2025-03-29 14:09:30 | [pearl_trainer] Logging to /home/h2khalil/MetaRL-Assistive-Robotics/data/local/experiment/pearl_trainer 2025-03-29 14:09:35 | [pearl_trainer] Obtaining samples... 2025-03-29 14:14:27 | [pearl_trainer] epoch #0 | Training... 2025-03-29 14:15:43 | [pearl_trainer] epoch #0 | Evaluating... 2025-03-29 14:15:43 | [pearl_trainer] epoch #0 | Sampling for adapation and meta-testing... 2025-03-29 14:18:57 | [pearl_trainer] epoch #0 | Finished meta-testing... 2025-03-29 14:18:57 | [pearl_trainer] epoch #0 | Saving snapshot... 2025-03-29 14:19:01 | [pearl_trainer] epoch #0 | Saved 2025-03-29 14:19:01 | [pearl_trainer] epoch #0 | Time 565.46 s 2025-03-29 14:19:01 | [pearl_trainer] epoch #0 | EpochTime 565.46 s ------------------------------------------------- --------- MetaTest/Average/AverageDiscountedReturn -62.5375 MetaTest/Average/AverageReturn -62.5375 MetaTest/Average/Iteration 0 MetaTest/Average/MaxReturn -51.9132 MetaTest/Average/MinReturn -73.1617 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 10.6243 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -62.5375 MetaTest/__unnamed_task__/AverageReturn -62.5375 MetaTest/__unnamed_task__/Iteration 0 MetaTest/__unnamed_task__/MaxReturn -51.9132 MetaTest/__unnamed_task__/MinReturn -73.1617 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 10.6243 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 4000 ------------------------------------------------- --------- 2025-03-29 14:22:00 | [pearl_trainer] epoch #1 | Training... 2025-03-29 14:23:42 | [pearl_trainer] epoch #1 | Evaluating... 2025-03-29 14:23:42 | [pearl_trainer] epoch #1 | Sampling for adapation and meta-testing... 2025-03-29 14:27:54 | [pearl_trainer] epoch #1 | Finished meta-testing... 2025-03-29 14:27:54 | [pearl_trainer] epoch #1 | Saving snapshot... 2025-03-29 14:27:57 | [pearl_trainer] epoch #1 | Saved 2025-03-29 14:27:57 | [pearl_trainer] epoch #1 | Time 1102.11 s 2025-03-29 14:27:57 | [pearl_trainer] epoch #1 | EpochTime 536.64 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -70.1468 MetaTest/Average/AverageReturn -70.1468 MetaTest/Average/Iteration 1 MetaTest/Average/MaxReturn -65.4212 MetaTest/Average/MinReturn -74.8724 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.72563 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -70.1468 MetaTest/__unnamed_task__/AverageReturn -70.1468 MetaTest/__unnamed_task__/Iteration 1 MetaTest/__unnamed_task__/MaxReturn -65.4212 MetaTest/__unnamed_task__/MinReturn -74.8724 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.72563 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 6000 ------------------------------------------------- ---------- 2025-03-29 14:30:51 | [pearl_trainer] epoch #2 | Training... 2025-03-29 14:31:35 | [pearl_trainer] epoch #2 | Evaluating... 2025-03-29 14:31:35 | [pearl_trainer] epoch #2 | Sampling for adapation and meta-testing... 2025-03-29 14:35:22 | [pearl_trainer] epoch #2 | Finished meta-testing... 2025-03-29 14:35:22 | [pearl_trainer] epoch #2 | Saving snapshot... 2025-03-29 14:35:25 | [pearl_trainer] epoch #2 | Saved 2025-03-29 14:35:25 | [pearl_trainer] epoch #2 | Time 1549.61 s 2025-03-29 14:35:25 | [pearl_trainer] epoch #2 | EpochTime 447.49 s ------------------------------------------------- --------- MetaTest/Average/AverageDiscountedReturn -50.7566 MetaTest/Average/AverageReturn -50.7566 MetaTest/Average/Iteration 2 MetaTest/Average/MaxReturn -44.3779 MetaTest/Average/MinReturn -57.1353 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 6.3787 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -50.7566 MetaTest/__unnamed_task__/AverageReturn -50.7566 MetaTest/__unnamed_task__/Iteration 2 MetaTest/__unnamed_task__/MaxReturn -44.3779 MetaTest/__unnamed_task__/MinReturn -57.1353 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 6.3787 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 8000 ------------------------------------------------- --------- 2025-03-29 14:39:17 | [pearl_trainer] epoch #3 | Training... 2025-03-29 14:40:56 | [pearl_trainer] epoch #3 | Evaluating... 2025-03-29 14:40:56 | [pearl_trainer] epoch #3 | Sampling for adapation and meta-testing... 2025-03-29 14:43:33 | [pearl_trainer] epoch #3 | Finished meta-testing... 2025-03-29 14:43:33 | [pearl_trainer] epoch #3 | Saving snapshot... 2025-03-29 14:43:34 | [pearl_trainer] epoch #3 | Saved 2025-03-29 14:43:34 | [pearl_trainer] epoch #3 | Time 2038.50 s 2025-03-29 14:43:34 | [pearl_trainer] epoch #3 | EpochTime 488.88 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -58.3137 MetaTest/Average/AverageReturn -58.3137 MetaTest/Average/Iteration 3 MetaTest/Average/MaxReturn -55.5249 MetaTest/Average/MinReturn -61.1025 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.7888 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -58.3137 MetaTest/__unnamed_task__/AverageReturn -58.3137 MetaTest/__unnamed_task__/Iteration 3 MetaTest/__unnamed_task__/MaxReturn -55.5249 MetaTest/__unnamed_task__/MinReturn -61.1025 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.7888 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 10000 ------------------------------------------------- ---------- 2025-03-29 14:44:37 | [pearl_trainer] epoch #4 | Training... 2025-03-29 14:44:55 | [pearl_trainer] epoch #4 | Evaluating... 2025-03-29 14:44:55 | [pearl_trainer] epoch #4 | Sampling for adapation and meta-testing... 2025-03-29 14:46:10 | [pearl_trainer] epoch #4 | Finished meta-testing... 2025-03-29 14:46:10 | [pearl_trainer] epoch #4 | Saving snapshot... 2025-03-29 14:46:11 | [pearl_trainer] epoch #4 | Saved 2025-03-29 14:46:11 | [pearl_trainer] epoch #4 | Time 2195.96 s 2025-03-29 14:46:11 | [pearl_trainer] epoch #4 | EpochTime 157.46 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -46.7176 MetaTest/Average/AverageReturn -46.7176 MetaTest/Average/Iteration 4 MetaTest/Average/MaxReturn -38.0802 MetaTest/Average/MinReturn -55.3551 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 8.63744 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -46.7176 MetaTest/__unnamed_task__/AverageReturn -46.7176 MetaTest/__unnamed_task__/Iteration 4 MetaTest/__unnamed_task__/MaxReturn -38.0802 MetaTest/__unnamed_task__/MinReturn -55.3551 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 8.63744 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 12000 ------------------------------------------------- ----------- 2025-03-29 14:47:47 | [pearl_trainer] epoch #5 | Training... 2025-03-29 14:48:24 | [pearl_trainer] epoch #5 | Evaluating... 2025-03-29 14:48:24 | [pearl_trainer] epoch #5 | Sampling for adapation and meta-testing... 2025-03-29 14:50:48 | [pearl_trainer] epoch #5 | Finished meta-testing... 2025-03-29 14:50:48 | [pearl_trainer] epoch #5 | Saving snapshot... 2025-03-29 14:50:49 | [pearl_trainer] epoch #5 | Saved 2025-03-29 14:50:49 | [pearl_trainer] epoch #5 | Time 2474.28 s 2025-03-29 14:50:49 | [pearl_trainer] epoch #5 | EpochTime 278.31 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -48.2018 MetaTest/Average/AverageReturn -48.2018 MetaTest/Average/Iteration 5 MetaTest/Average/MaxReturn -46.1346 MetaTest/Average/MinReturn -50.269 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.0672 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.2018 MetaTest/__unnamed_task__/AverageReturn -48.2018 MetaTest/__unnamed_task__/Iteration 5 MetaTest/__unnamed_task__/MaxReturn -46.1346 MetaTest/__unnamed_task__/MinReturn -50.269 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.0672 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 14000 ------------------------------------------------- ---------- 2025-03-29 14:53:00 | [pearl_trainer] epoch #6 | Training... 2025-03-29 14:54:07 | [pearl_trainer] epoch #6 | Evaluating... 2025-03-29 14:54:07 | [pearl_trainer] epoch #6 | Sampling for adapation and meta-testing... 2025-03-29 14:57:31 | [pearl_trainer] epoch #6 | Finished meta-testing... 2025-03-29 14:57:31 | [pearl_trainer] epoch #6 | Saving snapshot... 2025-03-29 14:57:36 | [pearl_trainer] epoch #6 | Saved 2025-03-29 14:57:36 | [pearl_trainer] epoch #6 | Time 2880.70 s 2025-03-29 14:57:36 | [pearl_trainer] epoch #6 | EpochTime 406.42 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -48.7072 MetaTest/Average/AverageReturn -48.7072 MetaTest/Average/Iteration 6 MetaTest/Average/MaxReturn -40.8002 MetaTest/Average/MinReturn -56.6143 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 7.90706 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -48.7072 MetaTest/__unnamed_task__/AverageReturn -48.7072 MetaTest/__unnamed_task__/Iteration 6 MetaTest/__unnamed_task__/MaxReturn -40.8002 MetaTest/__unnamed_task__/MinReturn -56.6143 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 7.90706 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 16000 ------------------------------------------------- ----------- 2025-03-29 15:00:20 | [pearl_trainer] epoch #7 | Training... 2025-03-29 15:01:45 | [pearl_trainer] epoch #7 | Evaluating... 2025-03-29 15:01:45 | [pearl_trainer] epoch #7 | Sampling for adapation and meta-testing... 2025-03-29 15:05:26 | [pearl_trainer] epoch #7 | Finished meta-testing... 2025-03-29 15:05:26 | [pearl_trainer] epoch #7 | Saving snapshot... 2025-03-29 15:05:28 | [pearl_trainer] epoch #7 | Saved 2025-03-29 15:05:28 | [pearl_trainer] epoch #7 | Time 3352.87 s 2025-03-29 15:05:28 | [pearl_trainer] epoch #7 | EpochTime 472.16 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -35.5643 MetaTest/Average/AverageReturn -35.5643 MetaTest/Average/Iteration 7 MetaTest/Average/MaxReturn -31.6593 MetaTest/Average/MinReturn -39.4694 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.90503 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.5643 MetaTest/__unnamed_task__/AverageReturn -35.5643 MetaTest/__unnamed_task__/Iteration 7 MetaTest/__unnamed_task__/MaxReturn -31.6593 MetaTest/__unnamed_task__/MinReturn -39.4694 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.90503 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 18000 ------------------------------------------------- ----------- 2025-03-29 15:07:40 | [pearl_trainer] epoch #8 | Training... 2025-03-29 15:08:36 | [pearl_trainer] epoch #8 | Evaluating... 2025-03-29 15:08:36 | [pearl_trainer] epoch #8 | Sampling for adapation and meta-testing... 2025-03-29 15:11:11 | [pearl_trainer] epoch #8 | Finished meta-testing... 2025-03-29 15:11:11 | [pearl_trainer] epoch #8 | Saving snapshot... 2025-03-29 15:11:13 | [pearl_trainer] epoch #8 | Saved 2025-03-29 15:11:13 | [pearl_trainer] epoch #8 | Time 3697.80 s 2025-03-29 15:11:13 | [pearl_trainer] epoch #8 | EpochTime 344.93 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -38.24 MetaTest/Average/AverageReturn -38.24 MetaTest/Average/Iteration 8 MetaTest/Average/MaxReturn -32.1657 MetaTest/Average/MinReturn -44.3142 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 6.07425 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.24 MetaTest/__unnamed_task__/AverageReturn -38.24 MetaTest/__unnamed_task__/Iteration 8 MetaTest/__unnamed_task__/MaxReturn -32.1657 MetaTest/__unnamed_task__/MinReturn -44.3142 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 6.07425 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 20000 ------------------------------------------------- ----------- 2025-03-29 15:13:23 | [pearl_trainer] epoch #9 | Training... 2025-03-29 15:14:33 | [pearl_trainer] epoch #9 | Evaluating... 2025-03-29 15:14:33 | [pearl_trainer] epoch #9 | Sampling for adapation and meta-testing... 2025-03-29 15:17:01 | [pearl_trainer] epoch #9 | Finished meta-testing... 2025-03-29 15:17:01 | [pearl_trainer] epoch #9 | Saving snapshot... 2025-03-29 15:17:04 | [pearl_trainer] epoch #9 | Saved 2025-03-29 15:17:04 | [pearl_trainer] epoch #9 | Time 4049.03 s 2025-03-29 15:17:04 | [pearl_trainer] epoch #9 | EpochTime 351.22 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -45.0645 MetaTest/Average/AverageReturn -45.0645 MetaTest/Average/Iteration 9 MetaTest/Average/MaxReturn -44.7053 MetaTest/Average/MinReturn -45.4236 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.359132 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -45.0645 MetaTest/__unnamed_task__/AverageReturn -45.0645 MetaTest/__unnamed_task__/Iteration 9 MetaTest/__unnamed_task__/MaxReturn -44.7053 MetaTest/__unnamed_task__/MinReturn -45.4236 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.359132 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 22000 ------------------------------------------------- ------------ 2025-03-29 15:19:13 | [pearl_trainer] epoch #10 | Training... 2025-03-29 15:20:06 | [pearl_trainer] epoch #10 | Evaluating... 2025-03-29 15:20:06 | [pearl_trainer] epoch #10 | Sampling for adapation and meta-testing... 2025-03-29 15:22:39 | [pearl_trainer] epoch #10 | Finished meta-testing... 2025-03-29 15:22:39 | [pearl_trainer] epoch #10 | Saving snapshot... 2025-03-29 15:22:42 | [pearl_trainer] epoch #10 | Saved 2025-03-29 15:22:42 | [pearl_trainer] epoch #10 | Time 4386.65 s 2025-03-29 15:22:42 | [pearl_trainer] epoch #10 | EpochTime 337.61 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -42.8473 MetaTest/Average/AverageReturn -42.8473 MetaTest/Average/Iteration 10 MetaTest/Average/MaxReturn -38.7146 MetaTest/Average/MinReturn -46.9799 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.13265 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -42.8473 MetaTest/__unnamed_task__/AverageReturn -42.8473 MetaTest/__unnamed_task__/Iteration 10 MetaTest/__unnamed_task__/MaxReturn -38.7146 MetaTest/__unnamed_task__/MinReturn -46.9799 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.13265 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 24000 ------------------------------------------------- ----------- 2025-03-29 15:25:22 | [pearl_trainer] epoch #11 | Training... 2025-03-29 15:26:16 | [pearl_trainer] epoch #11 | Evaluating... 2025-03-29 15:26:16 | [pearl_trainer] epoch #11 | Sampling for adapation and meta-testing... 2025-03-29 15:29:17 | [pearl_trainer] epoch #11 | Finished meta-testing... 2025-03-29 15:29:17 | [pearl_trainer] epoch #11 | Saving snapshot... 2025-03-29 15:29:19 | [pearl_trainer] epoch #11 | Saved 2025-03-29 15:29:19 | [pearl_trainer] epoch #11 | Time 4783.69 s 2025-03-29 15:29:19 | [pearl_trainer] epoch #11 | EpochTime 397.03 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.3735 MetaTest/Average/AverageReturn -33.3735 MetaTest/Average/Iteration 11 MetaTest/Average/MaxReturn -33.3607 MetaTest/Average/MinReturn -33.3863 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.0128278 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.3735 MetaTest/__unnamed_task__/AverageReturn -33.3735 MetaTest/__unnamed_task__/Iteration 11 MetaTest/__unnamed_task__/MaxReturn -33.3607 MetaTest/__unnamed_task__/MinReturn -33.3863 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.0128278 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 26000 ------------------------------------------------- ------------- 2025-03-29 15:31:39 | [pearl_trainer] epoch #12 | Training... 2025-03-29 15:32:44 | [pearl_trainer] epoch #12 | Evaluating... 2025-03-29 15:32:44 | [pearl_trainer] epoch #12 | Sampling for adapation and meta-testing... 2025-03-29 15:34:52 | [pearl_trainer] epoch #12 | Finished meta-testing... 2025-03-29 15:34:52 | [pearl_trainer] epoch #12 | Saving snapshot... 2025-03-29 15:34:53 | [pearl_trainer] epoch #12 | Saved 2025-03-29 15:34:53 | [pearl_trainer] epoch #12 | Time 5117.83 s 2025-03-29 15:34:53 | [pearl_trainer] epoch #12 | EpochTime 334.14 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -41.8433 MetaTest/Average/AverageReturn -41.8433 MetaTest/Average/Iteration 12 MetaTest/Average/MaxReturn -34.9485 MetaTest/Average/MinReturn -48.7381 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 6.89477 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -41.8433 MetaTest/__unnamed_task__/AverageReturn -41.8433 MetaTest/__unnamed_task__/Iteration 12 MetaTest/__unnamed_task__/MaxReturn -34.9485 MetaTest/__unnamed_task__/MinReturn -48.7381 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 6.89477 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 28000 ------------------------------------------------- ----------- 2025-03-29 15:36:04 | [pearl_trainer] epoch #13 | Training... 2025-03-29 15:36:21 | [pearl_trainer] epoch #13 | Evaluating... 2025-03-29 15:36:21 | [pearl_trainer] epoch #13 | Sampling for adapation and meta-testing... 2025-03-29 15:37:38 | [pearl_trainer] epoch #13 | Finished meta-testing... 2025-03-29 15:37:38 | [pearl_trainer] epoch #13 | Saving snapshot... 2025-03-29 15:37:38 | [pearl_trainer] epoch #13 | Saved 2025-03-29 15:37:38 | [pearl_trainer] epoch #13 | Time 5283.36 s 2025-03-29 15:37:38 | [pearl_trainer] epoch #13 | EpochTime 165.53 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.2659 MetaTest/Average/AverageReturn -33.2659 MetaTest/Average/Iteration 13 MetaTest/Average/MaxReturn -32.5335 MetaTest/Average/MinReturn -33.9982 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.732318 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.2659 MetaTest/__unnamed_task__/AverageReturn -33.2659 MetaTest/__unnamed_task__/Iteration 13 MetaTest/__unnamed_task__/MaxReturn -32.5335 MetaTest/__unnamed_task__/MinReturn -33.9982 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.732318 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 30000 ------------------------------------------------- ------------ 2025-03-29 15:38:42 | [pearl_trainer] epoch #14 | Training... 2025-03-29 15:39:00 | [pearl_trainer] epoch #14 | Evaluating... 2025-03-29 15:39:00 | [pearl_trainer] epoch #14 | Sampling for adapation and meta-testing... 2025-03-29 15:40:16 | [pearl_trainer] epoch #14 | Finished meta-testing... 2025-03-29 15:40:16 | [pearl_trainer] epoch #14 | Saving snapshot... 2025-03-29 15:40:16 | [pearl_trainer] epoch #14 | Saved 2025-03-29 15:40:16 | [pearl_trainer] epoch #14 | Time 5441.28 s 2025-03-29 15:40:16 | [pearl_trainer] epoch #14 | EpochTime 157.91 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.2524 MetaTest/Average/AverageReturn -35.2524 MetaTest/Average/Iteration 14 MetaTest/Average/MaxReturn -34.695 MetaTest/Average/MinReturn -35.8098 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.557421 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.2524 MetaTest/__unnamed_task__/AverageReturn -35.2524 MetaTest/__unnamed_task__/Iteration 14 MetaTest/__unnamed_task__/MaxReturn -34.695 MetaTest/__unnamed_task__/MinReturn -35.8098 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.557421 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 32000 ------------------------------------------------- ------------ 2025-03-29 15:41:27 | [pearl_trainer] epoch #15 | Training... 2025-03-29 15:41:44 | [pearl_trainer] epoch #15 | Evaluating... 2025-03-29 15:41:44 | [pearl_trainer] epoch #15 | Sampling for adapation and meta-testing... 2025-03-29 15:42:53 | [pearl_trainer] epoch #15 | Finished meta-testing... 2025-03-29 15:42:53 | [pearl_trainer] epoch #15 | Saving snapshot... 2025-03-29 15:42:54 | [pearl_trainer] epoch #15 | Saved 2025-03-29 15:42:54 | [pearl_trainer] epoch #15 | Time 5598.44 s 2025-03-29 15:42:54 | [pearl_trainer] epoch #15 | EpochTime 157.16 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -35.217 MetaTest/Average/AverageReturn -35.217 MetaTest/Average/Iteration 15 MetaTest/Average/MaxReturn -33.1225 MetaTest/Average/MinReturn -37.3115 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.09448 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.217 MetaTest/__unnamed_task__/AverageReturn -35.217 MetaTest/__unnamed_task__/Iteration 15 MetaTest/__unnamed_task__/MaxReturn -33.1225 MetaTest/__unnamed_task__/MinReturn -37.3115 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.09448 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 34000 ------------------------------------------------- ----------- 2025-03-29 15:43:56 | [pearl_trainer] epoch #16 | Training... 2025-03-29 15:44:13 | [pearl_trainer] epoch #16 | Evaluating... 2025-03-29 15:44:13 | [pearl_trainer] epoch #16 | Sampling for adapation and meta-testing... 2025-03-29 15:45:22 | [pearl_trainer] epoch #16 | Finished meta-testing... 2025-03-29 15:45:22 | [pearl_trainer] epoch #16 | Saving snapshot... 2025-03-29 15:45:23 | [pearl_trainer] epoch #16 | Saved 2025-03-29 15:45:23 | [pearl_trainer] epoch #16 | Time 5748.03 s 2025-03-29 15:45:23 | [pearl_trainer] epoch #16 | EpochTime 149.58 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -36.0744 MetaTest/Average/AverageReturn -36.0744 MetaTest/Average/Iteration 16 MetaTest/Average/MaxReturn -31.855 MetaTest/Average/MinReturn -40.2939 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.21945 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.0744 MetaTest/__unnamed_task__/AverageReturn -36.0744 MetaTest/__unnamed_task__/Iteration 16 MetaTest/__unnamed_task__/MaxReturn -31.855 MetaTest/__unnamed_task__/MinReturn -40.2939 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.21945 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 36000 ------------------------------------------------- ----------- 2025-03-29 15:46:30 | [pearl_trainer] epoch #17 | Training... 2025-03-29 15:46:50 | [pearl_trainer] epoch #17 | Evaluating... 2025-03-29 15:46:50 | [pearl_trainer] epoch #17 | Sampling for adapation and meta-testing... 2025-03-29 15:47:59 | [pearl_trainer] epoch #17 | Finished meta-testing... 2025-03-29 15:47:59 | [pearl_trainer] epoch #17 | Saving snapshot... 2025-03-29 15:48:00 | [pearl_trainer] epoch #17 | Saved 2025-03-29 15:48:00 | [pearl_trainer] epoch #17 | Time 5905.13 s 2025-03-29 15:48:00 | [pearl_trainer] epoch #17 | EpochTime 157.10 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -34.0249 MetaTest/Average/AverageReturn -34.0249 MetaTest/Average/Iteration 17 MetaTest/Average/MaxReturn -29.7481 MetaTest/Average/MinReturn -38.3016 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.27673 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.0249 MetaTest/__unnamed_task__/AverageReturn -34.0249 MetaTest/__unnamed_task__/Iteration 17 MetaTest/__unnamed_task__/MaxReturn -29.7481 MetaTest/__unnamed_task__/MinReturn -38.3016 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.27673 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 38000 ------------------------------------------------- ----------- 2025-03-29 15:49:10 | [pearl_trainer] epoch #18 | Training... 2025-03-29 15:49:26 | [pearl_trainer] epoch #18 | Evaluating... 2025-03-29 15:49:26 | [pearl_trainer] epoch #18 | Sampling for adapation and meta-testing... 2025-03-29 15:50:35 | [pearl_trainer] epoch #18 | Finished meta-testing... 2025-03-29 15:50:35 | [pearl_trainer] epoch #18 | Saving snapshot... 2025-03-29 15:50:35 | [pearl_trainer] epoch #18 | Saved 2025-03-29 15:50:35 | [pearl_trainer] epoch #18 | Time 6060.37 s 2025-03-29 15:50:35 | [pearl_trainer] epoch #18 | EpochTime 155.24 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -33.9498 MetaTest/Average/AverageReturn -33.9498 MetaTest/Average/Iteration 18 MetaTest/Average/MaxReturn -30.6836 MetaTest/Average/MinReturn -37.216 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.26622 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.9498 MetaTest/__unnamed_task__/AverageReturn -33.9498 MetaTest/__unnamed_task__/Iteration 18 MetaTest/__unnamed_task__/MaxReturn -30.6836 MetaTest/__unnamed_task__/MinReturn -37.216 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.26622 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 40000 ------------------------------------------------- ----------- 2025-03-29 15:51:38 | [pearl_trainer] epoch #19 | Training... 2025-03-29 15:51:55 | [pearl_trainer] epoch #19 | Evaluating... 2025-03-29 15:51:55 | [pearl_trainer] epoch #19 | Sampling for adapation and meta-testing... 2025-03-29 15:53:07 | [pearl_trainer] epoch #19 | Finished meta-testing... 2025-03-29 15:53:07 | [pearl_trainer] epoch #19 | Saving snapshot... 2025-03-29 15:53:08 | [pearl_trainer] epoch #19 | Saved 2025-03-29 15:53:08 | [pearl_trainer] epoch #19 | Time 6212.75 s 2025-03-29 15:53:08 | [pearl_trainer] epoch #19 | EpochTime 152.37 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -37.3881 MetaTest/Average/AverageReturn -37.3881 MetaTest/Average/Iteration 19 MetaTest/Average/MaxReturn -34.5452 MetaTest/Average/MinReturn -40.231 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.84288 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.3881 MetaTest/__unnamed_task__/AverageReturn -37.3881 MetaTest/__unnamed_task__/Iteration 19 MetaTest/__unnamed_task__/MaxReturn -34.5452 MetaTest/__unnamed_task__/MinReturn -40.231 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.84288 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 42000 ------------------------------------------------- ----------- 2025-03-29 15:54:23 | [pearl_trainer] epoch #20 | Training... 2025-03-29 15:54:45 | [pearl_trainer] epoch #20 | Evaluating... 2025-03-29 15:54:45 | [pearl_trainer] epoch #20 | Sampling for adapation and meta-testing... 2025-03-29 15:56:08 | [pearl_trainer] epoch #20 | Finished meta-testing... 2025-03-29 15:56:08 | [pearl_trainer] epoch #20 | Saving snapshot... 2025-03-29 15:56:08 | [pearl_trainer] epoch #20 | Saved 2025-03-29 15:56:08 | [pearl_trainer] epoch #20 | Time 6393.22 s 2025-03-29 15:56:08 | [pearl_trainer] epoch #20 | EpochTime 180.47 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -44.0086 MetaTest/Average/AverageReturn -44.0086 MetaTest/Average/Iteration 20 MetaTest/Average/MaxReturn -42.831 MetaTest/Average/MinReturn -45.1862 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.17758 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.0086 MetaTest/__unnamed_task__/AverageReturn -44.0086 MetaTest/__unnamed_task__/Iteration 20 MetaTest/__unnamed_task__/MaxReturn -42.831 MetaTest/__unnamed_task__/MinReturn -45.1862 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.17758 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 44000 ------------------------------------------------- ----------- 2025-03-29 15:57:16 | [pearl_trainer] epoch #21 | Training... 2025-03-29 15:57:33 | [pearl_trainer] epoch #21 | Evaluating... 2025-03-29 15:57:33 | [pearl_trainer] epoch #21 | Sampling for adapation and meta-testing... 2025-03-29 15:58:43 | [pearl_trainer] epoch #21 | Finished meta-testing... 2025-03-29 15:58:43 | [pearl_trainer] epoch #21 | Saving snapshot... 2025-03-29 15:58:43 | [pearl_trainer] epoch #21 | Saved 2025-03-29 15:58:43 | [pearl_trainer] epoch #21 | Time 6548.40 s 2025-03-29 15:58:43 | [pearl_trainer] epoch #21 | EpochTime 155.17 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -37.7471 MetaTest/Average/AverageReturn -37.7471 MetaTest/Average/Iteration 21 MetaTest/Average/MaxReturn -36.2567 MetaTest/Average/MinReturn -39.2374 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.49038 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.7471 MetaTest/__unnamed_task__/AverageReturn -37.7471 MetaTest/__unnamed_task__/Iteration 21 MetaTest/__unnamed_task__/MaxReturn -36.2567 MetaTest/__unnamed_task__/MinReturn -39.2374 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.49038 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 46000 ------------------------------------------------- ----------- 2025-03-29 15:59:48 | [pearl_trainer] epoch #22 | Training... 2025-03-29 16:00:05 | [pearl_trainer] epoch #22 | Evaluating... 2025-03-29 16:00:05 | [pearl_trainer] epoch #22 | Sampling for adapation and meta-testing... 2025-03-29 16:01:14 | [pearl_trainer] epoch #22 | Finished meta-testing... 2025-03-29 16:01:14 | [pearl_trainer] epoch #22 | Saving snapshot... 2025-03-29 16:01:15 | [pearl_trainer] epoch #22 | Saved 2025-03-29 16:01:15 | [pearl_trainer] epoch #22 | Time 6699.94 s 2025-03-29 16:01:15 | [pearl_trainer] epoch #22 | EpochTime 151.54 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -32.8235 MetaTest/Average/AverageReturn -32.8235 MetaTest/Average/Iteration 22 MetaTest/Average/MaxReturn -30.0118 MetaTest/Average/MinReturn -35.6351 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.81165 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -32.8235 MetaTest/__unnamed_task__/AverageReturn -32.8235 MetaTest/__unnamed_task__/Iteration 22 MetaTest/__unnamed_task__/MaxReturn -30.0118 MetaTest/__unnamed_task__/MinReturn -35.6351 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.81165 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 48000 ------------------------------------------------- ----------- 2025-03-29 16:02:18 | [pearl_trainer] epoch #23 | Training... 2025-03-29 16:02:35 | [pearl_trainer] epoch #23 | Evaluating... 2025-03-29 16:02:35 | [pearl_trainer] epoch #23 | Sampling for adapation and meta-testing... 2025-03-29 16:03:45 | [pearl_trainer] epoch #23 | Finished meta-testing... 2025-03-29 16:03:45 | [pearl_trainer] epoch #23 | Saving snapshot... 2025-03-29 16:03:46 | [pearl_trainer] epoch #23 | Saved 2025-03-29 16:03:46 | [pearl_trainer] epoch #23 | Time 6850.88 s 2025-03-29 16:03:46 | [pearl_trainer] epoch #23 | EpochTime 150.94 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.6725 MetaTest/Average/AverageReturn -33.6725 MetaTest/Average/Iteration 23 MetaTest/Average/MaxReturn -32.9533 MetaTest/Average/MinReturn -34.3917 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.719226 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.6725 MetaTest/__unnamed_task__/AverageReturn -33.6725 MetaTest/__unnamed_task__/Iteration 23 MetaTest/__unnamed_task__/MaxReturn -32.9533 MetaTest/__unnamed_task__/MinReturn -34.3917 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.719226 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 50000 ------------------------------------------------- ------------ 2025-03-29 16:04:50 | [pearl_trainer] epoch #24 | Training... 2025-03-29 16:05:06 | [pearl_trainer] epoch #24 | Evaluating... 2025-03-29 16:05:06 | [pearl_trainer] epoch #24 | Sampling for adapation and meta-testing... 2025-03-29 16:06:16 | [pearl_trainer] epoch #24 | Finished meta-testing... 2025-03-29 16:06:16 | [pearl_trainer] epoch #24 | Saving snapshot... 2025-03-29 16:06:17 | [pearl_trainer] epoch #24 | Saved 2025-03-29 16:06:17 | [pearl_trainer] epoch #24 | Time 7001.87 s 2025-03-29 16:06:17 | [pearl_trainer] epoch #24 | EpochTime 150.99 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -37.6239 MetaTest/Average/AverageReturn -37.6239 MetaTest/Average/Iteration 24 MetaTest/Average/MaxReturn -35.0424 MetaTest/Average/MinReturn -40.2054 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.58151 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.6239 MetaTest/__unnamed_task__/AverageReturn -37.6239 MetaTest/__unnamed_task__/Iteration 24 MetaTest/__unnamed_task__/MaxReturn -35.0424 MetaTest/__unnamed_task__/MinReturn -40.2054 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.58151 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 52000 ------------------------------------------------- ----------- 2025-03-29 16:07:20 | [pearl_trainer] epoch #25 | Training... 2025-03-29 16:07:35 | [pearl_trainer] epoch #25 | Evaluating... 2025-03-29 16:07:35 | [pearl_trainer] epoch #25 | Sampling for adapation and meta-testing... 2025-03-29 16:08:44 | [pearl_trainer] epoch #25 | Finished meta-testing... 2025-03-29 16:08:44 | [pearl_trainer] epoch #25 | Saving snapshot... 2025-03-29 16:08:44 | [pearl_trainer] epoch #25 | Saved 2025-03-29 16:08:44 | [pearl_trainer] epoch #25 | Time 7149.40 s 2025-03-29 16:08:44 | [pearl_trainer] epoch #25 | EpochTime 147.53 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -40.0989 MetaTest/Average/AverageReturn -40.0989 MetaTest/Average/Iteration 25 MetaTest/Average/MaxReturn -35.0731 MetaTest/Average/MinReturn -45.1246 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 5.02573 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -40.0989 MetaTest/__unnamed_task__/AverageReturn -40.0989 MetaTest/__unnamed_task__/Iteration 25 MetaTest/__unnamed_task__/MaxReturn -35.0731 MetaTest/__unnamed_task__/MinReturn -45.1246 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 5.02573 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 54000 ------------------------------------------------- ----------- 2025-03-29 16:09:47 | [pearl_trainer] epoch #26 | Training... 2025-03-29 16:10:02 | [pearl_trainer] epoch #26 | Evaluating... 2025-03-29 16:10:02 | [pearl_trainer] epoch #26 | Sampling for adapation and meta-testing... 2025-03-29 16:11:11 | [pearl_trainer] epoch #26 | Finished meta-testing... 2025-03-29 16:11:11 | [pearl_trainer] epoch #26 | Saving snapshot... 2025-03-29 16:11:12 | [pearl_trainer] epoch #26 | Saved 2025-03-29 16:11:12 | [pearl_trainer] epoch #26 | Time 7296.76 s 2025-03-29 16:11:12 | [pearl_trainer] epoch #26 | EpochTime 147.35 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.6875 MetaTest/Average/AverageReturn -33.6875 MetaTest/Average/Iteration 26 MetaTest/Average/MaxReturn -33.1244 MetaTest/Average/MinReturn -34.2506 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.563093 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.6875 MetaTest/__unnamed_task__/AverageReturn -33.6875 MetaTest/__unnamed_task__/Iteration 26 MetaTest/__unnamed_task__/MaxReturn -33.1244 MetaTest/__unnamed_task__/MinReturn -34.2506 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.563093 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 56000 ------------------------------------------------- ------------ 2025-03-29 16:12:15 | [pearl_trainer] epoch #27 | Training... 2025-03-29 16:12:30 | [pearl_trainer] epoch #27 | Evaluating... 2025-03-29 16:12:30 | [pearl_trainer] epoch #27 | Sampling for adapation and meta-testing... 2025-03-29 16:13:40 | [pearl_trainer] epoch #27 | Finished meta-testing... 2025-03-29 16:13:40 | [pearl_trainer] epoch #27 | Saving snapshot... 2025-03-29 16:13:40 | [pearl_trainer] epoch #27 | Saved 2025-03-29 16:13:40 | [pearl_trainer] epoch #27 | Time 7445.32 s 2025-03-29 16:13:40 | [pearl_trainer] epoch #27 | EpochTime 148.56 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -38.3124 MetaTest/Average/AverageReturn -38.3124 MetaTest/Average/Iteration 27 MetaTest/Average/MaxReturn -36.5136 MetaTest/Average/MinReturn -40.1112 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.79882 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.3124 MetaTest/__unnamed_task__/AverageReturn -38.3124 MetaTest/__unnamed_task__/Iteration 27 MetaTest/__unnamed_task__/MaxReturn -36.5136 MetaTest/__unnamed_task__/MinReturn -40.1112 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.79882 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 58000 ------------------------------------------------- ----------- 2025-03-29 16:14:45 | [pearl_trainer] epoch #28 | Training... 2025-03-29 16:15:02 | [pearl_trainer] epoch #28 | Evaluating... 2025-03-29 16:15:02 | [pearl_trainer] epoch #28 | Sampling for adapation and meta-testing... 2025-03-29 16:16:13 | [pearl_trainer] epoch #28 | Finished meta-testing... 2025-03-29 16:16:13 | [pearl_trainer] epoch #28 | Saving snapshot... 2025-03-29 16:16:14 | [pearl_trainer] epoch #28 | Saved 2025-03-29 16:16:14 | [pearl_trainer] epoch #28 | Time 7598.45 s 2025-03-29 16:16:14 | [pearl_trainer] epoch #28 | EpochTime 153.12 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -36.2928 MetaTest/Average/AverageReturn -36.2928 MetaTest/Average/Iteration 28 MetaTest/Average/MaxReturn -32.3222 MetaTest/Average/MinReturn -40.2635 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.97065 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.2928 MetaTest/__unnamed_task__/AverageReturn -36.2928 MetaTest/__unnamed_task__/Iteration 28 MetaTest/__unnamed_task__/MaxReturn -32.3222 MetaTest/__unnamed_task__/MinReturn -40.2635 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.97065 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 60000 ------------------------------------------------- ----------- 2025-03-29 16:17:17 | [pearl_trainer] epoch #29 | Training... 2025-03-29 16:17:34 | [pearl_trainer] epoch #29 | Evaluating... 2025-03-29 16:17:34 | [pearl_trainer] epoch #29 | Sampling for adapation and meta-testing... 2025-03-29 16:18:51 | [pearl_trainer] epoch #29 | Finished meta-testing... 2025-03-29 16:18:51 | [pearl_trainer] epoch #29 | Saving snapshot... 2025-03-29 16:18:52 | [pearl_trainer] epoch #29 | Saved 2025-03-29 16:18:52 | [pearl_trainer] epoch #29 | Time 7756.57 s 2025-03-29 16:18:52 | [pearl_trainer] epoch #29 | EpochTime 158.12 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -39.5714 MetaTest/Average/AverageReturn -39.5714 MetaTest/Average/Iteration 29 MetaTest/Average/MaxReturn -36.9528 MetaTest/Average/MinReturn -42.19 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.61859 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.5714 MetaTest/__unnamed_task__/AverageReturn -39.5714 MetaTest/__unnamed_task__/Iteration 29 MetaTest/__unnamed_task__/MaxReturn -36.9528 MetaTest/__unnamed_task__/MinReturn -42.19 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.61859 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 62000 ------------------------------------------------- ----------- 2025-03-29 16:20:02 | [pearl_trainer] epoch #30 | Training... 2025-03-29 16:20:19 | [pearl_trainer] epoch #30 | Evaluating... 2025-03-29 16:20:19 | [pearl_trainer] epoch #30 | Sampling for adapation and meta-testing... 2025-03-29 16:21:28 | [pearl_trainer] epoch #30 | Finished meta-testing... 2025-03-29 16:21:28 | [pearl_trainer] epoch #30 | Saving snapshot... 2025-03-29 16:21:29 | [pearl_trainer] epoch #30 | Saved 2025-03-29 16:21:29 | [pearl_trainer] epoch #30 | Time 7913.58 s 2025-03-29 16:21:29 | [pearl_trainer] epoch #30 | EpochTime 157.00 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -35.96 MetaTest/Average/AverageReturn -35.96 MetaTest/Average/Iteration 30 MetaTest/Average/MaxReturn -33.4676 MetaTest/Average/MinReturn -38.4525 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.49247 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.96 MetaTest/__unnamed_task__/AverageReturn -35.96 MetaTest/__unnamed_task__/Iteration 30 MetaTest/__unnamed_task__/MaxReturn -33.4676 MetaTest/__unnamed_task__/MinReturn -38.4525 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.49247 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 64000 ------------------------------------------------- ----------- 2025-03-29 16:22:31 | [pearl_trainer] epoch #31 | Training... 2025-03-29 16:22:48 | [pearl_trainer] epoch #31 | Evaluating... 2025-03-29 16:22:48 | [pearl_trainer] epoch #31 | Sampling for adapation and meta-testing... 2025-03-29 16:24:04 | [pearl_trainer] epoch #31 | Finished meta-testing... 2025-03-29 16:24:04 | [pearl_trainer] epoch #31 | Saving snapshot... 2025-03-29 16:24:05 | [pearl_trainer] epoch #31 | Saved 2025-03-29 16:24:05 | [pearl_trainer] epoch #31 | Time 8070.19 s 2025-03-29 16:24:05 | [pearl_trainer] epoch #31 | EpochTime 156.61 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -37.4498 MetaTest/Average/AverageReturn -37.4498 MetaTest/Average/Iteration 31 MetaTest/Average/MaxReturn -34.4368 MetaTest/Average/MinReturn -40.4628 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.01302 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.4498 MetaTest/__unnamed_task__/AverageReturn -37.4498 MetaTest/__unnamed_task__/Iteration 31 MetaTest/__unnamed_task__/MaxReturn -34.4368 MetaTest/__unnamed_task__/MinReturn -40.4628 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.01302 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 66000 ------------------------------------------------- ----------- 2025-03-29 16:25:12 | [pearl_trainer] epoch #32 | Training... 2025-03-29 16:25:31 | [pearl_trainer] epoch #32 | Evaluating... 2025-03-29 16:25:31 | [pearl_trainer] epoch #32 | Sampling for adapation and meta-testing... 2025-03-29 16:26:48 | [pearl_trainer] epoch #32 | Finished meta-testing... 2025-03-29 16:26:48 | [pearl_trainer] epoch #32 | Saving snapshot... 2025-03-29 16:26:49 | [pearl_trainer] epoch #32 | Saved 2025-03-29 16:26:49 | [pearl_trainer] epoch #32 | Time 8233.47 s 2025-03-29 16:26:49 | [pearl_trainer] epoch #32 | EpochTime 163.27 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -30.6989 MetaTest/Average/AverageReturn -30.6989 MetaTest/Average/Iteration 32 MetaTest/Average/MaxReturn -29.0664 MetaTest/Average/MinReturn -32.3313 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.63246 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -30.6989 MetaTest/__unnamed_task__/AverageReturn -30.6989 MetaTest/__unnamed_task__/Iteration 32 MetaTest/__unnamed_task__/MaxReturn -29.0664 MetaTest/__unnamed_task__/MinReturn -32.3313 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.63246 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 68000 ------------------------------------------------- ----------- 2025-03-29 16:27:59 | [pearl_trainer] epoch #33 | Training... 2025-03-29 16:28:17 | [pearl_trainer] epoch #33 | Evaluating... 2025-03-29 16:28:17 | [pearl_trainer] epoch #33 | Sampling for adapation and meta-testing... 2025-03-29 16:29:27 | [pearl_trainer] epoch #33 | Finished meta-testing... 2025-03-29 16:29:27 | [pearl_trainer] epoch #33 | Saving snapshot... 2025-03-29 16:29:28 | [pearl_trainer] epoch #33 | Saved 2025-03-29 16:29:28 | [pearl_trainer] epoch #33 | Time 8392.61 s 2025-03-29 16:29:28 | [pearl_trainer] epoch #33 | EpochTime 159.14 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -34.7205 MetaTest/Average/AverageReturn -34.7205 MetaTest/Average/Iteration 33 MetaTest/Average/MaxReturn -33.2211 MetaTest/Average/MinReturn -36.2199 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.49941 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.7205 MetaTest/__unnamed_task__/AverageReturn -34.7205 MetaTest/__unnamed_task__/Iteration 33 MetaTest/__unnamed_task__/MaxReturn -33.2211 MetaTest/__unnamed_task__/MinReturn -36.2199 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.49941 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 70000 ------------------------------------------------- ----------- 2025-03-29 16:30:32 | [pearl_trainer] epoch #34 | Training... 2025-03-29 16:30:49 | [pearl_trainer] epoch #34 | Evaluating... 2025-03-29 16:30:49 | [pearl_trainer] epoch #34 | Sampling for adapation and meta-testing... 2025-03-29 16:32:03 | [pearl_trainer] epoch #34 | Finished meta-testing... 2025-03-29 16:32:03 | [pearl_trainer] epoch #34 | Saving snapshot... 2025-03-29 16:32:04 | [pearl_trainer] epoch #34 | Saved 2025-03-29 16:32:04 | [pearl_trainer] epoch #34 | Time 8548.61 s 2025-03-29 16:32:04 | [pearl_trainer] epoch #34 | EpochTime 156.00 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -41.5597 MetaTest/Average/AverageReturn -41.5597 MetaTest/Average/Iteration 34 MetaTest/Average/MaxReturn -39.0648 MetaTest/Average/MinReturn -44.0547 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.49496 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -41.5597 MetaTest/__unnamed_task__/AverageReturn -41.5597 MetaTest/__unnamed_task__/Iteration 34 MetaTest/__unnamed_task__/MaxReturn -39.0648 MetaTest/__unnamed_task__/MinReturn -44.0547 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.49496 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 72000 ------------------------------------------------- ----------- 2025-03-29 16:33:10 | [pearl_trainer] epoch #35 | Training... 2025-03-29 16:33:27 | [pearl_trainer] epoch #35 | Evaluating... 2025-03-29 16:33:27 | [pearl_trainer] epoch #35 | Sampling for adapation and meta-testing... 2025-03-29 16:34:37 | [pearl_trainer] epoch #35 | Finished meta-testing... 2025-03-29 16:34:37 | [pearl_trainer] epoch #35 | Saving snapshot... 2025-03-29 16:34:38 | [pearl_trainer] epoch #35 | Saved 2025-03-29 16:34:38 | [pearl_trainer] epoch #35 | Time 8703.11 s 2025-03-29 16:34:38 | [pearl_trainer] epoch #35 | EpochTime 154.50 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -39.0659 MetaTest/Average/AverageReturn -39.0659 MetaTest/Average/Iteration 35 MetaTest/Average/MaxReturn -36.9408 MetaTest/Average/MinReturn -41.1909 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.12505 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.0659 MetaTest/__unnamed_task__/AverageReturn -39.0659 MetaTest/__unnamed_task__/Iteration 35 MetaTest/__unnamed_task__/MaxReturn -36.9408 MetaTest/__unnamed_task__/MinReturn -41.1909 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.12505 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 74000 ------------------------------------------------- ----------- 2025-03-29 16:35:43 | [pearl_trainer] epoch #36 | Training... 2025-03-29 16:36:00 | [pearl_trainer] epoch #36 | Evaluating... 2025-03-29 16:36:00 | [pearl_trainer] epoch #36 | Sampling for adapation and meta-testing... 2025-03-29 16:37:11 | [pearl_trainer] epoch #36 | Finished meta-testing... 2025-03-29 16:37:11 | [pearl_trainer] epoch #36 | Saving snapshot... 2025-03-29 16:37:12 | [pearl_trainer] epoch #36 | Saved 2025-03-29 16:37:12 | [pearl_trainer] epoch #36 | Time 8856.74 s 2025-03-29 16:37:12 | [pearl_trainer] epoch #36 | EpochTime 153.63 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -33.2438 MetaTest/Average/AverageReturn -33.2438 MetaTest/Average/Iteration 36 MetaTest/Average/MaxReturn -31.5188 MetaTest/Average/MinReturn -34.9688 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.72501 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.2438 MetaTest/__unnamed_task__/AverageReturn -33.2438 MetaTest/__unnamed_task__/Iteration 36 MetaTest/__unnamed_task__/MaxReturn -31.5188 MetaTest/__unnamed_task__/MinReturn -34.9688 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.72501 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 76000 ------------------------------------------------- ----------- 2025-03-29 16:38:16 | [pearl_trainer] epoch #37 | Training... 2025-03-29 16:38:32 | [pearl_trainer] epoch #37 | Evaluating... 2025-03-29 16:38:32 | [pearl_trainer] epoch #37 | Sampling for adapation and meta-testing... 2025-03-29 16:39:47 | [pearl_trainer] epoch #37 | Finished meta-testing... 2025-03-29 16:39:47 | [pearl_trainer] epoch #37 | Saving snapshot... 