{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4236615896224976, "min": 1.4191259145736694, "max": 1.4236615896224976, "count": 4 }, "Huggy.Policy.Entropy.sum": { "value": 70230.6484375, "min": 69556.09375, "max": 77729.78125, "count": 4 }, "Huggy.Environment.EpisodeLength.mean": { "value": 260.76439790575915, "min": 260.76439790575915, "max": 428.29059829059827, "count": 4 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49806.0, "min": 49685.0, "max": 50110.0, "count": 4 }, "Huggy.Step.mean": { "value": 199955.0, "min": 49477.0, "max": 199955.0, "count": 4 }, "Huggy.Step.sum": { "value": 199955.0, "min": 49477.0, "max": 199955.0, "count": 4 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8297739624977112, "min": 0.0997922271490097, "max": 0.8297739624977112, "count": 4 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 158.48683166503906, "min": 11.575898170471191, "max": 158.48683166503906, "count": 4 }, "Huggy.Environment.CumulativeReward.mean": { "value": 2.8454887217876172, "min": 1.8527788591795955, "max": 2.930535776540637, "count": 4 }, "Huggy.Environment.CumulativeReward.sum": { "value": 543.4883458614349, "min": 214.92234766483307, "max": 543.4883458614349, "count": 4 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 2.8454887217876172, "min": 1.8527788591795955, "max": 2.930535776540637, "count": 4 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 543.4883458614349, "min": 214.92234766483307, "max": 543.4883458614349, "count": 4 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016920511667073396, "min": 0.014842604078714633, "max": 0.019588373541773764, "count": 4 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03384102333414679, "min": 0.0305133039636227, "max": 0.044527812236143896, "count": 4 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.02442325862745444, "min": 0.022551890431592864, "max": 0.02938448969895641, "count": 4 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.04884651725490888, "min": 0.04510378086318573, "max": 0.07308483483890692, "count": 4 }, "Huggy.Policy.LearningRate.mean": { "value": 6.067303432113636e-05, "min": 6.067303432113636e-05, "max": 0.0002580436503490909, "count": 4 }, "Huggy.Policy.LearningRate.sum": { "value": 0.00012134606864227272, "min": 0.00012134606864227272, "max": 0.0005160873006981818, "count": 4 }, "Huggy.Policy.Epsilon.mean": { "value": 0.12022431818181822, "min": 0.12022431818181822, "max": 0.1860145454545454, "count": 4 }, "Huggy.Policy.Epsilon.sum": { "value": 0.24044863636363645, "min": 0.24044863636363645, "max": 0.4312304545454545, "count": 4 }, "Huggy.Policy.Beta.mean": { "value": 0.001019193477272727, "min": 0.001019193477272727, "max": 0.004302125818181819, "count": 4 }, "Huggy.Policy.Beta.sum": { "value": 0.002038386954545454, "min": 0.002038386954545454, "max": 0.008604251636363637, "count": 4 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715735287", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715735555" }, "total": 268.879832225, "count": 1, "self": 0.4394512810000606, "children": { "run_training.setup": { "total": 0.05369692399995074, "count": 1, "self": 0.05369692399995074 }, "TrainerController.start_learning": { "total": 268.38668401999996, "count": 1, "self": 0.4622347120042605, "children": { "TrainerController._reset_env": { "total": 2.8372498370000585, "count": 1, "self": 2.8372498370000585 }, "TrainerController.advance": { "total": 264.97110062599575, "count": 25113, "self": 0.5128743459763427, "children": { "env_step": { "total": 216.15132453400508, "count": 25113, "self": 177.12308603800648, "children": { "SubprocessEnvManager._take_step": { "total": 38.7055860240057, "count": 25113, "self": 2.144276944016383, "children": { "TorchPolicy.evaluate": { "total": 36.561309079989314, "count": 24748, "self": 36.561309079989314 } } }, "workers": { "total": 0.32265247199291025, "count": 25113, "self": 0.0, "children": { "worker_root": { "total": 267.550054148006, "count": 25113, "is_parallel": true, "self": 126.23448353400624, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010028639999291045, "count": 1, "is_parallel": true, "self": 0.00029415200003768405, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007087119998914204, "count": 2, "is_parallel": true, "self": 0.0007087119998914204 } } }, "UnityEnvironment.step": { "total": 0.03442820899999788, "count": 1, "is_parallel": true, "self": 0.00039440000011836673, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026892099992892327, "count": 1, "is_parallel": true, "self": 0.00026892099992892327 }, "communicator.exchange": { "total": 0.0329461320000064, "count": 1, "is_parallel": true, "self": 0.0329461320000064 }, "steps_from_proto": { "total": 0.0008187559999441874, "count": 1, "is_parallel": true, "self": 0.00020742199990309018, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006113340000410972, "count": 2, "is_parallel": true, "self": 0.0006113340000410972 } } } } } } }, "UnityEnvironment.step": { "total": 141.31557061399974, "count": 25112, "is_parallel": true, "self": 4.343631816963921, "children": { "UnityEnvironment._generate_step_input": { "total": 9.436099309012548, "count": 25112, "is_parallel": true, "self": 9.436099309012548 }, "communicator.exchange": { "total": 117.37866110200514, "count": 25112, "is_parallel": true, "self": 117.37866110200514 }, "steps_from_proto": { "total": 10.157178386018131, "count": 25112, "is_parallel": true, "self": 3.7688556360187704, "children": { "_process_rank_one_or_two_observation": { "total": 6.388322749999361, "count": 50224, "is_parallel": true, "self": 6.388322749999361 } } } } } } } } } } }, "trainer_advance": { "total": 48.30690174601432, "count": 25113, "self": 0.7430710000228373, "children": { "process_trajectory": { "total": 12.893158888991366, "count": 25113, "self": 12.69709905599143, "children": { "RLTrainer._checkpoint": { "total": 0.19605983299993568, "count": 1, "self": 0.19605983299993568 } } }, "_update_policy": { "total": 34.670671857000116, "count": 10, "self": 27.31808880700146, "children": { "TorchPPOOptimizer.update": { "total": 7.352583049998657, "count": 300, "self": 7.352583049998657 } } } } } } }, "trainer_threads": { "total": 1.0289999181622989e-06, "count": 1, "self": 1.0289999181622989e-06 }, "TrainerController._save_models": { "total": 0.11609781599997859, "count": 1, "self": 0.002180442999929255, "children": { "RLTrainer._checkpoint": { "total": 0.11391737300004934, "count": 1, "self": 0.11391737300004934 } } } } } } }