{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7129193544387817, "min": 0.7129193544387817, "max": 2.8399477005004883, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6775.58544921875, "min": 6775.58544921875, "max": 28990.185546875, "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": 12.568286895751953, "min": 0.6493656039237976, "max": 12.568286895751953, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2450.81591796875, "min": 125.9769287109375, "max": 2512.68505859375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06376773407671363, "min": 0.06303729918003156, "max": 0.07480492593056304, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2550709363068545, "min": 0.25214919672012626, "max": 0.3740246296528152, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18687986184422878, "min": 0.143810383259894, "max": 0.2750409629707243, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7475194473769151, "min": 0.575241533039576, "max": 1.2682422405364466, "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.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.386363636363637, "min": 4.0227272727272725, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 177.0, "max": 1350.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 4.0227272727272725, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 177.0, "max": 1350.0, "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": "1767604584", "python_version": "3.10.12 (main, Nov 4 2025, 08:48:33) [GCC 11.4.0]", "command_line_arguments": "/usr/local/lib/python3.10/dist-packages/mlagents/trainers/learn.py config/ppo/SnowballTarget.yaml --env=training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1767605004" }, "total": 420.0462367729999, "count": 1, "self": 0.4789151130000846, "children": { "run_training.setup": { "total": 0.015575675000036426, "count": 1, "self": 0.015575675000036426 }, "TrainerController.start_learning": { "total": 419.5517459849998, "count": 1, "self": 0.39738225599649013, "children": { "TrainerController._reset_env": { "total": 4.351109004999898, "count": 1, "self": 4.351109004999898 }, "TrainerController.advance": { "total": 414.6711300170034, "count": 18192, "self": 0.3892191160005041, "children": { "env_step": { "total": 302.8226869550017, "count": 18192, "self": 251.713234211011, "children": { "SubprocessEnvManager._take_step": { "total": 50.87050107098935, "count": 18192, "self": 1.8175279629947454, "children": { "TorchPolicy.evaluate": { "total": 49.0529731079946, "count": 18192, "self": 49.0529731079946 } } }, "workers": { "total": 0.23895167300133835, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 417.7713763080035, "count": 18192, "is_parallel": true, "self": 196.42828577999057, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019955570001002343, "count": 1, "is_parallel": true, "self": 0.0006047110000508837, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013908460000493506, "count": 10, "is_parallel": true, "self": 0.0013908460000493506 } } }, "UnityEnvironment.step": { "total": 0.051043671999877915, "count": 1, "is_parallel": true, "self": 0.000589509999826987, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043392099996708566, "count": 1, "is_parallel": true, "self": 0.00043392099996708566 }, "communicator.exchange": { "total": 0.04799759200000153, "count": 1, "is_parallel": true, "self": 0.04799759200000153 }, "steps_from_proto": { "total": 0.0020226490000823105, "count": 1, "is_parallel": true, "self": 0.0003916860000572342, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016309630000250763, "count": 10, "is_parallel": true, "self": 0.0016309630000250763 } } } } } } }, "UnityEnvironment.step": { "total": 221.3430905280129, "count": 18191, "is_parallel": true, "self": 9.899855793025836, "children": { "UnityEnvironment._generate_step_input": { "total": 5.500544546990795, "count": 18191, "is_parallel": true, "self": 5.500544546990795 }, "communicator.exchange": { "total": 166.24368432500364, "count": 18191, "is_parallel": true, "self": 166.24368432500364 }, "steps_from_proto": { "total": 39.699005862992635, "count": 18191, "is_parallel": true, "self": 7.0311746900054, "children": { "_process_rank_one_or_two_observation": { "total": 32.667831172987235, "count": 181910, "is_parallel": true, "self": 32.667831172987235 } } } } } } } } } } }, "trainer_advance": { "total": 111.4592239460012, "count": 18192, "self": 0.5030162169821324, "children": { "process_trajectory": { "total": 22.219853412019347, "count": 18192, "self": 21.553372681019255, "children": { "RLTrainer._checkpoint": { "total": 0.6664807310000924, "count": 4, "self": 0.6664807310000924 } } }, "_update_policy": { "total": 88.73635431699972, "count": 90, "self": 47.1698457539876, "children": { "TorchPPOOptimizer.update": { "total": 41.56650856301212, "count": 4587, "self": 41.56650856301212 } } } } } } }, "trainer_threads": { "total": 9.240000053978292e-07, "count": 1, "self": 9.240000053978292e-07 }, "TrainerController._save_models": { "total": 0.13212378299999727, "count": 1, "self": 0.0007380800000191812, "children": { "RLTrainer._checkpoint": { "total": 0.1313857029999781, "count": 1, "self": 0.1313857029999781 } } } } } } }