2025-03-29 16:39:48 | [pearl_trainer] epoch #37 | Saved 2025-03-29 16:39:48 | [pearl_trainer] epoch #37 | Time 9013.07 s 2025-03-29 16:39:48 | [pearl_trainer] epoch #37 | EpochTime 156.33 s ------------------------------------------------- ---------- MetaTest/Average/AverageDiscountedReturn -38.7898 MetaTest/Average/AverageReturn -38.7898 MetaTest/Average/Iteration 37 MetaTest/Average/MaxReturn -35.7543 MetaTest/Average/MinReturn -41.8253 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.0355 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.7898 MetaTest/__unnamed_task__/AverageReturn -38.7898 MetaTest/__unnamed_task__/Iteration 37 MetaTest/__unnamed_task__/MaxReturn -35.7543 MetaTest/__unnamed_task__/MinReturn -41.8253 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.0355 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 78000 ------------------------------------------------- ---------- 2025-03-29 16:40:54 | [pearl_trainer] epoch #38 | Training... 2025-03-29 16:41:11 | [pearl_trainer] epoch #38 | Evaluating... 2025-03-29 16:41:11 | [pearl_trainer] epoch #38 | Sampling for adapation and meta-testing... 2025-03-29 16:42:22 | [pearl_trainer] epoch #38 | Finished meta-testing... 2025-03-29 16:42:22 | [pearl_trainer] epoch #38 | Saving snapshot... 2025-03-29 16:42:22 | [pearl_trainer] epoch #38 | Saved 2025-03-29 16:42:22 | [pearl_trainer] epoch #38 | Time 9167.40 s 2025-03-29 16:42:22 | [pearl_trainer] epoch #38 | EpochTime 154.33 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.2735 MetaTest/Average/AverageReturn -33.2735 MetaTest/Average/Iteration 38 MetaTest/Average/MaxReturn -32.4041 MetaTest/Average/MinReturn -34.1428 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.869344 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.2735 MetaTest/__unnamed_task__/AverageReturn -33.2735 MetaTest/__unnamed_task__/Iteration 38 MetaTest/__unnamed_task__/MaxReturn -32.4041 MetaTest/__unnamed_task__/MinReturn -34.1428 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.869344 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 80000 ------------------------------------------------- ------------ 2025-03-29 16:43:26 | [pearl_trainer] epoch #39 | Training... 2025-03-29 16:43:44 | [pearl_trainer] epoch #39 | Evaluating... 2025-03-29 16:43:44 | [pearl_trainer] epoch #39 | Sampling for adapation and meta-testing... 2025-03-29 16:45:00 | [pearl_trainer] epoch #39 | Finished meta-testing... 2025-03-29 16:45:00 | [pearl_trainer] epoch #39 | Saving snapshot... 2025-03-29 16:45:01 | [pearl_trainer] epoch #39 | Saved 2025-03-29 16:45:01 | [pearl_trainer] epoch #39 | Time 9325.67 s 2025-03-29 16:45:01 | [pearl_trainer] epoch #39 | EpochTime 158.27 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.7509 MetaTest/Average/AverageReturn -33.7509 MetaTest/Average/Iteration 39 MetaTest/Average/MaxReturn -32.8239 MetaTest/Average/MinReturn -34.6779 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.926988 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.7509 MetaTest/__unnamed_task__/AverageReturn -33.7509 MetaTest/__unnamed_task__/Iteration 39 MetaTest/__unnamed_task__/MaxReturn -32.8239 MetaTest/__unnamed_task__/MinReturn -34.6779 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.926988 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 82000 ------------------------------------------------- ------------ 2025-03-29 16:46:04 | [pearl_trainer] epoch #40 | Training... 2025-03-29 16:46:22 | [pearl_trainer] epoch #40 | Evaluating... 2025-03-29 16:46:22 | [pearl_trainer] epoch #40 | Sampling for adapation and meta-testing... 2025-03-29 16:47:33 | [pearl_trainer] epoch #40 | Finished meta-testing... 2025-03-29 16:47:33 | [pearl_trainer] epoch #40 | Saving snapshot... 2025-03-29 16:47:34 | [pearl_trainer] epoch #40 | Saved 2025-03-29 16:47:34 | [pearl_trainer] epoch #40 | Time 9479.10 s 2025-03-29 16:47:34 | [pearl_trainer] epoch #40 | EpochTime 153.43 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.594 MetaTest/Average/AverageReturn -37.594 MetaTest/Average/Iteration 40 MetaTest/Average/MaxReturn -36.6477 MetaTest/Average/MinReturn -38.5402 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.946255 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.594 MetaTest/__unnamed_task__/AverageReturn -37.594 MetaTest/__unnamed_task__/Iteration 40 MetaTest/__unnamed_task__/MaxReturn -36.6477 MetaTest/__unnamed_task__/MinReturn -38.5402 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.946255 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 84000 ------------------------------------------------- ------------ 2025-03-29 16:48:38 | [pearl_trainer] epoch #41 | Training... 2025-03-29 16:48:55 | [pearl_trainer] epoch #41 | Evaluating... 2025-03-29 16:48:55 | [pearl_trainer] epoch #41 | Sampling for adapation and meta-testing... 2025-03-29 16:50:06 | [pearl_trainer] epoch #41 | Finished meta-testing... 2025-03-29 16:50:06 | [pearl_trainer] epoch #41 | Saving snapshot... 2025-03-29 16:50:07 | [pearl_trainer] epoch #41 | Saved 2025-03-29 16:50:07 | [pearl_trainer] epoch #41 | Time 9631.62 s 2025-03-29 16:50:07 | [pearl_trainer] epoch #41 | EpochTime 152.51 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -39.3521 MetaTest/Average/AverageReturn -39.3521 MetaTest/Average/Iteration 41 MetaTest/Average/MaxReturn -35.6486 MetaTest/Average/MinReturn -43.0557 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.70355 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.3521 MetaTest/__unnamed_task__/AverageReturn -39.3521 MetaTest/__unnamed_task__/Iteration 41 MetaTest/__unnamed_task__/MaxReturn -35.6486 MetaTest/__unnamed_task__/MinReturn -43.0557 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.70355 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 86000 ------------------------------------------------- ----------- 2025-03-29 16:51:11 | [pearl_trainer] epoch #42 | Training... 2025-03-29 16:51:29 | [pearl_trainer] epoch #42 | Evaluating... 2025-03-29 16:51:29 | [pearl_trainer] epoch #42 | Sampling for adapation and meta-testing... 2025-03-29 16:52:39 | [pearl_trainer] epoch #42 | Finished meta-testing... 2025-03-29 16:52:39 | [pearl_trainer] epoch #42 | Saving snapshot... 2025-03-29 16:52:40 | [pearl_trainer] epoch #42 | Saved 2025-03-29 16:52:40 | [pearl_trainer] epoch #42 | Time 9785.05 s 2025-03-29 16:52:40 | [pearl_trainer] epoch #42 | EpochTime 153.43 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -36.5353 MetaTest/Average/AverageReturn -36.5353 MetaTest/Average/Iteration 42 MetaTest/Average/MaxReturn -36.4694 MetaTest/Average/MinReturn -36.6011 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.0658613 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.5353 MetaTest/__unnamed_task__/AverageReturn -36.5353 MetaTest/__unnamed_task__/Iteration 42 MetaTest/__unnamed_task__/MaxReturn -36.4694 MetaTest/__unnamed_task__/MinReturn -36.6011 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.0658613 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 88000 ------------------------------------------------- ------------- 2025-03-29 16:53:44 | [pearl_trainer] epoch #43 | Training... 2025-03-29 16:54:02 | [pearl_trainer] epoch #43 | Evaluating... 2025-03-29 16:54:02 | [pearl_trainer] epoch #43 | Sampling for adapation and meta-testing... 2025-03-29 16:55:13 | [pearl_trainer] epoch #43 | Finished meta-testing... 2025-03-29 16:55:13 | [pearl_trainer] epoch #43 | Saving snapshot... 2025-03-29 16:55:13 | [pearl_trainer] epoch #43 | Saved 2025-03-29 16:55:13 | [pearl_trainer] epoch #43 | Time 9938.20 s 2025-03-29 16:55:13 | [pearl_trainer] epoch #43 | EpochTime 153.15 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -37.9606 MetaTest/Average/AverageReturn -37.9606 MetaTest/Average/Iteration 43 MetaTest/Average/MaxReturn -36.5722 MetaTest/Average/MinReturn -39.3489 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.38835 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.9606 MetaTest/__unnamed_task__/AverageReturn -37.9606 MetaTest/__unnamed_task__/Iteration 43 MetaTest/__unnamed_task__/MaxReturn -36.5722 MetaTest/__unnamed_task__/MinReturn -39.3489 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.38835 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 90000 ------------------------------------------------- ----------- 2025-03-29 16:56:17 | [pearl_trainer] epoch #44 | Training... 2025-03-29 16:56:34 | [pearl_trainer] epoch #44 | Evaluating... 2025-03-29 16:56:34 | [pearl_trainer] epoch #44 | Sampling for adapation and meta-testing... 2025-03-29 16:57:43 | [pearl_trainer] epoch #44 | Finished meta-testing... 2025-03-29 16:57:43 | [pearl_trainer] epoch #44 | Saving snapshot... 2025-03-29 16:57:43 | [pearl_trainer] epoch #44 | Saved 2025-03-29 16:57:43 | [pearl_trainer] epoch #44 | Time 10088.43 s 2025-03-29 16:57:43 | [pearl_trainer] epoch #44 | EpochTime 150.22 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.9831 MetaTest/Average/AverageReturn -33.9831 MetaTest/Average/Iteration 44 MetaTest/Average/MaxReturn -33.9357 MetaTest/Average/MinReturn -34.0306 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.0474847 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.9831 MetaTest/__unnamed_task__/AverageReturn -33.9831 MetaTest/__unnamed_task__/Iteration 44 MetaTest/__unnamed_task__/MaxReturn -33.9357 MetaTest/__unnamed_task__/MinReturn -34.0306 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.0474847 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 92000 ------------------------------------------------- ------------- 2025-03-29 16:58:47 | [pearl_trainer] epoch #45 | Training... 2025-03-29 16:59:04 | [pearl_trainer] epoch #45 | Evaluating... 2025-03-29 16:59:04 | [pearl_trainer] epoch #45 | Sampling for adapation and meta-testing... 2025-03-29 17:00:14 | [pearl_trainer] epoch #45 | Finished meta-testing... 2025-03-29 17:00:14 | [pearl_trainer] epoch #45 | Saving snapshot... 2025-03-29 17:00:14 | [pearl_trainer] epoch #45 | Saved 2025-03-29 17:00:14 | [pearl_trainer] epoch #45 | Time 10239.16 s 2025-03-29 17:00:14 | [pearl_trainer] epoch #45 | EpochTime 150.73 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -36.1682 MetaTest/Average/AverageReturn -36.1682 MetaTest/Average/Iteration 45 MetaTest/Average/MaxReturn -34.8124 MetaTest/Average/MinReturn -37.524 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.35582 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.1682 MetaTest/__unnamed_task__/AverageReturn -36.1682 MetaTest/__unnamed_task__/Iteration 45 MetaTest/__unnamed_task__/MaxReturn -34.8124 MetaTest/__unnamed_task__/MinReturn -37.524 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.35582 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 94000 ------------------------------------------------- ----------- 2025-03-29 17:01:18 | [pearl_trainer] epoch #46 | Training... 2025-03-29 17:01:36 | [pearl_trainer] epoch #46 | Evaluating... 2025-03-29 17:01:36 | [pearl_trainer] epoch #46 | Sampling for adapation and meta-testing... 2025-03-29 17:02:45 | [pearl_trainer] epoch #46 | Finished meta-testing... 2025-03-29 17:02:45 | [pearl_trainer] epoch #46 | Saving snapshot... 2025-03-29 17:02:46 | [pearl_trainer] epoch #46 | Saved 2025-03-29 17:02:46 | [pearl_trainer] epoch #46 | Time 10390.72 s 2025-03-29 17:02:46 | [pearl_trainer] epoch #46 | EpochTime 151.56 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.6562 MetaTest/Average/AverageReturn -35.6562 MetaTest/Average/Iteration 46 MetaTest/Average/MaxReturn -35.5316 MetaTest/Average/MinReturn -35.7807 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.124573 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.6562 MetaTest/__unnamed_task__/AverageReturn -35.6562 MetaTest/__unnamed_task__/Iteration 46 MetaTest/__unnamed_task__/MaxReturn -35.5316 MetaTest/__unnamed_task__/MinReturn -35.7807 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.124573 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 96000 ------------------------------------------------- ------------ 2025-03-29 17:03:48 | [pearl_trainer] epoch #47 | Training... 2025-03-29 17:04:05 | [pearl_trainer] epoch #47 | Evaluating... 2025-03-29 17:04:05 | [pearl_trainer] epoch #47 | Sampling for adapation and meta-testing... 2025-03-29 17:05:15 | [pearl_trainer] epoch #47 | Finished meta-testing... 2025-03-29 17:05:15 | [pearl_trainer] epoch #47 | Saving snapshot... 2025-03-29 17:05:16 | [pearl_trainer] epoch #47 | Saved 2025-03-29 17:05:16 | [pearl_trainer] epoch #47 | Time 10540.62 s 2025-03-29 17:05:16 | [pearl_trainer] epoch #47 | EpochTime 149.90 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -33.2387 MetaTest/Average/AverageReturn -33.2387 MetaTest/Average/Iteration 47 MetaTest/Average/MaxReturn -31.7126 MetaTest/Average/MinReturn -34.7649 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.52619 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.2387 MetaTest/__unnamed_task__/AverageReturn -33.2387 MetaTest/__unnamed_task__/Iteration 47 MetaTest/__unnamed_task__/MaxReturn -31.7126 MetaTest/__unnamed_task__/MinReturn -34.7649 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.52619 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 98000 ------------------------------------------------- ----------- 2025-03-29 17:06:19 | [pearl_trainer] epoch #48 | Training... 2025-03-29 17:06:35 | [pearl_trainer] epoch #48 | Evaluating... 2025-03-29 17:06:35 | [pearl_trainer] epoch #48 | Sampling for adapation and meta-testing... 2025-03-29 17:07:45 | [pearl_trainer] epoch #48 | Finished meta-testing... 2025-03-29 17:07:45 | [pearl_trainer] epoch #48 | Saving snapshot... 2025-03-29 17:07:45 | [pearl_trainer] epoch #48 | Saved 2025-03-29 17:07:45 | [pearl_trainer] epoch #48 | Time 10690.25 s 2025-03-29 17:07:45 | [pearl_trainer] epoch #48 | EpochTime 149.63 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.6111 MetaTest/Average/AverageReturn -33.6111 MetaTest/Average/Iteration 48 MetaTest/Average/MaxReturn -32.9388 MetaTest/Average/MinReturn -34.2835 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.672359 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.6111 MetaTest/__unnamed_task__/AverageReturn -33.6111 MetaTest/__unnamed_task__/Iteration 48 MetaTest/__unnamed_task__/MaxReturn -32.9388 MetaTest/__unnamed_task__/MinReturn -34.2835 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.672359 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 100000 ------------------------------------------------- ------------- 2025-03-29 17:08:49 | [pearl_trainer] epoch #49 | Training... 2025-03-29 17:09:04 | [pearl_trainer] epoch #49 | Evaluating... 2025-03-29 17:09:04 | [pearl_trainer] epoch #49 | Sampling for adapation and meta-testing... 2025-03-29 17:10:14 | [pearl_trainer] epoch #49 | Finished meta-testing... 2025-03-29 17:10:14 | [pearl_trainer] epoch #49 | Saving snapshot... 2025-03-29 17:10:15 | [pearl_trainer] epoch #49 | Saved 2025-03-29 17:10:15 | [pearl_trainer] epoch #49 | Time 10840.00 s 2025-03-29 17:10:15 | [pearl_trainer] epoch #49 | EpochTime 149.75 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -38.5599 MetaTest/Average/AverageReturn -38.5599 MetaTest/Average/Iteration 49 MetaTest/Average/MaxReturn -38.0777 MetaTest/Average/MinReturn -39.0421 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.482199 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.5599 MetaTest/__unnamed_task__/AverageReturn -38.5599 MetaTest/__unnamed_task__/Iteration 49 MetaTest/__unnamed_task__/MaxReturn -38.0777 MetaTest/__unnamed_task__/MinReturn -39.0421 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.482199 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 102000 ------------------------------------------------- ------------- 2025-03-29 17:11:19 | [pearl_trainer] epoch #50 | Training... 2025-03-29 17:11:34 | [pearl_trainer] epoch #50 | Evaluating... 2025-03-29 17:11:34 | [pearl_trainer] epoch #50 | Sampling for adapation and meta-testing... 2025-03-29 17:12:44 | [pearl_trainer] epoch #50 | Finished meta-testing... 2025-03-29 17:12:44 | [pearl_trainer] epoch #50 | Saving snapshot... 2025-03-29 17:12:45 | [pearl_trainer] epoch #50 | Saved 2025-03-29 17:12:45 | [pearl_trainer] epoch #50 | Time 10990.11 s 2025-03-29 17:12:45 | [pearl_trainer] epoch #50 | EpochTime 150.11 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.8166 MetaTest/Average/AverageReturn -33.8166 MetaTest/Average/Iteration 50 MetaTest/Average/MaxReturn -33.1082 MetaTest/Average/MinReturn -34.525 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.708393 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.8166 MetaTest/__unnamed_task__/AverageReturn -33.8166 MetaTest/__unnamed_task__/Iteration 50 MetaTest/__unnamed_task__/MaxReturn -33.1082 MetaTest/__unnamed_task__/MinReturn -34.525 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.708393 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 104000 ------------------------------------------------- ------------- 2025-03-29 17:13:49 | [pearl_trainer] epoch #51 | Training... 2025-03-29 17:14:04 | [pearl_trainer] epoch #51 | Evaluating... 2025-03-29 17:14:04 | [pearl_trainer] epoch #51 | Sampling for adapation and meta-testing... 2025-03-29 17:15:15 | [pearl_trainer] epoch #51 | Finished meta-testing... 2025-03-29 17:15:15 | [pearl_trainer] epoch #51 | Saving snapshot... 2025-03-29 17:15:15 | [pearl_trainer] epoch #51 | Saved 2025-03-29 17:15:15 | [pearl_trainer] epoch #51 | Time 11140.33 s 2025-03-29 17:15:15 | [pearl_trainer] epoch #51 | EpochTime 150.22 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.7907 MetaTest/Average/AverageReturn -38.7907 MetaTest/Average/Iteration 51 MetaTest/Average/MaxReturn -37.6489 MetaTest/Average/MinReturn -39.9326 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.14186 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.7907 MetaTest/__unnamed_task__/AverageReturn -38.7907 MetaTest/__unnamed_task__/Iteration 51 MetaTest/__unnamed_task__/MaxReturn -37.6489 MetaTest/__unnamed_task__/MinReturn -39.9326 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.14186 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 106000 ------------------------------------------------- ------------ 2025-03-29 17:16:19 | [pearl_trainer] epoch #52 | Training... 2025-03-29 17:16:35 | [pearl_trainer] epoch #52 | Evaluating... 2025-03-29 17:16:35 | [pearl_trainer] epoch #52 | Sampling for adapation and meta-testing... 2025-03-29 17:17:44 | [pearl_trainer] epoch #52 | Finished meta-testing... 2025-03-29 17:17:44 | [pearl_trainer] epoch #52 | Saving snapshot... 2025-03-29 17:17:45 | [pearl_trainer] epoch #52 | Saved 2025-03-29 17:17:45 | [pearl_trainer] epoch #52 | Time 11290.02 s 2025-03-29 17:17:45 | [pearl_trainer] epoch #52 | EpochTime 149.69 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.9007 MetaTest/Average/AverageReturn -35.9007 MetaTest/Average/Iteration 52 MetaTest/Average/MaxReturn -35.6193 MetaTest/Average/MinReturn -36.182 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.281349 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.9007 MetaTest/__unnamed_task__/AverageReturn -35.9007 MetaTest/__unnamed_task__/Iteration 52 MetaTest/__unnamed_task__/MaxReturn -35.6193 MetaTest/__unnamed_task__/MinReturn -36.182 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.281349 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 108000 ------------------------------------------------- ------------- 2025-03-29 17:18:49 | [pearl_trainer] epoch #53 | Training... 2025-03-29 17:19:04 | [pearl_trainer] epoch #53 | Evaluating... 2025-03-29 17:19:04 | [pearl_trainer] epoch #53 | Sampling for adapation and meta-testing... 2025-03-29 17:20:14 | [pearl_trainer] epoch #53 | Finished meta-testing... 2025-03-29 17:20:14 | [pearl_trainer] epoch #53 | Saving snapshot... 2025-03-29 17:20:14 | [pearl_trainer] epoch #53 | Saved 2025-03-29 17:20:14 | [pearl_trainer] epoch #53 | Time 11439.14 s 2025-03-29 17:20:14 | [pearl_trainer] epoch #53 | EpochTime 149.12 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.6951 MetaTest/Average/AverageReturn -34.6951 MetaTest/Average/Iteration 53 MetaTest/Average/MaxReturn -34.352 MetaTest/Average/MinReturn -35.0383 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.343147 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.6951 MetaTest/__unnamed_task__/AverageReturn -34.6951 MetaTest/__unnamed_task__/Iteration 53 MetaTest/__unnamed_task__/MaxReturn -34.352 MetaTest/__unnamed_task__/MinReturn -35.0383 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.343147 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 110000 ------------------------------------------------- ------------- 2025-03-29 17:21:18 | [pearl_trainer] epoch #54 | Training... 2025-03-29 17:21:33 | [pearl_trainer] epoch #54 | Evaluating... 2025-03-29 17:21:33 | [pearl_trainer] epoch #54 | Sampling for adapation and meta-testing... 2025-03-29 17:22:44 | [pearl_trainer] epoch #54 | Finished meta-testing... 2025-03-29 17:22:44 | [pearl_trainer] epoch #54 | Saving snapshot... 2025-03-29 17:22:44 | [pearl_trainer] epoch #54 | Saved 2025-03-29 17:22:44 | [pearl_trainer] epoch #54 | Time 11589.41 s 2025-03-29 17:22:44 | [pearl_trainer] epoch #54 | EpochTime 150.26 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.9638 MetaTest/Average/AverageReturn -34.9638 MetaTest/Average/Iteration 54 MetaTest/Average/MaxReturn -34.5161 MetaTest/Average/MinReturn -35.4116 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.447714 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.9638 MetaTest/__unnamed_task__/AverageReturn -34.9638 MetaTest/__unnamed_task__/Iteration 54 MetaTest/__unnamed_task__/MaxReturn -34.5161 MetaTest/__unnamed_task__/MinReturn -35.4116 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.447714 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 112000 ------------------------------------------------- ------------- 2025-03-29 17:23:48 | [pearl_trainer] epoch #55 | Training... 2025-03-29 17:24:05 | [pearl_trainer] epoch #55 | Evaluating... 2025-03-29 17:24:05 | [pearl_trainer] epoch #55 | Sampling for adapation and meta-testing... 2025-03-29 17:25:14 | [pearl_trainer] epoch #55 | Finished meta-testing... 2025-03-29 17:25:14 | [pearl_trainer] epoch #55 | Saving snapshot... 2025-03-29 17:25:14 | [pearl_trainer] epoch #55 | Saved 2025-03-29 17:25:14 | [pearl_trainer] epoch #55 | Time 11739.36 s 2025-03-29 17:25:14 | [pearl_trainer] epoch #55 | EpochTime 149.94 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.797 MetaTest/Average/AverageReturn -36.797 MetaTest/Average/Iteration 55 MetaTest/Average/MaxReturn -33.2251 MetaTest/Average/MinReturn -40.369 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.57195 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.797 MetaTest/__unnamed_task__/AverageReturn -36.797 MetaTest/__unnamed_task__/Iteration 55 MetaTest/__unnamed_task__/MaxReturn -33.2251 MetaTest/__unnamed_task__/MinReturn -40.369 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.57195 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 114000 ------------------------------------------------- ------------ 2025-03-29 17:26:17 | [pearl_trainer] epoch #56 | Training... 2025-03-29 17:26:34 | [pearl_trainer] epoch #56 | Evaluating... 2025-03-29 17:26:34 | [pearl_trainer] epoch #56 | Sampling for adapation and meta-testing... 2025-03-29 17:27:43 | [pearl_trainer] epoch #56 | Finished meta-testing... 2025-03-29 17:27:43 | [pearl_trainer] epoch #56 | Saving snapshot... 2025-03-29 17:27:44 | [pearl_trainer] epoch #56 | Saved 2025-03-29 17:27:44 | [pearl_trainer] epoch #56 | Time 11888.81 s 2025-03-29 17:27:44 | [pearl_trainer] epoch #56 | EpochTime 149.45 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.5857 MetaTest/Average/AverageReturn -38.5857 MetaTest/Average/Iteration 56 MetaTest/Average/MaxReturn -36.303 MetaTest/Average/MinReturn -40.8683 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.28266 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.5857 MetaTest/__unnamed_task__/AverageReturn -38.5857 MetaTest/__unnamed_task__/Iteration 56 MetaTest/__unnamed_task__/MaxReturn -36.303 MetaTest/__unnamed_task__/MinReturn -40.8683 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.28266 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 116000 ------------------------------------------------- ------------ 2025-03-29 17:28:47 | [pearl_trainer] epoch #57 | Training... 2025-03-29 17:29:04 | [pearl_trainer] epoch #57 | Evaluating... 2025-03-29 17:29:04 | [pearl_trainer] epoch #57 | Sampling for adapation and meta-testing... 2025-03-29 17:30:13 | [pearl_trainer] epoch #57 | Finished meta-testing... 2025-03-29 17:30:13 | [pearl_trainer] epoch #57 | Saving snapshot... 2025-03-29 17:30:14 | [pearl_trainer] epoch #57 | Saved 2025-03-29 17:30:14 | [pearl_trainer] epoch #57 | Time 12039.15 s 2025-03-29 17:30:14 | [pearl_trainer] epoch #57 | EpochTime 150.34 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -39.5793 MetaTest/Average/AverageReturn -39.5793 MetaTest/Average/Iteration 57 MetaTest/Average/MaxReturn -38.9961 MetaTest/Average/MinReturn -40.1624 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.583144 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.5793 MetaTest/__unnamed_task__/AverageReturn -39.5793 MetaTest/__unnamed_task__/Iteration 57 MetaTest/__unnamed_task__/MaxReturn -38.9961 MetaTest/__unnamed_task__/MinReturn -40.1624 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.583144 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 118000 ------------------------------------------------- ------------- 2025-03-29 17:31:18 | [pearl_trainer] epoch #58 | Training... 2025-03-29 17:31:35 | [pearl_trainer] epoch #58 | Evaluating... 2025-03-29 17:31:35 | [pearl_trainer] epoch #58 | Sampling for adapation and meta-testing... 2025-03-29 17:32:44 | [pearl_trainer] epoch #58 | Finished meta-testing... 2025-03-29 17:32:44 | [pearl_trainer] epoch #58 | Saving snapshot... 2025-03-29 17:32:45 | [pearl_trainer] epoch #58 | Saved 2025-03-29 17:32:45 | [pearl_trainer] epoch #58 | Time 12190.03 s 2025-03-29 17:32:45 | [pearl_trainer] epoch #58 | EpochTime 150.88 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -42.0882 MetaTest/Average/AverageReturn -42.0882 MetaTest/Average/Iteration 58 MetaTest/Average/MaxReturn -41.4576 MetaTest/Average/MinReturn -42.7187 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.630519 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -42.0882 MetaTest/__unnamed_task__/AverageReturn -42.0882 MetaTest/__unnamed_task__/Iteration 58 MetaTest/__unnamed_task__/MaxReturn -41.4576 MetaTest/__unnamed_task__/MinReturn -42.7187 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.630519 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 120000 ------------------------------------------------- ------------- 2025-03-29 17:33:48 | [pearl_trainer] epoch #59 | Training... 2025-03-29 17:34:05 | [pearl_trainer] epoch #59 | Evaluating... 2025-03-29 17:34:05 | [pearl_trainer] epoch #59 | Sampling for adapation and meta-testing... 2025-03-29 17:35:13 | [pearl_trainer] epoch #59 | Finished meta-testing... 2025-03-29 17:35:13 | [pearl_trainer] epoch #59 | Saving snapshot... 2025-03-29 17:35:14 | [pearl_trainer] epoch #59 | Saved 2025-03-29 17:35:14 | [pearl_trainer] epoch #59 | Time 12339.02 s 2025-03-29 17:35:14 | [pearl_trainer] epoch #59 | EpochTime 148.98 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.0259 MetaTest/Average/AverageReturn -34.0259 MetaTest/Average/Iteration 59 MetaTest/Average/MaxReturn -32.6258 MetaTest/Average/MinReturn -35.426 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.40013 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.0259 MetaTest/__unnamed_task__/AverageReturn -34.0259 MetaTest/__unnamed_task__/Iteration 59 MetaTest/__unnamed_task__/MaxReturn -32.6258 MetaTest/__unnamed_task__/MinReturn -35.426 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.40013 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 122000 ------------------------------------------------- ------------ 2025-03-29 17:36:17 | [pearl_trainer] epoch #60 | Training... 2025-03-29 17:36:34 | [pearl_trainer] epoch #60 | Evaluating... 2025-03-29 17:36:34 | [pearl_trainer] epoch #60 | Sampling for adapation and meta-testing... 2025-03-29 17:37:43 | [pearl_trainer] epoch #60 | Finished meta-testing... 2025-03-29 17:37:43 | [pearl_trainer] epoch #60 | Saving snapshot... 2025-03-29 17:37:44 | [pearl_trainer] epoch #60 | Saved 2025-03-29 17:37:44 | [pearl_trainer] epoch #60 | Time 12488.61 s 2025-03-29 17:37:44 | [pearl_trainer] epoch #60 | EpochTime 149.59 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -37.665 MetaTest/Average/AverageReturn -37.665 MetaTest/Average/Iteration 60 MetaTest/Average/MaxReturn -37.2925 MetaTest/Average/MinReturn -38.0375 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.372532 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.665 MetaTest/__unnamed_task__/AverageReturn -37.665 MetaTest/__unnamed_task__/Iteration 60 MetaTest/__unnamed_task__/MaxReturn -37.2925 MetaTest/__unnamed_task__/MinReturn -38.0375 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.372532 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 124000 ------------------------------------------------- ------------- 2025-03-29 17:38:47 | [pearl_trainer] epoch #61 | Training... 2025-03-29 17:39:04 | [pearl_trainer] epoch #61 | Evaluating... 2025-03-29 17:39:04 | [pearl_trainer] epoch #61 | Sampling for adapation and meta-testing... 2025-03-29 17:40:13 | [pearl_trainer] epoch #61 | Finished meta-testing... 2025-03-29 17:40:13 | [pearl_trainer] epoch #61 | Saving snapshot... 2025-03-29 17:40:14 | [pearl_trainer] epoch #61 | Saved 2025-03-29 17:40:14 | [pearl_trainer] epoch #61 | Time 12638.68 s 2025-03-29 17:40:14 | [pearl_trainer] epoch #61 | EpochTime 150.07 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.5344 MetaTest/Average/AverageReturn -34.5344 MetaTest/Average/Iteration 61 MetaTest/Average/MaxReturn -34.3289 MetaTest/Average/MinReturn -34.7399 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.205506 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.5344 MetaTest/__unnamed_task__/AverageReturn -34.5344 MetaTest/__unnamed_task__/Iteration 61 MetaTest/__unnamed_task__/MaxReturn -34.3289 MetaTest/__unnamed_task__/MinReturn -34.7399 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.205506 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 126000 ------------------------------------------------- ------------- 2025-03-29 17:41:17 | [pearl_trainer] epoch #62 | Training... 2025-03-29 17:41:33 | [pearl_trainer] epoch #62 | Evaluating... 2025-03-29 17:41:33 | [pearl_trainer] epoch #62 | Sampling for adapation and meta-testing... 2025-03-29 17:42:42 | [pearl_trainer] epoch #62 | Finished meta-testing... 2025-03-29 17:42:42 | [pearl_trainer] epoch #62 | Saving snapshot... 2025-03-29 17:42:43 | [pearl_trainer] epoch #62 | Saved 2025-03-29 17:42:43 | [pearl_trainer] epoch #62 | Time 12787.52 s 2025-03-29 17:42:43 | [pearl_trainer] epoch #62 | EpochTime 148.84 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.6482 MetaTest/Average/AverageReturn -35.6482 MetaTest/Average/Iteration 62 MetaTest/Average/MaxReturn -34.3587 MetaTest/Average/MinReturn -36.9376 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.28941 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.6482 MetaTest/__unnamed_task__/AverageReturn -35.6482 MetaTest/__unnamed_task__/Iteration 62 MetaTest/__unnamed_task__/MaxReturn -34.3587 MetaTest/__unnamed_task__/MinReturn -36.9376 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.28941 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 128000 ------------------------------------------------- ------------ 2025-03-29 17:43:46 | [pearl_trainer] epoch #63 | Training... 2025-03-29 17:44:03 | [pearl_trainer] epoch #63 | Evaluating... 2025-03-29 17:44:03 | [pearl_trainer] epoch #63 | Sampling for adapation and meta-testing... 2025-03-29 17:45:12 | [pearl_trainer] epoch #63 | Finished meta-testing... 2025-03-29 17:45:12 | [pearl_trainer] epoch #63 | Saving snapshot... 2025-03-29 17:45:13 | [pearl_trainer] epoch #63 | Saved 2025-03-29 17:45:13 | [pearl_trainer] epoch #63 | Time 12938.17 s 2025-03-29 17:45:13 | [pearl_trainer] epoch #63 | EpochTime 150.64 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.5574 MetaTest/Average/AverageReturn -35.5574 MetaTest/Average/Iteration 63 MetaTest/Average/MaxReturn -35.4226 MetaTest/Average/MinReturn -35.6922 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.134809 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.5574 MetaTest/__unnamed_task__/AverageReturn -35.5574 MetaTest/__unnamed_task__/Iteration 63 MetaTest/__unnamed_task__/MaxReturn -35.4226 MetaTest/__unnamed_task__/MinReturn -35.6922 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.134809 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 130000 ------------------------------------------------- ------------- 2025-03-29 17:46:17 | [pearl_trainer] epoch #64 | Training... 2025-03-29 17:46:35 | [pearl_trainer] epoch #64 | Evaluating... 2025-03-29 17:46:35 | [pearl_trainer] epoch #64 | Sampling for adapation and meta-testing... 2025-03-29 17:47:44 | [pearl_trainer] epoch #64 | Finished meta-testing... 2025-03-29 17:47:44 | [pearl_trainer] epoch #64 | Saving snapshot... 2025-03-29 17:47:45 | [pearl_trainer] epoch #64 | Saved 2025-03-29 17:47:45 | [pearl_trainer] epoch #64 | Time 13089.92 s 2025-03-29 17:47:45 | [pearl_trainer] epoch #64 | EpochTime 151.75 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.0607 MetaTest/Average/AverageReturn -34.0607 MetaTest/Average/Iteration 64 MetaTest/Average/MaxReturn -33.2208 MetaTest/Average/MinReturn -34.9006 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.839858 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.0607 MetaTest/__unnamed_task__/AverageReturn -34.0607 MetaTest/__unnamed_task__/Iteration 64 MetaTest/__unnamed_task__/MaxReturn -33.2208 MetaTest/__unnamed_task__/MinReturn -34.9006 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.839858 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 132000 ------------------------------------------------- ------------- 2025-03-29 17:48:48 | [pearl_trainer] epoch #65 | Training... 2025-03-29 17:49:06 | [pearl_trainer] epoch #65 | Evaluating... 2025-03-29 17:49:06 | [pearl_trainer] epoch #65 | Sampling for adapation and meta-testing... 2025-03-29 17:50:15 | [pearl_trainer] epoch #65 | Finished meta-testing... 2025-03-29 17:50:15 | [pearl_trainer] epoch #65 | Saving snapshot... 2025-03-29 17:50:16 | [pearl_trainer] epoch #65 | Saved 2025-03-29 17:50:16 | [pearl_trainer] epoch #65 | Time 13240.95 s 2025-03-29 17:50:16 | [pearl_trainer] epoch #65 | EpochTime 151.03 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -39.6105 MetaTest/Average/AverageReturn -39.6105 MetaTest/Average/Iteration 65 MetaTest/Average/MaxReturn -32.7996 MetaTest/Average/MinReturn -46.4213 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 6.81087 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.6105 MetaTest/__unnamed_task__/AverageReturn -39.6105 MetaTest/__unnamed_task__/Iteration 65 MetaTest/__unnamed_task__/MaxReturn -32.7996 MetaTest/__unnamed_task__/MinReturn -46.4213 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 6.81087 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 134000 ------------------------------------------------- ------------ 2025-03-29 17:51:19 | [pearl_trainer] epoch #66 | Training... 2025-03-29 17:51:35 | [pearl_trainer] epoch #66 | Evaluating... 2025-03-29 17:51:35 | [pearl_trainer] epoch #66 | Sampling for adapation and meta-testing... 2025-03-29 17:52:47 | [pearl_trainer] epoch #66 | Finished meta-testing... 2025-03-29 17:52:47 | [pearl_trainer] epoch #66 | Saving snapshot... 2025-03-29 17:52:48 | [pearl_trainer] epoch #66 | Saved 2025-03-29 17:52:48 | [pearl_trainer] epoch #66 | Time 13392.48 s 2025-03-29 17:52:48 | [pearl_trainer] epoch #66 | EpochTime 151.52 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.7861 MetaTest/Average/AverageReturn -38.7861 MetaTest/Average/Iteration 66 MetaTest/Average/MaxReturn -37.1374 MetaTest/Average/MinReturn -40.4347 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.64866 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.7861 MetaTest/__unnamed_task__/AverageReturn -38.7861 MetaTest/__unnamed_task__/Iteration 66 MetaTest/__unnamed_task__/MaxReturn -37.1374 MetaTest/__unnamed_task__/MinReturn -40.4347 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.64866 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 136000 ------------------------------------------------- ------------ 2025-03-29 17:53:52 | [pearl_trainer] epoch #67 | Training... 2025-03-29 17:54:08 | [pearl_trainer] epoch #67 | Evaluating... 2025-03-29 17:54:08 | [pearl_trainer] epoch #67 | Sampling for adapation and meta-testing... 2025-03-29 17:55:20 | [pearl_trainer] epoch #67 | Finished meta-testing... 2025-03-29 17:55:20 | [pearl_trainer] epoch #67 | Saving snapshot... 2025-03-29 17:55:21 | [pearl_trainer] epoch #67 | Saved 2025-03-29 17:55:21 | [pearl_trainer] epoch #67 | Time 13545.66 s 2025-03-29 17:55:21 | [pearl_trainer] epoch #67 | EpochTime 153.18 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -38.6991 MetaTest/Average/AverageReturn -38.6991 MetaTest/Average/Iteration 67 MetaTest/Average/MaxReturn -38.3232 MetaTest/Average/MinReturn -39.0751 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.375973 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.6991 MetaTest/__unnamed_task__/AverageReturn -38.6991 MetaTest/__unnamed_task__/Iteration 67 MetaTest/__unnamed_task__/MaxReturn -38.3232 MetaTest/__unnamed_task__/MinReturn -39.0751 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.375973 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 138000 ------------------------------------------------- ------------- 2025-03-29 17:56:25 | [pearl_trainer] epoch #68 | Training... 2025-03-29 17:56:41 | [pearl_trainer] epoch #68 | Evaluating... 2025-03-29 17:56:41 | [pearl_trainer] epoch #68 | Sampling for adapation and meta-testing... 2025-03-29 17:57:52 | [pearl_trainer] epoch #68 | Finished meta-testing... 2025-03-29 17:57:52 | [pearl_trainer] epoch #68 | Saving snapshot... 2025-03-29 17:57:53 | [pearl_trainer] epoch #68 | Saved 2025-03-29 17:57:53 | [pearl_trainer] epoch #68 | Time 13697.75 s 2025-03-29 17:57:53 | [pearl_trainer] epoch #68 | EpochTime 152.09 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -32.7585 MetaTest/Average/AverageReturn -32.7585 MetaTest/Average/Iteration 68 MetaTest/Average/MaxReturn -30.4237 MetaTest/Average/MinReturn -35.0933 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.33483 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -32.7585 MetaTest/__unnamed_task__/AverageReturn -32.7585 MetaTest/__unnamed_task__/Iteration 68 MetaTest/__unnamed_task__/MaxReturn -30.4237 MetaTest/__unnamed_task__/MinReturn -35.0933 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.33483 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 140000 ------------------------------------------------- ------------ 2025-03-29 17:58:57 | [pearl_trainer] epoch #69 | Training... 2025-03-29 17:59:14 | [pearl_trainer] epoch #69 | Evaluating... 2025-03-29 17:59:14 | [pearl_trainer] epoch #69 | Sampling for adapation and meta-testing... 2025-03-29 18:00:24 | [pearl_trainer] epoch #69 | Finished meta-testing... 2025-03-29 18:00:24 | [pearl_trainer] epoch #69 | Saving snapshot... 2025-03-29 18:00:25 | [pearl_trainer] epoch #69 | Saved 2025-03-29 18:00:25 | [pearl_trainer] epoch #69 | Time 13849.82 s 2025-03-29 18:00:25 | [pearl_trainer] epoch #69 | EpochTime 152.07 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -32.2883 MetaTest/Average/AverageReturn -32.2883 MetaTest/Average/Iteration 69 MetaTest/Average/MaxReturn -31.1927 MetaTest/Average/MinReturn -33.3839 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.09557 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -32.2883 MetaTest/__unnamed_task__/AverageReturn -32.2883 MetaTest/__unnamed_task__/Iteration 69 MetaTest/__unnamed_task__/MaxReturn -31.1927 MetaTest/__unnamed_task__/MinReturn -33.3839 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.09557 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 142000 ------------------------------------------------- ------------ 2025-03-29 18:01:30 | [pearl_trainer] epoch #70 | Training... 2025-03-29 18:01:47 | [pearl_trainer] epoch #70 | Evaluating... 2025-03-29 18:01:47 | [pearl_trainer] epoch #70 | Sampling for adapation and meta-testing... 2025-03-29 18:02:57 | [pearl_trainer] epoch #70 | Finished meta-testing... 2025-03-29 18:02:57 | [pearl_trainer] epoch #70 | Saving snapshot... 2025-03-29 18:02:57 | [pearl_trainer] epoch #70 | Saved 2025-03-29 18:02:57 | [pearl_trainer] epoch #70 | Time 14002.24 s 2025-03-29 18:02:57 | [pearl_trainer] epoch #70 | EpochTime 152.42 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -32.5806 MetaTest/Average/AverageReturn -32.5806 MetaTest/Average/Iteration 70 MetaTest/Average/MaxReturn -27.7225 MetaTest/Average/MinReturn -37.4387 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.85809 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -32.5806 MetaTest/__unnamed_task__/AverageReturn -32.5806 MetaTest/__unnamed_task__/Iteration 70 MetaTest/__unnamed_task__/MaxReturn -27.7225 MetaTest/__unnamed_task__/MinReturn -37.4387 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.85809 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 144000 ------------------------------------------------- ------------ 2025-03-29 18:04:00 | [pearl_trainer] epoch #71 | Training... 2025-03-29 18:04:17 | [pearl_trainer] epoch #71 | Evaluating... 2025-03-29 18:04:17 | [pearl_trainer] epoch #71 | Sampling for adapation and meta-testing... 2025-03-29 18:05:27 | [pearl_trainer] epoch #71 | Finished meta-testing... 2025-03-29 18:05:27 | [pearl_trainer] epoch #71 | Saving snapshot... 2025-03-29 18:05:28 | [pearl_trainer] epoch #71 | Saved 2025-03-29 18:05:28 | [pearl_trainer] epoch #71 | Time 14152.53 s 2025-03-29 18:05:28 | [pearl_trainer] epoch #71 | EpochTime 150.29 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.2466 MetaTest/Average/AverageReturn -34.2466 MetaTest/Average/Iteration 71 MetaTest/Average/MaxReturn -33.4009 MetaTest/Average/MinReturn -35.0924 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.845756 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.2466 MetaTest/__unnamed_task__/AverageReturn -34.2466 MetaTest/__unnamed_task__/Iteration 71 MetaTest/__unnamed_task__/MaxReturn -33.4009 MetaTest/__unnamed_task__/MinReturn -35.0924 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.845756 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 146000 ------------------------------------------------- ------------- 2025-03-29 18:06:30 | [pearl_trainer] epoch #72 | Training... 2025-03-29 18:06:45 | [pearl_trainer] epoch #72 | Evaluating... 2025-03-29 18:06:45 | [pearl_trainer] epoch #72 | Sampling for adapation and meta-testing... 2025-03-29 18:07:55 | [pearl_trainer] epoch #72 | Finished meta-testing... 2025-03-29 18:07:55 | [pearl_trainer] epoch #72 | Saving snapshot... 2025-03-29 18:07:56 | [pearl_trainer] epoch #72 | Saved 2025-03-29 18:07:56 | [pearl_trainer] epoch #72 | Time 14301.22 s 2025-03-29 18:07:56 | [pearl_trainer] epoch #72 | EpochTime 148.69 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.5957 MetaTest/Average/AverageReturn -36.5957 MetaTest/Average/Iteration 72 MetaTest/Average/MaxReturn -32.9338 MetaTest/Average/MinReturn -40.2575 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.66184 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.5957 MetaTest/__unnamed_task__/AverageReturn -36.5957 MetaTest/__unnamed_task__/Iteration 72 MetaTest/__unnamed_task__/MaxReturn -32.9338 MetaTest/__unnamed_task__/MinReturn -40.2575 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.66184 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 148000 ------------------------------------------------- ------------ 2025-03-29 18:09:00 | [pearl_trainer] epoch #73 | Training... 2025-03-29 18:09:16 | [pearl_trainer] epoch #73 | Evaluating... 2025-03-29 18:09:16 | [pearl_trainer] epoch #73 | Sampling for adapation and meta-testing... 2025-03-29 18:10:28 | [pearl_trainer] epoch #73 | Finished meta-testing... 2025-03-29 18:10:28 | [pearl_trainer] epoch #73 | Saving snapshot... 2025-03-29 18:10:29 | [pearl_trainer] epoch #73 | Saved 2025-03-29 18:10:29 | [pearl_trainer] epoch #73 | Time 14453.81 s 2025-03-29 18:10:29 | [pearl_trainer] epoch #73 | EpochTime 152.59 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.5441 MetaTest/Average/AverageReturn -34.5441 MetaTest/Average/Iteration 73 MetaTest/Average/MaxReturn -34.3955 MetaTest/Average/MinReturn -34.6928 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.148631 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.5441 MetaTest/__unnamed_task__/AverageReturn -34.5441 MetaTest/__unnamed_task__/Iteration 73 MetaTest/__unnamed_task__/MaxReturn -34.3955 MetaTest/__unnamed_task__/MinReturn -34.6928 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.148631 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 150000 ------------------------------------------------- ------------- 2025-03-29 18:11:34 | [pearl_trainer] epoch #74 | Training... 2025-03-29 18:11:52 | [pearl_trainer] epoch #74 | Evaluating... 2025-03-29 18:11:52 | [pearl_trainer] epoch #74 | Sampling for adapation and meta-testing... 2025-03-29 18:13:03 | [pearl_trainer] epoch #74 | Finished meta-testing... 2025-03-29 18:13:03 | [pearl_trainer] epoch #74 | Saving snapshot... 2025-03-29 18:13:03 | [pearl_trainer] epoch #74 | Saved 2025-03-29 18:13:03 | [pearl_trainer] epoch #74 | Time 14608.17 s 2025-03-29 18:13:03 | [pearl_trainer] epoch #74 | EpochTime 154.35 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -32.9321 MetaTest/Average/AverageReturn -32.9321 MetaTest/Average/Iteration 74 MetaTest/Average/MaxReturn -32.3053 MetaTest/Average/MinReturn -33.5589 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.626757 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -32.9321 MetaTest/__unnamed_task__/AverageReturn -32.9321 MetaTest/__unnamed_task__/Iteration 74 MetaTest/__unnamed_task__/MaxReturn -32.3053 MetaTest/__unnamed_task__/MinReturn -33.5589 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.626757 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 152000 ------------------------------------------------- ------------- 2025-03-29 18:14:07 | [pearl_trainer] epoch #75 | Training... 2025-03-29 18:14:24 | [pearl_trainer] epoch #75 | Evaluating... 2025-03-29 18:14:24 | [pearl_trainer] epoch #75 | Sampling for adapation and meta-testing... 2025-03-29 18:15:34 | [pearl_trainer] epoch #75 | Finished meta-testing... 2025-03-29 18:15:34 | [pearl_trainer] epoch #75 | Saving snapshot... 