{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4054855108261108, "min": 1.4054855108261108, "max": 1.4268125295639038, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70219.4609375, "min": 69056.953125, "max": 77260.765625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 78.23174603174603, "min": 74.54229607250755, "max": 412.4710743801653, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49286.0, "min": 49211.0, "max": 50003.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999940.0, "min": 49609.0, "max": 1999940.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999940.0, "min": 49609.0, "max": 1999940.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.440237522125244, "min": -0.00735867815092206, "max": 2.5000059604644775, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1539.7899169921875, "min": -0.8830413818359375, "max": 1599.18896484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7474839412467036, "min": 1.6690279394388199, "max": 3.9395381423704667, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2364.66236692667, "min": 200.2833527326584, "max": 2565.9841072559357, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7474839412467036, "min": 1.6690279394388199, "max": 3.9395381423704667, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2364.66236692667, "min": 200.2833527326584, "max": 2565.9841072559357, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014750066015565408, "min": 0.01365545433784266, "max": 0.019819401680595344, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04425019804669622, "min": 0.029551393520766092, "max": 0.05945820504178603, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05710335361460845, "min": 0.022222595910231274, "max": 0.058821321609947415, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17131006084382536, "min": 0.04444519182046255, "max": 0.17646396482984225, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.421348859583331e-06, "min": 3.421348859583331e-06, "max": 0.00029523165158945, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0264046578749992e-05, "min": 1.0264046578749992e-05, "max": 0.0008436894187701996, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114041666666669, "min": 0.10114041666666669, "max": 0.19841054999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034212500000001, "min": 0.20741145, "max": 0.5812298, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.690679166666662e-05, "min": 6.690679166666662e-05, "max": 0.004920686445000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020072037499999985, "min": 0.00020072037499999985, "max": 0.014063367019999998, "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": "1678200832", "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": "1.22.4", "end_time_seconds": "1678203185" }, "total": 2352.6687837649997, "count": 1, "self": 0.4627426249999189, "children": { "run_training.setup": { "total": 0.11310599000012189, "count": 1, "self": 0.11310599000012189 }, "TrainerController.start_learning": { "total": 2352.09293515, "count": 1, "self": 4.219656480111553, "children": { "TrainerController._reset_env": { "total": 8.542699095999978, "count": 1, "self": 8.542699095999978 }, "TrainerController.advance": { "total": 2339.2237586238884, "count": 232875, "self": 4.61831236998114, "children": { "env_step": { "total": 1810.1038579819963, "count": 232875, "self": 1517.12347182095, "children": { "SubprocessEnvManager._take_step": { "total": 290.2072387049782, "count": 232875, "self": 15.78435705594893, "children": { "TorchPolicy.evaluate": { "total": 274.42288164902925, "count": 222935, "self": 68.52559732904615, "children": { "TorchPolicy.sample_actions": { "total": 205.8972843199831, "count": 222935, "self": 205.8972843199831 } } } } }, "workers": { "total": 2.7731474560680454, "count": 232875, "self": 0.0, "children": { "worker_root": { "total": 2343.5427258280174, "count": 232875, "is_parallel": true, "self": 1112.6600580230179, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008709339999768417, "count": 1, "is_parallel": true, "self": 0.00032179799995901703, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005491360000178247, "count": 2, "is_parallel": true, "self": 0.0005491360000178247 } } }, "UnityEnvironment.step": { "total": 0.05629420500008564, "count": 1, "is_parallel": true, "self": 0.00031629800014343346, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018897199993261893, "count": 1, "is_parallel": true, "self": 0.00018897199993261893 }, "communicator.exchange": { "total": 0.05508643600001051, "count": 1, "is_parallel": true, "self": 0.05508643600001051 }, "steps_from_proto": { "total": 0.0007024989999990794, "count": 1, "is_parallel": true, "self": 0.00023543899987998884, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046706000011909055, "count": 2, "is_parallel": true, "self": 0.00046706000011909055 } } } } } } }, "UnityEnvironment.step": { "total": 1230.8826678049995, "count": 232874, "is_parallel": true, "self": 37.741238632253044, "children": { "UnityEnvironment._generate_step_input": { "total": 76.82494059183091, "count": 232874, "is_parallel": true, "self": 76.82494059183091 }, "communicator.exchange": { "total": 1026.2905578918856, "count": 232874, "is_parallel": true, "self": 1026.2905578918856 }, "steps_from_proto": { "total": 90.02593068903002, "count": 232874, "is_parallel": true, "self": 36.46953687183395, "children": { "_process_rank_one_or_two_observation": { "total": 53.55639381719607, "count": 465748, "is_parallel": true, "self": 53.55639381719607 } } } } } } } } } } }, "trainer_advance": { "total": 524.501588271911, "count": 232875, "self": 6.39642516984145, "children": { "process_trajectory": { "total": 167.29479995706902, "count": 232875, "self": 166.14709625406954, "children": { "RLTrainer._checkpoint": { "total": 1.147703702999479, "count": 10, "self": 1.147703702999479 } } }, "_update_policy": { "total": 350.81036314500057, "count": 97, "self": 293.65715180101097, "children": { "TorchPPOOptimizer.update": { "total": 57.1532113439896, "count": 2910, "self": 57.1532113439896 } } } } } } }, "trainer_threads": { "total": 7.509997885790654e-07, "count": 1, "self": 7.509997885790654e-07 }, "TrainerController._save_models": { "total": 0.10682019900013984, "count": 1, "self": 0.0019617530001596606, "children": { "RLTrainer._checkpoint": { "total": 0.10485844599998018, "count": 1, "self": 0.10485844599998018 } } } } } } }