{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4050054550170898, "min": 1.4050054550170898, "max": 1.426466941833496, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71059.5546875, "min": 68346.40625, "max": 77517.46875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.17304189435337, "min": 83.29005059021922, "max": 396.94444444444446, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49505.0, "min": 49008.0, "max": 50116.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999990.0, "min": 49538.0, "max": 1999990.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999990.0, "min": 49538.0, "max": 1999990.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4223861694335938, "min": -0.013070471584796906, "max": 2.47235107421875, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1329.8900146484375, "min": -1.633808970451355, "max": 1441.230224609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.673060900743759, "min": 1.835397591114044, "max": 3.904925320413895, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2016.5104345083237, "min": 229.42469888925552, "max": 2231.667940735817, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.673060900743759, "min": 1.835397591114044, "max": 3.904925320413895, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2016.5104345083237, "min": 229.42469888925552, "max": 2231.667940735817, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015100820154637202, "min": 0.012926023934051045, "max": 0.020140935306618406, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.045302460463911606, "min": 0.02585204786810209, "max": 0.060422805919855216, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0544252404736148, "min": 0.023119274775187174, "max": 0.06044914765904347, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1632757214208444, "min": 0.04623854955037435, "max": 0.17867978376646837, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2009989330333284e-06, "min": 3.2009989330333284e-06, "max": 0.000295292026569325, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.602996799099985e-06, "min": 9.602996799099985e-06, "max": 0.00084390826869725, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10106696666666666, "min": 0.10106696666666666, "max": 0.198430675, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3032009, "min": 0.20729844999999994, "max": 0.5813027500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.324163666666661e-05, "min": 6.324163666666661e-05, "max": 0.004921690682500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018972490999999983, "min": 0.00018972490999999983, "max": 0.014067007225, "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": "1674399470", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.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": "1674401596" }, "total": 2125.470415857, "count": 1, "self": 0.39231266299975687, "children": { "run_training.setup": { "total": 0.11053012399997897, "count": 1, "self": 0.11053012399997897 }, "TrainerController.start_learning": { "total": 2124.96757307, "count": 1, "self": 3.7658200860582838, "children": { "TrainerController._reset_env": { "total": 10.221566528999972, "count": 1, "self": 10.221566528999972 }, "TrainerController.advance": { "total": 2110.8687937959417, "count": 232302, "self": 3.9119652659719577, "children": { "env_step": { "total": 1661.0563144039554, "count": 232302, "self": 1394.0096496128915, "children": { "SubprocessEnvManager._take_step": { "total": 264.6021578470515, "count": 232302, "self": 13.66832179706114, "children": { "TorchPolicy.evaluate": { "total": 250.93383604999036, "count": 223024, "self": 63.34719635904014, "children": { "TorchPolicy.sample_actions": { "total": 187.58663969095022, "count": 223024, "self": 187.58663969095022 } } } } }, "workers": { "total": 2.44450694401246, "count": 232302, "self": 0.0, "children": { "worker_root": { "total": 2117.183505395948, "count": 232302, "is_parallel": true, "self": 970.1867642459383, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005973197999992408, "count": 1, "is_parallel": true, "self": 0.0003451019999829441, "children": { "_process_rank_one_or_two_observation": { "total": 0.005628096000009464, "count": 2, "is_parallel": true, "self": 0.005628096000009464 } } }, "UnityEnvironment.step": { "total": 0.033390313000040805, "count": 1, "is_parallel": true, "self": 0.0003062030000364757, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017908899997109984, "count": 1, "is_parallel": true, "self": 0.00017908899997109984 }, "communicator.exchange": { "total": 0.032198567000023104, "count": 1, "is_parallel": true, "self": 0.032198567000023104 }, "steps_from_proto": { "total": 0.000706454000010126, "count": 1, "is_parallel": true, "self": 0.00024187399992570136, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004645800000844247, "count": 2, "is_parallel": true, "self": 0.0004645800000844247 } } } } } } }, "UnityEnvironment.step": { "total": 1146.9967411500097, "count": 232301, "is_parallel": true, "self": 33.162797501857995, "children": { "UnityEnvironment._generate_step_input": { "total": 72.02616308098362, "count": 232301, "is_parallel": true, "self": 72.02616308098362 }, "communicator.exchange": { "total": 954.3269638700891, "count": 232301, "is_parallel": true, "self": 954.3269638700891 }, "steps_from_proto": { "total": 87.48081669707904, "count": 232301, "is_parallel": true, "self": 35.66905082307346, "children": { "_process_rank_one_or_two_observation": { "total": 51.81176587400557, "count": 464602, "is_parallel": true, "self": 51.81176587400557 } } } } } } } } } } }, "trainer_advance": { "total": 445.9005141260141, "count": 232302, "self": 5.970040178974216, "children": { "process_trajectory": { "total": 140.35670070004, "count": 232302, "self": 139.2322953900396, "children": { "RLTrainer._checkpoint": { "total": 1.124405310000384, "count": 10, "self": 1.124405310000384 } } }, "_update_policy": { "total": 299.5737732469999, "count": 97, "self": 246.70307008600543, "children": { "TorchPPOOptimizer.update": { "total": 52.87070316099448, "count": 2910, "self": 52.87070316099448 } } } } } } }, "trainer_threads": { "total": 8.930001058615744e-07, "count": 1, "self": 8.930001058615744e-07 }, "TrainerController._save_models": { "total": 0.111391765999997, "count": 1, "self": 0.0020617179998225765, "children": { "RLTrainer._checkpoint": { "total": 0.10933004800017443, "count": 1, "self": 0.10933004800017443 } } } } } } }