2025-03-29 18:15:35 | [pearl_trainer] epoch #75 | Saved 2025-03-29 18:15:35 | [pearl_trainer] epoch #75 | Time 14760.01 s 2025-03-29 18:15:35 | [pearl_trainer] epoch #75 | EpochTime 151.84 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -37.8601 MetaTest/Average/AverageReturn -37.8601 MetaTest/Average/Iteration 75 MetaTest/Average/MaxReturn -37.5516 MetaTest/Average/MinReturn -38.1685 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.308448 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.8601 MetaTest/__unnamed_task__/AverageReturn -37.8601 MetaTest/__unnamed_task__/Iteration 75 MetaTest/__unnamed_task__/MaxReturn -37.5516 MetaTest/__unnamed_task__/MinReturn -38.1685 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.308448 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 154000 ------------------------------------------------- ------------- 2025-03-29 18:16:39 | [pearl_trainer] epoch #76 | Training... 2025-03-29 18:16:55 | [pearl_trainer] epoch #76 | Evaluating... 2025-03-29 18:16:55 | [pearl_trainer] epoch #76 | Sampling for adapation and meta-testing... 2025-03-29 18:18:05 | [pearl_trainer] epoch #76 | Finished meta-testing... 2025-03-29 18:18:05 | [pearl_trainer] epoch #76 | Saving snapshot... 2025-03-29 18:18:06 | [pearl_trainer] epoch #76 | Saved 2025-03-29 18:18:06 | [pearl_trainer] epoch #76 | Time 14910.96 s 2025-03-29 18:18:06 | [pearl_trainer] epoch #76 | EpochTime 150.94 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -35.653 MetaTest/Average/AverageReturn -35.653 MetaTest/Average/Iteration 76 MetaTest/Average/MaxReturn -34.1432 MetaTest/Average/MinReturn -37.1628 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.5098 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.653 MetaTest/__unnamed_task__/AverageReturn -35.653 MetaTest/__unnamed_task__/Iteration 76 MetaTest/__unnamed_task__/MaxReturn -34.1432 MetaTest/__unnamed_task__/MinReturn -37.1628 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.5098 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 156000 ------------------------------------------------- ----------- 2025-03-29 18:19:09 | [pearl_trainer] epoch #77 | Training... 2025-03-29 18:19:25 | [pearl_trainer] epoch #77 | Evaluating... 2025-03-29 18:19:25 | [pearl_trainer] epoch #77 | Sampling for adapation and meta-testing... 2025-03-29 18:20:35 | [pearl_trainer] epoch #77 | Finished meta-testing... 2025-03-29 18:20:35 | [pearl_trainer] epoch #77 | Saving snapshot... 2025-03-29 18:20:35 | [pearl_trainer] epoch #77 | Saved 2025-03-29 18:20:35 | [pearl_trainer] epoch #77 | Time 15060.25 s 2025-03-29 18:20:35 | [pearl_trainer] epoch #77 | EpochTime 149.29 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.1953 MetaTest/Average/AverageReturn -35.1953 MetaTest/Average/Iteration 77 MetaTest/Average/MaxReturn -33.2371 MetaTest/Average/MinReturn -37.1536 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.95822 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.1953 MetaTest/__unnamed_task__/AverageReturn -35.1953 MetaTest/__unnamed_task__/Iteration 77 MetaTest/__unnamed_task__/MaxReturn -33.2371 MetaTest/__unnamed_task__/MinReturn -37.1536 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.95822 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 158000 ------------------------------------------------- ------------ 2025-03-29 18:21:38 | [pearl_trainer] epoch #78 | Training... 2025-03-29 18:21:54 | [pearl_trainer] epoch #78 | Evaluating... 2025-03-29 18:21:54 | [pearl_trainer] epoch #78 | Sampling for adapation and meta-testing... 2025-03-29 18:23:03 | [pearl_trainer] epoch #78 | Finished meta-testing... 2025-03-29 18:23:03 | [pearl_trainer] epoch #78 | Saving snapshot... 2025-03-29 18:23:04 | [pearl_trainer] epoch #78 | Saved 2025-03-29 18:23:04 | [pearl_trainer] epoch #78 | Time 15208.57 s 2025-03-29 18:23:04 | [pearl_trainer] epoch #78 | EpochTime 148.32 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -34.9262 MetaTest/Average/AverageReturn -34.9262 MetaTest/Average/Iteration 78 MetaTest/Average/MaxReturn -32.5776 MetaTest/Average/MinReturn -37.2748 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.3486 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.9262 MetaTest/__unnamed_task__/AverageReturn -34.9262 MetaTest/__unnamed_task__/Iteration 78 MetaTest/__unnamed_task__/MaxReturn -32.5776 MetaTest/__unnamed_task__/MinReturn -37.2748 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.3486 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 160000 ------------------------------------------------- ----------- 2025-03-29 18:24:07 | [pearl_trainer] epoch #79 | Training... 2025-03-29 18:24:22 | [pearl_trainer] epoch #79 | Evaluating... 2025-03-29 18:24:22 | [pearl_trainer] epoch #79 | Sampling for adapation and meta-testing... 2025-03-29 18:25:31 | [pearl_trainer] epoch #79 | Finished meta-testing... 2025-03-29 18:25:31 | [pearl_trainer] epoch #79 | Saving snapshot... 2025-03-29 18:25:32 | [pearl_trainer] epoch #79 | Saved 2025-03-29 18:25:32 | [pearl_trainer] epoch #79 | Time 15356.78 s 2025-03-29 18:25:32 | [pearl_trainer] epoch #79 | EpochTime 148.21 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.9184 MetaTest/Average/AverageReturn -34.9184 MetaTest/Average/Iteration 79 MetaTest/Average/MaxReturn -33.1405 MetaTest/Average/MinReturn -36.6963 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.77794 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.9184 MetaTest/__unnamed_task__/AverageReturn -34.9184 MetaTest/__unnamed_task__/Iteration 79 MetaTest/__unnamed_task__/MaxReturn -33.1405 MetaTest/__unnamed_task__/MinReturn -36.6963 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.77794 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 162000 ------------------------------------------------- ------------ 2025-03-29 18:26:35 | [pearl_trainer] epoch #80 | Training... 2025-03-29 18:26:51 | [pearl_trainer] epoch #80 | Evaluating... 2025-03-29 18:26:51 | [pearl_trainer] epoch #80 | Sampling for adapation and meta-testing... 2025-03-29 18:28:00 | [pearl_trainer] epoch #80 | Finished meta-testing... 2025-03-29 18:28:00 | [pearl_trainer] epoch #80 | Saving snapshot... 2025-03-29 18:28:00 | [pearl_trainer] epoch #80 | Saved 2025-03-29 18:28:00 | [pearl_trainer] epoch #80 | Time 15505.32 s 2025-03-29 18:28:00 | [pearl_trainer] epoch #80 | EpochTime 148.54 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -36.6817 MetaTest/Average/AverageReturn -36.6817 MetaTest/Average/Iteration 80 MetaTest/Average/MaxReturn -36.3867 MetaTest/Average/MinReturn -36.9767 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.294994 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.6817 MetaTest/__unnamed_task__/AverageReturn -36.6817 MetaTest/__unnamed_task__/Iteration 80 MetaTest/__unnamed_task__/MaxReturn -36.3867 MetaTest/__unnamed_task__/MinReturn -36.9767 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.294994 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 164000 ------------------------------------------------- ------------- 2025-03-29 18:29:03 | [pearl_trainer] epoch #81 | Training... 2025-03-29 18:29:19 | [pearl_trainer] epoch #81 | Evaluating... 2025-03-29 18:29:19 | [pearl_trainer] epoch #81 | Sampling for adapation and meta-testing... 2025-03-29 18:30:28 | [pearl_trainer] epoch #81 | Finished meta-testing... 2025-03-29 18:30:28 | [pearl_trainer] epoch #81 | Saving snapshot... 2025-03-29 18:30:29 | [pearl_trainer] epoch #81 | Saved 2025-03-29 18:30:29 | [pearl_trainer] epoch #81 | Time 15653.62 s 2025-03-29 18:30:29 | [pearl_trainer] epoch #81 | EpochTime 148.29 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -40.6015 MetaTest/Average/AverageReturn -40.6015 MetaTest/Average/Iteration 81 MetaTest/Average/MaxReturn -37.0844 MetaTest/Average/MinReturn -44.1185 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.51703 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -40.6015 MetaTest/__unnamed_task__/AverageReturn -40.6015 MetaTest/__unnamed_task__/Iteration 81 MetaTest/__unnamed_task__/MaxReturn -37.0844 MetaTest/__unnamed_task__/MinReturn -44.1185 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.51703 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 166000 ------------------------------------------------- ------------ 2025-03-29 18:31:32 | [pearl_trainer] epoch #82 | Training... 2025-03-29 18:31:48 | [pearl_trainer] epoch #82 | Evaluating... 2025-03-29 18:31:48 | [pearl_trainer] epoch #82 | Sampling for adapation and meta-testing... 2025-03-29 18:32:57 | [pearl_trainer] epoch #82 | Finished meta-testing... 2025-03-29 18:32:57 | [pearl_trainer] epoch #82 | Saving snapshot... 2025-03-29 18:32:58 | [pearl_trainer] epoch #82 | Saved 2025-03-29 18:32:58 | [pearl_trainer] epoch #82 | Time 15803.23 s 2025-03-29 18:32:58 | [pearl_trainer] epoch #82 | EpochTime 149.61 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -40.3673 MetaTest/Average/AverageReturn -40.3673 MetaTest/Average/Iteration 82 MetaTest/Average/MaxReturn -39.8943 MetaTest/Average/MinReturn -40.8403 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.472993 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -40.3673 MetaTest/__unnamed_task__/AverageReturn -40.3673 MetaTest/__unnamed_task__/Iteration 82 MetaTest/__unnamed_task__/MaxReturn -39.8943 MetaTest/__unnamed_task__/MinReturn -40.8403 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.472993 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 168000 ------------------------------------------------- ------------- 2025-03-29 18:34:02 | [pearl_trainer] epoch #83 | Training... 2025-03-29 18:34:18 | [pearl_trainer] epoch #83 | Evaluating... 2025-03-29 18:34:18 | [pearl_trainer] epoch #83 | Sampling for adapation and meta-testing... 2025-03-29 18:35:27 | [pearl_trainer] epoch #83 | Finished meta-testing... 2025-03-29 18:35:27 | [pearl_trainer] epoch #83 | Saving snapshot... 2025-03-29 18:35:28 | [pearl_trainer] epoch #83 | Saved 2025-03-29 18:35:28 | [pearl_trainer] epoch #83 | Time 15952.96 s 2025-03-29 18:35:28 | [pearl_trainer] epoch #83 | EpochTime 149.73 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -40.656 MetaTest/Average/AverageReturn -40.656 MetaTest/Average/Iteration 83 MetaTest/Average/MaxReturn -36.0044 MetaTest/Average/MinReturn -45.3077 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.65163 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -40.656 MetaTest/__unnamed_task__/AverageReturn -40.656 MetaTest/__unnamed_task__/Iteration 83 MetaTest/__unnamed_task__/MaxReturn -36.0044 MetaTest/__unnamed_task__/MinReturn -45.3077 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.65163 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 170000 ------------------------------------------------- ------------ 2025-03-29 18:36:31 | [pearl_trainer] epoch #84 | Training... 2025-03-29 18:36:48 | [pearl_trainer] epoch #84 | Evaluating... 2025-03-29 18:36:48 | [pearl_trainer] epoch #84 | Sampling for adapation and meta-testing... 2025-03-29 18:37:58 | [pearl_trainer] epoch #84 | Finished meta-testing... 2025-03-29 18:37:58 | [pearl_trainer] epoch #84 | Saving snapshot... 2025-03-29 18:37:58 | [pearl_trainer] epoch #84 | Saved 2025-03-29 18:37:58 | [pearl_trainer] epoch #84 | Time 16103.40 s 2025-03-29 18:37:58 | [pearl_trainer] epoch #84 | EpochTime 150.44 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.7817 MetaTest/Average/AverageReturn -36.7817 MetaTest/Average/Iteration 84 MetaTest/Average/MaxReturn -35.4362 MetaTest/Average/MinReturn -38.1273 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.34552 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.7817 MetaTest/__unnamed_task__/AverageReturn -36.7817 MetaTest/__unnamed_task__/Iteration 84 MetaTest/__unnamed_task__/MaxReturn -35.4362 MetaTest/__unnamed_task__/MinReturn -38.1273 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.34552 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 172000 ------------------------------------------------- ------------ 2025-03-29 18:39:01 | [pearl_trainer] epoch #85 | Training... 2025-03-29 18:39:18 | [pearl_trainer] epoch #85 | Evaluating... 2025-03-29 18:39:18 | [pearl_trainer] epoch #85 | Sampling for adapation and meta-testing... 2025-03-29 18:40:28 | [pearl_trainer] epoch #85 | Finished meta-testing... 2025-03-29 18:40:28 | [pearl_trainer] epoch #85 | Saving snapshot... 2025-03-29 18:40:29 | [pearl_trainer] epoch #85 | Saved 2025-03-29 18:40:29 | [pearl_trainer] epoch #85 | Time 16254.04 s 2025-03-29 18:40:29 | [pearl_trainer] epoch #85 | EpochTime 150.64 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.1566 MetaTest/Average/AverageReturn -35.1566 MetaTest/Average/Iteration 85 MetaTest/Average/MaxReturn -34.7199 MetaTest/Average/MinReturn -35.5933 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.436703 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.1566 MetaTest/__unnamed_task__/AverageReturn -35.1566 MetaTest/__unnamed_task__/Iteration 85 MetaTest/__unnamed_task__/MaxReturn -34.7199 MetaTest/__unnamed_task__/MinReturn -35.5933 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.436703 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 174000 ------------------------------------------------- ------------- 2025-03-29 18:41:31 | [pearl_trainer] epoch #86 | Training... 2025-03-29 18:41:49 | [pearl_trainer] epoch #86 | Evaluating... 2025-03-29 18:41:49 | [pearl_trainer] epoch #86 | Sampling for adapation and meta-testing... 2025-03-29 18:42:58 | [pearl_trainer] epoch #86 | Finished meta-testing... 2025-03-29 18:42:58 | [pearl_trainer] epoch #86 | Saving snapshot... 2025-03-29 18:42:59 | [pearl_trainer] epoch #86 | Saved 2025-03-29 18:42:59 | [pearl_trainer] epoch #86 | Time 16403.47 s 2025-03-29 18:42:59 | [pearl_trainer] epoch #86 | EpochTime 149.43 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -39.0985 MetaTest/Average/AverageReturn -39.0985 MetaTest/Average/Iteration 86 MetaTest/Average/MaxReturn -32.96 MetaTest/Average/MinReturn -45.237 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 6.1385 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.0985 MetaTest/__unnamed_task__/AverageReturn -39.0985 MetaTest/__unnamed_task__/Iteration 86 MetaTest/__unnamed_task__/MaxReturn -32.96 MetaTest/__unnamed_task__/MinReturn -45.237 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 6.1385 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 176000 ------------------------------------------------- ----------- 2025-03-29 18:44:01 | [pearl_trainer] epoch #87 | Training... 2025-03-29 18:44:18 | [pearl_trainer] epoch #87 | Evaluating... 2025-03-29 18:44:18 | [pearl_trainer] epoch #87 | Sampling for adapation and meta-testing... 2025-03-29 18:45:26 | [pearl_trainer] epoch #87 | Finished meta-testing... 2025-03-29 18:45:26 | [pearl_trainer] epoch #87 | Saving snapshot... 2025-03-29 18:45:27 | [pearl_trainer] epoch #87 | Saved 2025-03-29 18:45:27 | [pearl_trainer] epoch #87 | Time 16552.06 s 2025-03-29 18:45:27 | [pearl_trainer] epoch #87 | EpochTime 148.59 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -41.1641 MetaTest/Average/AverageReturn -41.1641 MetaTest/Average/Iteration 87 MetaTest/Average/MaxReturn -39.4886 MetaTest/Average/MinReturn -42.8396 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.6755 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -41.1641 MetaTest/__unnamed_task__/AverageReturn -41.1641 MetaTest/__unnamed_task__/Iteration 87 MetaTest/__unnamed_task__/MaxReturn -39.4886 MetaTest/__unnamed_task__/MinReturn -42.8396 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.6755 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 178000 ------------------------------------------------- ----------- 2025-03-29 18:46:30 | [pearl_trainer] epoch #88 | Training... 2025-03-29 18:46:46 | [pearl_trainer] epoch #88 | Evaluating... 2025-03-29 18:46:46 | [pearl_trainer] epoch #88 | Sampling for adapation and meta-testing... 2025-03-29 18:47:55 | [pearl_trainer] epoch #88 | Finished meta-testing... 2025-03-29 18:47:55 | [pearl_trainer] epoch #88 | Saving snapshot... 2025-03-29 18:47:56 | [pearl_trainer] epoch #88 | Saved 2025-03-29 18:47:56 | [pearl_trainer] epoch #88 | Time 16700.70 s 2025-03-29 18:47:56 | [pearl_trainer] epoch #88 | EpochTime 148.64 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.5562 MetaTest/Average/AverageReturn -34.5562 MetaTest/Average/Iteration 88 MetaTest/Average/MaxReturn -31.6639 MetaTest/Average/MinReturn -37.4484 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.89227 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.5562 MetaTest/__unnamed_task__/AverageReturn -34.5562 MetaTest/__unnamed_task__/Iteration 88 MetaTest/__unnamed_task__/MaxReturn -31.6639 MetaTest/__unnamed_task__/MinReturn -37.4484 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.89227 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 180000 ------------------------------------------------- ------------ 2025-03-29 18:48:59 | [pearl_trainer] epoch #89 | Training... 2025-03-29 18:49:16 | [pearl_trainer] epoch #89 | Evaluating... 2025-03-29 18:49:16 | [pearl_trainer] epoch #89 | Sampling for adapation and meta-testing... 2025-03-29 18:50:26 | [pearl_trainer] epoch #89 | Finished meta-testing... 2025-03-29 18:50:26 | [pearl_trainer] epoch #89 | Saving snapshot... 2025-03-29 18:50:26 | [pearl_trainer] epoch #89 | Saved 2025-03-29 18:50:26 | [pearl_trainer] epoch #89 | Time 16851.26 s 2025-03-29 18:50:26 | [pearl_trainer] epoch #89 | EpochTime 150.56 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.9098 MetaTest/Average/AverageReturn -37.9098 MetaTest/Average/Iteration 89 MetaTest/Average/MaxReturn -34.4839 MetaTest/Average/MinReturn -41.3358 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.42596 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.9098 MetaTest/__unnamed_task__/AverageReturn -37.9098 MetaTest/__unnamed_task__/Iteration 89 MetaTest/__unnamed_task__/MaxReturn -34.4839 MetaTest/__unnamed_task__/MinReturn -41.3358 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.42596 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 182000 ------------------------------------------------- ------------ 2025-03-29 18:51:29 | [pearl_trainer] epoch #90 | Training... 2025-03-29 18:51:46 | [pearl_trainer] epoch #90 | Evaluating... 2025-03-29 18:51:46 | [pearl_trainer] epoch #90 | Sampling for adapation and meta-testing... 2025-03-29 18:52:56 | [pearl_trainer] epoch #90 | Finished meta-testing... 2025-03-29 18:52:56 | [pearl_trainer] epoch #90 | Saving snapshot... 2025-03-29 18:52:57 | [pearl_trainer] epoch #90 | Saved 2025-03-29 18:52:57 | [pearl_trainer] epoch #90 | Time 17001.58 s 2025-03-29 18:52:57 | [pearl_trainer] epoch #90 | EpochTime 150.32 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.7703 MetaTest/Average/AverageReturn -33.7703 MetaTest/Average/Iteration 90 MetaTest/Average/MaxReturn -30.4028 MetaTest/Average/MinReturn -37.1378 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.36749 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.7703 MetaTest/__unnamed_task__/AverageReturn -33.7703 MetaTest/__unnamed_task__/Iteration 90 MetaTest/__unnamed_task__/MaxReturn -30.4028 MetaTest/__unnamed_task__/MinReturn -37.1378 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.36749 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 184000 ------------------------------------------------- ------------ 2025-03-29 18:54:01 | [pearl_trainer] epoch #91 | Training... 2025-03-29 18:54:18 | [pearl_trainer] epoch #91 | Evaluating... 2025-03-29 18:54:18 | [pearl_trainer] epoch #91 | Sampling for adapation and meta-testing... 2025-03-29 18:55:28 | [pearl_trainer] epoch #91 | Finished meta-testing... 2025-03-29 18:55:28 | [pearl_trainer] epoch #91 | Saving snapshot... 2025-03-29 18:55:29 | [pearl_trainer] epoch #91 | Saved 2025-03-29 18:55:29 | [pearl_trainer] epoch #91 | Time 17153.63 s 2025-03-29 18:55:29 | [pearl_trainer] epoch #91 | EpochTime 152.05 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.6392 MetaTest/Average/AverageReturn -37.6392 MetaTest/Average/Iteration 91 MetaTest/Average/MaxReturn -35.1018 MetaTest/Average/MinReturn -40.1766 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.53738 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.6392 MetaTest/__unnamed_task__/AverageReturn -37.6392 MetaTest/__unnamed_task__/Iteration 91 MetaTest/__unnamed_task__/MaxReturn -35.1018 MetaTest/__unnamed_task__/MinReturn -40.1766 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.53738 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 186000 ------------------------------------------------- ------------ 2025-03-29 18:56:32 | [pearl_trainer] epoch #92 | Training... 2025-03-29 18:56:47 | [pearl_trainer] epoch #92 | Evaluating... 2025-03-29 18:56:47 | [pearl_trainer] epoch #92 | Sampling for adapation and meta-testing... 2025-03-29 18:57:57 | [pearl_trainer] epoch #92 | Finished meta-testing... 2025-03-29 18:57:57 | [pearl_trainer] epoch #92 | Saving snapshot... 2025-03-29 18:57:58 | [pearl_trainer] epoch #92 | Saved 2025-03-29 18:57:58 | [pearl_trainer] epoch #92 | Time 17303.10 s 2025-03-29 18:57:58 | [pearl_trainer] epoch #92 | EpochTime 149.47 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.8037 MetaTest/Average/AverageReturn -37.8037 MetaTest/Average/Iteration 92 MetaTest/Average/MaxReturn -32.7632 MetaTest/Average/MinReturn -42.8441 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 5.04046 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.8037 MetaTest/__unnamed_task__/AverageReturn -37.8037 MetaTest/__unnamed_task__/Iteration 92 MetaTest/__unnamed_task__/MaxReturn -32.7632 MetaTest/__unnamed_task__/MinReturn -42.8441 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 5.04046 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 188000 ------------------------------------------------- ------------ 2025-03-29 18:59:02 | [pearl_trainer] epoch #93 | Training... 2025-03-29 18:59:17 | [pearl_trainer] epoch #93 | Evaluating... 2025-03-29 18:59:17 | [pearl_trainer] epoch #93 | Sampling for adapation and meta-testing... 2025-03-29 19:00:26 | [pearl_trainer] epoch #93 | Finished meta-testing... 2025-03-29 19:00:26 | [pearl_trainer] epoch #93 | Saving snapshot... 2025-03-29 19:00:27 | [pearl_trainer] epoch #93 | Saved 2025-03-29 19:00:27 | [pearl_trainer] epoch #93 | Time 17452.06 s 2025-03-29 19:00:27 | [pearl_trainer] epoch #93 | EpochTime 148.96 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.7907 MetaTest/Average/AverageReturn -33.7907 MetaTest/Average/Iteration 93 MetaTest/Average/MaxReturn -33.046 MetaTest/Average/MinReturn -34.5355 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.744772 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.7907 MetaTest/__unnamed_task__/AverageReturn -33.7907 MetaTest/__unnamed_task__/Iteration 93 MetaTest/__unnamed_task__/MaxReturn -33.046 MetaTest/__unnamed_task__/MinReturn -34.5355 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.744772 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 190000 ------------------------------------------------- ------------- 2025-03-29 19:01:30 | [pearl_trainer] epoch #94 | Training... 2025-03-29 19:01:45 | [pearl_trainer] epoch #94 | Evaluating... 2025-03-29 19:01:45 | [pearl_trainer] epoch #94 | Sampling for adapation and meta-testing... 2025-03-29 19:02:54 | [pearl_trainer] epoch #94 | Finished meta-testing... 2025-03-29 19:02:54 | [pearl_trainer] epoch #94 | Saving snapshot... 2025-03-29 19:02:55 | [pearl_trainer] epoch #94 | Saved 2025-03-29 19:02:55 | [pearl_trainer] epoch #94 | Time 17599.93 s 2025-03-29 19:02:55 | [pearl_trainer] epoch #94 | EpochTime 147.87 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.7138 MetaTest/Average/AverageReturn -35.7138 MetaTest/Average/Iteration 94 MetaTest/Average/MaxReturn -35.0943 MetaTest/Average/MinReturn -36.3333 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.619524 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.7138 MetaTest/__unnamed_task__/AverageReturn -35.7138 MetaTest/__unnamed_task__/Iteration 94 MetaTest/__unnamed_task__/MaxReturn -35.0943 MetaTest/__unnamed_task__/MinReturn -36.3333 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.619524 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 192000 ------------------------------------------------- ------------- 2025-03-29 19:03:58 | [pearl_trainer] epoch #95 | Training... 2025-03-29 19:04:13 | [pearl_trainer] epoch #95 | Evaluating... 2025-03-29 19:04:13 | [pearl_trainer] epoch #95 | Sampling for adapation and meta-testing... 2025-03-29 19:05:23 | [pearl_trainer] epoch #95 | Finished meta-testing... 2025-03-29 19:05:23 | [pearl_trainer] epoch #95 | Saving snapshot... 2025-03-29 19:05:24 | [pearl_trainer] epoch #95 | Saved 2025-03-29 19:05:24 | [pearl_trainer] epoch #95 | Time 17748.46 s 2025-03-29 19:05:24 | [pearl_trainer] epoch #95 | EpochTime 148.52 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -38.5618 MetaTest/Average/AverageReturn -38.5618 MetaTest/Average/Iteration 95 MetaTest/Average/MaxReturn -38.181 MetaTest/Average/MinReturn -38.9426 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.380778 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.5618 MetaTest/__unnamed_task__/AverageReturn -38.5618 MetaTest/__unnamed_task__/Iteration 95 MetaTest/__unnamed_task__/MaxReturn -38.181 MetaTest/__unnamed_task__/MinReturn -38.9426 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.380778 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 194000 ------------------------------------------------- ------------- 2025-03-29 19:06:27 | [pearl_trainer] epoch #96 | Training... 2025-03-29 19:06:43 | [pearl_trainer] epoch #96 | Evaluating... 2025-03-29 19:06:43 | [pearl_trainer] epoch #96 | Sampling for adapation and meta-testing... 2025-03-29 19:07:53 | [pearl_trainer] epoch #96 | Finished meta-testing... 2025-03-29 19:07:53 | [pearl_trainer] epoch #96 | Saving snapshot... 2025-03-29 19:07:53 | [pearl_trainer] epoch #96 | Saved 2025-03-29 19:07:53 | [pearl_trainer] epoch #96 | Time 17898.27 s 2025-03-29 19:07:53 | [pearl_trainer] epoch #96 | EpochTime 149.81 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.582 MetaTest/Average/AverageReturn -35.582 MetaTest/Average/Iteration 96 MetaTest/Average/MaxReturn -31.0021 MetaTest/Average/MinReturn -40.1619 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.57993 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.582 MetaTest/__unnamed_task__/AverageReturn -35.582 MetaTest/__unnamed_task__/Iteration 96 MetaTest/__unnamed_task__/MaxReturn -31.0021 MetaTest/__unnamed_task__/MinReturn -40.1619 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.57993 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 196000 ------------------------------------------------- ------------ 2025-03-29 19:08:57 | [pearl_trainer] epoch #97 | Training... 2025-03-29 19:09:12 | [pearl_trainer] epoch #97 | Evaluating... 2025-03-29 19:09:12 | [pearl_trainer] epoch #97 | Sampling for adapation and meta-testing... 2025-03-29 19:10:21 | [pearl_trainer] epoch #97 | Finished meta-testing... 2025-03-29 19:10:21 | [pearl_trainer] epoch #97 | Saving snapshot... 2025-03-29 19:10:22 | [pearl_trainer] epoch #97 | Saved 2025-03-29 19:10:22 | [pearl_trainer] epoch #97 | Time 18046.95 s 2025-03-29 19:10:22 | [pearl_trainer] epoch #97 | EpochTime 148.69 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.0595 MetaTest/Average/AverageReturn -36.0595 MetaTest/Average/Iteration 97 MetaTest/Average/MaxReturn -35.0357 MetaTest/Average/MinReturn -37.0832 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.02376 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.0595 MetaTest/__unnamed_task__/AverageReturn -36.0595 MetaTest/__unnamed_task__/Iteration 97 MetaTest/__unnamed_task__/MaxReturn -35.0357 MetaTest/__unnamed_task__/MinReturn -37.0832 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.02376 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 198000 ------------------------------------------------- ------------ 2025-03-29 19:11:25 | [pearl_trainer] epoch #98 | Training... 2025-03-29 19:11:40 | [pearl_trainer] epoch #98 | Evaluating... 2025-03-29 19:11:40 | [pearl_trainer] epoch #98 | Sampling for adapation and meta-testing... 2025-03-29 19:12:50 | [pearl_trainer] epoch #98 | Finished meta-testing... 2025-03-29 19:12:50 | [pearl_trainer] epoch #98 | Saving snapshot... 2025-03-29 19:12:51 | [pearl_trainer] epoch #98 | Saved 2025-03-29 19:12:51 | [pearl_trainer] epoch #98 | Time 18196.00 s 2025-03-29 19:12:51 | [pearl_trainer] epoch #98 | EpochTime 149.04 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -34.7521 MetaTest/Average/AverageReturn -34.7521 MetaTest/Average/Iteration 98 MetaTest/Average/MaxReturn -32.2705 MetaTest/Average/MinReturn -37.2337 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.4816 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.7521 MetaTest/__unnamed_task__/AverageReturn -34.7521 MetaTest/__unnamed_task__/Iteration 98 MetaTest/__unnamed_task__/MaxReturn -32.2705 MetaTest/__unnamed_task__/MinReturn -37.2337 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.4816 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 200000 ------------------------------------------------- ----------- 2025-03-29 19:13:54 | [pearl_trainer] epoch #99 | Training... 2025-03-29 19:14:10 | [pearl_trainer] epoch #99 | Evaluating... 2025-03-29 19:14:10 | [pearl_trainer] epoch #99 | Sampling for adapation and meta-testing... 2025-03-29 19:15:19 | [pearl_trainer] epoch #99 | Finished meta-testing... 2025-03-29 19:15:19 | [pearl_trainer] epoch #99 | Saving snapshot... 2025-03-29 19:15:19 | [pearl_trainer] epoch #99 | Saved 2025-03-29 19:15:19 | [pearl_trainer] epoch #99 | Time 18344.39 s 2025-03-29 19:15:19 | [pearl_trainer] epoch #99 | EpochTime 148.39 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -39.1775 MetaTest/Average/AverageReturn -39.1775 MetaTest/Average/Iteration 99 MetaTest/Average/MaxReturn -34.7934 MetaTest/Average/MinReturn -43.5617 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.38417 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.1775 MetaTest/__unnamed_task__/AverageReturn -39.1775 MetaTest/__unnamed_task__/Iteration 99 MetaTest/__unnamed_task__/MaxReturn -34.7934 MetaTest/__unnamed_task__/MinReturn -43.5617 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.38417 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 202000 ------------------------------------------------- ------------ 2025-03-29 19:16:22 | [pearl_trainer] epoch #100 | Training... 2025-03-29 19:16:38 | [pearl_trainer] epoch #100 | Evaluating... 2025-03-29 19:16:38 | [pearl_trainer] epoch #100 | Sampling for adapation and meta-testing... 2025-03-29 19:17:47 | [pearl_trainer] epoch #100 | Finished meta-testing... 2025-03-29 19:17:47 | [pearl_trainer] epoch #100 | Saving snapshot... 2025-03-29 19:17:48 | [pearl_trainer] epoch #100 | Saved 2025-03-29 19:17:48 | [pearl_trainer] epoch #100 | Time 18492.51 s 2025-03-29 19:17:48 | [pearl_trainer] epoch #100 | EpochTime 148.12 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.9827 MetaTest/Average/AverageReturn -37.9827 MetaTest/Average/Iteration 100 MetaTest/Average/MaxReturn -36.2718 MetaTest/Average/MinReturn -39.6937 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.71096 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.9827 MetaTest/__unnamed_task__/AverageReturn -37.9827 MetaTest/__unnamed_task__/Iteration 100 MetaTest/__unnamed_task__/MaxReturn -36.2718 MetaTest/__unnamed_task__/MinReturn -39.6937 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.71096 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 204000 ------------------------------------------------- ------------ 2025-03-29 19:18:51 | [pearl_trainer] epoch #101 | Training... 2025-03-29 19:19:06 | [pearl_trainer] epoch #101 | Evaluating... 2025-03-29 19:19:06 | [pearl_trainer] epoch #101 | Sampling for adapation and meta-testing... 2025-03-29 19:20:15 | [pearl_trainer] epoch #101 | Finished meta-testing... 2025-03-29 19:20:15 | [pearl_trainer] epoch #101 | Saving snapshot... 2025-03-29 19:20:16 | [pearl_trainer] epoch #101 | Saved 2025-03-29 19:20:16 | [pearl_trainer] epoch #101 | Time 18640.75 s 2025-03-29 19:20:16 | [pearl_trainer] epoch #101 | EpochTime 148.23 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -39.4335 MetaTest/Average/AverageReturn -39.4335 MetaTest/Average/Iteration 101 MetaTest/Average/MaxReturn -37.821 MetaTest/Average/MinReturn -41.0459 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.61245 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.4335 MetaTest/__unnamed_task__/AverageReturn -39.4335 MetaTest/__unnamed_task__/Iteration 101 MetaTest/__unnamed_task__/MaxReturn -37.821 MetaTest/__unnamed_task__/MinReturn -41.0459 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.61245 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 206000 ------------------------------------------------- ------------ 2025-03-29 19:21:19 | [pearl_trainer] epoch #102 | Training... 2025-03-29 19:21:35 | [pearl_trainer] epoch #102 | Evaluating... 2025-03-29 19:21:35 | [pearl_trainer] epoch #102 | Sampling for adapation and meta-testing... 2025-03-29 19:22:45 | [pearl_trainer] epoch #102 | Finished meta-testing... 2025-03-29 19:22:45 | [pearl_trainer] epoch #102 | Saving snapshot... 2025-03-29 19:22:46 | [pearl_trainer] epoch #102 | Saved 2025-03-29 19:22:46 | [pearl_trainer] epoch #102 | Time 18790.93 s 2025-03-29 19:22:46 | [pearl_trainer] epoch #102 | EpochTime 150.18 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -36.4355 MetaTest/Average/AverageReturn -36.4355 MetaTest/Average/Iteration 102 MetaTest/Average/MaxReturn -35.9512 MetaTest/Average/MinReturn -36.9198 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.484276 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.4355 MetaTest/__unnamed_task__/AverageReturn -36.4355 MetaTest/__unnamed_task__/Iteration 102 MetaTest/__unnamed_task__/MaxReturn -35.9512 MetaTest/__unnamed_task__/MinReturn -36.9198 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.484276 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 208000 ------------------------------------------------- ------------- 2025-03-29 19:23:49 | [pearl_trainer] epoch #103 | Training... 2025-03-29 19:24:05 | [pearl_trainer] epoch #103 | Evaluating... 2025-03-29 19:24:05 | [pearl_trainer] epoch #103 | Sampling for adapation and meta-testing... 2025-03-29 19:25:15 | [pearl_trainer] epoch #103 | Finished meta-testing... 2025-03-29 19:25:15 | [pearl_trainer] epoch #103 | Saving snapshot... 2025-03-29 19:25:15 | [pearl_trainer] epoch #103 | Saved 2025-03-29 19:25:15 | [pearl_trainer] epoch #103 | Time 18940.15 s 2025-03-29 19:25:15 | [pearl_trainer] epoch #103 | EpochTime 149.22 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.0662 MetaTest/Average/AverageReturn -36.0662 MetaTest/Average/Iteration 103 MetaTest/Average/MaxReturn -34.4114 MetaTest/Average/MinReturn -37.7211 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.65485 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.0662 MetaTest/__unnamed_task__/AverageReturn -36.0662 MetaTest/__unnamed_task__/Iteration 103 MetaTest/__unnamed_task__/MaxReturn -34.4114 MetaTest/__unnamed_task__/MinReturn -37.7211 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.65485 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 210000 ------------------------------------------------- ------------ 2025-03-29 19:26:18 | [pearl_trainer] epoch #104 | Training... 2025-03-29 19:26:33 | [pearl_trainer] epoch #104 | Evaluating... 2025-03-29 19:26:33 | [pearl_trainer] epoch #104 | Sampling for adapation and meta-testing... 2025-03-29 19:27:44 | [pearl_trainer] epoch #104 | Finished meta-testing... 2025-03-29 19:27:44 | [pearl_trainer] epoch #104 | Saving snapshot... 2025-03-29 19:27:45 | [pearl_trainer] epoch #104 | Saved 2025-03-29 19:27:45 | [pearl_trainer] epoch #104 | Time 19089.95 s 2025-03-29 19:27:45 | [pearl_trainer] epoch #104 | EpochTime 149.79 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -43.2847 MetaTest/Average/AverageReturn -43.2847 MetaTest/Average/Iteration 104 MetaTest/Average/MaxReturn -42.6519 MetaTest/Average/MinReturn -43.9176 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.632853 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -43.2847 MetaTest/__unnamed_task__/AverageReturn -43.2847 MetaTest/__unnamed_task__/Iteration 104 MetaTest/__unnamed_task__/MaxReturn -42.6519 MetaTest/__unnamed_task__/MinReturn -43.9176 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.632853 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 212000 ------------------------------------------------- ------------- 2025-03-29 19:28:49 | [pearl_trainer] epoch #105 | Training... 2025-03-29 19:29:07 | [pearl_trainer] epoch #105 | Evaluating... 2025-03-29 19:29:07 | [pearl_trainer] epoch #105 | Sampling for adapation and meta-testing... 2025-03-29 19:30:16 | [pearl_trainer] epoch #105 | Finished meta-testing... 2025-03-29 19:30:16 | [pearl_trainer] epoch #105 | Saving snapshot... 2025-03-29 19:30:17 | [pearl_trainer] epoch #105 | Saved 2025-03-29 19:30:17 | [pearl_trainer] epoch #105 | Time 19242.16 s 2025-03-29 19:30:17 | [pearl_trainer] epoch #105 | EpochTime 152.21 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.1531 MetaTest/Average/AverageReturn -34.1531 MetaTest/Average/Iteration 105 MetaTest/Average/MaxReturn -32.384 MetaTest/Average/MinReturn -35.9223 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.76915 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.1531 MetaTest/__unnamed_task__/AverageReturn -34.1531 MetaTest/__unnamed_task__/Iteration 105 MetaTest/__unnamed_task__/MaxReturn -32.384 MetaTest/__unnamed_task__/MinReturn -35.9223 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.76915 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 214000 ------------------------------------------------- ------------ 2025-03-29 19:31:21 | [pearl_trainer] epoch #106 | Training... 2025-03-29 19:31:38 | [pearl_trainer] epoch #106 | Evaluating... 2025-03-29 19:31:38 | [pearl_trainer] epoch #106 | Sampling for adapation and meta-testing... 2025-03-29 19:32:49 | [pearl_trainer] epoch #106 | Finished meta-testing... 2025-03-29 19:32:49 | [pearl_trainer] epoch #106 | Saving snapshot... 2025-03-29 19:32:50 | [pearl_trainer] epoch #106 | Saved 2025-03-29 19:32:50 | [pearl_trainer] epoch #106 | Time 19394.57 s 2025-03-29 19:32:50 | [pearl_trainer] epoch #106 | EpochTime 152.41 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.5341 MetaTest/Average/AverageReturn -35.5341 MetaTest/Average/Iteration 106 MetaTest/Average/MaxReturn -34.9606 MetaTest/Average/MinReturn -36.1075 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.573435 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.5341 MetaTest/__unnamed_task__/AverageReturn -35.5341 MetaTest/__unnamed_task__/Iteration 106 MetaTest/__unnamed_task__/MaxReturn -34.9606 MetaTest/__unnamed_task__/MinReturn -36.1075 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.573435 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 216000 ------------------------------------------------- ------------- 2025-03-29 19:33:55 | [pearl_trainer] epoch #107 | Training... 2025-03-29 19:34:13 | [pearl_trainer] epoch #107 | Evaluating... 2025-03-29 19:34:13 | [pearl_trainer] epoch #107 | Sampling for adapation and meta-testing... 2025-03-29 19:35:25 | [pearl_trainer] epoch #107 | Finished meta-testing... 2025-03-29 19:35:25 | [pearl_trainer] epoch #107 | Saving snapshot... 2025-03-29 19:35:25 | [pearl_trainer] epoch #107 | Saved 2025-03-29 19:35:25 | [pearl_trainer] epoch #107 | Time 19550.20 s 2025-03-29 19:35:25 | [pearl_trainer] epoch #107 | EpochTime 155.63 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -36.4956 MetaTest/Average/AverageReturn -36.4956 MetaTest/Average/Iteration 107 MetaTest/Average/MaxReturn -36.0155 MetaTest/Average/MinReturn -36.9757 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.480088 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.4956 MetaTest/__unnamed_task__/AverageReturn -36.4956 MetaTest/__unnamed_task__/Iteration 107 MetaTest/__unnamed_task__/MaxReturn -36.0155 MetaTest/__unnamed_task__/MinReturn -36.9757 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.480088 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 218000 ------------------------------------------------- ------------- 2025-03-29 19:36:30 | [pearl_trainer] epoch #108 | Training... 2025-03-29 19:36:48 | [pearl_trainer] epoch #108 | Evaluating... 2025-03-29 19:36:48 | [pearl_trainer] epoch #108 | Sampling for adapation and meta-testing... 2025-03-29 19:38:01 | [pearl_trainer] epoch #108 | Finished meta-testing... 2025-03-29 19:38:01 | [pearl_trainer] epoch #108 | Saving snapshot... 2025-03-29 19:38:02 | [pearl_trainer] epoch #108 | Saved 2025-03-29 19:38:02 | [pearl_trainer] epoch #108 | Time 19707.06 s 2025-03-29 19:38:02 | [pearl_trainer] epoch #108 | EpochTime 156.86 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -37.6431 MetaTest/Average/AverageReturn -37.6431 MetaTest/Average/Iteration 108 MetaTest/Average/MaxReturn -37.3747 MetaTest/Average/MinReturn -37.9115 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.268384 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.6431 MetaTest/__unnamed_task__/AverageReturn -37.6431 MetaTest/__unnamed_task__/Iteration 108 MetaTest/__unnamed_task__/MaxReturn -37.3747 MetaTest/__unnamed_task__/MinReturn -37.9115 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.268384 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 220000 ------------------------------------------------- ------------- 2025-03-29 19:39:08 | [pearl_trainer] epoch #109 | Training... 2025-03-29 19:39:26 | [pearl_trainer] epoch #109 | Evaluating... 2025-03-29 19:39:26 | [pearl_trainer] epoch #109 | Sampling for adapation and meta-testing... 2025-03-29 19:40:38 | [pearl_trainer] epoch #109 | Finished meta-testing... 2025-03-29 19:40:38 | [pearl_trainer] epoch #109 | Saving snapshot... 2025-03-29 19:40:39 | [pearl_trainer] epoch #109 | Saved 2025-03-29 19:40:39 | [pearl_trainer] epoch #109 | Time 19863.52 s 2025-03-29 19:40:39 | [pearl_trainer] epoch #109 | EpochTime 156.46 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.2802 MetaTest/Average/AverageReturn -33.2802 MetaTest/Average/Iteration 109 MetaTest/Average/MaxReturn -31.289 MetaTest/Average/MinReturn -35.2713 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.99115 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.2802 MetaTest/__unnamed_task__/AverageReturn -33.2802 MetaTest/__unnamed_task__/Iteration 109 MetaTest/__unnamed_task__/MaxReturn -31.289 MetaTest/__unnamed_task__/MinReturn -35.2713 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.99115 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 222000 ------------------------------------------------- ------------ 2025-03-29 19:41:44 | [pearl_trainer] epoch #110 | Training... 2025-03-29 19:42:01 | [pearl_trainer] epoch #110 | Evaluating... 2025-03-29 19:42:01 | [pearl_trainer] epoch #110 | Sampling for adapation and meta-testing... 2025-03-29 19:43:12 | [pearl_trainer] epoch #110 | Finished meta-testing... 2025-03-29 19:43:12 | [pearl_trainer] epoch #110 | Saving snapshot... 2025-03-29 19:43:13 | [pearl_trainer] epoch #110 | Saved 2025-03-29 19:43:13 | [pearl_trainer] epoch #110 | Time 20018.12 s 2025-03-29 19:43:13 | [pearl_trainer] epoch #110 | EpochTime 154.59 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.8432 MetaTest/Average/AverageReturn -33.8432 MetaTest/Average/Iteration 110 MetaTest/Average/MaxReturn -32.6455 MetaTest/Average/MinReturn -35.0409 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.19769 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.8432 MetaTest/__unnamed_task__/AverageReturn -33.8432 MetaTest/__unnamed_task__/Iteration 110 MetaTest/__unnamed_task__/MaxReturn -32.6455 MetaTest/__unnamed_task__/MinReturn -35.0409 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.19769 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 224000 ------------------------------------------------- ------------ 2025-03-29 19:44:19 | [pearl_trainer] epoch #111 | Training... 2025-03-29 19:44:36 | [pearl_trainer] epoch #111 | Evaluating... 2025-03-29 19:44:36 | [pearl_trainer] epoch #111 | Sampling for adapation and meta-testing... 2025-03-29 19:45:47 | [pearl_trainer] epoch #111 | Finished meta-testing... 2025-03-29 19:45:47 | [pearl_trainer] epoch #111 | Saving snapshot... 2025-03-29 19:45:48 | [pearl_trainer] epoch #111 | Saved 2025-03-29 19:45:48 | [pearl_trainer] epoch #111 | Time 20173.30 s 2025-03-29 19:45:48 | [pearl_trainer] epoch #111 | EpochTime 155.18 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.4726 MetaTest/Average/AverageReturn -35.4726 MetaTest/Average/Iteration 111 MetaTest/Average/MaxReturn -34.7454 MetaTest/Average/MinReturn -36.1998 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.727171 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.4726 MetaTest/__unnamed_task__/AverageReturn -35.4726 MetaTest/__unnamed_task__/Iteration 111 MetaTest/__unnamed_task__/MaxReturn -34.7454 MetaTest/__unnamed_task__/MinReturn -36.1998 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.727171 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 226000 ------------------------------------------------- ------------- 2025-03-29 19:46:54 | [pearl_trainer] epoch #112 | Training... 2025-03-29 19:47:11 | [pearl_trainer] epoch #112 | Evaluating... 2025-03-29 19:47:11 | [pearl_trainer] epoch #112 | Sampling for adapation and meta-testing... 2025-03-29 19:48:23 | [pearl_trainer] epoch #112 | Finished meta-testing... 2025-03-29 19:48:23 | [pearl_trainer] epoch #112 | Saving snapshot... 2025-03-29 19:48:24 | [pearl_trainer] epoch #112 | Saved 2025-03-29 19:48:24 | [pearl_trainer] epoch #112 | Time 20328.64 s 2025-03-29 19:48:24 | [pearl_trainer] epoch #112 | EpochTime 155.34 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -37.006 MetaTest/Average/AverageReturn -37.006 MetaTest/Average/Iteration 112 MetaTest/Average/MaxReturn -36.6494 MetaTest/Average/MinReturn -37.3627 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.356659 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.006 MetaTest/__unnamed_task__/AverageReturn -37.006 MetaTest/__unnamed_task__/Iteration 112 MetaTest/__unnamed_task__/MaxReturn -36.6494 MetaTest/__unnamed_task__/MinReturn -37.3627 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.356659 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 228000 ------------------------------------------------- ------------- 2025-03-29 19:49:29 | [pearl_trainer] epoch #113 | Training... 2025-03-29 19:49:45 | [pearl_trainer] epoch #113 | Evaluating... 