{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7178486585617065, "min": 0.6976361274719238, "max": 2.878765821456909, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7856.853515625, "min": 4877.86669921875, "max": 32109.75390625, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 6567.0, "max": 13134.0, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999800.0, "min": 9800.0, "max": 1999800.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999800.0, "min": 9800.0, "max": 1999800.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.986989974975586, "min": 0.19897232949733734, "max": 14.026093482971191, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 699.3494873046875, "min": 9.74964427947998, "max": 701.3046875, "count": 200 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 3.012399673461914, "min": 1.0613294839859009, "max": 5.97833251953125, "count": 200 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 150.61997985839844, "min": 52.00514602661133, "max": 298.9166259765625, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.6, "min": 3.0408163265306123, "max": 27.76, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1380.0, "min": 149.0, "max": 1388.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.6, "min": 3.0408163265306123, "max": 27.76, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1380.0, "min": 149.0, "max": 1388.0, "count": 200 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 6.236970176696778, "min": 5.940337533950806, "max": 14.174212512969971, "count": 200 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 311.84850883483887, "min": 297.0168766975403, "max": 708.7106256484985, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07039043672990362, "min": 0.060568576078295855, "max": 0.07814660576781642, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.21117131018971086, "min": 0.1290437142443543, "max": 0.37781506676544147, "count": 200 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.09840465098165484, "min": 0.08509081781481738, "max": 0.21042664999178812, "count": 200 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.2952139529449645, "min": 0.17018163562963476, "max": 1.0369116450641669, "count": 200 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 9.500996833333289e-07, "min": 9.500996833333289e-07, "max": 0.000299175000275, "count": 200 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.8502990499999867e-06, "min": 2.8502990499999867e-06, "max": 0.0014884500038499998, "count": 200 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10031666666666668, "min": 0.10031666666666668, "max": 0.199725, "count": 200 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.30095000000000005, "min": 0.23251, "max": 0.9961500000000001, "count": 200 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.580166666666659e-05, "min": 2.580166666666659e-05, "max": 0.0049862775, "count": 200 }, "SnowballTarget.Policy.Beta.sum": { "value": 7.740499999999976e-05, "min": 7.740499999999976e-05, "max": 0.024807885, "count": 200 }, "SnowballTarget.Losses.CuriosityForwardLoss.mean": { "value": 0.0300291647356818, "min": 0.02994706286665271, "max": 0.11994106799144957, "count": 200 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.0900874942070454, "min": 0.06337820248205481, "max": 0.4797642719657983, "count": 200 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 0.5733519672973609, "min": 0.5513428182773341, "max": 2.7830430374426, "count": 200 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 1.7200559018920827, "min": 1.1697937635240736, "max": 13.01859488206751, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707215110", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget-ppo --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707219958" }, "total": 4847.346488092001, "count": 1, "self": 0.4812986440010718, "children": { "run_training.setup": { "total": 0.07000914399941394, "count": 1, "self": 0.07000914399941394 }, "TrainerController.start_learning": { "total": 4846.7951803040005, "count": 1, "self": 6.687735729853557, "children": { "TrainerController._reset_env": { "total": 2.601962673000344, "count": 1, "self": 2.601962673000344 }, "TrainerController.advance": { "total": 4837.395461339146, "count": 182018, "self": 3.22620029013342, "children": { "env_step": { "total": 4834.169261049013, "count": 182018, "self": 2938.48247238571, "children": { "SubprocessEnvManager._take_step": { "total": 1892.3388483431345, "count": 182018, "self": 16.908851210350804, "children": { "TorchPolicy.evaluate": { "total": 1875.4299971327837, "count": 182018, "self": 1875.4299971327837 } } }, "workers": { "total": 3.3479403201681635, "count": 182018, "self": 0.0, "children": { "worker_root": { "total": 4832.826190093931, "count": 182018, "is_parallel": true, "self": 2419.7278922478063, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029851570006940165, "count": 1, "is_parallel": true, "self": 0.0008539790023860405, "children": { "_process_rank_one_or_two_observation": { "total": 0.002131177998307976, "count": 10, "is_parallel": true, "self": 0.002131177998307976 } } }, "UnityEnvironment.step": { "total": 0.038710275999619626, "count": 1, "is_parallel": true, "self": 0.0006204909996085917, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004150790000494453, "count": 1, "is_parallel": true, "self": 0.0004150790000494453 }, "communicator.exchange": { "total": 0.03580314400005591, "count": 1, "is_parallel": true, "self": 0.03580314400005591 }, "steps_from_proto": { "total": 0.0018715619999056798, "count": 1, "is_parallel": true, "self": 0.0003699810004036408, "children": { "_process_rank_one_or_two_observation": { "total": 0.001501580999502039, "count": 10, "is_parallel": true, "self": 0.001501580999502039 } } } } } } }, "UnityEnvironment.step": { "total": 2413.0982978461243, "count": 182017, "is_parallel": true, "self": 109.81895432847523, "children": { "UnityEnvironment._generate_step_input": { "total": 54.1800924606805, "count": 182017, "is_parallel": true, "self": 54.1800924606805 }, "communicator.exchange": { "total": 1900.838314420108, "count": 182017, "is_parallel": true, "self": 1900.838314420108 }, "steps_from_proto": { "total": 348.2609366368606, "count": 182017, "is_parallel": true, "self": 67.71488828660858, "children": { "_process_rank_one_or_two_observation": { "total": 280.546048350252, "count": 1820170, "is_parallel": true, "self": 280.546048350252 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.001056101000358467, "count": 1, "self": 0.001056101000358467, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 4843.667605999015, "count": 44043, "is_parallel": true, "self": 3.7794931780053957, "children": { "process_trajectory": { "total": 614.1665439580274, "count": 44043, "is_parallel": true, "self": 606.9923408430286, "children": { "RLTrainer._checkpoint": { "total": 7.174203114998818, "count": 40, "is_parallel": true, "self": 7.174203114998818 } } }, "_update_policy": { "total": 4225.721568862982, "count": 767, "is_parallel": true, "self": 2335.95828481279, "children": { "TorchPPOOptimizer.update": { "total": 1889.763284050192, "count": 46299, "is_parallel": true, "self": 1889.763284050192 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10896446100014145, "count": 1, "self": 0.0013898779998271493, "children": { "RLTrainer._checkpoint": { "total": 0.1075745830003143, "count": 1, "self": 0.1075745830003143 } } } } } } }