{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4073182344436646, "min": 1.4073182344436646, "max": 1.4288955926895142, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70443.3125, "min": 69219.828125, "max": 77798.6875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.08823529411765, "min": 77.92902208201893, "max": 413.23770491803276, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49008.0, "min": 48908.0, "max": 50415.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999979.0, "min": 49954.0, "max": 1999979.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999979.0, "min": 49954.0, "max": 1999979.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.450843572616577, "min": 0.15412874519824982, "max": 2.5021941661834717, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1333.2589111328125, "min": 18.649578094482422, "max": 1556.6134033203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.761364747934482, "min": 1.9229418403846172, "max": 4.0289105412501085, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2046.182422876358, "min": 232.6759626865387, "max": 2472.999159038067, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.761364747934482, "min": 1.9229418403846172, "max": 4.0289105412501085, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2046.182422876358, "min": 232.6759626865387, "max": 2472.999159038067, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015801548398869474, "min": 0.012923756687814602, "max": 0.021455501274128132, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04740464519660842, "min": 0.025847513375629204, "max": 0.05508991567379174, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054587341927819784, "min": 0.02123709407945474, "max": 0.06179736703634262, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16376202578345936, "min": 0.04247418815890948, "max": 0.18539210110902787, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.48874883711666e-06, "min": 3.48874883711666e-06, "max": 0.00029536935154354994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.046624651134998e-05, "min": 1.046624651134998e-05, "max": 0.00084407356864215, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116288333333334, "min": 0.10116288333333334, "max": 0.19845645000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30348865, "min": 0.20753310000000003, "max": 0.5813578500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.802787833333323e-05, "min": 6.802787833333323e-05, "max": 0.004922976854999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002040836349999997, "min": 0.0002040836349999997, "max": 0.014069756715000003, "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": "1679992500", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1679994870" }, "total": 2370.213944879, "count": 1, "self": 0.44209720499975447, "children": { "run_training.setup": { "total": 0.11435251300008531, "count": 1, "self": 0.11435251300008531 }, "TrainerController.start_learning": { "total": 2369.657495161, "count": 1, "self": 4.295704401881721, "children": { "TrainerController._reset_env": { "total": 9.504173465999997, "count": 1, "self": 9.504173465999997 }, "TrainerController.advance": { "total": 2355.7431364881186, "count": 232880, "self": 4.586581669060706, "children": { "env_step": { "total": 1828.3631720430824, "count": 232880, "self": 1543.3467540621155, "children": { "SubprocessEnvManager._take_step": { "total": 282.15866295693, "count": 232880, "self": 16.58630601900893, "children": { "TorchPolicy.evaluate": { "total": 265.5723569379211, "count": 223052, "self": 265.5723569379211 } } }, "workers": { "total": 2.857755024036919, "count": 232880, "self": 0.0, "children": { "worker_root": { "total": 2361.7492987700934, "count": 232880, "is_parallel": true, "self": 1104.8727152869294, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009497849999888786, "count": 1, "is_parallel": true, "self": 0.00025866100008897774, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006911239998999008, "count": 2, "is_parallel": true, "self": 0.0006911239998999008 } } }, "UnityEnvironment.step": { "total": 0.02864530800002285, "count": 1, "is_parallel": true, "self": 0.00027862499996444967, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021975399999973888, "count": 1, "is_parallel": true, "self": 0.00021975399999973888 }, "communicator.exchange": { "total": 0.0274698380000018, "count": 1, "is_parallel": true, "self": 0.0274698380000018 }, "steps_from_proto": { "total": 0.000677091000056862, "count": 1, "is_parallel": true, "self": 0.00018914899999344925, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004879420000634127, "count": 2, "is_parallel": true, "self": 0.0004879420000634127 } } } } } } }, "UnityEnvironment.step": { "total": 1256.876583483164, "count": 232879, "is_parallel": true, "self": 38.203242365256074, "children": { "UnityEnvironment._generate_step_input": { "total": 77.17453304894843, "count": 232879, "is_parallel": true, "self": 77.17453304894843 }, "communicator.exchange": { "total": 1052.9924773070402, "count": 232879, "is_parallel": true, "self": 1052.9924773070402 }, "steps_from_proto": { "total": 88.50633076191934, "count": 232879, "is_parallel": true, "self": 33.22439985095309, "children": { "_process_rank_one_or_two_observation": { "total": 55.28193091096625, "count": 465758, "is_parallel": true, "self": 55.28193091096625 } } } } } } } } } } }, "trainer_advance": { "total": 522.7933827759756, "count": 232880, "self": 6.3551337769888505, "children": { "process_trajectory": { "total": 144.99032242198814, "count": 232880, "self": 143.6220153169893, "children": { "RLTrainer._checkpoint": { "total": 1.3683071049988484, "count": 10, "self": 1.3683071049988484 } } }, "_update_policy": { "total": 371.4479265769986, "count": 97, "self": 312.67250409600047, "children": { "TorchPPOOptimizer.update": { "total": 58.775422480998145, "count": 2910, "self": 58.775422480998145 } } } } } } }, "trainer_threads": { "total": 1.2539999261207413e-06, "count": 1, "self": 1.2539999261207413e-06 }, "TrainerController._save_models": { "total": 0.11447955099993123, "count": 1, "self": 0.0022012740000718622, "children": { "RLTrainer._checkpoint": { "total": 0.11227827699985937, "count": 1, "self": 0.11227827699985937 } } } } } } }