2025-03-29 19:49:45 | [pearl_trainer] epoch #113 | Sampling for adapation and meta-testing... 2025-03-29 19:51:05 | [pearl_trainer] epoch #113 | Finished meta-testing... 2025-03-29 19:51:05 | [pearl_trainer] epoch #113 | Saving snapshot... 2025-03-29 19:51:05 | [pearl_trainer] epoch #113 | Saved 2025-03-29 19:51:05 | [pearl_trainer] epoch #113 | Time 20490.33 s 2025-03-29 19:51:05 | [pearl_trainer] epoch #113 | EpochTime 161.69 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -39.4859 MetaTest/Average/AverageReturn -39.4859 MetaTest/Average/Iteration 113 MetaTest/Average/MaxReturn -35.1533 MetaTest/Average/MinReturn -43.8185 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.33259 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.4859 MetaTest/__unnamed_task__/AverageReturn -39.4859 MetaTest/__unnamed_task__/Iteration 113 MetaTest/__unnamed_task__/MaxReturn -35.1533 MetaTest/__unnamed_task__/MinReturn -43.8185 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.33259 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 230000 ------------------------------------------------- ------------ 2025-03-29 19:52:10 | [pearl_trainer] epoch #114 | Training... 2025-03-29 19:52:28 | [pearl_trainer] epoch #114 | Evaluating... 2025-03-29 19:52:28 | [pearl_trainer] epoch #114 | Sampling for adapation and meta-testing... 2025-03-29 19:53:39 | [pearl_trainer] epoch #114 | Finished meta-testing... 2025-03-29 19:53:39 | [pearl_trainer] epoch #114 | Saving snapshot... 2025-03-29 19:53:40 | [pearl_trainer] epoch #114 | Saved 2025-03-29 19:53:40 | [pearl_trainer] epoch #114 | Time 20644.89 s 2025-03-29 19:53:40 | [pearl_trainer] epoch #114 | EpochTime 154.56 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -42.113 MetaTest/Average/AverageReturn -42.113 MetaTest/Average/Iteration 114 MetaTest/Average/MaxReturn -37.7564 MetaTest/Average/MinReturn -46.4697 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.35666 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -42.113 MetaTest/__unnamed_task__/AverageReturn -42.113 MetaTest/__unnamed_task__/Iteration 114 MetaTest/__unnamed_task__/MaxReturn -37.7564 MetaTest/__unnamed_task__/MinReturn -46.4697 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.35666 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 232000 ------------------------------------------------- ------------ 2025-03-29 19:54:45 | [pearl_trainer] epoch #115 | Training... 2025-03-29 19:55:03 | [pearl_trainer] epoch #115 | Evaluating... 2025-03-29 19:55:03 | [pearl_trainer] epoch #115 | Sampling for adapation and meta-testing... 2025-03-29 19:56:15 | [pearl_trainer] epoch #115 | Finished meta-testing... 2025-03-29 19:56:15 | [pearl_trainer] epoch #115 | Saving snapshot... 2025-03-29 19:56:15 | [pearl_trainer] epoch #115 | Saved 2025-03-29 19:56:15 | [pearl_trainer] epoch #115 | Time 20800.31 s 2025-03-29 19:56:15 | [pearl_trainer] epoch #115 | EpochTime 155.42 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -38.4774 MetaTest/Average/AverageReturn -38.4774 MetaTest/Average/Iteration 115 MetaTest/Average/MaxReturn -37.9376 MetaTest/Average/MinReturn -39.0172 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.539823 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.4774 MetaTest/__unnamed_task__/AverageReturn -38.4774 MetaTest/__unnamed_task__/Iteration 115 MetaTest/__unnamed_task__/MaxReturn -37.9376 MetaTest/__unnamed_task__/MinReturn -39.0172 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.539823 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 234000 ------------------------------------------------- ------------- 2025-03-29 19:57:19 | [pearl_trainer] epoch #116 | Training... 2025-03-29 19:57:37 | [pearl_trainer] epoch #116 | Evaluating... 2025-03-29 19:57:37 | [pearl_trainer] epoch #116 | Sampling for adapation and meta-testing... 2025-03-29 19:58:47 | [pearl_trainer] epoch #116 | Finished meta-testing... 2025-03-29 19:58:47 | [pearl_trainer] epoch #116 | Saving snapshot... 2025-03-29 19:58:48 | [pearl_trainer] epoch #116 | Saved 2025-03-29 19:58:48 | [pearl_trainer] epoch #116 | Time 20952.86 s 2025-03-29 19:58:48 | [pearl_trainer] epoch #116 | EpochTime 152.54 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.3499 MetaTest/Average/AverageReturn -34.3499 MetaTest/Average/Iteration 116 MetaTest/Average/MaxReturn -31.2847 MetaTest/Average/MinReturn -37.4152 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.06521 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.3499 MetaTest/__unnamed_task__/AverageReturn -34.3499 MetaTest/__unnamed_task__/Iteration 116 MetaTest/__unnamed_task__/MaxReturn -31.2847 MetaTest/__unnamed_task__/MinReturn -37.4152 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.06521 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 236000 ------------------------------------------------- ------------ 2025-03-29 19:59:52 | [pearl_trainer] epoch #117 | Training... 2025-03-29 20:00:10 | [pearl_trainer] epoch #117 | Evaluating... 2025-03-29 20:00:10 | [pearl_trainer] epoch #117 | Sampling for adapation and meta-testing... 2025-03-29 20:01:28 | [pearl_trainer] epoch #117 | Finished meta-testing... 2025-03-29 20:01:28 | [pearl_trainer] epoch #117 | Saving snapshot... 2025-03-29 20:01:29 | [pearl_trainer] epoch #117 | Saved 2025-03-29 20:01:29 | [pearl_trainer] epoch #117 | Time 21113.63 s 2025-03-29 20:01:29 | [pearl_trainer] epoch #117 | EpochTime 160.76 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -31.4743 MetaTest/Average/AverageReturn -31.4743 MetaTest/Average/Iteration 117 MetaTest/Average/MaxReturn -29.9733 MetaTest/Average/MinReturn -32.9752 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.50098 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -31.4743 MetaTest/__unnamed_task__/AverageReturn -31.4743 MetaTest/__unnamed_task__/Iteration 117 MetaTest/__unnamed_task__/MaxReturn -29.9733 MetaTest/__unnamed_task__/MinReturn -32.9752 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.50098 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 238000 ------------------------------------------------- ------------ 2025-03-29 20:02:32 | [pearl_trainer] epoch #118 | Training... 2025-03-29 20:02:51 | [pearl_trainer] epoch #118 | Evaluating... 2025-03-29 20:02:51 | [pearl_trainer] epoch #118 | Sampling for adapation and meta-testing... 2025-03-29 20:04:01 | [pearl_trainer] epoch #118 | Finished meta-testing... 2025-03-29 20:04:01 | [pearl_trainer] epoch #118 | Saving snapshot... 2025-03-29 20:04:02 | [pearl_trainer] epoch #118 | Saved 2025-03-29 20:04:02 | [pearl_trainer] epoch #118 | Time 21266.75 s 2025-03-29 20:04:02 | [pearl_trainer] epoch #118 | EpochTime 153.12 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.4839 MetaTest/Average/AverageReturn -35.4839 MetaTest/Average/Iteration 118 MetaTest/Average/MaxReturn -31.8626 MetaTest/Average/MinReturn -39.1053 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.62138 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.4839 MetaTest/__unnamed_task__/AverageReturn -35.4839 MetaTest/__unnamed_task__/Iteration 118 MetaTest/__unnamed_task__/MaxReturn -31.8626 MetaTest/__unnamed_task__/MinReturn -39.1053 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.62138 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 240000 ------------------------------------------------- ------------ 2025-03-29 20:05:11 | [pearl_trainer] epoch #119 | Training... 2025-03-29 20:05:27 | [pearl_trainer] epoch #119 | Evaluating... 2025-03-29 20:05:27 | [pearl_trainer] epoch #119 | Sampling for adapation and meta-testing... 2025-03-29 20:06:43 | [pearl_trainer] epoch #119 | Finished meta-testing... 2025-03-29 20:06:43 | [pearl_trainer] epoch #119 | Saving snapshot... 2025-03-29 20:06:44 | [pearl_trainer] epoch #119 | Saved 2025-03-29 20:06:44 | [pearl_trainer] epoch #119 | Time 21428.56 s 2025-03-29 20:06:44 | [pearl_trainer] epoch #119 | EpochTime 161.81 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -36.5047 MetaTest/Average/AverageReturn -36.5047 MetaTest/Average/Iteration 119 MetaTest/Average/MaxReturn -30.2875 MetaTest/Average/MinReturn -42.7219 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 6.2172 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.5047 MetaTest/__unnamed_task__/AverageReturn -36.5047 MetaTest/__unnamed_task__/Iteration 119 MetaTest/__unnamed_task__/MaxReturn -30.2875 MetaTest/__unnamed_task__/MinReturn -42.7219 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 6.2172 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 242000 ------------------------------------------------- ----------- 2025-03-29 20:07:59 | [pearl_trainer] epoch #120 | Training... 2025-03-29 20:08:14 | [pearl_trainer] epoch #120 | Evaluating... 2025-03-29 20:08:14 | [pearl_trainer] epoch #120 | Sampling for adapation and meta-testing... 2025-03-29 20:09:28 | [pearl_trainer] epoch #120 | Finished meta-testing... 2025-03-29 20:09:28 | [pearl_trainer] epoch #120 | Saving snapshot... 2025-03-29 20:09:30 | [pearl_trainer] epoch #120 | Saved 2025-03-29 20:09:30 | [pearl_trainer] epoch #120 | Time 21594.78 s 2025-03-29 20:09:30 | [pearl_trainer] epoch #120 | EpochTime 166.21 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.3508 MetaTest/Average/AverageReturn -33.3508 MetaTest/Average/Iteration 120 MetaTest/Average/MaxReturn -32.9993 MetaTest/Average/MinReturn -33.7024 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.351579 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.3508 MetaTest/__unnamed_task__/AverageReturn -33.3508 MetaTest/__unnamed_task__/Iteration 120 MetaTest/__unnamed_task__/MaxReturn -32.9993 MetaTest/__unnamed_task__/MinReturn -33.7024 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.351579 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 244000 ------------------------------------------------- ------------- 2025-03-29 20:10:44 | [pearl_trainer] epoch #121 | Training... 2025-03-29 20:11:01 | [pearl_trainer] epoch #121 | Evaluating... 2025-03-29 20:11:01 | [pearl_trainer] epoch #121 | Sampling for adapation and meta-testing... 2025-03-29 20:12:19 | [pearl_trainer] epoch #121 | Finished meta-testing... 2025-03-29 20:12:19 | [pearl_trainer] epoch #121 | Saving snapshot... 2025-03-29 20:12:20 | [pearl_trainer] epoch #121 | Saved 2025-03-29 20:12:20 | [pearl_trainer] epoch #121 | Time 21765.06 s 2025-03-29 20:12:20 | [pearl_trainer] epoch #121 | EpochTime 170.28 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.3822 MetaTest/Average/AverageReturn -34.3822 MetaTest/Average/Iteration 121 MetaTest/Average/MaxReturn -34.0597 MetaTest/Average/MinReturn -34.7047 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.322547 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.3822 MetaTest/__unnamed_task__/AverageReturn -34.3822 MetaTest/__unnamed_task__/Iteration 121 MetaTest/__unnamed_task__/MaxReturn -34.0597 MetaTest/__unnamed_task__/MinReturn -34.7047 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.322547 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 246000 ------------------------------------------------- ------------- 2025-03-29 20:13:26 | [pearl_trainer] epoch #122 | Training... 2025-03-29 20:13:44 | [pearl_trainer] epoch #122 | Evaluating... 2025-03-29 20:13:44 | [pearl_trainer] epoch #122 | Sampling for adapation and meta-testing... 2025-03-29 20:15:09 | [pearl_trainer] epoch #122 | Finished meta-testing... 2025-03-29 20:15:09 | [pearl_trainer] epoch #122 | Saving snapshot... 2025-03-29 20:15:10 | [pearl_trainer] epoch #122 | Saved 2025-03-29 20:15:10 | [pearl_trainer] epoch #122 | Time 21935.14 s 2025-03-29 20:15:10 | [pearl_trainer] epoch #122 | EpochTime 170.08 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.7555 MetaTest/Average/AverageReturn -33.7555 MetaTest/Average/Iteration 122 MetaTest/Average/MaxReturn -32.2005 MetaTest/Average/MinReturn -35.3105 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.55499 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.7555 MetaTest/__unnamed_task__/AverageReturn -33.7555 MetaTest/__unnamed_task__/Iteration 122 MetaTest/__unnamed_task__/MaxReturn -32.2005 MetaTest/__unnamed_task__/MinReturn -35.3105 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.55499 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 248000 ------------------------------------------------- ------------ 2025-03-29 20:16:27 | [pearl_trainer] epoch #123 | Training... 2025-03-29 20:16:45 | [pearl_trainer] epoch #123 | Evaluating... 2025-03-29 20:16:45 | [pearl_trainer] epoch #123 | Sampling for adapation and meta-testing... 2025-03-29 20:18:11 | [pearl_trainer] epoch #123 | Finished meta-testing... 2025-03-29 20:18:11 | [pearl_trainer] epoch #123 | Saving snapshot... 2025-03-29 20:18:13 | [pearl_trainer] epoch #123 | Saved 2025-03-29 20:18:13 | [pearl_trainer] epoch #123 | Time 22117.47 s 2025-03-29 20:18:13 | [pearl_trainer] epoch #123 | EpochTime 182.33 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -40.0981 MetaTest/Average/AverageReturn -40.0981 MetaTest/Average/Iteration 123 MetaTest/Average/MaxReturn -38.4074 MetaTest/Average/MinReturn -41.7888 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.69067 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -40.0981 MetaTest/__unnamed_task__/AverageReturn -40.0981 MetaTest/__unnamed_task__/Iteration 123 MetaTest/__unnamed_task__/MaxReturn -38.4074 MetaTest/__unnamed_task__/MinReturn -41.7888 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.69067 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 250000 ------------------------------------------------- ------------ 2025-03-29 20:19:32 | [pearl_trainer] epoch #124 | Training... 2025-03-29 20:19:53 | [pearl_trainer] epoch #124 | Evaluating... 2025-03-29 20:19:53 | [pearl_trainer] epoch #124 | Sampling for adapation and meta-testing... 2025-03-29 20:21:21 | [pearl_trainer] epoch #124 | Finished meta-testing... 2025-03-29 20:21:21 | [pearl_trainer] epoch #124 | Saving snapshot... 2025-03-29 20:21:22 | [pearl_trainer] epoch #124 | Saved 2025-03-29 20:21:22 | [pearl_trainer] epoch #124 | Time 22306.74 s 2025-03-29 20:21:22 | [pearl_trainer] epoch #124 | EpochTime 189.27 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -31.1925 MetaTest/Average/AverageReturn -31.1925 MetaTest/Average/Iteration 124 MetaTest/Average/MaxReturn -29.9919 MetaTest/Average/MinReturn -32.393 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.20057 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -31.1925 MetaTest/__unnamed_task__/AverageReturn -31.1925 MetaTest/__unnamed_task__/Iteration 124 MetaTest/__unnamed_task__/MaxReturn -29.9919 MetaTest/__unnamed_task__/MinReturn -32.393 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.20057 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 252000 ------------------------------------------------- ------------ 2025-03-29 20:22:41 | [pearl_trainer] epoch #125 | Training... 2025-03-29 20:23:04 | [pearl_trainer] epoch #125 | Evaluating... 2025-03-29 20:23:04 | [pearl_trainer] epoch #125 | Sampling for adapation and meta-testing... 2025-03-29 20:24:24 | [pearl_trainer] epoch #125 | Finished meta-testing... 2025-03-29 20:24:24 | [pearl_trainer] epoch #125 | Saving snapshot... 2025-03-29 20:24:25 | [pearl_trainer] epoch #125 | Saved 2025-03-29 20:24:25 | [pearl_trainer] epoch #125 | Time 22489.61 s 2025-03-29 20:24:25 | [pearl_trainer] epoch #125 | EpochTime 182.87 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -32.7845 MetaTest/Average/AverageReturn -32.7845 MetaTest/Average/Iteration 125 MetaTest/Average/MaxReturn -31.7456 MetaTest/Average/MinReturn -33.8234 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.03888 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -32.7845 MetaTest/__unnamed_task__/AverageReturn -32.7845 MetaTest/__unnamed_task__/Iteration 125 MetaTest/__unnamed_task__/MaxReturn -31.7456 MetaTest/__unnamed_task__/MinReturn -33.8234 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.03888 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 254000 ------------------------------------------------- ------------ 2025-03-29 20:25:31 | [pearl_trainer] epoch #126 | Training... 2025-03-29 20:25:49 | [pearl_trainer] epoch #126 | Evaluating... 2025-03-29 20:25:49 | [pearl_trainer] epoch #126 | Sampling for adapation and meta-testing... 2025-03-29 20:27:04 | [pearl_trainer] epoch #126 | Finished meta-testing... 2025-03-29 20:27:04 | [pearl_trainer] epoch #126 | Saving snapshot... 2025-03-29 20:27:05 | [pearl_trainer] epoch #126 | Saved 2025-03-29 20:27:05 | [pearl_trainer] epoch #126 | Time 22649.88 s 2025-03-29 20:27:05 | [pearl_trainer] epoch #126 | EpochTime 160.26 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.4892 MetaTest/Average/AverageReturn -34.4892 MetaTest/Average/Iteration 126 MetaTest/Average/MaxReturn -32.0474 MetaTest/Average/MinReturn -36.931 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.44179 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.4892 MetaTest/__unnamed_task__/AverageReturn -34.4892 MetaTest/__unnamed_task__/Iteration 126 MetaTest/__unnamed_task__/MaxReturn -32.0474 MetaTest/__unnamed_task__/MinReturn -36.931 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.44179 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 256000 ------------------------------------------------- ------------ 2025-03-29 20:28:14 | [pearl_trainer] epoch #127 | Training... 2025-03-29 20:28:33 | [pearl_trainer] epoch #127 | Evaluating... 2025-03-29 20:28:33 | [pearl_trainer] epoch #127 | Sampling for adapation and meta-testing... 2025-03-29 20:29:44 | [pearl_trainer] epoch #127 | Finished meta-testing... 2025-03-29 20:29:44 | [pearl_trainer] epoch #127 | Saving snapshot... 2025-03-29 20:29:45 | [pearl_trainer] epoch #127 | Saved 2025-03-29 20:29:45 | [pearl_trainer] epoch #127 | Time 22810.02 s 2025-03-29 20:29:45 | [pearl_trainer] epoch #127 | EpochTime 160.14 s ------------------------------------------------- -------------- MetaTest/Average/AverageDiscountedReturn -37.2803 MetaTest/Average/AverageReturn -37.2803 MetaTest/Average/Iteration 127 MetaTest/Average/MaxReturn -37.1956 MetaTest/Average/MinReturn -37.3649 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.0846381 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.2803 MetaTest/__unnamed_task__/AverageReturn -37.2803 MetaTest/__unnamed_task__/Iteration 127 MetaTest/__unnamed_task__/MaxReturn -37.1956 MetaTest/__unnamed_task__/MinReturn -37.3649 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.0846381 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 258000 ------------------------------------------------- -------------- 2025-03-29 20:30:49 | [pearl_trainer] epoch #128 | Training... 2025-03-29 20:31:03 | [pearl_trainer] epoch #128 | Evaluating... 2025-03-29 20:31:03 | [pearl_trainer] epoch #128 | Sampling for adapation and meta-testing... 2025-03-29 20:32:15 | [pearl_trainer] epoch #128 | Finished meta-testing... 2025-03-29 20:32:15 | [pearl_trainer] epoch #128 | Saving snapshot... 2025-03-29 20:32:15 | [pearl_trainer] epoch #128 | Saved 2025-03-29 20:32:15 | [pearl_trainer] epoch #128 | Time 22960.23 s 2025-03-29 20:32:15 | [pearl_trainer] epoch #128 | EpochTime 150.21 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.9117 MetaTest/Average/AverageReturn -35.9117 MetaTest/Average/Iteration 128 MetaTest/Average/MaxReturn -33.5463 MetaTest/Average/MinReturn -38.2771 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.36542 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.9117 MetaTest/__unnamed_task__/AverageReturn -35.9117 MetaTest/__unnamed_task__/Iteration 128 MetaTest/__unnamed_task__/MaxReturn -33.5463 MetaTest/__unnamed_task__/MinReturn -38.2771 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.36542 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 260000 ------------------------------------------------- ------------ 2025-03-29 20:33:20 | [pearl_trainer] epoch #129 | Training... 2025-03-29 20:33:34 | [pearl_trainer] epoch #129 | Evaluating... 2025-03-29 20:33:34 | [pearl_trainer] epoch #129 | Sampling for adapation and meta-testing... 2025-03-29 20:34:44 | [pearl_trainer] epoch #129 | Finished meta-testing... 2025-03-29 20:34:44 | [pearl_trainer] epoch #129 | Saving snapshot... 2025-03-29 20:34:45 | [pearl_trainer] epoch #129 | Saved 2025-03-29 20:34:45 | [pearl_trainer] epoch #129 | Time 23110.31 s 2025-03-29 20:34:45 | [pearl_trainer] epoch #129 | EpochTime 150.08 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.8372 MetaTest/Average/AverageReturn -36.8372 MetaTest/Average/Iteration 129 MetaTest/Average/MaxReturn -34.5974 MetaTest/Average/MinReturn -39.077 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.23982 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.8372 MetaTest/__unnamed_task__/AverageReturn -36.8372 MetaTest/__unnamed_task__/Iteration 129 MetaTest/__unnamed_task__/MaxReturn -34.5974 MetaTest/__unnamed_task__/MinReturn -39.077 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.23982 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 262000 ------------------------------------------------- ------------ 2025-03-29 20:35:51 | [pearl_trainer] epoch #130 | Training... 2025-03-29 20:36:08 | [pearl_trainer] epoch #130 | Evaluating... 2025-03-29 20:36:08 | [pearl_trainer] epoch #130 | Sampling for adapation and meta-testing... 2025-03-29 20:37:18 | [pearl_trainer] epoch #130 | Finished meta-testing... 2025-03-29 20:37:18 | [pearl_trainer] epoch #130 | Saving snapshot... 2025-03-29 20:37:19 | [pearl_trainer] epoch #130 | Saved 2025-03-29 20:37:19 | [pearl_trainer] epoch #130 | Time 23263.99 s 2025-03-29 20:37:19 | [pearl_trainer] epoch #130 | EpochTime 153.67 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.3688 MetaTest/Average/AverageReturn -34.3688 MetaTest/Average/Iteration 130 MetaTest/Average/MaxReturn -32.1081 MetaTest/Average/MinReturn -36.6295 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.26071 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.3688 MetaTest/__unnamed_task__/AverageReturn -34.3688 MetaTest/__unnamed_task__/Iteration 130 MetaTest/__unnamed_task__/MaxReturn -32.1081 MetaTest/__unnamed_task__/MinReturn -36.6295 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.26071 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 264000 ------------------------------------------------- ------------ 2025-03-29 20:38:23 | [pearl_trainer] epoch #131 | Training... 2025-03-29 20:38:41 | [pearl_trainer] epoch #131 | Evaluating... 2025-03-29 20:38:41 | [pearl_trainer] epoch #131 | Sampling for adapation and meta-testing... 2025-03-29 20:39:53 | [pearl_trainer] epoch #131 | Finished meta-testing... 2025-03-29 20:39:53 | [pearl_trainer] epoch #131 | Saving snapshot... 2025-03-29 20:39:54 | [pearl_trainer] epoch #131 | Saved 2025-03-29 20:39:54 | [pearl_trainer] epoch #131 | Time 23418.57 s 2025-03-29 20:39:54 | [pearl_trainer] epoch #131 | EpochTime 154.58 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.2417 MetaTest/Average/AverageReturn -38.2417 MetaTest/Average/Iteration 131 MetaTest/Average/MaxReturn -35.481 MetaTest/Average/MinReturn -41.0024 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.76071 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.2417 MetaTest/__unnamed_task__/AverageReturn -38.2417 MetaTest/__unnamed_task__/Iteration 131 MetaTest/__unnamed_task__/MaxReturn -35.481 MetaTest/__unnamed_task__/MinReturn -41.0024 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.76071 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 266000 ------------------------------------------------- ------------ 2025-03-29 20:41:02 | [pearl_trainer] epoch #132 | Training... 2025-03-29 20:41:19 | [pearl_trainer] epoch #132 | Evaluating... 2025-03-29 20:41:19 | [pearl_trainer] epoch #132 | Sampling for adapation and meta-testing... 2025-03-29 20:42:30 | [pearl_trainer] epoch #132 | Finished meta-testing... 2025-03-29 20:42:30 | [pearl_trainer] epoch #132 | Saving snapshot... 2025-03-29 20:42:31 | [pearl_trainer] epoch #132 | Saved 2025-03-29 20:42:31 | [pearl_trainer] epoch #132 | Time 23575.86 s 2025-03-29 20:42:31 | [pearl_trainer] epoch #132 | EpochTime 157.28 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.808 MetaTest/Average/AverageReturn -34.808 MetaTest/Average/Iteration 132 MetaTest/Average/MaxReturn -32.995 MetaTest/Average/MinReturn -36.6209 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.81292 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.808 MetaTest/__unnamed_task__/AverageReturn -34.808 MetaTest/__unnamed_task__/Iteration 132 MetaTest/__unnamed_task__/MaxReturn -32.995 MetaTest/__unnamed_task__/MinReturn -36.6209 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.81292 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 268000 ------------------------------------------------- ------------ 2025-03-29 20:43:36 | [pearl_trainer] epoch #133 | Training... 2025-03-29 20:43:52 | [pearl_trainer] epoch #133 | Evaluating... 2025-03-29 20:43:52 | [pearl_trainer] epoch #133 | Sampling for adapation and meta-testing... 2025-03-29 20:45:06 | [pearl_trainer] epoch #133 | Finished meta-testing... 2025-03-29 20:45:06 | [pearl_trainer] epoch #133 | Saving snapshot... 2025-03-29 20:45:06 | [pearl_trainer] epoch #133 | Saved 2025-03-29 20:45:06 | [pearl_trainer] epoch #133 | Time 23731.38 s 2025-03-29 20:45:06 | [pearl_trainer] epoch #133 | EpochTime 155.52 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.3137 MetaTest/Average/AverageReturn -38.3137 MetaTest/Average/Iteration 133 MetaTest/Average/MaxReturn -32.6228 MetaTest/Average/MinReturn -44.0045 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 5.69085 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.3137 MetaTest/__unnamed_task__/AverageReturn -38.3137 MetaTest/__unnamed_task__/Iteration 133 MetaTest/__unnamed_task__/MaxReturn -32.6228 MetaTest/__unnamed_task__/MinReturn -44.0045 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 5.69085 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 270000 ------------------------------------------------- ------------ 2025-03-29 20:46:13 | [pearl_trainer] epoch #134 | Training... 2025-03-29 20:46:31 | [pearl_trainer] epoch #134 | Evaluating... 2025-03-29 20:46:31 | [pearl_trainer] epoch #134 | Sampling for adapation and meta-testing... 2025-03-29 20:47:42 | [pearl_trainer] epoch #134 | Finished meta-testing... 2025-03-29 20:47:42 | [pearl_trainer] epoch #134 | Saving snapshot... 2025-03-29 20:47:43 | [pearl_trainer] epoch #134 | Saved 2025-03-29 20:47:43 | [pearl_trainer] epoch #134 | Time 23887.80 s 2025-03-29 20:47:43 | [pearl_trainer] epoch #134 | EpochTime 156.42 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.8099 MetaTest/Average/AverageReturn -36.8099 MetaTest/Average/Iteration 134 MetaTest/Average/MaxReturn -31.7992 MetaTest/Average/MinReturn -41.8207 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 5.01075 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.8099 MetaTest/__unnamed_task__/AverageReturn -36.8099 MetaTest/__unnamed_task__/Iteration 134 MetaTest/__unnamed_task__/MaxReturn -31.7992 MetaTest/__unnamed_task__/MinReturn -41.8207 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 5.01075 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 272000 ------------------------------------------------- ------------ 2025-03-29 20:48:48 | [pearl_trainer] epoch #135 | Training... 2025-03-29 20:49:05 | [pearl_trainer] epoch #135 | Evaluating... 2025-03-29 20:49:05 | [pearl_trainer] epoch #135 | Sampling for adapation and meta-testing... 2025-03-29 20:50:16 | [pearl_trainer] epoch #135 | Finished meta-testing... 2025-03-29 20:50:16 | [pearl_trainer] epoch #135 | Saving snapshot... 2025-03-29 20:50:17 | [pearl_trainer] epoch #135 | Saved 2025-03-29 20:50:17 | [pearl_trainer] epoch #135 | Time 24041.87 s 2025-03-29 20:50:17 | [pearl_trainer] epoch #135 | EpochTime 154.07 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -33.0954 MetaTest/Average/AverageReturn -33.0954 MetaTest/Average/Iteration 135 MetaTest/Average/MaxReturn -31.8287 MetaTest/Average/MinReturn -34.3621 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.2667 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.0954 MetaTest/__unnamed_task__/AverageReturn -33.0954 MetaTest/__unnamed_task__/Iteration 135 MetaTest/__unnamed_task__/MaxReturn -31.8287 MetaTest/__unnamed_task__/MinReturn -34.3621 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.2667 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 274000 ------------------------------------------------- ----------- 2025-03-29 20:51:22 | [pearl_trainer] epoch #136 | Training... 2025-03-29 20:51:40 | [pearl_trainer] epoch #136 | Evaluating... 2025-03-29 20:51:40 | [pearl_trainer] epoch #136 | Sampling for adapation and meta-testing... 2025-03-29 20:52:54 | [pearl_trainer] epoch #136 | Finished meta-testing... 2025-03-29 20:52:54 | [pearl_trainer] epoch #136 | Saving snapshot... 2025-03-29 20:52:54 | [pearl_trainer] epoch #136 | Saved 2025-03-29 20:52:54 | [pearl_trainer] epoch #136 | Time 24199.35 s 2025-03-29 20:52:54 | [pearl_trainer] epoch #136 | EpochTime 157.48 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -32.8025 MetaTest/Average/AverageReturn -32.8025 MetaTest/Average/Iteration 136 MetaTest/Average/MaxReturn -31.0662 MetaTest/Average/MinReturn -34.5389 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.73639 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -32.8025 MetaTest/__unnamed_task__/AverageReturn -32.8025 MetaTest/__unnamed_task__/Iteration 136 MetaTest/__unnamed_task__/MaxReturn -31.0662 MetaTest/__unnamed_task__/MinReturn -34.5389 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.73639 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 276000 ------------------------------------------------- ------------ 2025-03-29 20:54:04 | [pearl_trainer] epoch #137 | Training... 2025-03-29 20:54:21 | [pearl_trainer] epoch #137 | Evaluating... 2025-03-29 20:54:21 | [pearl_trainer] epoch #137 | Sampling for adapation and meta-testing... 2025-03-29 20:55:37 | [pearl_trainer] epoch #137 | Finished meta-testing... 2025-03-29 20:55:37 | [pearl_trainer] epoch #137 | Saving snapshot... 2025-03-29 20:55:37 | [pearl_trainer] epoch #137 | Saved 2025-03-29 20:55:37 | [pearl_trainer] epoch #137 | Time 24362.43 s 2025-03-29 20:55:37 | [pearl_trainer] epoch #137 | EpochTime 163.09 s ------------------------------------------------- -------------- MetaTest/Average/AverageDiscountedReturn -33.6071 MetaTest/Average/AverageReturn -33.6071 MetaTest/Average/Iteration 137 MetaTest/Average/MaxReturn -33.5821 MetaTest/Average/MinReturn -33.6321 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.0250152 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.6071 MetaTest/__unnamed_task__/AverageReturn -33.6071 MetaTest/__unnamed_task__/Iteration 137 MetaTest/__unnamed_task__/MaxReturn -33.5821 MetaTest/__unnamed_task__/MinReturn -33.6321 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.0250152 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 278000 ------------------------------------------------- -------------- 2025-03-29 20:56:43 | [pearl_trainer] epoch #138 | Training... 2025-03-29 20:56:58 | [pearl_trainer] epoch #138 | Evaluating... 2025-03-29 20:56:58 | [pearl_trainer] epoch #138 | Sampling for adapation and meta-testing... 2025-03-29 20:58:11 | [pearl_trainer] epoch #138 | Finished meta-testing... 2025-03-29 20:58:11 | [pearl_trainer] epoch #138 | Saving snapshot... 2025-03-29 20:58:12 | [pearl_trainer] epoch #138 | Saved 2025-03-29 20:58:12 | [pearl_trainer] epoch #138 | Time 24516.94 s 2025-03-29 20:58:12 | [pearl_trainer] epoch #138 | EpochTime 154.50 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -37.8783 MetaTest/Average/AverageReturn -37.8783 MetaTest/Average/Iteration 138 MetaTest/Average/MaxReturn -37.0973 MetaTest/Average/MinReturn -38.6592 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.780933 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.8783 MetaTest/__unnamed_task__/AverageReturn -37.8783 MetaTest/__unnamed_task__/Iteration 138 MetaTest/__unnamed_task__/MaxReturn -37.0973 MetaTest/__unnamed_task__/MinReturn -38.6592 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.780933 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 280000 ------------------------------------------------- ------------- 2025-03-29 20:59:21 | [pearl_trainer] epoch #139 | Training... 2025-03-29 20:59:37 | [pearl_trainer] epoch #139 | Evaluating... 2025-03-29 20:59:37 | [pearl_trainer] epoch #139 | Sampling for adapation and meta-testing... 2025-03-29 21:00:51 | [pearl_trainer] epoch #139 | Finished meta-testing... 2025-03-29 21:00:51 | [pearl_trainer] epoch #139 | Saving snapshot... 2025-03-29 21:00:52 | [pearl_trainer] epoch #139 | Saved 2025-03-29 21:00:52 | [pearl_trainer] epoch #139 | Time 24676.78 s 2025-03-29 21:00:52 | [pearl_trainer] epoch #139 | EpochTime 159.84 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.4427 MetaTest/Average/AverageReturn -34.4427 MetaTest/Average/Iteration 139 MetaTest/Average/MaxReturn -30.1845 MetaTest/Average/MinReturn -38.7009 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.25822 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.4427 MetaTest/__unnamed_task__/AverageReturn -34.4427 MetaTest/__unnamed_task__/Iteration 139 MetaTest/__unnamed_task__/MaxReturn -30.1845 MetaTest/__unnamed_task__/MinReturn -38.7009 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.25822 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 282000 ------------------------------------------------- ------------ 2025-03-29 21:02:01 | [pearl_trainer] epoch #140 | Training... 2025-03-29 21:02:17 | [pearl_trainer] epoch #140 | Evaluating... 2025-03-29 21:02:17 | [pearl_trainer] epoch #140 | Sampling for adapation and meta-testing... 2025-03-29 21:03:31 | [pearl_trainer] epoch #140 | Finished meta-testing... 2025-03-29 21:03:31 | [pearl_trainer] epoch #140 | Saving snapshot... 2025-03-29 21:03:32 | [pearl_trainer] epoch #140 | Saved 2025-03-29 21:03:32 | [pearl_trainer] epoch #140 | Time 24836.47 s 2025-03-29 21:03:32 | [pearl_trainer] epoch #140 | EpochTime 159.69 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.3735 MetaTest/Average/AverageReturn -35.3735 MetaTest/Average/Iteration 140 MetaTest/Average/MaxReturn -32.6561 MetaTest/Average/MinReturn -38.0909 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.71738 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.3735 MetaTest/__unnamed_task__/AverageReturn -35.3735 MetaTest/__unnamed_task__/Iteration 140 MetaTest/__unnamed_task__/MaxReturn -32.6561 MetaTest/__unnamed_task__/MinReturn -38.0909 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.71738 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 284000 ------------------------------------------------- ------------ 2025-03-29 21:04:42 | [pearl_trainer] epoch #141 | Training... 2025-03-29 21:04:59 | [pearl_trainer] epoch #141 | Evaluating... 2025-03-29 21:04:59 | [pearl_trainer] epoch #141 | Sampling for adapation and meta-testing... 2025-03-29 21:06:10 | [pearl_trainer] epoch #141 | Finished meta-testing... 2025-03-29 21:06:10 | [pearl_trainer] epoch #141 | Saving snapshot... 2025-03-29 21:06:11 | [pearl_trainer] epoch #141 | Saved 2025-03-29 21:06:11 | [pearl_trainer] epoch #141 | Time 24996.07 s 2025-03-29 21:06:11 | [pearl_trainer] epoch #141 | EpochTime 159.60 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -43.4452 MetaTest/Average/AverageReturn -43.4452 MetaTest/Average/Iteration 141 MetaTest/Average/MaxReturn -42.5933 MetaTest/Average/MinReturn -44.2971 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.851916 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -43.4452 MetaTest/__unnamed_task__/AverageReturn -43.4452 MetaTest/__unnamed_task__/Iteration 141 MetaTest/__unnamed_task__/MaxReturn -42.5933 MetaTest/__unnamed_task__/MinReturn -44.2971 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.851916 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 286000 ------------------------------------------------- ------------- 2025-03-29 21:07:16 | [pearl_trainer] epoch #142 | Training... 2025-03-29 21:07:37 | [pearl_trainer] epoch #142 | Evaluating... 2025-03-29 21:07:37 | [pearl_trainer] epoch #142 | Sampling for adapation and meta-testing... 2025-03-29 21:09:04 | [pearl_trainer] epoch #142 | Finished meta-testing... 2025-03-29 21:09:04 | [pearl_trainer] epoch #142 | Saving snapshot... 2025-03-29 21:09:05 | [pearl_trainer] epoch #142 | Saved 2025-03-29 21:09:05 | [pearl_trainer] epoch #142 | Time 25169.60 s 2025-03-29 21:09:05 | [pearl_trainer] epoch #142 | EpochTime 173.52 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -36.0937 MetaTest/Average/AverageReturn -36.0937 MetaTest/Average/Iteration 142 MetaTest/Average/MaxReturn -35.6323 MetaTest/Average/MinReturn -36.5552 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.461465 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.0937 MetaTest/__unnamed_task__/AverageReturn -36.0937 MetaTest/__unnamed_task__/Iteration 142 MetaTest/__unnamed_task__/MaxReturn -35.6323 MetaTest/__unnamed_task__/MinReturn -36.5552 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.461465 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 288000 ------------------------------------------------- ------------- 2025-03-29 21:10:23 | [pearl_trainer] epoch #143 | Training... 2025-03-29 21:10:45 | [pearl_trainer] epoch #143 | Evaluating... 2025-03-29 21:10:45 | [pearl_trainer] epoch #143 | Sampling for adapation and meta-testing... 2025-03-29 21:12:13 | [pearl_trainer] epoch #143 | Finished meta-testing... 2025-03-29 21:12:13 | [pearl_trainer] epoch #143 | Saving snapshot... 2025-03-29 21:12:14 | [pearl_trainer] epoch #143 | Saved 2025-03-29 21:12:14 | [pearl_trainer] epoch #143 | Time 25358.50 s 2025-03-29 21:12:14 | [pearl_trainer] epoch #143 | EpochTime 188.90 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.5605 MetaTest/Average/AverageReturn -38.5605 MetaTest/Average/Iteration 143 MetaTest/Average/MaxReturn -36.7498 MetaTest/Average/MinReturn -40.3711 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.81064 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.5605 MetaTest/__unnamed_task__/AverageReturn -38.5605 MetaTest/__unnamed_task__/Iteration 143 MetaTest/__unnamed_task__/MaxReturn -36.7498 MetaTest/__unnamed_task__/MinReturn -40.3711 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.81064 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 290000 ------------------------------------------------- ------------ 2025-03-29 21:13:30 | [pearl_trainer] epoch #144 | Training... 2025-03-29 21:13:48 | [pearl_trainer] epoch #144 | Evaluating... 2025-03-29 21:13:48 | [pearl_trainer] epoch #144 | Sampling for adapation and meta-testing... 2025-03-29 21:15:01 | [pearl_trainer] epoch #144 | Finished meta-testing... 2025-03-29 21:15:01 | [pearl_trainer] epoch #144 | Saving snapshot... 2025-03-29 21:15:02 | [pearl_trainer] epoch #144 | Saved 2025-03-29 21:15:02 | [pearl_trainer] epoch #144 | Time 25526.94 s 2025-03-29 21:15:02 | [pearl_trainer] epoch #144 | EpochTime 168.44 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -39.6828 MetaTest/Average/AverageReturn -39.6828 MetaTest/Average/Iteration 144 MetaTest/Average/MaxReturn -38.845 MetaTest/Average/MinReturn -40.5206 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.83778 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.6828 MetaTest/__unnamed_task__/AverageReturn -39.6828 MetaTest/__unnamed_task__/Iteration 144 MetaTest/__unnamed_task__/MaxReturn -38.845 MetaTest/__unnamed_task__/MinReturn -40.5206 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.83778 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 292000 ------------------------------------------------- ------------ 2025-03-29 21:16:05 | [pearl_trainer] epoch #145 | Training... 2025-03-29 21:16:22 | [pearl_trainer] epoch #145 | Evaluating... 2025-03-29 21:16:22 | [pearl_trainer] epoch #145 | Sampling for adapation and meta-testing... 2025-03-29 21:17:32 | [pearl_trainer] epoch #145 | Finished meta-testing... 2025-03-29 21:17:32 | [pearl_trainer] epoch #145 | Saving snapshot... 2025-03-29 21:17:32 | [pearl_trainer] epoch #145 | Saved 2025-03-29 21:17:32 | [pearl_trainer] epoch #145 | Time 25677.36 s 2025-03-29 21:17:32 | [pearl_trainer] epoch #145 | EpochTime 150.42 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -41.4566 MetaTest/Average/AverageReturn -41.4566 MetaTest/Average/Iteration 145 MetaTest/Average/MaxReturn -41.193 MetaTest/Average/MinReturn -41.7202 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.263602 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -41.4566 MetaTest/__unnamed_task__/AverageReturn -41.4566 MetaTest/__unnamed_task__/Iteration 145 MetaTest/__unnamed_task__/MaxReturn -41.193 MetaTest/__unnamed_task__/MinReturn -41.7202 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.263602 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 294000 ------------------------------------------------- ------------- 2025-03-29 21:18:41 | [pearl_trainer] epoch #146 | Training... 2025-03-29 21:18:56 | [pearl_trainer] epoch #146 | Evaluating... 2025-03-29 21:18:56 | [pearl_trainer] epoch #146 | Sampling for adapation and meta-testing... 2025-03-29 21:20:14 | [pearl_trainer] epoch #146 | Finished meta-testing... 2025-03-29 21:20:14 | [pearl_trainer] epoch #146 | Saving snapshot... 2025-03-29 21:20:15 | [pearl_trainer] epoch #146 | Saved 2025-03-29 21:20:15 | [pearl_trainer] epoch #146 | Time 25839.74 s 2025-03-29 21:20:15 | [pearl_trainer] epoch #146 | EpochTime 162.37 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.213 MetaTest/Average/AverageReturn -34.213 MetaTest/Average/Iteration 146 MetaTest/Average/MaxReturn -32.8482 MetaTest/Average/MinReturn -35.5779 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.36485 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.213 MetaTest/__unnamed_task__/AverageReturn -34.213 MetaTest/__unnamed_task__/Iteration 146 MetaTest/__unnamed_task__/MaxReturn -32.8482 MetaTest/__unnamed_task__/MinReturn -35.5779 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.36485 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 296000 ------------------------------------------------- ------------ 2025-03-29 21:21:21 | [pearl_trainer] epoch #147 | Training... 2025-03-29 21:21:38 | [pearl_trainer] epoch #147 | Evaluating... 2025-03-29 21:21:38 | [pearl_trainer] epoch #147 | Sampling for adapation and meta-testing... 2025-03-29 21:23:02 | [pearl_trainer] epoch #147 | Finished meta-testing... 2025-03-29 21:23:02 | [pearl_trainer] epoch #147 | Saving snapshot... 2025-03-29 21:23:03 | [pearl_trainer] epoch #147 | Saved 2025-03-29 21:23:03 | [pearl_trainer] epoch #147 | Time 26008.18 s 2025-03-29 21:23:03 | [pearl_trainer] epoch #147 | EpochTime 168.44 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -39.9711 MetaTest/Average/AverageReturn -39.9711 MetaTest/Average/Iteration 147 MetaTest/Average/MaxReturn -39.2841 MetaTest/Average/MinReturn -40.6581 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.686993 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.9711 MetaTest/__unnamed_task__/AverageReturn -39.9711 MetaTest/__unnamed_task__/Iteration 147 MetaTest/__unnamed_task__/MaxReturn -39.2841 MetaTest/__unnamed_task__/MinReturn -40.6581 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.686993 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 298000 ------------------------------------------------- ------------- 2025-03-29 21:24:17 | [pearl_trainer] epoch #148 | Training... 2025-03-29 21:24:36 | [pearl_trainer] epoch #148 | Evaluating... 2025-03-29 21:24:36 | [pearl_trainer] epoch #148 | Sampling for adapation and meta-testing... 2025-03-29 21:25:57 | [pearl_trainer] epoch #148 | Finished meta-testing... 2025-03-29 21:25:57 | [pearl_trainer] epoch #148 | Saving snapshot... 2025-03-29 21:25:58 | [pearl_trainer] epoch #148 | Saved 2025-03-29 21:25:58 | [pearl_trainer] epoch #148 | Time 26182.78 s 2025-03-29 21:25:58 | [pearl_trainer] epoch #148 | EpochTime 174.60 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -38.6995 MetaTest/Average/AverageReturn -38.6995 MetaTest/Average/Iteration 148 MetaTest/Average/MaxReturn -38.2274 MetaTest/Average/MinReturn -39.1716 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.472124 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.6995 MetaTest/__unnamed_task__/AverageReturn -38.6995 MetaTest/__unnamed_task__/Iteration 148 MetaTest/__unnamed_task__/MaxReturn -38.2274 MetaTest/__unnamed_task__/MinReturn -39.1716 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.472124 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 300000 ------------------------------------------------- ------------- 2025-03-29 21:27:06 | [pearl_trainer] epoch #149 | Training... 2025-03-29 21:27:26 | [pearl_trainer] epoch #149 | Evaluating... 2025-03-29 21:27:26 | [pearl_trainer] epoch #149 | Sampling for adapation and meta-testing... 2025-03-29 21:28:55 | [pearl_trainer] epoch #149 | Finished meta-testing... 2025-03-29 21:28:55 | [pearl_trainer] epoch #149 | Saving snapshot... 2025-03-29 21:28:56 | [pearl_trainer] epoch #149 | Saved 2025-03-29 21:28:56 | [pearl_trainer] epoch #149 | Time 26360.60 s 2025-03-29 21:28:56 | [pearl_trainer] epoch #149 | EpochTime 177.82 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -36.7614 MetaTest/Average/AverageReturn -36.7614 MetaTest/Average/Iteration 149 MetaTest/Average/MaxReturn -36.4985 MetaTest/Average/MinReturn -37.0243 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.262883 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.7614 MetaTest/__unnamed_task__/AverageReturn -36.7614 MetaTest/__unnamed_task__/Iteration 149 MetaTest/__unnamed_task__/MaxReturn -36.4985 MetaTest/__unnamed_task__/MinReturn -37.0243 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.262883 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 302000 ------------------------------------------------- ------------- 2025-03-29 21:30:15 | [pearl_trainer] epoch #150 | Training... 2025-03-29 21:30:32 | [pearl_trainer] epoch #150 | Evaluating... 2025-03-29 21:30:32 | [pearl_trainer] epoch #150 | Sampling for adapation and meta-testing... 2025-03-29 21:32:02 | [pearl_trainer] epoch #150 | Finished meta-testing... 2025-03-29 21:32:02 | [pearl_trainer] epoch #150 | Saving snapshot... 