{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9845409989356995, "min": 0.9845409989356995, "max": 2.8722968101501465, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9400.3974609375, "min": 9400.3974609375, "max": 29446.787109375, "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": 13.07028579711914, "min": 0.40643370151519775, "max": 13.077363967895508, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2548.705810546875, "min": 78.84813690185547, "max": 2667.7822265625, "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": 0.06528549286780189, "min": 0.05950623220003977, "max": 0.07634468464587138, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26114197147120755, "min": 0.23934367207317228, "max": 0.38172342322935693, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19148773079117137, "min": 0.13946746300230278, "max": 0.2822756876109862, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7659509231646855, "min": 0.5578698520092111, "max": 1.3794262873775818, "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": 25.886363636363637, "min": 3.772727272727273, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 166.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 3.772727272727273, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 166.0, "max": 1397.0, "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": "1704420802", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704421293" }, "total": 490.738330016, "count": 1, "self": 0.43684487300004093, "children": { "run_training.setup": { "total": 0.05368986600001335, "count": 1, "self": 0.05368986600001335 }, "TrainerController.start_learning": { "total": 490.24779527699997, "count": 1, "self": 0.704069946996583, "children": { "TrainerController._reset_env": { "total": 3.090912909999986, "count": 1, "self": 3.090912909999986 }, "TrainerController.advance": { "total": 486.3550216210035, "count": 18199, "self": 0.33510622601761497, "children": { "env_step": { "total": 486.0199153949859, "count": 18199, "self": 320.2597786869883, "children": { "SubprocessEnvManager._take_step": { "total": 165.40576263199983, "count": 18199, "self": 1.6677668490021347, "children": { "TorchPolicy.evaluate": { "total": 163.7379957829977, "count": 18199, "self": 163.7379957829977 } } }, "workers": { "total": 0.35437407599778226, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 488.8189186149902, "count": 18199, "is_parallel": true, "self": 239.91981613799288, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004614366999987851, "count": 1, "is_parallel": true, "self": 0.003185009999981503, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014293570000063482, "count": 10, "is_parallel": true, "self": 0.0014293570000063482 } } }, "UnityEnvironment.step": { "total": 0.10465657299999975, "count": 1, "is_parallel": true, "self": 0.000741890000085732, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004038710000031642, "count": 1, "is_parallel": true, "self": 0.0004038710000031642 }, "communicator.exchange": { "total": 0.10120194599994647, "count": 1, "is_parallel": true, "self": 0.10120194599994647 }, "steps_from_proto": { "total": 0.0023088659999643824, "count": 1, "is_parallel": true, "self": 0.0005087819998266241, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018000840001377583, "count": 10, "is_parallel": true, "self": 0.0018000840001377583 } } } } } } }, "UnityEnvironment.step": { "total": 248.8991024769973, "count": 18198, "is_parallel": true, "self": 11.724977285003717, "children": { "UnityEnvironment._generate_step_input": { "total": 6.010092023992684, "count": 18198, "is_parallel": true, "self": 6.010092023992684 }, "communicator.exchange": { "total": 193.72534248799798, "count": 18198, "is_parallel": true, "self": 193.72534248799798 }, "steps_from_proto": { "total": 37.438690680002935, "count": 18198, "is_parallel": true, "self": 7.1831973460309655, "children": { "_process_rank_one_or_two_observation": { "total": 30.25549333397197, "count": 181980, "is_parallel": true, "self": 30.25549333397197 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013014799992561166, "count": 1, "self": 0.00013014799992561166, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 480.06021448698704, "count": 739997, "is_parallel": true, "self": 16.15124746900142, "children": { "process_trajectory": { "total": 266.8272429739857, "count": 739997, "is_parallel": true, "self": 266.28468316798546, "children": { "RLTrainer._checkpoint": { "total": 0.542559806000213, "count": 4, "is_parallel": true, "self": 0.542559806000213 } } }, "_update_policy": { "total": 197.08172404399994, "count": 90, "is_parallel": true, "self": 61.19214206700292, "children": { "TorchPPOOptimizer.update": { "total": 135.88958197699702, "count": 4587, "is_parallel": true, "self": 135.88958197699702 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09766065099995558, "count": 1, "self": 0.0010660319999260537, "children": { "RLTrainer._checkpoint": { "total": 0.09659461900002952, "count": 1, "self": 0.09659461900002952 } } } } } } }