AverageReturn -229.252 MetaTest/Average/Iteration 495 MetaTest/Average/MaxReturn -209.016 MetaTest/Average/MinReturn -284.342 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 27.8719 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -229.252 MetaTest/__unnamed_task__/AverageReturn -229.252 MetaTest/__unnamed_task__/Iteration 495 MetaTest/__unnamed_task__/MaxReturn -209.016 MetaTest/__unnamed_task__/MinReturn -284.342 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 27.8719 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.032e+06 ------------------------------------------------- ------------ 2025-04-06 10:48:09 | [pearl_trainer] epoch #496 | Training... 2025-04-06 10:51:03 | [pearl_trainer] epoch #496 | Evaluating... 2025-04-06 10:51:03 | [pearl_trainer] epoch #496 | Sampling for adapation and meta-testing... 2025-04-06 10:55:44 | [pearl_trainer] epoch #496 | Finished meta-testing... 2025-04-06 10:55:44 | [pearl_trainer] epoch #496 | Saving snapshot... 2025-04-06 10:55:45 | [pearl_trainer] epoch #496 | Saved 2025-04-06 10:55:45 | [pearl_trainer] epoch #496 | Time 239208.92 s 2025-04-06 10:55:45 | [pearl_trainer] epoch #496 | EpochTime 510.61 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -258.869 MetaTest/Average/AverageReturn -258.869 MetaTest/Average/Iteration 496 MetaTest/Average/MaxReturn -189.14 MetaTest/Average/MinReturn -326.898 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 49.6628 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -258.869 MetaTest/__unnamed_task__/AverageReturn -258.869 MetaTest/__unnamed_task__/Iteration 496 MetaTest/__unnamed_task__/MaxReturn -189.14 MetaTest/__unnamed_task__/MinReturn -326.898 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 49.6628 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.034e+06 ------------------------------------------------- ------------ 2025-04-06 10:56:35 | [pearl_trainer] epoch #497 | Training... 2025-04-06 10:59:20 | [pearl_trainer] epoch #497 | Evaluating... 2025-04-06 10:59:20 | [pearl_trainer] epoch #497 | Sampling for adapation and meta-testing... 2025-04-06 11:04:04 | [pearl_trainer] epoch #497 | Finished meta-testing... 2025-04-06 11:04:04 | [pearl_trainer] epoch #497 | Saving snapshot... 2025-04-06 11:04:06 | [pearl_trainer] epoch #497 | Saved 2025-04-06 11:04:06 | [pearl_trainer] epoch #497 | Time 239709.53 s 2025-04-06 11:04:06 | [pearl_trainer] epoch #497 | EpochTime 500.61 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -283.781 MetaTest/Average/AverageReturn -283.781 MetaTest/Average/Iteration 497 MetaTest/Average/MaxReturn -190.548 MetaTest/Average/MinReturn -369.685 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 68.2166 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -283.781 MetaTest/__unnamed_task__/AverageReturn -283.781 MetaTest/__unnamed_task__/Iteration 497 MetaTest/__unnamed_task__/MaxReturn -190.548 MetaTest/__unnamed_task__/MinReturn -369.685 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 68.2166 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.036e+06 ------------------------------------------------- ------------ 2025-04-06 11:04:55 | [pearl_trainer] epoch #498 | Training... 2025-04-06 11:07:37 | [pearl_trainer] epoch #498 | Evaluating... 2025-04-06 11:07:37 | [pearl_trainer] epoch #498 | Sampling for adapation and meta-testing... 2025-04-06 11:12:34 | [pearl_trainer] epoch #498 | Finished meta-testing... 2025-04-06 11:12:34 | [pearl_trainer] epoch #498 | Saving snapshot... 2025-04-06 11:12:36 | [pearl_trainer] epoch #498 | Saved 2025-04-06 11:12:36 | [pearl_trainer] epoch #498 | Time 240219.42 s 2025-04-06 11:12:36 | [pearl_trainer] epoch #498 | EpochTime 509.88 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -284.892 MetaTest/Average/AverageReturn -284.892 MetaTest/Average/Iteration 498 MetaTest/Average/MaxReturn -248.079 MetaTest/Average/MinReturn -354.346 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 38.5503 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -284.892 MetaTest/__unnamed_task__/AverageReturn -284.892 MetaTest/__unnamed_task__/Iteration 498 MetaTest/__unnamed_task__/MaxReturn -248.079 MetaTest/__unnamed_task__/MinReturn -354.346 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 38.5503 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.038e+06 ------------------------------------------------- ------------ 2025-04-06 11:13:26 | [pearl_trainer] epoch #499 | Training... 2025-04-06 11:16:12 | [pearl_trainer] epoch #499 | Evaluating... 2025-04-06 11:16:12 | [pearl_trainer] epoch #499 | Sampling for adapation and meta-testing... 2025-04-06 11:20:32 | [pearl_trainer] epoch #499 | Finished meta-testing... 2025-04-06 11:20:32 | [pearl_trainer] epoch #499 | Saving snapshot... 2025-04-06 11:20:34 | [pearl_trainer] epoch #499 | Saved 2025-04-06 11:20:34 | [pearl_trainer] epoch #499 | Time 240697.75 s 2025-04-06 11:20:34 | [pearl_trainer] epoch #499 | EpochTime 478.33 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -320.128 MetaTest/Average/AverageReturn -320.128 MetaTest/Average/Iteration 499 MetaTest/Average/MaxReturn -242.724 MetaTest/Average/MinReturn -444.519 MetaTest/Average/NumEpisodes 5 MetaTest/Average/StdReturn 68.3924 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -320.128 MetaTest/__unnamed_task__/AverageReturn -320.128 MetaTest/__unnamed_task__/Iteration 499 MetaTest/__unnamed_task__/MaxReturn -242.724 MetaTest/__unnamed_task__/MinReturn -444.519 MetaTest/__unnamed_task__/NumEpisodes 5 MetaTest/__unnamed_task__/StdReturn 68.3924 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 1.04e+06 ------------------------------------------------- -----------