2025-03-29 21:32:03 | [pearl_trainer] epoch #150 | Saved 2025-03-29 21:32:03 | [pearl_trainer] epoch #150 | Time 26547.99 s 2025-03-29 21:32:03 | [pearl_trainer] epoch #150 | EpochTime 187.39 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.9553 MetaTest/Average/AverageReturn -38.9553 MetaTest/Average/Iteration 150 MetaTest/Average/MaxReturn -38.0809 MetaTest/Average/MinReturn -39.8296 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.87433 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.9553 MetaTest/__unnamed_task__/AverageReturn -38.9553 MetaTest/__unnamed_task__/Iteration 150 MetaTest/__unnamed_task__/MaxReturn -38.0809 MetaTest/__unnamed_task__/MinReturn -39.8296 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.87433 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 304000 ------------------------------------------------- ------------ 2025-03-29 21:33:13 | [pearl_trainer] epoch #151 | Training... 2025-03-29 21:33:31 | [pearl_trainer] epoch #151 | Evaluating... 2025-03-29 21:33:31 | [pearl_trainer] epoch #151 | Sampling for adapation and meta-testing... 2025-03-29 21:34:56 | [pearl_trainer] epoch #151 | Finished meta-testing... 2025-03-29 21:34:56 | [pearl_trainer] epoch #151 | Saving snapshot... 2025-03-29 21:34:57 | [pearl_trainer] epoch #151 | Saved 2025-03-29 21:34:57 | [pearl_trainer] epoch #151 | Time 26721.49 s 2025-03-29 21:34:57 | [pearl_trainer] epoch #151 | EpochTime 173.49 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.9861 MetaTest/Average/AverageReturn -37.9861 MetaTest/Average/Iteration 151 MetaTest/Average/MaxReturn -34.9169 MetaTest/Average/MinReturn -41.0554 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.06922 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.9861 MetaTest/__unnamed_task__/AverageReturn -37.9861 MetaTest/__unnamed_task__/Iteration 151 MetaTest/__unnamed_task__/MaxReturn -34.9169 MetaTest/__unnamed_task__/MinReturn -41.0554 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.06922 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 306000 ------------------------------------------------- ------------ 2025-03-29 21:36:18 | [pearl_trainer] epoch #152 | Training... 2025-03-29 21:36:42 | [pearl_trainer] epoch #152 | Evaluating... 2025-03-29 21:36:42 | [pearl_trainer] epoch #152 | Sampling for adapation and meta-testing... 2025-03-29 21:38:03 | [pearl_trainer] epoch #152 | Finished meta-testing... 2025-03-29 21:38:03 | [pearl_trainer] epoch #152 | Saving snapshot... 2025-03-29 21:38:04 | [pearl_trainer] epoch #152 | Saved 2025-03-29 21:38:04 | [pearl_trainer] epoch #152 | Time 26909.13 s 2025-03-29 21:38:04 | [pearl_trainer] epoch #152 | EpochTime 187.65 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.9108 MetaTest/Average/AverageReturn -33.9108 MetaTest/Average/Iteration 152 MetaTest/Average/MaxReturn -33.6701 MetaTest/Average/MinReturn -34.1515 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.240704 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.9108 MetaTest/__unnamed_task__/AverageReturn -33.9108 MetaTest/__unnamed_task__/Iteration 152 MetaTest/__unnamed_task__/MaxReturn -33.6701 MetaTest/__unnamed_task__/MinReturn -34.1515 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.240704 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 308000 ------------------------------------------------- ------------- 2025-03-29 21:39:09 | [pearl_trainer] epoch #153 | Training... 2025-03-29 21:39:26 | [pearl_trainer] epoch #153 | Evaluating... 2025-03-29 21:39:26 | [pearl_trainer] epoch #153 | Sampling for adapation and meta-testing... 2025-03-29 21:40:36 | [pearl_trainer] epoch #153 | Finished meta-testing... 2025-03-29 21:40:36 | [pearl_trainer] epoch #153 | Saving snapshot... 2025-03-29 21:40:37 | [pearl_trainer] epoch #153 | Saved 2025-03-29 21:40:37 | [pearl_trainer] epoch #153 | Time 27062.21 s 2025-03-29 21:40:37 | [pearl_trainer] epoch #153 | EpochTime 153.08 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.5295 MetaTest/Average/AverageReturn -35.5295 MetaTest/Average/Iteration 153 MetaTest/Average/MaxReturn -32.2967 MetaTest/Average/MinReturn -38.7622 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.23274 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.5295 MetaTest/__unnamed_task__/AverageReturn -35.5295 MetaTest/__unnamed_task__/Iteration 153 MetaTest/__unnamed_task__/MaxReturn -32.2967 MetaTest/__unnamed_task__/MinReturn -38.7622 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.23274 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 310000 ------------------------------------------------- ------------ 2025-03-29 21:41:42 | [pearl_trainer] epoch #154 | Training... 2025-03-29 21:42:05 | [pearl_trainer] epoch #154 | Evaluating... 2025-03-29 21:42:05 | [pearl_trainer] epoch #154 | Sampling for adapation and meta-testing... 2025-03-29 21:43:31 | [pearl_trainer] epoch #154 | Finished meta-testing... 2025-03-29 21:43:31 | [pearl_trainer] epoch #154 | Saving snapshot... 2025-03-29 21:43:32 | [pearl_trainer] epoch #154 | Saved 2025-03-29 21:43:32 | [pearl_trainer] epoch #154 | Time 27237.31 s 2025-03-29 21:43:32 | [pearl_trainer] epoch #154 | EpochTime 175.10 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -44.412 MetaTest/Average/AverageReturn -44.412 MetaTest/Average/Iteration 154 MetaTest/Average/MaxReturn -43.4679 MetaTest/Average/MinReturn -45.3561 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.944115 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.412 MetaTest/__unnamed_task__/AverageReturn -44.412 MetaTest/__unnamed_task__/Iteration 154 MetaTest/__unnamed_task__/MaxReturn -43.4679 MetaTest/__unnamed_task__/MinReturn -45.3561 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.944115 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 312000 ------------------------------------------------- ------------- 2025-03-29 21:44:42 | [pearl_trainer] epoch #155 | Training... 2025-03-29 21:45:00 | [pearl_trainer] epoch #155 | Evaluating... 2025-03-29 21:45:00 | [pearl_trainer] epoch #155 | Sampling for adapation and meta-testing... 2025-03-29 21:46:10 | [pearl_trainer] epoch #155 | Finished meta-testing... 2025-03-29 21:46:10 | [pearl_trainer] epoch #155 | Saving snapshot... 2025-03-29 21:46:11 | [pearl_trainer] epoch #155 | Saved 2025-03-29 21:46:11 | [pearl_trainer] epoch #155 | Time 27395.76 s 2025-03-29 21:46:11 | [pearl_trainer] epoch #155 | EpochTime 158.44 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.5772 MetaTest/Average/AverageReturn -36.5772 MetaTest/Average/Iteration 155 MetaTest/Average/MaxReturn -32.0257 MetaTest/Average/MinReturn -41.1287 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.55152 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.5772 MetaTest/__unnamed_task__/AverageReturn -36.5772 MetaTest/__unnamed_task__/Iteration 155 MetaTest/__unnamed_task__/MaxReturn -32.0257 MetaTest/__unnamed_task__/MinReturn -41.1287 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.55152 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 314000 ------------------------------------------------- ------------ 2025-03-29 21:47:17 | [pearl_trainer] epoch #156 | Training... 2025-03-29 21:47:38 | [pearl_trainer] epoch #156 | Evaluating... 2025-03-29 21:47:38 | [pearl_trainer] epoch #156 | Sampling for adapation and meta-testing... 2025-03-29 21:48:48 | [pearl_trainer] epoch #156 | Finished meta-testing... 2025-03-29 21:48:48 | [pearl_trainer] epoch #156 | Saving snapshot... 2025-03-29 21:48:49 | [pearl_trainer] epoch #156 | Saved 2025-03-29 21:48:49 | [pearl_trainer] epoch #156 | Time 27554.02 s 2025-03-29 21:48:49 | [pearl_trainer] epoch #156 | EpochTime 158.27 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.9179 MetaTest/Average/AverageReturn -33.9179 MetaTest/Average/Iteration 156 MetaTest/Average/MaxReturn -30.1032 MetaTest/Average/MinReturn -37.7326 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.81472 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.9179 MetaTest/__unnamed_task__/AverageReturn -33.9179 MetaTest/__unnamed_task__/Iteration 156 MetaTest/__unnamed_task__/MaxReturn -30.1032 MetaTest/__unnamed_task__/MinReturn -37.7326 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.81472 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 316000 ------------------------------------------------- ------------ 2025-03-29 21:49:53 | [pearl_trainer] epoch #157 | Training... 2025-03-29 21:50:10 | [pearl_trainer] epoch #157 | Evaluating... 2025-03-29 21:50:10 | [pearl_trainer] epoch #157 | Sampling for adapation and meta-testing... 2025-03-29 21:51:20 | [pearl_trainer] epoch #157 | Finished meta-testing... 2025-03-29 21:51:20 | [pearl_trainer] epoch #157 | Saving snapshot... 2025-03-29 21:51:21 | [pearl_trainer] epoch #157 | Saved 2025-03-29 21:51:21 | [pearl_trainer] epoch #157 | Time 27705.97 s 2025-03-29 21:51:21 | [pearl_trainer] epoch #157 | EpochTime 151.95 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -31.358 MetaTest/Average/AverageReturn -31.358 MetaTest/Average/Iteration 157 MetaTest/Average/MaxReturn -29.8712 MetaTest/Average/MinReturn -32.8448 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.48678 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -31.358 MetaTest/__unnamed_task__/AverageReturn -31.358 MetaTest/__unnamed_task__/Iteration 157 MetaTest/__unnamed_task__/MaxReturn -29.8712 MetaTest/__unnamed_task__/MinReturn -32.8448 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.48678 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 318000 ------------------------------------------------- ------------ 2025-03-29 21:52:27 | [pearl_trainer] epoch #158 | Training... 2025-03-29 21:52:44 | [pearl_trainer] epoch #158 | Evaluating... 2025-03-29 21:52:44 | [pearl_trainer] epoch #158 | Sampling for adapation and meta-testing... 2025-03-29 21:53:58 | [pearl_trainer] epoch #158 | Finished meta-testing... 2025-03-29 21:53:58 | [pearl_trainer] epoch #158 | Saving snapshot... 2025-03-29 21:53:59 | [pearl_trainer] epoch #158 | Saved 2025-03-29 21:53:59 | [pearl_trainer] epoch #158 | Time 27863.93 s 2025-03-29 21:53:59 | [pearl_trainer] epoch #158 | EpochTime 157.95 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -31.7847 MetaTest/Average/AverageReturn -31.7847 MetaTest/Average/Iteration 158 MetaTest/Average/MaxReturn -31.3949 MetaTest/Average/MinReturn -32.1746 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.389844 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -31.7847 MetaTest/__unnamed_task__/AverageReturn -31.7847 MetaTest/__unnamed_task__/Iteration 158 MetaTest/__unnamed_task__/MaxReturn -31.3949 MetaTest/__unnamed_task__/MinReturn -32.1746 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.389844 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 320000 ------------------------------------------------- ------------- 2025-03-29 21:55:04 | [pearl_trainer] epoch #159 | Training... 2025-03-29 21:55:18 | [pearl_trainer] epoch #159 | Evaluating... 2025-03-29 21:55:18 | [pearl_trainer] epoch #159 | Sampling for adapation and meta-testing... 2025-03-29 21:56:29 | [pearl_trainer] epoch #159 | Finished meta-testing... 2025-03-29 21:56:29 | [pearl_trainer] epoch #159 | Saving snapshot... 2025-03-29 21:56:30 | [pearl_trainer] epoch #159 | Saved 2025-03-29 21:56:30 | [pearl_trainer] epoch #159 | Time 28014.59 s 2025-03-29 21:56:30 | [pearl_trainer] epoch #159 | EpochTime 150.66 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.3971 MetaTest/Average/AverageReturn -35.3971 MetaTest/Average/Iteration 159 MetaTest/Average/MaxReturn -34.897 MetaTest/Average/MinReturn -35.8971 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.500077 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.3971 MetaTest/__unnamed_task__/AverageReturn -35.3971 MetaTest/__unnamed_task__/Iteration 159 MetaTest/__unnamed_task__/MaxReturn -34.897 MetaTest/__unnamed_task__/MinReturn -35.8971 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.500077 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 322000 ------------------------------------------------- ------------- 2025-03-29 21:57:36 | [pearl_trainer] epoch #160 | Training... 2025-03-29 21:57:54 | [pearl_trainer] epoch #160 | Evaluating... 2025-03-29 21:57:54 | [pearl_trainer] epoch #160 | Sampling for adapation and meta-testing... 2025-03-29 21:59:10 | [pearl_trainer] epoch #160 | Finished meta-testing... 2025-03-29 21:59:10 | [pearl_trainer] epoch #160 | Saving snapshot... 2025-03-29 21:59:11 | [pearl_trainer] epoch #160 | Saved 2025-03-29 21:59:11 | [pearl_trainer] epoch #160 | Time 28175.82 s 2025-03-29 21:59:11 | [pearl_trainer] epoch #160 | EpochTime 161.23 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.7401 MetaTest/Average/AverageReturn -35.7401 MetaTest/Average/Iteration 160 MetaTest/Average/MaxReturn -32.5939 MetaTest/Average/MinReturn -38.8863 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.14621 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.7401 MetaTest/__unnamed_task__/AverageReturn -35.7401 MetaTest/__unnamed_task__/Iteration 160 MetaTest/__unnamed_task__/MaxReturn -32.5939 MetaTest/__unnamed_task__/MinReturn -38.8863 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.14621 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 324000 ------------------------------------------------- ------------ 2025-03-29 22:00:23 | [pearl_trainer] epoch #161 | Training... 2025-03-29 22:00:37 | [pearl_trainer] epoch #161 | Evaluating... 2025-03-29 22:00:37 | [pearl_trainer] epoch #161 | Sampling for adapation and meta-testing... 2025-03-29 22:01:47 | [pearl_trainer] epoch #161 | Finished meta-testing... 2025-03-29 22:01:47 | [pearl_trainer] epoch #161 | Saving snapshot... 2025-03-29 22:01:48 | [pearl_trainer] epoch #161 | Saved 2025-03-29 22:01:48 | [pearl_trainer] epoch #161 | Time 28332.91 s 2025-03-29 22:01:48 | [pearl_trainer] epoch #161 | EpochTime 157.09 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.8176 MetaTest/Average/AverageReturn -36.8176 MetaTest/Average/Iteration 161 MetaTest/Average/MaxReturn -35.7404 MetaTest/Average/MinReturn -37.8947 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.07717 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.8176 MetaTest/__unnamed_task__/AverageReturn -36.8176 MetaTest/__unnamed_task__/Iteration 161 MetaTest/__unnamed_task__/MaxReturn -35.7404 MetaTest/__unnamed_task__/MinReturn -37.8947 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.07717 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 326000 ------------------------------------------------- ------------ 2025-03-29 22:02:52 | [pearl_trainer] epoch #162 | Training... 2025-03-29 22:03:08 | [pearl_trainer] epoch #162 | Evaluating... 2025-03-29 22:03:08 | [pearl_trainer] epoch #162 | Sampling for adapation and meta-testing... 2025-03-29 22:04:22 | [pearl_trainer] epoch #162 | Finished meta-testing... 2025-03-29 22:04:22 | [pearl_trainer] epoch #162 | Saving snapshot... 2025-03-29 22:04:23 | [pearl_trainer] epoch #162 | Saved 2025-03-29 22:04:23 | [pearl_trainer] epoch #162 | Time 28487.53 s 2025-03-29 22:04:23 | [pearl_trainer] epoch #162 | EpochTime 154.63 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.64 MetaTest/Average/AverageReturn -34.64 MetaTest/Average/Iteration 162 MetaTest/Average/MaxReturn -33.2045 MetaTest/Average/MinReturn -36.0755 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.43549 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.64 MetaTest/__unnamed_task__/AverageReturn -34.64 MetaTest/__unnamed_task__/Iteration 162 MetaTest/__unnamed_task__/MaxReturn -33.2045 MetaTest/__unnamed_task__/MinReturn -36.0755 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.43549 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 328000 ------------------------------------------------- ------------ 2025-03-29 22:05:32 | [pearl_trainer] epoch #163 | Training... 2025-03-29 22:05:50 | [pearl_trainer] epoch #163 | Evaluating... 2025-03-29 22:05:50 | [pearl_trainer] epoch #163 | Sampling for adapation and meta-testing... 2025-03-29 22:07:01 | [pearl_trainer] epoch #163 | Finished meta-testing... 2025-03-29 22:07:01 | [pearl_trainer] epoch #163 | Saving snapshot... 2025-03-29 22:07:02 | [pearl_trainer] epoch #163 | Saved 2025-03-29 22:07:02 | [pearl_trainer] epoch #163 | Time 28646.84 s 2025-03-29 22:07:02 | [pearl_trainer] epoch #163 | EpochTime 159.30 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.0854 MetaTest/Average/AverageReturn -37.0854 MetaTest/Average/Iteration 163 MetaTest/Average/MaxReturn -34.6251 MetaTest/Average/MinReturn -39.5457 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.46032 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.0854 MetaTest/__unnamed_task__/AverageReturn -37.0854 MetaTest/__unnamed_task__/Iteration 163 MetaTest/__unnamed_task__/MaxReturn -34.6251 MetaTest/__unnamed_task__/MinReturn -39.5457 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.46032 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 330000 ------------------------------------------------- ------------ 2025-03-29 22:08:11 | [pearl_trainer] epoch #164 | Training... 2025-03-29 22:08:28 | [pearl_trainer] epoch #164 | Evaluating... 2025-03-29 22:08:28 | [pearl_trainer] epoch #164 | Sampling for adapation and meta-testing... 2025-03-29 22:09:44 | [pearl_trainer] epoch #164 | Finished meta-testing... 2025-03-29 22:09:44 | [pearl_trainer] epoch #164 | Saving snapshot... 2025-03-29 22:09:44 | [pearl_trainer] epoch #164 | Saved 2025-03-29 22:09:44 | [pearl_trainer] epoch #164 | Time 28809.25 s 2025-03-29 22:09:44 | [pearl_trainer] epoch #164 | EpochTime 162.41 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.608 MetaTest/Average/AverageReturn -35.608 MetaTest/Average/Iteration 164 MetaTest/Average/MaxReturn -34.5215 MetaTest/Average/MinReturn -36.6945 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.08651 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.608 MetaTest/__unnamed_task__/AverageReturn -35.608 MetaTest/__unnamed_task__/Iteration 164 MetaTest/__unnamed_task__/MaxReturn -34.5215 MetaTest/__unnamed_task__/MinReturn -36.6945 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.08651 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 332000 ------------------------------------------------- ------------ 2025-03-29 22:10:49 | [pearl_trainer] epoch #165 | Training... 2025-03-29 22:11:06 | [pearl_trainer] epoch #165 | Evaluating... 2025-03-29 22:11:06 | [pearl_trainer] epoch #165 | Sampling for adapation and meta-testing... 2025-03-29 22:12:23 | [pearl_trainer] epoch #165 | Finished meta-testing... 2025-03-29 22:12:23 | [pearl_trainer] epoch #165 | Saving snapshot... 2025-03-29 22:12:24 | [pearl_trainer] epoch #165 | Saved 2025-03-29 22:12:24 | [pearl_trainer] epoch #165 | Time 28969.41 s 2025-03-29 22:12:24 | [pearl_trainer] epoch #165 | EpochTime 160.15 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.8856 MetaTest/Average/AverageReturn -34.8856 MetaTest/Average/Iteration 165 MetaTest/Average/MaxReturn -34.5001 MetaTest/Average/MinReturn -35.271 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.385472 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.8856 MetaTest/__unnamed_task__/AverageReturn -34.8856 MetaTest/__unnamed_task__/Iteration 165 MetaTest/__unnamed_task__/MaxReturn -34.5001 MetaTest/__unnamed_task__/MinReturn -35.271 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.385472 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 334000 ------------------------------------------------- ------------- 2025-03-29 22:13:30 | [pearl_trainer] epoch #166 | Training... 2025-03-29 22:13:44 | [pearl_trainer] epoch #166 | Evaluating... 2025-03-29 22:13:44 | [pearl_trainer] epoch #166 | Sampling for adapation and meta-testing... 2025-03-29 22:14:55 | [pearl_trainer] epoch #166 | Finished meta-testing... 2025-03-29 22:14:55 | [pearl_trainer] epoch #166 | Saving snapshot... 2025-03-29 22:14:56 | [pearl_trainer] epoch #166 | Saved 2025-03-29 22:14:56 | [pearl_trainer] epoch #166 | Time 29120.70 s 2025-03-29 22:14:56 | [pearl_trainer] epoch #166 | EpochTime 151.29 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -37.0053 MetaTest/Average/AverageReturn -37.0053 MetaTest/Average/Iteration 166 MetaTest/Average/MaxReturn -30.2981 MetaTest/Average/MinReturn -43.7125 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 6.7072 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.0053 MetaTest/__unnamed_task__/AverageReturn -37.0053 MetaTest/__unnamed_task__/Iteration 166 MetaTest/__unnamed_task__/MaxReturn -30.2981 MetaTest/__unnamed_task__/MinReturn -43.7125 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 6.7072 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 336000 ------------------------------------------------- ----------- 2025-03-29 22:15:59 | [pearl_trainer] epoch #167 | Training... 2025-03-29 22:16:15 | [pearl_trainer] epoch #167 | Evaluating... 2025-03-29 22:16:15 | [pearl_trainer] epoch #167 | Sampling for adapation and meta-testing... 2025-03-29 22:17:32 | [pearl_trainer] epoch #167 | Finished meta-testing... 2025-03-29 22:17:32 | [pearl_trainer] epoch #167 | Saving snapshot... 2025-03-29 22:17:33 | [pearl_trainer] epoch #167 | Saved 2025-03-29 22:17:33 | [pearl_trainer] epoch #167 | Time 29278.04 s 2025-03-29 22:17:33 | [pearl_trainer] epoch #167 | EpochTime 157.34 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.1377 MetaTest/Average/AverageReturn -33.1377 MetaTest/Average/Iteration 167 MetaTest/Average/MaxReturn -32.819 MetaTest/Average/MinReturn -33.4563 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.318647 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.1377 MetaTest/__unnamed_task__/AverageReturn -33.1377 MetaTest/__unnamed_task__/Iteration 167 MetaTest/__unnamed_task__/MaxReturn -32.819 MetaTest/__unnamed_task__/MinReturn -33.4563 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.318647 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 338000 ------------------------------------------------- ------------- 2025-03-29 22:18:39 | [pearl_trainer] epoch #168 | Training... 2025-03-29 22:18:56 | [pearl_trainer] epoch #168 | Evaluating... 2025-03-29 22:18:56 | [pearl_trainer] epoch #168 | Sampling for adapation and meta-testing... 2025-03-29 22:20:07 | [pearl_trainer] epoch #168 | Finished meta-testing... 2025-03-29 22:20:07 | [pearl_trainer] epoch #168 | Saving snapshot... 2025-03-29 22:20:08 | [pearl_trainer] epoch #168 | Saved 2025-03-29 22:20:08 | [pearl_trainer] epoch #168 | Time 29433.03 s 2025-03-29 22:20:08 | [pearl_trainer] epoch #168 | EpochTime 154.99 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.9141 MetaTest/Average/AverageReturn -37.9141 MetaTest/Average/Iteration 168 MetaTest/Average/MaxReturn -35.2706 MetaTest/Average/MinReturn -40.5577 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.64356 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.9141 MetaTest/__unnamed_task__/AverageReturn -37.9141 MetaTest/__unnamed_task__/Iteration 168 MetaTest/__unnamed_task__/MaxReturn -35.2706 MetaTest/__unnamed_task__/MinReturn -40.5577 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.64356 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 340000 ------------------------------------------------- ------------ 2025-03-29 22:21:18 | [pearl_trainer] epoch #169 | Training... 2025-03-29 22:21:38 | [pearl_trainer] epoch #169 | Evaluating... 2025-03-29 22:21:38 | [pearl_trainer] epoch #169 | Sampling for adapation and meta-testing... 2025-03-29 22:23:02 | [pearl_trainer] epoch #169 | Finished meta-testing... 2025-03-29 22:23:02 | [pearl_trainer] epoch #169 | Saving snapshot... 2025-03-29 22:23:03 | [pearl_trainer] epoch #169 | Saved 2025-03-29 22:23:03 | [pearl_trainer] epoch #169 | Time 29607.58 s 2025-03-29 22:23:03 | [pearl_trainer] epoch #169 | EpochTime 174.55 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -36.1654 MetaTest/Average/AverageReturn -36.1654 MetaTest/Average/Iteration 169 MetaTest/Average/MaxReturn -36.0213 MetaTest/Average/MinReturn -36.3096 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.144115 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.1654 MetaTest/__unnamed_task__/AverageReturn -36.1654 MetaTest/__unnamed_task__/Iteration 169 MetaTest/__unnamed_task__/MaxReturn -36.0213 MetaTest/__unnamed_task__/MinReturn -36.3096 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.144115 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 342000 ------------------------------------------------- ------------- 2025-03-29 22:24:17 | [pearl_trainer] epoch #170 | Training... 2025-03-29 22:24:34 | [pearl_trainer] epoch #170 | Evaluating... 2025-03-29 22:24:34 | [pearl_trainer] epoch #170 | Sampling for adapation and meta-testing... 2025-03-29 22:25:45 | [pearl_trainer] epoch #170 | Finished meta-testing... 2025-03-29 22:25:45 | [pearl_trainer] epoch #170 | Saving snapshot... 2025-03-29 22:25:46 | [pearl_trainer] epoch #170 | Saved 2025-03-29 22:25:46 | [pearl_trainer] epoch #170 | Time 29771.09 s 2025-03-29 22:25:46 | [pearl_trainer] epoch #170 | EpochTime 163.51 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.1758 MetaTest/Average/AverageReturn -33.1758 MetaTest/Average/Iteration 170 MetaTest/Average/MaxReturn -31.4009 MetaTest/Average/MinReturn -34.9507 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.77493 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.1758 MetaTest/__unnamed_task__/AverageReturn -33.1758 MetaTest/__unnamed_task__/Iteration 170 MetaTest/__unnamed_task__/MaxReturn -31.4009 MetaTest/__unnamed_task__/MinReturn -34.9507 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.77493 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 344000 ------------------------------------------------- ------------ 2025-03-29 22:26:51 | [pearl_trainer] epoch #171 | Training... 2025-03-29 22:27:08 | [pearl_trainer] epoch #171 | Evaluating... 2025-03-29 22:27:08 | [pearl_trainer] epoch #171 | Sampling for adapation and meta-testing... 2025-03-29 22:28:18 | [pearl_trainer] epoch #171 | Finished meta-testing... 2025-03-29 22:28:18 | [pearl_trainer] epoch #171 | Saving snapshot... 2025-03-29 22:28:19 | [pearl_trainer] epoch #171 | Saved 2025-03-29 22:28:19 | [pearl_trainer] epoch #171 | Time 29923.95 s 2025-03-29 22:28:19 | [pearl_trainer] epoch #171 | EpochTime 152.85 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.4145 MetaTest/Average/AverageReturn -35.4145 MetaTest/Average/Iteration 171 MetaTest/Average/MaxReturn -34.9544 MetaTest/Average/MinReturn -35.8747 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.460144 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.4145 MetaTest/__unnamed_task__/AverageReturn -35.4145 MetaTest/__unnamed_task__/Iteration 171 MetaTest/__unnamed_task__/MaxReturn -34.9544 MetaTest/__unnamed_task__/MinReturn -35.8747 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.460144 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 346000 ------------------------------------------------- ------------- 2025-03-29 22:29:27 | [pearl_trainer] epoch #172 | Training... 2025-03-29 22:29:46 | [pearl_trainer] epoch #172 | Evaluating... 2025-03-29 22:29:46 | [pearl_trainer] epoch #172 | Sampling for adapation and meta-testing... 2025-03-29 22:30:56 | [pearl_trainer] epoch #172 | Finished meta-testing... 2025-03-29 22:30:56 | [pearl_trainer] epoch #172 | Saving snapshot... 2025-03-29 22:30:57 | [pearl_trainer] epoch #172 | Saved 2025-03-29 22:30:57 | [pearl_trainer] epoch #172 | Time 30081.52 s 2025-03-29 22:30:57 | [pearl_trainer] epoch #172 | EpochTime 157.57 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -40.3934 MetaTest/Average/AverageReturn -40.3934 MetaTest/Average/Iteration 172 MetaTest/Average/MaxReturn -39.7365 MetaTest/Average/MinReturn -41.0503 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.656877 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -40.3934 MetaTest/__unnamed_task__/AverageReturn -40.3934 MetaTest/__unnamed_task__/Iteration 172 MetaTest/__unnamed_task__/MaxReturn -39.7365 MetaTest/__unnamed_task__/MinReturn -41.0503 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.656877 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 348000 ------------------------------------------------- ------------- 2025-03-29 22:31:59 | [pearl_trainer] epoch #173 | Training... 2025-03-29 22:32:22 | [pearl_trainer] epoch #173 | Evaluating... 2025-03-29 22:32:22 | [pearl_trainer] epoch #173 | Sampling for adapation and meta-testing... 2025-03-29 22:33:39 | [pearl_trainer] epoch #173 | Finished meta-testing... 2025-03-29 22:33:39 | [pearl_trainer] epoch #173 | Saving snapshot... 2025-03-29 22:33:40 | [pearl_trainer] epoch #173 | Saved 2025-03-29 22:33:40 | [pearl_trainer] epoch #173 | Time 30244.59 s 2025-03-29 22:33:40 | [pearl_trainer] epoch #173 | EpochTime 163.08 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.3275 MetaTest/Average/AverageReturn -36.3275 MetaTest/Average/Iteration 173 MetaTest/Average/MaxReturn -32.1756 MetaTest/Average/MinReturn -40.4793 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.15185 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.3275 MetaTest/__unnamed_task__/AverageReturn -36.3275 MetaTest/__unnamed_task__/Iteration 173 MetaTest/__unnamed_task__/MaxReturn -32.1756 MetaTest/__unnamed_task__/MinReturn -40.4793 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.15185 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 350000 ------------------------------------------------- ------------ 2025-03-29 22:34:57 | [pearl_trainer] epoch #174 | Training... 2025-03-29 22:35:16 | [pearl_trainer] epoch #174 | Evaluating... 2025-03-29 22:35:16 | [pearl_trainer] epoch #174 | Sampling for adapation and meta-testing... 2025-03-29 22:36:41 | [pearl_trainer] epoch #174 | Finished meta-testing... 2025-03-29 22:36:41 | [pearl_trainer] epoch #174 | Saving snapshot... 2025-03-29 22:36:42 | [pearl_trainer] epoch #174 | Saved 2025-03-29 22:36:42 | [pearl_trainer] epoch #174 | Time 30426.83 s 2025-03-29 22:36:42 | [pearl_trainer] epoch #174 | EpochTime 182.24 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.7476 MetaTest/Average/AverageReturn -37.7476 MetaTest/Average/Iteration 174 MetaTest/Average/MaxReturn -35.3213 MetaTest/Average/MinReturn -40.1739 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.42629 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.7476 MetaTest/__unnamed_task__/AverageReturn -37.7476 MetaTest/__unnamed_task__/Iteration 174 MetaTest/__unnamed_task__/MaxReturn -35.3213 MetaTest/__unnamed_task__/MinReturn -40.1739 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.42629 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 352000 ------------------------------------------------- ------------ 2025-03-29 22:37:54 | [pearl_trainer] epoch #175 | Training... 2025-03-29 22:38:11 | [pearl_trainer] epoch #175 | Evaluating... 2025-03-29 22:38:11 | [pearl_trainer] epoch #175 | Sampling for adapation and meta-testing... 2025-03-29 22:39:22 | [pearl_trainer] epoch #175 | Finished meta-testing... 2025-03-29 22:39:22 | [pearl_trainer] epoch #175 | Saving snapshot... 2025-03-29 22:39:22 | [pearl_trainer] epoch #175 | Saved 2025-03-29 22:39:22 | [pearl_trainer] epoch #175 | Time 30587.33 s 2025-03-29 22:39:22 | [pearl_trainer] epoch #175 | EpochTime 160.50 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -32.3519 MetaTest/Average/AverageReturn -32.3519 MetaTest/Average/Iteration 175 MetaTest/Average/MaxReturn -28.3042 MetaTest/Average/MinReturn -36.3996 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.04768 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -32.3519 MetaTest/__unnamed_task__/AverageReturn -32.3519 MetaTest/__unnamed_task__/Iteration 175 MetaTest/__unnamed_task__/MaxReturn -28.3042 MetaTest/__unnamed_task__/MinReturn -36.3996 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.04768 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 354000 ------------------------------------------------- ------------ 2025-03-29 22:40:26 | [pearl_trainer] epoch #176 | Training... 2025-03-29 22:40:44 | [pearl_trainer] epoch #176 | Evaluating... 2025-03-29 22:40:44 | [pearl_trainer] epoch #176 | Sampling for adapation and meta-testing... 2025-03-29 22:41:58 | [pearl_trainer] epoch #176 | Finished meta-testing... 2025-03-29 22:41:58 | [pearl_trainer] epoch #176 | Saving snapshot... 2025-03-29 22:41:58 | [pearl_trainer] epoch #176 | Saved 2025-03-29 22:41:58 | [pearl_trainer] epoch #176 | Time 30743.30 s 2025-03-29 22:41:58 | [pearl_trainer] epoch #176 | EpochTime 155.96 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.6819 MetaTest/Average/AverageReturn -33.6819 MetaTest/Average/Iteration 176 MetaTest/Average/MaxReturn -32.9564 MetaTest/Average/MinReturn -34.4073 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.725449 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.6819 MetaTest/__unnamed_task__/AverageReturn -33.6819 MetaTest/__unnamed_task__/Iteration 176 MetaTest/__unnamed_task__/MaxReturn -32.9564 MetaTest/__unnamed_task__/MinReturn -34.4073 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.725449 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 356000 ------------------------------------------------- ------------- 2025-03-29 22:43:02 | [pearl_trainer] epoch #177 | Training... 2025-03-29 22:43:18 | [pearl_trainer] epoch #177 | Evaluating... 2025-03-29 22:43:18 | [pearl_trainer] epoch #177 | Sampling for adapation and meta-testing... 2025-03-29 22:44:27 | [pearl_trainer] epoch #177 | Finished meta-testing... 2025-03-29 22:44:27 | [pearl_trainer] epoch #177 | Saving snapshot... 2025-03-29 22:44:28 | [pearl_trainer] epoch #177 | Saved 2025-03-29 22:44:28 | [pearl_trainer] epoch #177 | Time 30893.34 s 2025-03-29 22:44:28 | [pearl_trainer] epoch #177 | EpochTime 150.04 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.5692 MetaTest/Average/AverageReturn -33.5692 MetaTest/Average/Iteration 177 MetaTest/Average/MaxReturn -33.0547 MetaTest/Average/MinReturn -34.0837 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.514508 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.5692 MetaTest/__unnamed_task__/AverageReturn -33.5692 MetaTest/__unnamed_task__/Iteration 177 MetaTest/__unnamed_task__/MaxReturn -33.0547 MetaTest/__unnamed_task__/MinReturn -34.0837 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.514508 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 358000 ------------------------------------------------- ------------- 2025-03-29 22:45:33 | [pearl_trainer] epoch #178 | Training... 2025-03-29 22:45:49 | [pearl_trainer] epoch #178 | Evaluating... 2025-03-29 22:45:49 | [pearl_trainer] epoch #178 | Sampling for adapation and meta-testing... 2025-03-29 22:46:58 | [pearl_trainer] epoch #178 | Finished meta-testing... 2025-03-29 22:46:58 | [pearl_trainer] epoch #178 | Saving snapshot... 2025-03-29 22:46:59 | [pearl_trainer] epoch #178 | Saved 2025-03-29 22:46:59 | [pearl_trainer] epoch #178 | Time 31044.18 s 2025-03-29 22:46:59 | [pearl_trainer] epoch #178 | EpochTime 150.85 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.8277 MetaTest/Average/AverageReturn -35.8277 MetaTest/Average/Iteration 178 MetaTest/Average/MaxReturn -30.9355 MetaTest/Average/MinReturn -40.7199 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.89218 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.8277 MetaTest/__unnamed_task__/AverageReturn -35.8277 MetaTest/__unnamed_task__/Iteration 178 MetaTest/__unnamed_task__/MaxReturn -30.9355 MetaTest/__unnamed_task__/MinReturn -40.7199 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.89218 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 360000 ------------------------------------------------- ------------ 2025-03-29 22:48:03 | [pearl_trainer] epoch #179 | Training... 2025-03-29 22:48:19 | [pearl_trainer] epoch #179 | Evaluating... 2025-03-29 22:48:19 | [pearl_trainer] epoch #179 | Sampling for adapation and meta-testing... 2025-03-29 22:49:37 | [pearl_trainer] epoch #179 | Finished meta-testing... 2025-03-29 22:49:37 | [pearl_trainer] epoch #179 | Saving snapshot... 2025-03-29 22:49:37 | [pearl_trainer] epoch #179 | Saved 2025-03-29 22:49:37 | [pearl_trainer] epoch #179 | Time 31202.40 s 2025-03-29 22:49:37 | [pearl_trainer] epoch #179 | EpochTime 158.21 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.8495 MetaTest/Average/AverageReturn -37.8495 MetaTest/Average/Iteration 179 MetaTest/Average/MaxReturn -33.7172 MetaTest/Average/MinReturn -41.9817 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.13228 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.8495 MetaTest/__unnamed_task__/AverageReturn -37.8495 MetaTest/__unnamed_task__/Iteration 179 MetaTest/__unnamed_task__/MaxReturn -33.7172 MetaTest/__unnamed_task__/MinReturn -41.9817 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.13228 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 362000 ------------------------------------------------- ------------ 2025-03-29 22:50:42 | [pearl_trainer] epoch #180 | Training... 2025-03-29 22:50:57 | [pearl_trainer] epoch #180 | Evaluating... 2025-03-29 22:50:57 | [pearl_trainer] epoch #180 | Sampling for adapation and meta-testing... 2025-03-29 22:52:12 | [pearl_trainer] epoch #180 | Finished meta-testing... 2025-03-29 22:52:12 | [pearl_trainer] epoch #180 | Saving snapshot... 2025-03-29 22:52:13 | [pearl_trainer] epoch #180 | Saved 2025-03-29 22:52:13 | [pearl_trainer] epoch #180 | Time 31357.78 s 2025-03-29 22:52:13 | [pearl_trainer] epoch #180 | EpochTime 155.38 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.0948 MetaTest/Average/AverageReturn -38.0948 MetaTest/Average/Iteration 180 MetaTest/Average/MaxReturn -35.2832 MetaTest/Average/MinReturn -40.9063 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.81153 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.0948 MetaTest/__unnamed_task__/AverageReturn -38.0948 MetaTest/__unnamed_task__/Iteration 180 MetaTest/__unnamed_task__/MaxReturn -35.2832 MetaTest/__unnamed_task__/MinReturn -40.9063 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.81153 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 364000 ------------------------------------------------- ------------ 2025-03-29 22:53:18 | [pearl_trainer] epoch #181 | Training... 2025-03-29 22:53:33 | [pearl_trainer] epoch #181 | Evaluating... 2025-03-29 22:53:33 | [pearl_trainer] epoch #181 | Sampling for adapation and meta-testing... 2025-03-29 22:54:45 | [pearl_trainer] epoch #181 | Finished meta-testing... 2025-03-29 22:54:45 | [pearl_trainer] epoch #181 | Saving snapshot... 2025-03-29 22:54:46 | [pearl_trainer] epoch #181 | Saved 2025-03-29 22:54:46 | [pearl_trainer] epoch #181 | Time 31510.84 s 2025-03-29 22:54:46 | [pearl_trainer] epoch #181 | EpochTime 153.06 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.7822 MetaTest/Average/AverageReturn -35.7822 MetaTest/Average/Iteration 181 MetaTest/Average/MaxReturn -35.4607 MetaTest/Average/MinReturn -36.1038 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.321551 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.7822 MetaTest/__unnamed_task__/AverageReturn -35.7822 MetaTest/__unnamed_task__/Iteration 181 MetaTest/__unnamed_task__/MaxReturn -35.4607 MetaTest/__unnamed_task__/MinReturn -36.1038 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.321551 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 366000 ------------------------------------------------- ------------- 2025-03-29 22:55:51 | [pearl_trainer] epoch #182 | Training... 2025-03-29 22:56:06 | [pearl_trainer] epoch #182 | Evaluating... 2025-03-29 22:56:06 | [pearl_trainer] epoch #182 | Sampling for adapation and meta-testing... 2025-03-29 22:57:17 | [pearl_trainer] epoch #182 | Finished meta-testing... 2025-03-29 22:57:17 | [pearl_trainer] epoch #182 | Saving snapshot... 2025-03-29 22:57:18 | [pearl_trainer] epoch #182 | Saved 2025-03-29 22:57:18 | [pearl_trainer] epoch #182 | Time 31662.79 s 2025-03-29 22:57:18 | [pearl_trainer] epoch #182 | EpochTime 151.95 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.0778 MetaTest/Average/AverageReturn -34.0778 MetaTest/Average/Iteration 182 MetaTest/Average/MaxReturn -33.3998 MetaTest/Average/MinReturn -34.7558 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.678005 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.0778 MetaTest/__unnamed_task__/AverageReturn -34.0778 MetaTest/__unnamed_task__/Iteration 182 MetaTest/__unnamed_task__/MaxReturn -33.3998 MetaTest/__unnamed_task__/MinReturn -34.7558 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.678005 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 368000 ------------------------------------------------- ------------- 2025-03-29 22:58:23 | [pearl_trainer] epoch #183 | Training... 2025-03-29 22:58:40 | [pearl_trainer] epoch #183 | Evaluating... 2025-03-29 22:58:40 | [pearl_trainer] epoch #183 | Sampling for adapation and meta-testing... 2025-03-29 22:59:52 | [pearl_trainer] epoch #183 | Finished meta-testing... 2025-03-29 22:59:52 | [pearl_trainer] epoch #183 | Saving snapshot... 2025-03-29 22:59:53 | [pearl_trainer] epoch #183 | Saved 2025-03-29 22:59:53 | [pearl_trainer] epoch #183 | Time 31817.60 s 2025-03-29 22:59:53 | [pearl_trainer] epoch #183 | EpochTime 154.81 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -31.883 MetaTest/Average/AverageReturn -31.883 MetaTest/Average/Iteration 183 MetaTest/Average/MaxReturn -31.3817 MetaTest/Average/MinReturn -32.3843 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.501295 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -31.883 MetaTest/__unnamed_task__/AverageReturn -31.883 MetaTest/__unnamed_task__/Iteration 183 MetaTest/__unnamed_task__/MaxReturn -31.3817 MetaTest/__unnamed_task__/MinReturn -32.3843 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.501295 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 370000 ------------------------------------------------- ------------- 2025-03-29 23:00:59 | [pearl_trainer] epoch #184 | Training... 2025-03-29 23:01:14 | [pearl_trainer] epoch #184 | Evaluating... 2025-03-29 23:01:14 | [pearl_trainer] epoch #184 | Sampling for adapation and meta-testing... 2025-03-29 23:02:28 | [pearl_trainer] epoch #184 | Finished meta-testing... 2025-03-29 23:02:28 | [pearl_trainer] epoch #184 | Saving snapshot... 2025-03-29 23:02:28 | [pearl_trainer] epoch #184 | Saved 2025-03-29 23:02:28 | [pearl_trainer] epoch #184 | Time 31973.39 s 2025-03-29 23:02:28 | [pearl_trainer] epoch #184 | EpochTime 155.79 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.6898 MetaTest/Average/AverageReturn -34.6898 MetaTest/Average/Iteration 184 MetaTest/Average/MaxReturn -33.8155 MetaTest/Average/MinReturn -35.5641 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.87426 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.6898 MetaTest/__unnamed_task__/AverageReturn -34.6898 MetaTest/__unnamed_task__/Iteration 184 MetaTest/__unnamed_task__/MaxReturn -33.8155 MetaTest/__unnamed_task__/MinReturn -35.5641 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.87426 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 372000 ------------------------------------------------- ------------ 2025-03-29 23:03:35 | [pearl_trainer] epoch #185 | Training... 2025-03-29 23:03:49 | [pearl_trainer] epoch #185 | Evaluating... 2025-03-29 23:03:49 | [pearl_trainer] epoch #185 | Sampling for adapation and meta-testing... 2025-03-29 23:05:02 | [pearl_trainer] epoch #185 | Finished meta-testing... 2025-03-29 23:05:02 | [pearl_trainer] epoch #185 | Saving snapshot... 2025-03-29 23:05:02 | [pearl_trainer] epoch #185 | Saved 2025-03-29 23:05:02 | [pearl_trainer] epoch #185 | Time 32127.35 s 2025-03-29 23:05:02 | [pearl_trainer] epoch #185 | EpochTime 153.96 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -39.0058 MetaTest/Average/AverageReturn -39.0058 MetaTest/Average/Iteration 185 MetaTest/Average/MaxReturn -37.3824 MetaTest/Average/MinReturn -40.6293 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.62345 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.0058 MetaTest/__unnamed_task__/AverageReturn -39.0058 MetaTest/__unnamed_task__/Iteration 185 MetaTest/__unnamed_task__/MaxReturn -37.3824 MetaTest/__unnamed_task__/MinReturn -40.6293 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.62345 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 374000 ------------------------------------------------- ------------ 2025-03-29 23:06:07 | [pearl_trainer] epoch #186 | Training... 2025-03-29 23:06:21 | [pearl_trainer] epoch #186 | Evaluating... 2025-03-29 23:06:21 | [pearl_trainer] epoch #186 | Sampling for adapation and meta-testing... 2025-03-29 23:07:34 | [pearl_trainer] epoch #186 | Finished meta-testing... 2025-03-29 23:07:34 | [pearl_trainer] epoch #186 | Saving snapshot... 2025-03-29 23:07:35 | [pearl_trainer] epoch #186 | Saved 2025-03-29 23:07:35 | [pearl_trainer] epoch #186 | Time 32279.69 s 2025-03-29 23:07:35 | [pearl_trainer] epoch #186 | EpochTime 152.34 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.5532 MetaTest/Average/AverageReturn -33.5532 MetaTest/Average/Iteration 186 MetaTest/Average/MaxReturn -30.8631 MetaTest/Average/MinReturn -36.2433 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.69014 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.5532 MetaTest/__unnamed_task__/AverageReturn -33.5532 MetaTest/__unnamed_task__/Iteration 186 MetaTest/__unnamed_task__/MaxReturn -30.8631 MetaTest/__unnamed_task__/MinReturn -36.2433 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.69014 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 376000 ------------------------------------------------- ------------ 2025-03-29 23:08:41 | [pearl_trainer] epoch #187 | Training... 2025-03-29 23:08:57 | [pearl_trainer] epoch #187 | Evaluating... 2025-03-29 23:08:57 | [pearl_trainer] epoch #187 | Sampling for adapation and meta-testing... 2025-03-29 23:10:11 | [pearl_trainer] epoch #187 | Finished meta-testing... 2025-03-29 23:10:11 | [pearl_trainer] epoch #187 | Saving snapshot... 2025-03-29 23:10:11 | [pearl_trainer] epoch #187 | Saved 2025-03-29 23:10:11 | [pearl_trainer] epoch #187 | Time 32436.42 s 2025-03-29 23:10:11 | [pearl_trainer] epoch #187 | EpochTime 156.72 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.9906 MetaTest/Average/AverageReturn -35.9906 MetaTest/Average/Iteration 187 MetaTest/Average/MaxReturn -34.8921 MetaTest/Average/MinReturn -37.0892 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.09858 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.9906 MetaTest/__unnamed_task__/AverageReturn -35.9906 MetaTest/__unnamed_task__/Iteration 187 MetaTest/__unnamed_task__/MaxReturn -34.8921 MetaTest/__unnamed_task__/MinReturn -37.0892 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.09858 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 378000 ------------------------------------------------- ------------ 2025-03-29 23:11:18 | [pearl_trainer] epoch #188 | Training... 