{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.940886914730072, "min": 0.940886914730072, "max": 2.866940498352051, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9014.6376953125, "min": 9014.6376953125, "max": 29391.875, "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": 12.903731346130371, "min": 0.4992696940898895, "max": 12.903731346130371, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2516.2275390625, "min": 96.85832214355469, "max": 2608.384765625, "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.Losses.PolicyLoss.mean": { "value": 0.06991891990160451, "min": 0.06129298825960052, "max": 0.07567988075567045, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27967567960641804, "min": 0.24517195303840209, "max": 0.37839940377835224, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2014498026201538, "min": 0.1203280047550067, "max": 0.2877670353534175, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8057992104806152, "min": 0.4813120190200268, "max": 1.4388351767670875, "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": 26.318181818181817, "min": 3.272727272727273, "max": 26.318181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1158.0, "min": 144.0, "max": 1395.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.318181818181817, "min": 3.272727272727273, "max": 26.318181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1158.0, "min": 144.0, "max": 1395.0, "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": "1708555123", "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=SnowballTarget1 --no-graphics", "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": "1708555731" }, "total": 608.197760926, "count": 1, "self": 0.5437324230000513, "children": { "run_training.setup": { "total": 0.06963680100000147, "count": 1, "self": 0.06963680100000147 }, "TrainerController.start_learning": { "total": 607.584391702, "count": 1, "self": 0.8240112440097391, "children": { "TrainerController._reset_env": { "total": 4.754220170000053, "count": 1, "self": 4.754220170000053 }, "TrainerController.advance": { "total": 601.8969509459902, "count": 18203, "self": 0.43957579399614133, "children": { "env_step": { "total": 601.457375151994, "count": 18203, "self": 460.1657447209825, "children": { "SubprocessEnvManager._take_step": { "total": 140.8653471460085, "count": 18203, "self": 2.612621367016459, "children": { "TorchPolicy.evaluate": { "total": 138.25272577899204, "count": 18203, "self": 138.25272577899204 } } }, "workers": { "total": 0.4262832850030236, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 605.6635993859928, "count": 18203, "is_parallel": true, "self": 282.7427514209895, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009389493000071525, "count": 1, "is_parallel": true, "self": 0.005576772000040364, "children": { "_process_rank_one_or_two_observation": { "total": 0.0038127210000311607, "count": 10, "is_parallel": true, "self": 0.0038127210000311607 } } }, "UnityEnvironment.step": { "total": 0.05353189300001304, "count": 1, "is_parallel": true, "self": 0.0009828440000774208, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004093179999244967, "count": 1, "is_parallel": true, "self": 0.0004093179999244967 }, "communicator.exchange": { "total": 0.04952994799998578, "count": 1, "is_parallel": true, "self": 0.04952994799998578 }, "steps_from_proto": { "total": 0.0026097830000253452, "count": 1, "is_parallel": true, "self": 0.0005351390002488188, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020746439997765265, "count": 10, "is_parallel": true, "self": 0.0020746439997765265 } } } } } } }, "UnityEnvironment.step": { "total": 322.9208479650033, "count": 18202, "is_parallel": true, "self": 15.953089047028811, "children": { "UnityEnvironment._generate_step_input": { "total": 7.926293364985327, "count": 18202, "is_parallel": true, "self": 7.926293364985327 }, "communicator.exchange": { "total": 252.43754052299641, "count": 18202, "is_parallel": true, "self": 252.43754052299641 }, "steps_from_proto": { "total": 46.60392502999275, "count": 18202, "is_parallel": true, "self": 9.231193756021185, "children": { "_process_rank_one_or_two_observation": { "total": 37.37273127397157, "count": 182020, "is_parallel": true, "self": 37.37273127397157 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013033100003667641, "count": 1, "self": 0.00013033100003667641, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 594.4289725270081, "count": 827936, "is_parallel": true, "self": 18.934560917017166, "children": { "process_trajectory": { "total": 327.02800601499086, "count": 827936, "is_parallel": true, "self": 325.57753359999094, "children": { "RLTrainer._checkpoint": { "total": 1.450472414999922, "count": 4, "is_parallel": true, "self": 1.450472414999922 } } }, "_update_policy": { "total": 248.46640559500008, "count": 90, "is_parallel": true, "self": 59.37399634899202, "children": { "TorchPPOOptimizer.update": { "total": 189.09240924600806, "count": 4587, "is_parallel": true, "self": 189.09240924600806 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10907901099994888, "count": 1, "self": 0.0013061099998594727, "children": { "RLTrainer._checkpoint": { "total": 0.1077729010000894, "count": 1, "self": 0.1077729010000894 } } } } } } }