{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4069931507110596, "min": 1.4069931507110596, "max": 1.4300596714019775, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69845.953125, "min": 67866.8203125, "max": 75373.796875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.47491638795987, "min": 78.93679092382496, "max": 364.35036496350364, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49320.0, "min": 48704.0, "max": 50042.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999265.0, "min": 49303.0, "max": 1999265.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999265.0, "min": 49303.0, "max": 1999265.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4085474014282227, "min": 0.1462697982788086, "max": 2.4646005630493164, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1440.311279296875, "min": 19.89269256591797, "max": 1510.46240234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7571899662647756, "min": 1.8059315817321049, "max": 3.9688558351580996, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2246.799599826336, "min": 245.60669511556625, "max": 2409.1778694987297, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7571899662647756, "min": 1.8059315817321049, "max": 3.9688558351580996, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2246.799599826336, "min": 245.60669511556625, "max": 2409.1778694987297, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017905657676359016, "min": 0.014158833313356607, "max": 0.01925155019917939, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05371697302907705, "min": 0.029859393846345485, "max": 0.057754650597538176, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05426854714751244, "min": 0.02143987637634079, "max": 0.06148403063416481, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1628056414425373, "min": 0.04287975275268158, "max": 0.1788545691718658, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6004487998833414e-06, "min": 3.6004487998833414e-06, "max": 0.00029533860155379996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0801346399650025e-05, "min": 1.0801346399650025e-05, "max": 0.0008440149186616998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120011666666667, "min": 0.10120011666666667, "max": 0.19844619999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30360035, "min": 0.2075844, "max": 0.5813383, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.98858216666668e-05, "min": 6.98858216666668e-05, "max": 0.004922465380000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020965746500000037, "min": 0.00020965746500000037, "max": 0.014068781170000003, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691054424", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691056965" }, "total": 2541.4021368169997, "count": 1, "self": 0.44899295599952893, "children": { "run_training.setup": { "total": 0.04318200800003069, "count": 1, "self": 0.04318200800003069 }, "TrainerController.start_learning": { "total": 2540.909961853, "count": 1, "self": 4.528916205066707, "children": { "TrainerController._reset_env": { "total": 6.231890802000009, "count": 1, "self": 6.231890802000009 }, "TrainerController.advance": { "total": 2530.0287596909334, "count": 232571, "self": 4.716260406862148, "children": { "env_step": { "total": 1966.2256459709954, "count": 232571, "self": 1660.7983762819551, "children": { "SubprocessEnvManager._take_step": { "total": 302.3784046090312, "count": 232571, "self": 17.264209544094967, "children": { "TorchPolicy.evaluate": { "total": 285.1141950649362, "count": 222915, "self": 285.1141950649362 } } }, "workers": { "total": 3.0488650800090227, "count": 232571, "self": 0.0, "children": { "worker_root": { "total": 2533.073321367989, "count": 232571, "is_parallel": true, "self": 1178.7324292099984, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011653759999603608, "count": 1, "is_parallel": true, "self": 0.0002857349999203507, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008796410000400101, "count": 2, "is_parallel": true, "self": 0.0008796410000400101 } } }, "UnityEnvironment.step": { "total": 0.05162234299996271, "count": 1, "is_parallel": true, "self": 0.00037381099997446654, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025750600002538704, "count": 1, "is_parallel": true, "self": 0.00025750600002538704 }, "communicator.exchange": { "total": 0.050078364000000875, "count": 1, "is_parallel": true, "self": 0.050078364000000875 }, "steps_from_proto": { "total": 0.0009126619999619834, "count": 1, "is_parallel": true, "self": 0.00027945400000817244, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006332079999538109, "count": 2, "is_parallel": true, "self": 0.0006332079999538109 } } } } } } }, "UnityEnvironment.step": { "total": 1354.3408921579908, "count": 232570, "is_parallel": true, "self": 40.545964840132456, "children": { "UnityEnvironment._generate_step_input": { "total": 87.03837244884784, "count": 232570, "is_parallel": true, "self": 87.03837244884784 }, "communicator.exchange": { "total": 1125.4566976559847, "count": 232570, "is_parallel": true, "self": 1125.4566976559847 }, "steps_from_proto": { "total": 101.29985721302558, "count": 232570, "is_parallel": true, "self": 38.37954731889221, "children": { "_process_rank_one_or_two_observation": { "total": 62.92030989413337, "count": 465140, "is_parallel": true, "self": 62.92030989413337 } } } } } } } } } } }, "trainer_advance": { "total": 559.0868533130761, "count": 232571, "self": 6.718291772046541, "children": { "process_trajectory": { "total": 145.57391033803043, "count": 232571, "self": 144.22954578003095, "children": { "RLTrainer._checkpoint": { "total": 1.3443645579994836, "count": 10, "self": 1.3443645579994836 } } }, "_update_policy": { "total": 406.79465120299903, "count": 97, "self": 346.8075006869883, "children": { "TorchPPOOptimizer.update": { "total": 59.98715051601073, "count": 2910, "self": 59.98715051601073 } } } } } } }, "trainer_threads": { "total": 1.0069998097606003e-06, "count": 1, "self": 1.0069998097606003e-06 }, "TrainerController._save_models": { "total": 0.12039414799983206, "count": 1, "self": 0.0019720049999705225, "children": { "RLTrainer._checkpoint": { "total": 0.11842214299986153, "count": 1, "self": 0.11842214299986153 } } } } } } }