2025-03-29 23:11:35 | [pearl_trainer] epoch #188 | Evaluating... 2025-03-29 23:11:35 | [pearl_trainer] epoch #188 | Sampling for adapation and meta-testing... 2025-03-29 23:12:45 | [pearl_trainer] epoch #188 | Finished meta-testing... 2025-03-29 23:12:45 | [pearl_trainer] epoch #188 | Saving snapshot... 2025-03-29 23:12:46 | [pearl_trainer] epoch #188 | Saved 2025-03-29 23:12:46 | [pearl_trainer] epoch #188 | Time 32591.04 s 2025-03-29 23:12:46 | [pearl_trainer] epoch #188 | EpochTime 154.62 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -39.2095 MetaTest/Average/AverageReturn -39.2095 MetaTest/Average/Iteration 188 MetaTest/Average/MaxReturn -33.2619 MetaTest/Average/MinReturn -45.1571 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 5.9476 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.2095 MetaTest/__unnamed_task__/AverageReturn -39.2095 MetaTest/__unnamed_task__/Iteration 188 MetaTest/__unnamed_task__/MaxReturn -33.2619 MetaTest/__unnamed_task__/MinReturn -45.1571 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 5.9476 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 380000 ------------------------------------------------- ----------- 2025-03-29 23:13:50 | [pearl_trainer] epoch #189 | Training... 2025-03-29 23:14:07 | [pearl_trainer] epoch #189 | Evaluating... 2025-03-29 23:14:07 | [pearl_trainer] epoch #189 | Sampling for adapation and meta-testing... 2025-03-29 23:15:18 | [pearl_trainer] epoch #189 | Finished meta-testing... 2025-03-29 23:15:18 | [pearl_trainer] epoch #189 | Saving snapshot... 2025-03-29 23:15:19 | [pearl_trainer] epoch #189 | Saved 2025-03-29 23:15:19 | [pearl_trainer] epoch #189 | Time 32743.77 s 2025-03-29 23:15:19 | [pearl_trainer] epoch #189 | EpochTime 152.73 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.1778 MetaTest/Average/AverageReturn -33.1778 MetaTest/Average/Iteration 189 MetaTest/Average/MaxReturn -32.2986 MetaTest/Average/MinReturn -34.057 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.879194 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.1778 MetaTest/__unnamed_task__/AverageReturn -33.1778 MetaTest/__unnamed_task__/Iteration 189 MetaTest/__unnamed_task__/MaxReturn -32.2986 MetaTest/__unnamed_task__/MinReturn -34.057 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.879194 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 382000 ------------------------------------------------- ------------- 2025-03-29 23:16:23 | [pearl_trainer] epoch #190 | Training... 2025-03-29 23:16:41 | [pearl_trainer] epoch #190 | Evaluating... 2025-03-29 23:16:41 | [pearl_trainer] epoch #190 | Sampling for adapation and meta-testing... 2025-03-29 23:17:51 | [pearl_trainer] epoch #190 | Finished meta-testing... 2025-03-29 23:17:51 | [pearl_trainer] epoch #190 | Saving snapshot... 2025-03-29 23:17:52 | [pearl_trainer] epoch #190 | Saved 2025-03-29 23:17:52 | [pearl_trainer] epoch #190 | Time 32896.46 s 2025-03-29 23:17:52 | [pearl_trainer] epoch #190 | EpochTime 152.69 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -37.9862 MetaTest/Average/AverageReturn -37.9862 MetaTest/Average/Iteration 190 MetaTest/Average/MaxReturn -36.1587 MetaTest/Average/MinReturn -39.8138 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.8276 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.9862 MetaTest/__unnamed_task__/AverageReturn -37.9862 MetaTest/__unnamed_task__/Iteration 190 MetaTest/__unnamed_task__/MaxReturn -36.1587 MetaTest/__unnamed_task__/MinReturn -39.8138 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.8276 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 384000 ------------------------------------------------- ----------- 2025-03-29 23:18:57 | [pearl_trainer] epoch #191 | Training... 2025-03-29 23:19:14 | [pearl_trainer] epoch #191 | Evaluating... 2025-03-29 23:19:14 | [pearl_trainer] epoch #191 | Sampling for adapation and meta-testing... 2025-03-29 23:20:30 | [pearl_trainer] epoch #191 | Finished meta-testing... 2025-03-29 23:20:30 | [pearl_trainer] epoch #191 | Saving snapshot... 2025-03-29 23:20:31 | [pearl_trainer] epoch #191 | Saved 2025-03-29 23:20:31 | [pearl_trainer] epoch #191 | Time 33055.87 s 2025-03-29 23:20:31 | [pearl_trainer] epoch #191 | EpochTime 159.41 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -38.8294 MetaTest/Average/AverageReturn -38.8294 MetaTest/Average/Iteration 191 MetaTest/Average/MaxReturn -34.437 MetaTest/Average/MinReturn -43.2218 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.3924 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.8294 MetaTest/__unnamed_task__/AverageReturn -38.8294 MetaTest/__unnamed_task__/Iteration 191 MetaTest/__unnamed_task__/MaxReturn -34.437 MetaTest/__unnamed_task__/MinReturn -43.2218 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.3924 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 386000 ------------------------------------------------- ----------- 2025-03-29 23:21:35 | [pearl_trainer] epoch #192 | Training... 2025-03-29 23:21:52 | [pearl_trainer] epoch #192 | Evaluating... 2025-03-29 23:21:52 | [pearl_trainer] epoch #192 | Sampling for adapation and meta-testing... 2025-03-29 23:23:04 | [pearl_trainer] epoch #192 | Finished meta-testing... 2025-03-29 23:23:04 | [pearl_trainer] epoch #192 | Saving snapshot... 2025-03-29 23:23:05 | [pearl_trainer] epoch #192 | Saved 2025-03-29 23:23:05 | [pearl_trainer] epoch #192 | Time 33210.04 s 2025-03-29 23:23:05 | [pearl_trainer] epoch #192 | EpochTime 154.17 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -37.3731 MetaTest/Average/AverageReturn -37.3731 MetaTest/Average/Iteration 192 MetaTest/Average/MaxReturn -36.7222 MetaTest/Average/MinReturn -38.0241 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.650941 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.3731 MetaTest/__unnamed_task__/AverageReturn -37.3731 MetaTest/__unnamed_task__/Iteration 192 MetaTest/__unnamed_task__/MaxReturn -36.7222 MetaTest/__unnamed_task__/MinReturn -38.0241 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.650941 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 388000 ------------------------------------------------- ------------- 2025-03-29 23:24:09 | [pearl_trainer] epoch #193 | Training... 2025-03-29 23:24:26 | [pearl_trainer] epoch #193 | Evaluating... 2025-03-29 23:24:26 | [pearl_trainer] epoch #193 | Sampling for adapation and meta-testing... 2025-03-29 23:25:36 | [pearl_trainer] epoch #193 | Finished meta-testing... 2025-03-29 23:25:36 | [pearl_trainer] epoch #193 | Saving snapshot... 2025-03-29 23:25:36 | [pearl_trainer] epoch #193 | Saved 2025-03-29 23:25:36 | [pearl_trainer] epoch #193 | Time 33361.38 s 2025-03-29 23:25:36 | [pearl_trainer] epoch #193 | EpochTime 151.34 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.423 MetaTest/Average/AverageReturn -35.423 MetaTest/Average/Iteration 193 MetaTest/Average/MaxReturn -35.2541 MetaTest/Average/MinReturn -35.5919 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.168867 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.423 MetaTest/__unnamed_task__/AverageReturn -35.423 MetaTest/__unnamed_task__/Iteration 193 MetaTest/__unnamed_task__/MaxReturn -35.2541 MetaTest/__unnamed_task__/MinReturn -35.5919 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.168867 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 390000 ------------------------------------------------- ------------- 2025-03-29 23:26:41 | [pearl_trainer] epoch #194 | Training... 2025-03-29 23:26:56 | [pearl_trainer] epoch #194 | Evaluating... 2025-03-29 23:26:56 | [pearl_trainer] epoch #194 | Sampling for adapation and meta-testing... 2025-03-29 23:28:06 | [pearl_trainer] epoch #194 | Finished meta-testing... 2025-03-29 23:28:06 | [pearl_trainer] epoch #194 | Saving snapshot... 2025-03-29 23:28:07 | [pearl_trainer] epoch #194 | Saved 2025-03-29 23:28:07 | [pearl_trainer] epoch #194 | Time 33511.69 s 2025-03-29 23:28:07 | [pearl_trainer] epoch #194 | EpochTime 150.30 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -40.1169 MetaTest/Average/AverageReturn -40.1169 MetaTest/Average/Iteration 194 MetaTest/Average/MaxReturn -30.0844 MetaTest/Average/MinReturn -50.1494 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 10.0325 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -40.1169 MetaTest/__unnamed_task__/AverageReturn -40.1169 MetaTest/__unnamed_task__/Iteration 194 MetaTest/__unnamed_task__/MaxReturn -30.0844 MetaTest/__unnamed_task__/MinReturn -50.1494 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 10.0325 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 392000 ------------------------------------------------- ----------- 2025-03-29 23:29:10 | [pearl_trainer] epoch #195 | Training... 2025-03-29 23:29:26 | [pearl_trainer] epoch #195 | Evaluating... 2025-03-29 23:29:26 | [pearl_trainer] epoch #195 | Sampling for adapation and meta-testing... 2025-03-29 23:30:38 | [pearl_trainer] epoch #195 | Finished meta-testing... 2025-03-29 23:30:38 | [pearl_trainer] epoch #195 | Saving snapshot... 2025-03-29 23:30:39 | [pearl_trainer] epoch #195 | Saved 2025-03-29 23:30:39 | [pearl_trainer] epoch #195 | Time 33663.81 s 2025-03-29 23:30:39 | [pearl_trainer] epoch #195 | EpochTime 152.12 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -41.9504 MetaTest/Average/AverageReturn -41.9504 MetaTest/Average/Iteration 195 MetaTest/Average/MaxReturn -39.6178 MetaTest/Average/MinReturn -44.2831 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.33264 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -41.9504 MetaTest/__unnamed_task__/AverageReturn -41.9504 MetaTest/__unnamed_task__/Iteration 195 MetaTest/__unnamed_task__/MaxReturn -39.6178 MetaTest/__unnamed_task__/MinReturn -44.2831 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.33264 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 394000 ------------------------------------------------- ------------ 2025-03-29 23:31:44 | [pearl_trainer] epoch #196 | Training... 2025-03-29 23:32:00 | [pearl_trainer] epoch #196 | Evaluating... 2025-03-29 23:32:00 | [pearl_trainer] epoch #196 | Sampling for adapation and meta-testing... 2025-03-29 23:33:12 | [pearl_trainer] epoch #196 | Finished meta-testing... 2025-03-29 23:33:12 | [pearl_trainer] epoch #196 | Saving snapshot... 2025-03-29 23:33:12 | [pearl_trainer] epoch #196 | Saved 2025-03-29 23:33:12 | [pearl_trainer] epoch #196 | Time 33817.28 s 2025-03-29 23:33:12 | [pearl_trainer] epoch #196 | EpochTime 153.46 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.2327 MetaTest/Average/AverageReturn -34.2327 MetaTest/Average/Iteration 196 MetaTest/Average/MaxReturn -33.3729 MetaTest/Average/MinReturn -35.0925 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.859823 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.2327 MetaTest/__unnamed_task__/AverageReturn -34.2327 MetaTest/__unnamed_task__/Iteration 196 MetaTest/__unnamed_task__/MaxReturn -33.3729 MetaTest/__unnamed_task__/MinReturn -35.0925 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.859823 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 396000 ------------------------------------------------- ------------- 2025-03-29 23:34:18 | [pearl_trainer] epoch #197 | Training... 2025-03-29 23:34:35 | [pearl_trainer] epoch #197 | Evaluating... 2025-03-29 23:34:35 | [pearl_trainer] epoch #197 | Sampling for adapation and meta-testing... 2025-03-29 23:35:46 | [pearl_trainer] epoch #197 | Finished meta-testing... 2025-03-29 23:35:46 | [pearl_trainer] epoch #197 | Saving snapshot... 2025-03-29 23:35:47 | [pearl_trainer] epoch #197 | Saved 2025-03-29 23:35:47 | [pearl_trainer] epoch #197 | Time 33971.99 s 2025-03-29 23:35:47 | [pearl_trainer] epoch #197 | EpochTime 154.71 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -31.5856 MetaTest/Average/AverageReturn -31.5856 MetaTest/Average/Iteration 197 MetaTest/Average/MaxReturn -29.7039 MetaTest/Average/MinReturn -33.4673 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.88172 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -31.5856 MetaTest/__unnamed_task__/AverageReturn -31.5856 MetaTest/__unnamed_task__/Iteration 197 MetaTest/__unnamed_task__/MaxReturn -29.7039 MetaTest/__unnamed_task__/MinReturn -33.4673 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.88172 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 398000 ------------------------------------------------- ------------ 2025-03-29 23:36:51 | [pearl_trainer] epoch #198 | Training... 2025-03-29 23:37:07 | [pearl_trainer] epoch #198 | Evaluating... 2025-03-29 23:37:07 | [pearl_trainer] epoch #198 | Sampling for adapation and meta-testing... 2025-03-29 23:38:16 | [pearl_trainer] epoch #198 | Finished meta-testing... 2025-03-29 23:38:16 | [pearl_trainer] epoch #198 | Saving snapshot... 2025-03-29 23:38:17 | [pearl_trainer] epoch #198 | Saved 2025-03-29 23:38:17 | [pearl_trainer] epoch #198 | Time 34121.98 s 2025-03-29 23:38:17 | [pearl_trainer] epoch #198 | EpochTime 149.98 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.9548 MetaTest/Average/AverageReturn -35.9548 MetaTest/Average/Iteration 198 MetaTest/Average/MaxReturn -33.0204 MetaTest/Average/MinReturn -38.8893 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.93447 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.9548 MetaTest/__unnamed_task__/AverageReturn -35.9548 MetaTest/__unnamed_task__/Iteration 198 MetaTest/__unnamed_task__/MaxReturn -33.0204 MetaTest/__unnamed_task__/MinReturn -38.8893 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.93447 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 400000 ------------------------------------------------- ------------ 2025-03-29 23:39:20 | [pearl_trainer] epoch #199 | Training... 2025-03-29 23:39:36 | [pearl_trainer] epoch #199 | Evaluating... 2025-03-29 23:39:36 | [pearl_trainer] epoch #199 | Sampling for adapation and meta-testing... 2025-03-29 23:40:46 | [pearl_trainer] epoch #199 | Finished meta-testing... 2025-03-29 23:40:46 | [pearl_trainer] epoch #199 | Saving snapshot... 2025-03-29 23:40:47 | [pearl_trainer] epoch #199 | Saved 2025-03-29 23:40:47 | [pearl_trainer] epoch #199 | Time 34271.72 s 2025-03-29 23:40:47 | [pearl_trainer] epoch #199 | EpochTime 149.74 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.1439 MetaTest/Average/AverageReturn -34.1439 MetaTest/Average/Iteration 199 MetaTest/Average/MaxReturn -33.2805 MetaTest/Average/MinReturn -35.0073 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.863422 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.1439 MetaTest/__unnamed_task__/AverageReturn -34.1439 MetaTest/__unnamed_task__/Iteration 199 MetaTest/__unnamed_task__/MaxReturn -33.2805 MetaTest/__unnamed_task__/MinReturn -35.0073 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.863422 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 402000 ------------------------------------------------- ------------- 2025-03-29 23:41:51 | [pearl_trainer] epoch #200 | Training... 2025-03-29 23:42:06 | [pearl_trainer] epoch #200 | Evaluating... 2025-03-29 23:42:06 | [pearl_trainer] epoch #200 | Sampling for adapation and meta-testing... 2025-03-29 23:43:18 | [pearl_trainer] epoch #200 | Finished meta-testing... 2025-03-29 23:43:18 | [pearl_trainer] epoch #200 | Saving snapshot... 2025-03-29 23:43:19 | [pearl_trainer] epoch #200 | Saved 2025-03-29 23:43:19 | [pearl_trainer] epoch #200 | Time 34423.68 s 2025-03-29 23:43:19 | [pearl_trainer] epoch #200 | EpochTime 151.96 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.8252 MetaTest/Average/AverageReturn -33.8252 MetaTest/Average/Iteration 200 MetaTest/Average/MaxReturn -32.1906 MetaTest/Average/MinReturn -35.4597 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.63456 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.8252 MetaTest/__unnamed_task__/AverageReturn -33.8252 MetaTest/__unnamed_task__/Iteration 200 MetaTest/__unnamed_task__/MaxReturn -32.1906 MetaTest/__unnamed_task__/MinReturn -35.4597 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.63456 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 404000 ------------------------------------------------- ------------ 2025-03-29 23:44:22 | [pearl_trainer] epoch #201 | Training... 2025-03-29 23:44:38 | [pearl_trainer] epoch #201 | Evaluating... 2025-03-29 23:44:38 | [pearl_trainer] epoch #201 | Sampling for adapation and meta-testing... 2025-03-29 23:45:49 | [pearl_trainer] epoch #201 | Finished meta-testing... 2025-03-29 23:45:49 | [pearl_trainer] epoch #201 | Saving snapshot... 2025-03-29 23:45:49 | [pearl_trainer] epoch #201 | Saved 2025-03-29 23:45:49 | [pearl_trainer] epoch #201 | Time 34574.26 s 2025-03-29 23:45:49 | [pearl_trainer] epoch #201 | EpochTime 150.58 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.1673 MetaTest/Average/AverageReturn -35.1673 MetaTest/Average/Iteration 201 MetaTest/Average/MaxReturn -34.6499 MetaTest/Average/MinReturn -35.6848 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.517444 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.1673 MetaTest/__unnamed_task__/AverageReturn -35.1673 MetaTest/__unnamed_task__/Iteration 201 MetaTest/__unnamed_task__/MaxReturn -34.6499 MetaTest/__unnamed_task__/MinReturn -35.6848 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.517444 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 406000 ------------------------------------------------- ------------- 2025-03-29 23:46:53 | [pearl_trainer] epoch #202 | Training... 2025-03-29 23:47:10 | [pearl_trainer] epoch #202 | Evaluating... 2025-03-29 23:47:10 | [pearl_trainer] epoch #202 | Sampling for adapation and meta-testing... 2025-03-29 23:48:19 | [pearl_trainer] epoch #202 | Finished meta-testing... 2025-03-29 23:48:19 | [pearl_trainer] epoch #202 | Saving snapshot... 2025-03-29 23:48:20 | [pearl_trainer] epoch #202 | Saved 2025-03-29 23:48:20 | [pearl_trainer] epoch #202 | Time 34725.41 s 2025-03-29 23:48:20 | [pearl_trainer] epoch #202 | EpochTime 151.14 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.7584 MetaTest/Average/AverageReturn -37.7584 MetaTest/Average/Iteration 202 MetaTest/Average/MaxReturn -32.6161 MetaTest/Average/MinReturn -42.9008 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 5.14235 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.7584 MetaTest/__unnamed_task__/AverageReturn -37.7584 MetaTest/__unnamed_task__/Iteration 202 MetaTest/__unnamed_task__/MaxReturn -32.6161 MetaTest/__unnamed_task__/MinReturn -42.9008 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 5.14235 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 408000 ------------------------------------------------- ------------ 2025-03-29 23:49:26 | [pearl_trainer] epoch #203 | Training... 2025-03-29 23:49:41 | [pearl_trainer] epoch #203 | Evaluating... 2025-03-29 23:49:41 | [pearl_trainer] epoch #203 | Sampling for adapation and meta-testing... 2025-03-29 23:50:51 | [pearl_trainer] epoch #203 | Finished meta-testing... 2025-03-29 23:50:51 | [pearl_trainer] epoch #203 | Saving snapshot... 2025-03-29 23:50:51 | [pearl_trainer] epoch #203 | Saved 2025-03-29 23:50:51 | [pearl_trainer] epoch #203 | Time 34876.29 s 2025-03-29 23:50:51 | [pearl_trainer] epoch #203 | EpochTime 150.88 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.0443 MetaTest/Average/AverageReturn -36.0443 MetaTest/Average/Iteration 203 MetaTest/Average/MaxReturn -35.8731 MetaTest/Average/MinReturn -36.2155 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.17121 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.0443 MetaTest/__unnamed_task__/AverageReturn -36.0443 MetaTest/__unnamed_task__/Iteration 203 MetaTest/__unnamed_task__/MaxReturn -35.8731 MetaTest/__unnamed_task__/MinReturn -36.2155 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.17121 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 410000 ------------------------------------------------- ------------ 2025-03-29 23:51:54 | [pearl_trainer] epoch #204 | Training... 2025-03-29 23:52:10 | [pearl_trainer] epoch #204 | Evaluating... 2025-03-29 23:52:10 | [pearl_trainer] epoch #204 | Sampling for adapation and meta-testing... 2025-03-29 23:53:19 | [pearl_trainer] epoch #204 | Finished meta-testing... 2025-03-29 23:53:19 | [pearl_trainer] epoch #204 | Saving snapshot... 2025-03-29 23:53:20 | [pearl_trainer] epoch #204 | Saved 2025-03-29 23:53:20 | [pearl_trainer] epoch #204 | Time 35024.93 s 2025-03-29 23:53:20 | [pearl_trainer] epoch #204 | EpochTime 148.64 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.728 MetaTest/Average/AverageReturn -38.728 MetaTest/Average/Iteration 204 MetaTest/Average/MaxReturn -35.6899 MetaTest/Average/MinReturn -41.7661 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.03807 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.728 MetaTest/__unnamed_task__/AverageReturn -38.728 MetaTest/__unnamed_task__/Iteration 204 MetaTest/__unnamed_task__/MaxReturn -35.6899 MetaTest/__unnamed_task__/MinReturn -41.7661 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.03807 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 412000 ------------------------------------------------- ------------ 2025-03-29 23:54:23 | [pearl_trainer] epoch #205 | Training... 2025-03-29 23:54:38 | [pearl_trainer] epoch #205 | Evaluating... 2025-03-29 23:54:38 | [pearl_trainer] epoch #205 | Sampling for adapation and meta-testing... 2025-03-29 23:55:48 | [pearl_trainer] epoch #205 | Finished meta-testing... 2025-03-29 23:55:48 | [pearl_trainer] epoch #205 | Saving snapshot... 2025-03-29 23:55:49 | [pearl_trainer] epoch #205 | Saved 2025-03-29 23:55:49 | [pearl_trainer] epoch #205 | Time 35173.60 s 2025-03-29 23:55:49 | [pearl_trainer] epoch #205 | EpochTime 148.67 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -40.7763 MetaTest/Average/AverageReturn -40.7763 MetaTest/Average/Iteration 205 MetaTest/Average/MaxReturn -36.531 MetaTest/Average/MinReturn -45.0216 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.24531 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -40.7763 MetaTest/__unnamed_task__/AverageReturn -40.7763 MetaTest/__unnamed_task__/Iteration 205 MetaTest/__unnamed_task__/MaxReturn -36.531 MetaTest/__unnamed_task__/MinReturn -45.0216 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.24531 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 414000 ------------------------------------------------- ------------ 2025-03-29 23:56:52 | [pearl_trainer] epoch #206 | Training... 2025-03-29 23:57:08 | [pearl_trainer] epoch #206 | Evaluating... 2025-03-29 23:57:08 | [pearl_trainer] epoch #206 | Sampling for adapation and meta-testing... 2025-03-29 23:58:18 | [pearl_trainer] epoch #206 | Finished meta-testing... 2025-03-29 23:58:18 | [pearl_trainer] epoch #206 | Saving snapshot... 2025-03-29 23:58:19 | [pearl_trainer] epoch #206 | Saved 2025-03-29 23:58:19 | [pearl_trainer] epoch #206 | Time 35323.73 s 2025-03-29 23:58:19 | [pearl_trainer] epoch #206 | EpochTime 150.13 s ------------------------------------------------- -------------- MetaTest/Average/AverageDiscountedReturn -38.2384 MetaTest/Average/AverageReturn -38.2384 MetaTest/Average/Iteration 206 MetaTest/Average/MaxReturn -38.1819 MetaTest/Average/MinReturn -38.2949 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.0565009 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.2384 MetaTest/__unnamed_task__/AverageReturn -38.2384 MetaTest/__unnamed_task__/Iteration 206 MetaTest/__unnamed_task__/MaxReturn -38.1819 MetaTest/__unnamed_task__/MinReturn -38.2949 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.0565009 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 416000 ------------------------------------------------- -------------- 2025-03-29 23:59:22 | [pearl_trainer] epoch #207 | Training... 2025-03-29 23:59:38 | [pearl_trainer] epoch #207 | Evaluating... 2025-03-29 23:59:38 | [pearl_trainer] epoch #207 | Sampling for adapation and meta-testing... 2025-03-30 00:00:48 | [pearl_trainer] epoch #207 | Finished meta-testing... 2025-03-30 00:00:48 | [pearl_trainer] epoch #207 | Saving snapshot... 2025-03-30 00:00:48 | [pearl_trainer] epoch #207 | Saved 2025-03-30 00:00:48 | [pearl_trainer] epoch #207 | Time 35473.32 s 2025-03-30 00:00:48 | [pearl_trainer] epoch #207 | EpochTime 149.59 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.5926 MetaTest/Average/AverageReturn -33.5926 MetaTest/Average/Iteration 207 MetaTest/Average/MaxReturn -30.8169 MetaTest/Average/MinReturn -36.3683 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.77568 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.5926 MetaTest/__unnamed_task__/AverageReturn -33.5926 MetaTest/__unnamed_task__/Iteration 207 MetaTest/__unnamed_task__/MaxReturn -30.8169 MetaTest/__unnamed_task__/MinReturn -36.3683 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.77568 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 418000 ------------------------------------------------- ------------ 2025-03-30 00:01:52 | [pearl_trainer] epoch #208 | Training... 2025-03-30 00:02:06 | [pearl_trainer] epoch #208 | Evaluating... 2025-03-30 00:02:06 | [pearl_trainer] epoch #208 | Sampling for adapation and meta-testing... 2025-03-30 00:03:17 | [pearl_trainer] epoch #208 | Finished meta-testing... 2025-03-30 00:03:17 | [pearl_trainer] epoch #208 | Saving snapshot... 2025-03-30 00:03:18 | [pearl_trainer] epoch #208 | Saved 2025-03-30 00:03:18 | [pearl_trainer] epoch #208 | Time 35623.11 s 2025-03-30 00:03:18 | [pearl_trainer] epoch #208 | EpochTime 149.78 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.5785 MetaTest/Average/AverageReturn -38.5785 MetaTest/Average/Iteration 208 MetaTest/Average/MaxReturn -36.401 MetaTest/Average/MinReturn -40.756 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.17751 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.5785 MetaTest/__unnamed_task__/AverageReturn -38.5785 MetaTest/__unnamed_task__/Iteration 208 MetaTest/__unnamed_task__/MaxReturn -36.401 MetaTest/__unnamed_task__/MinReturn -40.756 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.17751 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 420000 ------------------------------------------------- ------------ 2025-03-30 00:04:23 | [pearl_trainer] epoch #209 | Training... 2025-03-30 00:04:42 | [pearl_trainer] epoch #209 | Evaluating... 2025-03-30 00:04:42 | [pearl_trainer] epoch #209 | Sampling for adapation and meta-testing... 2025-03-30 00:05:52 | [pearl_trainer] epoch #209 | Finished meta-testing... 2025-03-30 00:05:52 | [pearl_trainer] epoch #209 | Saving snapshot... 2025-03-30 00:05:53 | [pearl_trainer] epoch #209 | Saved 2025-03-30 00:05:53 | [pearl_trainer] epoch #209 | Time 35777.93 s 2025-03-30 00:05:53 | [pearl_trainer] epoch #209 | EpochTime 154.82 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -44.9595 MetaTest/Average/AverageReturn -44.9595 MetaTest/Average/Iteration 209 MetaTest/Average/MaxReturn -43.8199 MetaTest/Average/MinReturn -46.0992 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.13964 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.9595 MetaTest/__unnamed_task__/AverageReturn -44.9595 MetaTest/__unnamed_task__/Iteration 209 MetaTest/__unnamed_task__/MaxReturn -43.8199 MetaTest/__unnamed_task__/MinReturn -46.0992 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.13964 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 422000 ------------------------------------------------- ------------ 2025-03-30 00:07:00 | [pearl_trainer] epoch #210 | Training... 2025-03-30 00:07:15 | [pearl_trainer] epoch #210 | Evaluating... 2025-03-30 00:07:15 | [pearl_trainer] epoch #210 | Sampling for adapation and meta-testing... 2025-03-30 00:08:25 | [pearl_trainer] epoch #210 | Finished meta-testing... 2025-03-30 00:08:25 | [pearl_trainer] epoch #210 | Saving snapshot... 2025-03-30 00:08:25 | [pearl_trainer] epoch #210 | Saved 2025-03-30 00:08:25 | [pearl_trainer] epoch #210 | Time 35930.38 s 2025-03-30 00:08:25 | [pearl_trainer] epoch #210 | EpochTime 152.45 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -36.8938 MetaTest/Average/AverageReturn -36.8938 MetaTest/Average/Iteration 210 MetaTest/Average/MaxReturn -36.6978 MetaTest/Average/MinReturn -37.0898 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.195998 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.8938 MetaTest/__unnamed_task__/AverageReturn -36.8938 MetaTest/__unnamed_task__/Iteration 210 MetaTest/__unnamed_task__/MaxReturn -36.6978 MetaTest/__unnamed_task__/MinReturn -37.0898 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.195998 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 424000 ------------------------------------------------- ------------- 2025-03-30 00:09:29 | [pearl_trainer] epoch #211 | Training... 2025-03-30 00:09:44 | [pearl_trainer] epoch #211 | Evaluating... 2025-03-30 00:09:44 | [pearl_trainer] epoch #211 | Sampling for adapation and meta-testing... 2025-03-30 00:10:54 | [pearl_trainer] epoch #211 | Finished meta-testing... 2025-03-30 00:10:54 | [pearl_trainer] epoch #211 | Saving snapshot... 2025-03-30 00:10:55 | [pearl_trainer] epoch #211 | Saved 2025-03-30 00:10:55 | [pearl_trainer] epoch #211 | Time 36079.66 s 2025-03-30 00:10:55 | [pearl_trainer] epoch #211 | EpochTime 149.27 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.8522 MetaTest/Average/AverageReturn -33.8522 MetaTest/Average/Iteration 211 MetaTest/Average/MaxReturn -32.9618 MetaTest/Average/MinReturn -34.7426 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.890404 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.8522 MetaTest/__unnamed_task__/AverageReturn -33.8522 MetaTest/__unnamed_task__/Iteration 211 MetaTest/__unnamed_task__/MaxReturn -32.9618 MetaTest/__unnamed_task__/MinReturn -34.7426 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.890404 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 426000 ------------------------------------------------- ------------- 2025-03-30 00:12:00 | [pearl_trainer] epoch #212 | Training... 2025-03-30 00:12:16 | [pearl_trainer] epoch #212 | Evaluating... 2025-03-30 00:12:16 | [pearl_trainer] epoch #212 | Sampling for adapation and meta-testing... 2025-03-30 00:13:28 | [pearl_trainer] epoch #212 | Finished meta-testing... 2025-03-30 00:13:28 | [pearl_trainer] epoch #212 | Saving snapshot... 2025-03-30 00:13:29 | [pearl_trainer] epoch #212 | Saved 2025-03-30 00:13:29 | [pearl_trainer] epoch #212 | Time 36233.73 s 2025-03-30 00:13:29 | [pearl_trainer] epoch #212 | EpochTime 154.07 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -38.4082 MetaTest/Average/AverageReturn -38.4082 MetaTest/Average/Iteration 212 MetaTest/Average/MaxReturn -38.1126 MetaTest/Average/MinReturn -38.7038 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.295607 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.4082 MetaTest/__unnamed_task__/AverageReturn -38.4082 MetaTest/__unnamed_task__/Iteration 212 MetaTest/__unnamed_task__/MaxReturn -38.1126 MetaTest/__unnamed_task__/MinReturn -38.7038 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.295607 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 428000 ------------------------------------------------- ------------- 2025-03-30 00:14:34 | [pearl_trainer] epoch #213 | Training... 2025-03-30 00:14:50 | [pearl_trainer] epoch #213 | Evaluating... 2025-03-30 00:14:50 | [pearl_trainer] epoch #213 | Sampling for adapation and meta-testing... 2025-03-30 00:16:02 | [pearl_trainer] epoch #213 | Finished meta-testing... 2025-03-30 00:16:02 | [pearl_trainer] epoch #213 | Saving snapshot... 2025-03-30 00:16:03 | [pearl_trainer] epoch #213 | Saved 2025-03-30 00:16:03 | [pearl_trainer] epoch #213 | Time 36387.56 s 2025-03-30 00:16:03 | [pearl_trainer] epoch #213 | EpochTime 153.83 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.9991 MetaTest/Average/AverageReturn -38.9991 MetaTest/Average/Iteration 213 MetaTest/Average/MaxReturn -35.5473 MetaTest/Average/MinReturn -42.4508 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.45174 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.9991 MetaTest/__unnamed_task__/AverageReturn -38.9991 MetaTest/__unnamed_task__/Iteration 213 MetaTest/__unnamed_task__/MaxReturn -35.5473 MetaTest/__unnamed_task__/MinReturn -42.4508 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.45174 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 430000 ------------------------------------------------- ------------ 2025-03-30 00:17:10 | [pearl_trainer] epoch #214 | Training... 2025-03-30 00:17:24 | [pearl_trainer] epoch #214 | Evaluating... 2025-03-30 00:17:24 | [pearl_trainer] epoch #214 | Sampling for adapation and meta-testing... 2025-03-30 00:18:36 | [pearl_trainer] epoch #214 | Finished meta-testing... 2025-03-30 00:18:36 | [pearl_trainer] epoch #214 | Saving snapshot... 2025-03-30 00:18:37 | [pearl_trainer] epoch #214 | Saved 2025-03-30 00:18:37 | [pearl_trainer] epoch #214 | Time 36541.68 s 2025-03-30 00:18:37 | [pearl_trainer] epoch #214 | EpochTime 154.12 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.7805 MetaTest/Average/AverageReturn -35.7805 MetaTest/Average/Iteration 214 MetaTest/Average/MaxReturn -35.2167 MetaTest/Average/MinReturn -36.3442 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.563771 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.7805 MetaTest/__unnamed_task__/AverageReturn -35.7805 MetaTest/__unnamed_task__/Iteration 214 MetaTest/__unnamed_task__/MaxReturn -35.2167 MetaTest/__unnamed_task__/MinReturn -36.3442 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.563771 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 432000 ------------------------------------------------- ------------- 2025-03-30 00:19:41 | [pearl_trainer] epoch #215 | Training... 2025-03-30 00:19:56 | [pearl_trainer] epoch #215 | Evaluating... 2025-03-30 00:19:56 | [pearl_trainer] epoch #215 | Sampling for adapation and meta-testing... 2025-03-30 00:21:09 | [pearl_trainer] epoch #215 | Finished meta-testing... 2025-03-30 00:21:09 | [pearl_trainer] epoch #215 | Saving snapshot... 2025-03-30 00:21:10 | [pearl_trainer] epoch #215 | Saved 2025-03-30 00:21:10 | [pearl_trainer] epoch #215 | Time 36694.98 s 2025-03-30 00:21:10 | [pearl_trainer] epoch #215 | EpochTime 153.30 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -37.6697 MetaTest/Average/AverageReturn -37.6697 MetaTest/Average/Iteration 215 MetaTest/Average/MaxReturn -34.7066 MetaTest/Average/MinReturn -40.6328 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.9631 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.6697 MetaTest/__unnamed_task__/AverageReturn -37.6697 MetaTest/__unnamed_task__/Iteration 215 MetaTest/__unnamed_task__/MaxReturn -34.7066 MetaTest/__unnamed_task__/MinReturn -40.6328 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.9631 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 434000 ------------------------------------------------- ----------- 2025-03-30 00:22:17 | [pearl_trainer] epoch #216 | Training... 2025-03-30 00:22:34 | [pearl_trainer] epoch #216 | Evaluating... 2025-03-30 00:22:34 | [pearl_trainer] epoch #216 | Sampling for adapation and meta-testing... 2025-03-30 00:23:44 | [pearl_trainer] epoch #216 | Finished meta-testing... 2025-03-30 00:23:44 | [pearl_trainer] epoch #216 | Saving snapshot... 2025-03-30 00:23:45 | [pearl_trainer] epoch #216 | Saved 2025-03-30 00:23:45 | [pearl_trainer] epoch #216 | Time 36849.45 s 2025-03-30 00:23:45 | [pearl_trainer] epoch #216 | EpochTime 154.47 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -37.3376 MetaTest/Average/AverageReturn -37.3376 MetaTest/Average/Iteration 216 MetaTest/Average/MaxReturn -36.8829 MetaTest/Average/MinReturn -37.7923 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.454707 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.3376 MetaTest/__unnamed_task__/AverageReturn -37.3376 MetaTest/__unnamed_task__/Iteration 216 MetaTest/__unnamed_task__/MaxReturn -36.8829 MetaTest/__unnamed_task__/MinReturn -37.7923 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.454707 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 436000 ------------------------------------------------- ------------- 2025-03-30 00:24:48 | [pearl_trainer] epoch #217 | Training... 2025-03-30 00:25:05 | [pearl_trainer] epoch #217 | Evaluating... 2025-03-30 00:25:05 | [pearl_trainer] epoch #217 | Sampling for adapation and meta-testing... 2025-03-30 00:26:16 | [pearl_trainer] epoch #217 | Finished meta-testing... 2025-03-30 00:26:16 | [pearl_trainer] epoch #217 | Saving snapshot... 2025-03-30 00:26:17 | [pearl_trainer] epoch #217 | Saved 2025-03-30 00:26:17 | [pearl_trainer] epoch #217 | Time 37001.76 s 2025-03-30 00:26:17 | [pearl_trainer] epoch #217 | EpochTime 152.30 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.8735 MetaTest/Average/AverageReturn -35.8735 MetaTest/Average/Iteration 217 MetaTest/Average/MaxReturn -35.2994 MetaTest/Average/MinReturn -36.4477 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.574117 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.8735 MetaTest/__unnamed_task__/AverageReturn -35.8735 MetaTest/__unnamed_task__/Iteration 217 MetaTest/__unnamed_task__/MaxReturn -35.2994 MetaTest/__unnamed_task__/MinReturn -36.4477 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.574117 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 438000 ------------------------------------------------- ------------- 2025-03-30 00:27:23 | [pearl_trainer] epoch #218 | Training... 2025-03-30 00:27:40 | [pearl_trainer] epoch #218 | Evaluating... 2025-03-30 00:27:40 | [pearl_trainer] epoch #218 | Sampling for adapation and meta-testing... 2025-03-30 00:28:52 | [pearl_trainer] epoch #218 | Finished meta-testing... 2025-03-30 00:28:52 | [pearl_trainer] epoch #218 | Saving snapshot... 2025-03-30 00:28:53 | [pearl_trainer] epoch #218 | Saved 2025-03-30 00:28:53 | [pearl_trainer] epoch #218 | Time 37157.61 s 2025-03-30 00:28:53 | [pearl_trainer] epoch #218 | EpochTime 155.85 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -39.5318 MetaTest/Average/AverageReturn -39.5318 MetaTest/Average/Iteration 218 MetaTest/Average/MaxReturn -35.4543 MetaTest/Average/MinReturn -43.6093 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.07752 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.5318 MetaTest/__unnamed_task__/AverageReturn -39.5318 MetaTest/__unnamed_task__/Iteration 218 MetaTest/__unnamed_task__/MaxReturn -35.4543 MetaTest/__unnamed_task__/MinReturn -43.6093 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.07752 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 440000 ------------------------------------------------- ------------ 2025-03-30 00:29:58 | [pearl_trainer] epoch #219 | Training... 2025-03-30 00:30:14 | [pearl_trainer] epoch #219 | Evaluating... 2025-03-30 00:30:14 | [pearl_trainer] epoch #219 | Sampling for adapation and meta-testing... 2025-03-30 00:31:27 | [pearl_trainer] epoch #219 | Finished meta-testing... 2025-03-30 00:31:27 | [pearl_trainer] epoch #219 | Saving snapshot... 2025-03-30 00:31:28 | [pearl_trainer] epoch #219 | Saved 2025-03-30 00:31:28 | [pearl_trainer] epoch #219 | Time 37312.48 s 2025-03-30 00:31:28 | [pearl_trainer] epoch #219 | EpochTime 154.87 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.6745 MetaTest/Average/AverageReturn -35.6745 MetaTest/Average/Iteration 219 MetaTest/Average/MaxReturn -33.71 MetaTest/Average/MinReturn -37.639 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.96452 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.6745 MetaTest/__unnamed_task__/AverageReturn -35.6745 MetaTest/__unnamed_task__/Iteration 219 MetaTest/__unnamed_task__/MaxReturn -33.71 MetaTest/__unnamed_task__/MinReturn -37.639 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.96452 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 442000 ------------------------------------------------- ------------ 2025-03-30 00:32:35 | [pearl_trainer] epoch #220 | Training... 2025-03-30 00:32:53 | [pearl_trainer] epoch #220 | Evaluating... 2025-03-30 00:32:53 | [pearl_trainer] epoch #220 | Sampling for adapation and meta-testing... 2025-03-30 00:34:08 | [pearl_trainer] epoch #220 | Finished meta-testing... 2025-03-30 00:34:08 | [pearl_trainer] epoch #220 | Saving snapshot... 2025-03-30 00:34:09 | [pearl_trainer] epoch #220 | Saved 2025-03-30 00:34:09 | [pearl_trainer] epoch #220 | Time 37473.45 s 2025-03-30 00:34:09 | [pearl_trainer] epoch #220 | EpochTime 160.97 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -32.6831 MetaTest/Average/AverageReturn -32.6831 MetaTest/Average/Iteration 220 MetaTest/Average/MaxReturn -32.5101 MetaTest/Average/MinReturn -32.8561 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.173021 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -32.6831 MetaTest/__unnamed_task__/AverageReturn -32.6831 MetaTest/__unnamed_task__/Iteration 220 MetaTest/__unnamed_task__/MaxReturn -32.5101 MetaTest/__unnamed_task__/MinReturn -32.8561 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.173021 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 444000 ------------------------------------------------- ------------- 2025-03-30 00:35:13 | [pearl_trainer] epoch #221 | Training... 2025-03-30 00:35:30 | [pearl_trainer] epoch #221 | Evaluating... 2025-03-30 00:35:30 | [pearl_trainer] epoch #221 | Sampling for adapation and meta-testing... 2025-03-30 00:36:41 | [pearl_trainer] epoch #221 | Finished meta-testing... 2025-03-30 00:36:41 | [pearl_trainer] epoch #221 | Saving snapshot... 2025-03-30 00:36:42 | [pearl_trainer] epoch #221 | Saved 2025-03-30 00:36:42 | [pearl_trainer] epoch #221 | Time 37626.62 s 2025-03-30 00:36:42 | [pearl_trainer] epoch #221 | EpochTime 153.17 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.6772 MetaTest/Average/AverageReturn -36.6772 MetaTest/Average/Iteration 221 MetaTest/Average/MaxReturn -32.9352 MetaTest/Average/MinReturn -40.4191 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.74195 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.6772 MetaTest/__unnamed_task__/AverageReturn -36.6772 MetaTest/__unnamed_task__/Iteration 221 MetaTest/__unnamed_task__/MaxReturn -32.9352 MetaTest/__unnamed_task__/MinReturn -40.4191 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.74195 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 446000 ------------------------------------------------- ------------ 2025-03-30 00:37:46 | [pearl_trainer] epoch #222 | Training... 2025-03-30 00:38:04 | [pearl_trainer] epoch #222 | Evaluating... 2025-03-30 00:38:04 | [pearl_trainer] epoch #222 | Sampling for adapation and meta-testing... 2025-03-30 00:39:15 | [pearl_trainer] epoch #222 | Finished meta-testing... 2025-03-30 00:39:15 | [pearl_trainer] epoch #222 | Saving snapshot... 2025-03-30 00:39:16 | [pearl_trainer] epoch #222 | Saved 2025-03-30 00:39:16 | [pearl_trainer] epoch #222 | Time 37780.47 s 2025-03-30 00:39:16 | [pearl_trainer] epoch #222 | EpochTime 153.84 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -37.6004 MetaTest/Average/AverageReturn -37.6004 MetaTest/Average/Iteration 222 MetaTest/Average/MaxReturn -34.1275 MetaTest/Average/MinReturn -41.0733 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.4729 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.6004 MetaTest/__unnamed_task__/AverageReturn -37.6004 MetaTest/__unnamed_task__/Iteration 222 MetaTest/__unnamed_task__/MaxReturn -34.1275 MetaTest/__unnamed_task__/MinReturn -41.0733 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.4729 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 448000 ------------------------------------------------- ----------- 2025-03-30 00:40:20 | [pearl_trainer] epoch #223 | Training... 2025-03-30 00:40:38 | [pearl_trainer] epoch #223 | Evaluating... 2025-03-30 00:40:38 | [pearl_trainer] epoch #223 | Sampling for adapation and meta-testing... 2025-03-30 00:41:49 | [pearl_trainer] epoch #223 | Finished meta-testing... 2025-03-30 00:41:49 | [pearl_trainer] epoch #223 | Saving snapshot... 2025-03-30 00:41:50 | [pearl_trainer] epoch #223 | Saved 2025-03-30 00:41:50 | [pearl_trainer] epoch #223 | Time 37935.05 s 2025-03-30 00:41:50 | [pearl_trainer] epoch #223 | EpochTime 154.58 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.1547 MetaTest/Average/AverageReturn -35.1547 MetaTest/Average/Iteration 223 MetaTest/Average/MaxReturn -34.793 MetaTest/Average/MinReturn -35.5165 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.361745 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.1547 MetaTest/__unnamed_task__/AverageReturn -35.1547 MetaTest/__unnamed_task__/Iteration 223 MetaTest/__unnamed_task__/MaxReturn -34.793 MetaTest/__unnamed_task__/MinReturn -35.5165 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.361745 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 450000 ------------------------------------------------- ------------- 2025-03-30 00:42:56 | [pearl_trainer] epoch #224 | Training... 2025-03-30 00:43:13 | [pearl_trainer] epoch #224 | Evaluating... 2025-03-30 00:43:13 | [pearl_trainer] epoch #224 | Sampling for adapation and meta-testing... 2025-03-30 00:44:23 | [pearl_trainer] epoch #224 | Finished meta-testing... 2025-03-30 00:44:23 | [pearl_trainer] epoch #224 | Saving snapshot... 2025-03-30 00:44:24 | [pearl_trainer] epoch #224 | Saved 2025-03-30 00:44:24 | [pearl_trainer] epoch #224 | Time 38089.37 s 2025-03-30 00:44:24 | [pearl_trainer] epoch #224 | EpochTime 154.32 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.987 MetaTest/Average/AverageReturn -34.987 MetaTest/Average/Iteration 224 MetaTest/Average/MaxReturn -34.2081 MetaTest/Average/MinReturn -35.7658 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.778856 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.987 MetaTest/__unnamed_task__/AverageReturn -34.987 MetaTest/__unnamed_task__/Iteration 224 MetaTest/__unnamed_task__/MaxReturn -34.2081 MetaTest/__unnamed_task__/MinReturn -35.7658 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.778856 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 452000 ------------------------------------------------- ------------- 2025-03-30 00:45:29 | [pearl_trainer] epoch #225 | Training... 2025-03-30 00:45:46 | [pearl_trainer] epoch #225 | Evaluating... 2025-03-30 00:45:46 | [pearl_trainer] epoch #225 | Sampling for adapation and meta-testing... 2025-03-30 00:46:58 | [pearl_trainer] epoch #225 | Finished meta-testing... 2025-03-30 00:46:58 | [pearl_trainer] epoch #225 | Saving snapshot... 