{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9859325885772705, "min": 0.9730374813079834, "max": 2.8631248474121094, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9413.6845703125, "min": 9413.6845703125, "max": 29352.755859375, "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": 12.909087181091309, "min": 0.2758808135986328, "max": 12.909087181091309, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2517.27197265625, "min": 53.520877838134766, "max": 2597.32958984375, "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": 0.06520190748172656, "min": 0.06227102151808817, "max": 0.07441185108253587, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26080762992690626, "min": 0.2490840860723527, "max": 0.37205925541267937, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20347246819851444, "min": 0.124856798715579, "max": 0.29419127844420134, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8138898727940578, "min": 0.499427194862316, "max": 1.4421731221909615, "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": 25.863636363636363, "min": 3.6363636363636362, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1138.0, "min": 160.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.863636363636363, "min": 3.6363636363636362, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1138.0, "min": 160.0, "max": 1394.0, "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": "1716624363", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716624805" }, "total": 441.781463742, "count": 1, "self": 0.43647613300004195, "children": { "run_training.setup": { "total": 0.0569991990000176, "count": 1, "self": 0.0569991990000176 }, "TrainerController.start_learning": { "total": 441.28798840999997, "count": 1, "self": 0.5302731120025328, "children": { "TrainerController._reset_env": { "total": 2.9572008149999647, "count": 1, "self": 2.9572008149999647 }, "TrainerController.advance": { "total": 437.7063747199974, "count": 18201, "self": 0.2500895809914141, "children": { "env_step": { "total": 437.456285139006, "count": 18201, "self": 284.05463036000833, "children": { "SubprocessEnvManager._take_step": { "total": 153.12804244499347, "count": 18201, "self": 1.4288832209932707, "children": { "TorchPolicy.evaluate": { "total": 151.6991592240002, "count": 18201, "self": 151.6991592240002 } } }, "workers": { "total": 0.2736123340042127, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 440.0266215949989, "count": 18201, "is_parallel": true, "self": 222.52259101299938, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004907012999979088, "count": 1, "is_parallel": true, "self": 0.003415052999798718, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014919600001803701, "count": 10, "is_parallel": true, "self": 0.0014919600001803701 } } }, "UnityEnvironment.step": { "total": 0.044636711000009655, "count": 1, "is_parallel": true, "self": 0.0007237430000373024, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039786999997204475, "count": 1, "is_parallel": true, "self": 0.00039786999997204475 }, "communicator.exchange": { "total": 0.03463614800000414, "count": 1, "is_parallel": true, "self": 0.03463614800000414 }, "steps_from_proto": { "total": 0.008878949999996166, "count": 1, "is_parallel": true, "self": 0.0005708789999516739, "children": { "_process_rank_one_or_two_observation": { "total": 0.008308071000044492, "count": 10, "is_parallel": true, "self": 0.008308071000044492 } } } } } } }, "UnityEnvironment.step": { "total": 217.50403058199953, "count": 18200, "is_parallel": true, "self": 10.048652350009093, "children": { "UnityEnvironment._generate_step_input": { "total": 5.147551899994198, "count": 18200, "is_parallel": true, "self": 5.147551899994198 }, "communicator.exchange": { "total": 169.83221881400306, "count": 18200, "is_parallel": true, "self": 169.83221881400306 }, "steps_from_proto": { "total": 32.47560751799318, "count": 18200, "is_parallel": true, "self": 5.9743851800125185, "children": { "_process_rank_one_or_two_observation": { "total": 26.501222337980664, "count": 182000, "is_parallel": true, "self": 26.501222337980664 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011915599998246762, "count": 1, "self": 0.00011915599998246762, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 432.36911055603315, "count": 662874, "is_parallel": true, "self": 13.609090680037696, "children": { "process_trajectory": { "total": 239.89426180099503, "count": 662874, "is_parallel": true, "self": 238.85071361699482, "children": { "RLTrainer._checkpoint": { "total": 1.0435481840002012, "count": 4, "is_parallel": true, "self": 1.0435481840002012 } } }, "_update_policy": { "total": 178.86575807500043, "count": 90, "is_parallel": true, "self": 55.61841529600264, "children": { "TorchPPOOptimizer.update": { "total": 123.24734277899779, "count": 4587, "is_parallel": true, "self": 123.24734277899779 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09402060700006132, "count": 1, "self": 0.0009930050000548363, "children": { "RLTrainer._checkpoint": { "total": 0.09302760200000648, "count": 1, "self": 0.09302760200000648 } } } } } } }