{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4002721309661865, "min": 1.4002721309661865, "max": 1.4280060529708862, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69676.140625, "min": 67966.2421875, "max": 76075.609375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.65750915750915, "min": 83.60067681895093, "max": 400.344, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49499.0, "min": 48760.0, "max": 50166.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999975.0, "min": 49935.0, "max": 1999975.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999975.0, "min": 49935.0, "max": 1999975.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4170806407928467, "min": 0.09072420746088028, "max": 2.4525015354156494, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1319.72607421875, "min": 11.249801635742188, "max": 1391.8880615234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7468422024677963, "min": 1.7647129924547287, "max": 3.98961003053756, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2045.7758425474167, "min": 218.82441106438637, "max": 2219.7877008914948, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7468422024677963, "min": 1.7647129924547287, "max": 3.98961003053756, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2045.7758425474167, "min": 218.82441106438637, "max": 2219.7877008914948, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015111817199633353, "min": 0.013834237759268338, "max": 0.020111286904041965, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04533545159890006, "min": 0.027668475518536677, "max": 0.05715000895482565, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053942567275630106, "min": 0.020940518751740453, "max": 0.0602139142031471, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16182770182689032, "min": 0.041881037503480906, "max": 0.17918667706350486, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.321248892949994e-06, "min": 3.321248892949994e-06, "max": 0.00029532345155885, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.963746678849982e-06, "min": 9.963746678849982e-06, "max": 0.0008442168185944, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110705000000003, "min": 0.10110705000000003, "max": 0.19844115000000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033211500000001, "min": 0.20738760000000006, "max": 0.5814056000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.524179499999993e-05, "min": 6.524179499999993e-05, "max": 0.0049222133850000006, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001957253849999998, "min": 0.0001957253849999998, "max": 0.014072139440000003, "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": "1690895773", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690898579" }, "total": 2805.8592221399995, "count": 1, "self": 0.5452631209982428, "children": { "run_training.setup": { "total": 0.041438457000367634, "count": 1, "self": 0.041438457000367634 }, "TrainerController.start_learning": { "total": 2805.272520562001, "count": 1, "self": 5.068249426931288, "children": { "TrainerController._reset_env": { "total": 7.70414764599991, "count": 1, "self": 7.70414764599991 }, "TrainerController.advance": { "total": 2792.3625781380706, "count": 231991, "self": 5.220106218011097, "children": { "env_step": { "total": 2154.1087523249626, "count": 231991, "self": 1824.6397942499343, "children": { "SubprocessEnvManager._take_step": { "total": 326.1531671890325, "count": 231991, "self": 18.883089099049357, "children": { "TorchPolicy.evaluate": { "total": 307.27007808998314, "count": 222892, "self": 307.27007808998314 } } }, "workers": { "total": 3.315790885995739, "count": 231991, "self": 0.0, "children": { "worker_root": { "total": 2796.8266412491275, "count": 231991, "is_parallel": true, "self": 1303.456974724154, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010024000002886169, "count": 1, "is_parallel": true, "self": 0.00029301199992914917, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007093880003594677, "count": 2, "is_parallel": true, "self": 0.0007093880003594677 } } }, "UnityEnvironment.step": { "total": 0.03293135600051755, "count": 1, "is_parallel": true, "self": 0.0004081350007254514, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002728629997363896, "count": 1, "is_parallel": true, "self": 0.0002728629997363896 }, "communicator.exchange": { "total": 0.03144985699964309, "count": 1, "is_parallel": true, "self": 0.03144985699964309 }, "steps_from_proto": { "total": 0.0008005010004126234, "count": 1, "is_parallel": true, "self": 0.0002268170001116232, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005736840003010002, "count": 2, "is_parallel": true, "self": 0.0005736840003010002 } } } } } } }, "UnityEnvironment.step": { "total": 1493.3696665249736, "count": 231990, "is_parallel": true, "self": 45.93672177032204, "children": { "UnityEnvironment._generate_step_input": { "total": 92.6834510438839, "count": 231990, "is_parallel": true, "self": 92.6834510438839 }, "communicator.exchange": { "total": 1243.2846897058744, "count": 231990, "is_parallel": true, "self": 1243.2846897058744 }, "steps_from_proto": { "total": 111.46480400489327, "count": 231990, "is_parallel": true, "self": 40.503378475058526, "children": { "_process_rank_one_or_two_observation": { "total": 70.96142552983474, "count": 463980, "is_parallel": true, "self": 70.96142552983474 } } } } } } } } } } }, "trainer_advance": { "total": 633.033719595097, "count": 231991, "self": 7.503759915297451, "children": { "process_trajectory": { "total": 154.2636048368022, "count": 231991, "self": 152.71611542080336, "children": { "RLTrainer._checkpoint": { "total": 1.5474894159988253, "count": 10, "self": 1.5474894159988253 } } }, "_update_policy": { "total": 471.2663548429973, "count": 97, "self": 406.66702889199496, "children": { "TorchPPOOptimizer.update": { "total": 64.59932595100236, "count": 2910, "self": 64.59932595100236 } } } } } } }, "trainer_threads": { "total": 1.0169997040065937e-06, "count": 1, "self": 1.0169997040065937e-06 }, "TrainerController._save_models": { "total": 0.13754433399935806, "count": 1, "self": 0.002199360999838973, "children": { "RLTrainer._checkpoint": { "total": 0.1353449729995191, "count": 1, "self": 0.1353449729995191 } } } } } } }