2025-03-30 00:46:59 | [pearl_trainer] epoch #225 | Saved 2025-03-30 00:46:59 | [pearl_trainer] epoch #225 | Time 38243.63 s 2025-03-30 00:46:59 | [pearl_trainer] epoch #225 | EpochTime 154.25 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.5733 MetaTest/Average/AverageReturn -35.5733 MetaTest/Average/Iteration 225 MetaTest/Average/MaxReturn -31.3853 MetaTest/Average/MinReturn -39.7612 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.18793 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.5733 MetaTest/__unnamed_task__/AverageReturn -35.5733 MetaTest/__unnamed_task__/Iteration 225 MetaTest/__unnamed_task__/MaxReturn -31.3853 MetaTest/__unnamed_task__/MinReturn -39.7612 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.18793 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 454000 ------------------------------------------------- ------------ 2025-03-30 00:48:03 | [pearl_trainer] epoch #226 | Training... 2025-03-30 00:48:21 | [pearl_trainer] epoch #226 | Evaluating... 2025-03-30 00:48:21 | [pearl_trainer] epoch #226 | Sampling for adapation and meta-testing... 2025-03-30 00:49:31 | [pearl_trainer] epoch #226 | Finished meta-testing... 2025-03-30 00:49:31 | [pearl_trainer] epoch #226 | Saving snapshot... 2025-03-30 00:49:32 | [pearl_trainer] epoch #226 | Saved 2025-03-30 00:49:32 | [pearl_trainer] epoch #226 | Time 38396.68 s 2025-03-30 00:49:32 | [pearl_trainer] epoch #226 | EpochTime 153.05 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.8158 MetaTest/Average/AverageReturn -37.8158 MetaTest/Average/Iteration 226 MetaTest/Average/MaxReturn -35.6916 MetaTest/Average/MinReturn -39.94 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.12416 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.8158 MetaTest/__unnamed_task__/AverageReturn -37.8158 MetaTest/__unnamed_task__/Iteration 226 MetaTest/__unnamed_task__/MaxReturn -35.6916 MetaTest/__unnamed_task__/MinReturn -39.94 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.12416 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 456000 ------------------------------------------------- ------------ 2025-03-30 00:50:36 | [pearl_trainer] epoch #227 | Training... 2025-03-30 00:50:53 | [pearl_trainer] epoch #227 | Evaluating... 2025-03-30 00:50:53 | [pearl_trainer] epoch #227 | Sampling for adapation and meta-testing... 2025-03-30 00:52:04 | [pearl_trainer] epoch #227 | Finished meta-testing... 2025-03-30 00:52:04 | [pearl_trainer] epoch #227 | Saving snapshot... 2025-03-30 00:52:05 | [pearl_trainer] epoch #227 | Saved 2025-03-30 00:52:05 | [pearl_trainer] epoch #227 | Time 38549.53 s 2025-03-30 00:52:05 | [pearl_trainer] epoch #227 | EpochTime 152.85 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -32.7552 MetaTest/Average/AverageReturn -32.7552 MetaTest/Average/Iteration 227 MetaTest/Average/MaxReturn -31.0042 MetaTest/Average/MinReturn -34.5062 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.75099 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -32.7552 MetaTest/__unnamed_task__/AverageReturn -32.7552 MetaTest/__unnamed_task__/Iteration 227 MetaTest/__unnamed_task__/MaxReturn -31.0042 MetaTest/__unnamed_task__/MinReturn -34.5062 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.75099 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 458000 ------------------------------------------------- ------------ 2025-03-30 00:53:10 | [pearl_trainer] epoch #228 | Training... 2025-03-30 00:53:28 | [pearl_trainer] epoch #228 | Evaluating... 2025-03-30 00:53:28 | [pearl_trainer] epoch #228 | Sampling for adapation and meta-testing... 2025-03-30 00:54:40 | [pearl_trainer] epoch #228 | Finished meta-testing... 2025-03-30 00:54:40 | [pearl_trainer] epoch #228 | Saving snapshot... 2025-03-30 00:54:40 | [pearl_trainer] epoch #228 | Saved 2025-03-30 00:54:40 | [pearl_trainer] epoch #228 | Time 38705.23 s 2025-03-30 00:54:40 | [pearl_trainer] epoch #228 | EpochTime 155.70 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.9839 MetaTest/Average/AverageReturn -35.9839 MetaTest/Average/Iteration 228 MetaTest/Average/MaxReturn -35.5821 MetaTest/Average/MinReturn -36.3856 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.401758 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.9839 MetaTest/__unnamed_task__/AverageReturn -35.9839 MetaTest/__unnamed_task__/Iteration 228 MetaTest/__unnamed_task__/MaxReturn -35.5821 MetaTest/__unnamed_task__/MinReturn -36.3856 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.401758 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 460000 ------------------------------------------------- ------------- 2025-03-30 00:55:46 | [pearl_trainer] epoch #229 | Training... 2025-03-30 00:56:03 | [pearl_trainer] epoch #229 | Evaluating... 2025-03-30 00:56:03 | [pearl_trainer] epoch #229 | Sampling for adapation and meta-testing... 2025-03-30 00:57:15 | [pearl_trainer] epoch #229 | Finished meta-testing... 2025-03-30 00:57:15 | [pearl_trainer] epoch #229 | Saving snapshot... 2025-03-30 00:57:15 | [pearl_trainer] epoch #229 | Saved 2025-03-30 00:57:15 | [pearl_trainer] epoch #229 | Time 38860.43 s 2025-03-30 00:57:15 | [pearl_trainer] epoch #229 | EpochTime 155.19 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -37.0391 MetaTest/Average/AverageReturn -37.0391 MetaTest/Average/Iteration 229 MetaTest/Average/MaxReturn -36.4799 MetaTest/Average/MinReturn -37.5984 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.559271 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.0391 MetaTest/__unnamed_task__/AverageReturn -37.0391 MetaTest/__unnamed_task__/Iteration 229 MetaTest/__unnamed_task__/MaxReturn -36.4799 MetaTest/__unnamed_task__/MinReturn -37.5984 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.559271 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 462000 ------------------------------------------------- ------------- 2025-03-30 00:58:19 | [pearl_trainer] epoch #230 | Training... 2025-03-30 00:58:37 | [pearl_trainer] epoch #230 | Evaluating... 2025-03-30 00:58:37 | [pearl_trainer] epoch #230 | Sampling for adapation and meta-testing... 2025-03-30 00:59:48 | [pearl_trainer] epoch #230 | Finished meta-testing... 2025-03-30 00:59:48 | [pearl_trainer] epoch #230 | Saving snapshot... 2025-03-30 00:59:49 | [pearl_trainer] epoch #230 | Saved 2025-03-30 00:59:49 | [pearl_trainer] epoch #230 | Time 39013.46 s 2025-03-30 00:59:49 | [pearl_trainer] epoch #230 | EpochTime 153.03 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.9331 MetaTest/Average/AverageReturn -35.9331 MetaTest/Average/Iteration 230 MetaTest/Average/MaxReturn -34.6996 MetaTest/Average/MinReturn -37.1667 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.23352 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.9331 MetaTest/__unnamed_task__/AverageReturn -35.9331 MetaTest/__unnamed_task__/Iteration 230 MetaTest/__unnamed_task__/MaxReturn -34.6996 MetaTest/__unnamed_task__/MinReturn -37.1667 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.23352 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 464000 ------------------------------------------------- ------------ 2025-03-30 01:00:53 | [pearl_trainer] epoch #231 | Training... 2025-03-30 01:01:11 | [pearl_trainer] epoch #231 | Evaluating... 2025-03-30 01:01:11 | [pearl_trainer] epoch #231 | Sampling for adapation and meta-testing... 2025-03-30 01:02:21 | [pearl_trainer] epoch #231 | Finished meta-testing... 2025-03-30 01:02:21 | [pearl_trainer] epoch #231 | Saving snapshot... 2025-03-30 01:02:22 | [pearl_trainer] epoch #231 | Saved 2025-03-30 01:02:22 | [pearl_trainer] epoch #231 | Time 39166.89 s 2025-03-30 01:02:22 | [pearl_trainer] epoch #231 | EpochTime 153.42 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.9973 MetaTest/Average/AverageReturn -34.9973 MetaTest/Average/Iteration 231 MetaTest/Average/MaxReturn -32.3902 MetaTest/Average/MinReturn -37.6044 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.60712 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.9973 MetaTest/__unnamed_task__/AverageReturn -34.9973 MetaTest/__unnamed_task__/Iteration 231 MetaTest/__unnamed_task__/MaxReturn -32.3902 MetaTest/__unnamed_task__/MinReturn -37.6044 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.60712 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 466000 ------------------------------------------------- ------------ 2025-03-30 01:03:26 | [pearl_trainer] epoch #232 | Training... 2025-03-30 01:03:44 | [pearl_trainer] epoch #232 | Evaluating... 2025-03-30 01:03:44 | [pearl_trainer] epoch #232 | Sampling for adapation and meta-testing... 2025-03-30 01:04:55 | [pearl_trainer] epoch #232 | Finished meta-testing... 2025-03-30 01:04:55 | [pearl_trainer] epoch #232 | Saving snapshot... 2025-03-30 01:04:55 | [pearl_trainer] epoch #232 | Saved 2025-03-30 01:04:55 | [pearl_trainer] epoch #232 | Time 39320.32 s 2025-03-30 01:04:55 | [pearl_trainer] epoch #232 | EpochTime 153.44 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -36.7635 MetaTest/Average/AverageReturn -36.7635 MetaTest/Average/Iteration 232 MetaTest/Average/MaxReturn -36.3215 MetaTest/Average/MinReturn -37.2055 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.442023 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.7635 MetaTest/__unnamed_task__/AverageReturn -36.7635 MetaTest/__unnamed_task__/Iteration 232 MetaTest/__unnamed_task__/MaxReturn -36.3215 MetaTest/__unnamed_task__/MinReturn -37.2055 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.442023 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 468000 ------------------------------------------------- ------------- 2025-03-30 01:06:01 | [pearl_trainer] epoch #233 | Training... 2025-03-30 01:06:18 | [pearl_trainer] epoch #233 | Evaluating... 2025-03-30 01:06:18 | [pearl_trainer] epoch #233 | Sampling for adapation and meta-testing... 2025-03-30 01:07:28 | [pearl_trainer] epoch #233 | Finished meta-testing... 2025-03-30 01:07:28 | [pearl_trainer] epoch #233 | Saving snapshot... 2025-03-30 01:07:29 | [pearl_trainer] epoch #233 | Saved 2025-03-30 01:07:29 | [pearl_trainer] epoch #233 | Time 39473.84 s 2025-03-30 01:07:29 | [pearl_trainer] epoch #233 | EpochTime 153.52 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -36.5495 MetaTest/Average/AverageReturn -36.5495 MetaTest/Average/Iteration 233 MetaTest/Average/MaxReturn -36.0438 MetaTest/Average/MinReturn -37.0552 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.505683 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.5495 MetaTest/__unnamed_task__/AverageReturn -36.5495 MetaTest/__unnamed_task__/Iteration 233 MetaTest/__unnamed_task__/MaxReturn -36.0438 MetaTest/__unnamed_task__/MinReturn -37.0552 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.505683 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 470000 ------------------------------------------------- ------------- 2025-03-30 01:08:32 | [pearl_trainer] epoch #234 | Training... 2025-03-30 01:08:47 | [pearl_trainer] epoch #234 | Evaluating... 2025-03-30 01:08:47 | [pearl_trainer] epoch #234 | Sampling for adapation and meta-testing... 2025-03-30 01:09:57 | [pearl_trainer] epoch #234 | Finished meta-testing... 2025-03-30 01:09:57 | [pearl_trainer] epoch #234 | Saving snapshot... 2025-03-30 01:09:58 | [pearl_trainer] epoch #234 | Saved 2025-03-30 01:09:58 | [pearl_trainer] epoch #234 | Time 39622.96 s 2025-03-30 01:09:58 | [pearl_trainer] epoch #234 | EpochTime 149.12 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -37.9381 MetaTest/Average/AverageReturn -37.9381 MetaTest/Average/Iteration 234 MetaTest/Average/MaxReturn -37.7123 MetaTest/Average/MinReturn -38.1639 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.225778 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.9381 MetaTest/__unnamed_task__/AverageReturn -37.9381 MetaTest/__unnamed_task__/Iteration 234 MetaTest/__unnamed_task__/MaxReturn -37.7123 MetaTest/__unnamed_task__/MinReturn -38.1639 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.225778 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 472000 ------------------------------------------------- ------------- 2025-03-30 01:11:02 | [pearl_trainer] epoch #235 | Training... 2025-03-30 01:11:18 | [pearl_trainer] epoch #235 | Evaluating... 2025-03-30 01:11:18 | [pearl_trainer] epoch #235 | Sampling for adapation and meta-testing... 2025-03-30 01:12:29 | [pearl_trainer] epoch #235 | Finished meta-testing... 2025-03-30 01:12:29 | [pearl_trainer] epoch #235 | Saving snapshot... 2025-03-30 01:12:29 | [pearl_trainer] epoch #235 | Saved 2025-03-30 01:12:29 | [pearl_trainer] epoch #235 | Time 39774.29 s 2025-03-30 01:12:29 | [pearl_trainer] epoch #235 | EpochTime 151.32 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.2731 MetaTest/Average/AverageReturn -34.2731 MetaTest/Average/Iteration 235 MetaTest/Average/MaxReturn -30.6744 MetaTest/Average/MinReturn -37.8719 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.59878 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.2731 MetaTest/__unnamed_task__/AverageReturn -34.2731 MetaTest/__unnamed_task__/Iteration 235 MetaTest/__unnamed_task__/MaxReturn -30.6744 MetaTest/__unnamed_task__/MinReturn -37.8719 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.59878 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 474000 ------------------------------------------------- ------------ 2025-03-30 01:13:34 | [pearl_trainer] epoch #236 | Training... 2025-03-30 01:13:49 | [pearl_trainer] epoch #236 | Evaluating... 2025-03-30 01:13:49 | [pearl_trainer] epoch #236 | Sampling for adapation and meta-testing... 2025-03-30 01:14:59 | [pearl_trainer] epoch #236 | Finished meta-testing... 2025-03-30 01:14:59 | [pearl_trainer] epoch #236 | Saving snapshot... 2025-03-30 01:15:00 | [pearl_trainer] epoch #236 | Saved 2025-03-30 01:15:00 | [pearl_trainer] epoch #236 | Time 39925.09 s 2025-03-30 01:15:00 | [pearl_trainer] epoch #236 | EpochTime 150.80 s ------------------------------------------------- -------------- MetaTest/Average/AverageDiscountedReturn -30.3965 MetaTest/Average/AverageReturn -30.3965 MetaTest/Average/Iteration 236 MetaTest/Average/MaxReturn -30.3854 MetaTest/Average/MinReturn -30.4076 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.0111367 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -30.3965 MetaTest/__unnamed_task__/AverageReturn -30.3965 MetaTest/__unnamed_task__/Iteration 236 MetaTest/__unnamed_task__/MaxReturn -30.3854 MetaTest/__unnamed_task__/MinReturn -30.4076 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.0111367 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 476000 ------------------------------------------------- -------------- 2025-03-30 01:16:04 | [pearl_trainer] epoch #237 | Training... 2025-03-30 01:16:19 | [pearl_trainer] epoch #237 | Evaluating... 2025-03-30 01:16:19 | [pearl_trainer] epoch #237 | Sampling for adapation and meta-testing... 2025-03-30 01:17:29 | [pearl_trainer] epoch #237 | Finished meta-testing... 2025-03-30 01:17:29 | [pearl_trainer] epoch #237 | Saving snapshot... 2025-03-30 01:17:30 | [pearl_trainer] epoch #237 | Saved 2025-03-30 01:17:30 | [pearl_trainer] epoch #237 | Time 40075.23 s 2025-03-30 01:17:30 | [pearl_trainer] epoch #237 | EpochTime 150.14 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -44.6267 MetaTest/Average/AverageReturn -44.6267 MetaTest/Average/Iteration 237 MetaTest/Average/MaxReturn -39.6864 MetaTest/Average/MinReturn -49.567 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.94031 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -44.6267 MetaTest/__unnamed_task__/AverageReturn -44.6267 MetaTest/__unnamed_task__/Iteration 237 MetaTest/__unnamed_task__/MaxReturn -39.6864 MetaTest/__unnamed_task__/MinReturn -49.567 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.94031 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 478000 ------------------------------------------------- ------------ 2025-03-30 01:18:34 | [pearl_trainer] epoch #238 | Training... 2025-03-30 01:18:50 | [pearl_trainer] epoch #238 | Evaluating... 2025-03-30 01:18:50 | [pearl_trainer] epoch #238 | Sampling for adapation and meta-testing... 2025-03-30 01:20:00 | [pearl_trainer] epoch #238 | Finished meta-testing... 2025-03-30 01:20:00 | [pearl_trainer] epoch #238 | Saving snapshot... 2025-03-30 01:20:01 | [pearl_trainer] epoch #238 | Saved 2025-03-30 01:20:01 | [pearl_trainer] epoch #238 | Time 40226.05 s 2025-03-30 01:20:01 | [pearl_trainer] epoch #238 | EpochTime 150.82 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.2081 MetaTest/Average/AverageReturn -38.2081 MetaTest/Average/Iteration 238 MetaTest/Average/MaxReturn -37.2078 MetaTest/Average/MinReturn -39.2083 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.00025 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.2081 MetaTest/__unnamed_task__/AverageReturn -38.2081 MetaTest/__unnamed_task__/Iteration 238 MetaTest/__unnamed_task__/MaxReturn -37.2078 MetaTest/__unnamed_task__/MinReturn -39.2083 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.00025 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 480000 ------------------------------------------------- ------------ 2025-03-30 01:21:05 | [pearl_trainer] epoch #239 | Training... 2025-03-30 01:21:21 | [pearl_trainer] epoch #239 | Evaluating... 2025-03-30 01:21:21 | [pearl_trainer] epoch #239 | Sampling for adapation and meta-testing... 2025-03-30 01:22:31 | [pearl_trainer] epoch #239 | Finished meta-testing... 2025-03-30 01:22:31 | [pearl_trainer] epoch #239 | Saving snapshot... 2025-03-30 01:22:32 | [pearl_trainer] epoch #239 | Saved 2025-03-30 01:22:32 | [pearl_trainer] epoch #239 | Time 40377.02 s 2025-03-30 01:22:32 | [pearl_trainer] epoch #239 | EpochTime 150.97 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -31.9625 MetaTest/Average/AverageReturn -31.9625 MetaTest/Average/Iteration 239 MetaTest/Average/MaxReturn -27.205 MetaTest/Average/MinReturn -36.72 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.75751 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -31.9625 MetaTest/__unnamed_task__/AverageReturn -31.9625 MetaTest/__unnamed_task__/Iteration 239 MetaTest/__unnamed_task__/MaxReturn -27.205 MetaTest/__unnamed_task__/MinReturn -36.72 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.75751 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 482000 ------------------------------------------------- ------------ 2025-03-30 01:23:36 | [pearl_trainer] epoch #240 | Training... 2025-03-30 01:23:51 | [pearl_trainer] epoch #240 | Evaluating... 2025-03-30 01:23:51 | [pearl_trainer] epoch #240 | Sampling for adapation and meta-testing... 2025-03-30 01:25:02 | [pearl_trainer] epoch #240 | Finished meta-testing... 2025-03-30 01:25:02 | [pearl_trainer] epoch #240 | Saving snapshot... 2025-03-30 01:25:03 | [pearl_trainer] epoch #240 | Saved 2025-03-30 01:25:03 | [pearl_trainer] epoch #240 | Time 40528.08 s 2025-03-30 01:25:03 | [pearl_trainer] epoch #240 | EpochTime 151.06 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.1341 MetaTest/Average/AverageReturn -37.1341 MetaTest/Average/Iteration 240 MetaTest/Average/MaxReturn -34.5797 MetaTest/Average/MinReturn -39.6885 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.55442 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.1341 MetaTest/__unnamed_task__/AverageReturn -37.1341 MetaTest/__unnamed_task__/Iteration 240 MetaTest/__unnamed_task__/MaxReturn -34.5797 MetaTest/__unnamed_task__/MinReturn -39.6885 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.55442 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 484000 ------------------------------------------------- ------------ 2025-03-30 01:26:08 | [pearl_trainer] epoch #241 | Training... 2025-03-30 01:26:24 | [pearl_trainer] epoch #241 | Evaluating... 2025-03-30 01:26:24 | [pearl_trainer] epoch #241 | Sampling for adapation and meta-testing... 2025-03-30 01:27:35 | [pearl_trainer] epoch #241 | Finished meta-testing... 2025-03-30 01:27:35 | [pearl_trainer] epoch #241 | Saving snapshot... 2025-03-30 01:27:35 | [pearl_trainer] epoch #241 | Saved 2025-03-30 01:27:35 | [pearl_trainer] epoch #241 | Time 40680.33 s 2025-03-30 01:27:35 | [pearl_trainer] epoch #241 | EpochTime 152.25 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -31.0379 MetaTest/Average/AverageReturn -31.0379 MetaTest/Average/Iteration 241 MetaTest/Average/MaxReturn -28.9137 MetaTest/Average/MinReturn -33.1622 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.12423 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -31.0379 MetaTest/__unnamed_task__/AverageReturn -31.0379 MetaTest/__unnamed_task__/Iteration 241 MetaTest/__unnamed_task__/MaxReturn -28.9137 MetaTest/__unnamed_task__/MinReturn -33.1622 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.12423 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 486000 ------------------------------------------------- ------------ 2025-03-30 01:28:39 | [pearl_trainer] epoch #242 | Training... 2025-03-30 01:28:56 | [pearl_trainer] epoch #242 | Evaluating... 2025-03-30 01:28:56 | [pearl_trainer] epoch #242 | Sampling for adapation and meta-testing... 2025-03-30 01:30:05 | [pearl_trainer] epoch #242 | Finished meta-testing... 2025-03-30 01:30:05 | [pearl_trainer] epoch #242 | Saving snapshot... 2025-03-30 01:30:06 | [pearl_trainer] epoch #242 | Saved 2025-03-30 01:30:06 | [pearl_trainer] epoch #242 | Time 40830.94 s 2025-03-30 01:30:06 | [pearl_trainer] epoch #242 | EpochTime 150.61 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.5409 MetaTest/Average/AverageReturn -36.5409 MetaTest/Average/Iteration 242 MetaTest/Average/MaxReturn -33.6858 MetaTest/Average/MinReturn -39.3959 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.85506 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.5409 MetaTest/__unnamed_task__/AverageReturn -36.5409 MetaTest/__unnamed_task__/Iteration 242 MetaTest/__unnamed_task__/MaxReturn -33.6858 MetaTest/__unnamed_task__/MinReturn -39.3959 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.85506 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 488000 ------------------------------------------------- ------------ 2025-03-30 01:31:09 | [pearl_trainer] epoch #243 | Training... 2025-03-30 01:31:26 | [pearl_trainer] epoch #243 | Evaluating... 2025-03-30 01:31:26 | [pearl_trainer] epoch #243 | Sampling for adapation and meta-testing... 2025-03-30 01:32:37 | [pearl_trainer] epoch #243 | Finished meta-testing... 2025-03-30 01:32:37 | [pearl_trainer] epoch #243 | Saving snapshot... 2025-03-30 01:32:38 | [pearl_trainer] epoch #243 | Saved 2025-03-30 01:32:38 | [pearl_trainer] epoch #243 | Time 40982.89 s 2025-03-30 01:32:38 | [pearl_trainer] epoch #243 | EpochTime 151.95 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -36.856 MetaTest/Average/AverageReturn -36.856 MetaTest/Average/Iteration 243 MetaTest/Average/MaxReturn -35.856 MetaTest/Average/MinReturn -37.856 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.999957 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.856 MetaTest/__unnamed_task__/AverageReturn -36.856 MetaTest/__unnamed_task__/Iteration 243 MetaTest/__unnamed_task__/MaxReturn -35.856 MetaTest/__unnamed_task__/MinReturn -37.856 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.999957 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 490000 ------------------------------------------------- ------------- 2025-03-30 01:33:42 | [pearl_trainer] epoch #244 | Training... 2025-03-30 01:34:00 | [pearl_trainer] epoch #244 | Evaluating... 2025-03-30 01:34:00 | [pearl_trainer] epoch #244 | Sampling for adapation and meta-testing... 2025-03-30 01:35:11 | [pearl_trainer] epoch #244 | Finished meta-testing... 2025-03-30 01:35:11 | [pearl_trainer] epoch #244 | Saving snapshot... 2025-03-30 01:35:11 | [pearl_trainer] epoch #244 | Saved 2025-03-30 01:35:11 | [pearl_trainer] epoch #244 | Time 41136.29 s 2025-03-30 01:35:11 | [pearl_trainer] epoch #244 | EpochTime 153.40 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -41.6254 MetaTest/Average/AverageReturn -41.6254 MetaTest/Average/Iteration 244 MetaTest/Average/MaxReturn -39.3522 MetaTest/Average/MinReturn -43.8987 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.27328 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -41.6254 MetaTest/__unnamed_task__/AverageReturn -41.6254 MetaTest/__unnamed_task__/Iteration 244 MetaTest/__unnamed_task__/MaxReturn -39.3522 MetaTest/__unnamed_task__/MinReturn -43.8987 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.27328 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 492000 ------------------------------------------------- ------------ 2025-03-30 01:36:15 | [pearl_trainer] epoch #245 | Training... 2025-03-30 01:36:32 | [pearl_trainer] epoch #245 | Evaluating... 2025-03-30 01:36:32 | [pearl_trainer] epoch #245 | Sampling for adapation and meta-testing... 2025-03-30 01:37:42 | [pearl_trainer] epoch #245 | Finished meta-testing... 2025-03-30 01:37:42 | [pearl_trainer] epoch #245 | Saving snapshot... 2025-03-30 01:37:43 | [pearl_trainer] epoch #245 | Saved 2025-03-30 01:37:43 | [pearl_trainer] epoch #245 | Time 41287.60 s 2025-03-30 01:37:43 | [pearl_trainer] epoch #245 | EpochTime 151.31 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.6079 MetaTest/Average/AverageReturn -34.6079 MetaTest/Average/Iteration 245 MetaTest/Average/MaxReturn -32.6094 MetaTest/Average/MinReturn -36.6065 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.99859 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.6079 MetaTest/__unnamed_task__/AverageReturn -34.6079 MetaTest/__unnamed_task__/Iteration 245 MetaTest/__unnamed_task__/MaxReturn -32.6094 MetaTest/__unnamed_task__/MinReturn -36.6065 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.99859 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 494000 ------------------------------------------------- ------------ 2025-03-30 01:38:47 | [pearl_trainer] epoch #246 | Training... 2025-03-30 01:39:03 | [pearl_trainer] epoch #246 | Evaluating... 2025-03-30 01:39:03 | [pearl_trainer] epoch #246 | Sampling for adapation and meta-testing... 2025-03-30 01:40:13 | [pearl_trainer] epoch #246 | Finished meta-testing... 2025-03-30 01:40:13 | [pearl_trainer] epoch #246 | Saving snapshot... 2025-03-30 01:40:14 | [pearl_trainer] epoch #246 | Saved 2025-03-30 01:40:14 | [pearl_trainer] epoch #246 | Time 41438.65 s 2025-03-30 01:40:14 | [pearl_trainer] epoch #246 | EpochTime 151.05 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.142 MetaTest/Average/AverageReturn -33.142 MetaTest/Average/Iteration 246 MetaTest/Average/MaxReturn -31.4063 MetaTest/Average/MinReturn -34.8777 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.73569 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.142 MetaTest/__unnamed_task__/AverageReturn -33.142 MetaTest/__unnamed_task__/Iteration 246 MetaTest/__unnamed_task__/MaxReturn -31.4063 MetaTest/__unnamed_task__/MinReturn -34.8777 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.73569 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 496000 ------------------------------------------------- ------------ 2025-03-30 01:41:18 | [pearl_trainer] epoch #247 | Training... 2025-03-30 01:41:33 | [pearl_trainer] epoch #247 | Evaluating... 2025-03-30 01:41:33 | [pearl_trainer] epoch #247 | Sampling for adapation and meta-testing... 2025-03-30 01:42:44 | [pearl_trainer] epoch #247 | Finished meta-testing... 2025-03-30 01:42:44 | [pearl_trainer] epoch #247 | Saving snapshot... 2025-03-30 01:42:45 | [pearl_trainer] epoch #247 | Saved 2025-03-30 01:42:45 | [pearl_trainer] epoch #247 | Time 41590.17 s 2025-03-30 01:42:45 | [pearl_trainer] epoch #247 | EpochTime 151.51 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -37.236 MetaTest/Average/AverageReturn -37.236 MetaTest/Average/Iteration 247 MetaTest/Average/MaxReturn -36.9741 MetaTest/Average/MinReturn -37.4979 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.261934 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.236 MetaTest/__unnamed_task__/AverageReturn -37.236 MetaTest/__unnamed_task__/Iteration 247 MetaTest/__unnamed_task__/MaxReturn -36.9741 MetaTest/__unnamed_task__/MinReturn -37.4979 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.261934 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 498000 ------------------------------------------------- ------------- 2025-03-30 01:43:50 | [pearl_trainer] epoch #248 | Training... 2025-03-30 01:44:06 | [pearl_trainer] epoch #248 | Evaluating... 2025-03-30 01:44:06 | [pearl_trainer] epoch #248 | Sampling for adapation and meta-testing... 2025-03-30 01:45:17 | [pearl_trainer] epoch #248 | Finished meta-testing... 2025-03-30 01:45:17 | [pearl_trainer] epoch #248 | Saving snapshot... 2025-03-30 01:45:18 | [pearl_trainer] epoch #248 | Saved 2025-03-30 01:45:18 | [pearl_trainer] epoch #248 | Time 41742.59 s 2025-03-30 01:45:18 | [pearl_trainer] epoch #248 | EpochTime 152.42 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.6303 MetaTest/Average/AverageReturn -35.6303 MetaTest/Average/Iteration 248 MetaTest/Average/MaxReturn -33.1439 MetaTest/Average/MinReturn -38.1166 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.48636 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.6303 MetaTest/__unnamed_task__/AverageReturn -35.6303 MetaTest/__unnamed_task__/Iteration 248 MetaTest/__unnamed_task__/MaxReturn -33.1439 MetaTest/__unnamed_task__/MinReturn -38.1166 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.48636 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 500000 ------------------------------------------------- ------------ 2025-03-30 01:46:22 | [pearl_trainer] epoch #249 | Training... 2025-03-30 01:46:38 | [pearl_trainer] epoch #249 | Evaluating... 2025-03-30 01:46:38 | [pearl_trainer] epoch #249 | Sampling for adapation and meta-testing... 2025-03-30 01:47:49 | [pearl_trainer] epoch #249 | Finished meta-testing... 2025-03-30 01:47:49 | [pearl_trainer] epoch #249 | Saving snapshot... 2025-03-30 01:47:50 | [pearl_trainer] epoch #249 | Saved 2025-03-30 01:47:50 | [pearl_trainer] epoch #249 | Time 41894.66 s 2025-03-30 01:47:50 | [pearl_trainer] epoch #249 | EpochTime 152.07 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.7083 MetaTest/Average/AverageReturn -33.7083 MetaTest/Average/Iteration 249 MetaTest/Average/MaxReturn -29.1596 MetaTest/Average/MinReturn -38.257 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.54869 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.7083 MetaTest/__unnamed_task__/AverageReturn -33.7083 MetaTest/__unnamed_task__/Iteration 249 MetaTest/__unnamed_task__/MaxReturn -29.1596 MetaTest/__unnamed_task__/MinReturn -38.257 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.54869 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 502000 ------------------------------------------------- ------------ 2025-03-30 01:48:55 | [pearl_trainer] epoch #250 | Training... 2025-03-30 01:49:11 | [pearl_trainer] epoch #250 | Evaluating... 2025-03-30 01:49:11 | [pearl_trainer] epoch #250 | Sampling for adapation and meta-testing... 2025-03-30 01:50:21 | [pearl_trainer] epoch #250 | Finished meta-testing... 2025-03-30 01:50:21 | [pearl_trainer] epoch #250 | Saving snapshot... 2025-03-30 01:50:22 | [pearl_trainer] epoch #250 | Saved 2025-03-30 01:50:22 | [pearl_trainer] epoch #250 | Time 42046.64 s 2025-03-30 01:50:22 | [pearl_trainer] epoch #250 | EpochTime 151.98 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.3271 MetaTest/Average/AverageReturn -35.3271 MetaTest/Average/Iteration 250 MetaTest/Average/MaxReturn -33.9713 MetaTest/Average/MinReturn -36.6829 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.35577 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.3271 MetaTest/__unnamed_task__/AverageReturn -35.3271 MetaTest/__unnamed_task__/Iteration 250 MetaTest/__unnamed_task__/MaxReturn -33.9713 MetaTest/__unnamed_task__/MinReturn -36.6829 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.35577 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 504000 ------------------------------------------------- ------------ 2025-03-30 01:51:26 | [pearl_trainer] epoch #251 | Training... 2025-03-30 01:51:42 | [pearl_trainer] epoch #251 | Evaluating... 2025-03-30 01:51:42 | [pearl_trainer] epoch #251 | Sampling for adapation and meta-testing... 2025-03-30 01:52:53 | [pearl_trainer] epoch #251 | Finished meta-testing... 2025-03-30 01:52:53 | [pearl_trainer] epoch #251 | Saving snapshot... 2025-03-30 01:52:54 | [pearl_trainer] epoch #251 | Saved 2025-03-30 01:52:54 | [pearl_trainer] epoch #251 | Time 42198.63 s 2025-03-30 01:52:54 | [pearl_trainer] epoch #251 | EpochTime 151.99 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.5565 MetaTest/Average/AverageReturn -33.5565 MetaTest/Average/Iteration 251 MetaTest/Average/MaxReturn -28.8765 MetaTest/Average/MinReturn -38.2366 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.68009 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.5565 MetaTest/__unnamed_task__/AverageReturn -33.5565 MetaTest/__unnamed_task__/Iteration 251 MetaTest/__unnamed_task__/MaxReturn -28.8765 MetaTest/__unnamed_task__/MinReturn -38.2366 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.68009 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 506000 ------------------------------------------------- ------------ 2025-03-30 01:53:58 | [pearl_trainer] epoch #252 | Training... 2025-03-30 01:54:14 | [pearl_trainer] epoch #252 | Evaluating... 2025-03-30 01:54:14 | [pearl_trainer] epoch #252 | Sampling for adapation and meta-testing... 2025-03-30 01:55:23 | [pearl_trainer] epoch #252 | Finished meta-testing... 2025-03-30 01:55:23 | [pearl_trainer] epoch #252 | Saving snapshot... 2025-03-30 01:55:24 | [pearl_trainer] epoch #252 | Saved 2025-03-30 01:55:24 | [pearl_trainer] epoch #252 | Time 42349.18 s 2025-03-30 01:55:24 | [pearl_trainer] epoch #252 | EpochTime 150.55 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.3234 MetaTest/Average/AverageReturn -36.3234 MetaTest/Average/Iteration 252 MetaTest/Average/MaxReturn -33.4265 MetaTest/Average/MinReturn -39.2202 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.89683 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.3234 MetaTest/__unnamed_task__/AverageReturn -36.3234 MetaTest/__unnamed_task__/Iteration 252 MetaTest/__unnamed_task__/MaxReturn -33.4265 MetaTest/__unnamed_task__/MinReturn -39.2202 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.89683 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 508000 ------------------------------------------------- ------------ 2025-03-30 01:56:28 | [pearl_trainer] epoch #253 | Training... 2025-03-30 01:56:43 | [pearl_trainer] epoch #253 | Evaluating... 2025-03-30 01:56:43 | [pearl_trainer] epoch #253 | Sampling for adapation and meta-testing... 2025-03-30 01:57:53 | [pearl_trainer] epoch #253 | Finished meta-testing... 2025-03-30 01:57:53 | [pearl_trainer] epoch #253 | Saving snapshot... 2025-03-30 01:57:54 | [pearl_trainer] epoch #253 | Saved 2025-03-30 01:57:54 | [pearl_trainer] epoch #253 | Time 42499.43 s 2025-03-30 01:57:54 | [pearl_trainer] epoch #253 | EpochTime 150.25 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.8375 MetaTest/Average/AverageReturn -35.8375 MetaTest/Average/Iteration 253 MetaTest/Average/MaxReturn -35.5933 MetaTest/Average/MinReturn -36.0816 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.244176 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.8375 MetaTest/__unnamed_task__/AverageReturn -35.8375 MetaTest/__unnamed_task__/Iteration 253 MetaTest/__unnamed_task__/MaxReturn -35.5933 MetaTest/__unnamed_task__/MinReturn -36.0816 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.244176 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 510000 ------------------------------------------------- ------------- 2025-03-30 01:58:59 | [pearl_trainer] epoch #254 | Training... 2025-03-30 01:59:17 | [pearl_trainer] epoch #254 | Evaluating... 2025-03-30 01:59:17 | [pearl_trainer] epoch #254 | Sampling for adapation and meta-testing... 2025-03-30 02:00:28 | [pearl_trainer] epoch #254 | Finished meta-testing... 2025-03-30 02:00:28 | [pearl_trainer] epoch #254 | Saving snapshot... 2025-03-30 02:00:29 | [pearl_trainer] epoch #254 | Saved 2025-03-30 02:00:29 | [pearl_trainer] epoch #254 | Time 42653.49 s 2025-03-30 02:00:29 | [pearl_trainer] epoch #254 | EpochTime 154.05 s ------------------------------------------------- -------------- MetaTest/Average/AverageDiscountedReturn -35.1325 MetaTest/Average/AverageReturn -35.1325 MetaTest/Average/Iteration 254 MetaTest/Average/MaxReturn -35.0807 MetaTest/Average/MinReturn -35.1842 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.0517552 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.1325 MetaTest/__unnamed_task__/AverageReturn -35.1325 MetaTest/__unnamed_task__/Iteration 254 MetaTest/__unnamed_task__/MaxReturn -35.0807 MetaTest/__unnamed_task__/MinReturn -35.1842 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.0517552 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 512000 ------------------------------------------------- -------------- 2025-03-30 02:01:33 | [pearl_trainer] epoch #255 | Training... 2025-03-30 02:01:51 | [pearl_trainer] epoch #255 | Evaluating... 2025-03-30 02:01:51 | [pearl_trainer] epoch #255 | Sampling for adapation and meta-testing... 2025-03-30 02:03:02 | [pearl_trainer] epoch #255 | Finished meta-testing... 2025-03-30 02:03:02 | [pearl_trainer] epoch #255 | Saving snapshot... 2025-03-30 02:03:03 | [pearl_trainer] epoch #255 | Saved 2025-03-30 02:03:03 | [pearl_trainer] epoch #255 | Time 42807.82 s 2025-03-30 02:03:03 | [pearl_trainer] epoch #255 | EpochTime 154.33 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -40.9341 MetaTest/Average/AverageReturn -40.9341 MetaTest/Average/Iteration 255 MetaTest/Average/MaxReturn -40.8855 MetaTest/Average/MinReturn -40.9827 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.048596 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -40.9341 MetaTest/__unnamed_task__/AverageReturn -40.9341 MetaTest/__unnamed_task__/Iteration 255 MetaTest/__unnamed_task__/MaxReturn -40.8855 MetaTest/__unnamed_task__/MinReturn -40.9827 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.048596 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 514000 ------------------------------------------------- ------------- 2025-03-30 02:04:07 | [pearl_trainer] epoch #256 | Training... 2025-03-30 02:04:24 | [pearl_trainer] epoch #256 | Evaluating... 2025-03-30 02:04:24 | [pearl_trainer] epoch #256 | Sampling for adapation and meta-testing... 2025-03-30 02:05:33 | [pearl_trainer] epoch #256 | Finished meta-testing... 2025-03-30 02:05:33 | [pearl_trainer] epoch #256 | Saving snapshot... 2025-03-30 02:05:34 | [pearl_trainer] epoch #256 | Saved 2025-03-30 02:05:34 | [pearl_trainer] epoch #256 | Time 42959.42 s 2025-03-30 02:05:34 | [pearl_trainer] epoch #256 | EpochTime 151.60 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.5401 MetaTest/Average/AverageReturn -35.5401 MetaTest/Average/Iteration 256 MetaTest/Average/MaxReturn -31.4574 MetaTest/Average/MinReturn -39.6229 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.08277 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.5401 MetaTest/__unnamed_task__/AverageReturn -35.5401 MetaTest/__unnamed_task__/Iteration 256 MetaTest/__unnamed_task__/MaxReturn -31.4574 MetaTest/__unnamed_task__/MinReturn -39.6229 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.08277 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 516000 ------------------------------------------------- ------------ 2025-03-30 02:06:38 | [pearl_trainer] epoch #257 | Training... 2025-03-30 02:06:54 | [pearl_trainer] epoch #257 | Evaluating... 2025-03-30 02:06:54 | [pearl_trainer] epoch #257 | Sampling for adapation and meta-testing... 2025-03-30 02:08:04 | [pearl_trainer] epoch #257 | Finished meta-testing... 2025-03-30 02:08:04 | [pearl_trainer] epoch #257 | Saving snapshot... 2025-03-30 02:08:05 | [pearl_trainer] epoch #257 | Saved 2025-03-30 02:08:05 | [pearl_trainer] epoch #257 | Time 43109.91 s 2025-03-30 02:08:05 | [pearl_trainer] epoch #257 | EpochTime 150.49 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.6632 MetaTest/Average/AverageReturn -36.6632 MetaTest/Average/Iteration 257 MetaTest/Average/MaxReturn -33.4715 MetaTest/Average/MinReturn -39.855 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.19173 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.6632 MetaTest/__unnamed_task__/AverageReturn -36.6632 MetaTest/__unnamed_task__/Iteration 257 MetaTest/__unnamed_task__/MaxReturn -33.4715 MetaTest/__unnamed_task__/MinReturn -39.855 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.19173 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 518000 ------------------------------------------------- ------------ 2025-03-30 02:09:09 | [pearl_trainer] epoch #258 | Training... 2025-03-30 02:09:24 | [pearl_trainer] epoch #258 | Evaluating... 2025-03-30 02:09:24 | [pearl_trainer] epoch #258 | Sampling for adapation and meta-testing... 2025-03-30 02:10:34 | [pearl_trainer] epoch #258 | Finished meta-testing... 2025-03-30 02:10:34 | [pearl_trainer] epoch #258 | Saving snapshot... 2025-03-30 02:10:35 | [pearl_trainer] epoch #258 | Saved 2025-03-30 02:10:35 | [pearl_trainer] epoch #258 | Time 43259.94 s 2025-03-30 02:10:35 | [pearl_trainer] epoch #258 | EpochTime 150.02 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.9702 MetaTest/Average/AverageReturn -35.9702 MetaTest/Average/Iteration 258 MetaTest/Average/MaxReturn -34.59 MetaTest/Average/MinReturn -37.3504 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.38024 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.9702 MetaTest/__unnamed_task__/AverageReturn -35.9702 MetaTest/__unnamed_task__/Iteration 258 MetaTest/__unnamed_task__/MaxReturn -34.59 MetaTest/__unnamed_task__/MinReturn -37.3504 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.38024 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 520000 ------------------------------------------------- ------------ 2025-03-30 02:11:39 | [pearl_trainer] epoch #259 | Training... 2025-03-30 02:11:54 | [pearl_trainer] epoch #259 | Evaluating... 2025-03-30 02:11:54 | [pearl_trainer] epoch #259 | Sampling for adapation and meta-testing... 2025-03-30 02:13:04 | [pearl_trainer] epoch #259 | Finished meta-testing... 2025-03-30 02:13:04 | [pearl_trainer] epoch #259 | Saving snapshot... 2025-03-30 02:13:05 | [pearl_trainer] epoch #259 | Saved 2025-03-30 02:13:05 | [pearl_trainer] epoch #259 | Time 43409.60 s 2025-03-30 02:13:05 | [pearl_trainer] epoch #259 | EpochTime 149.66 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.7852 MetaTest/Average/AverageReturn -38.7852 MetaTest/Average/Iteration 259 MetaTest/Average/MaxReturn -37.3275 MetaTest/Average/MinReturn -40.2429 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.45771 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.7852 MetaTest/__unnamed_task__/AverageReturn -38.7852 MetaTest/__unnamed_task__/Iteration 259 MetaTest/__unnamed_task__/MaxReturn -37.3275 MetaTest/__unnamed_task__/MinReturn -40.2429 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.45771 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 522000 ------------------------------------------------- ------------ 2025-03-30 02:14:09 | [pearl_trainer] epoch #260 | Training... 2025-03-30 02:14:25 | [pearl_trainer] epoch #260 | Evaluating... 2025-03-30 02:14:25 | [pearl_trainer] epoch #260 | Sampling for adapation and meta-testing... 2025-03-30 02:15:35 | [pearl_trainer] epoch #260 | Finished meta-testing... 2025-03-30 02:15:35 | [pearl_trainer] epoch #260 | Saving snapshot... 2025-03-30 02:15:35 | [pearl_trainer] epoch #260 | Saved 2025-03-30 02:15:35 | [pearl_trainer] epoch #260 | Time 43560.27 s 2025-03-30 02:15:35 | [pearl_trainer] epoch #260 | EpochTime 150.67 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -36.8476 MetaTest/Average/AverageReturn -36.8476 MetaTest/Average/Iteration 260 MetaTest/Average/MaxReturn -33.9136 MetaTest/Average/MinReturn -39.7816 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.934 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.8476 MetaTest/__unnamed_task__/AverageReturn -36.8476 MetaTest/__unnamed_task__/Iteration 260 MetaTest/__unnamed_task__/MaxReturn -33.9136 MetaTest/__unnamed_task__/MinReturn -39.7816 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.934 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 524000 ------------------------------------------------- ----------- 2025-03-30 02:16:39 | [pearl_trainer] epoch #261 | Training... 2025-03-30 02:16:55 | [pearl_trainer] epoch #261 | Evaluating... 2025-03-30 02:16:55 | [pearl_trainer] epoch #261 | Sampling for adapation and meta-testing... 2025-03-30 02:18:05 | [pearl_trainer] epoch #261 | Finished meta-testing... 2025-03-30 02:18:05 | [pearl_trainer] epoch #261 | Saving snapshot... 2025-03-30 02:18:06 | [pearl_trainer] epoch #261 | Saved 2025-03-30 02:18:06 | [pearl_trainer] epoch #261 | Time 43710.78 s 2025-03-30 02:18:06 | [pearl_trainer] epoch #261 | EpochTime 150.50 s ------------------------------------------------- -------------- MetaTest/Average/AverageDiscountedReturn -39.2695 MetaTest/Average/AverageReturn -39.2695 MetaTest/Average/Iteration 261 MetaTest/Average/MaxReturn -39.2159 MetaTest/Average/MinReturn -39.3231 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.0535911 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -39.2695 MetaTest/__unnamed_task__/AverageReturn -39.2695 MetaTest/__unnamed_task__/Iteration 261 MetaTest/__unnamed_task__/MaxReturn -39.2159 MetaTest/__unnamed_task__/MinReturn -39.3231 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.0535911 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 526000 ------------------------------------------------- -------------- 2025-03-30 02:19:10 | [pearl_trainer] epoch #262 | Training... 2025-03-30 02:19:27 | [pearl_trainer] epoch #262 | Evaluating... 2025-03-30 02:19:27 | [pearl_trainer] epoch #262 | Sampling for adapation and meta-testing... 2025-03-30 02:20:36 | [pearl_trainer] epoch #262 | Finished meta-testing... 2025-03-30 02:20:36 | [pearl_trainer] epoch #262 | Saving snapshot... 2025-03-30 02:20:38 | [pearl_trainer] epoch #262 | Saved 2025-03-30 02:20:38 | [pearl_trainer] epoch #262 | Time 43862.45 s 2025-03-30 02:20:38 | [pearl_trainer] epoch #262 | EpochTime 151.67 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.4657 MetaTest/Average/AverageReturn -36.4657 MetaTest/Average/Iteration 262 MetaTest/Average/MaxReturn -33.2497 MetaTest/Average/MinReturn -39.6817 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.21603 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.4657 MetaTest/__unnamed_task__/AverageReturn -36.4657 MetaTest/__unnamed_task__/Iteration 262 MetaTest/__unnamed_task__/MaxReturn -33.2497 MetaTest/__unnamed_task__/MinReturn -39.6817 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.21603 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 528000 ------------------------------------------------- ------------ 2025-03-30 02:21:41 | [pearl_trainer] epoch #263 | Training... 