{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9061346054077148, "min": 0.9058530926704407, "max": 2.853827953338623, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8651.7734375, "min": 8651.7734375, "max": 29226.052734375, "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": 12.708526611328125, "min": 0.2515510320663452, "max": 12.708526611328125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2478.16259765625, "min": 48.800899505615234, "max": 2559.197265625, "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": 0.06337084483547027, "min": 0.06277192963263552, "max": 0.07269275540237169, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2534833793418811, "min": 0.25108771853054207, "max": 0.36346377701185845, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1980083387198986, "min": 0.11977582843289436, "max": 0.2931200280493381, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7920333548795944, "min": 0.47910331373157744, "max": 1.4286242787744485, "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": 25.045454545454547, "min": 3.1363636363636362, "max": 25.2, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 138.0, "max": 1386.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 3.1363636363636362, "max": 25.2, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 138.0, "max": 1386.0, "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": "1673527929", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673528341" }, "total": 412.0392429399999, "count": 1, "self": 0.37539920299991536, "children": { "run_training.setup": { "total": 0.10982325899999523, "count": 1, "self": 0.10982325899999523 }, "TrainerController.start_learning": { "total": 411.554020478, "count": 1, "self": 0.48075347700205384, "children": { "TrainerController._reset_env": { "total": 6.800302784000223, "count": 1, "self": 6.800302784000223 }, "TrainerController.advance": { "total": 404.15211719599756, "count": 18201, "self": 0.23480704900339333, "children": { "env_step": { "total": 403.91731014699417, "count": 18201, "self": 263.8538727369855, "children": { "SubprocessEnvManager._take_step": { "total": 139.81482375201335, "count": 18201, "self": 1.2961089630066454, "children": { "TorchPolicy.evaluate": { "total": 138.5187147890067, "count": 18201, "self": 31.362966589005055, "children": { "TorchPolicy.sample_actions": { "total": 107.15574820000165, "count": 18201, "self": 107.15574820000165 } } } } }, "workers": { "total": 0.24861365799529267, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 410.37428508299877, "count": 18201, "is_parallel": true, "self": 198.5829503840232, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017849529999693914, "count": 1, "is_parallel": true, "self": 0.0006027859994901519, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011821670004792395, "count": 10, "is_parallel": true, "self": 0.0011821670004792395 } } }, "UnityEnvironment.step": { "total": 0.03980926200006252, "count": 1, "is_parallel": true, "self": 0.0003353760000663897, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002204009999786649, "count": 1, "is_parallel": true, "self": 0.0002204009999786649 }, "communicator.exchange": { "total": 0.0376343860000361, "count": 1, "is_parallel": true, "self": 0.0376343860000361 }, "steps_from_proto": { "total": 0.001619098999981361, "count": 1, "is_parallel": true, "self": 0.0004205799998544535, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011985190001269075, "count": 10, "is_parallel": true, "self": 0.0011985190001269075 } } } } } } }, "UnityEnvironment.step": { "total": 211.79133469897556, "count": 18200, "is_parallel": true, "self": 8.090806627957136, "children": { "UnityEnvironment._generate_step_input": { "total": 4.89719994599136, "count": 18200, "is_parallel": true, "self": 4.89719994599136 }, "communicator.exchange": { "total": 167.1225284180316, "count": 18200, "is_parallel": true, "self": 167.1225284180316 }, "steps_from_proto": { "total": 31.680799706995458, "count": 18200, "is_parallel": true, "self": 6.311164202934151, "children": { "_process_rank_one_or_two_observation": { "total": 25.369635504061307, "count": 182000, "is_parallel": true, "self": 25.369635504061307 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.6882000106052146e-05, "count": 1, "self": 4.6882000106052146e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 401.45167342803256, "count": 330621, "is_parallel": true, "self": 8.448533229996656, "children": { "process_trajectory": { "total": 228.93086318403516, "count": 330621, "is_parallel": true, "self": 228.24401889903515, "children": { "RLTrainer._checkpoint": { "total": 0.6868442850000065, "count": 4, "is_parallel": true, "self": 0.6868442850000065 } } }, "_update_policy": { "total": 164.07227701400075, "count": 90, "is_parallel": true, "self": 42.39176071199904, "children": { "TorchPPOOptimizer.update": { "total": 121.6805163020017, "count": 4587, "is_parallel": true, "self": 121.6805163020017 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12080013900003905, "count": 1, "self": 0.000840158000073643, "children": { "RLTrainer._checkpoint": { "total": 0.11995998099996541, "count": 1, "self": 0.11995998099996541 } } } } } } }