{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1581305265426636, "min": 1.1581305265426636, "max": 2.8782541751861572, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11108.7880859375, "min": 11108.7880859375, "max": 29539.5234375, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.321924209594727, "min": 0.4501103162765503, "max": 12.321924209594727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2402.775146484375, "min": 87.32140350341797, "max": 2488.74560546875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06827242503070509, "min": 0.06030330126226295, "max": 0.07599485026969655, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27308970012282036, "min": 0.2412132050490518, "max": 0.36840799069442953, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2155262331898306, "min": 0.11668531904134022, "max": 0.296727734380493, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8621049327593224, "min": 0.4667412761653609, "max": 1.468994970122973, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.545454545454547, "min": 3.090909090909091, "max": 24.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1080.0, "min": 136.0, "max": 1335.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.545454545454547, "min": 3.090909090909091, "max": 24.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1080.0, "min": 136.0, "max": 1335.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691180965", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691181373" }, "total": 408.0440758259999, "count": 1, "self": 0.3224431800001639, "children": { "run_training.setup": { "total": 0.03897239699995225, "count": 1, "self": 0.03897239699995225 }, "TrainerController.start_learning": { "total": 407.6826602489998, "count": 1, "self": 0.5437071829965134, "children": { "TrainerController._reset_env": { "total": 4.034002839000095, "count": 1, "self": 4.034002839000095 }, "TrainerController.advance": { "total": 402.96459743700325, "count": 18204, "self": 0.26049890101853634, "children": { "env_step": { "total": 402.7040985359847, "count": 18204, "self": 288.16335626095383, "children": { "SubprocessEnvManager._take_step": { "total": 114.279799371016, "count": 18204, "self": 1.6616863460326385, "children": { "TorchPolicy.evaluate": { "total": 112.61811302498336, "count": 18204, "self": 112.61811302498336 } } }, "workers": { "total": 0.2609429040148825, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 406.8504196630013, "count": 18204, "is_parallel": true, "self": 204.64677485500806, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002026320999902964, "count": 1, "is_parallel": true, "self": 0.0005743859996982792, "children": { "_process_rank_one_or_two_observation": { "total": 0.001451935000204685, "count": 10, "is_parallel": true, "self": 0.001451935000204685 } } }, "UnityEnvironment.step": { "total": 0.036847523999995246, "count": 1, "is_parallel": true, "self": 0.00041479199967398017, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005174140001145133, "count": 1, "is_parallel": true, "self": 0.0005174140001145133 }, "communicator.exchange": { "total": 0.03458672100009608, "count": 1, "is_parallel": true, "self": 0.03458672100009608 }, "steps_from_proto": { "total": 0.0013285970001106762, "count": 1, "is_parallel": true, "self": 0.000344322000273678, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009842749998369982, "count": 10, "is_parallel": true, "self": 0.0009842749998369982 } } } } } } }, "UnityEnvironment.step": { "total": 202.20364480799321, "count": 18203, "is_parallel": true, "self": 9.922728076983276, "children": { "UnityEnvironment._generate_step_input": { "total": 5.01637647000166, "count": 18203, "is_parallel": true, "self": 5.01637647000166 }, "communicator.exchange": { "total": 155.28674794300764, "count": 18203, "is_parallel": true, "self": 155.28674794300764 }, "steps_from_proto": { "total": 31.97779231800064, "count": 18203, "is_parallel": true, "self": 5.6191752820479905, "children": { "_process_rank_one_or_two_observation": { "total": 26.358617035952648, "count": 182030, "is_parallel": true, "self": 26.358617035952648 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017292500001531153, "count": 1, "self": 0.00017292500001531153, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 401.4413459419525, "count": 228797, "is_parallel": true, "self": 5.043709702887554, "children": { "process_trajectory": { "total": 221.16978317206667, "count": 228797, "is_parallel": true, "self": 220.3793899460668, "children": { "RLTrainer._checkpoint": { "total": 0.7903932259998783, "count": 4, "is_parallel": true, "self": 0.7903932259998783 } } }, "_update_policy": { "total": 175.22785306699825, "count": 90, "is_parallel": true, "self": 47.7203158620066, "children": { "TorchPPOOptimizer.update": { "total": 127.50753720499165, "count": 4587, "is_parallel": true, "self": 127.50753720499165 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1401798649999364, "count": 1, "self": 0.0006311509998795373, "children": { "RLTrainer._checkpoint": { "total": 0.13954871400005686, "count": 1, "self": 0.13954871400005686 } } } } } } }