2025-03-30 02:21:59 | [pearl_trainer] epoch #263 | Evaluating... 2025-03-30 02:21:59 | [pearl_trainer] epoch #263 | Sampling for adapation and meta-testing... 2025-03-30 02:23:10 | [pearl_trainer] epoch #263 | Finished meta-testing... 2025-03-30 02:23:10 | [pearl_trainer] epoch #263 | Saving snapshot... 2025-03-30 02:23:11 | [pearl_trainer] epoch #263 | Saved 2025-03-30 02:23:11 | [pearl_trainer] epoch #263 | Time 44015.92 s 2025-03-30 02:23:11 | [pearl_trainer] epoch #263 | EpochTime 153.48 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -33.0779 MetaTest/Average/AverageReturn -33.0779 MetaTest/Average/Iteration 263 MetaTest/Average/MaxReturn -32.418 MetaTest/Average/MinReturn -33.7378 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.659938 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.0779 MetaTest/__unnamed_task__/AverageReturn -33.0779 MetaTest/__unnamed_task__/Iteration 263 MetaTest/__unnamed_task__/MaxReturn -32.418 MetaTest/__unnamed_task__/MinReturn -33.7378 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.659938 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 530000 ------------------------------------------------- ------------- 2025-03-30 02:24:15 | [pearl_trainer] epoch #264 | Training... 2025-03-30 02:24:33 | [pearl_trainer] epoch #264 | Evaluating... 2025-03-30 02:24:33 | [pearl_trainer] epoch #264 | Sampling for adapation and meta-testing... 2025-03-30 02:25:44 | [pearl_trainer] epoch #264 | Finished meta-testing... 2025-03-30 02:25:44 | [pearl_trainer] epoch #264 | Saving snapshot... 2025-03-30 02:25:45 | [pearl_trainer] epoch #264 | Saved 2025-03-30 02:25:45 | [pearl_trainer] epoch #264 | Time 44169.57 s 2025-03-30 02:25:45 | [pearl_trainer] epoch #264 | EpochTime 153.65 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -36.4013 MetaTest/Average/AverageReturn -36.4013 MetaTest/Average/Iteration 264 MetaTest/Average/MaxReturn -35.7709 MetaTest/Average/MinReturn -37.0317 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.630378 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.4013 MetaTest/__unnamed_task__/AverageReturn -36.4013 MetaTest/__unnamed_task__/Iteration 264 MetaTest/__unnamed_task__/MaxReturn -35.7709 MetaTest/__unnamed_task__/MinReturn -37.0317 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.630378 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 532000 ------------------------------------------------- ------------- 2025-03-30 02:26:49 | [pearl_trainer] epoch #265 | Training... 2025-03-30 02:27:06 | [pearl_trainer] epoch #265 | Evaluating... 2025-03-30 02:27:06 | [pearl_trainer] epoch #265 | Sampling for adapation and meta-testing... 2025-03-30 02:28:17 | [pearl_trainer] epoch #265 | Finished meta-testing... 2025-03-30 02:28:17 | [pearl_trainer] epoch #265 | Saving snapshot... 2025-03-30 02:28:18 | [pearl_trainer] epoch #265 | Saved 2025-03-30 02:28:18 | [pearl_trainer] epoch #265 | Time 44322.54 s 2025-03-30 02:28:18 | [pearl_trainer] epoch #265 | EpochTime 152.96 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -41.0141 MetaTest/Average/AverageReturn -41.0141 MetaTest/Average/Iteration 265 MetaTest/Average/MaxReturn -39.9572 MetaTest/Average/MinReturn -42.0709 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.05682 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -41.0141 MetaTest/__unnamed_task__/AverageReturn -41.0141 MetaTest/__unnamed_task__/Iteration 265 MetaTest/__unnamed_task__/MaxReturn -39.9572 MetaTest/__unnamed_task__/MinReturn -42.0709 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.05682 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 534000 ------------------------------------------------- ------------ 2025-03-30 02:29:22 | [pearl_trainer] epoch #266 | Training... 2025-03-30 02:29:40 | [pearl_trainer] epoch #266 | Evaluating... 2025-03-30 02:29:40 | [pearl_trainer] epoch #266 | Sampling for adapation and meta-testing... 2025-03-30 02:30:50 | [pearl_trainer] epoch #266 | Finished meta-testing... 2025-03-30 02:30:50 | [pearl_trainer] epoch #266 | Saving snapshot... 2025-03-30 02:30:50 | [pearl_trainer] epoch #266 | Saved 2025-03-30 02:30:50 | [pearl_trainer] epoch #266 | Time 44475.44 s 2025-03-30 02:30:50 | [pearl_trainer] epoch #266 | EpochTime 152.90 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.8676 MetaTest/Average/AverageReturn -34.8676 MetaTest/Average/Iteration 266 MetaTest/Average/MaxReturn -31.6613 MetaTest/Average/MinReturn -38.0739 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.20633 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.8676 MetaTest/__unnamed_task__/AverageReturn -34.8676 MetaTest/__unnamed_task__/Iteration 266 MetaTest/__unnamed_task__/MaxReturn -31.6613 MetaTest/__unnamed_task__/MinReturn -38.0739 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.20633 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 536000 ------------------------------------------------- ------------ 2025-03-30 02:31:54 | [pearl_trainer] epoch #267 | Training... 2025-03-30 02:32:11 | [pearl_trainer] epoch #267 | Evaluating... 2025-03-30 02:32:11 | [pearl_trainer] epoch #267 | Sampling for adapation and meta-testing... 2025-03-30 02:33:21 | [pearl_trainer] epoch #267 | Finished meta-testing... 2025-03-30 02:33:21 | [pearl_trainer] epoch #267 | Saving snapshot... 2025-03-30 02:33:22 | [pearl_trainer] epoch #267 | Saved 2025-03-30 02:33:22 | [pearl_trainer] epoch #267 | Time 44626.74 s 2025-03-30 02:33:22 | [pearl_trainer] epoch #267 | EpochTime 151.30 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.121 MetaTest/Average/AverageReturn -36.121 MetaTest/Average/Iteration 267 MetaTest/Average/MaxReturn -33.5943 MetaTest/Average/MinReturn -38.6477 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.52668 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.121 MetaTest/__unnamed_task__/AverageReturn -36.121 MetaTest/__unnamed_task__/Iteration 267 MetaTest/__unnamed_task__/MaxReturn -33.5943 MetaTest/__unnamed_task__/MinReturn -38.6477 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.52668 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 538000 ------------------------------------------------- ------------ 2025-03-30 02:34:25 | [pearl_trainer] epoch #268 | Training... 2025-03-30 02:34:42 | [pearl_trainer] epoch #268 | Evaluating... 2025-03-30 02:34:42 | [pearl_trainer] epoch #268 | Sampling for adapation and meta-testing... 2025-03-30 02:35:52 | [pearl_trainer] epoch #268 | Finished meta-testing... 2025-03-30 02:35:52 | [pearl_trainer] epoch #268 | Saving snapshot... 2025-03-30 02:35:53 | [pearl_trainer] epoch #268 | Saved 2025-03-30 02:35:53 | [pearl_trainer] epoch #268 | Time 44777.67 s 2025-03-30 02:35:53 | [pearl_trainer] epoch #268 | EpochTime 150.93 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.6901 MetaTest/Average/AverageReturn -37.6901 MetaTest/Average/Iteration 268 MetaTest/Average/MaxReturn -34.2524 MetaTest/Average/MinReturn -41.1278 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.43774 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.6901 MetaTest/__unnamed_task__/AverageReturn -37.6901 MetaTest/__unnamed_task__/Iteration 268 MetaTest/__unnamed_task__/MaxReturn -34.2524 MetaTest/__unnamed_task__/MinReturn -41.1278 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.43774 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 540000 ------------------------------------------------- ------------ 2025-03-30 02:36:56 | [pearl_trainer] epoch #269 | Training... 2025-03-30 02:37:14 | [pearl_trainer] epoch #269 | Evaluating... 2025-03-30 02:37:14 | [pearl_trainer] epoch #269 | Sampling for adapation and meta-testing... 2025-03-30 02:38:24 | [pearl_trainer] epoch #269 | Finished meta-testing... 2025-03-30 02:38:24 | [pearl_trainer] epoch #269 | Saving snapshot... 2025-03-30 02:38:25 | [pearl_trainer] epoch #269 | Saved 2025-03-30 02:38:25 | [pearl_trainer] epoch #269 | Time 44929.69 s 2025-03-30 02:38:25 | [pearl_trainer] epoch #269 | EpochTime 152.02 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.5686 MetaTest/Average/AverageReturn -34.5686 MetaTest/Average/Iteration 269 MetaTest/Average/MaxReturn -32.584 MetaTest/Average/MinReturn -36.5532 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.98459 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.5686 MetaTest/__unnamed_task__/AverageReturn -34.5686 MetaTest/__unnamed_task__/Iteration 269 MetaTest/__unnamed_task__/MaxReturn -32.584 MetaTest/__unnamed_task__/MinReturn -36.5532 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.98459 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 542000 ------------------------------------------------- ------------ 2025-03-30 02:39:28 | [pearl_trainer] epoch #270 | Training... 2025-03-30 02:39:46 | [pearl_trainer] epoch #270 | Evaluating... 2025-03-30 02:39:46 | [pearl_trainer] epoch #270 | Sampling for adapation and meta-testing... 2025-03-30 02:40:55 | [pearl_trainer] epoch #270 | Finished meta-testing... 2025-03-30 02:40:55 | [pearl_trainer] epoch #270 | Saving snapshot... 2025-03-30 02:40:56 | [pearl_trainer] epoch #270 | Saved 2025-03-30 02:40:56 | [pearl_trainer] epoch #270 | Time 45080.77 s 2025-03-30 02:40:56 | [pearl_trainer] epoch #270 | EpochTime 151.08 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.5943 MetaTest/Average/AverageReturn -36.5943 MetaTest/Average/Iteration 270 MetaTest/Average/MaxReturn -33.6016 MetaTest/Average/MinReturn -39.5871 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.99278 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.5943 MetaTest/__unnamed_task__/AverageReturn -36.5943 MetaTest/__unnamed_task__/Iteration 270 MetaTest/__unnamed_task__/MaxReturn -33.6016 MetaTest/__unnamed_task__/MinReturn -39.5871 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.99278 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 544000 ------------------------------------------------- ------------ 2025-03-30 02:42:00 | [pearl_trainer] epoch #271 | Training... 2025-03-30 02:42:17 | [pearl_trainer] epoch #271 | Evaluating... 2025-03-30 02:42:17 | [pearl_trainer] epoch #271 | Sampling for adapation and meta-testing... 2025-03-30 02:43:27 | [pearl_trainer] epoch #271 | Finished meta-testing... 2025-03-30 02:43:27 | [pearl_trainer] epoch #271 | Saving snapshot... 2025-03-30 02:43:29 | [pearl_trainer] epoch #271 | Saved 2025-03-30 02:43:29 | [pearl_trainer] epoch #271 | Time 45233.47 s 2025-03-30 02:43:29 | [pearl_trainer] epoch #271 | EpochTime 152.69 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -33.473 MetaTest/Average/AverageReturn -33.473 MetaTest/Average/Iteration 271 MetaTest/Average/MaxReturn -31.1101 MetaTest/Average/MinReturn -35.8359 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.36294 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -33.473 MetaTest/__unnamed_task__/AverageReturn -33.473 MetaTest/__unnamed_task__/Iteration 271 MetaTest/__unnamed_task__/MaxReturn -31.1101 MetaTest/__unnamed_task__/MinReturn -35.8359 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.36294 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 546000 ------------------------------------------------- ------------ 2025-03-30 02:44:33 | [pearl_trainer] epoch #272 | Training... 2025-03-30 02:44:50 | [pearl_trainer] epoch #272 | Evaluating... 2025-03-30 02:44:50 | [pearl_trainer] epoch #272 | Sampling for adapation and meta-testing... 2025-03-30 02:46:00 | [pearl_trainer] epoch #272 | Finished meta-testing... 2025-03-30 02:46:00 | [pearl_trainer] epoch #272 | Saving snapshot... 2025-03-30 02:46:01 | [pearl_trainer] epoch #272 | Saved 2025-03-30 02:46:01 | [pearl_trainer] epoch #272 | Time 45386.04 s 2025-03-30 02:46:01 | [pearl_trainer] epoch #272 | EpochTime 152.57 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.1989 MetaTest/Average/AverageReturn -36.1989 MetaTest/Average/Iteration 272 MetaTest/Average/MaxReturn -34.9619 MetaTest/Average/MinReturn -37.4359 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.23698 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.1989 MetaTest/__unnamed_task__/AverageReturn -36.1989 MetaTest/__unnamed_task__/Iteration 272 MetaTest/__unnamed_task__/MaxReturn -34.9619 MetaTest/__unnamed_task__/MinReturn -37.4359 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.23698 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 548000 ------------------------------------------------- ------------ 2025-03-30 02:47:05 | [pearl_trainer] epoch #273 | Training... 2025-03-30 02:47:21 | [pearl_trainer] epoch #273 | Evaluating... 2025-03-30 02:47:21 | [pearl_trainer] epoch #273 | Sampling for adapation and meta-testing... 2025-03-30 02:48:32 | [pearl_trainer] epoch #273 | Finished meta-testing... 2025-03-30 02:48:32 | [pearl_trainer] epoch #273 | Saving snapshot... 2025-03-30 02:48:33 | [pearl_trainer] epoch #273 | Saved 2025-03-30 02:48:33 | [pearl_trainer] epoch #273 | Time 45537.49 s 2025-03-30 02:48:33 | [pearl_trainer] epoch #273 | EpochTime 151.45 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.9218 MetaTest/Average/AverageReturn -36.9218 MetaTest/Average/Iteration 273 MetaTest/Average/MaxReturn -33.6275 MetaTest/Average/MinReturn -40.216 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.29429 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.9218 MetaTest/__unnamed_task__/AverageReturn -36.9218 MetaTest/__unnamed_task__/Iteration 273 MetaTest/__unnamed_task__/MaxReturn -33.6275 MetaTest/__unnamed_task__/MinReturn -40.216 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.29429 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 550000 ------------------------------------------------- ------------ 2025-03-30 02:49:36 | [pearl_trainer] epoch #274 | Training... 2025-03-30 02:49:52 | [pearl_trainer] epoch #274 | Evaluating... 2025-03-30 02:49:52 | [pearl_trainer] epoch #274 | Sampling for adapation and meta-testing... 2025-03-30 02:51:02 | [pearl_trainer] epoch #274 | Finished meta-testing... 2025-03-30 02:51:02 | [pearl_trainer] epoch #274 | Saving snapshot... 2025-03-30 02:51:03 | [pearl_trainer] epoch #274 | Saved 2025-03-30 02:51:03 | [pearl_trainer] epoch #274 | Time 45687.84 s 2025-03-30 02:51:03 | [pearl_trainer] epoch #274 | EpochTime 150.35 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.4584 MetaTest/Average/AverageReturn -35.4584 MetaTest/Average/Iteration 274 MetaTest/Average/MaxReturn -33.1776 MetaTest/Average/MinReturn -37.7391 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.28074 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.4584 MetaTest/__unnamed_task__/AverageReturn -35.4584 MetaTest/__unnamed_task__/Iteration 274 MetaTest/__unnamed_task__/MaxReturn -33.1776 MetaTest/__unnamed_task__/MinReturn -37.7391 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.28074 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 552000 ------------------------------------------------- ------------ 2025-03-30 02:52:07 | [pearl_trainer] epoch #275 | Training... 2025-03-30 02:52:23 | [pearl_trainer] epoch #275 | Evaluating... 2025-03-30 02:52:23 | [pearl_trainer] epoch #275 | Sampling for adapation and meta-testing... 2025-03-30 02:53:33 | [pearl_trainer] epoch #275 | Finished meta-testing... 2025-03-30 02:53:33 | [pearl_trainer] epoch #275 | Saving snapshot... 2025-03-30 02:53:34 | [pearl_trainer] epoch #275 | Saved 2025-03-30 02:53:34 | [pearl_trainer] epoch #275 | Time 45838.50 s 2025-03-30 02:53:34 | [pearl_trainer] epoch #275 | EpochTime 150.65 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.6126 MetaTest/Average/AverageReturn -34.6126 MetaTest/Average/Iteration 275 MetaTest/Average/MaxReturn -33.0679 MetaTest/Average/MinReturn -36.1572 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.54464 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.6126 MetaTest/__unnamed_task__/AverageReturn -34.6126 MetaTest/__unnamed_task__/Iteration 275 MetaTest/__unnamed_task__/MaxReturn -33.0679 MetaTest/__unnamed_task__/MinReturn -36.1572 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.54464 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 554000 ------------------------------------------------- ------------ 2025-03-30 02:54:37 | [pearl_trainer] epoch #276 | Training... 2025-03-30 02:54:53 | [pearl_trainer] epoch #276 | Evaluating... 2025-03-30 02:54:53 | [pearl_trainer] epoch #276 | Sampling for adapation and meta-testing... 2025-03-30 02:56:04 | [pearl_trainer] epoch #276 | Finished meta-testing... 2025-03-30 02:56:04 | [pearl_trainer] epoch #276 | Saving snapshot... 2025-03-30 02:56:04 | [pearl_trainer] epoch #276 | Saved 2025-03-30 02:56:04 | [pearl_trainer] epoch #276 | Time 45989.38 s 2025-03-30 02:56:04 | [pearl_trainer] epoch #276 | EpochTime 150.88 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -37.2782 MetaTest/Average/AverageReturn -37.2782 MetaTest/Average/Iteration 276 MetaTest/Average/MaxReturn -30.9977 MetaTest/Average/MinReturn -43.5588 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 6.28058 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -37.2782 MetaTest/__unnamed_task__/AverageReturn -37.2782 MetaTest/__unnamed_task__/Iteration 276 MetaTest/__unnamed_task__/MaxReturn -30.9977 MetaTest/__unnamed_task__/MinReturn -43.5588 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 6.28058 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 556000 ------------------------------------------------- ------------ 2025-03-30 02:57:08 | [pearl_trainer] epoch #277 | Training... 2025-03-30 02:57:24 | [pearl_trainer] epoch #277 | Evaluating... 2025-03-30 02:57:24 | [pearl_trainer] epoch #277 | Sampling for adapation and meta-testing... 2025-03-30 02:58:35 | [pearl_trainer] epoch #277 | Finished meta-testing... 2025-03-30 02:58:35 | [pearl_trainer] epoch #277 | Saving snapshot... 2025-03-30 02:58:36 | [pearl_trainer] epoch #277 | Saved 2025-03-30 02:58:36 | [pearl_trainer] epoch #277 | Time 46140.56 s 2025-03-30 02:58:36 | [pearl_trainer] epoch #277 | EpochTime 151.18 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.2467 MetaTest/Average/AverageReturn -36.2467 MetaTest/Average/Iteration 277 MetaTest/Average/MaxReturn -34.8974 MetaTest/Average/MinReturn -37.5959 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.34927 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.2467 MetaTest/__unnamed_task__/AverageReturn -36.2467 MetaTest/__unnamed_task__/Iteration 277 MetaTest/__unnamed_task__/MaxReturn -34.8974 MetaTest/__unnamed_task__/MinReturn -37.5959 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.34927 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 558000 ------------------------------------------------- ------------ 2025-03-30 02:59:40 | [pearl_trainer] epoch #278 | Training... 2025-03-30 02:59:56 | [pearl_trainer] epoch #278 | Evaluating... 2025-03-30 02:59:56 | [pearl_trainer] epoch #278 | Sampling for adapation and meta-testing... 2025-03-30 03:01:06 | [pearl_trainer] epoch #278 | Finished meta-testing... 2025-03-30 03:01:06 | [pearl_trainer] epoch #278 | Saving snapshot... 2025-03-30 03:01:07 | [pearl_trainer] epoch #278 | Saved 2025-03-30 03:01:07 | [pearl_trainer] epoch #278 | Time 46291.58 s 2025-03-30 03:01:07 | [pearl_trainer] epoch #278 | EpochTime 151.01 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -35.2466 MetaTest/Average/AverageReturn -35.2466 MetaTest/Average/Iteration 278 MetaTest/Average/MaxReturn -35.2388 MetaTest/Average/MinReturn -35.2544 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.00781 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.2466 MetaTest/__unnamed_task__/AverageReturn -35.2466 MetaTest/__unnamed_task__/Iteration 278 MetaTest/__unnamed_task__/MaxReturn -35.2388 MetaTest/__unnamed_task__/MinReturn -35.2544 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.00781 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 560000 ------------------------------------------------- ------------ 2025-03-30 03:02:11 | [pearl_trainer] epoch #279 | Training... 2025-03-30 03:02:27 | [pearl_trainer] epoch #279 | Evaluating... 2025-03-30 03:02:27 | [pearl_trainer] epoch #279 | Sampling for adapation and meta-testing... 2025-03-30 03:03:38 | [pearl_trainer] epoch #279 | Finished meta-testing... 2025-03-30 03:03:38 | [pearl_trainer] epoch #279 | Saving snapshot... 2025-03-30 03:03:38 | [pearl_trainer] epoch #279 | Saved 2025-03-30 03:03:38 | [pearl_trainer] epoch #279 | Time 46443.32 s 2025-03-30 03:03:38 | [pearl_trainer] epoch #279 | EpochTime 151.74 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.6984 MetaTest/Average/AverageReturn -36.6984 MetaTest/Average/Iteration 279 MetaTest/Average/MaxReturn -35.6383 MetaTest/Average/MinReturn -37.7585 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.06012 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.6984 MetaTest/__unnamed_task__/AverageReturn -36.6984 MetaTest/__unnamed_task__/Iteration 279 MetaTest/__unnamed_task__/MaxReturn -35.6383 MetaTest/__unnamed_task__/MinReturn -37.7585 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.06012 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 562000 ------------------------------------------------- ------------ 2025-03-30 03:04:43 | [pearl_trainer] epoch #280 | Training... 2025-03-30 03:04:59 | [pearl_trainer] epoch #280 | Evaluating... 2025-03-30 03:04:59 | [pearl_trainer] epoch #280 | Sampling for adapation and meta-testing... 2025-03-30 03:06:10 | [pearl_trainer] epoch #280 | Finished meta-testing... 2025-03-30 03:06:10 | [pearl_trainer] epoch #280 | Saving snapshot... 2025-03-30 03:06:11 | [pearl_trainer] epoch #280 | Saved 2025-03-30 03:06:11 | [pearl_trainer] epoch #280 | Time 46595.86 s 2025-03-30 03:06:11 | [pearl_trainer] epoch #280 | EpochTime 152.54 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.1621 MetaTest/Average/AverageReturn -38.1621 MetaTest/Average/Iteration 280 MetaTest/Average/MaxReturn -35.4857 MetaTest/Average/MinReturn -40.8385 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.67642 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.1621 MetaTest/__unnamed_task__/AverageReturn -38.1621 MetaTest/__unnamed_task__/Iteration 280 MetaTest/__unnamed_task__/MaxReturn -35.4857 MetaTest/__unnamed_task__/MinReturn -40.8385 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.67642 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 564000 ------------------------------------------------- ------------ 2025-03-30 03:07:16 | [pearl_trainer] epoch #281 | Training... 2025-03-30 03:07:32 | [pearl_trainer] epoch #281 | Evaluating... 2025-03-30 03:07:32 | [pearl_trainer] epoch #281 | Sampling for adapation and meta-testing... 2025-03-30 03:08:44 | [pearl_trainer] epoch #281 | Finished meta-testing... 2025-03-30 03:08:44 | [pearl_trainer] epoch #281 | Saving snapshot... 2025-03-30 03:08:45 | [pearl_trainer] epoch #281 | Saved 2025-03-30 03:08:45 | [pearl_trainer] epoch #281 | Time 46749.81 s 2025-03-30 03:08:45 | [pearl_trainer] epoch #281 | EpochTime 153.94 s ------------------------------------------------- ----------- MetaTest/Average/AverageDiscountedReturn -34.8087 MetaTest/Average/AverageReturn -34.8087 MetaTest/Average/Iteration 281 MetaTest/Average/MaxReturn -33.0949 MetaTest/Average/MinReturn -36.5225 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.7138 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.8087 MetaTest/__unnamed_task__/AverageReturn -34.8087 MetaTest/__unnamed_task__/Iteration 281 MetaTest/__unnamed_task__/MaxReturn -33.0949 MetaTest/__unnamed_task__/MinReturn -36.5225 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.7138 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 566000 ------------------------------------------------- ----------- 2025-03-30 03:09:50 | [pearl_trainer] epoch #282 | Training... 2025-03-30 03:10:06 | [pearl_trainer] epoch #282 | Evaluating... 2025-03-30 03:10:06 | [pearl_trainer] epoch #282 | Sampling for adapation and meta-testing... 2025-03-30 03:11:17 | [pearl_trainer] epoch #282 | Finished meta-testing... 2025-03-30 03:11:17 | [pearl_trainer] epoch #282 | Saving snapshot... 2025-03-30 03:11:17 | [pearl_trainer] epoch #282 | Saved 2025-03-30 03:11:17 | [pearl_trainer] epoch #282 | Time 46902.43 s 2025-03-30 03:11:17 | [pearl_trainer] epoch #282 | EpochTime 152.62 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.1653 MetaTest/Average/AverageReturn -38.1653 MetaTest/Average/Iteration 282 MetaTest/Average/MaxReturn -36.4583 MetaTest/Average/MinReturn -39.8723 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.70702 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.1653 MetaTest/__unnamed_task__/AverageReturn -38.1653 MetaTest/__unnamed_task__/Iteration 282 MetaTest/__unnamed_task__/MaxReturn -36.4583 MetaTest/__unnamed_task__/MinReturn -39.8723 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.70702 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 568000 ------------------------------------------------- ------------ 2025-03-30 03:12:22 | [pearl_trainer] epoch #283 | Training... 2025-03-30 03:12:38 | [pearl_trainer] epoch #283 | Evaluating... 2025-03-30 03:12:38 | [pearl_trainer] epoch #283 | Sampling for adapation and meta-testing... 2025-03-30 03:13:49 | [pearl_trainer] epoch #283 | Finished meta-testing... 2025-03-30 03:13:49 | [pearl_trainer] epoch #283 | Saving snapshot... 2025-03-30 03:13:50 | [pearl_trainer] epoch #283 | Saved 2025-03-30 03:13:50 | [pearl_trainer] epoch #283 | Time 47055.10 s 2025-03-30 03:13:50 | [pearl_trainer] epoch #283 | EpochTime 152.68 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.5538 MetaTest/Average/AverageReturn -34.5538 MetaTest/Average/Iteration 283 MetaTest/Average/MaxReturn -27.5945 MetaTest/Average/MinReturn -41.5132 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 6.95937 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.5538 MetaTest/__unnamed_task__/AverageReturn -34.5538 MetaTest/__unnamed_task__/Iteration 283 MetaTest/__unnamed_task__/MaxReturn -27.5945 MetaTest/__unnamed_task__/MinReturn -41.5132 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 6.95937 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 570000 ------------------------------------------------- ------------ 2025-03-30 03:14:53 | [pearl_trainer] epoch #284 | Training... 2025-03-30 03:15:12 | [pearl_trainer] epoch #284 | Evaluating... 2025-03-30 03:15:12 | [pearl_trainer] epoch #284 | Sampling for adapation and meta-testing... 2025-03-30 03:16:22 | [pearl_trainer] epoch #284 | Finished meta-testing... 2025-03-30 03:16:22 | [pearl_trainer] epoch #284 | Saving snapshot... 2025-03-30 03:16:23 | [pearl_trainer] epoch #284 | Saved 2025-03-30 03:16:23 | [pearl_trainer] epoch #284 | Time 47207.54 s 2025-03-30 03:16:23 | [pearl_trainer] epoch #284 | EpochTime 152.43 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -34.1936 MetaTest/Average/AverageReturn -34.1936 MetaTest/Average/Iteration 284 MetaTest/Average/MaxReturn -30.7025 MetaTest/Average/MinReturn -37.6848 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.49115 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.1936 MetaTest/__unnamed_task__/AverageReturn -34.1936 MetaTest/__unnamed_task__/Iteration 284 MetaTest/__unnamed_task__/MaxReturn -30.7025 MetaTest/__unnamed_task__/MinReturn -37.6848 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.49115 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 572000 ------------------------------------------------- ------------ 2025-03-30 03:17:26 | [pearl_trainer] epoch #285 | Training... 2025-03-30 03:17:44 | [pearl_trainer] epoch #285 | Evaluating... 2025-03-30 03:17:44 | [pearl_trainer] epoch #285 | Sampling for adapation and meta-testing... 2025-03-30 03:18:54 | [pearl_trainer] epoch #285 | Finished meta-testing... 2025-03-30 03:18:54 | [pearl_trainer] epoch #285 | Saving snapshot... 2025-03-30 03:18:55 | [pearl_trainer] epoch #285 | Saved 2025-03-30 03:18:55 | [pearl_trainer] epoch #285 | Time 47359.99 s 2025-03-30 03:18:55 | [pearl_trainer] epoch #285 | EpochTime 152.45 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -31.9404 MetaTest/Average/AverageReturn -31.9404 MetaTest/Average/Iteration 285 MetaTest/Average/MaxReturn -30.0863 MetaTest/Average/MinReturn -33.7945 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 1.85409 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -31.9404 MetaTest/__unnamed_task__/AverageReturn -31.9404 MetaTest/__unnamed_task__/Iteration 285 MetaTest/__unnamed_task__/MaxReturn -30.0863 MetaTest/__unnamed_task__/MinReturn -33.7945 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 1.85409 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 574000 ------------------------------------------------- ------------ 2025-03-30 03:19:58 | [pearl_trainer] epoch #286 | Training... 2025-03-30 03:20:16 | [pearl_trainer] epoch #286 | Evaluating... 2025-03-30 03:20:16 | [pearl_trainer] epoch #286 | Sampling for adapation and meta-testing... 2025-03-30 03:21:26 | [pearl_trainer] epoch #286 | Finished meta-testing... 2025-03-30 03:21:26 | [pearl_trainer] epoch #286 | Saving snapshot... 2025-03-30 03:21:27 | [pearl_trainer] epoch #286 | Saved 2025-03-30 03:21:27 | [pearl_trainer] epoch #286 | Time 47511.94 s 2025-03-30 03:21:27 | [pearl_trainer] epoch #286 | EpochTime 151.95 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.1474 MetaTest/Average/AverageReturn -35.1474 MetaTest/Average/Iteration 286 MetaTest/Average/MaxReturn -34.1894 MetaTest/Average/MinReturn -36.1054 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.957988 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.1474 MetaTest/__unnamed_task__/AverageReturn -35.1474 MetaTest/__unnamed_task__/Iteration 286 MetaTest/__unnamed_task__/MaxReturn -34.1894 MetaTest/__unnamed_task__/MinReturn -36.1054 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.957988 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 576000 ------------------------------------------------- ------------- 2025-03-30 03:22:32 | [pearl_trainer] epoch #287 | Training... 2025-03-30 03:22:49 | [pearl_trainer] epoch #287 | Evaluating... 2025-03-30 03:22:49 | [pearl_trainer] epoch #287 | Sampling for adapation and meta-testing... 2025-03-30 03:24:00 | [pearl_trainer] epoch #287 | Finished meta-testing... 2025-03-30 03:24:00 | [pearl_trainer] epoch #287 | Saving snapshot... 2025-03-30 03:24:00 | [pearl_trainer] epoch #287 | Saved 2025-03-30 03:24:00 | [pearl_trainer] epoch #287 | Time 47665.43 s 2025-03-30 03:24:00 | [pearl_trainer] epoch #287 | EpochTime 153.48 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.4757 MetaTest/Average/AverageReturn -36.4757 MetaTest/Average/Iteration 287 MetaTest/Average/MaxReturn -33.9879 MetaTest/Average/MinReturn -38.9636 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.48786 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.4757 MetaTest/__unnamed_task__/AverageReturn -36.4757 MetaTest/__unnamed_task__/Iteration 287 MetaTest/__unnamed_task__/MaxReturn -33.9879 MetaTest/__unnamed_task__/MinReturn -38.9636 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.48786 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 578000 ------------------------------------------------- ------------ 2025-03-30 03:25:05 | [pearl_trainer] epoch #288 | Training... 2025-03-30 03:25:22 | [pearl_trainer] epoch #288 | Evaluating... 2025-03-30 03:25:22 | [pearl_trainer] epoch #288 | Sampling for adapation and meta-testing... 2025-03-30 03:26:32 | [pearl_trainer] epoch #288 | Finished meta-testing... 2025-03-30 03:26:32 | [pearl_trainer] epoch #288 | Saving snapshot... 2025-03-30 03:26:33 | [pearl_trainer] epoch #288 | Saved 2025-03-30 03:26:33 | [pearl_trainer] epoch #288 | Time 47817.99 s 2025-03-30 03:26:33 | [pearl_trainer] epoch #288 | EpochTime 152.56 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.2816 MetaTest/Average/AverageReturn -36.2816 MetaTest/Average/Iteration 288 MetaTest/Average/MaxReturn -32.3212 MetaTest/Average/MinReturn -40.242 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.96042 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.2816 MetaTest/__unnamed_task__/AverageReturn -36.2816 MetaTest/__unnamed_task__/Iteration 288 MetaTest/__unnamed_task__/MaxReturn -32.3212 MetaTest/__unnamed_task__/MinReturn -40.242 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.96042 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 580000 ------------------------------------------------- ------------ 2025-03-30 03:27:37 | [pearl_trainer] epoch #289 | Training... 2025-03-30 03:27:54 | [pearl_trainer] epoch #289 | Evaluating... 2025-03-30 03:27:54 | [pearl_trainer] epoch #289 | Sampling for adapation and meta-testing... 2025-03-30 03:29:03 | [pearl_trainer] epoch #289 | Finished meta-testing... 2025-03-30 03:29:03 | [pearl_trainer] epoch #289 | Saving snapshot... 2025-03-30 03:29:04 | [pearl_trainer] epoch #289 | Saved 2025-03-30 03:29:04 | [pearl_trainer] epoch #289 | Time 47969.23 s 2025-03-30 03:29:04 | [pearl_trainer] epoch #289 | EpochTime 151.23 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -41.7307 MetaTest/Average/AverageReturn -41.7307 MetaTest/Average/Iteration 289 MetaTest/Average/MaxReturn -39.2991 MetaTest/Average/MinReturn -44.1623 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.43159 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -41.7307 MetaTest/__unnamed_task__/AverageReturn -41.7307 MetaTest/__unnamed_task__/Iteration 289 MetaTest/__unnamed_task__/MaxReturn -39.2991 MetaTest/__unnamed_task__/MinReturn -44.1623 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.43159 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 582000 ------------------------------------------------- ------------ 2025-03-30 03:30:08 | [pearl_trainer] epoch #290 | Training... 2025-03-30 03:30:26 | [pearl_trainer] epoch #290 | Evaluating... 2025-03-30 03:30:26 | [pearl_trainer] epoch #290 | Sampling for adapation and meta-testing... 2025-03-30 03:31:36 | [pearl_trainer] epoch #290 | Finished meta-testing... 2025-03-30 03:31:36 | [pearl_trainer] epoch #290 | Saving snapshot... 2025-03-30 03:31:37 | [pearl_trainer] epoch #290 | Saved 2025-03-30 03:31:37 | [pearl_trainer] epoch #290 | Time 48121.73 s 2025-03-30 03:31:37 | [pearl_trainer] epoch #290 | EpochTime 152.51 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -41.3876 MetaTest/Average/AverageReturn -41.3876 MetaTest/Average/Iteration 290 MetaTest/Average/MaxReturn -37.7644 MetaTest/Average/MinReturn -45.0109 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.62325 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -41.3876 MetaTest/__unnamed_task__/AverageReturn -41.3876 MetaTest/__unnamed_task__/Iteration 290 MetaTest/__unnamed_task__/MaxReturn -37.7644 MetaTest/__unnamed_task__/MinReturn -45.0109 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.62325 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 584000 ------------------------------------------------- ------------ 2025-03-30 03:32:41 | [pearl_trainer] epoch #291 | Training... 2025-03-30 03:32:58 | [pearl_trainer] epoch #291 | Evaluating... 2025-03-30 03:32:58 | [pearl_trainer] epoch #291 | Sampling for adapation and meta-testing... 2025-03-30 03:34:08 | [pearl_trainer] epoch #291 | Finished meta-testing... 2025-03-30 03:34:08 | [pearl_trainer] epoch #291 | Saving snapshot... 2025-03-30 03:34:09 | [pearl_trainer] epoch #291 | Saved 2025-03-30 03:34:09 | [pearl_trainer] epoch #291 | Time 48273.82 s 2025-03-30 03:34:09 | [pearl_trainer] epoch #291 | EpochTime 152.08 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.2812 MetaTest/Average/AverageReturn -36.2812 MetaTest/Average/Iteration 291 MetaTest/Average/MaxReturn -33.2912 MetaTest/Average/MinReturn -39.2711 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.98993 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.2812 MetaTest/__unnamed_task__/AverageReturn -36.2812 MetaTest/__unnamed_task__/Iteration 291 MetaTest/__unnamed_task__/MaxReturn -33.2912 MetaTest/__unnamed_task__/MinReturn -39.2711 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.98993 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 586000 ------------------------------------------------- ------------ 2025-03-30 03:35:13 | [pearl_trainer] epoch #292 | Training... 2025-03-30 03:35:30 | [pearl_trainer] epoch #292 | Evaluating... 2025-03-30 03:35:30 | [pearl_trainer] epoch #292 | Sampling for adapation and meta-testing... 2025-03-30 03:36:40 | [pearl_trainer] epoch #292 | Finished meta-testing... 2025-03-30 03:36:40 | [pearl_trainer] epoch #292 | Saving snapshot... 2025-03-30 03:36:41 | [pearl_trainer] epoch #292 | Saved 2025-03-30 03:36:41 | [pearl_trainer] epoch #292 | Time 48425.83 s 2025-03-30 03:36:41 | [pearl_trainer] epoch #292 | EpochTime 152.01 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -32.7604 MetaTest/Average/AverageReturn -32.7604 MetaTest/Average/Iteration 292 MetaTest/Average/MaxReturn -32.0906 MetaTest/Average/MinReturn -33.4301 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.669745 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -32.7604 MetaTest/__unnamed_task__/AverageReturn -32.7604 MetaTest/__unnamed_task__/Iteration 292 MetaTest/__unnamed_task__/MaxReturn -32.0906 MetaTest/__unnamed_task__/MinReturn -33.4301 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.669745 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 588000 ------------------------------------------------- ------------- 2025-03-30 03:37:45 | [pearl_trainer] epoch #293 | Training... 2025-03-30 03:38:03 | [pearl_trainer] epoch #293 | Evaluating... 2025-03-30 03:38:03 | [pearl_trainer] epoch #293 | Sampling for adapation and meta-testing... 2025-03-30 03:39:13 | [pearl_trainer] epoch #293 | Finished meta-testing... 2025-03-30 03:39:13 | [pearl_trainer] epoch #293 | Saving snapshot... 2025-03-30 03:39:13 | [pearl_trainer] epoch #293 | Saved 2025-03-30 03:39:13 | [pearl_trainer] epoch #293 | Time 48578.39 s 2025-03-30 03:39:13 | [pearl_trainer] epoch #293 | EpochTime 152.56 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.115 MetaTest/Average/AverageReturn -36.115 MetaTest/Average/Iteration 293 MetaTest/Average/MaxReturn -31.9467 MetaTest/Average/MinReturn -40.2834 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 4.16836 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.115 MetaTest/__unnamed_task__/AverageReturn -36.115 MetaTest/__unnamed_task__/Iteration 293 MetaTest/__unnamed_task__/MaxReturn -31.9467 MetaTest/__unnamed_task__/MinReturn -40.2834 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 4.16836 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 590000 ------------------------------------------------- ------------ 2025-03-30 03:40:17 | [pearl_trainer] epoch #294 | Training... 2025-03-30 03:40:35 | [pearl_trainer] epoch #294 | Evaluating... 2025-03-30 03:40:35 | [pearl_trainer] epoch #294 | Sampling for adapation and meta-testing... 2025-03-30 03:41:46 | [pearl_trainer] epoch #294 | Finished meta-testing... 2025-03-30 03:41:46 | [pearl_trainer] epoch #294 | Saving snapshot... 2025-03-30 03:41:46 | [pearl_trainer] epoch #294 | Saved 2025-03-30 03:41:46 | [pearl_trainer] epoch #294 | Time 48731.24 s 2025-03-30 03:41:46 | [pearl_trainer] epoch #294 | EpochTime 152.85 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -35.7103 MetaTest/Average/AverageReturn -35.7103 MetaTest/Average/Iteration 294 MetaTest/Average/MaxReturn -35.0221 MetaTest/Average/MinReturn -36.3984 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.688171 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -35.7103 MetaTest/__unnamed_task__/AverageReturn -35.7103 MetaTest/__unnamed_task__/Iteration 294 MetaTest/__unnamed_task__/MaxReturn -35.0221 MetaTest/__unnamed_task__/MinReturn -36.3984 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.688171 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 592000 ------------------------------------------------- ------------- 2025-03-30 03:42:50 | [pearl_trainer] epoch #295 | Training... 2025-03-30 03:43:07 | [pearl_trainer] epoch #295 | Evaluating... 2025-03-30 03:43:07 | [pearl_trainer] epoch #295 | Sampling for adapation and meta-testing... 2025-03-30 03:44:17 | [pearl_trainer] epoch #295 | Finished meta-testing... 2025-03-30 03:44:17 | [pearl_trainer] epoch #295 | Saving snapshot... 2025-03-30 03:44:18 | [pearl_trainer] epoch #295 | Saved 2025-03-30 03:44:18 | [pearl_trainer] epoch #295 | Time 48882.86 s 2025-03-30 03:44:18 | [pearl_trainer] epoch #295 | EpochTime 151.62 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -36.4173 MetaTest/Average/AverageReturn -36.4173 MetaTest/Average/Iteration 295 MetaTest/Average/MaxReturn -33.8312 MetaTest/Average/MinReturn -39.0034 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 2.58611 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.4173 MetaTest/__unnamed_task__/AverageReturn -36.4173 MetaTest/__unnamed_task__/Iteration 295 MetaTest/__unnamed_task__/MaxReturn -33.8312 MetaTest/__unnamed_task__/MinReturn -39.0034 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 2.58611 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 594000 ------------------------------------------------- ------------ 2025-03-30 03:45:22 | [pearl_trainer] epoch #296 | Training... 2025-03-30 03:45:40 | [pearl_trainer] epoch #296 | Evaluating... 2025-03-30 03:45:40 | [pearl_trainer] epoch #296 | Sampling for adapation and meta-testing... 2025-03-30 03:46:51 | [pearl_trainer] epoch #296 | Finished meta-testing... 2025-03-30 03:46:51 | [pearl_trainer] epoch #296 | Saving snapshot... 2025-03-30 03:46:51 | [pearl_trainer] epoch #296 | Saved 2025-03-30 03:46:51 | [pearl_trainer] epoch #296 | Time 49036.22 s 2025-03-30 03:46:51 | [pearl_trainer] epoch #296 | EpochTime 153.36 s ------------------------------------------------- -------------- MetaTest/Average/AverageDiscountedReturn -36.6888 MetaTest/Average/AverageReturn -36.6888 MetaTest/Average/Iteration 296 MetaTest/Average/MaxReturn -36.6334 MetaTest/Average/MinReturn -36.7442 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.0554073 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -36.6888 MetaTest/__unnamed_task__/AverageReturn -36.6888 MetaTest/__unnamed_task__/Iteration 296 MetaTest/__unnamed_task__/MaxReturn -36.6334 MetaTest/__unnamed_task__/MinReturn -36.7442 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.0554073 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 596000 ------------------------------------------------- -------------- 2025-03-30 03:47:56 | [pearl_trainer] epoch #297 | Training... 2025-03-30 03:48:14 | [pearl_trainer] epoch #297 | Evaluating... 2025-03-30 03:48:14 | [pearl_trainer] epoch #297 | Sampling for adapation and meta-testing... 2025-03-30 03:49:24 | [pearl_trainer] epoch #297 | Finished meta-testing... 2025-03-30 03:49:24 | [pearl_trainer] epoch #297 | Saving snapshot... 2025-03-30 03:49:25 | [pearl_trainer] epoch #297 | Saved 2025-03-30 03:49:25 | [pearl_trainer] epoch #297 | Time 49189.95 s 2025-03-30 03:49:25 | [pearl_trainer] epoch #297 | EpochTime 153.72 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -41.3184 MetaTest/Average/AverageReturn -41.3184 MetaTest/Average/Iteration 297 MetaTest/Average/MaxReturn -40.7125 MetaTest/Average/MinReturn -41.9244 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.605923 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -41.3184 MetaTest/__unnamed_task__/AverageReturn -41.3184 MetaTest/__unnamed_task__/Iteration 297 MetaTest/__unnamed_task__/MaxReturn -40.7125 MetaTest/__unnamed_task__/MinReturn -41.9244 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.605923 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 598000 ------------------------------------------------- ------------- 2025-03-30 03:50:29 | [pearl_trainer] epoch #298 | Training... 2025-03-30 03:50:46 | [pearl_trainer] epoch #298 | Evaluating... 2025-03-30 03:50:46 | [pearl_trainer] epoch #298 | Sampling for adapation and meta-testing... 2025-03-30 03:51:56 | [pearl_trainer] epoch #298 | Finished meta-testing... 2025-03-30 03:51:56 | [pearl_trainer] epoch #298 | Saving snapshot... 2025-03-30 03:51:57 | [pearl_trainer] epoch #298 | Saved 2025-03-30 03:51:57 | [pearl_trainer] epoch #298 | Time 49341.97 s 2025-03-30 03:51:57 | [pearl_trainer] epoch #298 | EpochTime 152.02 s ------------------------------------------------- ------------ MetaTest/Average/AverageDiscountedReturn -38.6762 MetaTest/Average/AverageReturn -38.6762 MetaTest/Average/Iteration 298 MetaTest/Average/MaxReturn -34.9209 MetaTest/Average/MinReturn -42.4316 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 3.75535 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -38.6762 MetaTest/__unnamed_task__/AverageReturn -38.6762 MetaTest/__unnamed_task__/Iteration 298 MetaTest/__unnamed_task__/MaxReturn -34.9209 MetaTest/__unnamed_task__/MinReturn -42.4316 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 3.75535 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 600000 ------------------------------------------------- ------------ 2025-03-30 03:53:01 | [pearl_trainer] epoch #299 | Training... 2025-03-30 03:53:19 | [pearl_trainer] epoch #299 | Evaluating... 2025-03-30 03:53:19 | [pearl_trainer] epoch #299 | Sampling for adapation and meta-testing... 2025-03-30 03:54:29 | [pearl_trainer] epoch #299 | Finished meta-testing... 2025-03-30 03:54:29 | [pearl_trainer] epoch #299 | Saving snapshot... 2025-03-30 03:54:30 | [pearl_trainer] epoch #299 | Saved 2025-03-30 03:54:30 | [pearl_trainer] epoch #299 | Time 49495.00 s 2025-03-30 03:54:30 | [pearl_trainer] epoch #299 | EpochTime 153.03 s ------------------------------------------------- ------------- MetaTest/Average/AverageDiscountedReturn -34.4136 MetaTest/Average/AverageReturn -34.4136 MetaTest/Average/Iteration 299 MetaTest/Average/MaxReturn -34.0284 MetaTest/Average/MinReturn -34.7988 MetaTest/Average/NumEpisodes 2 MetaTest/Average/StdReturn 0.385199 MetaTest/Average/TerminationRate 0 MetaTest/__unnamed_task__/AverageDiscountedReturn -34.4136 MetaTest/__unnamed_task__/AverageReturn -34.4136 MetaTest/__unnamed_task__/Iteration 299 MetaTest/__unnamed_task__/MaxReturn -34.0284 MetaTest/__unnamed_task__/MinReturn -34.7988 MetaTest/__unnamed_task__/NumEpisodes 2 MetaTest/__unnamed_task__/StdReturn 0.385199 MetaTest/__unnamed_task__/TerminationRate 0 TotalEnvSteps 602000 ------------------------------------------------- -------------