{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8601392507553101, "min": 0.8601392507553101, "max": 2.840636730194092, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8174.763671875, "min": 8174.763671875, "max": 28997.21875, "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": 12.887419700622559, "min": 0.23316049575805664, "max": 12.887419700622559, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2513.046875, "min": 45.23313522338867, "max": 2624.9189453125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0690735132506519, "min": 0.05837427680899946, "max": 0.07189602547684142, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2762940530026076, "min": 0.23349710723599784, "max": 0.3573660112657201, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19972319919250758, "min": 0.10497054382108664, "max": 0.2902792335140939, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7988927967700303, "min": 0.41988217528434657, "max": 1.4513961675704694, "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": 25.227272727272727, "min": 3.2045454545454546, "max": 25.527272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 141.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.2045454545454546, "max": 25.527272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 141.0, "max": 1404.0, "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": "1734846461", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1734846877" }, "total": 415.43571792399985, "count": 1, "self": 0.42650838399981694, "children": { "run_training.setup": { "total": 0.05571712699997988, "count": 1, "self": 0.05571712699997988 }, "TrainerController.start_learning": { "total": 414.95349241300005, "count": 1, "self": 0.3167108309955893, "children": { "TrainerController._reset_env": { "total": 1.9499199289998614, "count": 1, "self": 1.9499199289998614 }, "TrainerController.advance": { "total": 412.59829945300476, "count": 18192, "self": 0.3614045479860124, "children": { "env_step": { "total": 292.6633274070066, "count": 18192, "self": 223.50441977703372, "children": { "SubprocessEnvManager._take_step": { "total": 68.94978026099375, "count": 18192, "self": 1.2231710119910986, "children": { "TorchPolicy.evaluate": { "total": 67.72660924900265, "count": 18192, "self": 67.72660924900265 } } }, "workers": { "total": 0.2091273689791251, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 413.6036781069929, "count": 18192, "is_parallel": true, "self": 217.6224119320011, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021452639998642553, "count": 1, "is_parallel": true, "self": 0.000679925999520492, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014653380003437633, "count": 10, "is_parallel": true, "self": 0.0014653380003437633 } } }, "UnityEnvironment.step": { "total": 0.03467592099991634, "count": 1, "is_parallel": true, "self": 0.000635223999779555, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003880710000885301, "count": 1, "is_parallel": true, "self": 0.0003880710000885301 }, "communicator.exchange": { "total": 0.03176816600011989, "count": 1, "is_parallel": true, "self": 0.03176816600011989 }, "steps_from_proto": { "total": 0.0018844599999283673, "count": 1, "is_parallel": true, "self": 0.00035521299992069544, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015292470000076719, "count": 10, "is_parallel": true, "self": 0.0015292470000076719 } } } } } } }, "UnityEnvironment.step": { "total": 195.9812661749918, "count": 18191, "is_parallel": true, "self": 9.735875756954783, "children": { "UnityEnvironment._generate_step_input": { "total": 5.510735966008951, "count": 18191, "is_parallel": true, "self": 5.510735966008951 }, "communicator.exchange": { "total": 149.12005212103418, "count": 18191, "is_parallel": true, "self": 149.12005212103418 }, "steps_from_proto": { "total": 31.614602330993876, "count": 18191, "is_parallel": true, "self": 5.687291541004697, "children": { "_process_rank_one_or_two_observation": { "total": 25.92731078998918, "count": 181910, "is_parallel": true, "self": 25.92731078998918 } } } } } } } } } } }, "trainer_advance": { "total": 119.57356749801215, "count": 18192, "self": 0.3818977630119207, "children": { "process_trajectory": { "total": 28.02857006799968, "count": 18192, "self": 27.589345622999645, "children": { "RLTrainer._checkpoint": { "total": 0.4392244450000362, "count": 4, "self": 0.4392244450000362 } } }, "_update_policy": { "total": 91.16309966700055, "count": 90, "self": 37.484549399997604, "children": { "TorchPPOOptimizer.update": { "total": 53.67855026700295, "count": 4587, "self": 53.67855026700295 } } } } } } }, "trainer_threads": { "total": 1.7249999473278876e-06, "count": 1, "self": 1.7249999473278876e-06 }, "TrainerController._save_models": { "total": 0.08856047499989472, "count": 1, "self": 0.001554381999767429, "children": { "RLTrainer._checkpoint": { "total": 0.0870060930001273, "count": 1, "self": 0.0870060930001273 } } } } } } }