{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4015074968338013, "min": 1.4015074968338013, "max": 1.4303128719329834, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72087.9375, "min": 68552.0234375, "max": 76717.53125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.48990825688074, "min": 79.64354838709677, "max": 424.7542372881356, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49317.0, "min": 49258.0, "max": 50121.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999989.0, "min": 49637.0, "max": 1999989.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999989.0, "min": 49637.0, "max": 1999989.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.425534725189209, "min": 0.04629138484597206, "max": 2.4626967906951904, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1321.9163818359375, "min": 5.4160919189453125, "max": 1521.162109375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7095283443774654, "min": 1.766136981228478, "max": 4.068033982371019, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2021.6929476857185, "min": 206.63802680373192, "max": 2453.0244913697243, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7095283443774654, "min": 1.766136981228478, "max": 4.068033982371019, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2021.6929476857185, "min": 206.63802680373192, "max": 2453.0244913697243, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01651306366159891, "min": 0.0133181548594924, "max": 0.020330355091330903, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04953919098479673, "min": 0.0266363097189848, "max": 0.05898549433331937, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05001063971883721, "min": 0.022542660931746165, "max": 0.05774296981592973, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15003191915651162, "min": 0.04508532186349233, "max": 0.16778697284559407, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7740987419999995e-06, "min": 3.7740987419999995e-06, "max": 0.00029534992655002494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1322296225999999e-05, "min": 1.1322296225999999e-05, "max": 0.0008441559186146998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10125800000000001, "min": 0.10125800000000001, "max": 0.198449975, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30377400000000004, "min": 0.20766825000000005, "max": 0.5813853, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.27742e-05, "min": 7.27742e-05, "max": 0.004922653752499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021832260000000003, "min": 0.00021832260000000003, "max": 0.014071126469999997, "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": "1692143830", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=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": "1692146290" }, "total": 2459.739815831, "count": 1, "self": 0.4365918140006215, "children": { "run_training.setup": { "total": 0.06263775200000055, "count": 1, "self": 0.06263775200000055 }, "TrainerController.start_learning": { "total": 2459.240586265, "count": 1, "self": 4.435491765908409, "children": { "TrainerController._reset_env": { "total": 4.952630305000071, "count": 1, "self": 4.952630305000071 }, "TrainerController.advance": { "total": 2449.7270869410913, "count": 232773, "self": 4.6139049081457415, "children": { "env_step": { "total": 1879.9590173390027, "count": 232773, "self": 1583.9489741898783, "children": { "SubprocessEnvManager._take_step": { "total": 293.1076972500613, "count": 232773, "self": 16.862752069009616, "children": { "TorchPolicy.evaluate": { "total": 276.24494518105166, "count": 223119, "self": 276.24494518105166 } } }, "workers": { "total": 2.9023458990629933, "count": 232773, "self": 0.0, "children": { "worker_root": { "total": 2451.754805790912, "count": 232773, "is_parallel": true, "self": 1162.7842349488553, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001138545999992857, "count": 1, "is_parallel": true, "self": 0.00031538700011424226, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008231589998786148, "count": 2, "is_parallel": true, "self": 0.0008231589998786148 } } }, "UnityEnvironment.step": { "total": 0.029646680999917407, "count": 1, "is_parallel": true, "self": 0.0003491039999516943, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022403200000553625, "count": 1, "is_parallel": true, "self": 0.00022403200000553625 }, "communicator.exchange": { "total": 0.02831388100003096, "count": 1, "is_parallel": true, "self": 0.02831388100003096 }, "steps_from_proto": { "total": 0.0007596639999292165, "count": 1, "is_parallel": true, "self": 0.00020895000000109576, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005507139999281208, "count": 2, "is_parallel": true, "self": 0.0005507139999281208 } } } } } } }, "UnityEnvironment.step": { "total": 1288.9705708420568, "count": 232772, "is_parallel": true, "self": 39.69358176103265, "children": { "UnityEnvironment._generate_step_input": { "total": 79.71332946704558, "count": 232772, "is_parallel": true, "self": 79.71332946704558 }, "communicator.exchange": { "total": 1071.4796261198821, "count": 232772, "is_parallel": true, "self": 1071.4796261198821 }, "steps_from_proto": { "total": 98.08403349409639, "count": 232772, "is_parallel": true, "self": 34.440469777200065, "children": { "_process_rank_one_or_two_observation": { "total": 63.643563716896324, "count": 465544, "is_parallel": true, "self": 63.643563716896324 } } } } } } } } } } }, "trainer_advance": { "total": 565.1541646939427, "count": 232773, "self": 6.8913737739092085, "children": { "process_trajectory": { "total": 143.59203550703342, "count": 232773, "self": 142.13532717203339, "children": { "RLTrainer._checkpoint": { "total": 1.4567083350000303, "count": 10, "self": 1.4567083350000303 } } }, "_update_policy": { "total": 414.67075541300005, "count": 97, "self": 352.93165697999325, "children": { "TorchPPOOptimizer.update": { "total": 61.7390984330068, "count": 2910, "self": 61.7390984330068 } } } } } } }, "trainer_threads": { "total": 9.54999904934084e-07, "count": 1, "self": 9.54999904934084e-07 }, "TrainerController._save_models": { "total": 0.12537629799999195, "count": 1, "self": 0.0020009469999422436, "children": { "RLTrainer._checkpoint": { "total": 0.1233753510000497, "count": 1, "self": 0.1233753510000497 } } } } } } }